chore(zk): add a shortint wrapper for the CompactPkeCrs

This allows to detect unused dispatch enums

.cargo/config.toml

@@ -1,2 +1,6 @@
 [alias]
 xtask = "run --manifest-path ./tasks/Cargo.toml --"
+
+# Accessed by wasm-bindgen when testing for the wasm target
+[target.wasm32-unknown-unknown]
+runner = 'wasm-bindgen-test-runner'

.github/workflows/aws_tfhe_backward_compat_tests.yml

@@ -26,7 +26,7 @@ jobs:
     steps:
       - name: Start instance
         id: start-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: start
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -44,17 +44,13 @@ jobs:
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     steps:
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           persist-credentials: 'false'
           token: ${{ secrets.FHE_ACTIONS_TOKEN }}
 
-      - name: Set up home
-        run: |
-          echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
-
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: stable
 
@@ -76,7 +72,7 @@ jobs:
           echo "branch=${BRANCH}" >> "${GITHUB_OUTPUT}"
 
       - name: Clone test data
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           persist-credentials: 'false'
           repository: zama-ai/tfhe-backward-compat-data
@@ -91,7 +87,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Backward compatibility tests finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
@@ -104,7 +100,7 @@ jobs:
     steps:
       - name: Stop instance
         id: stop-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: stop
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -115,7 +111,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Instance teardown (backward-compat-tests) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/aws_tfhe_fast_tests.yml

@@ -51,24 +51,26 @@ jobs:
       any_file_changed: ${{ env.IS_PULL_REQUEST == 'false' || steps.aggregated-changes.outputs.any_changed }}
     steps:
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
+          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
 
       - name: Check for file changes
         id: changed-files
-        uses: tj-actions/changed-files@48d8f15b2aaa3d255ca5af3eba4870f807ce6b3c
+        uses: tj-actions/changed-files@bab30c2299617f6615ec02a68b9a40d10bd21366
         with:
           since_last_remote_commit: true
           files_yaml: |
             dependencies:
               - tfhe/Cargo.toml
-              - concrete-csprng/**
+              - tfhe-csprng/**
+              - tfhe-fft/**
               - tfhe-zk-pok/**
               - utils/tfhe-versionable/**
               - utils/tfhe-versionable-derive/**
             csprng:
-              - concrete-csprng/**
+              - tfhe-csprng/**
             zk_pok:
               - tfhe-zk-pok/**
             versionable:
@@ -131,7 +133,7 @@ jobs:
     steps:
       - name: Start instance
         id: start-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: start
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -151,24 +153,20 @@ jobs:
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     steps:
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           persist-credentials: 'false'
           token: ${{ secrets.FHE_ACTIONS_TOKEN }}
 
-      - name: Set up home
-        run: |
-          echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
-
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: stable
 
-      - name: Run concrete-csprng tests
+      - name: Run tfhe-csprng tests
         if: needs.should-run.outputs.csprng_test == 'true'
         run: |
-          make test_concrete_csprng
+          make test_tfhe_csprng
 
       - name: Run tfhe-zk-pok tests
         if: needs.should-run.outputs.zk_pok_test == 'true'
@@ -195,10 +193,37 @@ jobs:
         run: |
           make test_user_doc
 
+      - name: Get Node version
+        run: |
+          echo "NODE_VERSION=$(make node_version)" >> "${GITHUB_ENV}"
+
+      - name: Node cache restoration
+        id: node-cache
+        uses: actions/cache/restore@1bd1e32a3bdc45362d1e726936510720a7c30a57 #v4.2.0
+        with:
+          path: |
+            ~/.nvm
+            ~/.npm
+          key: node-${{ env.NODE_VERSION }}
+
+      - name: Install Node
+        if: steps.node-cache.outputs.cache-hit != 'true'
+        run: |
+          make install_node
+
+      - name: Node cache save
+        uses: actions/cache/save@1bd1e32a3bdc45362d1e726936510720a7c30a57 #v4.2.0
+        if: steps.node-cache.outputs.cache-hit != 'true'
+        with:
+          path: |
+            ~/.nvm
+            ~/.npm
+          key: node-${{ env.NODE_VERSION }}
+
       - name: Run js on wasm API tests
         if: needs.should-run.outputs.wasm_test == 'true'
         run: |
-          make test_nodejs_wasm_api_in_docker
+          make test_nodejs_wasm_api_ci
 
       - name: Gen Keys if required
         if: needs.should-run.outputs.shortint_test == 'true' ||
@@ -221,14 +246,18 @@ jobs:
         run: |
           make test_high_level_api
 
-      - name: Run safe deserialization tests
+      - name: Run safe serialization tests
         run: |
-          make test_safe_deserialization
+          make test_safe_serialization
+
+      - name: Run zk tests
+        run: |
+          make test_zk
 
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Fast AWS tests finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
@@ -241,7 +270,7 @@ jobs:
     steps:
       - name: Stop instance
         id: stop-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: stop
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -252,7 +281,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Instance teardown (fast-tests) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/aws_tfhe_integer_tests.yml

@@ -39,24 +39,27 @@ jobs:
         steps.changed-files.outputs.integer_any_changed }}
     steps:
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
+          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
           persist-credentials: "false"
 
       - name: Check for file changes
         id: changed-files
-        uses: tj-actions/changed-files@48d8f15b2aaa3d255ca5af3eba4870f807ce6b3c
+        uses: tj-actions/changed-files@bab30c2299617f6615ec02a68b9a40d10bd21366
         with:
           since_last_remote_commit: true
           files_yaml: |
             integer:
               - tfhe/Cargo.toml
-              - concrete-csprng/**
+              - tfhe-csprng/**
+              - tfhe-fft/**
               - tfhe-zk-pok/**
               - tfhe/src/core_crypto/**
               - tfhe/src/shortint/**
               - tfhe/src/integer/**
+              - .github/workflows/aws_tfhe_integer_tests.yml
 
   setup-instance:
     name: Setup instance (unsigned-integer-tests)
@@ -72,7 +75,7 @@ jobs:
     steps:
       - name: Start instance
         id: start-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: start
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -90,17 +93,13 @@ jobs:
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     steps:
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           persist-credentials: "false"
           token: ${{ secrets.FHE_ACTIONS_TOKEN }}
 
-      - name: Set up home
-        run: |
-          echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
-
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: stable
 
@@ -128,7 +127,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Unsigned Integer tests finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
@@ -141,7 +140,7 @@ jobs:
     steps:
       - name: Stop instance
         id: stop-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: stop
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -152,7 +151,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Instance teardown (unsigned-integer-tests) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/aws_tfhe_signed_integer_tests.yml

@@ -39,24 +39,27 @@ jobs:
         steps.changed-files.outputs.integer_any_changed }}
     steps:
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
+          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
           persist-credentials: "false"
 
       - name: Check for file changes
         id: changed-files
-        uses: tj-actions/changed-files@48d8f15b2aaa3d255ca5af3eba4870f807ce6b3c
+        uses: tj-actions/changed-files@bab30c2299617f6615ec02a68b9a40d10bd21366
         with:
           since_last_remote_commit: true
           files_yaml: |
             integer:
               - tfhe/Cargo.toml
-              - concrete-csprng/**
+              - tfhe-csprng/**
+              - tfhe-fft/**
               - tfhe-zk-pok/**
               - tfhe/src/core_crypto/**
               - tfhe/src/shortint/**
               - tfhe/src/integer/**
+              - .github/workflows/aws_tfhe_signed_integer_tests.yml
 
   setup-instance:
     name: Setup instance (unsigned-integer-tests)
@@ -72,7 +75,7 @@ jobs:
     steps:
       - name: Start instance
         id: start-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: start
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -90,17 +93,13 @@ jobs:
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     steps:
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           persist-credentials: "false"
           token: ${{ secrets.FHE_ACTIONS_TOKEN }}
 
-      - name: Set up home
-        run: |
-          echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
-
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: stable
 
@@ -132,7 +131,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Signed Integer tests finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
@@ -145,7 +144,7 @@ jobs:
     steps:
       - name: Stop instance
         id: stop-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: stop
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -156,7 +155,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Instance teardown (signed-integer-tests) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/aws_tfhe_tests.yml

@@ -40,6 +40,9 @@ jobs:
       shortint_test: ${{ env.IS_PULL_REQUEST == 'false' ||
         steps.changed-files.outputs.shortint_any_changed ||
         steps.changed-files.outputs.dependencies_any_changed }}
+      strings_test: ${{ env.IS_PULL_REQUEST == 'false' ||
+        steps.changed-files.outputs.strings_any_changed ||
+        steps.changed-files.outputs.dependencies_any_changed }}
       high_level_api_test: ${{ env.IS_PULL_REQUEST == 'false' ||
         steps.changed-files.outputs.high_level_api_any_changed ||
         steps.changed-files.outputs.dependencies_any_changed }}
@@ -57,22 +60,24 @@ jobs:
       any_file_changed: ${{ env.IS_PULL_REQUEST == 'false' || steps.aggregated-changes.outputs.any_changed }}
     steps:
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
+          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
 
       - name: Check for file changes
         id: changed-files
-        uses: tj-actions/changed-files@48d8f15b2aaa3d255ca5af3eba4870f807ce6b3c
+        uses: tj-actions/changed-files@bab30c2299617f6615ec02a68b9a40d10bd21366
         with:
           since_last_remote_commit: true
           files_yaml: |
             dependencies:
               - tfhe/Cargo.toml
-              - concrete-csprng/**
+              - tfhe-csprng/**
+              - tfhe-fft/**
               - tfhe-zk-pok/**
             csprng:
-              - concrete-csprng/**
+              - tfhe-csprng/**
             zk_pok:
               - tfhe-zk-pok/**
             core_crypto:
@@ -83,6 +88,11 @@ jobs:
             shortint:
               - tfhe/src/core_crypto/**
               - tfhe/src/shortint/**
+            strings:
+              - tfhe/src/core_crypto/**
+              - tfhe/src/shortint/**
+              - tfhe/src/integer/**
+              - tfhe/src/strings/**
             high_level_api:
               - tfhe/src/**
               - '!tfhe/src/c_api/**'
@@ -112,6 +122,7 @@ jobs:
           steps.changed-files.outputs.core_crypto_any_changed == 'true' ||
           steps.changed-files.outputs.boolean_any_changed == 'true' ||
           steps.changed-files.outputs.shortint_any_changed == 'true' ||
+          steps.changed-files.outputs.strings_any_changed == 'true' ||
           steps.changed-files.outputs.high_level_api_any_changed == 'true' ||
           steps.changed-files.outputs.c_api_any_changed == 'true' ||
           steps.changed-files.outputs.examples_any_changed == 'true' ||
@@ -131,7 +142,7 @@ jobs:
     steps:
       - name: Start instance
         id: start-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: start
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -151,24 +162,20 @@ jobs:
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     steps:
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           persist-credentials: 'false'
           token: ${{ secrets.FHE_ACTIONS_TOKEN }}
 
-      - name: Set up home
-        run: |
-          echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
-
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: stable
 
-      - name: Run concrete-csprng tests
+      - name: Run tfhe-csprng tests
         if: needs.should-run.outputs.csprng_test == 'true'
         run: |
-          make test_concrete_csprng
+          make test_tfhe_csprng
 
       - name: Run tfhe-zk-pok tests
         if: needs.should-run.outputs.zk_pok_test == 'true'
@@ -205,6 +212,11 @@ jobs:
         run: |
           BIG_TESTS_INSTANCE=TRUE make test_shortint_ci
 
+      - name: Run strings tests
+        if: needs.should-run.outputs.strings_test == 'true'
+        run: |
+          BIG_TESTS_INSTANCE=TRUE make test_strings
+
       - name: Run high-level API tests
         if: needs.should-run.outputs.high_level_api_test == 'true'
         run: |
@@ -225,7 +237,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "CPU tests finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
@@ -238,7 +250,7 @@ jobs:
     steps:
       - name: Stop instance
         id: stop-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: stop
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -249,7 +261,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Instance teardown (cpu-tests) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/aws_tfhe_wasm_tests.yml

@@ -27,7 +27,7 @@ jobs:
     steps:
       - name: Start instance
         id: start-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: start
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -45,23 +45,45 @@ jobs:
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     steps:
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           persist-credentials: 'false'
           token: ${{ secrets.FHE_ACTIONS_TOKEN }}
 
-      - name: Set up home
-        run: |
-          echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
-
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: stable
 
-      - name: Install web resources
+      - name: Get Node version
+        run: |
+          echo "NODE_VERSION=$(make node_version)" >> "${GITHUB_ENV}"
+
+      - name: Node cache restoration
+        id: node-cache
+        uses: actions/cache/restore@1bd1e32a3bdc45362d1e726936510720a7c30a57 #v4.2.0
+        with:
+          path: |
+            ~/.nvm
+            ~/.npm
+          key: node-${{ env.NODE_VERSION }}
+
+      - name: Install Node
+        if: steps.node-cache.outputs.cache-hit != 'true'
         run: |
           make install_node
+
+      - name: Node cache save
+        uses: actions/cache/save@1bd1e32a3bdc45362d1e726936510720a7c30a57 #v4.2.0
+        if: steps.node-cache.outputs.cache-hit != 'true'
+        with:
+          path: |
+            ~/.nvm
+            ~/.npm
+          key: node-${{ env.NODE_VERSION }}
+
+      - name: Install web resources
+        run: |
           make install_chrome_browser
           make install_chrome_web_driver
 
@@ -71,16 +93,20 @@ jobs:
 
       - name: Run js on wasm API tests
         run: |
-          make test_nodejs_wasm_api_in_docker
+          make test_nodejs_wasm_api_ci
 
       - name: Run parallel wasm tests
         run: |
           make test_web_js_api_parallel_chrome_ci
 
+      - name: Run x86_64/wasm zk compatibility tests
+        run: |
+          make test_zk_wasm_x86_compat_ci
+
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "WASM tests finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
@@ -93,7 +119,7 @@ jobs:
     steps:
       - name: Stop instance
         id: stop-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: stop
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -104,7 +130,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Instance teardown (wasm-tests) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/benchmark_boolean.yml

@@ -29,7 +29,7 @@ jobs:
     steps:
       - name: Start instance
         id: start-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: start
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -48,7 +48,7 @@ jobs:
     continue-on-error: true
     steps:
       - name: Checkout tfhe-rs repo with tags
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
           token: ${{ secrets.FHE_ACTIONS_TOKEN }}
@@ -61,13 +61,8 @@ jobs:
             echo "COMMIT_HASH=$(git describe --tags --dirty)";
           } >> "${GITHUB_ENV}"
 
-      - name: Set up home
-        # "Install rust" step require root user to have a HOME directory which is not set.
-        run: |
-          echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
-
       - name: Install rust
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: nightly
 
@@ -85,8 +80,7 @@ jobs:
           --commit-date "${{ env.COMMIT_DATE }}" \
           --bench-date "${{ env.BENCH_DATE }}" \
           --walk-subdirs \
-          --name-suffix avx512 \
-          --throughput
+          --name-suffix avx512
 
       - name: Measure key sizes
         run: |
@@ -95,17 +89,17 @@ jobs:
       - name: Parse key sizes results
         run: |
           python3 ./ci/benchmark_parser.py tfhe/boolean_key_sizes.csv ${{ env.RESULTS_FILENAME }} \
-          --key-sizes \
+          --object-sizes \
           --append-results
 
       - name: Upload parsed results artifact
-        uses: actions/upload-artifact@50769540e7f4bd5e21e526ee35c689e35e0d6874
+        uses: actions/upload-artifact@b4b15b8c7c6ac21ea08fcf65892d2ee8f75cf882
         with:
           name: ${{ github.sha }}_boolean
           path: ${{ env.RESULTS_FILENAME }}
 
       - name: Checkout Slab repo
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           repository: zama-ai/slab
           path: slab
@@ -120,7 +114,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Boolean benchmarks finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
@@ -133,7 +127,7 @@ jobs:
     steps:
       - name: Stop instance
         id: stop-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: stop
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -144,7 +138,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Instance teardown (boolean-benchmarks) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/benchmark_core_crypto.yml

@@ -26,7 +26,7 @@ jobs:
     steps:
       - name: Start instance
         id: start-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: start
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -44,7 +44,7 @@ jobs:
       cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
     steps:
       - name: Checkout tfhe-rs repo with tags
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
           token: ${{ secrets.FHE_ACTIONS_TOKEN }}
@@ -57,13 +57,8 @@ jobs:
             echo "COMMIT_HASH=$(git describe --tags --dirty)";
           } >> "${GITHUB_ENV}"
 
-      - name: Set up home
-        # "Install rust" step require root user to have a HOME directory which is not set.
-        run: |
-          echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
-
       - name: Install rust
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: nightly
 
@@ -83,17 +78,16 @@ jobs:
           --commit-date "${{ env.COMMIT_DATE }}" \
           --bench-date "${{ env.BENCH_DATE }}" \
           --name-suffix avx512 \
-          --walk-subdirs \
-          --throughput
+          --walk-subdirs
 
       - name: Upload parsed results artifact
-        uses: actions/upload-artifact@50769540e7f4bd5e21e526ee35c689e35e0d6874
+        uses: actions/upload-artifact@b4b15b8c7c6ac21ea08fcf65892d2ee8f75cf882
         with:
           name: ${{ github.sha }}_core_crypto
           path: ${{ env.RESULTS_FILENAME }}
 
       - name: Checkout Slab repo
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           repository: zama-ai/slab
           path: slab
@@ -108,7 +102,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "PBS benchmarks finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
@@ -121,7 +115,7 @@ jobs:
     steps:
       - name: Stop instance
         id: stop-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: stop
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -132,7 +126,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Instance teardown (core-crypto-benchmarks) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/benchmark_erc20.yml

@@ -0,0 +1,141 @@
+# Run all ERC20 benchmarks on an AWS instance and return parsed results to Slab CI bot.
+name: ERC20 benchmarks
+
+on:
+  workflow_dispatch:
+  schedule:
+    # Weekly benchmarks will be triggered each Saturday at 5a.m.
+    - cron: '0 5 * * 6'
+
+env:
+  CARGO_TERM_COLOR: always
+  RESULTS_FILENAME: parsed_benchmark_results_${{ github.sha }}.json
+  ACTION_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
+  RUST_BACKTRACE: "full"
+  RUST_MIN_STACK: "8388608"
+  SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
+  SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
+  SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
+  SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+
+jobs:
+  setup-instance:
+    name: Setup instance (erc20-benchmarks)
+    runs-on: ubuntu-latest
+    if: github.event_name == 'workflow_dispatch' ||
+      (github.event_name == 'schedule' && github.repository == 'zama-ai/tfhe-rs')
+    outputs:
+      runner-name: ${{ steps.start-instance.outputs.label }}
+    steps:
+      - name: Start instance
+        id: start-instance
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
+        with:
+          mode: start
+          github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
+          slab-url: ${{ secrets.SLAB_BASE_URL }}
+          job-secret: ${{ secrets.JOB_SECRET }}
+          backend: aws
+          profile: bench
+
+  erc20-benchmarks:
+    name: Execute ERC20 benchmarks
+    needs: setup-instance
+    runs-on: ${{ needs.setup-instance.outputs.runner-name }}
+    concurrency:
+      group: ${{ github.workflow }}_${{ github.ref }}
+      cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
+    continue-on-error: true
+    timeout-minutes: 720  # 12 hours
+    steps:
+      - name: Checkout tfhe-rs repo with tags
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          fetch-depth: 0
+          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
+
+      - name: Get benchmark details
+        run: |
+          {
+            echo "BENCH_DATE=$(date --iso-8601=seconds)";
+            echo "COMMIT_DATE=$(git --no-pager show -s --format=%cd --date=iso8601-strict ${{ github.sha }})";
+            echo "COMMIT_HASH=$(git describe --tags --dirty)";
+          } >> "${GITHUB_ENV}"
+
+      - name: Install rust
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
+        with:
+          toolchain: nightly
+
+      - name: Checkout Slab repo
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          repository: zama-ai/slab
+          path: slab
+          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
+
+      - name: Run benchmarks
+        run: |
+          make bench_hlapi_erc20
+
+      - name: Parse results
+        run: |
+          python3 ./ci/benchmark_parser.py target/criterion ${{ env.RESULTS_FILENAME }} \
+          --database tfhe_rs \
+          --hardware "hpc7a.96xlarge" \
+          --project-version "${{ env.COMMIT_HASH }}" \
+          --branch ${{ github.ref_name }} \
+          --commit-date "${{ env.COMMIT_DATE }}" \
+          --bench-date "${{ env.BENCH_DATE }}" \
+          --walk-subdirs \
+          --name-suffix avx512
+
+      - name: Parse PBS counts
+        run: |
+          python3 ./ci/benchmark_parser.py tfhe/erc20_pbs_count.csv ${{ env.RESULTS_FILENAME }} \
+          --object-sizes \
+          --append-results
+
+      - name: Upload parsed results artifact
+        uses: actions/upload-artifact@b4b15b8c7c6ac21ea08fcf65892d2ee8f75cf882
+        with:
+          name: ${{ github.sha }}_erc20
+          path: ${{ env.RESULTS_FILENAME }}
+
+      - name: Send data to Slab
+        shell: bash
+        run: |
+          python3 slab/scripts/data_sender.py ${{ env.RESULTS_FILENAME }} "${{ secrets.JOB_SECRET }}" \
+          --slab-url "${{ secrets.SLAB_URL }}"
+
+      - name: Slack Notification
+        if: ${{ failure() }}
+        continue-on-error: true
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        env:
+          SLACK_COLOR: ${{ job.status }}
+          SLACK_MESSAGE: "ERC20 benchmarks finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
+
+  teardown-instance:
+    name: Teardown instance (erc20-benchmarks)
+    if: ${{ always() && needs.setup-instance.result != 'skipped' }}
+    needs: [ setup-instance, erc20-benchmarks ]
+    runs-on: ubuntu-latest
+    steps:
+      - name: Stop instance
+        id: stop-instance
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
+        with:
+          mode: stop
+          github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
+          slab-url: ${{ secrets.SLAB_BASE_URL }}
+          job-secret: ${{ secrets.JOB_SECRET }}
+          label: ${{ needs.setup-instance.outputs.runner-name }}
+
+      - name: Slack Notification
+        if: ${{ failure() }}
+        continue-on-error: true
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        env:
+          SLACK_COLOR: ${{ job.status }}
+          SLACK_MESSAGE: "Instance teardown (erc20-benchmarks) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/benchmark_gpu_4090.yml

@@ -39,7 +39,7 @@ jobs:
 
     steps:
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
           token: ${{ secrets.FHE_ACTIONS_TOKEN }}
@@ -54,12 +54,12 @@ jobs:
           echo "FAST_BENCH=TRUE" >> "${GITHUB_ENV}"
 
       - name: Install rust
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: nightly
 
       - name: Checkout Slab repo
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           repository: zama-ai/slab
           path: slab
@@ -79,11 +79,10 @@ jobs:
           --branch ${{ github.ref_name }} \
           --commit-date "${{ env.COMMIT_DATE }}" \
           --bench-date "${{ env.BENCH_DATE }}" \
-          --walk-subdirs \
-          --throughput
+          --walk-subdirs
 
       - name: Upload parsed results artifact
-        uses: actions/upload-artifact@50769540e7f4bd5e21e526ee35c689e35e0d6874
+        uses: actions/upload-artifact@b4b15b8c7c6ac21ea08fcf65892d2ee8f75cf882
         with:
           name: ${{ github.sha }}_integer_multi_bit_gpu_default
           path: ${{ env.RESULTS_FILENAME }}
@@ -97,7 +96,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Integer RTX 4090 full benchmarks finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
@@ -114,9 +113,10 @@ jobs:
 
     steps:
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
+          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
 
       - name: Get benchmark details
         run: |
@@ -127,12 +127,12 @@ jobs:
           } >> "${GITHUB_ENV}"
 
       - name: Install rust
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: nightly
 
       - name: Checkout Slab repo
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           repository: zama-ai/slab
           path: slab
@@ -154,10 +154,10 @@ jobs:
           --commit-date "${{ env.COMMIT_DATE }}" \
           --bench-date "${{ env.BENCH_DATE }}" \
           --walk-subdirs \
-          --throughput
+      
 
       - name: Upload parsed results artifact
-        uses: actions/upload-artifact@50769540e7f4bd5e21e526ee35c689e35e0d6874
+        uses: actions/upload-artifact@b4b15b8c7c6ac21ea08fcf65892d2ee8f75cf882
         with:
           name: ${{ github.sha }}_core_crypto
           path: ${{ env.RESULTS_FILENAME }}
@@ -179,7 +179,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Core crypto RTX 4090 full benchmarks finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/benchmark_gpu_core_crypto.yml

@@ -27,7 +27,7 @@ jobs:
     steps:
       - name: Start instance
         id: start-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: start
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -56,7 +56,7 @@ jobs:
       - name: Install dependencies
         run: |
           sudo apt update
-          sudo apt install -y checkinstall zlib1g-dev libssl-dev
+          sudo apt install -y checkinstall zlib1g-dev libssl-dev libclang-dev
           wget https://github.com/Kitware/CMake/releases/download/v${{ env.CMAKE_VERSION }}/cmake-${{ env.CMAKE_VERSION }}.tar.gz
           tar -zxvf cmake-${{ env.CMAKE_VERSION }}.tar.gz
           cd cmake-${{ env.CMAKE_VERSION }}
@@ -65,7 +65,7 @@ jobs:
           sudo make install
 
       - name: Checkout tfhe-rs repo with tags
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
           token: ${{ secrets.FHE_ACTIONS_TOKEN }}
@@ -84,7 +84,7 @@ jobs:
           echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
 
       - name: Install rust
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: nightly
 
@@ -125,17 +125,16 @@ jobs:
           --commit-date "${{ env.COMMIT_DATE }}" \
           --bench-date "${{ env.BENCH_DATE }}" \
           --name-suffix avx512 \
-          --walk-subdirs \
-          --throughput
+          --walk-subdirs
 
       - name: Upload parsed results artifact
-        uses: actions/upload-artifact@50769540e7f4bd5e21e526ee35c689e35e0d6874
+        uses: actions/upload-artifact@b4b15b8c7c6ac21ea08fcf65892d2ee8f75cf882
         with:
           name: ${{ github.sha }}_core_crypto
           path: ${{ env.RESULTS_FILENAME }}
 
       - name: Checkout Slab repo
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           repository: zama-ai/slab
           path: slab
@@ -155,7 +154,7 @@ jobs:
     continue-on-error: true
     steps:
       - name: Send message
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ needs.cuda-core-crypto-benchmarks.result }}
           SLACK_MESSAGE: "PBS GPU benchmarks finished with status: ${{ needs.cuda-core-crypto-benchmarks.result }}. (${{ env.ACTION_RUN_URL }})"
@@ -168,7 +167,7 @@ jobs:
     steps:
       - name: Stop instance
         id: stop-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: stop
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -179,7 +178,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Instance teardown (cuda-core-crypto-benchmarks) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/benchmark_gpu_erc20.yml

@@ -0,0 +1,41 @@
+# Run CUDA ERC20 benchmarks on a Hyperstack VM and return parsed results to Slab CI bot.
+name: Cuda ERC20 benchmarks
+
+on:
+  workflow_dispatch:
+    inputs:
+      profile:
+        description: "Instance type"
+        required: true
+        type: choice
+        options:
+          - "l40 (n3-L40x1)"
+          - "single-h100 (n3-H100x1)"
+          - "2-h100 (n3-H100x2)"
+          - "multi-h100 (n3-H100x8)"
+
+jobs:
+  parse-inputs:
+    runs-on: ubuntu-latest
+    outputs:
+      profile: ${{ steps.parse_profile.outputs.profile }}
+      hardware_name: ${{ steps.parse_hardware_name.outputs.name }}
+    steps:
+      - name: Parse profile
+        id: parse_profile
+        run: |
+          echo "profile=$(echo '${{ inputs.profile }}' | sed 's|\(.*\)[[:space:]](.*)|\1|')" >> "${GITHUB_OUTPUT}"
+
+      - name: Parse hardware name
+        id: parse_hardware_name
+        run: |
+          echo "name=$(echo '${{ inputs.profile }}' | sed 's|.*[[:space:]](\(.*\))|\1|')" >> "${GITHUB_OUTPUT}"
+
+  run-benchmarks:
+    name: Run benchmarks
+    needs: parse-inputs
+    uses: ./.github/workflows/benchmark_gpu_erc20_common.yml
+    with:
+      profile: ${{ needs.parse-inputs.outputs.profile }}
+      hardware_name: ${{ needs.parse-inputs.outputs.hardware_name }}
+    secrets: inherit

.github/workflows/benchmark_gpu_erc20_common.yml

@@ -1,15 +1,40 @@
-# Run integer benchmarks on an instance with CUDA and return parsed results to Slab CI bot.
-name: Integer 2xH100 benchmarks
+# Run ERC20 benchmarks on an instance with CUDA and return parsed results to Slab CI bot.
+name: Cuda ERC20 benchmarks - common
 
 on:
-  workflow_dispatch:
-  schedule:
-    # Weekly benchmarks will be triggered each Saturday at 1a.m.
-    - cron: '0 1 * * 6'
+  workflow_call:
+    inputs:
+      backend:
+        type: string
+        default: hyperstack
+      profile:
+        type: string
+        required: true
+      hardware_name:
+        type: string
+        required: true
+    secrets:
+      FHE_ACTIONS_TOKEN:
+        required: true
+      SLAB_ACTION_TOKEN:
+        required: true
+      SLAB_BASE_URL:
+        required: true
+      SLAB_URL:
+        required: true
+      JOB_SECRET:
+        required: true
+      SLACK_CHANNEL:
+        required: true
+      BOT_USERNAME:
+        required: true
+      SLACK_WEBHOOK:
+        required: true
 
 env:
   CARGO_TERM_COLOR: always
   RESULTS_FILENAME: parsed_benchmark_results_${{ github.sha }}.json
+  PARSE_INTEGER_BENCH_CSV_FILE: tfhe_rs_integer_benches_${{ github.sha }}.csv
   ACTION_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
   RUST_BACKTRACE: "full"
   RUST_MIN_STACK: "8388608"
@@ -20,37 +45,32 @@ env:
 
 jobs:
   setup-instance:
-    name: Setup instance (cuda-integer-full-2-gpu-benchmarks)
+    name: Setup instance (cuda-erc20-benchmarks)
     runs-on: ubuntu-latest
-    if: github.event_name != 'schedule' ||
+    if:  github.event_name == 'workflow_dispatch' ||
       (github.event_name == 'schedule' && github.repository == 'zama-ai/tfhe-rs')
     outputs:
       runner-name: ${{ steps.start-instance.outputs.label }}
     steps:
       - name: Start instance
         id: start-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: start
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
           slab-url: ${{ secrets.SLAB_BASE_URL }}
           job-secret: ${{ secrets.JOB_SECRET }}
-          backend: hyperstack
-          profile: 2-h100
+          backend: ${{ inputs.backend }}
+          profile: ${{ inputs.profile }}
 
-  cuda-integer-full-2-gpu-benchmarks:
-    name: Execute 2xH100 integer benchmarks
+  cuda-erc20-benchmarks:
+    name: Cuda ERC20 benchmarks (${{ inputs.profile }})
     needs: setup-instance
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
-    timeout-minutes: 1440 # 24 hours
-    continue-on-error: true
     strategy:
       fail-fast: false
-      max-parallel: 1
+      # explicit include-based build matrix, of known valid options
       matrix:
-        command: [integer_multi_bit]
-        op_flavor: [default]
-        # explicit include-based build matrix, of known valid options
         include:
           - os: ubuntu-22.04
             cuda: "12.2"
@@ -72,7 +92,7 @@ jobs:
           sudo make install
 
       - name: Checkout tfhe-rs repo with tags
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
           token: ${{ secrets.FHE_ACTIONS_TOKEN }}
@@ -91,7 +111,7 @@ jobs:
           echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
 
       - name: Install rust
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: nightly
 
@@ -115,41 +135,40 @@ jobs:
             echo "CUDAHOSTCXX=/usr/bin/g++-${{ matrix.gcc }}";
           } >> "${GITHUB_ENV}"
 
-      - name: Checkout Slab repo
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
-        with:
-          repository: zama-ai/slab
-          path: slab
-          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
-
       - name: Check device is detected
         if: ${{ !cancelled() }}
         run: nvidia-smi
 
-      - name: Run benchmarks with AVX512
+      - name: Run benchmarks
         run: |
-          make BENCH_OP_FLAVOR=${{ matrix.op_flavor }} bench_${{ matrix.command }}_gpu
+          make bench_hlapi_erc20_gpu
 
       - name: Parse results
         run: |
           python3 ./ci/benchmark_parser.py target/criterion ${{ env.RESULTS_FILENAME }} \
           --database tfhe_rs \
-          --hardware "n3-H100x2" \
+          --hardware "${{ inputs.hardware_name }}" \
           --backend gpu \
           --project-version "${{ env.COMMIT_HASH }}" \
           --branch ${{ github.ref_name }} \
           --commit-date "${{ env.COMMIT_DATE }}" \
           --bench-date "${{ env.BENCH_DATE }}" \
           --walk-subdirs \
-          --name-suffix avx512 \
-          --throughput
+          --name-suffix avx512
 
       - name: Upload parsed results artifact
-        uses: actions/upload-artifact@50769540e7f4bd5e21e526ee35c689e35e0d6874
+        uses: actions/upload-artifact@b4b15b8c7c6ac21ea08fcf65892d2ee8f75cf882
         with:
-          name: ${{ github.sha }}_${{ matrix.command }}_${{ matrix.op_flavor }}
+          name: ${{ github.sha }}_erc20
           path: ${{ env.RESULTS_FILENAME }}
 
+      - name: Checkout Slab repo
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          repository: zama-ai/slab
+          path: slab
+          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
+
       - name: Send data to Slab
         shell: bash
         run: |
@@ -158,26 +177,26 @@ jobs:
 
   slack-notify:
     name: Slack Notification
-    needs: [ setup-instance, cuda-integer-full-2-gpu-benchmarks ]
+    needs: [ setup-instance, cuda-erc20-benchmarks ]
     runs-on: ubuntu-latest
-    if: ${{ always() && needs.cuda-integer-full-2-gpu-benchmarks.result != 'skipped' && failure() }}
+    if: ${{ always() && needs.cuda-erc20-benchmarks.result != 'skipped' && failure() }}
     continue-on-error: true
     steps:
       - name: Send message
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
-          SLACK_COLOR: ${{ needs.cuda-integer-full-2-gpu-benchmarks.result }}
-          SLACK_MESSAGE: "Integer GPU 2xH100 benchmarks finished with status: ${{ needs.cuda-integer-full-2-gpu-benchmarks.result }}. (${{ env.ACTION_RUN_URL }})"
+          SLACK_COLOR: ${{ needs.cuda-erc20-benchmarks.result }}
+          SLACK_MESSAGE: "Cuda ERC20 benchmarks (${{ inputs.profile }}) finished with status: ${{ needs.cuda-erc20-benchmarks.result }}. (${{ env.ACTION_RUN_URL }})"
 
   teardown-instance:
-    name: Teardown instance (cuda-integer-full-2-gpu-benchmarks)
+    name: Teardown instance (cuda-erc20-${{ inputs.profile }}-benchmarks)
     if: ${{ always() && needs.setup-instance.result != 'skipped' }}
-    needs: [ setup-instance, cuda-integer-full-2-gpu-benchmarks ]
+    needs: [ setup-instance, cuda-erc20-benchmarks, slack-notify ]
     runs-on: ubuntu-latest
     steps:
       - name: Stop instance
         id: stop-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: stop
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -188,7 +207,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "Instance teardown (cuda-integer-full-2-gpu-benchmarks) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Instance teardown (cuda-erc20-${{ inputs.profile }}-benchmarks) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/benchmark_gpu_erc20_weekly.yml

@@ -0,0 +1,35 @@
+# Run CUDA ERC20 benchmarks on multiple Hyperstack VMs and return parsed results to Slab CI bot.
+name: Cuda ERC20 weekly benchmarks
+
+on:
+  schedule:
+    # Weekly benchmarks will be triggered each Saturday at 5a.m.
+    - cron: '0 5 * * 6'
+
+jobs:
+  run-benchmarks-1-h100:
+    name: Run benchmarks (1xH100)
+    if: github.repository == 'zama-ai/tfhe-rs'
+    uses: ./.github/workflows/benchmark_gpu_erc20_common.yml
+    with:
+      profile: single-h100
+      hardware_name: n3-H100x1
+    secrets: inherit
+
+  run-benchmarks-2-h100:
+    name: Run benchmarks (2xH100)
+    if: github.repository == 'zama-ai/tfhe-rs'
+    uses: ./.github/workflows/benchmark_gpu_erc20_common.yml
+    with:
+      profile: 2-h100
+      hardware_name: n3-H100x2
+    secrets: inherit
+
+  run-benchmarks-8-h100:
+    name: Run benchmarks (8xH100)
+    if: github.repository == 'zama-ai/tfhe-rs'
+    uses: ./.github/workflows/benchmark_gpu_erc20_common.yml
+    with:
+      profile: multi-h100
+      hardware_name: n3-H100x8
+    secrets: inherit

.github/workflows/benchmark_gpu_integer.yml

@@ -1,201 +1,78 @@
-# Run integer benchmarks on an instance with CUDA and return parsed results to Slab CI bot.
-name: Integer GPU benchmarks
+# Run CUDA benchmarks on a Hyperstack VM and return parsed results to Slab CI bot.
+name: Cuda benchmarks
 
 on:
   workflow_dispatch:
-  push:
-    branches:
-      - main
-
-env:
-  CARGO_TERM_COLOR: always
-  RESULTS_FILENAME: parsed_benchmark_results_${{ github.sha }}.json
-  PARSE_INTEGER_BENCH_CSV_FILE: tfhe_rs_integer_benches_${{ github.sha }}.csv
-  ACTION_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
-  RUST_BACKTRACE: "full"
-  RUST_MIN_STACK: "8388608"
-  SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
-  SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
-  SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
-  SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+    inputs:
+      profile:
+        description: "Instance type"
+        required: true
+        type: choice
+        options:
+          - "l40 (n3-L40x1)"
+          - "single-h100 (n3-H100x1)"
+          - "2-h100 (n3-H100x2)"
+          - "4-h100 (n3-H100x4)"
+          - "multi-h100 (n3-H100x8)"
+          - "multi-h100-nvlink (n3-H100x8-NVLink)"
+          - "multi-a100-nvlink (n3-A100x8-NVLink)"
+      command:
+        description: "Benchmark command to run"
+        type: choice
+        default: integer_multi_bit
+        options:
+          - integer
+          - integer_multi_bit
+          - integer_compression
+          - pbs
+          - ks
+      op_flavor:
+        description: "Operations set to run"
+        type: choice
+        default: default
+        options:
+          - default
+          - fast_default
+          - unchecked
+      all_precisions:
+        description: "Run all precisions"
+        type: boolean
+        default: false
+      bench_type:
+        description: "Benchmarks type"
+        type: choice
+        default: latency
+        options:
+          - latency
+          - throughput
+          - both
 
 jobs:
-  setup-instance:
-    name: Setup instance (cuda-integer-benchmarks)
+  parse-inputs:
     runs-on: ubuntu-latest
-    if:  github.event_name == 'workflow_dispatch' ||
-      (github.event_name == 'push' && github.repository == 'zama-ai/tfhe-rs')
     outputs:
-      runner-name: ${{ steps.start-instance.outputs.label }}
+      profile: ${{ steps.parse_profile.outputs.profile }}
+      hardware_name: ${{ steps.parse_hardware_name.outputs.name }}
     steps:
-      - name: Start instance
-        id: start-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
-        with:
-          mode: start
-          github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
-          slab-url: ${{ secrets.SLAB_BASE_URL }}
-          job-secret: ${{ secrets.JOB_SECRET }}
-          backend: hyperstack
-          profile: single-h100
-
-  cuda-integer-benchmarks:
-    name: Execute GPU integer benchmarks
-    needs: setup-instance
-    runs-on: ${{ needs.setup-instance.outputs.runner-name }}
-    strategy:
-      fail-fast: false
-      # explicit include-based build matrix, of known valid options
-      matrix:
-        include:
-          - os: ubuntu-22.04
-            cuda: "12.2"
-            gcc: 11
-    env:
-      CUDA_PATH: /usr/local/cuda-${{ matrix.cuda }}
-      CMAKE_VERSION: 3.29.6
-    steps:
-      # Mandatory on hyperstack since a bootable volume is not re-usable yet.
-      - name: Install dependencies
+      - name: Parse profile
+        id: parse_profile
         run: |
-          sudo apt update
-          sudo apt install -y checkinstall zlib1g-dev libssl-dev
-          wget https://github.com/Kitware/CMake/releases/download/v${{ env.CMAKE_VERSION }}/cmake-${{ env.CMAKE_VERSION }}.tar.gz
-          tar -zxvf cmake-${{ env.CMAKE_VERSION }}.tar.gz
-          cd cmake-${{ env.CMAKE_VERSION }}
-          ./bootstrap
-          make -j"$(nproc)"
-          sudo make install
+          echo "profile=$(echo '${{ inputs.profile }}' | sed 's|\(.*\)[[:space:]](.*)|\1|')" >> "${GITHUB_OUTPUT}"
 
-      - name: Checkout tfhe-rs repo with tags
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
-        with:
-          fetch-depth: 0
-          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
-
-      - name: Get benchmark details
+      - name: Parse hardware name
+        id: parse_hardware_name
         run: |
-          {
-            echo "BENCH_DATE=$(date --iso-8601=seconds)";
-            echo "COMMIT_DATE=$(git --no-pager show -s --format=%cd --date=iso8601-strict ${{ github.sha }})";
-            echo "COMMIT_HASH=$(git describe --tags --dirty)";
-          } >> "${GITHUB_ENV}"
+          echo "name=$(echo '${{ inputs.profile }}' | sed 's|.*[[:space:]](\(.*\))|\1|')" >> "${GITHUB_OUTPUT}"
 
-      - name: Set up home
-        # "Install rust" step require root user to have a HOME directory which is not set.
-        run: |
-          echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
-
-      - name: Install rust
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
-        with:
-          toolchain: nightly
-
-      - name: Export CUDA variables
-        if: ${{ !cancelled() }}
-        run: |
-          {
-            echo "CUDA_PATH=$CUDA_PATH";
-            echo "LD_LIBRARY_PATH=$CUDA_PATH/lib:$LD_LIBRARY_PATH";
-            echo "CUDACXX=/usr/local/cuda-${{ matrix.cuda }}/bin/nvcc";
-          } >> "${GITHUB_ENV}"
-          echo "$CUDA_PATH/bin" >> "${GITHUB_PATH}"
-
-      # Specify the correct host compilers
-      - name: Export gcc and g++ variables
-        if: ${{ !cancelled() }}
-        run: |
-          {
-            echo "CC=/usr/bin/gcc-${{ matrix.gcc }}";
-            echo "CXX=/usr/bin/g++-${{ matrix.gcc }}";
-            echo "CUDAHOSTCXX=/usr/bin/g++-${{ matrix.gcc }}";
-          } >> "${GITHUB_ENV}"
-
-      - name: Check device is detected
-        if: ${{ !cancelled() }}
-        run: nvidia-smi
-
-      - name: Run benchmarks with AVX512
-        run: |
-          make FAST_BENCH=TRUE BENCH_OP_FLAVOR=default bench_integer_gpu
-
-      - name: Parse benchmarks to csv
-        run: |
-          make PARSE_INTEGER_BENCH_CSV_FILE=${{ env.PARSE_INTEGER_BENCH_CSV_FILE }} \
-            parse_integer_benches
-
-      - name: Upload csv results artifact
-        uses: actions/upload-artifact@50769540e7f4bd5e21e526ee35c689e35e0d6874
-        with:
-          name: ${{ github.sha }}_csv_integer
-          path: ${{ env.PARSE_INTEGER_BENCH_CSV_FILE }}
-
-      - name: Parse results
-        run: |
-          python3 ./ci/benchmark_parser.py target/criterion ${{ env.RESULTS_FILENAME }} \
-          --database tfhe_rs \
-          --hardware "n3-H100x1" \
-          --backend gpu \
-          --project-version "${{ env.COMMIT_HASH }}" \
-          --branch ${{ github.ref_name }} \
-          --commit-date "${{ env.COMMIT_DATE }}" \
-          --bench-date "${{ env.BENCH_DATE }}" \
-          --walk-subdirs \
-          --name-suffix avx512 \
-          --throughput
-
-      - name: Upload parsed results artifact
-        uses: actions/upload-artifact@50769540e7f4bd5e21e526ee35c689e35e0d6874
-        with:
-          name: ${{ github.sha }}_integer
-          path: ${{ env.RESULTS_FILENAME }}
-
-      - name: Checkout Slab repo
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
-        with:
-          repository: zama-ai/slab
-          path: slab
-          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
-
-      - name: Send data to Slab
-        shell: bash
-        run: |
-          python3 slab/scripts/data_sender.py ${{ env.RESULTS_FILENAME }} "${{ secrets.JOB_SECRET }}" \
-          --slab-url "${{ secrets.SLAB_URL }}"
-
-  slack-notify:
-    name: Slack Notification
-    needs: [ setup-instance, cuda-integer-benchmarks ]
-    runs-on: ubuntu-latest
-    if: ${{ always() && needs.cuda-integer-benchmarks.result != 'skipped' && failure() }}
-    continue-on-error: true
-    steps:
-      - name: Send message
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
-        env:
-          SLACK_COLOR: ${{ needs.cuda-integer-benchmarks.result }}
-          SLACK_MESSAGE: "Integer GPU benchmarks finished with status: ${{ needs.cuda-integer-benchmarks.result }}. (${{ env.ACTION_RUN_URL }})"
-
-  teardown-instance:
-    name: Teardown instance (cuda-integer-benchmarks)
-    if: ${{ always() && needs.setup-instance.result != 'skipped' }}
-    needs: [ setup-instance, cuda-integer-benchmarks, slack-notify ]
-    runs-on: ubuntu-latest
-    steps:
-      - name: Stop instance
-        id: stop-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
-        with:
-          mode: stop
-          github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
-          slab-url: ${{ secrets.SLAB_BASE_URL }}
-          job-secret: ${{ secrets.JOB_SECRET }}
-          label: ${{ needs.setup-instance.outputs.runner-name }}
-
-      - name: Slack Notification
-        if: ${{ failure() }}
-        continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
-        env:
-          SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "Instance teardown (cuda-integer-benchmarks) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
+  run-benchmarks:
+    name: Run benchmarks
+    needs: parse-inputs
+    uses: ./.github/workflows/benchmark_gpu_integer_common.yml
+    with:
+      profile: ${{ needs.parse-inputs.outputs.profile }}
+      hardware_name: ${{ needs.parse-inputs.outputs.hardware_name }}
+      command: ${{ inputs.command }}
+      op_flavor: ${{ inputs.op_flavor }}
+      bench_type: ${{ inputs.bench_type }}
+      all_precisions: ${{ inputs.all_precisions }}
+    secrets: inherit

.github/workflows/benchmark_gpu_integer_common.yml

@@ -1,21 +1,47 @@
-# Run 64-bit multi-bit integer benchmarks on an instance with CUDA and return parsed results to Slab CI bot.
-name: Integer multi GPU Multi-bit benchmarks
+# Run integer benchmarks on CUDA instance and return parsed results to Slab CI bot.
+name: Cuda benchmarks - common
 
 on:
-  workflow_dispatch:
+  workflow_call:
     inputs:
+      backend:
+        type: string
+        default: hyperstack
+      profile:
+        type: string
+        required: true
+      hardware_name:
+        type: string
+        required: true
+      command: # Use a comma separated values to generate an array
+        type: string
+        required: true
+      op_flavor: # Use a comma separated values to generate an array
+        type: string
+        required: true
+      bench_type:
+        type: string
+        default: latency
       all_precisions:
-        description: "Run all precisions"
         type: boolean
         default: false
-      fast_default:
-        description: "Run only deduplicated default operations without scalar variants"
-        type: boolean
-        default: false
-
-  schedule:
-    # Weekly benchmarks will be triggered each Saturday at 1a.m.
-    - cron: '0 1 * * 6'
+    secrets:
+      FHE_ACTIONS_TOKEN:
+        required: true
+      SLAB_ACTION_TOKEN:
+        required: true
+      SLAB_BASE_URL:
+        required: true
+      SLAB_URL:
+        required: true
+      JOB_SECRET:
+        required: true
+      SLACK_CHANNEL:
+        required: true
+      BOT_USERNAME:
+        required: true
+      SLACK_WEBHOOK:
+        required: true
 
 env:
   CARGO_TERM_COLOR: always
@@ -28,32 +54,82 @@ env:
   SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
   SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
   FAST_BENCH: TRUE
-  BENCH_OP_FLAVOR: default
 
 jobs:
-  setup-instance:
-    name: Setup instance (cuda-integer-multi-bit-multi-gpu-benchmarks)
+  prepare-matrix:
+    name: Prepare operations matrix
+    runs-on: ubuntu-latest
+    outputs:
+      command: ${{ steps.set_command.outputs.command }}
+      op_flavor: ${{ steps.set_op_flavor.outputs.op_flavor }}
+      bench_type: ${{ steps.set_bench_type.outputs.bench_type }}
+    steps:
+      - name: Set single command
+        if: ${{ !contains(inputs.command, ',')}}
+        run: |
+          echo "COMMAND=[\"${{ inputs.command }}\"]" >> "${GITHUB_ENV}"
+
+      - name: Set multiple commands
+        if: ${{ contains(inputs.command, ',')}}
+        run: |
+          PARSED_COMMAND=$(echo "${{ inputs.command }}" | sed 's/[[:space:]]*,[[:space:]]*/\\", \\"/g')
+          echo "COMMAND=[\"${PARSED_COMMAND}\"]" >> "${GITHUB_ENV}"
+
+      - name: Set single operations flavor
+        if: ${{ !contains(inputs.op_flavor, ',')}}
+        run: |
+          echo "OP_FLAVOR=[\"${{ inputs.op_flavor }}\"]" >> "${GITHUB_ENV}"
+
+      - name: Set multiple operations flavors
+        if: ${{ contains(inputs.op_flavor, ',')}}
+        run: |
+          PARSED_OP_FLAVOR=$(echo "${{ inputs.op_flavor }}" | sed 's/[[:space:]]*,[[:space:]]*/", "/g')
+          echo "OP_FLAVOR=[\"${PARSED_OP_FLAVOR}\"]" >> "${GITHUB_ENV}"
+
+      - name: Set benchmark types
+        run: |
+          if [[ "${{ inputs.bench_type }}" == "both" ]]; then
+            echo "BENCH_TYPE=[\"latency\", \"throughput\"]" >> "${GITHUB_ENV}"
+          else
+            echo "BENCH_TYPE=[\"${{ inputs.bench_type }}\"]" >> "${GITHUB_ENV}"
+          fi
+
+      - name: Set command output
+        id: set_command
+        run: |
+          echo "command=${{ toJSON(env.COMMAND) }}" >> "${GITHUB_OUTPUT}"
+
+      - name: Set operation flavor output
+        id: set_op_flavor
+        run: |
+          echo "op_flavor=${{ toJSON(env.OP_FLAVOR) }}" >> "${GITHUB_OUTPUT}"
+
+      - name: Set benchmark types output
+        id: set_bench_type
+        run: |
+          echo "bench_type=${{ toJSON(env.BENCH_TYPE) }}" >> "${GITHUB_OUTPUT}"
+
+  setup-instance:
+    name: Setup instance (cuda-${{ inputs.profile }}-benchmarks)
+    needs: prepare-matrix
     runs-on: ubuntu-latest
-    if: ${{ (github.event_name == 'push' && github.repository == 'zama-ai/tfhe-rs') ||
-      (github.event_name == 'schedule' && github.repository == 'zama-ai/tfhe-rs') ||
-      github.event_name == 'workflow_dispatch' }}
     outputs:
       runner-name: ${{ steps.start-instance.outputs.label }}
     steps:
       - name: Start instance
         id: start-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: start
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
           slab-url: ${{ secrets.SLAB_BASE_URL }}
           job-secret: ${{ secrets.JOB_SECRET }}
-          backend: hyperstack
-          profile: multi-h100
+          backend: ${{ inputs.backend }}
+          profile: ${{ inputs.profile }}
 
-  cuda-integer-multi-bit-multi-gpu-benchmarks:
-    name: Execute multi GPU integer multi-bit benchmarks
-    needs: setup-instance
+  cuda-benchmarks:
+    name: Cuda benchmarks (${{ inputs.profile }})
+    needs: [ prepare-matrix, setup-instance ]
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     timeout-minutes: 1440 # 24 hours
     continue-on-error: true
@@ -61,6 +137,10 @@ jobs:
       fail-fast: false
       max-parallel: 1
       matrix:
+        command: ${{ fromJSON(needs.prepare-matrix.outputs.command) }}
+        op_flavor: ${{ fromJSON(needs.prepare-matrix.outputs.op_flavor) }}
+        bench_type: ${{ fromJSON(needs.prepare-matrix.outputs.bench_type) }}
+        # explicit include-based build matrix, of known valid options
         include:
           - os: ubuntu-22.04
             cuda: "12.2"
@@ -73,7 +153,7 @@ jobs:
       - name: Install dependencies
         run: |
           sudo apt update
-          sudo apt install -y checkinstall zlib1g-dev libssl-dev
+          sudo apt install -y checkinstall zlib1g-dev libssl-dev libclang-dev
           wget https://github.com/Kitware/CMake/releases/download/v${{ env.CMAKE_VERSION }}/cmake-${{ env.CMAKE_VERSION }}.tar.gz
           tar -zxvf cmake-${{ env.CMAKE_VERSION }}.tar.gz
           cd cmake-${{ env.CMAKE_VERSION }}
@@ -82,7 +162,7 @@ jobs:
           sudo make install
 
       - name: Checkout tfhe-rs repo with tags
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
           token: ${{ secrets.FHE_ACTIONS_TOKEN }}
@@ -101,7 +181,7 @@ jobs:
           echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
 
       - name: Install rust
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: nightly
 
@@ -126,35 +206,30 @@ jobs:
           } >> "${GITHUB_ENV}"
 
       - name: Checkout Slab repo
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           repository: zama-ai/slab
           path: slab
           token: ${{ secrets.FHE_ACTIONS_TOKEN }}
 
+      - name: Check device is detected
+        if: ${{ !cancelled() }}
+        run: nvidia-smi
+
       - name: Should run benchmarks with all precisions
         if: inputs.all_precisions
         run: |
           echo "FAST_BENCH=FALSE" >> "${GITHUB_ENV}"
 
-      - name: Should run fast subset benchmarks
-        if: inputs.fast_default
+      - name: Run benchmarks
         run: |
-          echo "BENCH_OP_FLAVOR=fast_default" >> "${GITHUB_ENV}"
-
-      - name: Check device is detected
-        if: ${{ !cancelled() }}
-        run: nvidia-smi
-
-      - name: Run multi-bit benchmarks with AVX512
-        run: |
-          make bench_unsigned_integer_multi_bit_gpu
+          make BENCH_OP_FLAVOR=${{ matrix.op_flavor }} BENCH_TYPE=${{ matrix.bench_type }} bench_${{ matrix.command }}_gpu
 
       - name: Parse results
         run: |
           python3 ./ci/benchmark_parser.py target/criterion ${{ env.RESULTS_FILENAME }} \
           --database tfhe_rs \
-          --hardware "n3-H100x8" \
+          --hardware "${{ inputs.hardware_name }}" \
           --backend gpu \
           --project-version "${{ env.COMMIT_HASH }}" \
           --branch ${{ github.ref_name }} \
@@ -162,12 +237,12 @@ jobs:
           --bench-date "${{ env.BENCH_DATE }}" \
           --walk-subdirs \
           --name-suffix avx512 \
-          --throughput
+          --bench-type ${{ matrix.bench_type }}
 
       - name: Upload parsed results artifact
-        uses: actions/upload-artifact@50769540e7f4bd5e21e526ee35c689e35e0d6874
+        uses: actions/upload-artifact@b4b15b8c7c6ac21ea08fcf65892d2ee8f75cf882
         with:
-          name: ${{ github.sha }}_integer
+          name: ${{ github.sha }}_${{ matrix.command }}_${{ matrix.op_flavor }}
           path: ${{ env.RESULTS_FILENAME }}
 
       - name: Send data to Slab
@@ -178,26 +253,26 @@ jobs:
 
   slack-notify:
     name: Slack Notification
-    needs: [ setup-instance, cuda-integer-multi-bit-multi-gpu-benchmarks ]
+    needs: [ setup-instance, cuda-benchmarks ]
     runs-on: ubuntu-latest
-    if: ${{ always() && needs.cuda-integer-multi-bit-multi-gpu-benchmarks.result != 'skipped' && failure() }}
+    if: ${{ always() && needs.cuda-benchmarks.result != 'skipped' && failure() }}
     continue-on-error: true
     steps:
       - name: Send message
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
-          SLACK_COLOR: ${{ needs.cuda-integer-multi-bit-multi-gpu-benchmarks.result }}
-          SLACK_MESSAGE: "Integer multi GPU multi-bit benchmarks finished with status: ${{ needs.cuda-integer-multi-bit-multi-gpu-benchmarks.result }}. (${{ env.ACTION_RUN_URL }})"
+          SLACK_COLOR: ${{ needs.cuda-benchmarks.result }}
+          SLACK_MESSAGE: "Cuda benchmarks (${{ inputs.profile }}) finished with status: ${{ needs.cuda-benchmarks.result }}. (${{ env.ACTION_RUN_URL }})"
 
   teardown-instance:
-    name: Teardown instance (cuda-integer-multi-bit-multi-gpu-benchmarks)
+    name: Teardown instance (cuda-${{ inputs.profile }}-benchmarks)
     if: ${{ always() && needs.setup-instance.result != 'skipped' }}
-    needs: [ setup-instance, cuda-integer-multi-bit-multi-gpu-benchmarks ]
+    needs: [ setup-instance, cuda-benchmarks, slack-notify ]
     runs-on: ubuntu-latest
     steps:
       - name: Stop instance
         id: stop-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: stop
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -208,7 +283,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "Instance teardown (cuda-integer-multi-bit-multi-gpu-benchmarks) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Instance teardown (cuda-${{ inputs.profile }}-benchmarks) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/benchmark_gpu_integer_full.yml

@@ -1,200 +0,0 @@
-# Run all integer benchmarks on an instance with CUDA and return parsed results to Slab CI bot.
-name: Integer GPU full benchmarks
-
-on:
-  workflow_dispatch:
-  schedule:
-    # Weekly benchmarks will be triggered each Saturday at 1a.m.
-    - cron: '0 1 * * 6'
-
-env:
-  CARGO_TERM_COLOR: always
-  RESULTS_FILENAME: parsed_benchmark_results_${{ github.sha }}.json
-  ACTION_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
-  RUST_BACKTRACE: "full"
-  RUST_MIN_STACK: "8388608"
-  SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
-  SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
-  SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
-  SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
-
-jobs:
-  setup-instance:
-    name: Setup instance (cuda-integer-full-benchmarks)
-    runs-on: ubuntu-latest
-    if: github.event_name != 'schedule' ||
-      (github.event_name == 'schedule' && github.repository == 'zama-ai/tfhe-rs')
-    outputs:
-      runner-name: ${{ steps.start-instance.outputs.label }}
-    steps:
-      - name: Start instance
-        id: start-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
-        with:
-          mode: start
-          github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
-          slab-url: ${{ secrets.SLAB_BASE_URL }}
-          job-secret: ${{ secrets.JOB_SECRET }}
-          backend: hyperstack
-          profile: single-h100
-
-  cuda-integer-full-benchmarks:
-    name: Execute GPU integer benchmarks for all operations flavor
-    needs: setup-instance
-    runs-on: ${{ needs.setup-instance.outputs.runner-name }}
-    timeout-minutes: 1440 # 24 hours
-    continue-on-error: true
-    strategy:
-      fail-fast: false
-      max-parallel: 1
-      matrix:
-        command: [integer, integer_multi_bit]
-        op_flavor: [default]
-        # explicit include-based build matrix, of known valid options
-        include:
-          - os: ubuntu-22.04
-            cuda: "12.2"
-            gcc: 11
-    env:
-      CUDA_PATH: /usr/local/cuda-${{ matrix.cuda }}
-      CMAKE_VERSION: 3.29.6
-    steps:
-      # Mandatory on hyperstack since a bootable volume is not re-usable yet.
-      - name: Install dependencies
-        run: |
-          sudo apt update
-          sudo apt install -y checkinstall zlib1g-dev libssl-dev
-          wget https://github.com/Kitware/CMake/releases/download/v${{ env.CMAKE_VERSION }}/cmake-${{ env.CMAKE_VERSION }}.tar.gz
-          tar -zxvf cmake-${{ env.CMAKE_VERSION }}.tar.gz
-          cd cmake-${{ env.CMAKE_VERSION }}
-          ./bootstrap
-          make -j"$(nproc)"
-          sudo make install
-
-      - name: Checkout tfhe-rs repo with tags
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
-        with:
-          fetch-depth: 0
-          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
-
-      - name: Get benchmark details
-        run: |
-          {
-            echo "BENCH_DATE=$(date --iso-8601=seconds)";
-            echo "COMMIT_DATE=$(git --no-pager show -s --format=%cd --date=iso8601-strict ${{ github.sha }})";
-            echo "COMMIT_HASH=$(git describe --tags --dirty)";
-          } >> "${GITHUB_ENV}"
-
-      - name: Set up home
-        # "Install rust" step require root user to have a HOME directory which is not set.
-        run: |
-          echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
-
-      - name: Install rust
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
-        with:
-          toolchain: nightly
-
-      - name: Export CUDA variables
-        if: ${{ !cancelled() }}
-        run: |
-          {
-            echo "CUDA_PATH=$CUDA_PATH";
-            echo "LD_LIBRARY_PATH=$CUDA_PATH/lib:$LD_LIBRARY_PATH";
-            echo "CUDACXX=/usr/local/cuda-${{ matrix.cuda }}/bin/nvcc";
-          } >> "${GITHUB_ENV}"
-          echo "$CUDA_PATH/bin" >> "${GITHUB_PATH}"
-
-      # Specify the correct host compilers
-      - name: Export gcc and g++ variables
-        if: ${{ !cancelled() }}
-        run: |
-          {
-            echo "CC=/usr/bin/gcc-${{ matrix.gcc }}";
-            echo "CXX=/usr/bin/g++-${{ matrix.gcc }}";
-            echo "CUDAHOSTCXX=/usr/bin/g++-${{ matrix.gcc }}";
-          } >> "${GITHUB_ENV}"
-
-      - name: Checkout Slab repo
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
-        with:
-          repository: zama-ai/slab
-          path: slab
-          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
-
-      - name: Check device is detected
-        if: ${{ !cancelled() }}
-        run: nvidia-smi
-
-      - name: Run benchmarks with AVX512
-        run: |
-          make BENCH_OP_FLAVOR=${{ matrix.op_flavor }} bench_${{ matrix.command }}_gpu
-
-      # Run these benchmarks only once
-      - name: Run compression benchmarks with AVX512
-        if: matrix.op_flavor == 'default' && matrix.command == 'integer'
-        run: |
-          make bench_integer_compression_gpu
-
-      - name: Parse results
-        run: |
-          python3 ./ci/benchmark_parser.py target/criterion ${{ env.RESULTS_FILENAME }} \
-          --database tfhe_rs \
-          --hardware "n3-H100x1" \
-          --backend gpu \
-          --project-version "${{ env.COMMIT_HASH }}" \
-          --branch ${{ github.ref_name }} \
-          --commit-date "${{ env.COMMIT_DATE }}" \
-          --bench-date "${{ env.BENCH_DATE }}" \
-          --walk-subdirs \
-          --name-suffix avx512 \
-          --throughput
-
-      - name: Upload parsed results artifact
-        uses: actions/upload-artifact@50769540e7f4bd5e21e526ee35c689e35e0d6874
-        with:
-          name: ${{ github.sha }}_${{ matrix.command }}_${{ matrix.op_flavor }}
-          path: ${{ env.RESULTS_FILENAME }}
-
-      - name: Send data to Slab
-        shell: bash
-        run: |
-          python3 slab/scripts/data_sender.py ${{ env.RESULTS_FILENAME }} "${{ secrets.JOB_SECRET }}" \
-          --slab-url "${{ secrets.SLAB_URL }}"
-
-  slack-notify:
-    name: Slack Notification
-    needs: [ setup-instance, cuda-integer-full-benchmarks ]
-    runs-on: ubuntu-latest
-    if: ${{ always() && needs.cuda-integer-full-benchmarks.result != 'skipped' && failure() }}
-    continue-on-error: true
-    steps:
-      - name: Send message
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
-        env:
-          SLACK_COLOR: ${{ needs.cuda-integer-full-benchmarks.result }}
-          SLACK_MESSAGE: "Integer GPU full benchmarks finished with status: ${{ needs.cuda-integer-full-benchmarks.result }}. (${{ env.ACTION_RUN_URL }})"
-
-  teardown-instance:
-    name: Teardown instance (cuda-integer-full-benchmarks)
-    if: ${{ always() && needs.setup-instance.result != 'skipped' }}
-    needs: [ setup-instance, cuda-integer-full-benchmarks, slack-notify ]
-    runs-on: ubuntu-latest
-    steps:
-      - name: Stop instance
-        id: stop-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
-        with:
-          mode: stop
-          github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
-          slab-url: ${{ secrets.SLAB_BASE_URL }}
-          job-secret: ${{ secrets.JOB_SECRET }}
-          label: ${{ needs.setup-instance.outputs.runner-name }}
-
-      - name: Slack Notification
-        if: ${{ failure() }}
-        continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
-        env:
-          SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "Instance teardown (cuda-integer-full-benchmarks) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/benchmark_gpu_integer_multi_bit.yml

@@ -1,224 +0,0 @@
-# Run integer benchmarks with multi-bit cryptographic parameters on an instance and return parsed results to Slab CI bot.
-name: Integer GPU Multi-bit benchmarks
-
-on:
-  workflow_dispatch:
-    inputs:
-      all_precisions:
-        description: "Run all precisions"
-        type: boolean
-        default: false
-      fast_default:
-        description: "Run only deduplicated default operations without scalar variants"
-        type: boolean
-        default: false
-
-  schedule:
-    # Weekly benchmarks will be triggered each Saturday at 1a.m.
-    - cron: '0 1 * * 6'
-
-env:
-  CARGO_TERM_COLOR: always
-  RESULTS_FILENAME: parsed_benchmark_results_${{ github.sha }}.json
-  PARSE_INTEGER_BENCH_CSV_FILE: tfhe_rs_integer_benches_${{ github.sha }}.csv
-  ACTION_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
-  RUST_BACKTRACE: "full"
-  RUST_MIN_STACK: "8388608"
-  SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
-  SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
-  SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
-  SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
-  FAST_BENCH: TRUE
-  BENCH_OP_FLAVOR: default
-
-jobs:
-  setup-instance:
-    name: Setup instance (cuda-integer-multi-bit-benchmarks)
-    runs-on: ubuntu-latest
-    if: github.event_name != 'schedule' ||
-      (github.event_name == 'schedule' && github.repository == 'zama-ai/tfhe-rs')
-    outputs:
-      runner-name: ${{ steps.start-instance.outputs.label }}
-    steps:
-      - name: Start instance
-        id: start-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
-        with:
-          mode: start
-          github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
-          slab-url: ${{ secrets.SLAB_BASE_URL }}
-          job-secret: ${{ secrets.JOB_SECRET }}
-          backend: hyperstack
-          profile: single-h100
-
-  cuda-integer-multi-bit-benchmarks:
-    name: Execute GPU integer multi-bit benchmarks
-    needs: setup-instance
-    runs-on: ${{ needs.setup-instance.outputs.runner-name }}
-    timeout-minutes: 1440 # 24 hours
-    strategy:
-      fail-fast: false
-      # explicit include-based build matrix, of known valid options
-      matrix:
-        include:
-          - os: ubuntu-22.04
-            cuda: "12.2"
-            gcc: 11
-    env:
-      CUDA_PATH: /usr/local/cuda-${{ matrix.cuda }}
-      CMAKE_VERSION: 3.29.6
-    steps:
-      # Mandatory on hyperstack since a bootable volume is not re-usable yet.
-      - name: Install dependencies
-        run: |
-          sudo apt update
-          sudo apt install -y checkinstall zlib1g-dev libssl-dev
-          wget https://github.com/Kitware/CMake/releases/download/v${{ env.CMAKE_VERSION }}/cmake-${{ env.CMAKE_VERSION }}.tar.gz
-          tar -zxvf cmake-${{ env.CMAKE_VERSION }}.tar.gz
-          cd cmake-${{ env.CMAKE_VERSION }}
-          ./bootstrap
-          make -j"$(nproc)"
-          sudo make install
-
-      - name: Checkout tfhe-rs repo with tags
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
-        with:
-          fetch-depth: 0
-          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
-
-      - name: Get benchmark details
-        run: |
-          {
-            echo "BENCH_DATE=$(date --iso-8601=seconds)";
-            echo "COMMIT_DATE=$(git --no-pager show -s --format=%cd --date=iso8601-strict ${{ github.sha }})";
-            echo "COMMIT_HASH=$(git describe --tags --dirty)";
-          } >> "${GITHUB_ENV}"
-
-      - name: Set up home
-        # "Install rust" step require root user to have a HOME directory which is not set.
-        run: |
-          echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
-
-      - name: Install rust
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
-        with:
-          toolchain: nightly
-
-      - name: Export CUDA variables
-        if: ${{ !cancelled() }}
-        run: |
-          {
-            echo "CUDA_PATH=$CUDA_PATH";
-            echo "LD_LIBRARY_PATH=$CUDA_PATH/lib:$LD_LIBRARY_PATH";
-            echo "CUDACXX=/usr/local/cuda-${{ matrix.cuda }}/bin/nvcc";
-          } >> "${GITHUB_ENV}"
-          echo "$CUDA_PATH/bin" >> "${GITHUB_PATH}"
-
-      # Specify the correct host compilers
-      - name: Export gcc and g++ variables
-        if: ${{ !cancelled() }}
-        run: |
-          {
-            echo "CC=/usr/bin/gcc-${{ matrix.gcc }}";
-            echo "CXX=/usr/bin/g++-${{ matrix.gcc }}";
-            echo "CUDAHOSTCXX=/usr/bin/g++-${{ matrix.gcc }}";
-          } >> "${GITHUB_ENV}"
-
-      - name: Should run benchmarks with all precisions
-        if: inputs.all_precisions
-        run: |
-          echo "FAST_BENCH=FALSE" >> "${GITHUB_ENV}"
-
-      - name: Should run fast subset benchmarks
-        if: inputs.fast_default
-        run: |
-          echo "BENCH_OP_FLAVOR=fast_default" >> "${GITHUB_ENV}"
-
-      - name: Check device is detected
-        if: ${{ !cancelled() }}
-        run: nvidia-smi
-
-      - name: Run multi-bit benchmarks with AVX512
-        run: |
-          make bench_unsigned_integer_multi_bit_gpu
-
-      - name: Parse benchmarks to csv
-        run: |
-          make PARSE_INTEGER_BENCH_CSV_FILE=${{ env.PARSE_INTEGER_BENCH_CSV_FILE }} \
-            parse_integer_benches
-
-      - name: Upload csv results artifact
-        uses: actions/upload-artifact@50769540e7f4bd5e21e526ee35c689e35e0d6874
-        with:
-          name: ${{ github.sha }}_csv_integer
-          path: ${{ env.PARSE_INTEGER_BENCH_CSV_FILE }}
-
-      - name: Parse results
-        run: |
-          python3 ./ci/benchmark_parser.py target/criterion ${{ env.RESULTS_FILENAME }} \
-          --database tfhe_rs \
-          --hardware "n3-H100x1" \
-          --backend gpu \
-          --project-version "${{ env.COMMIT_HASH }}" \
-          --branch ${{ github.ref_name }} \
-          --commit-date "${{ env.COMMIT_DATE }}" \
-          --bench-date "${{ env.BENCH_DATE }}" \
-          --walk-subdirs \
-          --name-suffix avx512 \
-          --throughput
-
-      - name: Upload parsed results artifact
-        uses: actions/upload-artifact@50769540e7f4bd5e21e526ee35c689e35e0d6874
-        with:
-          name: ${{ github.sha }}_integer
-          path: ${{ env.RESULTS_FILENAME }}
-
-      - name: Checkout Slab repo
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
-        with:
-          repository: zama-ai/slab
-          path: slab
-          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
-
-      - name: Send data to Slab
-        shell: bash
-        run: |
-          python3 slab/scripts/data_sender.py ${{ env.RESULTS_FILENAME }} "${{ secrets.JOB_SECRET }}" \
-          --slab-url "${{ secrets.SLAB_URL }}"
-
-  slack-notify:
-    name: Slack Notification
-    needs: [ setup-instance, cuda-integer-multi-bit-benchmarks ]
-    runs-on: ubuntu-latest
-    if: ${{ always() && needs.cuda-integer-multi-bit-benchmarks.result != 'skipped' && failure() }}
-    continue-on-error: true
-    steps:
-      - name: Send message
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
-        env:
-          SLACK_COLOR: ${{ needs.cuda-integer-multi-bit-benchmarks.result }}
-          SLACK_MESSAGE: "Integer GPU multi-bit benchmarks finished with status: ${{ needs.cuda-integer-multi-bit-benchmarks.result }}. (${{ env.ACTION_RUN_URL }})"
-
-  teardown-instance:
-    name: Teardown instance (cuda-integer-full-benchmarks)
-    if: ${{ always() && needs.setup-instance.result != 'skipped' }}
-    needs: [ setup-instance, cuda-integer-multi-bit-benchmarks, slack-notify ]
-    runs-on: ubuntu-latest
-    steps:
-      - name: Stop instance
-        id: stop-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
-        with:
-          mode: stop
-          github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
-          slab-url: ${{ secrets.SLAB_BASE_URL }}
-          job-secret: ${{ secrets.JOB_SECRET }}
-          label: ${{ needs.setup-instance.outputs.runner-name }}
-
-      - name: Slack Notification
-        if: ${{ failure() }}
-        continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
-        env:
-          SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "Instance teardown (cuda-integer-multi-bit-benchmarks) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/benchmark_gpu_integer_multi_gpu_full.yml

@@ -1,194 +0,0 @@
-# Run all integer benchmarks on an instance with CUDA and return parsed results to Slab CI bot.
-name: Integer multi GPU full benchmarks
-
-on:
-  workflow_dispatch:
-  schedule:
-    # Weekly benchmarks will be triggered each Saturday at 1a.m.
-    - cron: '0 1 * * 6'
-
-env:
-  CARGO_TERM_COLOR: always
-  RESULTS_FILENAME: parsed_benchmark_results_${{ github.sha }}.json
-  ACTION_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
-  RUST_BACKTRACE: "full"
-  RUST_MIN_STACK: "8388608"
-  SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
-  SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
-  SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
-  SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
-
-jobs:
-  setup-instance:
-    name: Setup instance (cuda-integer-full-multi-gpu-benchmarks)
-    runs-on: ubuntu-latest
-    if: github.event_name != 'schedule' ||
-      (github.event_name == 'schedule' && github.repository == 'zama-ai/tfhe-rs')
-    outputs:
-      runner-name: ${{ steps.start-instance.outputs.label }}
-    steps:
-      - name: Start instance
-        id: start-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
-        with:
-          mode: start
-          github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
-          slab-url: ${{ secrets.SLAB_BASE_URL }}
-          job-secret: ${{ secrets.JOB_SECRET }}
-          backend: hyperstack
-          profile: multi-h100
-
-  cuda-integer-full-multi-gpu-benchmarks:
-    name: Execute multi GPU integer benchmarks
-    needs: setup-instance
-    runs-on: ${{ needs.setup-instance.outputs.runner-name }}
-    timeout-minutes: 1440 # 24 hours
-    continue-on-error: true
-    strategy:
-      fail-fast: false
-      max-parallel: 1
-      matrix:
-        command: [integer_multi_bit]
-        op_flavor: [default]
-        # explicit include-based build matrix, of known valid options
-        include:
-          - os: ubuntu-22.04
-            cuda: "12.2"
-            gcc: 11
-    env:
-      CUDA_PATH: /usr/local/cuda-${{ matrix.cuda }}
-      CMAKE_VERSION: 3.29.6
-    steps:
-      # Mandatory on hyperstack since a bootable volume is not re-usable yet.
-      - name: Install dependencies
-        run: |
-          sudo apt update
-          sudo apt install -y checkinstall zlib1g-dev libssl-dev
-          wget https://github.com/Kitware/CMake/releases/download/v${{ env.CMAKE_VERSION }}/cmake-${{ env.CMAKE_VERSION }}.tar.gz
-          tar -zxvf cmake-${{ env.CMAKE_VERSION }}.tar.gz
-          cd cmake-${{ env.CMAKE_VERSION }}
-          ./bootstrap
-          make -j"$(nproc)"
-          sudo make install
-
-      - name: Checkout tfhe-rs repo with tags
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
-        with:
-          fetch-depth: 0
-          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
-
-      - name: Get benchmark details
-        run: |
-          {
-            echo "BENCH_DATE=$(date --iso-8601=seconds)";
-            echo "COMMIT_DATE=$(git --no-pager show -s --format=%cd --date=iso8601-strict ${{ github.sha }})";
-            echo "COMMIT_HASH=$(git describe --tags --dirty)";
-          } >> "${GITHUB_ENV}"
-
-      - name: Set up home
-        # "Install rust" step require root user to have a HOME directory which is not set.
-        run: |
-          echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
-
-      - name: Install rust
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
-        with:
-          toolchain: nightly
-
-      - name: Export CUDA variables
-        if: ${{ !cancelled() }}
-        run: |
-          {
-            echo "CUDA_PATH=$CUDA_PATH";
-            echo "LD_LIBRARY_PATH=$CUDA_PATH/lib:$LD_LIBRARY_PATH";
-            echo "CUDACXX=/usr/local/cuda-${{ matrix.cuda }}/bin/nvcc";
-          } >> "${GITHUB_ENV}"
-          echo "$CUDA_PATH/bin" >> "${GITHUB_PATH}"
-
-      # Specify the correct host compilers
-      - name: Export gcc and g++ variables
-        if: ${{ !cancelled() }}
-        run: |
-          {
-            echo "CC=/usr/bin/gcc-${{ matrix.gcc }}";
-            echo "CXX=/usr/bin/g++-${{ matrix.gcc }}";
-            echo "CUDAHOSTCXX=/usr/bin/g++-${{ matrix.gcc }}";
-          } >> "${GITHUB_ENV}"
-
-      - name: Checkout Slab repo
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
-        with:
-          repository: zama-ai/slab
-          path: slab
-          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
-
-      - name: Check device is detected
-        if: ${{ !cancelled() }}
-        run: nvidia-smi
-
-      - name: Run benchmarks with AVX512
-        run: |
-          make BENCH_OP_FLAVOR=${{ matrix.op_flavor }} bench_${{ matrix.command }}_gpu
-
-      - name: Parse results
-        run: |
-          python3 ./ci/benchmark_parser.py target/criterion ${{ env.RESULTS_FILENAME }} \
-          --database tfhe_rs \
-          --hardware "n3-H100x8" \
-          --backend gpu \
-          --project-version "${{ env.COMMIT_HASH }}" \
-          --branch ${{ github.ref_name }} \
-          --commit-date "${{ env.COMMIT_DATE }}" \
-          --bench-date "${{ env.BENCH_DATE }}" \
-          --walk-subdirs \
-          --name-suffix avx512 \
-          --throughput
-
-      - name: Upload parsed results artifact
-        uses: actions/upload-artifact@50769540e7f4bd5e21e526ee35c689e35e0d6874
-        with:
-          name: ${{ github.sha }}_${{ matrix.command }}_${{ matrix.op_flavor }}
-          path: ${{ env.RESULTS_FILENAME }}
-
-      - name: Send data to Slab
-        shell: bash
-        run: |
-          python3 slab/scripts/data_sender.py ${{ env.RESULTS_FILENAME }} "${{ secrets.JOB_SECRET }}" \
-          --slab-url "${{ secrets.SLAB_URL }}"
-
-  slack-notify:
-    name: Slack Notification
-    needs: [ setup-instance, cuda-integer-full-multi-gpu-benchmarks ]
-    runs-on: ubuntu-latest
-    if: ${{ always() && needs.cuda-integer-full-multi-gpu-benchmarks.result != 'skipped' && failure() }}
-    continue-on-error: true
-    steps:
-      - name: Send message
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
-        env:
-          SLACK_COLOR: ${{ needs.cuda-integer-full-multi-gpu-benchmarks.result }}
-          SLACK_MESSAGE: "Integer GPU full benchmarks finished with status: ${{ needs.cuda-integer-full-multi-gpu-benchmarks.result }}. (${{ env.ACTION_RUN_URL }})"
-
-  teardown-instance:
-    name: Teardown instance (cuda-integer-full-multi-gpu-benchmarks)
-    if: ${{ always() && needs.setup-instance.result != 'skipped' }}
-    needs: [ setup-instance, cuda-integer-full-multi-gpu-benchmarks ]
-    runs-on: ubuntu-latest
-    steps:
-      - name: Stop instance
-        id: stop-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
-        with:
-          mode: stop
-          github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
-          slab-url: ${{ secrets.SLAB_BASE_URL }}
-          job-secret: ${{ secrets.JOB_SECRET }}
-          label: ${{ needs.setup-instance.outputs.runner-name }}
-
-      - name: Slack Notification
-        if: ${{ failure() }}
-        continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
-        env:
-          SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "Instance teardown (cuda-integer-full-multi-gpu-benchmarks) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/benchmark_gpu_integer_weekly.yml

@@ -0,0 +1,60 @@
+# Run CUDA benchmarks on multiple Hyperstack VMs and return parsed results to Slab CI bot.
+name: Cuda weekly benchmarks
+
+on:
+  schedule:
+    # Weekly benchmarks will be triggered each Saturday at 1a.m.
+    - cron: '0 1 * * 6'
+
+jobs:
+  run-benchmarks-1-h100:
+    name: Run benchmarks (1xH100)
+    if: github.repository == 'zama-ai/tfhe-rs'
+    uses: ./.github/workflows/benchmark_gpu_integer_common.yml
+    with:
+      profile: single-h100
+      hardware_name: n3-H100x1
+      command: integer,integer_multi_bit
+      op_flavor: default
+      bench_type: latency
+      all_precisions: true
+    secrets: inherit
+
+  run-benchmarks-2-h100:
+    name: Run benchmarks (2xH100)
+    if: github.repository == 'zama-ai/tfhe-rs'
+    uses: ./.github/workflows/benchmark_gpu_integer_common.yml
+    with:
+      profile: 2-h100
+      hardware_name: n3-H100x2
+      command: integer_multi_bit
+      op_flavor: default
+      bench_type: latency
+      all_precisions: true
+    secrets: inherit
+
+  run-benchmarks-8-h100:
+    name: Run benchmarks (8xH100)
+    if: github.repository == 'zama-ai/tfhe-rs'
+    uses: ./.github/workflows/benchmark_gpu_integer_common.yml
+    with:
+      profile: multi-h100
+      hardware_name: n3-H100x8
+      command: integer_multi_bit
+      op_flavor: default
+      bench_type: latency
+      all_precisions: true
+    secrets: inherit
+
+  run-benchmarks-l40:
+    name: Run benchmarks (L40)
+    if: github.repository == 'zama-ai/tfhe-rs'
+    uses: ./.github/workflows/benchmark_gpu_integer_common.yml
+    with:
+      profile: l40
+      hardware_name: n3-L40x1
+      command: integer_multi_bit,integer_compression,pbs,ks
+      op_flavor: default
+      bench_type: latency
+      all_precisions: true
+    secrets: inherit

.github/workflows/benchmark_gpu_l40.yml

@@ -1,206 +0,0 @@
-# Run benchmarks on an L40 VM and return parsed results to Slab CI bot.
-name: Cuda benchmarks (L40)
-
-on:
-  workflow_dispatch:
-  schedule:
-    # Weekly benchmarks will be triggered each Saturday at 1a.m.
-    - cron: '0 1 * * 6'
-
-env:
-  CARGO_TERM_COLOR: always
-  RESULTS_FILENAME: parsed_benchmark_results_${{ github.sha }}.json
-  ACTION_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
-  RUST_BACKTRACE: "full"
-  RUST_MIN_STACK: "8388608"
-  SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
-  SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
-  SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
-  SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
-
-jobs:
-  setup-instance:
-    name: Setup instance (cuda-l40-benchmarks)
-    runs-on: ubuntu-latest
-    if: github.event_name != 'schedule' ||
-      (github.event_name == 'schedule' && github.repository == 'zama-ai/tfhe-rs')
-    outputs:
-      runner-name: ${{ steps.start-instance.outputs.label }}
-    steps:
-      - name: Start instance
-        id: start-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
-        with:
-          mode: start
-          github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
-          slab-url: ${{ secrets.SLAB_BASE_URL }}
-          job-secret: ${{ secrets.JOB_SECRET }}
-          backend: hyperstack
-          profile: l40 
-
-  cuda-l40-benchmarks:
-    name: Cuda benchmarks (L40)
-    needs: setup-instance
-    runs-on: ${{ needs.setup-instance.outputs.runner-name }}
-    timeout-minutes: 1440 # 24 hours
-    continue-on-error: true
-    strategy:
-      fail-fast: false
-      max-parallel: 1
-      matrix:
-        command: [integer_multi_bit]
-        op_flavor: [default]
-        # explicit include-based build matrix, of known valid options
-        include:
-          - os: ubuntu-22.04
-            cuda: "12.2"
-            gcc: 11
-    env:
-      CUDA_PATH: /usr/local/cuda-${{ matrix.cuda }}
-      CMAKE_VERSION: 3.29.6
-    steps:
-      # Mandatory on hyperstack since a bootable volume is not re-usable yet.
-      - name: Install dependencies
-        run: |
-          sudo apt update
-          sudo apt install -y checkinstall zlib1g-dev libssl-dev
-          wget https://github.com/Kitware/CMake/releases/download/v${{ env.CMAKE_VERSION }}/cmake-${{ env.CMAKE_VERSION }}.tar.gz
-          tar -zxvf cmake-${{ env.CMAKE_VERSION }}.tar.gz
-          cd cmake-${{ env.CMAKE_VERSION }}
-          ./bootstrap
-          make -j"$(nproc)"
-          sudo make install
-
-      - name: Checkout tfhe-rs repo with tags
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
-        with:
-          fetch-depth: 0
-          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
-
-      - name: Get benchmark details
-        run: |
-          {
-            echo "BENCH_DATE=$(date --iso-8601=seconds)";
-            echo "COMMIT_DATE=$(git --no-pager show -s --format=%cd --date=iso8601-strict ${{ github.sha }})";
-            echo "COMMIT_HASH=$(git describe --tags --dirty)";
-          } >> "${GITHUB_ENV}"
-
-      - name: Set up home
-        # "Install rust" step require root user to have a HOME directory which is not set.
-        run: |
-          echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
-
-      - name: Install rust
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
-        with:
-          toolchain: nightly
-
-      - name: Export CUDA variables
-        if: ${{ !cancelled() }}
-        run: |
-          {
-            echo "CUDA_PATH=$CUDA_PATH";
-            echo "LD_LIBRARY_PATH=$CUDA_PATH/lib:$LD_LIBRARY_PATH";
-            echo "CUDACXX=/usr/local/cuda-${{ matrix.cuda }}/bin/nvcc";
-          } >> "${GITHUB_ENV}"
-          echo "$CUDA_PATH/bin" >> "${GITHUB_PATH}"
-
-      # Specify the correct host compilers
-      - name: Export gcc and g++ variables
-        if: ${{ !cancelled() }}
-        run: |
-          {
-            echo "CC=/usr/bin/gcc-${{ matrix.gcc }}";
-            echo "CXX=/usr/bin/g++-${{ matrix.gcc }}";
-            echo "CUDAHOSTCXX=/usr/bin/g++-${{ matrix.gcc }}";
-          } >> "${GITHUB_ENV}"
-
-      - name: Checkout Slab repo
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
-        with:
-          repository: zama-ai/slab
-          path: slab
-          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
-
-      - name: Check device is detected
-        if: ${{ !cancelled() }}
-        run: nvidia-smi
-
-      - name: Run benchmarks with AVX512
-        run: |
-          make BENCH_OP_FLAVOR=${{ matrix.op_flavor }} bench_${{ matrix.command }}_gpu
-
-      - name: Run compression benchmarks with AVX512
-        run: |
-          make bench_integer_compression_gpu
-
-      - name: Run PBS benchmarks 
-        run: |
-          make bench_pbs_gpu
-
-      - name: Run KS benchmarks 
-        run: |
-          make bench_ks_gpu
-
-      - name: Parse results
-        run: |
-          python3 ./ci/benchmark_parser.py target/criterion ${{ env.RESULTS_FILENAME }} \
-          --database tfhe_rs \
-          --hardware "n3-L40x1" \
-          --backend gpu \
-          --project-version "${{ env.COMMIT_HASH }}" \
-          --branch ${{ github.ref_name }} \
-          --commit-date "${{ env.COMMIT_DATE }}" \
-          --bench-date "${{ env.BENCH_DATE }}" \
-          --walk-subdirs \
-          --name-suffix avx512 \
-          --throughput
-
-      - name: Upload parsed results artifact
-        uses: actions/upload-artifact@50769540e7f4bd5e21e526ee35c689e35e0d6874
-        with:
-          name: ${{ github.sha }}_${{ matrix.command }}_${{ matrix.op_flavor }}
-          path: ${{ env.RESULTS_FILENAME }}
-
-      - name: Send data to Slab
-        shell: bash
-        run: |
-          python3 slab/scripts/data_sender.py ${{ env.RESULTS_FILENAME }} "${{ secrets.JOB_SECRET }}" \
-          --slab-url "${{ secrets.SLAB_URL }}"
-
-  slack-notify:
-    name: Slack Notification
-    needs: [ setup-instance, cuda-l40-benchmarks ]
-    runs-on: ubuntu-latest
-    if: ${{ always() && needs.cuda-l40-benchmarks.result != 'skipped' && failure() }}
-    continue-on-error: true
-    steps:
-      - name: Send message
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
-        env:
-          SLACK_COLOR: ${{ needs.cuda-l40-benchmarks.result }}
-          SLACK_MESSAGE: "Cuda benchmarks (L40) finished with status: ${{ needs.cuda-l40-benchmarks.result }}. (${{ env.ACTION_RUN_URL }})"
-
-  teardown-instance:
-    name: Teardown instance (cuda-l40-benchmarks)
-    if: ${{ always() && needs.setup-instance.result != 'skipped' }}
-    needs: [ setup-instance, cuda-l40-benchmarks, slack-notify ]
-    runs-on: ubuntu-latest
-    steps:
-      - name: Stop instance
-        id: stop-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
-        with:
-          mode: stop
-          github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
-          slab-url: ${{ secrets.SLAB_BASE_URL }}
-          job-secret: ${{ secrets.JOB_SECRET }}
-          label: ${{ needs.setup-instance.outputs.runner-name }}
-
-      - name: Slack Notification
-        if: ${{ failure() }}
-        continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
-        env:
-          SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "Instance teardown (cuda-l40-benchmarks) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/benchmark_integer.yml

@@ -8,6 +8,14 @@ on:
         description: "Run all precisions"
         type: boolean
         default: false
+      bench_type:
+        description: "Benchmarks type"
+        type: choice
+        default: latency
+        options:
+          - latency
+          - throughput
+          - both
 
   schedule:
     # Weekly benchmarks will be triggered each Saturday at 1a.m.
@@ -36,10 +44,10 @@ jobs:
       (github.event_name == 'schedule' && github.repository == 'zama-ai/tfhe-rs')
     outputs:
       op_flavor: ${{ steps.set_op_flavor.outputs.op_flavor }}
+      bench_type: ${{ steps.set_bench_type.outputs.bench_type }}
     steps:
       - name: Weekly benchmarks
-        if: github.event_name == 'workflow_dispatch' ||
-          github.event.schedule == '0 1 * * 6'
+        if: github.event.schedule == '0 1 * * 6'
         run: |
           echo "OP_FLAVOR=[\"default\"]" >> "${GITHUB_ENV}"
 
@@ -48,11 +56,31 @@ jobs:
         run: |
           echo "OP_FLAVOR=[\"default\", \"smart\", \"unchecked\", \"misc\"]" >> "${GITHUB_ENV}"
 
-      -  name: Set operation flavor output
-         id: set_op_flavor
-         run: |
+      - name: Set benchmark types
+        if: github.event_name == 'workflow_dispatch'
+        run: |
+          echo "OP_FLAVOR=[\"default\"]" >> "${GITHUB_ENV}"
+          if [[ "${{ inputs.bench_type }}" == "both" ]]; then
+            echo "BENCH_TYPE=[\"latency\", \"throughput\"]" >> "${GITHUB_ENV}"
+          else
+            echo "BENCH_TYPE=[\"${{ inputs.bench_type }}\"]" >> "${GITHUB_ENV}"
+          fi
+
+      - name: Default benchmark type
+        if: github.event_name != 'workflow_dispatch'
+        run: |
+          echo "BENCH_TYPE=[\"latency\"]" >> "${GITHUB_ENV}"
+
+      - name: Set operation flavor output
+        id: set_op_flavor
+        run: |
           echo "op_flavor=${{ toJSON(env.OP_FLAVOR) }}" >> "${GITHUB_OUTPUT}"
 
+      - name: Set benchmark types output
+        id: set_bench_type
+        run: |
+          echo "bench_type=${{ toJSON(env.BENCH_TYPE) }}" >> "${GITHUB_OUTPUT}"
+
   setup-instance:
     name: Setup instance (integer-benchmarks)
     needs: prepare-matrix
@@ -62,7 +90,7 @@ jobs:
     steps:
       - name: Start instance
         id: start-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: start
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -85,9 +113,10 @@ jobs:
       matrix:
         command: [ integer, integer_multi_bit]
         op_flavor: ${{ fromJson(needs.prepare-matrix.outputs.op_flavor) }}
+        bench_type: ${{ fromJSON(needs.prepare-matrix.outputs.bench_type) }}
     steps:
       - name: Checkout tfhe-rs repo with tags
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
           token: ${{ secrets.FHE_ACTIONS_TOKEN }}
@@ -100,18 +129,13 @@ jobs:
             echo "COMMIT_HASH=$(git describe --tags --dirty)";
           } >> "${GITHUB_ENV}"
 
-      - name: Set up home
-        # "Install rust" step require root user to have a HOME directory which is not set.
-        run: |
-          echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
-
       - name: Install rust
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: nightly
 
       - name: Checkout Slab repo
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           repository: zama-ai/slab
           path: slab
@@ -124,13 +148,13 @@ jobs:
 
       - name: Run benchmarks with AVX512
         run: |
-          make BENCH_OP_FLAVOR=${{ matrix.op_flavor }} bench_${{ matrix.command }}
+          make BENCH_OP_FLAVOR=${{ matrix.op_flavor }} BENCH_TYPE=${{ matrix.bench_type }} bench_${{ matrix.command }}
 
-      # Run these benchmarks only once
+      # Run these benchmarks only once per benchmark type
       - name: Run compression benchmarks with AVX512
         if: matrix.op_flavor == 'default' && matrix.command == 'integer'
         run: |
-          make bench_integer_compression
+          make BENCH_TYPE=${{ matrix.bench_type }} bench_integer_compression
 
       - name: Parse results
         run: |
@@ -143,12 +167,12 @@ jobs:
           --bench-date "${{ env.BENCH_DATE }}" \
           --walk-subdirs \
           --name-suffix avx512 \
-          --throughput
+          --bench-type ${{ matrix.bench_type }}
 
       - name: Upload parsed results artifact
-        uses: actions/upload-artifact@50769540e7f4bd5e21e526ee35c689e35e0d6874
+        uses: actions/upload-artifact@b4b15b8c7c6ac21ea08fcf65892d2ee8f75cf882
         with:
-          name: ${{ github.sha }}_${{ matrix.command }}_${{ matrix.op_flavor }}
+          name: ${{ github.sha }}_${{ matrix.command }}_${{ matrix.op_flavor }}_${{ matrix.bench_type }}
           path: ${{ env.RESULTS_FILENAME }}
 
       - name: Send data to Slab
@@ -160,7 +184,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Integer full benchmarks finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
@@ -173,7 +197,7 @@ jobs:
     steps:
       - name: Stop instance
         id: stop-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: stop
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -184,7 +208,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Instance teardown (integer-benchmarks) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/benchmark_shortint.yml

@@ -56,7 +56,7 @@ jobs:
     steps:
       - name: Start instance
         id: start-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: start
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -79,7 +79,7 @@ jobs:
         op_flavor: ${{ fromJson(needs.prepare-matrix.outputs.op_flavor) }}
     steps:
       - name: Checkout tfhe-rs repo with tags
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
           token: ${{ secrets.FHE_ACTIONS_TOKEN }}
@@ -92,18 +92,13 @@ jobs:
             echo "COMMIT_HASH=$(git describe --tags --dirty)";
           } >> "${GITHUB_ENV}"
 
-      - name: Set up home
-        # "Install rust" step require root user to have a HOME directory which is not set.
-        run: |
-          echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
-
       - name: Install rust
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: nightly
 
       - name: Checkout Slab repo
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           repository: zama-ai/slab
           path: slab
@@ -125,8 +120,7 @@ jobs:
           --commit-date "${COMMIT_DATE}" \
           --bench-date "${{ env.BENCH_DATE }}" \
           --walk-subdirs \
-          --name-suffix avx512 \
-          --throughput
+          --name-suffix avx512
 
       # This small benchmark needs to be executed only once.
       - name: Measure key sizes
@@ -138,11 +132,11 @@ jobs:
         if: matrix.op_flavor == 'default'
         run: |
           python3 ./ci/benchmark_parser.py tfhe/shortint_key_sizes.csv ${{ env.RESULTS_FILENAME }} \
-          --key-sizes \
+          --object-sizes \
           --append-results
 
       - name: Upload parsed results artifact
-        uses: actions/upload-artifact@50769540e7f4bd5e21e526ee35c689e35e0d6874
+        uses: actions/upload-artifact@b4b15b8c7c6ac21ea08fcf65892d2ee8f75cf882
         with:
           name: ${{ github.sha }}_shortint_${{ matrix.op_flavor }}
           path: ${{ env.RESULTS_FILENAME }}
@@ -156,7 +150,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Shortint full benchmarks finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
@@ -169,7 +163,7 @@ jobs:
     steps:
       - name: Stop instance
         id: stop-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: stop
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -180,7 +174,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Instance teardown (shortint-benchmarks) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/benchmark_signed_integer.yml

@@ -8,6 +8,14 @@ on:
         description: "Run all precisions"
         type: boolean
         default: false
+      bench_type:
+        description: "Benchmarks type"
+        type: choice
+        default: latency
+        options:
+          - latency
+          - throughput
+          - both
 
   schedule:
     # Weekly benchmarks will be triggered each Saturday at 1a.m.
@@ -36,10 +44,10 @@ jobs:
       (github.event_name == 'schedule' && github.repository == 'zama-ai/tfhe-rs')
     outputs:
       op_flavor: ${{ steps.set_op_flavor.outputs.op_flavor }}
+      bench_type: ${{ steps.set_bench_type.outputs.bench_type }}
     steps:
       - name: Weekly benchmarks
-        if: github.event_name == 'workflow_dispatch' ||
-          github.event.schedule == '0 1 * * 6'
+        if: github.event.schedule == '0 1 * * 6'
         run: |
           echo "OP_FLAVOR=[\"default\"]" >> "${GITHUB_ENV}"
 
@@ -48,11 +56,31 @@ jobs:
         run: |
           echo "OP_FLAVOR=[\"default\", \"unchecked\"]" >> "${GITHUB_ENV}"
 
+      - name: Set benchmark types
+        if: github.event_name == 'workflow_dispatch'
+        run: |
+          echo "OP_FLAVOR=[\"default\"]" >> "${GITHUB_ENV}"
+          if [[ "${{ inputs.bench_type }}" == "both" ]]; then
+            echo "BENCH_TYPE=[\"latency\", \"throughput\"]" >> "${GITHUB_ENV}"
+          else
+            echo "BENCH_TYPE=[\"${{ inputs.bench_type }}\"]" >> "${GITHUB_ENV}"
+          fi
+
+      - name: Default benchmark type
+        if: github.event_name != 'workflow_dispatch'
+        run: |
+          echo "BENCH_TYPE=[\"latency\"]" >> "${GITHUB_ENV}"
+
       - name: Set operation flavor output
         id: set_op_flavor
         run: |
           echo "op_flavor=${{ toJSON(env.OP_FLAVOR) }}" >> "${GITHUB_OUTPUT}"
 
+      - name: Set benchmark types output
+        id: set_bench_type
+        run: |
+          echo "bench_type=${{ toJSON(env.BENCH_TYPE) }}" >> "${GITHUB_OUTPUT}"
+
   setup-instance:
     name: Setup instance (signed-integer-benchmarks)
     needs: prepare-matrix
@@ -62,7 +90,7 @@ jobs:
     steps:
       - name: Start instance
         id: start-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: start
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -84,10 +112,11 @@ jobs:
       max-parallel: 1
       matrix:
         command: [ integer, integer_multi_bit ]
-        op_flavor: [ default, unchecked ]
+        op_flavor: ${{ fromJSON(needs.prepare-matrix.outputs.op_flavor) }}
+        bench_type: ${{ fromJSON(needs.prepare-matrix.outputs.bench_type) }}
     steps:
       - name: Checkout tfhe-rs repo with tags
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
           token: ${{ secrets.FHE_ACTIONS_TOKEN }}
@@ -100,18 +129,13 @@ jobs:
             echo "COMMIT_HASH=$(git describe --tags --dirty)";
           } >> "${GITHUB_ENV}"
 
-      - name: Set up home
-        # "Install rust" step require root user to have a HOME directory which is not set.
-        run: |
-          echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
-
       - name: Install rust
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: nightly
 
       - name: Checkout Slab repo
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           repository: zama-ai/slab
           path: slab
@@ -124,7 +148,7 @@ jobs:
 
       - name: Run benchmarks with AVX512
         run: |
-          make BENCH_OP_FLAVOR=${{ matrix.op_flavor }} bench_signed_${{ matrix.command }}
+          make BENCH_OP_FLAVOR=${{ matrix.op_flavor }} BENCH_TYPE=${{ matrix.bench_type }} bench_signed_${{ matrix.command }}
 
       - name: Parse results
         run: |
@@ -137,12 +161,12 @@ jobs:
           --bench-date "${{ env.BENCH_DATE }}" \
           --walk-subdirs \
           --name-suffix avx512 \
-          --throughput
+          --bench-type ${{ matrix.bench_type }}
 
       - name: Upload parsed results artifact
-        uses: actions/upload-artifact@50769540e7f4bd5e21e526ee35c689e35e0d6874
+        uses: actions/upload-artifact@b4b15b8c7c6ac21ea08fcf65892d2ee8f75cf882
         with:
-          name: ${{ github.sha }}_${{ matrix.command }}_${{ matrix.op_flavor }}
+          name: ${{ github.sha }}_${{ matrix.command }}_${{ matrix.op_flavor }}_${{ matrix.bench_type }}
           path: ${{ env.RESULTS_FILENAME }}
 
       - name: Send data to Slab
@@ -154,7 +178,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Signed integer full benchmarks finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
@@ -167,7 +191,7 @@ jobs:
     steps:
       - name: Stop instance
         id: stop-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: stop
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -178,7 +202,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Instance teardown (signed-integer-benchmarks) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/benchmark_tfhe_fft.yml

@@ -0,0 +1,143 @@
+# Run FFT benchmarks on an AWS instance and return parsed results to Slab CI bot.
+name: FFT benchmarks
+
+env:
+  CARGO_TERM_COLOR: always
+  ACTION_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
+  RESULTS_FILENAME: parsed_benchmark_results_${{ github.sha }}.json
+  RUST_BACKTRACE: "full"
+  SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
+  SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
+  SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
+  SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+
+on:
+  workflow_dispatch:
+  push:
+    branches:
+      - "main"
+    paths:
+      - tfhe-fft/**
+      - .github/workflows/benchmark_tfhe_fft.yml
+  schedule:
+    # Job will be triggered each Thursday at 11p.m.
+    - cron: '0 23 * * 4'
+
+jobs:
+  setup-ec2:
+    name: Setup EC2 instance (fft-benchmarks)
+    runs-on: ubuntu-latest
+    outputs:
+      runner-name: ${{ steps.start-instance.outputs.label }}
+    steps:
+      - name: Start instance
+        id: start-instance
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
+        with:
+          mode: start
+          github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
+          slab-url: ${{ secrets.SLAB_BASE_URL }}
+          job-secret: ${{ secrets.JOB_SECRET }}
+          backend: aws
+          profile: bench
+
+  fft-benchmarks:
+    name: Execute FFT benchmarks in EC2
+    needs: setup-ec2
+    concurrency:
+      group: ${{ github.workflow }}_${{ github.ref }}
+      cancel-in-progress: true
+    runs-on: ${{ needs.setup-ec2.outputs.runner-name }}
+    steps:
+      - name: Checkout tfhe-rs repo with tags
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          fetch-depth: 0
+
+      - name: Get benchmark details
+        run: |
+          {
+            echo "BENCH_DATE=$(date --iso-8601=seconds)";
+            echo "COMMIT_DATE=$(git --no-pager show -s --format=%cd --date=iso8601-strict ${{ github.sha }})";
+            echo "COMMIT_HASH=$(git describe --tags --dirty)";
+          } >> "${GITHUB_ENV}"
+
+      - name: Install rust
+        uses: actions-rs/toolchain@16499b5e05bf2e26879000db0c1d13f7e13fa3af
+        with:
+          toolchain: nightly
+          override: true
+
+      - name: Run benchmarks with AVX512
+        run: |
+          make bench_fft
+
+      - name: Parse AVX512 results
+        run: |
+          python3 ./ci/fft_benchmark_parser.py target/criterion ${{ env.RESULTS_FILENAME }} \
+          --database concrete_fft \
+          --hardware "hpc7a.96xlarge" \
+          --project-version "${{ env.COMMIT_HASH }}" \
+          --branch ${{ github.ref_name }} \
+          --commit-date "${{ env.COMMIT_DATE }}" \
+          --bench-date "${{ env.BENCH_DATE }}" \
+          --name-suffix avx512
+
+      - name: Upload parsed results artifact
+        uses: actions/upload-artifact@b4b15b8c7c6ac21ea08fcf65892d2ee8f75cf882
+        with:
+          name: ${{ github.sha }}_fft
+          path: ${{ env.RESULTS_FILENAME }}
+
+      - name: Checkout Slab repo
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          repository: zama-ai/slab
+          path: slab
+          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
+
+      - name: Send data to Slab
+        shell: bash
+        run: |
+          echo "Computing HMac on downloaded artifact"
+          SIGNATURE="$(slab/scripts/hmac_calculator.sh ${{ env.RESULTS_FILENAME }} '${{ secrets.JOB_SECRET }}')"
+          echo "Sending results to Slab..."
+          curl -v -k \
+          -H "Content-Type: application/json" \
+          -H "X-Slab-Repository: ${{ github.repository }}" \
+          -H "X-Slab-Command: store_data_v2" \
+          -H "X-Hub-Signature-256: sha256=${SIGNATURE}" \
+          -d @${{ env.RESULTS_FILENAME }} \
+          ${{ secrets.SLAB_URL }}
+
+      - name: Slack Notification
+        if: ${{ failure() }}
+        continue-on-error: true
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        env:
+          SLACK_COLOR: ${{ job.status }}
+          SLACK_MESSAGE: "tfhe-fft benchmarks failed. (${{ env.ACTION_RUN_URL }})"
+
+  teardown-ec2:
+    name: Teardown EC2 instance (fft-benchmarks)
+    if: ${{ always() && needs.setup-ec2.result != 'skipped' }}
+    needs: [ setup-ec2, fft-benchmarks ]
+    runs-on: ubuntu-latest
+    steps:
+      - name: Stop instance
+        id: stop-instance
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
+        with:
+          mode: stop
+          github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
+          slab-url: ${{ secrets.SLAB_BASE_URL }}
+          job-secret: ${{ secrets.JOB_SECRET }}
+          label: ${{ needs.setup-ec2.outputs.runner-name }}
+
+      - name: Slack Notification
+        if: ${{ failure() }}
+        continue-on-error: true
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        env:
+          SLACK_COLOR: ${{ job.status }}
+          SLACK_MESSAGE: "EC2 teardown (fft-benchmarks) failed. (${{ env.ACTION_RUN_URL }})"

.github/workflows/benchmark_tfhe_ntt.yml

@@ -0,0 +1,143 @@
+# Run NTT benchmarks on an AWS instance and return parsed results to Slab CI bot.
+name: NTT benchmarks
+
+env:
+  CARGO_TERM_COLOR: always
+  ACTION_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
+  RESULTS_FILENAME: parsed_benchmark_results_${{ github.sha }}.json
+  RUST_BACKTRACE: "full"
+  SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
+  SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
+  SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
+  SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+
+on:
+  workflow_dispatch:
+  push:
+    branches:
+      - "main"
+    paths:
+      - tfhe-ntt/**
+      - .github/workflows/benchmark_tfhe_ntt.yml
+  schedule:
+    # Job will be triggered each Friday at 11p.m.
+    - cron: "0 23 * * 5"
+
+jobs:
+  setup-ec2:
+    name: Setup EC2 instance (ntt-benchmarks)
+    runs-on: ubuntu-latest
+    outputs:
+      runner-name: ${{ steps.start-instance.outputs.label }}
+    steps:
+      - name: Start instance
+        id: start-instance
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
+        with:
+          mode: start
+          github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
+          slab-url: ${{ secrets.SLAB_BASE_URL }}
+          job-secret: ${{ secrets.JOB_SECRET }}
+          backend: aws
+          profile: bench
+
+  ntt-benchmarks:
+    name: Execute NTT benchmarks in EC2
+    needs: setup-ec2
+    concurrency:
+      group: ${{ github.workflow }}_${{ github.ref }}
+      cancel-in-progress: true
+    runs-on: ${{ needs.setup-ec2.outputs.runner-name }}
+    steps:
+      - name: Checkout tfhe-rs repo with tags
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          fetch-depth: 0
+
+      - name: Get benchmark details
+        run: |
+          {
+            echo "BENCH_DATE=$(date --iso-8601=seconds)";
+            echo "COMMIT_DATE=$(git --no-pager show -s --format=%cd --date=iso8601-strict ${{ github.sha }})";
+            echo "COMMIT_HASH=$(git describe --tags --dirty)";
+          } >> "${GITHUB_ENV}"
+
+      - name: Install rust
+        uses: actions-rs/toolchain@16499b5e05bf2e26879000db0c1d13f7e13fa3af
+        with:
+          toolchain: nightly
+          override: true
+
+      - name: Run benchmarks
+        run: |
+          make bench_ntt
+
+      - name: Parse results
+        run: |
+          python3 ./ci/ntt_benchmark_parser.py target/criterion ${{ env.RESULTS_FILENAME }} \
+          --database concrete_ntt \
+          --hardware "hpc7a.96xlarge" \
+          --project-version "${{ env.COMMIT_HASH }}" \
+          --branch ${{ github.ref_name }} \
+          --commit-date "${{ env.COMMIT_DATE }}" \
+          --bench-date "${{ env.BENCH_DATE }}" \
+          --name-suffix avx512
+
+      - name: Upload parsed results artifact
+        uses: actions/upload-artifact@b4b15b8c7c6ac21ea08fcf65892d2ee8f75cf882
+        with:
+          name: ${{ github.sha }}_ntt
+          path: ${{ env.RESULTS_FILENAME }}
+
+      - name: Checkout Slab repo
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          repository: zama-ai/slab
+          path: slab
+          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
+
+      - name: Send data to Slab
+        shell: bash
+        run: |
+          echo "Computing HMac on downloaded artifact"
+          SIGNATURE="$(slab/scripts/hmac_calculator.sh ${{ env.RESULTS_FILENAME }} '${{ secrets.JOB_SECRET }}')"
+          echo "Sending results to Slab..."
+          curl -v -k \
+          -H "Content-Type: application/json" \
+          -H "X-Slab-Repository: ${{ github.repository }}" \
+          -H "X-Slab-Command: store_data_v2" \
+          -H "X-Hub-Signature-256: sha256=${SIGNATURE}" \
+          -d @${{ env.RESULTS_FILENAME }} \
+          ${{ secrets.SLAB_URL }}
+
+      - name: Slack Notification
+        if: ${{ failure() }}
+        continue-on-error: true
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        env:
+          SLACK_COLOR: ${{ job.status }}
+          SLACK_MESSAGE: "tfhe-ntt benchmarks failed. (${{ env.ACTION_RUN_URL }})"
+
+  teardown-ec2:
+    name: Teardown EC2 instance (ntt-benchmarks)
+    if: ${{ always() && needs.setup-ec2.result != 'skipped' }}
+    needs: [setup-ec2, ntt-benchmarks]
+    runs-on: ubuntu-latest
+    steps:
+      - name: Stop instance
+        id: stop-instance
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
+        with:
+          mode: stop
+          github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
+          slab-url: ${{ secrets.SLAB_BASE_URL }}
+          job-secret: ${{ secrets.JOB_SECRET }}
+          label: ${{ needs.setup-ec2.outputs.runner-name }}
+
+      - name: Slack Notification
+        if: ${{ failure() }}
+        continue-on-error: true
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        env:
+          SLACK_COLOR: ${{ job.status }}
+          SLACK_MESSAGE: "EC2 teardown (ntt-benchmarks) failed. (${{ env.ACTION_RUN_URL }})"

.github/workflows/benchmark_tfhe_zk_pok.yml

@@ -0,0 +1,172 @@
+# Run benchmarks of the tfhe-zk-pok crate on an instance and return parsed results to Slab CI bot.
+name: tfhe-zk-pok benchmarks
+
+on:
+  workflow_dispatch:
+  push:
+    branches:
+      - main
+  schedule:
+    # Weekly benchmarks will be triggered each Saturday at 3a.m.
+    - cron: '0 3 * * 6'
+env:
+  CARGO_TERM_COLOR: always
+  RESULTS_FILENAME: parsed_benchmark_results_${{ github.sha }}.json
+  PARSE_INTEGER_BENCH_CSV_FILE: tfhe_rs_integer_benches_${{ github.sha }}.csv
+  ACTION_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
+  RUST_BACKTRACE: "full"
+  RUST_MIN_STACK: "8388608"
+  SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
+  SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
+  SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
+  SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+
+jobs:
+  should-run:
+    runs-on: ubuntu-latest
+    if: github.event_name == 'workflow_dispatch' ||
+      ((github.event_name == 'push' || github.event_name == 'schedule') && github.repository == 'zama-ai/tfhe-rs')
+    outputs:
+      zk_pok_changed: ${{ steps.changed-files.outputs.zk_pok_any_changed }}
+    steps:
+      - name: Checkout tfhe-rs
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          fetch-depth: 0
+
+      - name: Check for file changes
+        id: changed-files
+        uses: tj-actions/changed-files@bab30c2299617f6615ec02a68b9a40d10bd21366
+        with:
+          since_last_remote_commit: true
+          files_yaml: |
+            zk_pok:
+              - tfhe-zk-pok/**
+              - .github/workflows/benchmark_tfhe_zk_pok.yml
+
+  setup-instance:
+    name: Setup instance (tfhe-zk-pok-benchmarks)
+    runs-on: ubuntu-latest
+    needs: should-run
+    if: github.event_name == 'workflow_dispatch' ||
+      (github.event_name == 'schedule' && github.repository == 'zama-ai/tfhe-rs') ||
+      (github.event_name == 'push' &&
+      github.repository == 'zama-ai/tfhe-rs' &&
+      needs.should-run.outputs.zk_pok_changed == 'true')
+    outputs:
+      runner-name: ${{ steps.start-instance.outputs.label }}
+    steps:
+      - name: Start instance
+        id: start-instance
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
+        with:
+          mode: start
+          github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
+          slab-url: ${{ secrets.SLAB_BASE_URL }}
+          job-secret: ${{ secrets.JOB_SECRET }}
+          backend: aws
+          profile: bench
+
+  tfhe-zk-pok-benchmarks:
+    name: Execute tfhe-zk-pok benchmarks
+    if: needs.setup-instance.result != 'skipped'
+    needs: setup-instance
+    concurrency:
+      group: ${{ github.workflow }}_${{github.event_name}}_${{ github.ref }}${{ github.ref == 'refs/heads/main' && github.sha || '' }}
+      cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
+    runs-on: ${{ needs.setup-instance.outputs.runner-name }}
+    steps:
+      - name: Checkout tfhe-rs repo with tags
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          fetch-depth: 0
+          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
+
+      - name: Get benchmark details
+        run: |
+          {
+            echo "BENCH_DATE=$(date --iso-8601=seconds)";
+            echo "COMMIT_DATE=$(git --no-pager show -s --format=%cd --date=iso8601-strict ${{ github.sha }})";
+            echo "COMMIT_HASH=$(git describe --tags --dirty)";
+          } >> "${GITHUB_ENV}"
+
+      - name: Install rust
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
+        with:
+          toolchain: nightly
+
+      - name: Checkout Slab repo
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          repository: zama-ai/slab
+          path: slab
+          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
+
+      - name: Run benchmarks
+        run: |
+          make bench_tfhe_zk_pok
+
+      - name: Parse results
+        run: |
+          python3 ./ci/benchmark_parser.py target/criterion ${{ env.RESULTS_FILENAME }} \
+          --database tfhe_rs \
+          --crate tfhe-zk-pok \
+          --hardware "hpc7a.96xlarge" \
+          --backend cpu \
+          --project-version "${{ env.COMMIT_HASH }}" \
+          --branch ${{ github.ref_name }} \
+          --commit-date "${{ env.COMMIT_DATE }}" \
+          --bench-date "${{ env.BENCH_DATE }}" \
+          --walk-subdirs \
+          --name-suffix avx512
+
+      - name: Upload parsed results artifact
+        uses: actions/upload-artifact@b4b15b8c7c6ac21ea08fcf65892d2ee8f75cf882
+        with:
+          name: ${{ github.sha }}_tfhe_zk_pok
+          path: ${{ env.RESULTS_FILENAME }}
+
+      - name: Checkout Slab repo
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          repository: zama-ai/slab
+          path: slab
+          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
+
+      - name: Send data to Slab
+        shell: bash
+        run: |
+          python3 slab/scripts/data_sender.py ${{ env.RESULTS_FILENAME }} "${{ secrets.JOB_SECRET }}" \
+          --slab-url "${{ secrets.SLAB_URL }}"
+
+      - name: Slack Notification
+        if: ${{ failure() }}
+        continue-on-error: true
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        env:
+          SLACK_COLOR: ${{ job.status }}
+          SLACK_MESSAGE: "tfhe-zk-pok benchmarks finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
+
+  teardown-instance:
+    name: Teardown instance (tfhe-zk-pok-benchmarks)
+    if: ${{ always() && needs.setup-instance.result != 'skipped' }}
+    needs: [ setup-instance, tfhe-zk-pok-benchmarks ]
+    runs-on: ubuntu-latest
+    steps:
+      - name: Stop instance
+        id: stop-instance
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
+        with:
+          mode: stop
+          github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
+          slab-url: ${{ secrets.SLAB_BASE_URL }}
+          job-secret: ${{ secrets.JOB_SECRET }}
+          label: ${{ needs.setup-instance.outputs.runner-name }}
+
+      - name: Slack Notification
+        if: ${{ failure() }}
+        continue-on-error: true
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        env:
+          SLACK_COLOR: ${{ job.status }}
+          SLACK_MESSAGE: "Instance teardown (tfhe-zk-pok-benchmarks) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/benchmark_wasm_client.yml

@@ -33,19 +33,20 @@ jobs:
       wasm_bench: ${{ steps.changed-files.outputs.wasm_bench_any_changed }}
     steps:
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
+          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
 
       - name: Check for file changes
         id: changed-files
-        uses: tj-actions/changed-files@48d8f15b2aaa3d255ca5af3eba4870f807ce6b3c
+        uses: tj-actions/changed-files@bab30c2299617f6615ec02a68b9a40d10bd21366
         with:
           since_last_remote_commit: true
           files_yaml: |
             wasm_bench:
               - tfhe/Cargo.toml
-              - concrete-csprng/**
+              - tfhe-csprng/**
               - tfhe-zk-pok/**
               - tfhe/src/**
               - '!tfhe/src/c_api/**'
@@ -64,7 +65,7 @@ jobs:
     steps:
       - name: Start instance
         id: start-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: start
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -78,9 +79,13 @@ jobs:
     needs: setup-instance
     if: needs.setup-instance.result != 'skipped'
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
+    strategy:
+      max-parallel: 1
+      matrix:
+        browser: [ chrome, firefox ]
     steps:
       - name: Checkout tfhe-rs repo with tags
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
           token: ${{ secrets.FHE_ACTIONS_TOKEN }}
@@ -93,25 +98,46 @@ jobs:
             echo "COMMIT_HASH=$(git describe --tags --dirty)";
           } >> "${GITHUB_ENV}"
 
-      - name: Set up home
-        # "Install rust" step require root user to have a HOME directory which is not set.
-        run: |
-          echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
-
       - name: Install rust
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: nightly
 
-      - name: Install web resources
+      - name: Get Node version
+        run: |
+          echo "NODE_VERSION=$(make node_version)" >> "${GITHUB_ENV}"
+
+      - name: Node cache restoration
+        id: node-cache
+        uses: actions/cache/restore@1bd1e32a3bdc45362d1e726936510720a7c30a57 #v4.2.0
+        with:
+          path: |
+            ~/.nvm
+            ~/.npm
+          key: node-${{ env.NODE_VERSION }}
+
+      - name: Install Node
+        if: steps.node-cache.outputs.cache-hit != 'true'
         run: |
           make install_node
-          make install_chrome_browser
-          make install_chrome_web_driver
+
+      - name: Node cache save
+        uses: actions/cache/save@1bd1e32a3bdc45362d1e726936510720a7c30a57 #v4.2.0
+        if: steps.node-cache.outputs.cache-hit != 'true'
+        with:
+          path: |
+            ~/.nvm
+            ~/.npm
+          key: node-${{ env.NODE_VERSION }}
+
+      - name: Install web resources
+        run: |
+          make install_${{ matrix.browser }}_browser
+          make install_${{ matrix.browser }}_web_driver
 
       - name: Run benchmarks
         run: |
-          make bench_web_js_api_parallel_chrome_ci
+          make bench_web_js_api_parallel_${{ matrix.browser }}_ci
 
       - name: Parse results
         run: |
@@ -124,25 +150,29 @@ jobs:
           --commit-date "${{ env.COMMIT_DATE }}" \
           --bench-date "${{ env.BENCH_DATE }}" \
           --key-gen
+          rm tfhe/wasm_pk_gen.csv
 
+      # Run these benchmarks only once
       - name: Measure public key and ciphertext sizes in HL Api
+        if:  matrix.browser == 'chrome'
         run: |
           make measure_hlapi_compact_pk_ct_sizes
 
       - name: Parse key and ciphertext sizes results
+        if:  matrix.browser == 'chrome'
         run: |
           python3 ./ci/benchmark_parser.py tfhe/hlapi_cpk_and_cctl_sizes.csv ${{ env.RESULTS_FILENAME }} \
           --key-gen \
           --append-results
 
       - name: Upload parsed results artifact
-        uses: actions/upload-artifact@50769540e7f4bd5e21e526ee35c689e35e0d6874
+        uses: actions/upload-artifact@b4b15b8c7c6ac21ea08fcf65892d2ee8f75cf882
         with:
-          name: ${{ github.sha }}_wasm
+          name: ${{ github.sha }}_wasm_${{ matrix.browser }}
           path: ${{ env.RESULTS_FILENAME }}
 
       - name: Checkout Slab repo
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           repository: zama-ai/slab
           path: slab
@@ -157,10 +187,10 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "WASM benchmarks finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "WASM benchmarks (${{ matrix.browser }}) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
 
   teardown-instance:
     name: Teardown instance (wasm-client-benchmarks)
@@ -170,7 +200,7 @@ jobs:
     steps:
       - name: Stop instance
         id: stop-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: stop
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -181,7 +211,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Instance teardown (wasm-client-benchmarks) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/benchmark_zk_pke.yml

@@ -3,6 +3,16 @@ name: PKE ZK benchmarks
 
 on:
   workflow_dispatch:
+    inputs:
+      bench_type:
+        description: "Benchmarks type"
+        type: choice
+        default: latency
+        options:
+          - latency
+          - throughput
+          - both
+
   push:
     branches:
       - main
@@ -30,19 +40,21 @@ jobs:
       zk_pok_changed: ${{ steps.changed-files.outputs.zk_pok_any_changed }}
     steps:
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
+          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
 
       - name: Check for file changes
         id: changed-files
-        uses: tj-actions/changed-files@48d8f15b2aaa3d255ca5af3eba4870f807ce6b3c
+        uses: tj-actions/changed-files@bab30c2299617f6615ec02a68b9a40d10bd21366
         with:
           since_last_remote_commit: true
           files_yaml: |
             zk_pok:
               - tfhe/Cargo.toml
-              - concrete-csprng/**
+              - tfhe-csprng/**
+              - tfhe-fft/**
               - tfhe-zk-pok/**
               - tfhe/src/core_crypto/**
               - tfhe/src/shortint/**
@@ -51,10 +63,37 @@ jobs:
               - tfhe/benches/integer/zk_pke.rs
               - .github/workflows/zk_pke_benchmark.yml
 
+  prepare-matrix:
+    name: Prepare operations matrix
+    runs-on: ubuntu-latest
+    if: github.event_name != 'schedule' ||
+      (github.event_name == 'schedule' && github.repository == 'zama-ai/tfhe-rs')
+    outputs:
+      bench_type: ${{ steps.set_bench_type.outputs.bench_type }}
+    steps:
+      - name: Set benchmark types
+        if: github.event_name == 'workflow_dispatch'
+        run: |
+          if [[ "${{ inputs.bench_type }}" == "both" ]]; then
+            echo "BENCH_TYPE=[\"latency\", \"throughput\"]" >> "${GITHUB_ENV}"
+          else
+            echo "BENCH_TYPE=[\"${{ inputs.bench_type }}\"]" >> "${GITHUB_ENV}"
+          fi
+
+      - name: Default benchmark type
+        if: github.event_name != 'workflow_dispatch'
+        run: |
+          echo "BENCH_TYPE=[\"latency\"]" >> "${GITHUB_ENV}"
+
+      - name: Set benchmark types output
+        id: set_bench_type
+        run: |
+          echo "bench_type=${{ toJSON(env.BENCH_TYPE) }}" >> "${GITHUB_OUTPUT}"
+
   setup-instance:
     name: Setup instance (pke-zk-benchmarks)
     runs-on: ubuntu-latest
-    needs: should-run
+    needs: [ should-run, prepare-matrix ]
     if: github.event_name == 'workflow_dispatch' ||
       (github.event_name == 'schedule' && github.repository == 'zama-ai/tfhe-rs') ||
       (github.event_name == 'push' &&
@@ -65,7 +104,7 @@ jobs:
     steps:
       - name: Start instance
         id: start-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: start
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -77,14 +116,18 @@ jobs:
   pke-zk-benchmarks:
     name: Execute PKE ZK benchmarks
     if: needs.setup-instance.result != 'skipped'
-    needs: setup-instance
+    needs: [ prepare-matrix, setup-instance ]
     concurrency:
       group: ${{ github.workflow }}_${{github.event_name}}_${{ github.ref }}${{ github.ref == 'refs/heads/main' && github.sha || '' }}
       cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
+    strategy:
+      max-parallel: 1
+      matrix:
+        bench_type: ${{ fromJSON(needs.prepare-matrix.outputs.bench_type) }}
     steps:
       - name: Checkout tfhe-rs repo with tags
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
           token: ${{ secrets.FHE_ACTIONS_TOKEN }}
@@ -97,18 +140,13 @@ jobs:
             echo "COMMIT_HASH=$(git describe --tags --dirty)";
           } >> "${GITHUB_ENV}"
 
-      - name: Set up home
-        # "Install rust" step require root user to have a HOME directory which is not set.
-        run: |
-          echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
-
       - name: Install rust
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: nightly
 
       - name: Checkout Slab repo
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           repository: zama-ai/slab
           path: slab
@@ -116,7 +154,7 @@ jobs:
 
       - name: Run benchmarks with AVX512
         run: |
-          make bench_integer_zk
+          make BENCH_TYPE=${{ matrix.bench_type }} bench_integer_zk
 
       - name: Parse results
         run: |
@@ -130,22 +168,22 @@ jobs:
           --bench-date "${{ env.BENCH_DATE }}" \
           --walk-subdirs \
           --name-suffix avx512 \
-          --throughput
+          --bench-type ${{ matrix.bench_type }}
 
       - name: Parse CRS sizes results
         run: |
           python3 ./ci/benchmark_parser.py tfhe/pke_zk_crs_sizes.csv ${{ env.RESULTS_FILENAME }} \
-          --key-sizes \
+          --object-sizes \
           --append-results
 
       - name: Upload parsed results artifact
-        uses: actions/upload-artifact@50769540e7f4bd5e21e526ee35c689e35e0d6874
+        uses: actions/upload-artifact@b4b15b8c7c6ac21ea08fcf65892d2ee8f75cf882
         with:
           name: ${{ github.sha }}_integer_zk
           path: ${{ env.RESULTS_FILENAME }}
 
       - name: Checkout Slab repo
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           repository: zama-ai/slab
           path: slab
@@ -160,7 +198,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "PKE ZK benchmarks finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
@@ -173,7 +211,7 @@ jobs:
     steps:
       - name: Stop instance
         id: stop-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: stop
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -184,7 +222,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Instance teardown (pke-zk-benchmarks) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/cargo_build.yml

@@ -1,4 +1,4 @@
-name: Cargo Build
+name: Cargo Build TFHE-rs
 
 on:
   pull_request:
@@ -25,10 +25,10 @@ jobs:
       fail-fast: false
 
     steps:
-      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: stable
 
@@ -47,10 +47,10 @@ jobs:
         run: |
           make pcc
 
-      - name: Build concrete-csprng
+      - name: Build tfhe-csprng
         if: ${{ contains(matrix.os, 'ubuntu') }}
         run: |
-          make build_concrete_csprng
+          make build_tfhe_csprng
 
       - name: Build Release core
         if: ${{ contains(matrix.os, 'ubuntu') }}

.github/workflows/cargo_build_tfhe_fft.yml

@@ -0,0 +1,44 @@
+# Build tfhe-fft
+name: Cargo Build tfhe-fft
+
+on:
+  pull_request:
+
+env:
+  CARGO_TERM_COLOR: always
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref }}
+  cancel-in-progress: true
+
+jobs:
+  cargo-builds-fft:
+    runs-on: ${{ matrix.runner_type }}
+
+    strategy:
+      matrix:
+        runner_type: [ubuntu-latest, macos-latest, windows-latest]
+      fail-fast: false
+
+    steps:
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+
+      - name: Install Rust
+        uses: actions-rs/toolchain@16499b5e05bf2e26879000db0c1d13f7e13fa3af
+        with:
+          toolchain: stable
+          override: true
+
+      - name: Run pcc checks
+        if: matrix.runner_type == 'ubuntu-latest'
+        run: |
+          sudo apt install -y libfftw3-dev
+          make pcc_fft
+
+      - name: Build release
+        run: |
+          make build_fft
+
+      - name: Build release no-std
+        run: |
+          make build_fft_no_std

.github/workflows/cargo_build_tfhe_ntt.yml

@@ -0,0 +1,40 @@
+# Build tfhe-ntt
+name: Cargo Build tfhe-ntt
+
+on:
+  pull_request:
+
+env:
+  CARGO_TERM_COLOR: always
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref }}
+  cancel-in-progress: true
+
+jobs:
+  cargo-builds:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ubuntu-latest, macos-latest, windows-latest]
+      fail-fast: false
+    steps:
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+
+      - name: Install Rust
+        uses: actions-rs/toolchain@16499b5e05bf2e26879000db0c1d13f7e13fa3af
+        with:
+          toolchain: stable
+          override: true
+
+      - name: Run pcc checks
+        run: |
+          make pcc_ntt
+
+      - name: Build release
+        run: |
+          make build_ntt
+
+      - name: Build release no-std
+        run: |
+          make build_ntt_no_std

.github/workflows/cargo_test_fft.yml

@@ -0,0 +1,71 @@
+# Test tfhe-fft
+name: Cargo Test tfhe-fft
+
+on:
+  pull_request:
+
+env:
+  CARGO_TERM_COLOR: always
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref }}
+  cancel-in-progress: true
+
+jobs:
+  cargo-tests:
+    runs-on: ${{ matrix.runner_type }}
+    strategy:
+      matrix:
+        runner_type: [ubuntu-latest, macos-latest, windows-latest]
+      fail-fast: false
+    steps:
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+
+      - name: Install Rust
+        uses: actions-rs/toolchain@16499b5e05bf2e26879000db0c1d13f7e13fa3af
+        with:
+          toolchain: stable
+          override: true
+
+      - name: Test debug
+        run: |
+          make test_fft
+
+      - name: Test serialization
+        run: make test_fft_serde
+
+      - name: Test no-std
+        run: |
+          make test_fft_no_std
+
+  cargo-tests-nightly:
+    runs-on: ${{ matrix.runner_type }}
+    strategy:
+      matrix:
+        runner_type: [ubuntu-latest, macos-latest, windows-latest]
+    steps:
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+
+      - name: Install Rust
+        uses: actions-rs/toolchain@16499b5e05bf2e26879000db0c1d13f7e13fa3af
+        with:
+          toolchain: nightly
+          override: true
+
+      - name: Test nightly
+        run: |
+          make test_fft_nightly
+
+      - name: Test no-std nightly
+        run: |
+          make test_fft_no_std_nightly
+
+  cargo-tests-node-js:
+    runs-on: "ubuntu-latest"
+    steps:
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+
+      - name: Test node js
+        run: |
+          make install_node
+          make test_fft_node_js_ci

.github/workflows/cargo_test_ntt.yml

@@ -0,0 +1,54 @@
+# Test tfhe-ntt
+name: Cargo Test tfhe-ntt
+
+on:
+  pull_request:
+
+env:
+  CARGO_TERM_COLOR: always
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref }}
+  cancel-in-progress: true
+
+jobs:
+  cargo-tests:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ubuntu-latest, macos-latest, windows-latest]
+      fail-fast: false
+    steps:
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+
+      - name: Install Rust
+        uses: actions-rs/toolchain@16499b5e05bf2e26879000db0c1d13f7e13fa3af
+        with:
+          toolchain: stable
+          override: true
+
+      - name: Test debug
+        run: make test_ntt
+
+      - name: Test no-std
+        run: make test_ntt_no_std
+
+  cargo-tests-nightly:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ubuntu-latest, macos-latest, windows-latest]
+    steps:
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+
+      - name: Install Rust
+        uses: actions-rs/toolchain@16499b5e05bf2e26879000db0c1d13f7e13fa3af
+        with:
+          toolchain: nightly
+          override: true
+
+      - name: Test nightly
+        run: make test_ntt_nightly
+
+      - name: Test no-std nightly
+        run: make test_ntt_no_std_nightly

.github/workflows/check_commit.yml

@@ -28,3 +28,6 @@ jobs:
           excludeTitle: "true" # optional: this excludes the title of a pull request
           checkAllCommitMessages: "true" # optional: this checks all commits associated with a pull request
           accessToken: ${{ secrets.GITHUB_TOKEN }} # github access token is only required if checkAllCommitMessages is true
+
+      - name: Check commit signatures
+        uses: 1Password/check-signed-commits-action@ed2885f3ed2577a4f5d3c3fe895432a557d23d52

.github/workflows/ci_lint.yml

@@ -13,7 +13,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
 
       - name: Get actionlint
         run: |
@@ -27,7 +27,7 @@ jobs:
           make lint_workflow
 
       - name: Ensure SHA pinned actions
-        uses: zgosalvez/github-actions-ensure-sha-pinned-actions@0901cf7b71c7ea6261ec69a3dc2bd3f9264f893e # v3.0.12
+        uses: zgosalvez/github-actions-ensure-sha-pinned-actions@5d6ac37a4cef8b8df67f482a8e384987766f0213 # v3.0.17
         with:
           allowlist: |
             slsa-framework/slsa-github-generator

.github/workflows/code_coverage.yml

@@ -25,7 +25,7 @@ jobs:
     steps:
       - name: Start instance
         id: start-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: start
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -44,26 +44,22 @@ jobs:
     timeout-minutes: 5760 # 4 days
     steps:
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
-
-      - name: Set up home
-        run: |
-          echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: stable
 
       - name: Check for file changes
         id: changed-files
-        uses: tj-actions/changed-files@48d8f15b2aaa3d255ca5af3eba4870f807ce6b3c
+        uses: tj-actions/changed-files@bab30c2299617f6615ec02a68b9a40d10bd21366
         with:
           files_yaml: |
             tfhe:
               - tfhe/src/**
-            concrete_csprng:
-              - concrete-csprng/src/**
+            tfhe_csprng:
+              - tfhe-csprng/src/**
 
       - name: Generate Keys
         if: steps.changed-files.outputs.tfhe_any_changed == 'true'
@@ -87,7 +83,7 @@ jobs:
           make test_shortint_cov
 
       - name: Upload tfhe coverage to Codecov
-        uses: codecov/codecov-action@e28ff129e5465c2c0dcc6f003fc735cb6ae0c673
+        uses: codecov/codecov-action@7f8b4b4bde536c465e797be725718b88c5d95e0e
         if: steps.changed-files.outputs.tfhe_any_changed == 'true'
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
@@ -101,7 +97,7 @@ jobs:
           make test_integer_cov
 
       - name: Upload tfhe coverage to Codecov
-        uses: codecov/codecov-action@e28ff129e5465c2c0dcc6f003fc735cb6ae0c673
+        uses: codecov/codecov-action@7f8b4b4bde536c465e797be725718b88c5d95e0e
         if: steps.changed-files.outputs.tfhe_any_changed == 'true'
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
@@ -112,7 +108,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Code coverage finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
@@ -125,7 +121,7 @@ jobs:
     steps:
       - name: Stop instance
         id: stop-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: stop
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -136,7 +132,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Instance teardown (code-coverage) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/csprng_randomness_tests.yml

@@ -27,7 +27,7 @@ jobs:
     steps:
       - name: Start instance
         id: start-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: start
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -45,17 +45,13 @@ jobs:
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     steps:
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           persist-credentials: 'false'
           token: ${{ secrets.FHE_ACTIONS_TOKEN }}
 
-      - name: Set up home
-        run: |
-          echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
-
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: stable
 
@@ -66,10 +62,10 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "concrete-csprng randomness check finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "tfhe-csprng randomness check finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
 
   teardown-instance:
     name: Teardown instance (csprng-randomness-tests)
@@ -79,7 +75,7 @@ jobs:
     steps:
       - name: Stop instance
         id: stop-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: stop
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -90,7 +86,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Instance teardown (csprng-randomness-tests) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/data_pr_close.yml

@@ -117,7 +117,7 @@ jobs:
     - name: Slack Notification
       if: ${{ always() && job.status == 'failure' }}
       continue-on-error: true
-      uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+      uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
       env:
         SLACK_COLOR: ${{ job.status }}
         SLACK_MESSAGE: "Failed to auto-${{ env.CLOSE_TYPE }} PR on data repo: ${{ fromJson(env.GH_API_RES || env.TARGET_REPO_PR).message }}"

.github/workflows/gpu_4090_tests.yml

@@ -34,13 +34,13 @@ jobs:
 
     steps:
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           persist-credentials: 'false'
           token: ${{ secrets.FHE_ACTIONS_TOKEN }}
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: stable
 
@@ -77,7 +77,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "CUDA RTX 4090 tests finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/gpu_fast_h100_tests.yml

@@ -28,13 +28,14 @@ jobs:
       gpu_test: ${{ env.IS_PULL_REQUEST == 'false' || steps.changed-files.outputs.gpu_any_changed }}
     steps:
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
+          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
 
       - name: Check for file changes
         id: changed-files
-        uses: tj-actions/changed-files@48d8f15b2aaa3d255ca5af3eba4870f807ce6b3c
+        uses: tj-actions/changed-files@bab30c2299617f6615ec02a68b9a40d10bd21366
         with:
           since_last_remote_commit: true
           files_yaml: |
@@ -44,14 +45,16 @@ jobs:
               - backends/tfhe-cuda-backend/**
               - tfhe/src/core_crypto/gpu/**
               - tfhe/src/integer/gpu/**
+              - tfhe/src/integer/server_key/radix_parallel/tests_unsigned/**
+              - tfhe/src/integer/server_key/radix_parallel/tests_signed/**
+              - tfhe/src/integer/server_key/radix_parallel/tests_cases_unsigned.rs
               - tfhe/src/shortint/parameters/**
               - tfhe/src/high_level_api/**
               - tfhe/src/c_api/**
               - 'tfhe/docs/**.md'
-              - Makefile
               - '.github/workflows/gpu_fast_h100_tests.yml'
-              - scripts/**
-              - ci/**
+              - scripts/integer-tests.sh
+              - ci/slab.toml
 
   setup-instance:
     name: Setup instance (cuda-h100-tests)
@@ -65,7 +68,7 @@ jobs:
     steps:
       - name: Start instance
         id: start-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: start
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -99,7 +102,7 @@ jobs:
       - name: Install dependencies
         run: |
           sudo apt update
-          sudo apt install -y checkinstall zlib1g-dev libssl-dev 
+          sudo apt install -y checkinstall zlib1g-dev libssl-dev libclang-dev
           wget https://github.com/Kitware/CMake/releases/download/v${{ env.CMAKE_VERSION }}/cmake-${{ env.CMAKE_VERSION }}.tar.gz
           tar -zxvf cmake-${{ env.CMAKE_VERSION }}.tar.gz
           cd cmake-${{ env.CMAKE_VERSION }}
@@ -108,7 +111,7 @@ jobs:
           sudo make install
 
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           persist-credentials: 'false'
           token: ${{ secrets.FHE_ACTIONS_TOKEN }}
@@ -118,7 +121,7 @@ jobs:
           echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: stable
 
@@ -147,8 +150,8 @@ jobs:
 
       - name: Run core crypto and internal CUDA backend tests
         run: |
-          BIG_TESTS_INSTANCE=FALSE make test_core_crypto_gpu
-          BIG_TESTS_INSTANCE=FALSE make test_integer_compression_gpu
+          BIG_TESTS_INSTANCE=TRUE make test_core_crypto_gpu
+          BIG_TESTS_INSTANCE=TRUE make test_integer_compression_gpu
           BIG_TESTS_INSTANCE=TRUE make test_cuda_backend
 
       - name: Run user docs tests
@@ -171,7 +174,7 @@ jobs:
     continue-on-error: true
     steps:
       - name: Send message
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ needs.cuda-tests-linux.result }}
           SLACK_MESSAGE: "Fast H100 tests finished with status: ${{ needs.cuda-tests-linux.result }}. (${{ env.ACTION_RUN_URL }})"
@@ -184,7 +187,7 @@ jobs:
     steps:
       - name: Stop instance
         id: stop-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: stop
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -195,7 +198,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Instance teardown (cuda-h100-tests) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/gpu_fast_tests.yml

@@ -27,13 +27,14 @@ jobs:
       gpu_test: ${{ env.IS_PULL_REQUEST == 'false' || steps.changed-files.outputs.gpu_any_changed }}
     steps:
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
+          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
 
       - name: Check for file changes
         id: changed-files
-        uses: tj-actions/changed-files@48d8f15b2aaa3d255ca5af3eba4870f807ce6b3c
+        uses: tj-actions/changed-files@bab30c2299617f6615ec02a68b9a40d10bd21366
         with:
           since_last_remote_commit: true
           files_yaml: |
@@ -42,15 +43,17 @@ jobs:
               - tfhe/build.rs
               - backends/tfhe-cuda-backend/**
               - tfhe/src/core_crypto/gpu/**
+              - tfhe/src/integer/server_key/radix_parallel/tests_unsigned/**
+              - tfhe/src/integer/server_key/radix_parallel/tests_signed/**
+              - tfhe/src/integer/server_key/radix_parallel/tests_cases_unsigned.rs
               - tfhe/src/integer/gpu/**
               - tfhe/src/shortint/parameters/**
               - tfhe/src/high_level_api/**
               - tfhe/src/c_api/**
               - 'tfhe/docs/**.md'
               - '.github/workflows/gpu_fast_tests.yml'
-              - Makefile
-              - scripts/**
-              - ci/**
+              - scripts/integer-tests.sh
+              - ci/slab.toml
 
   setup-instance:
     name: Setup instance (cuda-tests)
@@ -63,7 +66,7 @@ jobs:
     steps:
       - name: Start instance
         id: start-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: start
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -97,7 +100,7 @@ jobs:
       - name: Install dependencies
         run: |
           sudo apt update
-          sudo apt install -y checkinstall zlib1g-dev libssl-dev 
+          sudo apt install -y checkinstall zlib1g-dev libssl-dev libclang-dev
           wget https://github.com/Kitware/CMake/releases/download/v${{ env.CMAKE_VERSION }}/cmake-${{ env.CMAKE_VERSION }}.tar.gz
           tar -zxvf cmake-${{ env.CMAKE_VERSION }}.tar.gz
           cd cmake-${{ env.CMAKE_VERSION }}
@@ -106,7 +109,7 @@ jobs:
           sudo make install
 
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           persist-credentials: 'false'
           token: ${{ secrets.FHE_ACTIONS_TOKEN }}
@@ -116,7 +119,7 @@ jobs:
           echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: stable
 
@@ -169,7 +172,7 @@ jobs:
     continue-on-error: true
     steps:
       - name: Send message
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ needs.cuda-tests-linux.result }}
           SLACK_MESSAGE: "Base GPU tests finished with status: ${{ needs.cuda-tests-linux.result }}. (${{ env.ACTION_RUN_URL }})"
@@ -182,7 +185,7 @@ jobs:
     steps:
       - name: Stop instance
         id: stop-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: stop
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -193,7 +196,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Instance teardown (cuda-tests) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/gpu_full_h100_tests.yml

@@ -25,7 +25,7 @@ jobs:
     steps:
       - name: Start instance
         id: start-instance
-        uses: zama-ai/slab-github-runner@447a2d0fd2d1a9d647aa0d0723a6e9255372f261
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: start
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -57,7 +57,7 @@ jobs:
       - name: Install dependencies
         run: |
           sudo apt update
-          sudo apt install -y checkinstall zlib1g-dev libssl-dev 
+          sudo apt install -y checkinstall zlib1g-dev libssl-dev libclang-dev
           wget https://github.com/Kitware/CMake/releases/download/v${{ env.CMAKE_VERSION }}/cmake-${{ env.CMAKE_VERSION }}.tar.gz
           tar -zxvf cmake-${{ env.CMAKE_VERSION }}.tar.gz
           cd cmake-${{ env.CMAKE_VERSION }}
@@ -66,7 +66,7 @@ jobs:
           sudo make install
 
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           persist-credentials: 'false'
           token: ${{ secrets.FHE_ACTIONS_TOKEN }}
@@ -76,7 +76,7 @@ jobs:
           echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: stable
 
@@ -127,7 +127,7 @@ jobs:
     continue-on-error: true
     steps:
       - name: Send message
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ needs.cuda-tests-linux.result }}
           SLACK_MESSAGE: "Full H100 tests finished with status: ${{ needs.cuda-tests-linux.result }}. (${{ env.ACTION_RUN_URL }})"
@@ -139,7 +139,7 @@ jobs:
     steps:
       - name: Stop instance
         id: stop-instance
-        uses: zama-ai/slab-github-runner@447a2d0fd2d1a9d647aa0d0723a6e9255372f261
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: stop
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -150,7 +150,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Instance teardown (cuda-h100-tests) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/gpu_full_multi_gpu_tests.yml

@@ -28,13 +28,14 @@ jobs:
       gpu_test: ${{ env.IS_PULL_REQUEST == 'false' || steps.changed-files.outputs.gpu_any_changed }}
     steps:
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
+          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
 
       - name: Check for file changes
         id: changed-files
-        uses: tj-actions/changed-files@48d8f15b2aaa3d255ca5af3eba4870f807ce6b3c
+        uses: tj-actions/changed-files@bab30c2299617f6615ec02a68b9a40d10bd21366
         with:
           since_last_remote_commit: true
           files_yaml: |
@@ -43,15 +44,17 @@ jobs:
               - tfhe/build.rs
               - backends/tfhe-cuda-backend/**
               - tfhe/src/core_crypto/gpu/**
+              - tfhe/src/integer/server_key/radix_parallel/tests_unsigned/**
+              - tfhe/src/integer/server_key/radix_parallel/tests_signed/**
+              - tfhe/src/integer/server_key/radix_parallel/tests_cases_unsigned.rs
               - tfhe/src/integer/gpu/**
               - tfhe/src/shortint/parameters/**
               - tfhe/src/high_level_api/**
               - tfhe/src/c_api/**
               - 'tfhe/docs/**.md'
-              - Makefile
               - '.github/workflows/**_multi_gpu_tests.yml'
-              - scripts/**
-              - ci/**
+              - scripts/integer-tests.sh
+              - ci/slab.toml
 
   setup-instance:
     name: Setup instance (cuda-tests-multi-gpu)
@@ -65,7 +68,7 @@ jobs:
     steps:
       - name: Start instance
         id: start-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: start
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -99,7 +102,7 @@ jobs:
       - name: Install dependencies
         run: |
           sudo apt update
-          sudo apt install -y checkinstall zlib1g-dev libssl-dev 
+          sudo apt install -y checkinstall zlib1g-dev libssl-dev libclang-dev
           wget https://github.com/Kitware/CMake/releases/download/v${{ env.CMAKE_VERSION }}/cmake-${{ env.CMAKE_VERSION }}.tar.gz
           tar -zxvf cmake-${{ env.CMAKE_VERSION }}.tar.gz
           cd cmake-${{ env.CMAKE_VERSION }}
@@ -108,7 +111,7 @@ jobs:
           sudo make install
 
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           persist-credentials: 'false'
           token: ${{ secrets.FHE_ACTIONS_TOKEN }}
@@ -118,7 +121,7 @@ jobs:
           echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: stable
 
@@ -174,7 +177,7 @@ jobs:
     continue-on-error: true
     steps:
       - name: Send message
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ needs.cuda-tests-linux.result }}
           SLACK_MESSAGE: "Multi-GPU tests finished with status: ${{ needs.cuda-tests-linux.result }}. (${{ env.ACTION_RUN_URL }})"
@@ -187,7 +190,7 @@ jobs:
     steps:
       - name: Stop instance
         id: stop-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: stop
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -198,7 +201,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Instance teardown (cuda-tests-multi-gpu) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/gpu_integer_long_run_tests.yml

@@ -0,0 +1,146 @@
+name: AWS Long Run Tests on GPU
+
+env:
+  CARGO_TERM_COLOR: always
+  ACTION_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
+  RUSTFLAGS: "-C target-cpu=native"
+  RUST_BACKTRACE: "full"
+  RUST_MIN_STACK: "8388608"
+  SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
+  SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
+  SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
+  SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+
+on:
+  # Allows you to run this workflow manually from the Actions tab as an alternative.
+  workflow_dispatch:
+  schedule:
+    # Weekly tests will be triggered each Friday at 1a.m.
+    - cron: '0 1 * * FRI'
+
+jobs:
+  setup-instance:
+    name: Setup instance (gpu-tests)
+    if: github.event_name != 'schedule' ||
+      (github.event_name == 'schedule' && github.repository == 'zama-ai/tfhe-rs')
+    runs-on: ubuntu-latest
+    outputs:
+      runner-name: ${{ steps.start-instance.outputs.label }}
+    steps:
+      - name: Start instance
+        id: start-instance
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
+        with:
+          mode: start
+          github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
+          slab-url: ${{ secrets.SLAB_BASE_URL }}
+          job-secret: ${{ secrets.JOB_SECRET }}
+          backend: hyperstack
+          profile: 2-h100
+
+  cuda-tests:
+    name: Long run GPU H100 tests
+    needs: [ setup-instance ]
+    concurrency:
+      group: ${{ github.workflow }}_${{github.event_name}}_${{ github.ref }}
+      cancel-in-progress: true
+    runs-on: ${{ needs.setup-instance.outputs.runner-name }}
+    strategy:
+      fail-fast: false
+      # explicit include-based build matrix, of known valid options
+      matrix:
+        include:
+          - os: ubuntu-22.04
+            cuda: "12.2"
+            gcc: 11 
+    env:
+      CUDA_PATH: /usr/local/cuda-${{ matrix.cuda }}
+      CMAKE_VERSION: 3.29.6
+    steps:
+      # Mandatory on hyperstack since a bootable volume is not re-usable yet.
+      - name: Install dependencies
+        run: |
+          sudo apt update
+          sudo apt install -y checkinstall zlib1g-dev libssl-dev libclang-dev
+          wget https://github.com/Kitware/CMake/releases/download/v${{ env.CMAKE_VERSION }}/cmake-${{ env.CMAKE_VERSION }}.tar.gz
+          tar -zxvf cmake-${{ env.CMAKE_VERSION }}.tar.gz
+          cd cmake-${{ env.CMAKE_VERSION }}
+          ./bootstrap
+          make -j"$(nproc)"
+          sudo make install
+
+      - name: Checkout tfhe-rs
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+
+      - name: Set up home
+        run: |
+          echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
+
+      - name: Install latest stable
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
+        with:
+          toolchain: stable
+
+      - name: Export CUDA variables
+        if: ${{ !cancelled() }}
+        run: |
+          echo "CUDA_PATH=$CUDA_PATH" >> "${GITHUB_ENV}"
+          echo "$CUDA_PATH/bin" >> "${GITHUB_PATH}"
+          echo "LD_LIBRARY_PATH=$CUDA_PATH/lib:$LD_LIBRARY_PATH" >> "${GITHUB_ENV}"
+          echo "CUDACXX=/usr/local/cuda-${{ matrix.cuda }}/bin/nvcc" >> "${GITHUB_ENV}"
+
+      # Specify the correct host compilers
+      - name: Export gcc and g++ variables
+        if: ${{ !cancelled() }}
+        run: |
+          {
+            echo "CC=/usr/bin/gcc-${{ matrix.gcc }}";
+            echo "CXX=/usr/bin/g++-${{ matrix.gcc }}";
+            echo "CUDAHOSTCXX=/usr/bin/g++-${{ matrix.gcc }}";
+            echo "HOME=/home/ubuntu";
+          } >> "${GITHUB_ENV}"
+
+      - name: Check device is detected
+        if: ${{ !cancelled() }}
+        run: nvidia-smi
+
+      - name: Run tests
+        run: |
+          make test_integer_long_run_gpu
+
+  slack-notify:
+    name: Slack Notification
+    needs: [ setup-instance, cuda-tests ]
+    runs-on: ubuntu-latest
+    if: ${{ always() && needs.cuda-tests.result != 'skipped' && failure() }}
+    continue-on-error: true
+    steps:
+      - name: Send message
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        env:
+          SLACK_COLOR: ${{ needs.cuda-tests.result }}
+          SLACK_MESSAGE: "Integer GPU H100 long run tests finished with status: ${{ needs.cuda-tests.result }}. (${{ env.ACTION_RUN_URL }})"
+
+  teardown-instance:
+    name: Teardown instance (gpu-tests)
+    if: ${{ always() && needs.setup-instance.result != 'skipped' }}
+    needs: [ setup-instance, cuda-tests ]
+    runs-on: ubuntu-latest
+    steps:
+      - name: Stop instance
+        id: stop-instance
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
+        with:
+          mode: stop
+          github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
+          slab-url: ${{ secrets.SLAB_BASE_URL }}
+          job-secret: ${{ secrets.JOB_SECRET }}
+          label: ${{ needs.setup-instance.outputs.runner-name }}
+
+      - name: Slack Notification
+        if: ${{ failure() }}
+        continue-on-error: true
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        env:
+          SLACK_COLOR: ${{ job.status }}
+          SLACK_MESSAGE: "Instance teardown (gpu-long-run-tests) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/gpu_pcc.yml

@@ -24,7 +24,7 @@ jobs:
     steps:
       - name: Start instance
         id: start-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: start
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -53,7 +53,7 @@ jobs:
 
     steps:
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           persist-credentials: 'false'
           token: ${{ secrets.FHE_ACTIONS_TOKEN }}
@@ -63,7 +63,7 @@ jobs:
           echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: stable
 
@@ -97,7 +97,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "CUDA AWS post-commit checks finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
@@ -110,7 +110,7 @@ jobs:
     steps:
       - name: Stop instance
         id: stop-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: stop
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -121,7 +121,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Instance teardown (cuda-pcc) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/gpu_signed_integer_classic_tests.yml

@@ -0,0 +1,188 @@
+# Signed integer GPU tests on an RTXA6000 VM on hyperstack with classical PBS
+name: TFHE Cuda Backend - Signed integer tests with classical PBS
+
+env:
+  CARGO_TERM_COLOR: always
+  ACTION_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
+  RUSTFLAGS: "-C target-cpu=native"
+  RUST_BACKTRACE: "full"
+  RUST_MIN_STACK: "8388608"
+  SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
+  SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
+  SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
+  SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+  IS_PULL_REQUEST: ${{ github.event_name == 'pull_request' }}
+
+on:
+  # Allows you to run this workflow manually from the Actions tab as an alternative.
+  workflow_dispatch:
+  pull_request:
+      types: [ labeled ]
+
+jobs:
+  should-run:
+    runs-on: ubuntu-latest
+    permissions:
+      pull-requests: write
+    outputs:
+      gpu_test: ${{ env.IS_PULL_REQUEST == 'false' || steps.changed-files.outputs.gpu_any_changed }}
+    steps:
+      - name: Checkout tfhe-rs
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          fetch-depth: 0
+          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
+
+      - name: Check for file changes
+        id: changed-files
+        uses: tj-actions/changed-files@bab30c2299617f6615ec02a68b9a40d10bd21366
+        with:
+          since_last_remote_commit: true
+          files_yaml: |
+            gpu:
+              - tfhe/Cargo.toml
+              - tfhe/build.rs
+              - backends/tfhe-cuda-backend/**
+              - tfhe/src/core_crypto/gpu/**
+              - tfhe/src/integer/server_key/radix_parallel/tests_unsigned/**
+              - tfhe/src/integer/server_key/radix_parallel/tests_signed/**
+              - tfhe/src/integer/server_key/radix_parallel/tests_cases_unsigned.rs
+              - tfhe/src/integer/gpu/**
+              - tfhe/src/shortint/parameters/**
+              - tfhe/src/high_level_api/**
+              - tfhe/src/c_api/**
+              - 'tfhe/docs/**.md'
+              - '.github/workflows/gpu_signed_integer_classic_tests.yml'
+              - scripts/integer-tests.sh
+              - ci/slab.toml
+
+  setup-instance:
+    name: Setup instance (cuda-signed-classic-tests)
+    needs: should-run
+    if: github.event_name != 'pull_request' ||
+      (github.event.action != 'labeled' && needs.should-run.outputs.gpu_test == 'true') ||
+      (github.event.action == 'labeled' && github.event.label.name == 'approved' && needs.should-run.outputs.gpu_test == 'true')
+    runs-on: ubuntu-latest
+    outputs:
+      runner-name: ${{ steps.start-instance.outputs.label }}
+    steps:
+      - name: Start instance
+        id: start-instance
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
+        with:
+          mode: start
+          github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
+          slab-url: ${{ secrets.SLAB_BASE_URL }}
+          job-secret: ${{ secrets.JOB_SECRET }}
+          backend: hyperstack
+          profile: gpu-test
+
+  cuda-tests-linux:
+    name: CUDA signed integer tests with classical PBS
+    needs: [ should-run, setup-instance ]
+    if: github.event_name != 'pull_request' ||
+      (github.event_name == 'pull_request' && needs.setup-instance.result != 'skipped')
+    concurrency:
+      group: ${{ github.workflow }}_${{ github.ref }}
+      cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
+    runs-on: ${{ needs.setup-instance.outputs.runner-name }}
+    strategy:
+      fail-fast: false
+      # explicit include-based build matrix, of known valid options
+      matrix:
+        include:
+          - os: ubuntu-22.04
+            cuda: "12.2"
+            gcc: 11 
+    env:
+      CUDA_PATH: /usr/local/cuda-${{ matrix.cuda }}
+      CMAKE_VERSION: 3.29.6
+    steps:
+      # Mandatory on hyperstack since a bootable volume is not re-usable yet.
+      - name: Install dependencies
+        run: |
+          sudo apt update
+          sudo apt install -y checkinstall zlib1g-dev libssl-dev libclang-dev
+          wget https://github.com/Kitware/CMake/releases/download/v${{ env.CMAKE_VERSION }}/cmake-${{ env.CMAKE_VERSION }}.tar.gz
+          tar -zxvf cmake-${{ env.CMAKE_VERSION }}.tar.gz
+          cd cmake-${{ env.CMAKE_VERSION }}
+          ./bootstrap
+          make -j"$(nproc)"
+          sudo make install
+
+
+      - name: Checkout tfhe-rs
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+
+      - name: Set up home
+        run: |
+          echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
+
+      - name: Install latest stable
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
+        with:
+          toolchain: stable
+
+      - name: Export CUDA variables
+        if: ${{ !cancelled() }}
+        run: |
+          echo "CUDA_PATH=$CUDA_PATH" >> "${GITHUB_ENV}"
+          echo "$CUDA_PATH/bin" >> "${GITHUB_PATH}"
+          echo "LD_LIBRARY_PATH=$CUDA_PATH/lib:$LD_LIBRARY_PATH" >> "${GITHUB_ENV}"
+          echo "CUDACXX=/usr/local/cuda-${{ matrix.cuda }}/bin/nvcc" >> "${GITHUB_ENV}"
+
+      # Specify the correct host compilers
+      - name: Export gcc and g++ variables
+        if: ${{ !cancelled() }}
+        run: |
+          {
+            echo "CC=/usr/bin/gcc-${{ matrix.gcc }}";
+            echo "CXX=/usr/bin/g++-${{ matrix.gcc }}";
+            echo "CUDAHOSTCXX=/usr/bin/g++-${{ matrix.gcc }}";
+            echo "HOME=/home/ubuntu";
+          } >> "${GITHUB_ENV}"
+
+      - name: Check device is detected
+        if: ${{ !cancelled() }}
+        run: nvidia-smi
+
+      - name: Run signed integer tests
+        run: |
+          BIG_TESTS_INSTANCE=TRUE make test_signed_integer_gpu_ci
+
+  slack-notify:
+    name: Slack Notification
+    needs: [ setup-instance, cuda-tests-linux ]
+    runs-on: ubuntu-latest
+    if: ${{ always() && needs.cuda-tests-linux.result != 'skipped' && failure() }}
+    continue-on-error: true
+    steps:
+      - name: Send message
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        env:
+          SLACK_COLOR: ${{ needs.cuda-tests-linux.result }}
+          SLACK_MESSAGE: "Integer GPU signed integer tests with classical PBS finished with status: ${{ needs.cuda-tests-linux.result }}. (${{ env.ACTION_RUN_URL }})"
+
+  teardown-instance:
+    name: Teardown instance (cuda-signed-classic-tests)
+    if: ${{ always() && needs.setup-instance.result != 'skipped' }}
+    needs: [ setup-instance, cuda-tests-linux ]
+    runs-on: ubuntu-latest
+    steps:
+      - name: Stop instance
+        id: stop-instance
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
+        with:
+          mode: stop
+          github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
+          slab-url: ${{ secrets.SLAB_BASE_URL }}
+          job-secret: ${{ secrets.JOB_SECRET }}
+          label: ${{ needs.setup-instance.outputs.runner-name }}
+
+      - name: Slack Notification
+        if: ${{ failure() }}
+        continue-on-error: true
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        env:
+          SLACK_COLOR: ${{ job.status }}
+          SLACK_MESSAGE: "Instance teardown (cuda-signed-classic-tests) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/gpu_signed_integer_h100_tests.yml

@@ -28,14 +28,14 @@ jobs:
       gpu_test: ${{ env.IS_PULL_REQUEST == 'false' || steps.changed-files.outputs.gpu_any_changed }}
     steps:
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
           token: ${{ secrets.FHE_ACTIONS_TOKEN }}
 
       - name: Check for file changes
         id: changed-files
-        uses: tj-actions/changed-files@48d8f15b2aaa3d255ca5af3eba4870f807ce6b3c
+        uses: tj-actions/changed-files@bab30c2299617f6615ec02a68b9a40d10bd21366
         with:
           since_last_remote_commit: true
           files_yaml: |
@@ -44,15 +44,17 @@ jobs:
               - tfhe/build.rs
               - backends/tfhe-cuda-backend/**
               - tfhe/src/core_crypto/gpu/**
+              - tfhe/src/integer/server_key/radix_parallel/tests_unsigned/**
+              - tfhe/src/integer/server_key/radix_parallel/tests_signed/**
+              - tfhe/src/integer/server_key/radix_parallel/tests_cases_unsigned.rs
               - tfhe/src/integer/gpu/**
               - tfhe/src/shortint/parameters/**
               - tfhe/src/high_level_api/**
               - tfhe/src/c_api/**
               - 'tfhe/docs/**.md'
-              - Makefile
               - '.github/workflows/gpu_signed_integer_h100_tests.yml'
-              - scripts/**
-              - ci/**
+              - scripts/integer-tests.sh
+              - ci/slab.toml
 
   setup-instance:
     name: Setup instance (cuda-h100-tests)
@@ -66,7 +68,7 @@ jobs:
     steps:
       - name: Start instance
         id: start-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: start
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -100,7 +102,7 @@ jobs:
       - name: Install dependencies
         run: |
           sudo apt update
-          sudo apt install -y checkinstall zlib1g-dev libssl-dev 
+          sudo apt install -y checkinstall zlib1g-dev libssl-dev libclang-dev
           wget https://github.com/Kitware/CMake/releases/download/v${{ env.CMAKE_VERSION }}/cmake-${{ env.CMAKE_VERSION }}.tar.gz
           tar -zxvf cmake-${{ env.CMAKE_VERSION }}.tar.gz
           cd cmake-${{ env.CMAKE_VERSION }}
@@ -108,15 +110,16 @@ jobs:
           make -j"$(nproc)"
           sudo make install
 
+
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
 
       - name: Set up home
         run: |
           echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: stable
 
@@ -143,10 +146,6 @@ jobs:
         if: ${{ !cancelled() }}
         run: nvidia-smi
 
-      - name: Run signed integer tests
-        run: |
-          BIG_TESTS_INSTANCE=TRUE make test_signed_integer_gpu_ci
-
       - name: Run signed integer multi-bit tests
         run: |
           BIG_TESTS_INSTANCE=TRUE make test_signed_integer_multi_bit_gpu_ci
@@ -159,7 +158,7 @@ jobs:
     continue-on-error: true
     steps:
       - name: Send message
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ needs.cuda-tests-linux.result }}
           SLACK_MESSAGE: "Integer GPU H100 tests finished with status: ${{ needs.cuda-tests-linux.result }}. (${{ env.ACTION_RUN_URL }})"
@@ -172,7 +171,7 @@ jobs:
     steps:
       - name: Stop instance
         id: stop-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: stop
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -183,7 +182,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Instance teardown (cuda-h100-tests) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/gpu_signed_integer_tests.yml

@@ -22,7 +22,6 @@ on:
     types:
       - opened
       - synchronize
-      - labeled
   schedule:
     # Nightly tests @ 1AM after each work day
     - cron: "0 1 * * MON-FRI"
@@ -36,13 +35,14 @@ jobs:
       gpu_test: ${{ env.IS_PULL_REQUEST == 'false' || steps.changed-files.outputs.gpu_any_changed }}
     steps:
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
+          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
 
       - name: Check for file changes
         id: changed-files
-        uses: tj-actions/changed-files@48d8f15b2aaa3d255ca5af3eba4870f807ce6b3c
+        uses: tj-actions/changed-files@bab30c2299617f6615ec02a68b9a40d10bd21366
         with:
           since_last_remote_commit: true
           files_yaml: |
@@ -51,15 +51,17 @@ jobs:
               - tfhe/build.rs
               - backends/tfhe-cuda-backend/**
               - tfhe/src/core_crypto/gpu/**
+              - tfhe/src/integer/server_key/radix_parallel/tests_unsigned/**
+              - tfhe/src/integer/server_key/radix_parallel/tests_signed/**
+              - tfhe/src/integer/server_key/radix_parallel/tests_cases_unsigned.rs
               - tfhe/src/integer/gpu/**
               - tfhe/src/shortint/parameters/**
               - tfhe/src/high_level_api/**
               - tfhe/src/c_api/**
               - 'tfhe/docs/**.md'
               - '.github/workflows/gpu_signed_integer_tests.yml'
-              - Makefile
-              - scripts/**
-              - ci/**
+              - scripts/integer-tests.sh
+              - ci/slab.toml
 
   setup-instance:
     name: Setup instance (cuda-signed-integer-tests)
@@ -67,13 +69,13 @@ jobs:
     needs: should-run
     if: (github.event_name == 'schedule' && github.repository == 'zama-ai/tfhe-rs') ||
       github.event_name == 'workflow_dispatch' ||
-      (github.event.action != 'labeled' && needs.should-run.outputs.gpu_test == 'true')
+      needs.should-run.outputs.gpu_test == 'true'
     outputs:
       runner-name: ${{ steps.start-instance.outputs.label }}
     steps:
       - name: Start instance
         id: start-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: start
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -107,7 +109,7 @@ jobs:
       - name: Install dependencies
         run: |
           sudo apt update
-          sudo apt install -y checkinstall zlib1g-dev libssl-dev 
+          sudo apt install -y checkinstall zlib1g-dev libssl-dev libclang-dev
           wget https://github.com/Kitware/CMake/releases/download/v${{ env.CMAKE_VERSION }}/cmake-${{ env.CMAKE_VERSION }}.tar.gz
           tar -zxvf cmake-${{ env.CMAKE_VERSION }}.tar.gz
           cd cmake-${{ env.CMAKE_VERSION }}
@@ -115,8 +117,9 @@ jobs:
           make -j"$(nproc)"
           sudo make install
 
+
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           persist-credentials: 'false'
           token: ${{ secrets.FHE_ACTIONS_TOKEN }}
@@ -126,7 +129,7 @@ jobs:
           echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: stable
 
@@ -173,7 +176,7 @@ jobs:
     continue-on-error: true
     steps:
       - name: Send message
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ needs.cuda-signed-integer-tests.result }}
           SLACK_MESSAGE: "Base GPU tests finished with status: ${{ needs.cuda-signed-integer-tests.result }}. (${{ env.ACTION_RUN_URL }})"
@@ -186,7 +189,7 @@ jobs:
     steps:
       - name: Stop instance
         id: stop-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: stop
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -197,7 +200,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Instance teardown (cuda-signed-integer-tests) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/gpu_unsigned_integer_classic_tests.yml

@@ -0,0 +1,188 @@
+# Test unsigned integers on an RTXA6000 VM on hyperstack with the classical PBS
+name: TFHE Cuda Backend - Unsigned integer tests with classical PBS
+
+env:
+  CARGO_TERM_COLOR: always
+  ACTION_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
+  RUSTFLAGS: "-C target-cpu=native"
+  RUST_BACKTRACE: "full"
+  RUST_MIN_STACK: "8388608"
+  SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
+  SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
+  SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
+  SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+  IS_PULL_REQUEST: ${{ github.event_name == 'pull_request' }}
+
+on:
+  # Allows you to run this workflow manually from the Actions tab as an alternative.
+  workflow_dispatch:
+  pull_request:
+      types: [ labeled ]
+
+jobs:
+  should-run:
+    runs-on: ubuntu-latest
+    permissions:
+      pull-requests: write
+    outputs:
+      gpu_test: ${{ env.IS_PULL_REQUEST == 'false' || steps.changed-files.outputs.gpu_any_changed }}
+    steps:
+      - name: Checkout tfhe-rs
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          fetch-depth: 0
+          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
+
+      - name: Check for file changes
+        id: changed-files
+        uses: tj-actions/changed-files@bab30c2299617f6615ec02a68b9a40d10bd21366
+        with:
+          since_last_remote_commit: true
+          files_yaml: |
+            gpu:
+              - tfhe/Cargo.toml
+              - tfhe/build.rs
+              - backends/tfhe-cuda-backend/**
+              - tfhe/src/core_crypto/gpu/**
+              - tfhe/src/integer/server_key/radix_parallel/tests_unsigned/**
+              - tfhe/src/integer/server_key/radix_parallel/tests_signed/**
+              - tfhe/src/integer/server_key/radix_parallel/tests_cases_unsigned.rs
+              - tfhe/src/integer/gpu/**
+              - tfhe/src/shortint/parameters/**
+              - tfhe/src/high_level_api/**
+              - tfhe/src/c_api/**
+              - 'tfhe/docs/**.md'
+              - '.github/workflows/gpu_unsigned_integer_classic_tests.yml'
+              - scripts/integer-tests.sh
+              - ci/slab.toml
+
+  setup-instance:
+    name: Setup instance (cuda-unsigned-classic-tests)
+    needs: should-run
+    if: github.event_name != 'pull_request' ||
+      (github.event.action != 'labeled' && needs.should-run.outputs.gpu_test == 'true') ||
+      (github.event.action == 'labeled' && github.event.label.name == 'approved' && needs.should-run.outputs.gpu_test == 'true')
+    runs-on: ubuntu-latest
+    outputs:
+      runner-name: ${{ steps.start-instance.outputs.label }}
+    steps:
+      - name: Start instance
+        id: start-instance
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
+        with:
+          mode: start
+          github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
+          slab-url: ${{ secrets.SLAB_BASE_URL }}
+          job-secret: ${{ secrets.JOB_SECRET }}
+          backend: hyperstack
+          profile: gpu-test
+
+  cuda-tests-linux:
+    name: CUDA unsigned integer tests with classical PBS
+    needs: [ should-run, setup-instance ]
+    if: github.event_name != 'pull_request' ||
+      (github.event_name == 'pull_request' && needs.setup-instance.result != 'skipped')
+    concurrency:
+      group: ${{ github.workflow }}_${{ github.ref }}
+      cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
+    runs-on: ${{ needs.setup-instance.outputs.runner-name }}
+    strategy:
+      fail-fast: false
+      # explicit include-based build matrix, of known valid options
+      matrix:
+        include:
+          - os: ubuntu-22.04
+            cuda: "12.2"
+            gcc: 11 
+    env:
+      CUDA_PATH: /usr/local/cuda-${{ matrix.cuda }}
+      CMAKE_VERSION: 3.29.6
+    steps:
+      # Mandatory on hyperstack since a bootable volume is not re-usable yet.
+      - name: Install dependencies
+        run: |
+          sudo apt update
+          sudo apt install -y checkinstall zlib1g-dev libssl-dev libclang-dev
+          wget https://github.com/Kitware/CMake/releases/download/v${{ env.CMAKE_VERSION }}/cmake-${{ env.CMAKE_VERSION }}.tar.gz
+          tar -zxvf cmake-${{ env.CMAKE_VERSION }}.tar.gz
+          cd cmake-${{ env.CMAKE_VERSION }}
+          ./bootstrap
+          make -j"$(nproc)"
+          sudo make install
+
+
+      - name: Checkout tfhe-rs
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+
+      - name: Set up home
+        run: |
+          echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
+
+      - name: Install latest stable
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
+        with:
+          toolchain: stable
+
+      - name: Export CUDA variables
+        if: ${{ !cancelled() }}
+        run: |
+          echo "CUDA_PATH=$CUDA_PATH" >> "${GITHUB_ENV}"
+          echo "$CUDA_PATH/bin" >> "${GITHUB_PATH}"
+          echo "LD_LIBRARY_PATH=$CUDA_PATH/lib:$LD_LIBRARY_PATH" >> "${GITHUB_ENV}"
+          echo "CUDACXX=/usr/local/cuda-${{ matrix.cuda }}/bin/nvcc" >> "${GITHUB_ENV}"
+
+      # Specify the correct host compilers
+      - name: Export gcc and g++ variables
+        if: ${{ !cancelled() }}
+        run: |
+          {
+            echo "CC=/usr/bin/gcc-${{ matrix.gcc }}";
+            echo "CXX=/usr/bin/g++-${{ matrix.gcc }}";
+            echo "CUDAHOSTCXX=/usr/bin/g++-${{ matrix.gcc }}";
+            echo "HOME=/home/ubuntu";
+          } >> "${GITHUB_ENV}"
+
+      - name: Check device is detected
+        if: ${{ !cancelled() }}
+        run: nvidia-smi
+
+      - name: Run unsigned integer tests
+        run: |
+          BIG_TESTS_INSTANCE=TRUE make test_unsigned_integer_gpu_ci
+
+  slack-notify:
+    name: Slack Notification
+    needs: [ setup-instance, cuda-tests-linux ]
+    runs-on: ubuntu-latest
+    if: ${{ always() && needs.cuda-tests-linux.result != 'skipped' && failure() }}
+    continue-on-error: true
+    steps:
+      - name: Send message
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        env:
+          SLACK_COLOR: ${{ needs.cuda-tests-linux.result }}
+          SLACK_MESSAGE: "Unsigned integer GPU classic tests finished with status: ${{ needs.cuda-tests-linux.result }}. (${{ env.ACTION_RUN_URL }})"
+
+  teardown-instance:
+    name: Teardown instance (cuda-unsigned-classic-tests)
+    if: ${{ always() && needs.setup-instance.result != 'skipped' }}
+    needs: [ setup-instance, cuda-tests-linux ]
+    runs-on: ubuntu-latest
+    steps:
+      - name: Stop instance
+        id: stop-instance
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
+        with:
+          mode: stop
+          github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
+          slab-url: ${{ secrets.SLAB_BASE_URL }}
+          job-secret: ${{ secrets.JOB_SECRET }}
+          label: ${{ needs.setup-instance.outputs.runner-name }}
+
+      - name: Slack Notification
+        if: ${{ failure() }}
+        continue-on-error: true
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        env:
+          SLACK_COLOR: ${{ job.status }}
+          SLACK_MESSAGE: "Instance teardown (cuda-unsigned-classic-tests) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/gpu_unsigned_integer_h100_tests.yml

@@ -28,14 +28,14 @@ jobs:
       gpu_test: ${{ env.IS_PULL_REQUEST == 'false' || steps.changed-files.outputs.gpu_any_changed }}
     steps:
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
           token: ${{ secrets.FHE_ACTIONS_TOKEN }}
 
       - name: Check for file changes
         id: changed-files
-        uses: tj-actions/changed-files@48d8f15b2aaa3d255ca5af3eba4870f807ce6b3c
+        uses: tj-actions/changed-files@bab30c2299617f6615ec02a68b9a40d10bd21366
         with:
           since_last_remote_commit: true
           files_yaml: |
@@ -44,15 +44,17 @@ jobs:
               - tfhe/build.rs
               - backends/tfhe-cuda-backend/**
               - tfhe/src/core_crypto/gpu/**
+              - tfhe/src/integer/server_key/radix_parallel/tests_unsigned/**
+              - tfhe/src/integer/server_key/radix_parallel/tests_signed/**
+              - tfhe/src/integer/server_key/radix_parallel/tests_cases_unsigned.rs
               - tfhe/src/integer/gpu/**
               - tfhe/src/shortint/parameters/**
               - tfhe/src/high_level_api/**
               - tfhe/src/c_api/**
               - 'tfhe/docs/**.md'
-              - Makefile
-              - '.github/workflows/gpu_unsigned_integer_tests.yml'
-              - scripts/**
-              - ci/**
+              - '.github/workflows/gpu_unsigned_integer_h100_tests.yml'
+              - scripts/integer-tests.sh
+              - ci/slab.toml
 
   setup-instance:
     name: Setup instance (cuda-h100-tests)
@@ -66,7 +68,7 @@ jobs:
     steps:
       - name: Start instance
         id: start-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: start
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -100,7 +102,7 @@ jobs:
       - name: Install dependencies
         run: |
           sudo apt update
-          sudo apt install -y checkinstall zlib1g-dev libssl-dev 
+          sudo apt install -y checkinstall zlib1g-dev libssl-dev libclang-dev
           wget https://github.com/Kitware/CMake/releases/download/v${{ env.CMAKE_VERSION }}/cmake-${{ env.CMAKE_VERSION }}.tar.gz
           tar -zxvf cmake-${{ env.CMAKE_VERSION }}.tar.gz
           cd cmake-${{ env.CMAKE_VERSION }}
@@ -108,15 +110,16 @@ jobs:
           make -j"$(nproc)"
           sudo make install
 
+
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
 
       - name: Set up home
         run: |
           echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: stable
 
@@ -143,10 +146,6 @@ jobs:
         if: ${{ !cancelled() }}
         run: nvidia-smi
 
-      - name: Run unsigned integer tests
-        run: |
-          BIG_TESTS_INSTANCE=TRUE make test_unsigned_integer_gpu_ci
-
       - name: Run unsigned integer multi-bit tests
         run: |
           BIG_TESTS_INSTANCE=TRUE make test_unsigned_integer_multi_bit_gpu_ci
@@ -159,7 +158,7 @@ jobs:
     continue-on-error: true
     steps:
       - name: Send message
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ needs.cuda-tests-linux.result }}
           SLACK_MESSAGE: "Unsigned integer GPU H100 tests finished with status: ${{ needs.cuda-tests-linux.result }}. (${{ env.ACTION_RUN_URL }})"
@@ -172,7 +171,7 @@ jobs:
     steps:
       - name: Stop instance
         id: stop-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: stop
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -183,7 +182,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Instance teardown (cuda-h100-tests) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/gpu_unsigned_integer_tests.yml

@@ -21,7 +21,6 @@ on:
     types:
       - opened
       - synchronize
-      - labeled
   schedule:
     # Nightly tests @ 1AM after each work day
     - cron: "0 1 * * MON-FRI"
@@ -35,14 +34,14 @@ jobs:
       gpu_test: ${{ env.IS_PULL_REQUEST == 'false' || steps.changed-files.outputs.gpu_any_changed }}
     steps:
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
           token: ${{ secrets.FHE_ACTIONS_TOKEN }}
 
       - name: Check for file changes
         id: changed-files
-        uses: tj-actions/changed-files@48d8f15b2aaa3d255ca5af3eba4870f807ce6b3c
+        uses: tj-actions/changed-files@bab30c2299617f6615ec02a68b9a40d10bd21366
         with:
           since_last_remote_commit: true
           files_yaml: |
@@ -51,29 +50,31 @@ jobs:
               - tfhe/build.rs
               - backends/tfhe-cuda-backend/**
               - tfhe/src/core_crypto/gpu/**
+              - tfhe/src/integer/server_key/radix_parallel/tests_unsigned/**
+              - tfhe/src/integer/server_key/radix_parallel/tests_signed/**
+              - tfhe/src/integer/server_key/radix_parallel/tests_cases_unsigned.rs
               - tfhe/src/integer/gpu/**
               - tfhe/src/shortint/parameters/**
               - tfhe/src/high_level_api/**
               - tfhe/src/c_api/**
               - 'tfhe/docs/**.md'
               - '.github/workflows/gpu_unsigned_integer_tests.yml'
-              - Makefile
-              - scripts/**
-              - ci/**
+              - scripts/integer-tests.sh
+              - ci/slab.toml
 
   setup-instance:
     name: Setup instance (cuda-unsigned-integer-tests)
     needs: should-run
     if: (github.event_name == 'schedule' && github.repository == 'zama-ai/tfhe-rs') ||
       github.event_name == 'workflow_dispatch' ||
-      (github.event.action != 'labeled' && needs.should-run.outputs.gpu_test == 'true')
+      needs.should-run.outputs.gpu_test == 'true'
     runs-on: ubuntu-latest
     outputs:
       runner-name: ${{ steps.start-instance.outputs.label }}
     steps:
       - name: Start instance
         id: start-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: start
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -107,7 +108,7 @@ jobs:
       - name: Install dependencies
         run: |
           sudo apt update
-          sudo apt install -y checkinstall zlib1g-dev libssl-dev 
+          sudo apt install -y checkinstall zlib1g-dev libssl-dev libclang-dev
           wget https://github.com/Kitware/CMake/releases/download/v${{ env.CMAKE_VERSION }}/cmake-${{ env.CMAKE_VERSION }}.tar.gz
           tar -zxvf cmake-${{ env.CMAKE_VERSION }}.tar.gz
           cd cmake-${{ env.CMAKE_VERSION }}
@@ -115,15 +116,16 @@ jobs:
           make -j"$(nproc)"
           sudo make install
 
+
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
 
       - name: Set up home
         run: |
           echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: stable
 
@@ -170,7 +172,7 @@ jobs:
     continue-on-error: true
     steps:
       - name: Send message
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ needs.cuda-unsigned-integer-tests.result }}
           SLACK_MESSAGE: "Unsigned integer GPU tests finished with status: ${{ needs.cuda-unsigned-integer-tests.result }}. (${{ env.ACTION_RUN_URL }})"
@@ -183,7 +185,7 @@ jobs:
     steps:
       - name: Stop instance
         id: stop-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: stop
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -194,7 +196,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Instance teardown (cuda-unsigned-integer-tests) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/integer_long_run_tests.yml

@@ -0,0 +1,94 @@
+name: AWS Long Run Tests on CPU
+
+env:
+  CARGO_TERM_COLOR: always
+  ACTION_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
+  RUSTFLAGS: "-C target-cpu=native"
+  RUST_BACKTRACE: "full"
+  RUST_MIN_STACK: "8388608"
+  SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
+  SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
+  SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
+  SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+
+on:
+  # Allows you to run this workflow manually from the Actions tab as an alternative.
+  workflow_dispatch:
+  schedule:
+    # Weekly tests will be triggered each Friday at 1a.m.
+    - cron: '0 1 * * FRI'
+
+jobs:
+  setup-instance:
+    name: Setup instance (cpu-tests)
+    if: github.event_name != 'schedule' ||
+      (github.event_name == 'schedule' && github.repository == 'zama-ai/tfhe-rs')
+    runs-on: ubuntu-latest
+    outputs:
+      runner-name: ${{ steps.start-instance.outputs.label }}
+    steps:
+      - name: Start instance
+        id: start-instance
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
+        with:
+          mode: start
+          github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
+          slab-url: ${{ secrets.SLAB_BASE_URL }}
+          job-secret: ${{ secrets.JOB_SECRET }}
+          backend: aws
+          profile: cpu-big
+
+  cpu-tests:
+    name: Long run CPU tests
+    needs: [ setup-instance ]
+    concurrency:
+      group: ${{ github.workflow }}_${{github.event_name}}_${{ github.ref }}
+      cancel-in-progress: true
+    runs-on: ${{ needs.setup-instance.outputs.runner-name }}
+    steps:
+      - name: Checkout tfhe-rs
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          persist-credentials: 'false'
+          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
+
+      - name: Install latest stable
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
+        with:
+          toolchain: stable
+
+      - name: Run tests
+        run: |
+          make test_integer_long_run
+
+      - name: Slack Notification
+        if: ${{ failure() }}
+        continue-on-error: true
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        env:
+          SLACK_COLOR: ${{ job.status }}
+          SLACK_MESSAGE: "CPU long run tests finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
+
+  teardown-instance:
+    name: Teardown instance (cpu-tests)
+    if: ${{ always() && needs.setup-instance.result != 'skipped' }}
+    needs: [ setup-instance, cpu-tests ]
+    runs-on: ubuntu-latest
+    steps:
+      - name: Stop instance
+        id: stop-instance
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
+        with:
+          mode: stop
+          github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
+          slab-url: ${{ secrets.SLAB_BASE_URL }}
+          job-secret: ${{ secrets.JOB_SECRET }}
+          label: ${{ needs.setup-instance.outputs.runner-name }}
+
+      - name: Slack Notification
+        if: ${{ failure() }}
+        continue-on-error: true
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        env:
+          SLACK_COLOR: ${{ job.status }}
+          SLACK_MESSAGE: "Instance teardown (cpu-long-run-tests) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/m1_tests.yml

@@ -3,7 +3,7 @@ name: Tests on M1 CPU
 on:
   workflow_dispatch:
   pull_request:
-    types: [ labeled ]
+    types: [labeled]
   # Have a nightly build for M1 tests
   schedule:
     # * is a special character in YAML so you have to quote this string
@@ -27,29 +27,66 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
-  cargo-builds:
+  cargo-builds-m1:
     if: ${{ (github.event_name == 'schedule' &&  github.repository == 'zama-ai/tfhe-rs') || github.event_name == 'workflow_dispatch' || contains(github.event.label.name, 'm1_test') }}
     runs-on: ["self-hosted", "m1mac"]
     # 12 hours, default is 6 hours, hopefully this is more than enough
     timeout-minutes: 720
 
     steps:
-      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
-          persist-credentials: 'false'
+          persist-credentials: "false"
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: stable
 
+      - name: Run pcc FFT checks
+        run: |
+          make pcc_fft
+
+      - name: Build FFT release
+        run: |
+          make build_fft
+
+      - name: Build FFT release no-std
+        run: |
+          make build_fft_no_std
+
+      - name: Run FFT tests
+        run: |
+          make test_fft
+          make test_fft_serde
+          make test_fft_nightly
+          make test_fft_no_std
+          make test_fft_no_std_nightly
+          # we don't run the js stuff here as it's causing issues with the M1 config
+
+      - name: Run pcc NTT checks
+        run: |
+          make pcc_ntt
+
+      - name: Build NTT release
+        run: |
+          make build_ntt
+
+      - name: Build NTT release no-std
+        run: |
+          make build_ntt_no_std
+
+      - name: Run NTT tests
+        run: |
+          make test_ntt_all
+
       - name: Run pcc checks
         run: |
           make pcc
 
-      - name: Build concrete-csprng
+      - name: Build tfhe-csprng
         run: |
-          make build_concrete_csprng
+          make build_tfhe_csprng
 
       - name: Build Release core
         run: |
@@ -75,9 +112,9 @@ jobs:
         run: |
           make build_c_api
 
-      - name: Run concrete-csprng tests
+      - name: Run tfhe-csprng tests
         run: |
-          make test_concrete_csprng
+          make test_tfhe_csprng
 
       - name: Run tfhe-zk-pok tests
         run: |
@@ -137,7 +174,7 @@ jobs:
     name: Remove m1_test label
     runs-on: ubuntu-latest
     needs:
-      - cargo-builds
+      - cargo-builds-m1
     if: ${{ always() }}
     steps:
       - uses: actions-ecosystem/action-remove-labels@2ce5d41b4b6aa8503e285553f75ed56e0a40bae0
@@ -147,13 +184,13 @@ jobs:
           github_token: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Slack Notification
-        if: ${{ needs.cargo-builds.result != 'skipped' }}
+        if: ${{ needs.cargo-builds-m1.result != 'skipped' }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
-          SLACK_COLOR: ${{ needs.cargo-builds.result }}
+          SLACK_COLOR: ${{ needs.cargo-builds-m1.result }}
           SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
           SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
-          SLACK_MESSAGE: "M1 tests finished with status: ${{ needs.cargo-builds.result }}. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "M1 tests finished with status: ${{ needs.cargo-builds-m1.result }}. (${{ env.ACTION_RUN_URL }})"
           SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
           SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}

.github/workflows/make_release.yml

@@ -30,19 +30,27 @@ env:
   NPM_TAG: ""
 
 jobs:
+  verify_tag:
+    uses: ./.github/workflows/verify_tagged_commit.yml
+    secrets:
+      RELEASE_TEAM: ${{ secrets.RELEASE_TEAM }}
+      READ_ORG_TOKEN: ${{ secrets.READ_ORG_TOKEN }}
+
   package:
     runs-on: ubuntu-latest
+    needs: verify_tag
     outputs:
       hash: ${{ steps.hash.outputs.hash }}
     steps:
       - name: Checkout
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
+          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
       - name: Prepare package
         run: |
           cargo package -p tfhe
-      - uses: actions/upload-artifact@50769540e7f4bd5e21e526ee35c689e35e0d6874 # v4.4.0
+      - uses: actions/upload-artifact@b4b15b8c7c6ac21ea08fcf65892d2ee8f75cf882 # v4.4.3
         with:
           name: crate
           path: target/package/*.crate
@@ -74,9 +82,10 @@ jobs:
       id-token: write
     steps:
       - name: Checkout
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
+          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
       - name: Create NPM version tag
         if: ${{ inputs.npm_latest_tag }}
         run: |
@@ -101,7 +110,7 @@ jobs:
       - name: Slack notification (hashes comparison)
         if: ${{ needs.package.outputs.hash != steps.published_hash.outputs.pub_hash }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: failure
           SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
@@ -146,7 +155,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}

.github/workflows/make_release_concrete_csprng.yml

@@ -1,4 +1,4 @@
-name: Publish concrete-csprng release
+name: Publish tfhe-csprng release
 
 on:
   workflow_dispatch:
@@ -12,30 +12,38 @@ env:
   ACTION_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
 
 jobs:
+  verify_tag:
+    uses: ./.github/workflows/verify_tagged_commit.yml
+    secrets:
+      RELEASE_TEAM: ${{ secrets.RELEASE_TEAM }}
+      READ_ORG_TOKEN: ${{ secrets.READ_ORG_TOKEN }}
+
   publish_release:
-    name: Publish concrete-csprng Release
+    name: Publish tfhe-csprng Release
+    needs: verify_tag
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
+          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
 
       - name: Publish crate.io package
         env:
           CRATES_TOKEN: ${{ secrets.CARGO_REGISTRY_TOKEN }}
           DRY_RUN: ${{ inputs.dry_run && '--dry-run' || '' }}
         run: |
-          cargo publish -p concrete-csprng --token ${{ env.CRATES_TOKEN }} ${{ env.DRY_RUN }}
+          cargo publish -p tfhe-csprng --token ${{ env.CRATES_TOKEN }} ${{ env.DRY_RUN }}
 
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
           SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
-          SLACK_MESSAGE: "concrete-csprng release finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "tfhe-csprng release finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
           SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
           SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}

.github/workflows/make_release_cuda.yml

@@ -21,15 +21,22 @@ env:
   SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
 
 jobs:
+  verify_tag:
+    uses: ./.github/workflows/verify_tagged_commit.yml
+    secrets:
+      RELEASE_TEAM: ${{ secrets.RELEASE_TEAM }}
+      READ_ORG_TOKEN: ${{ secrets.READ_ORG_TOKEN }}
+
   setup-instance:
     name: Setup instance (publish-cuda-release)
+    needs: verify_tag
     runs-on: ubuntu-latest
     outputs:
       runner-name: ${{ steps.start-instance.outputs.label }}
     steps:
       - name: Start instance
         id: start-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: start
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -54,16 +61,17 @@ jobs:
       CUDA_PATH: /usr/local/cuda-${{ matrix.cuda }}
     steps:
       - name: Checkout
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
+          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
 
       - name: Set up home
         run: |
           echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@7b1c307e0dcbda6122208f10795a713336a9b35a
+        uses: dtolnay/rust-toolchain@315e265cd78dad1e1dcf3a5074f6d6c47029d5aa
         with:
           toolchain: stable
 
@@ -99,7 +107,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "tfhe-cuda-backend release finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
@@ -112,7 +120,7 @@ jobs:
     steps:
       - name: Stop instance
         id: stop-instance
-        uses: zama-ai/slab-github-runner@c0e7168795bd78f61f61146951ed9d0c73c9b701
+        uses: zama-ai/slab-github-runner@98f0788261a7323d5d695a883e20df36591a92b7
         with:
           mode: stop
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
@@ -123,7 +131,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Instance teardown (publish-cuda-release) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/make_release_tfhe_fft.yml

@@ -0,0 +1,49 @@
+# Publish new release of tfhe-fft
+name: Publish tfhe-fft release
+
+on:
+  workflow_dispatch:
+    inputs:
+      dry_run:
+        description: "Dry-run"
+        type: boolean
+        default: true
+
+env:
+  ACTION_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
+
+jobs:
+  verify_tag:
+    uses: ./.github/workflows/verify_tagged_commit.yml
+    secrets:
+      RELEASE_TEAM: ${{ secrets.RELEASE_TEAM }}
+      READ_ORG_TOKEN: ${{ secrets.READ_ORG_TOKEN }}
+
+  publish_release:
+    name: Publish tfhe-fft Release
+    runs-on: ubuntu-latest
+    needs: verify_tag
+    steps:
+      - name: Checkout
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          fetch-depth: 0
+
+      - name: Publish crate.io package
+        env:
+          CRATES_TOKEN: ${{ secrets.CARGO_REGISTRY_TOKEN }}
+          DRY_RUN: ${{ inputs.dry_run && '--dry-run' || '' }}
+        run: |
+          cargo publish -p tfhe-fft --token ${{ env.CRATES_TOKEN }} ${{ env.DRY_RUN }}
+
+      - name: Slack Notification
+        if: ${{ failure() }}
+        continue-on-error: true
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        env:
+          SLACK_COLOR: ${{ job.status }}
+          SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
+          SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
+          SLACK_MESSAGE: "tfhe-fft release failed: (${{ env.ACTION_RUN_URL }})"
+          SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
+          SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}

.github/workflows/make_release_tfhe_ntt.yml

@@ -0,0 +1,49 @@
+# Publish new release of tfhe-ntt
+name: Publish tfhe-ntt release
+
+on:
+  workflow_dispatch:
+    inputs:
+      dry_run:
+        description: "Dry-run"
+        type: boolean
+        default: true
+
+env:
+  ACTION_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
+
+jobs:
+  verify_tag:
+    uses: ./.github/workflows/verify_tagged_commit.yml
+    secrets:
+      RELEASE_TEAM: ${{ secrets.RELEASE_TEAM }}
+      READ_ORG_TOKEN: ${{ secrets.READ_ORG_TOKEN }}
+
+  publish_release:
+    name: Publish tfhe-ntt Release
+    runs-on: ubuntu-latest
+    needs: verify_tag
+    steps:
+      - name: Checkout
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          fetch-depth: 0
+
+      - name: Publish crate.io package
+        env:
+          CRATES_TOKEN: ${{ secrets.CARGO_REGISTRY_TOKEN }}
+          DRY_RUN: ${{ inputs.dry_run && '--dry-run' || '' }}
+        run: |
+          cargo publish -p tfhe-ntt --token ${{ env.CRATES_TOKEN }} ${{ env.DRY_RUN }}
+
+      - name: Slack Notification
+        if: ${{ failure() }}
+        continue-on-error: true
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        env:
+          SLACK_COLOR: ${{ job.status }}
+          SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
+          SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
+          SLACK_MESSAGE: "tfhe-ntt release failed: (${{ env.ACTION_RUN_URL }})"
+          SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
+          SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}

.github/workflows/make_release_tfhe_versionable.yml

@@ -2,31 +2,51 @@ name: Publish tfhe-versionable release
 
 on:
   workflow_dispatch:
+    inputs:
+      dry_run:
+        description: "Dry-run"
+        type: boolean
+        default: true
 
 env:
   ACTION_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
 
 jobs:
+  verify_tag:
+    uses: ./.github/workflows/verify_tagged_commit.yml
+    secrets:
+      RELEASE_TEAM: ${{ secrets.RELEASE_TEAM }}
+      READ_ORG_TOKEN: ${{ secrets.READ_ORG_TOKEN }}
+
   publish_release:
     name: Publish tfhe-versionable Release
+    needs: verify_tag
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
+          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
 
-      - name: Publish crate.io package
+      - name: Publish proc-macro crate
+        env:
+          CRATES_TOKEN: ${{ secrets.CARGO_REGISTRY_TOKEN }}
+          DRY_RUN: ${{ inputs.dry_run && '--dry-run' || '' }}
+        run: |
+          cargo publish -p tfhe-versionable-derive --token ${{ env.CRATES_TOKEN }} ${{ env.DRY_RUN }}
+
+      - name: Publish main crate
+        if: ${{ ! inputs.dry_run }}
         env:
           CRATES_TOKEN: ${{ secrets.CARGO_REGISTRY_TOKEN }}
         run: |
-          cargo publish -p tfhe-versionable-derive --token ${{ env.CRATES_TOKEN }}
           cargo publish -p tfhe-versionable --token ${{ env.CRATES_TOKEN }}
 
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}

.github/workflows/make_release_zk_pok.yml

@@ -13,14 +13,22 @@ env:
   ACTION_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
 
 jobs:
+  verify_tag:
+    uses: ./.github/workflows/verify_tagged_commit.yml
+    secrets:
+      RELEASE_TEAM: ${{ secrets.RELEASE_TEAM }}
+      READ_ORG_TOKEN: ${{ secrets.READ_ORG_TOKEN }}
+
   publish_release:
     name: Publish tfhe-zk-pok Release
+    needs: verify_tag
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
+          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
 
       - name: Publish crate.io package
         env:
@@ -32,7 +40,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}

.github/workflows/parameters_check.yml

@@ -17,10 +17,10 @@ jobs:
     runs-on: large_ubuntu_16
     steps:
       - name: Checkout tfhe-rs
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
 
       - name: Checkout lattice-estimator
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           repository: malb/lattice-estimator
           path: lattice_estimator
@@ -42,7 +42,7 @@ jobs:
       - name: Slack Notification
         if: ${{ always() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@4e5fb42d249be6a45a298f3c9543b111b02f7907
+        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}

.github/workflows/sync_on_push.yml

@@ -13,9 +13,10 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repo
-        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
+          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
       - name: git-sync
         uses: wei/git-sync@55c6b63b4f21607da0e9877ca9b4d11a29fc6d83
         with:

.github/workflows/verify_tagged_commit.yml

@@ -0,0 +1,32 @@
+# Verify a tagged commit
+name: Verify tagged commit
+
+on:
+  workflow_call:
+    secrets:
+      RELEASE_TEAM:
+        required: true
+      READ_ORG_TOKEN:
+        required: true
+
+jobs:
+  checks:
+    runs-on: ubuntu-latest
+    if: startsWith(github.ref, 'refs/tags/')
+    steps:
+      # Check triggering actor membership
+      - name: Actor verification
+        id: actor_check
+        uses: morfien101/actions-authorized-user@4a3cfbf0bcb3cafe4a71710a278920c5d94bb38b
+        with:
+          username: ${{ github.triggering_actor }}
+          org: ${{ github.repository_owner }}
+          team: ${{ secrets.RELEASE_TEAM }}
+          github_token: ${{ secrets.READ_ORG_TOKEN }}
+
+      - name: Actor authorized
+        run: |
+          if [ "${{ steps.actor_check.outputs.authorized }}" == "false" ]; then
+            echo "Actor '${{ github.triggering_actor }}' is not authorized to perform release"
+            exit 1
+          fi

.gitignore

@@ -12,7 +12,8 @@ target/
 **/*.bin
 
 # Some of our bench outputs
-/tfhe/benchmarks_parameters
+/crates/tfhe/benchmarks_parameters
+/crates/tfhe-zk-pok/benchmarks_parameters
 **/*.csv
 
 # dieharder run log
@@ -25,9 +26,11 @@ dieharder_run.log
 backends/tfhe-cuda-backend/cuda/cmake-build-debug/
 
 # WASM tests
-tfhe/web_wasm_parallel_tests/server.PID
+crates/tfhe/tests/web_wasm_parallel/server.PID
 venv/
-web_test_runners/
+web-test-runner/
+node_modules/
+package-lock.json
 
 # Dir used for backward compatibility test data
-tfhe/tfhe-backward-compat-data/
+crates/tfhe/tfhe-backward-compat-data/

Cargo.toml

@@ -1,22 +1,40 @@
 [workspace]
 resolver = "2"
 members = [
-    "tfhe",
-    "tfhe-zk-pok",
+    "crates/*",
     "tasks",
     "apps/trivium",
-    "concrete-csprng",
     "backends/tfhe-cuda-backend",
-    "utils/tfhe-versionable",
-    "utils/tfhe-versionable-derive",
 ]
 
 exclude = [
-    "tfhe/backward_compatibility_tests",
+    "crates/tfhe/backward_compatibility_tests",
     "utils/cargo-tfhe-lints-inner",
     "utils/cargo-tfhe-lints"
 ]
 
+[workspace.dependencies]
+aligned-vec = { version = "0.5", default-features = false }
+bytemuck = "1.14.3"
+dyn-stack = { version = "0.10", default-features = false }
+num-complex = "0.4"
+pulp = { version = "0.18.22", default-features = false }
+serde = { version = "1.0", default-features = false }
+wasm-bindgen = ">=0.2.86,<0.2.94"
+
+[workspace.package]
+version = "0.11.0"
+license = "BSD-3-Clause-Clear"
+repository = "https://github.com/zama-ai/tfhe-rs"
+documentation = "https://docs.zama.ai/tfhe-rs"
+
+[workspace.lints.rust]
+unexpected_cfgs = { level = "warn", check-cfg = [
+    'cfg(bench)',
+    'cfg(tarpaulin)',
+    'cfg(tfhe_lints)',
+] }
+
 [profile.bench]
 lto = "fat"
 

Makefile

@@ -5,9 +5,10 @@ CARGO_RS_CHECK_TOOLCHAIN:=+$(RS_CHECK_TOOLCHAIN)
 TARGET_ARCH_FEATURE:=$(shell ./scripts/get_arch_feature.sh)
 CPU_COUNT=$(shell ./scripts/cpu_count.sh)
 RS_BUILD_TOOLCHAIN:=stable
+TFHE_SRC:=crates/tfhe
 CARGO_RS_BUILD_TOOLCHAIN:=+$(RS_BUILD_TOOLCHAIN)
 CARGO_PROFILE?=release
-MIN_RUST_VERSION:=$(shell grep '^rust-version[[:space:]]*=' tfhe/Cargo.toml | cut -d '=' -f 2 | xargs)
+MIN_RUST_VERSION:=$(shell grep '^rust-version[[:space:]]*=' $(TFHE_SRC)/Cargo.toml | cut -d '=' -f 2 | xargs)
 AVX512_SUPPORT?=OFF
 WASM_RUSTFLAGS:=
 BIG_TESTS_INSTANCE?=FALSE
@@ -18,25 +19,21 @@ FAST_TESTS?=FALSE
 FAST_BENCH?=FALSE
 NIGHTLY_TESTS?=FALSE
 BENCH_OP_FLAVOR?=DEFAULT
+BENCH_TYPE?=latency
 NODE_VERSION=22.6
-FORWARD_COMPAT?=OFF
 BACKWARD_COMPAT_DATA_URL=https://github.com/zama-ai/tfhe-backward-compat-data.git
-BACKWARD_COMPAT_DATA_BRANCH?=v0.2
+BACKWARD_COMPAT_DATA_BRANCH?=v0.4
 BACKWARD_COMPAT_DATA_PROJECT=tfhe-backward-compat-data
 BACKWARD_COMPAT_DATA_DIR=$(BACKWARD_COMPAT_DATA_PROJECT)
 TFHE_SPEC:=tfhe
+# We are kind of hacking the cut here, the version cannot contain a quote '"'
+WASM_BINDGEN_VERSION:=$(shell grep '^wasm-bindgen[[:space:]]*=' Cargo.toml | cut -d '"' -f 2 | xargs)
 WEB_RUNNER_DIR=web-test-runner
-WEB_SERVER_DIR=tfhe/web_wasm_parallel_tests
+WEB_SERVER_DIR=tfhe/tests/web_wasm_parallel
 # This is done to avoid forgetting it, we still precise the RUSTFLAGS in the commands to be able to
 # copy paste the command in the terminal and change them if required without forgetting the flags
 export RUSTFLAGS?=-C target-cpu=native
 
-ifeq ($(AVX512_SUPPORT),ON)
-		AVX512_FEATURE=nightly-avx512
-else
-		AVX512_FEATURE=
-endif
-
 ifeq ($(GEN_KEY_CACHE_MULTI_BIT_ONLY),TRUE)
 		MULTI_BIT_ONLY=--multi-bit-only
 else
@@ -49,12 +46,6 @@ else
 		COVERAGE_ONLY=
 endif
 
-ifeq ($(FORWARD_COMPAT),ON)
-		FORWARD_COMPAT_FEATURE=forward_compatibility
-else
-		FORWARD_COMPAT_FEATURE=
-endif
-
 # Variables used only for regex_engine example
 REGEX_STRING?=''
 REGEX_PATTERN?=''
@@ -104,12 +95,26 @@ install_rs_build_toolchain:
 	( echo "Unable to install $(RS_BUILD_TOOLCHAIN) toolchain, check your rustup installation. \
 	Rustup can be downloaded at https://rustup.rs/" && exit 1 )
 
+.PHONY: install_build_wasm32_target # Install the wasm32 toolchain used for builds
+install_build_wasm32_target: install_rs_build_toolchain
+	rustup +$(RS_BUILD_TOOLCHAIN) target add wasm32-unknown-unknown || \
+	( echo "Unable to install wasm32-unknown-unknown target toolchain, check your rustup installation. \
+	Rustup can be downloaded at https://rustup.rs/" && exit 1 )
+
 .PHONY: install_cargo_nextest # Install cargo nextest used for shortint tests
 install_cargo_nextest: install_rs_build_toolchain
 	@cargo nextest --version > /dev/null 2>&1 || \
 	cargo $(CARGO_RS_BUILD_TOOLCHAIN) install cargo-nextest --locked || \
 	( echo "Unable to install cargo nextest, unknown error." && exit 1 )
 
+# The installation should use the ^ symbol if the specified version in the root Cargo.toml is of the
+# form "0.2.96" then we get ^0.2.96 e.g., as we don't lock those dependencies
+# this allows to get the matching CLI
+# If a version range is specified no need to add the leading ^
+.PHONY: install_wasm_bindgen_cli # Install wasm-bindgen-cli to get access to the test runner
+install_wasm_bindgen_cli: install_rs_build_toolchain
+	cargo +$(RS_BUILD_TOOLCHAIN) install --locked wasm-bindgen-cli --version "$(WASM_BINDGEN_VERSION)"
+
 .PHONY: install_wasm_pack # Install wasm-pack to build JS packages
 install_wasm_pack: install_rs_build_toolchain
 	@wasm-pack --version > /dev/null 2>&1 || \
@@ -128,6 +133,10 @@ install_node:
 	$(SHELL) -i -c 'nvm install $(NODE_VERSION)' || \
 	( echo "Unable to install node, unknown error." && exit 1 )
 
+.PHONY: node_version  # Return Node version that will be installed
+node_version:
+	@echo "$(NODE_VERSION)"
+
 .PHONY: install_dieharder # Install dieharder for apt distributions or macOS
 install_dieharder:
 	@dieharder -h > /dev/null 2>&1 || \
@@ -148,6 +157,12 @@ install_tfhe_lints:
 	(cd utils/cargo-tfhe-lints-inner && cargo install --path .) && \
 	cd utils/cargo-tfhe-lints && cargo install --path .
 
+.PHONY: install_typos_checker # Install typos checker
+install_typos_checker: install_rs_build_toolchain
+	@typos --version > /dev/null 2>&1 || \
+	cargo $(CARGO_RS_BUILD_TOOLCHAIN) install typos-cli || \
+	( echo "Unable to install typos-cli, unknown error." && exit 1 )
+
 .PHONY: setup_venv # Setup Python virtualenv for wasm tests
 setup_venv:
 	python3 -m venv venv
@@ -161,24 +176,44 @@ install_web_resource:
 	echo "$(checksum) $(filename)" > checksum && \
 	sha256sum -c checksum && \
 	rm checksum && \
-	unzip $(filename)
+	$(decompress_cmd) $(filename)
 
-install_chrome_browser: url = "https://storage.googleapis.com/chrome-for-testing-public/128.0.6613.137/linux64/chrome-linux64.zip"
-install_chrome_browser: checksum = "c5d7da679f3a353ae4e4420ab113de06d4bd459152f5b17558390c02d9520566"
+install_chrome_browser: url = "https://storage.googleapis.com/chrome-for-testing-public/130.0.6723.69/linux64/chrome-linux64.zip"
+install_chrome_browser: checksum = "f789d53911a50cfa4a2bc1f09cde57567247f52515436d92b1aa9de93c2787d0"
 install_chrome_browser: dest = "$(WEB_RUNNER_DIR)/chrome"
 install_chrome_browser: filename = "chrome-linux64.zip"
+install_chrome_browser: decompress_cmd = unzip
 
 .PHONY: install_chrome_browser # Install Chrome browser for Linux
 install_chrome_browser: install_web_resource
 
-install_chrome_web_driver: url = "https://storage.googleapis.com/chrome-for-testing-public/128.0.6613.137/linux64/chromedriver-linux64.zip"
-install_chrome_web_driver: checksum = "f041092f403fb7455a6da2871070b6587c32814a3e3c2b0a794d3d4aa4739151"
+install_chrome_web_driver: url = "https://storage.googleapis.com/chrome-for-testing-public/130.0.6723.69/linux64/chromedriver-linux64.zip"
+install_chrome_web_driver: checksum = "90fe8dedf33eefe4b72704f626fa9f5834427c042235cfeb4251f18c9f0336ea"
 install_chrome_web_driver: dest = "$(WEB_RUNNER_DIR)/chrome"
 install_chrome_web_driver: filename = "chromedriver-linux64.zip"
+install_chrome_web_driver: decompress_cmd = unzip
 
 .PHONY: install_chrome_web_driver # Install Chrome web driver for Linux
 install_chrome_web_driver: install_web_resource
 
+install_firefox_browser: url = "https://download-installer.cdn.mozilla.net/pub/firefox/releases/131.0/linux-x86_64/en-US/firefox-131.0.tar.bz2"
+install_firefox_browser: checksum = "4ca8504a62a31472ecb8c3a769d4301dd4ac692d4cc5d51b8fe2cf41e7b11106"
+install_firefox_browser: dest = "$(WEB_RUNNER_DIR)/firefox"
+install_firefox_browser: filename = "firefox-131.0.tar.bz2"
+install_firefox_browser: decompress_cmd = tar -xvf
+
+.PHONY: install_firefox_browser # Install firefox browser for Linux
+install_firefox_browser: install_web_resource
+
+install_firefox_web_driver: url = "https://github.com/mozilla/geckodriver/releases/download/v0.35.0/geckodriver-v0.35.0-linux64.tar.gz"
+install_firefox_web_driver: checksum = "ac26e9ba8f3b8ce0fbf7339b9c9020192f6dcfcbf04a2bcd2af80dfe6bb24260"
+install_firefox_web_driver: dest = "$(WEB_RUNNER_DIR)/firefox"
+install_firefox_web_driver: filename = "geckodriver-v0.35.0-linux64.tar.gz"
+install_firefox_web_driver: decompress_cmd = tar -xvf
+
+.PHONY: install_firefox_web_driver # Install firefox web driver for Linux
+install_firefox_web_driver: install_web_resource
+
 .PHONY: check_linelint_installed # Check if linelint newline linter is installed
 check_linelint_installed:
 	@printf "\n" | linelint - > /dev/null 2>&1 || \
@@ -209,7 +244,7 @@ fmt_js: check_nvm_installed
 	source ~/.nvm/nvm.sh && \
 	nvm install $(NODE_VERSION) && \
 	nvm use $(NODE_VERSION) && \
-	$(MAKE) -C tfhe/web_wasm_parallel_tests fmt
+	$(MAKE) -C $(TFHE_SRC)/tests/web_wasm_parallel fmt
 
 .PHONY: fmt_gpu # Format rust and cuda code
 fmt_gpu: install_rs_check_toolchain
@@ -218,7 +253,7 @@ fmt_gpu: install_rs_check_toolchain
 
 .PHONY: fmt_c_tests # Format c tests
 fmt_c_tests:
-	find tfhe/c_api_tests/ -regex '.*\.\(cpp\|hpp\|cu\|c\|h\)' -exec clang-format -style=file -i {} \;
+	find $(TFHE_SRC)/tests/c_api/ -regex '.*\.\(cpp\|hpp\|cu\|c\|h\)' -exec clang-format -style=file -i {} \;
 
 .PHONY: check_fmt # Check rust code format
 check_fmt: install_rs_check_toolchain
@@ -226,7 +261,7 @@ check_fmt: install_rs_check_toolchain
 
 .PHONY: check_fmt_c_tests  # Check C tests format
 check_fmt_c_tests:
-	find tfhe/c_api_tests/ -regex '.*\.\(cpp\|hpp\|cu\|c\|h\)' -exec clang-format --dry-run --Werror -style=file {} \;
+	find $(TFHE_SRC)/tests/c_api/ -regex '.*\.\(cpp\|hpp\|cu\|c\|h\)' -exec clang-format --dry-run --Werror -style=file {} \;
 
 .PHONY: check_fmt_gpu # Check rust and cuda code format
 check_fmt_gpu: install_rs_check_toolchain
@@ -238,7 +273,11 @@ check_fmt_js: check_nvm_installed
 	source ~/.nvm/nvm.sh && \
 	nvm install $(NODE_VERSION) && \
 	nvm use $(NODE_VERSION) && \
-	$(MAKE) -C tfhe/web_wasm_parallel_tests check_fmt
+	$(MAKE) -C $(TFHE_SRC)/tests/web_wasm_parallel check_fmt
+
+.PHONY: check_typos # Check for typos in codebase
+check_typos: install_typos_checker
+	@typos && echo "No typos found"
 
 .PHONY: clippy_gpu # Run clippy lints on tfhe with "gpu" enabled
 clippy_gpu: install_rs_check_toolchain
@@ -280,6 +319,9 @@ clippy_core: install_rs_check_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" clippy \
 		--features=$(TARGET_ARCH_FEATURE),experimental,nightly-avx512 \
 		-p $(TFHE_SPEC) -- --no-deps -D warnings
+	RUSTFLAGS="$(RUSTFLAGS)" cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" clippy \
+		--features=$(TARGET_ARCH_FEATURE),zk-pok \
+		-p $(TFHE_SPEC) -- --no-deps -D warnings
 
 .PHONY: clippy_boolean # Run clippy lints enabling the boolean features
 clippy_boolean: install_rs_check_toolchain
@@ -295,6 +337,9 @@ clippy_shortint: install_rs_check_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" clippy \
 		--features=$(TARGET_ARCH_FEATURE),shortint,experimental \
 		-p $(TFHE_SPEC) -- --no-deps -D warnings
+	RUSTFLAGS="$(RUSTFLAGS)" cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" clippy \
+		--features=$(TARGET_ARCH_FEATURE),zk-pok,shortint \
+		-p $(TFHE_SPEC) -- --no-deps -D warnings
 
 .PHONY: clippy_integer # Run clippy lints enabling the integer features
 clippy_integer: install_rs_check_toolchain
@@ -319,7 +364,7 @@ clippy_rustdoc: install_rs_check_toolchain
 	fi && \
 	CLIPPYFLAGS="-D warnings" RUSTDOCFLAGS="--no-run --nocapture --test-builder ./scripts/clippy_driver.sh -Z unstable-options" \
 		cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" test --doc \
-		--features=$(TARGET_ARCH_FEATURE),boolean,shortint,integer,zk-pok,pbs-stats \
+		--features=$(TARGET_ARCH_FEATURE),boolean,shortint,integer,zk-pok,pbs-stats,strings \
 		-p $(TFHE_SPEC)
 
 .PHONY: clippy_c_api # Run clippy lints enabling the boolean, shortint and the C API
@@ -350,17 +395,17 @@ clippy_trivium: install_rs_check_toolchain
 .PHONY: clippy_all_targets # Run clippy lints on all targets (benches, examples, etc.)
 clippy_all_targets: install_rs_check_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" clippy --all-targets \
-		--features=$(TARGET_ARCH_FEATURE),boolean,shortint,integer,internal-keycache,zk-pok \
+		--features=$(TARGET_ARCH_FEATURE),boolean,shortint,integer,internal-keycache,zk-pok,strings \
 		-p $(TFHE_SPEC) -- --no-deps -D warnings
 	RUSTFLAGS="$(RUSTFLAGS)" cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" clippy --all-targets \
-		--features=$(TARGET_ARCH_FEATURE),boolean,shortint,integer,internal-keycache,zk-pok,experimental \
+		--features=$(TARGET_ARCH_FEATURE),boolean,shortint,integer,internal-keycache,zk-pok,strings,experimental \
 		-p $(TFHE_SPEC) -- --no-deps -D warnings
 
-.PHONY: clippy_concrete_csprng # Run clippy lints on concrete-csprng
-clippy_concrete_csprng: install_rs_check_toolchain
+.PHONY: clippy_tfhe_csprng # Run clippy lints on tfhe-csprng
+clippy_tfhe_csprng: install_rs_check_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" clippy --all-targets \
 		--features=$(TARGET_ARCH_FEATURE) \
-		-p concrete-csprng -- --no-deps -D warnings
+		-p tfhe-csprng -- --no-deps -D warnings
 
 .PHONY: clippy_zk_pok # Run clippy lints on tfhe-zk-pok
 clippy_zk_pok: install_rs_check_toolchain
@@ -376,21 +421,29 @@ clippy_versionable: install_rs_check_toolchain
 
 .PHONY: clippy_all # Run all clippy targets
 clippy_all: clippy_rustdoc clippy clippy_boolean clippy_shortint clippy_integer clippy_all_targets \
-clippy_c_api clippy_js_wasm_api clippy_tasks clippy_core clippy_concrete_csprng clippy_zk_pok clippy_trivium \
+clippy_c_api clippy_js_wasm_api clippy_tasks clippy_core clippy_tfhe_csprng clippy_zk_pok clippy_trivium \
 clippy_versionable
 
 .PHONY: clippy_fast # Run main clippy targets
 clippy_fast: clippy_rustdoc clippy clippy_all_targets clippy_c_api clippy_js_wasm_api clippy_tasks \
-clippy_core clippy_concrete_csprng
+clippy_core clippy_tfhe_csprng
 
 .PHONY: clippy_cuda_backend # Run clippy lints on the tfhe-cuda-backend
 clippy_cuda_backend: install_rs_check_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" clippy --all-targets \
 		-p tfhe-cuda-backend -- --no-deps -D warnings
 
+.PHONY: check_rust_bindings_did_not_change # Check rust bindings are up to date for tfhe-cuda-backend
+check_rust_bindings_did_not_change:
+	cargo build -p tfhe-cuda-backend && "$(MAKE)" fmt_gpu && \
+	git diff --quiet HEAD -- backends/tfhe-cuda-backend/src/bindings.rs || \
+	( echo "Generated bindings have changed! Please run 'git add backends/tfhe-cuda-backend/src/bindings.rs' \
+	and commit the changes." && exit 1 ) 
+
+
 .PHONY: tfhe_lints # Run custom tfhe-rs lints
 tfhe_lints: install_tfhe_lints
-	cd tfhe && RUSTFLAGS="$(RUSTFLAGS)" cargo tfhe-lints \
+	cd $(TFHE_SRC) && RUSTFLAGS="$(RUSTFLAGS)" cargo tfhe-lints \
 		--features=$(TARGET_ARCH_FEATURE),boolean,shortint,integer,zk-pok -- -D warnings
 
 .PHONY: build_core # Build core_crypto without experimental features
@@ -399,7 +452,7 @@ build_core: install_rs_build_toolchain install_rs_check_toolchain
 		--features=$(TARGET_ARCH_FEATURE) -p $(TFHE_SPEC)
 	@if [[ "$(AVX512_SUPPORT)" == "ON" ]]; then \
 		RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_CHECK_TOOLCHAIN) build --profile $(CARGO_PROFILE) \
-			--features=$(TARGET_ARCH_FEATURE),$(AVX512_FEATURE) -p $(TFHE_SPEC); \
+			--features=$(TARGET_ARCH_FEATURE),nightly-avx512 -p $(TFHE_SPEC); \
 	fi
 
 .PHONY: build_core_experimental # Build core_crypto with experimental features
@@ -408,7 +461,7 @@ build_core_experimental: install_rs_build_toolchain install_rs_check_toolchain
 		--features=$(TARGET_ARCH_FEATURE),experimental -p $(TFHE_SPEC)
 	@if [[ "$(AVX512_SUPPORT)" == "ON" ]]; then \
 		RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_CHECK_TOOLCHAIN) build --profile $(CARGO_PROFILE) \
-			--features=$(TARGET_ARCH_FEATURE),experimental,$(AVX512_FEATURE) -p $(TFHE_SPEC); \
+			--features=$(TARGET_ARCH_FEATURE),experimental,nightly-avx512 -p $(TFHE_SPEC); \
 	fi
 
 .PHONY: build_boolean # Build with boolean enabled
@@ -436,62 +489,53 @@ build_tfhe_coverage: install_rs_build_toolchain
 	RUSTFLAGS="$(RUSTFLAGS) --cfg tarpaulin" cargo $(CARGO_RS_BUILD_TOOLCHAIN) build --profile $(CARGO_PROFILE) \
 		--features=$(TARGET_ARCH_FEATURE),boolean,shortint,integer,internal-keycache -p $(TFHE_SPEC) --tests
 
-.PHONY: symlink_c_libs_without_fingerprint # Link the .a and .so files without the changing hash part in target
-symlink_c_libs_without_fingerprint:
-	@./scripts/symlink_c_libs_without_fingerprint.sh \
-		--cargo-profile "$(CARGO_PROFILE)" \
-		--lib-name tfhe-c-api-dynamic-buffer
-
 .PHONY: build_c_api # Build the C API for boolean, shortint and integer
 build_c_api: install_rs_check_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_CHECK_TOOLCHAIN) build --profile $(CARGO_PROFILE) \
-		--features=$(TARGET_ARCH_FEATURE),boolean-c-api,shortint-c-api,high-level-c-api,zk-pok,$(FORWARD_COMPAT_FEATURE) \
+		--features=$(TARGET_ARCH_FEATURE),boolean-c-api,shortint-c-api,high-level-c-api,zk-pok \
 		-p $(TFHE_SPEC)
-	@"$(MAKE)" symlink_c_libs_without_fingerprint
 
 .PHONY: build_c_api_gpu # Build the C API for boolean, shortint and integer
 build_c_api_gpu: install_rs_check_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_CHECK_TOOLCHAIN) build --profile $(CARGO_PROFILE) \
 		--features=$(TARGET_ARCH_FEATURE),boolean-c-api,shortint-c-api,high-level-c-api,zk-pok,gpu \
 		-p $(TFHE_SPEC)
-	@"$(MAKE)" symlink_c_libs_without_fingerprint
 
 .PHONY: build_c_api_experimental_deterministic_fft # Build the C API for boolean, shortint and integer with experimental deterministic FFT
 build_c_api_experimental_deterministic_fft: install_rs_check_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_CHECK_TOOLCHAIN) build --profile $(CARGO_PROFILE) \
-		--features=$(TARGET_ARCH_FEATURE),boolean-c-api,shortint-c-api,high-level-c-api,zk-pok,experimental-force_fft_algo_dif4,$(FORWARD_COMPAT_FEATURE) \
+		--features=$(TARGET_ARCH_FEATURE),boolean-c-api,shortint-c-api,high-level-c-api,zk-pok,experimental-force_fft_algo_dif4 \
 		-p $(TFHE_SPEC)
-	@"$(MAKE)" symlink_c_libs_without_fingerprint
 
 .PHONY: build_web_js_api # Build the js API targeting the web browser
 build_web_js_api: install_rs_build_toolchain install_wasm_pack
-	cd tfhe && \
+	cd $(TFHE_SRC) && \
 	RUSTFLAGS="$(WASM_RUSTFLAGS)" rustup run "$(RS_BUILD_TOOLCHAIN)" \
 		wasm-pack build --release --target=web \
 		-- --features=boolean-client-js-wasm-api,shortint-client-js-wasm-api,integer-client-js-wasm-api,zk-pok
 
 .PHONY: build_web_js_api_parallel # Build the js API targeting the web browser with parallelism support
 build_web_js_api_parallel: install_rs_check_toolchain install_wasm_pack
-	cd tfhe && \
+	cd $(TFHE_SRC) && \
 	rustup component add rust-src --toolchain $(RS_CHECK_TOOLCHAIN) && \
 	RUSTFLAGS="$(WASM_RUSTFLAGS) -C target-feature=+atomics,+bulk-memory,+mutable-globals" rustup run $(RS_CHECK_TOOLCHAIN) \
 		wasm-pack build --release --target=web \
 		-- --features=boolean-client-js-wasm-api,shortint-client-js-wasm-api,integer-client-js-wasm-api,parallel-wasm-api,zk-pok \
 		-Z build-std=panic_abort,std && \
 	find pkg/snippets -type f -iname workerHelpers.worker.js -exec sed -i "s|from '..\/..\/..\/';|from '..\/..\/..\/tfhe.js';|" {} \;
-	jq '.files += ["snippets"]' tfhe/pkg/package.json > tmp_pkg.json && mv -f tmp_pkg.json tfhe/pkg/package.json
+	jq '.files += ["snippets"]' $(TFHE_SRC)/pkg/package.json > tmp_pkg.json && mv -f tmp_pkg.json $(TFHE_SRC)/pkg/package.json
 
 .PHONY: build_node_js_api # Build the js API targeting nodejs
 build_node_js_api: install_rs_build_toolchain install_wasm_pack
-	cd tfhe && \
+	cd $(TFHE_SRC) && \
 	RUSTFLAGS="$(WASM_RUSTFLAGS)" rustup run "$(RS_BUILD_TOOLCHAIN)" \
 		wasm-pack build --release --target=nodejs \
 		-- --features=boolean-client-js-wasm-api,shortint-client-js-wasm-api,integer-client-js-wasm-api,zk-pok
 
-.PHONY: build_concrete_csprng # Build concrete_csprng
-build_concrete_csprng: install_rs_build_toolchain
+.PHONY: build_tfhe_csprng # Build tfhe_csprng
+build_tfhe_csprng: install_rs_build_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) build --profile $(CARGO_PROFILE) \
-		--features=$(TARGET_ARCH_FEATURE) -p concrete-csprng --all-targets
+		--features=$(TARGET_ARCH_FEATURE) -p tfhe-csprng --all-targets
 
 .PHONY: test_core_crypto # Run the tests of the core_crypto module including experimental ones
 test_core_crypto: install_rs_build_toolchain install_rs_check_toolchain
@@ -499,7 +543,7 @@ test_core_crypto: install_rs_build_toolchain install_rs_check_toolchain
 		--features=$(TARGET_ARCH_FEATURE),experimental,zk-pok -p $(TFHE_SPEC) -- core_crypto::
 	@if [[ "$(AVX512_SUPPORT)" == "ON" ]]; then \
 		RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_CHECK_TOOLCHAIN) test --profile $(CARGO_PROFILE) \
-			--features=$(TARGET_ARCH_FEATURE),experimental,zk-pok,$(AVX512_FEATURE) -p $(TFHE_SPEC) -- core_crypto::; \
+			--features=$(TARGET_ARCH_FEATURE),experimental,zk-pok,nightly-avx512 -p $(TFHE_SPEC) -- core_crypto::; \
 	fi
 
 .PHONY: test_core_crypto_cov # Run the tests of the core_crypto module with code coverage
@@ -513,7 +557,7 @@ test_core_crypto_cov: install_rs_build_toolchain install_rs_check_toolchain inst
 		RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_CHECK_TOOLCHAIN) tarpaulin --profile $(CARGO_PROFILE) \
 			--out xml --output-dir coverage/core_crypto_avx512 --line --engine llvm --timeout 500 \
 			--implicit-test-threads $(COVERAGE_EXCLUDED_FILES) \
-			--features=$(TARGET_ARCH_FEATURE),experimental,internal-keycache,$(AVX512_FEATURE) \
+			--features=$(TARGET_ARCH_FEATURE),experimental,internal-keycache,nightly-avx512 \
 			-p $(TFHE_SPEC) -- -Z unstable-options --report-time core_crypto::; \
 	fi
 
@@ -531,23 +575,35 @@ test_gpu: test_core_crypto_gpu test_integer_gpu test_cuda_backend
 .PHONY: test_core_crypto_gpu # Run the tests of the core_crypto module including experimental on the gpu backend
 test_core_crypto_gpu: install_rs_build_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --profile $(CARGO_PROFILE) \
-		--features=$(TARGET_ARCH_FEATURE),gpu -p $(TFHE_SPEC) -- core_crypto::gpu:: --test-threads=1
+		--features=$(TARGET_ARCH_FEATURE),gpu -p $(TFHE_SPEC) -- core_crypto::gpu::
 	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --doc --profile $(CARGO_PROFILE) \
-		--features=$(TARGET_ARCH_FEATURE),gpu -p $(TFHE_SPEC) -- core_crypto::gpu:: --test-threads=1
+		--features=$(TARGET_ARCH_FEATURE),gpu -p $(TFHE_SPEC) -- core_crypto::gpu::
 
 .PHONY: test_integer_gpu # Run the tests of the integer module including experimental on the gpu backend
 test_integer_gpu: install_rs_build_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --profile $(CARGO_PROFILE) \
-		--features=$(TARGET_ARCH_FEATURE),integer,gpu -p $(TFHE_SPEC) -- integer::gpu::server_key:: --test-threads=1
+		--features=$(TARGET_ARCH_FEATURE),integer,gpu -p $(TFHE_SPEC) -- integer::gpu::server_key:: --test-threads=6
 	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --doc --profile $(CARGO_PROFILE) \
 		--features=$(TARGET_ARCH_FEATURE),integer,gpu -p $(TFHE_SPEC) -- integer::gpu::server_key::
 
+.PHONY: test_integer_long_run_gpu # Run the tests of the integer module including experimental on the gpu backend
+test_integer_long_run_gpu: install_rs_build_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --profile $(CARGO_PROFILE) \
+		--features=$(TARGET_ARCH_FEATURE),integer,gpu,__long_run_tests -p $(TFHE_SPEC) -- integer::gpu::server_key::radix::tests_long_run --test-threads=6
+
+.PHONY: test_integer_compression
+test_integer_compression: install_rs_build_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --profile $(CARGO_PROFILE) \
+		--features=$(TARGET_ARCH_FEATURE),integer -p $(TFHE_SPEC) -- integer::ciphertext::compressed_ciphertext_list::tests::
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --doc --profile $(CARGO_PROFILE) \
+		--features=$(TARGET_ARCH_FEATURE),integer -p $(TFHE_SPEC) -- integer::ciphertext::compress
+
 .PHONY: test_integer_compression_gpu
 test_integer_compression_gpu: install_rs_build_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --profile $(CARGO_PROFILE) \
-		--features=$(TARGET_ARCH_FEATURE),integer,gpu -p $(TFHE_SPEC) -- integer::gpu::ciphertext::compressed_ciphertext_list::tests:: --test-threads=1
+		--features=$(TARGET_ARCH_FEATURE),integer,gpu -p $(TFHE_SPEC) -- integer::gpu::ciphertext::compressed_ciphertext_list::tests::
 	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --doc --profile $(CARGO_PROFILE) \
-		--features=$(TARGET_ARCH_FEATURE),integer,gpu -p $(TFHE_SPEC) -- integer::gpu::ciphertext::compress --test-threads=1
+		--features=$(TARGET_ARCH_FEATURE),integer,gpu -p $(TFHE_SPEC) -- integer::gpu::ciphertext::compress
 
 .PHONY: test_integer_gpu_ci # Run the tests for integer ci on gpu backend
 test_integer_gpu_ci: install_rs_check_toolchain install_cargo_nextest
@@ -715,10 +771,21 @@ test_signed_integer_multi_bit_ci: install_rs_check_toolchain install_cargo_nexte
 		--cargo-profile "$(CARGO_PROFILE)" --multi-bit --avx512-support "$(AVX512_SUPPORT)" \
 		--signed-only --tfhe-package "$(TFHE_SPEC)"
 
-.PHONY: test_safe_deserialization # Run the tests for safe deserialization
-test_safe_deserialization: install_rs_build_toolchain install_cargo_nextest
+.PHONY: test_integer_long_run # Run the long run tests for integer
+test_integer_long_run: install_rs_build_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --profile $(CARGO_PROFILE) \
-		--features=$(TARGET_ARCH_FEATURE),boolean,shortint,integer,internal-keycache -p $(TFHE_SPEC) -- safe_deserialization::
+						--features=$(TARGET_ARCH_FEATURE),integer,internal-keycache,__long_run_tests -p $(TFHE_SPEC) -- integer::server_key::radix_parallel::tests_long_run
+
+
+.PHONY: test_safe_serialization # Run the tests for safe serialization
+test_safe_serialization: install_rs_build_toolchain install_cargo_nextest
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --profile $(CARGO_PROFILE) \
+		--features=$(TARGET_ARCH_FEATURE),boolean,shortint,integer,internal-keycache -p $(TFHE_SPEC) -- safe_serialization::
+
+.PHONY: test_zk # Run the tests for the zk module of the TFHE-rs crate
+test_zk: install_rs_build_toolchain install_cargo_nextest
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --profile $(CARGO_PROFILE) \
+		--features=$(TARGET_ARCH_FEATURE),shortint,zk-pok -p $(TFHE_SPEC) -- zk::
 
 .PHONY: test_integer # Run all the tests for integer
 test_integer: install_rs_build_toolchain
@@ -745,6 +812,13 @@ test_high_level_api_gpu: install_rs_build_toolchain install_cargo_nextest
 		--features=$(TARGET_ARCH_FEATURE),integer,internal-keycache,gpu -p $(TFHE_SPEC) \
 		-E "test(/high_level_api::.*gpu.*/)"
 
+.PHONY: test_strings # Run the tests for strings ci
+test_strings: install_rs_build_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --profile $(CARGO_PROFILE) \
+		--features=$(TARGET_ARCH_FEATURE),shortint,integer,strings -p $(TFHE_SPEC) \
+		-- strings::
+
+
 .PHONY: test_user_doc # Run tests from the .md documentation
 test_user_doc: install_rs_build_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --profile $(CARGO_PROFILE) --doc \
@@ -758,11 +832,7 @@ test_user_doc_gpu: install_rs_build_toolchain
 		--features=$(TARGET_ARCH_FEATURE),boolean,shortint,integer,internal-keycache,gpu,zk-pok -p $(TFHE_SPEC) \
 		-- test_user_docs::
 
-.PHONY: test_fhe_strings # Run tests for fhe_strings example
-test_fhe_strings: install_rs_build_toolchain
-	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --profile $(CARGO_PROFILE) \
-		--example fhe_strings \
-		--features=$(TARGET_ARCH_FEATURE),integer
+
 
 .PHONY: test_regex_engine # Run tests for regex_engine example
 test_regex_engine: install_rs_build_toolchain
@@ -789,16 +859,29 @@ test_kreyvium: install_rs_build_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --profile $(CARGO_PROFILE) \
 		-p tfhe-trivium -- --test-threads=1 kreyvium::
 
-.PHONY: test_concrete_csprng # Run concrete-csprng tests
-test_concrete_csprng: install_rs_build_toolchain
+.PHONY: test_tfhe_csprng # Run tfhe-csprng tests
+test_tfhe_csprng: install_rs_build_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --profile $(CARGO_PROFILE) \
-		--features=$(TARGET_ARCH_FEATURE) -p concrete-csprng
+		--features=$(TARGET_ARCH_FEATURE) -p tfhe-csprng
 
 .PHONY: test_zk_pok # Run tfhe-zk-pok tests
 test_zk_pok: install_rs_build_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --profile $(CARGO_PROFILE) \
 		-p tfhe-zk-pok
 
+.PHONY: test_zk_wasm_x86_compat_ci
+test_zk_wasm_x86_compat_ci: check_nvm_installed
+	source ~/.nvm/nvm.sh && \
+	nvm install $(NODE_VERSION) && \
+	nvm use $(NODE_VERSION) && \
+	$(MAKE) test_zk_wasm_x86_compat
+
+.PHONY: test_zk_wasm_x86_compat # Check compatibility between wasm and x86_64 proofs
+test_zk_wasm_x86_compat: install_rs_build_toolchain build_node_js_api
+	cd $(TFHE_SRC)/tests/zk_wasm_x86_test && npm install
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --profile $(CARGO_PROFILE) \
+		-p tfhe --test zk_wasm_x86_test --features=$(TARGET_ARCH_FEATURE),integer,zk-pok
+
 .PHONY: test_versionable # Run tests for tfhe-versionable subcrate
 test_versionable: install_rs_build_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --profile $(CARGO_PROFILE) \
@@ -809,11 +892,11 @@ test_versionable: install_rs_build_toolchain
 .PHONY: test_backward_compatibility_ci
 test_backward_compatibility_ci: install_rs_build_toolchain
 	TFHE_BACKWARD_COMPAT_DATA_DIR="$(BACKWARD_COMPAT_DATA_DIR)" RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --profile $(CARGO_PROFILE) \
-		--config "patch.'$(BACKWARD_COMPAT_DATA_URL)'.$(BACKWARD_COMPAT_DATA_PROJECT).path=\"tfhe/$(BACKWARD_COMPAT_DATA_DIR)\"" \
+		--config "patch.'$(BACKWARD_COMPAT_DATA_URL)'.$(BACKWARD_COMPAT_DATA_PROJECT).path=\"$(TFHE_SRC)/$(BACKWARD_COMPAT_DATA_DIR)\"" \
 		--features=$(TARGET_ARCH_FEATURE),shortint,integer,zk-pok -p $(TFHE_SPEC) test_backward_compatibility -- --nocapture
 
 .PHONY: test_backward_compatibility # Same as test_backward_compatibility_ci but tries to clone the data repo first if needed
-test_backward_compatibility: tfhe/$(BACKWARD_COMPAT_DATA_DIR) test_backward_compatibility_ci
+test_backward_compatibility: $(TFHE_SRC)/$(BACKWARD_COMPAT_DATA_DIR) test_backward_compatibility_ci
 
 .PHONY: backward_compat_branch # Prints the required backward compatibility branch
 backward_compat_branch:
@@ -825,7 +908,7 @@ doc: install_rs_check_toolchain
 	DOCS_RS=1 \
 	RUSTDOCFLAGS="--html-in-header katex-header.html" \
 	cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" doc \
-		--features=$(TARGET_ARCH_FEATURE),boolean,shortint,integer,gpu,internal-keycache,experimental,zk-pok --no-deps -p $(TFHE_SPEC)
+		--features=$(TARGET_ARCH_FEATURE),boolean,shortint,integer,strings,gpu,internal-keycache,experimental,zk-pok --no-deps -p $(TFHE_SPEC)
 
 .PHONY: docs # Build rust doc alias for doc
 docs: doc
@@ -836,7 +919,7 @@ lint_doc: install_rs_check_toolchain
 	DOCS_RS=1 \
 	RUSTDOCFLAGS="--html-in-header katex-header.html -Dwarnings" \
 	cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" doc \
-		--features=$(TARGET_ARCH_FEATURE),boolean,shortint,integer,gpu,internal-keycache,experimental,zk-pok -p $(TFHE_SPEC) --no-deps
+		--features=$(TARGET_ARCH_FEATURE),boolean,shortint,integer,strings,gpu,internal-keycache,experimental,zk-pok -p $(TFHE_SPEC) --no-deps
 
 .PHONY: lint_docs # Build rust doc with linting enabled alias for lint_doc
 lint_docs: lint_doc
@@ -856,11 +939,11 @@ check_md_docs_are_tested:
 
 .PHONY: check_intra_md_links # Checks broken internal links in Markdown docs
 check_intra_md_links: install_mlc
-	mlc --offline --match-file-extension tfhe/docs
+	mlc --offline --match-file-extension $(TFHE_SRC)/docs
 
 .PHONY: check_md_links # Checks all broken links in Markdown docs
 check_md_links: install_mlc
-	mlc --match-file-extension tfhe/docs
+	mlc --match-file-extension $(TFHE_SRC)/docs
 
 .PHONY: check_compile_tests # Build tests in debug without running them
 check_compile_tests: install_rs_build_toolchain
@@ -883,26 +966,16 @@ check_compile_tests_benches_gpu: install_rs_build_toolchain
 		cmake .. -DCMAKE_BUILD_TYPE=Debug -DTFHE_CUDA_BACKEND_BUILD_TESTS=ON -DTFHE_CUDA_BACKEND_BUILD_BENCHMARKS=ON && \
 		"$(MAKE)" -j "$(CPU_COUNT)"
 
-.PHONY: build_nodejs_test_docker # Build a docker image with tools to run nodejs tests for wasm API
-build_nodejs_test_docker:
-	DOCKER_BUILDKIT=1 docker build --build-arg RUST_TOOLCHAIN="$(RS_BUILD_TOOLCHAIN)" \
-		-f docker/Dockerfile.wasm_tests --build-arg NODE_VERSION=$(NODE_VERSION) -t tfhe-wasm-tests .
-
-.PHONY: test_nodejs_wasm_api_in_docker # Run tests for the nodejs on wasm API in a docker container
-test_nodejs_wasm_api_in_docker: build_nodejs_test_docker
-	if [[ -t 1 ]]; then RUN_FLAGS="-it"; else RUN_FLAGS="-i"; fi && \
-	docker run --rm "$${RUN_FLAGS}" \
-		-v "$$(pwd)":/tfhe-wasm-tests/tfhe-rs \
-		-v tfhe-rs-root-target-cache:/root/tfhe-rs-target \
-		-v tfhe-rs-pkg-cache:/tfhe-wasm-tests/tfhe-rs/tfhe/pkg \
-		-v tfhe-rs-root-cargo-registry-cache:/root/.cargo/registry \
-		-v tfhe-rs-root-cache:/root/.cache \
-		tfhe-wasm-tests /bin/bash -i -c 'make test_nodejs_wasm_api'
-
 .PHONY: test_nodejs_wasm_api # Run tests for the nodejs on wasm API
 test_nodejs_wasm_api: build_node_js_api
-	cd tfhe/js_on_wasm_tests && npm install && npm run test
+	cd $(TFHE_SRC)/tests/js_on_wasm && npm install && npm run test
 
+.PHONY: test_nodejs_wasm_api_ci # Run tests for the nodejs on wasm API
+test_nodejs_wasm_api_ci: build_node_js_api
+	source ~/.nvm/nvm.sh && \
+	nvm install $(NODE_VERSION) && \
+	nvm use $(NODE_VERSION) && \
+	$(MAKE) test_nodejs_wasm_api
 
 # This is an internal target, not meant to be called on its own.
 run_web_js_api_parallel: build_web_js_api_parallel setup_venv
@@ -921,16 +994,31 @@ test_web_js_api_parallel_chrome: driver_path = "$(WEB_RUNNER_DIR)/chrome/chromed
 test_web_js_api_parallel_chrome: browser_kind = chrome
 test_web_js_api_parallel_chrome: filter = Test
 
-.PHONY: test_web_js_api_parallel_chrome # Run tests for the web wasm api
+.PHONY: test_web_js_api_parallel_chrome # Run tests for the web wasm api on Chrome
 test_web_js_api_parallel_chrome: run_web_js_api_parallel
 
-.PHONY: test_web_js_api_parallel_chrome_ci # Run tests for the web wasm api
+.PHONY: test_web_js_api_parallel_chrome_ci # Run tests for the web wasm api on Chrome
 test_web_js_api_parallel_chrome_ci: setup_venv
 	source ~/.nvm/nvm.sh && \
 	nvm install $(NODE_VERSION) && \
 	nvm use $(NODE_VERSION) && \
 	$(MAKE) test_web_js_api_parallel_chrome
 
+test_web_js_api_parallel_firefox: browser_path = "$(WEB_RUNNER_DIR)/firefox/firefox/firefox"
+test_web_js_api_parallel_firefox: driver_path = "$(WEB_RUNNER_DIR)/firefox/geckodriver"
+test_web_js_api_parallel_firefox: browser_kind = firefox
+test_web_js_api_parallel_firefox: filter = Test
+
+.PHONY: test_web_js_api_parallel_firefox # Run tests for the web wasm api on Firefox
+test_web_js_api_parallel_firefox: run_web_js_api_parallel
+
+.PHONY: test_web_js_api_parallel_firefox_ci # Run tests for the web wasm api on Firefox
+test_web_js_api_parallel_firefox_ci: setup_venv
+	source ~/.nvm/nvm.sh && \
+	nvm install $(NODE_VERSION) && \
+	nvm use $(NODE_VERSION) && \
+	$(MAKE) test_web_js_api_parallel_firefox
+
 .PHONY: no_tfhe_typo # Check we did not invert the h and f in tfhe
 no_tfhe_typo:
 	@./scripts/no_tfhe_typo.sh
@@ -940,49 +1028,56 @@ no_dbg_log:
 	@./scripts/no_dbg_calls.sh
 
 .PHONY: dieharder_csprng # Run the dieharder test suite on our CSPRNG implementation
-dieharder_csprng: install_dieharder build_concrete_csprng
+dieharder_csprng: install_dieharder build_tfhe_csprng
 	./scripts/dieharder_test.sh
 
 #
 # Benchmarks
 #
 
+.PHONY: print_doc_bench_parameters # Print parameters used in doc benchmarks
+print_doc_bench_parameters:
+	RUSTFLAGS="" cargo run --example print_doc_bench_parameters \
+	--features=$(TARGET_ARCH_FEATURE),shortint,internal-keycache -p tfhe
+
 .PHONY: bench_integer # Run benchmarks for unsigned integer
 bench_integer: install_rs_check_toolchain
-	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_BENCH_OP_FLAVOR=$(BENCH_OP_FLAVOR) __TFHE_RS_FAST_BENCH=$(FAST_BENCH) \
+	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_BENCH_OP_FLAVOR=$(BENCH_OP_FLAVOR) __TFHE_RS_FAST_BENCH=$(FAST_BENCH) __TFHE_RS_BENCH_TYPE=$(BENCH_TYPE) \
 	cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
 	--bench integer-bench \
 	--features=$(TARGET_ARCH_FEATURE),integer,internal-keycache,nightly-avx512 -p $(TFHE_SPEC) --
 
 .PHONY: bench_signed_integer # Run benchmarks for signed integer
 bench_signed_integer: install_rs_check_toolchain
-	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_BENCH_OP_FLAVOR=$(BENCH_OP_FLAVOR) __TFHE_RS_FAST_BENCH=$(FAST_BENCH) \
+	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_BENCH_OP_FLAVOR=$(BENCH_OP_FLAVOR) __TFHE_RS_FAST_BENCH=$(FAST_BENCH) __TFHE_RS_BENCH_TYPE=$(BENCH_TYPE) \
 	cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
 	--bench integer-signed-bench \
 	--features=$(TARGET_ARCH_FEATURE),integer,internal-keycache,nightly-avx512 -p $(TFHE_SPEC) --
 
 .PHONY: bench_integer_gpu # Run benchmarks for integer on GPU backend
 bench_integer_gpu: install_rs_check_toolchain
-	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_BENCH_OP_FLAVOR=$(BENCH_OP_FLAVOR) __TFHE_RS_FAST_BENCH=$(FAST_BENCH) \
+	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_BENCH_OP_FLAVOR=$(BENCH_OP_FLAVOR) __TFHE_RS_FAST_BENCH=$(FAST_BENCH) __TFHE_RS_BENCH_TYPE=$(BENCH_TYPE) \
 	cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
 	--bench integer-bench \
 	--features=$(TARGET_ARCH_FEATURE),integer,gpu,internal-keycache,nightly-avx512 -p $(TFHE_SPEC) --
 
 .PHONY: bench_integer_compression # Run benchmarks for unsigned integer compression
 bench_integer_compression: install_rs_check_toolchain
-	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
+	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_BENCH_TYPE=$(BENCH_TYPE) \
+	cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
 	--bench	glwe_packing_compression-integer-bench \
 	--features=$(TARGET_ARCH_FEATURE),integer,internal-keycache,nightly-avx512 -p $(TFHE_SPEC) --
 
 .PHONY: bench_integer_compression_gpu
 bench_integer_compression_gpu: install_rs_check_toolchain
-	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
+	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_BENCH_TYPE=$(BENCH_TYPE) \
+	cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
 	--bench	glwe_packing_compression-integer-bench \
 	--features=$(TARGET_ARCH_FEATURE),integer,internal-keycache,gpu -p $(TFHE_SPEC) --
 
 .PHONY: bench_integer_multi_bit # Run benchmarks for unsigned integer using multi-bit parameters
 bench_integer_multi_bit: install_rs_check_toolchain
-	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_BENCH_TYPE=MULTI_BIT \
+	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_PARAM_TYPE=MULTI_BIT __TFHE_RS_BENCH_TYPE=$(BENCH_TYPE) \
 	__TFHE_RS_BENCH_OP_FLAVOR=$(BENCH_OP_FLAVOR) __TFHE_RS_FAST_BENCH=$(FAST_BENCH) \
 	cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
 	--bench integer-bench \
@@ -990,7 +1085,7 @@ bench_integer_multi_bit: install_rs_check_toolchain
 
 .PHONY: bench_signed_integer_multi_bit # Run benchmarks for signed integer using multi-bit parameters
 bench_signed_integer_multi_bit: install_rs_check_toolchain
-	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_BENCH_TYPE=MULTI_BIT \
+	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_PARAM_TYPE=MULTI_BIT __TFHE_RS_BENCH_TYPE=$(BENCH_TYPE) \
 	__TFHE_RS_BENCH_OP_FLAVOR=$(BENCH_OP_FLAVOR) __TFHE_RS_FAST_BENCH=$(FAST_BENCH) \
 	cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
 	--bench integer-signed-bench \
@@ -998,23 +1093,23 @@ bench_signed_integer_multi_bit: install_rs_check_toolchain
 
 .PHONY: bench_integer_multi_bit_gpu # Run benchmarks for integer on GPU backend using multi-bit parameters
 bench_integer_multi_bit_gpu: install_rs_check_toolchain
-	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_BENCH_TYPE=MULTI_BIT \
-	__TFHE_RS_BENCH_OP_FLAVOR=$(BENCH_OP_FLAVOR) __TFHE_RS_FAST_BENCH=$(FAST_BENCH) \
+	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_PARAM_TYPE=MULTI_BIT \
+	__TFHE_RS_BENCH_OP_FLAVOR=$(BENCH_OP_FLAVOR) __TFHE_RS_FAST_BENCH=$(FAST_BENCH) __TFHE_RS_BENCH_TYPE=$(BENCH_TYPE) \
 	cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
 	--bench integer-bench \
 	--features=$(TARGET_ARCH_FEATURE),integer,gpu,internal-keycache,nightly-avx512 -p $(TFHE_SPEC) --
 
 .PHONY: bench_unsigned_integer_multi_bit_gpu # Run benchmarks for unsigned integer on GPU backend using multi-bit parameters
 bench_unsigned_integer_multi_bit_gpu: install_rs_check_toolchain
-	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_BENCH_TYPE=MULTI_BIT \
-	__TFHE_RS_BENCH_OP_FLAVOR=$(BENCH_OP_FLAVOR) __TFHE_RS_FAST_BENCH=$(FAST_BENCH) \
+	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_PARAM_TYPE=MULTI_BIT \
+	__TFHE_RS_BENCH_OP_FLAVOR=$(BENCH_OP_FLAVOR) __TFHE_RS_FAST_BENCH=$(FAST_BENCH) __TFHE_RS_BENCH_TYPE=$(BENCH_TYPE) \
 	cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
 	--bench integer-bench \
 	--features=$(TARGET_ARCH_FEATURE),integer,gpu,internal-keycache,nightly-avx512 -p $(TFHE_SPEC) -- ::unsigned
 
 .PHONY: bench_integer_zk # Run benchmarks for integer encryption with ZK proofs
 bench_integer_zk: install_rs_check_toolchain
-	RUSTFLAGS="$(RUSTFLAGS)" \
+	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_BENCH_TYPE=$(BENCH_TYPE) \
 	cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
 	--bench zk-pke-bench \
 	--features=$(TARGET_ARCH_FEATURE),integer,internal-keycache,zk-pok,nightly-avx512 \
@@ -1036,7 +1131,7 @@ bench_shortint_oprf: install_rs_check_toolchain
 
 .PHONY: bench_shortint_multi_bit # Run benchmarks for shortint using multi-bit parameters
 bench_shortint_multi_bit: install_rs_check_toolchain
-	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_BENCH_TYPE=MULTI_BIT \
+	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_PARAM_TYPE=MULTI_BIT \
 	__TFHE_RS_BENCH_OP_FLAVOR=$(BENCH_OP_FLAVOR) \
 	cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
 	--bench shortint-bench \
@@ -1093,6 +1188,38 @@ bench_web_js_api_parallel_chrome_ci: setup_venv
 	nvm use $(NODE_VERSION) && \
 	$(MAKE) bench_web_js_api_parallel_chrome
 
+bench_web_js_api_parallel_firefox: browser_path = "$(WEB_RUNNER_DIR)/firefox/firefox/firefox"
+bench_web_js_api_parallel_firefox: driver_path = "$(WEB_RUNNER_DIR)/firefox/geckodriver"
+bench_web_js_api_parallel_firefox: browser_kind = firefox
+bench_web_js_api_parallel_firefox: filter = Bench
+
+.PHONY: bench_web_js_api_parallel_firefox # Run benchmarks for the web wasm api
+bench_web_js_api_parallel_firefox: run_web_js_api_parallel
+
+.PHONY: bench_web_js_api_parallel_firefox_ci # Run benchmarks for the web wasm api
+bench_web_js_api_parallel_firefox_ci: setup_venv
+	source ~/.nvm/nvm.sh && \
+	nvm install $(NODE_VERSION) && \
+	nvm use $(NODE_VERSION) && \
+	$(MAKE) bench_web_js_api_parallel_firefox
+
+.PHONY: bench_hlapi_erc20 # Run benchmarks for ECR20 operations
+bench_hlapi_erc20: install_rs_check_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
+	--bench hlapi-erc20 \
+	--features=$(TARGET_ARCH_FEATURE),integer,internal-keycache,pbs-stats,nightly-avx512 -p $(TFHE_SPEC) --
+
+.PHONY: bench_hlapi_erc20_gpu # Run benchmarks for ECR20 operations on GPU
+bench_hlapi_erc20_gpu: install_rs_check_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
+	--bench hlapi-erc20 \
+	--features=$(TARGET_ARCH_FEATURE),integer,gpu,internal-keycache,pbs-stats,nightly-avx512 -p $(TFHE_SPEC) --
+
+.PHONY: bench_tfhe_zk_pok # Run benchmarks for the tfhe_zk_pok crate
+bench_tfhe_zk_pok: install_rs_check_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" \
+	cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench -p tfhe-zk-pok --
+
 #
 # Utility tools
 #
@@ -1101,8 +1228,8 @@ bench_web_js_api_parallel_chrome_ci: setup_venv
 gen_key_cache: install_rs_build_toolchain
 	RUSTFLAGS="$(RUSTFLAGS) --cfg tarpaulin" cargo $(CARGO_RS_BUILD_TOOLCHAIN) run --profile $(CARGO_PROFILE) \
 		--example generates_test_keys \
-		--features=$(TARGET_ARCH_FEATURE),boolean,shortint,internal-keycache -- \
-		$(MULTI_BIT_ONLY) $(COVERAGE_ONLY)
+		--features=$(TARGET_ARCH_FEATURE),boolean,shortint,experimental,internal-keycache -p $(TFHE_SPEC) \
+		-- $(MULTI_BIT_ONLY) $(COVERAGE_ONLY)
 
 .PHONY: gen_key_cache_core_crypto # Run function to generate keys and cache them for core_crypto tests
 gen_key_cache_core_crypto: install_rs_build_toolchain
@@ -1149,9 +1276,9 @@ write_params_to_file: install_rs_check_toolchain
 
 .PHONY: clone_backward_compat_data # Clone the data repo needed for backward compatibility tests
 clone_backward_compat_data:
-	./scripts/clone_backward_compat_data.sh $(BACKWARD_COMPAT_DATA_URL) $(BACKWARD_COMPAT_DATA_BRANCH) tfhe/$(BACKWARD_COMPAT_DATA_DIR)
+	./scripts/clone_backward_compat_data.sh $(BACKWARD_COMPAT_DATA_URL) $(BACKWARD_COMPAT_DATA_BRANCH) $(TFHE_SRC)/$(BACKWARD_COMPAT_DATA_DIR)
 
-tfhe/$(BACKWARD_COMPAT_DATA_DIR): clone_backward_compat_data
+$(TFHE_SRC)/$(BACKWARD_COMPAT_DATA_DIR): clone_backward_compat_data
 
 #
 # Real use case examples
@@ -1178,19 +1305,202 @@ sha256_bool: install_rs_check_toolchain
 	--features=$(TARGET_ARCH_FEATURE),boolean
 
 .PHONY: pcc # pcc stands for pre commit checks (except GPU)
-pcc: no_tfhe_typo no_dbg_log check_fmt lint_doc check_md_docs_are_tested check_intra_md_links \
+pcc: no_tfhe_typo no_dbg_log check_fmt check_typos lint_doc check_md_docs_are_tested check_intra_md_links \
 clippy_all tfhe_lints check_compile_tests
 
 .PHONY: pcc_gpu # pcc stands for pre commit checks for GPU compilation
-pcc_gpu: clippy_gpu clippy_cuda_backend check_compile_tests_benches_gpu
+pcc_gpu: clippy_gpu clippy_cuda_backend check_compile_tests_benches_gpu check_rust_bindings_did_not_change
 
 .PHONY: fpcc # pcc stands for pre commit checks, the f stands for fast
-fpcc: no_tfhe_typo no_dbg_log check_fmt lint_doc check_md_docs_are_tested clippy_fast \
+fpcc: no_tfhe_typo no_dbg_log check_fmt check_typos lint_doc check_md_docs_are_tested clippy_fast \
 check_compile_tests
 
 .PHONY: conformance # Automatically fix problems that can be fixed
 conformance: fix_newline fmt
 
+#=============================== FFT Section ==================================
+.PHONY: doc_fft # Build rust doc for tfhe-fft
+doc_fft: install_rs_check_toolchain
+	@# Even though we are not in docs.rs, this allows to "just" build the doc
+	DOCS_RS=1 \
+	RUSTDOCFLAGS="--html-in-header katex-header.html" \
+	cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" doc \
+		--all-features --no-deps -p tfhe-fft
+
+.PHONY: docs_fft # Build rust doc tfhe-fft, alias for doc
+docs_fft: doc_fft
+
+.PHONY: lint_doc_fft # Build rust doc for tfhe-fft with linting enabled
+lint_doc_fft: install_rs_check_toolchain
+	@# Even though we are not in docs.rs, this allows to "just" build the doc
+	DOCS_RS=1 \
+	RUSTDOCFLAGS="--html-in-header katex-header.html -Dwarnings" \
+	cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" doc \
+		--all-features --no-deps -p tfhe-fft
+
+.PHONY: lint_docs_fft # Build rust doc for tfhe-fft with linting enabled, alias for lint_doc
+lint_docs_fft: lint_doc_fft
+
+.PHONY: clippy_fft # Run clippy lints on tfhe-fft
+clippy_fft: install_rs_check_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" clippy --all-targets \
+		--all-features -p tfhe-fft -- --no-deps -D warnings
+
+.PHONY: pcc_fft # pcc stands for pre commit checks
+pcc_fft: check_fmt lint_doc_fft clippy_fft
+
+.PHONY: build_fft
+build_fft: install_rs_build_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) build --release -p tfhe-fft
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) build --release -p tfhe-fft \
+		--features=fft128
+
+.PHONY: build_fft_no_std
+build_fft_no_std: install_rs_build_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) build --release -p tfhe-fft \
+		--no-default-features
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) build --release -p tfhe-fft \
+		--no-default-features \
+		--features=fft128
+
+##### Tests #####
+
+.PHONY: test_fft
+test_fft: install_rs_build_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --release -p tfhe-fft
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --release -p tfhe-fft \
+		--features=fft128
+
+.PHONY: test_fft_serde
+test_fft_serde: install_rs_build_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --release -p tfhe-fft \
+		--features=serde
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --release -p tfhe-fft \
+		--features=serde,fft128
+
+.PHONY: test_fft_nightly
+test_fft_nightly: install_rs_check_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_CHECK_TOOLCHAIN) test --release -p tfhe-fft \
+		--features=nightly
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_CHECK_TOOLCHAIN) test --release -p tfhe-fft \
+		--features=nightly,fft128
+
+.PHONY: test_fft_no_std
+test_fft_no_std: install_rs_build_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --release -p tfhe-fft \
+		--no-default-features 
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --release -p tfhe-fft \
+		--no-default-features \
+		--features=fft128
+
+.PHONY: test_fft_no_std_nightly
+test_fft_no_std_nightly: install_rs_check_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_CHECK_TOOLCHAIN) test --release -p tfhe-fft \
+		--no-default-features \
+		--features=nightly
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_CHECK_TOOLCHAIN) test --release -p tfhe-fft \
+		--no-default-features \
+		--features=nightly,fft128
+
+.PHONY: test_fft_node_js
+test_fft_node_js: install_rs_build_toolchain install_build_wasm32_target install_wasm_bindgen_cli
+	RUSTFLAGS="" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --release \
+		--features=serde --target wasm32-unknown-unknown -p tfhe-fft
+
+.PHONY: test_fft_node_js_ci
+test_fft_node_js_ci: check_nvm_installed
+	source ~/.nvm/nvm.sh && \
+	nvm install $(NODE_VERSION) && \
+	nvm use $(NODE_VERSION) && \
+	"$(MAKE)" test_fft_node_js
+
+.PHONY: test_fft_all
+test_fft_all: test_fft test_fft_serde test_fft_nightly test_fft_no_std test_fft_no_std_nightly \
+test_fft_node_js_ci
+
+##### Bench #####
+
+.PHONY: bench_fft # Run FFT benchmarks
+bench_fft: install_rs_check_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" bench --bench fft -p tfhe-fft \
+		--features=serde \
+		--features=nightly \
+		--features=fft128
+#============================End FFT Section ==================================
+
+#=============================== NTT Section ==================================
+.PHONY: doc_ntt # Build rust doc for tfhe-ntt
+doc_ntt: install_rs_check_toolchain
+	@# Even though we are not in docs.rs, this allows to "just" build the doc
+	DOCS_RS=1 \
+	RUSTDOCFLAGS="--html-in-header katex-header.html" \
+	cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" doc \
+		--all-features --no-deps -p tfhe-ntt
+
+.PHONY: docs_ntt # Build rust doc tfhe-ntt, alias for doc
+docs_ntt: doc_ntt
+
+.PHONY: lint_doc_ntt # Build rust doc for tfhe-ntt with linting enabled
+lint_doc_ntt: install_rs_check_toolchain
+	@# Even though we are not in docs.rs, this allows to "just" build the doc
+	DOCS_RS=1 \
+	RUSTDOCFLAGS="--html-in-header katex-header.html -Dwarnings" \
+	cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" doc \
+		--all-features --no-deps -p tfhe-ntt
+
+.PHONY: lint_docs_ntt # Build rust doc for tfhe-ntt with linting enabled, alias for lint_doc
+lint_docs_ntt: lint_doc_ntt
+
+.PHONY: clippy_ntt # Run clippy lints on tfhe-ntt
+clippy_ntt: install_rs_check_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" clippy --all-targets \
+		--all-features -p tfhe-ntt -- --no-deps -D warnings
+
+.PHONY: pcc_ntt # pcc stands for pre commit checks
+pcc_ntt: check_fmt lint_doc_ntt clippy_ntt
+
+.PHONY: build_ntt
+build_ntt: install_rs_build_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) build --release -p tfhe-ntt
+
+.PHONY: build_ntt_no_std
+build_ntt_no_std: install_rs_build_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) build --release -p tfhe-ntt \
+		--no-default-features
+
+##### Tests #####
+
+.PHONY: test_ntt
+test_ntt: install_rs_build_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --release -p tfhe-ntt
+
+.PHONY: test_ntt_nightly
+test_ntt_nightly: install_rs_check_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_CHECK_TOOLCHAIN) test --release -p tfhe-ntt \
+		--features=nightly
+
+.PHONY: test_ntt_no_std
+test_ntt_no_std: install_rs_build_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --release -p tfhe-ntt \
+		--no-default-features 
+
+.PHONY: test_ntt_no_std_nightly
+test_ntt_no_std_nightly: install_rs_check_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_CHECK_TOOLCHAIN) test --release -p tfhe-ntt \
+		--no-default-features \
+		--features=nightly
+
+.PHONY: test_ntt_all
+test_ntt_all: test_ntt test_ntt_no_std test_ntt_nightly test_ntt_no_std_nightly
+
+##### Bench #####
+
+.PHONY: bench_ntt # Run NTT benchmarks
+bench_ntt: install_rs_check_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" bench --bench ntt -p tfhe-ntt \
+		--features=nightly
+#============================End NTT Section ==================================
+
 .PHONY: help # Generate list of targets with descriptions
 help:
 	@grep '^\.PHONY: .* #' Makefile | sed 's/\.PHONY: \(.*\) # \(.*\)/\1\t\2/' | expand -t30 | sort

README.md

@@ -89,7 +89,7 @@ tfhe = { version = "*", features = ["boolean", "shortint", "integer", "x86_64"]
 ```
 
 > [!Note]
-> Note: You need to use a Rust version >= 1.73 to compile TFHE-rs.
+> Note: You need to use a Rust version >= 1.81 to compile TFHE-rs.
 
 > [!Note]
 > Note: aarch64-based machines are not yet supported for Windows as it's currently missing an entropy source to be able to seed the [CSPRNGs](https://en.wikipedia.org/wiki/Cryptographically_secure_pseudorandom_number_generator) used in TFHE-rs.

_typos.toml

@@ -0,0 +1,15 @@
+[default]
+extend-ignore-identifiers-re = [
+    # Related to serialized object
+    "ser",
+    "unser",
+    # Used when dumping tfhe-rs parameters set into Sage format
+    "ND.*",
+    # Related to FHE strings example handling "banana"
+    "ba",
+    "enc_ba",
+    # Example with string replacing "hello" with "herlo"
+    "herlo",
+    # Example in trivium
+    "C9217BA0D762ACA1"
+]

apps/trivium/Cargo.toml

@@ -9,11 +9,11 @@ edition = "2021"
 rayon = { version = "1.7.0"}
 
 [target.'cfg(target_arch = "x86_64")'.dependencies.tfhe]
-path = "../../tfhe"
+path = "../../crates/tfhe"
 features = [ "boolean", "shortint", "integer", "x86_64" ]
 
 [target.'cfg(target_arch = "aarch64")'.dependencies.tfhe]
-path = "../../tfhe"
+path = "../../crates/tfhe"
 features = [ "boolean", "shortint", "integer", "aarch64-unix" ]
 
 [dev-dependencies]

apps/trivium/README.md

@@ -7,7 +7,7 @@ using multithreading to accelerate the computation.
 
 
 Quite similarly, the function `TriviumStream::<FheBool>::new` will return a very similar object running in FHE space. Its arguments are
-2 arrays of 80 FheBool representing the encrypted Trivium key, and the encrypted IV. It also requires a reference to the the server key of the 
+2 arrays of 80 FheBool representing the encrypted Trivium key, and the encrypted IV. It also requires a reference to the server key of the 
 current scheme. This means that any user of this feature must also have the `tfhe-rs` crate as a dependency.
 
 

apps/trivium/benches/kreyvium_shortint.rs

@@ -1,5 +1,6 @@
 use criterion::Criterion;
 use tfhe::prelude::*;
+use tfhe::shortint::parameters::PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M64;
 use tfhe::shortint::prelude::*;
 use tfhe::{generate_keys, ConfigBuilder, FheUint64};
 use tfhe_trivium::{KreyviumStreamShortint, TransCiphering};
@@ -10,7 +11,8 @@ pub fn kreyvium_shortint_warmup(c: &mut Criterion) {
     let underlying_ck: tfhe::shortint::ClientKey = (*hl_client_key.as_ref()).clone().into();
     let underlying_sk: tfhe::shortint::ServerKey = (*hl_server_key.as_ref()).clone().into();
 
-    let (client_key, server_key): (ClientKey, ServerKey) = gen_keys(PARAM_MESSAGE_1_CARRY_1_KS_PBS);
+    let (client_key, server_key): (ClientKey, ServerKey) =
+        gen_keys(PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M64);
 
     let ksk = KeySwitchingKey::new(
         (&client_key, Some(&server_key)),
@@ -60,7 +62,8 @@ pub fn kreyvium_shortint_gen(c: &mut Criterion) {
     let underlying_ck: tfhe::shortint::ClientKey = (*hl_client_key.as_ref()).clone().into();
     let underlying_sk: tfhe::shortint::ServerKey = (*hl_server_key.as_ref()).clone().into();
 
-    let (client_key, server_key): (ClientKey, ServerKey) = gen_keys(PARAM_MESSAGE_1_CARRY_1_KS_PBS);
+    let (client_key, server_key): (ClientKey, ServerKey) =
+        gen_keys(PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M64);
 
     let ksk = KeySwitchingKey::new(
         (&client_key, Some(&server_key)),
@@ -105,7 +108,8 @@ pub fn kreyvium_shortint_trans(c: &mut Criterion) {
     let underlying_ck: tfhe::shortint::ClientKey = (*hl_client_key.as_ref()).clone().into();
     let underlying_sk: tfhe::shortint::ServerKey = (*hl_server_key.as_ref()).clone().into();
 
-    let (client_key, server_key): (ClientKey, ServerKey) = gen_keys(PARAM_MESSAGE_1_CARRY_1_KS_PBS);
+    let (client_key, server_key): (ClientKey, ServerKey) =
+        gen_keys(PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M64);
 
     let ksk = KeySwitchingKey::new(
         (&client_key, Some(&server_key)),

apps/trivium/benches/trivium_shortint.rs

@@ -1,5 +1,6 @@
 use criterion::Criterion;
 use tfhe::prelude::*;
+use tfhe::shortint::parameters::PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M64;
 use tfhe::shortint::prelude::*;
 use tfhe::{generate_keys, ConfigBuilder, FheUint64};
 use tfhe_trivium::{TransCiphering, TriviumStreamShortint};
@@ -10,7 +11,8 @@ pub fn trivium_shortint_warmup(c: &mut Criterion) {
     let underlying_ck: tfhe::shortint::ClientKey = (*hl_client_key.as_ref()).clone().into();
     let underlying_sk: tfhe::shortint::ServerKey = (*hl_server_key.as_ref()).clone().into();
 
-    let (client_key, server_key): (ClientKey, ServerKey) = gen_keys(PARAM_MESSAGE_1_CARRY_1_KS_PBS);
+    let (client_key, server_key): (ClientKey, ServerKey) =
+        gen_keys(PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M64);
 
     let ksk = KeySwitchingKey::new(
         (&client_key, Some(&server_key)),
@@ -60,7 +62,8 @@ pub fn trivium_shortint_gen(c: &mut Criterion) {
     let underlying_ck: tfhe::shortint::ClientKey = (*hl_client_key.as_ref()).clone().into();
     let underlying_sk: tfhe::shortint::ServerKey = (*hl_server_key.as_ref()).clone().into();
 
-    let (client_key, server_key): (ClientKey, ServerKey) = gen_keys(PARAM_MESSAGE_1_CARRY_1_KS_PBS);
+    let (client_key, server_key): (ClientKey, ServerKey) =
+        gen_keys(PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M64);
 
     let ksk = KeySwitchingKey::new(
         (&client_key, Some(&server_key)),
@@ -105,7 +108,8 @@ pub fn trivium_shortint_trans(c: &mut Criterion) {
     let underlying_ck: tfhe::shortint::ClientKey = (*hl_client_key.as_ref()).clone().into();
     let underlying_sk: tfhe::shortint::ServerKey = (*hl_server_key.as_ref()).clone().into();
 
-    let (client_key, server_key): (ClientKey, ServerKey) = gen_keys(PARAM_MESSAGE_1_CARRY_1_KS_PBS);
+    let (client_key, server_key): (ClientKey, ServerKey) =
+        gen_keys(PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M64);
 
     let ksk = KeySwitchingKey::new(
         (&client_key, Some(&server_key)),

apps/trivium/src/kreyvium/test.rs

@@ -1,7 +1,7 @@
 use crate::{KreyviumStream, KreyviumStreamByte, KreyviumStreamShortint, TransCiphering};
 use tfhe::prelude::*;
+use tfhe::shortint::parameters::PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M64;
 use tfhe::{generate_keys, ConfigBuilder, FheBool, FheUint64, FheUint8};
-
 // Values for these tests come from the github repo renaud1239/Kreyvium,
 // commit fd6828f68711276c25f55e605935028f5e843f43
 
@@ -221,7 +221,8 @@ fn kreyvium_test_shortint_long() {
     let underlying_ck: tfhe::shortint::ClientKey = (*hl_client_key.as_ref()).clone().into();
     let underlying_sk: tfhe::shortint::ServerKey = (*hl_server_key.as_ref()).clone().into();
 
-    let (client_key, server_key): (ClientKey, ServerKey) = gen_keys(PARAM_MESSAGE_1_CARRY_1_KS_PBS);
+    let (client_key, server_key): (ClientKey, ServerKey) =
+        gen_keys(PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M64);
 
     let ksk = KeySwitchingKey::new(
         (&client_key, Some(&server_key)),

apps/trivium/src/trivium/test.rs

@@ -1,7 +1,7 @@
 use crate::{TransCiphering, TriviumStream, TriviumStreamByte, TriviumStreamShortint};
 use tfhe::prelude::*;
+use tfhe::shortint::parameters::PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M64;
 use tfhe::{generate_keys, ConfigBuilder, FheBool, FheUint64, FheUint8};
-
 // Values for these tests come from the github repo cantora/avr-crypto-lib, commit 2a5b018,
 // file testvectors/trivium-80.80.test-vectors
 
@@ -357,7 +357,8 @@ fn trivium_test_shortint_long() {
     let underlying_ck: tfhe::shortint::ClientKey = (*hl_client_key.as_ref()).clone().into();
     let underlying_sk: tfhe::shortint::ServerKey = (*hl_server_key.as_ref()).clone().into();
 
-    let (client_key, server_key): (ClientKey, ServerKey) = gen_keys(PARAM_MESSAGE_1_CARRY_1_KS_PBS);
+    let (client_key, server_key): (ClientKey, ServerKey) =
+        gen_keys(PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M64);
 
     let ksk = KeySwitchingKey::new(
         (&client_key, Some(&server_key)),

backends/tfhe-cuda-backend/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "tfhe-cuda-backend"
-version = "0.4.0"
+version = "0.6.0"
 edition = "2021"
 authors = ["Zama team"]
 license = "BSD-3-Clause-Clear"
@@ -14,3 +14,4 @@ keywords = ["fully", "homomorphic", "encryption", "fhe", "cryptography"]
 [build-dependencies]
 cmake = { version = "0.1" }
 pkg-config = { version = "0.3" }
+bindgen = "0.70.1"

backends/tfhe-cuda-backend/build.rs

@@ -1,8 +1,8 @@
-use std::env;
+use std::path::PathBuf;
 use std::process::Command;
 
 fn main() {
-    if let Ok(val) = env::var("DOCS_RS") {
+    if let Ok(val) = std::env::var("DOCS_RS") {
         if val.parse::<u32>() == Ok(1) {
             return;
         }
@@ -26,7 +26,8 @@ fn main() {
     println!("cargo::rerun-if-changed=cuda/tests_and_benchmarks");
     println!("cargo::rerun-if-changed=cuda/CMakeLists.txt");
     println!("cargo::rerun-if-changed=src");
-    if env::consts::OS == "linux" {
+
+    if std::env::consts::OS == "linux" {
         let output = Command::new("./get_os_name.sh").output().unwrap();
         let distribution = String::from_utf8(output.stdout).unwrap();
         if distribution != "Ubuntu\n" {
@@ -35,6 +36,7 @@ fn main() {
                 Only Ubuntu is supported by tfhe-cuda-backend at this time. Build may fail\n"
             );
         }
+
         let dest = cmake::build("cuda");
         println!("cargo:rustc-link-search=native={}", dest.display());
         println!("cargo:rustc-link-lib=static=tfhe_cuda_backend");
@@ -51,6 +53,57 @@ fn main() {
         println!("cargo:rustc-link-lib=cudart");
         println!("cargo:rustc-link-search=native=/usr/lib/x86_64-linux-gnu/");
         println!("cargo:rustc-link-lib=stdc++");
+
+        let header_path = "wrapper.h";
+        let headers = vec![
+            "wrapper.h",
+            "cuda/include/ciphertext.h",
+            "cuda/include/integer/compression/compression.h",
+            "cuda/include/integer/integer.h",
+            "cuda/include/keyswitch.h",
+            "cuda/include/linear_algebra.h",
+            "cuda/include/pbs/programmable_bootstrap.h",
+            "cuda/include/pbs/programmable_bootstrap_multibit.h",
+        ];
+        let out_path = PathBuf::from("src").join("bindings.rs");
+        let bindings_modified = if out_path.exists() {
+            std::fs::metadata(&out_path).unwrap().modified().unwrap()
+        } else {
+            std::time::SystemTime::UNIX_EPOCH // If bindings file doesn't exist, consider it older
+        };
+        let mut headers_modified = bindings_modified;
+        for header in headers {
+            println!("cargo:rerun-if-changed={}", header);
+            // Check modification times
+            let header_modified = std::fs::metadata(header).unwrap().modified().unwrap();
+            if header_modified > headers_modified {
+                headers_modified = header_modified;
+            }
+        }
+
+        // Regenerate bindings only if header has been modified
+        if headers_modified > bindings_modified {
+            let bindings = bindgen::Builder::default()
+                .header(header_path)
+                // allow only what we are interested in, the custom types appearing in the interface
+                .allowlist_type("PBS_TYPE")
+                .allowlist_type("SHIFT_OR_ROTATE_TYPE")
+                // and the functions reachable from the headers included in wrapper.h
+                .allowlist_function(".*")
+                .clang_arg("-x")
+                .clang_arg("c++")
+                .clang_arg("-std=c++17")
+                .clang_arg("-I/usr/include")
+                .clang_arg("-I/usr/local/include")
+                .ctypes_prefix("ffi")
+                .raw_line("use crate::ffi;")
+                .generate()
+                .expect("Unable to generate bindings");
+
+            bindings
+                .write_to_file(&out_path)
+                .expect("Couldn't write bindings!");
+        }
     } else {
         panic!(
             "Error: platform not supported, tfhe-cuda-backend not built (only Linux is supported)"

backends/tfhe-cuda-backend/cuda/include/ciphertext.h

@@ -1,25 +1,24 @@
 #ifndef CUDA_CIPHERTEXT_H
 #define CUDA_CIPHERTEXT_H
 
-#include "device.h"
-#include <cstdint>
+#include "stdint.h"
 
 extern "C" {
 void cuda_convert_lwe_ciphertext_vector_to_gpu_64(void *stream,
                                                   uint32_t gpu_index,
-                                                  void *dest, void *src,
+                                                  void *dest, void const *src,
                                                   uint32_t number_of_cts,
                                                   uint32_t lwe_dimension);
 void cuda_convert_lwe_ciphertext_vector_to_cpu_64(void *stream,
                                                   uint32_t gpu_index,
-                                                  void *dest, void *src,
+                                                  void *dest, void const *src,
                                                   uint32_t number_of_cts,
                                                   uint32_t lwe_dimension);
 
 void cuda_glwe_sample_extract_64(void *stream, uint32_t gpu_index,
-                                 void *lwe_array_out, void *glwe_array_in,
-                                 uint32_t *nth_array, uint32_t num_glwes,
+                                 void *lwe_array_out, void const *glwe_array_in,
+                                 uint32_t const *nth_array, uint32_t num_nths,
                                  uint32_t glwe_dimension,
                                  uint32_t polynomial_size);
-};
+}
 #endif

backends/tfhe-cuda-backend/cuda/include/device.h

@@ -27,12 +27,23 @@ inline void cuda_error(cudaError_t code, const char *file, int line) {
     std::abort();                                                              \
   }
 
+cudaEvent_t cuda_create_event(uint32_t gpu_index);
+
+void cuda_event_record(cudaEvent_t event, cudaStream_t stream,
+                       uint32_t gpu_index);
+void cuda_stream_wait_event(cudaStream_t stream, cudaEvent_t event,
+                            uint32_t gpu_index);
+
+void cuda_event_destroy(cudaEvent_t event, uint32_t gpu_index);
+
 cudaStream_t cuda_create_stream(uint32_t gpu_index);
 
 void cuda_destroy_stream(cudaStream_t stream, uint32_t gpu_index);
 
 void cuda_synchronize_stream(cudaStream_t stream, uint32_t gpu_index);
 
+uint32_t cuda_is_available();
+
 void *cuda_malloc(uint64_t size, uint32_t gpu_index);
 
 void *cuda_malloc_async(uint64_t size, cudaStream_t stream, uint32_t gpu_index);
@@ -42,7 +53,7 @@ void cuda_check_valid_malloc(uint64_t size, uint32_t gpu_index);
 void cuda_memcpy_async_to_gpu(void *dest, void *src, uint64_t size,
                               cudaStream_t stream, uint32_t gpu_index);
 
-void cuda_memcpy_async_gpu_to_gpu(void *dest, void *src, uint64_t size,
+void cuda_memcpy_async_gpu_to_gpu(void *dest, void const *src, uint64_t size,
                                   cudaStream_t stream, uint32_t gpu_index);
 
 void cuda_memcpy_gpu_to_gpu(void *dest, void *src, uint64_t size,

backends/tfhe-cuda-backend/cuda/include/integer/compression/compression.h

@@ -0,0 +1,45 @@
+#ifndef CUDA_INTEGER_COMPRESSION_H
+#define CUDA_INTEGER_COMPRESSION_H
+
+#include "../../pbs/pbs_enums.h"
+
+extern "C" {
+void scratch_cuda_integer_compress_radix_ciphertext_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    int8_t **mem_ptr, uint32_t compression_glwe_dimension,
+    uint32_t compression_polynomial_size, uint32_t lwe_dimension,
+    uint32_t ks_level, uint32_t ks_base_log, uint32_t num_radix_blocks,
+    uint32_t message_modulus, uint32_t carry_modulus, PBS_TYPE pbs_type,
+    uint32_t lwe_per_glwe, uint32_t storage_log_modulus,
+    bool allocate_gpu_memory);
+
+void scratch_cuda_integer_decompress_radix_ciphertext_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    int8_t **mem_ptr, uint32_t encryption_glwe_dimension,
+    uint32_t encryption_polynomial_size, uint32_t compression_glwe_dimension,
+    uint32_t compression_polynomial_size, uint32_t lwe_dimension,
+    uint32_t pbs_level, uint32_t pbs_base_log, uint32_t num_radix_blocks,
+    uint32_t message_modulus, uint32_t carry_modulus, PBS_TYPE pbs_type,
+    uint32_t storage_log_modulus, uint32_t body_count,
+    bool allocate_gpu_memory);
+
+void cuda_integer_compress_radix_ciphertext_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    void *glwe_array_out, void const *lwe_array_in, void *const *fp_ksk,
+    uint32_t num_nths, int8_t *mem_ptr);
+
+void cuda_integer_decompress_radix_ciphertext_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    void *lwe_array_out, void const *glwe_in, uint32_t const *indexes_array,
+    uint32_t indexes_array_size, void *const *bsks, int8_t *mem_ptr);
+
+void cleanup_cuda_integer_compress_radix_ciphertext_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    int8_t **mem_ptr_void);
+
+void cleanup_cuda_integer_decompress_radix_ciphertext_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    int8_t **mem_ptr_void);
+}
+
+#endif

backends/tfhe-cuda-backend/cuda/include/integer/compression/compression_utilities.h

@@ -1,46 +1,7 @@
-#ifndef CUDA_INTEGER_COMPRESSION_H
-#define CUDA_INTEGER_COMPRESSION_H
+#ifndef CUDA_INTEGER_COMPRESSION_UTILITIES_H
+#define CUDA_INTEGER_COMPRESSION_UTILITIES_H
 
-#include "integer.h"
-
-extern "C" {
-void scratch_cuda_integer_compress_radix_ciphertext_64(
-    void **streams, uint32_t *gpu_indexes, uint32_t gpu_count, int8_t **mem_ptr,
-    uint32_t compression_glwe_dimension, uint32_t compression_polynomial_size,
-    uint32_t lwe_dimension, uint32_t ks_level, uint32_t ks_base_log,
-    uint32_t num_lwes, uint32_t message_modulus, uint32_t carry_modulus,
-    PBS_TYPE pbs_type, uint32_t lwe_per_glwe, uint32_t storage_log_modulus,
-    bool allocate_gpu_memory);
-
-void scratch_cuda_integer_decompress_radix_ciphertext_64(
-    void **streams, uint32_t *gpu_indexes, uint32_t gpu_count, int8_t **mem_ptr,
-    uint32_t encryption_glwe_dimension, uint32_t encryption_polynomial_size,
-    uint32_t compression_glwe_dimension, uint32_t compression_polynomial_size,
-    uint32_t lwe_dimension, uint32_t pbs_level, uint32_t pbs_base_log,
-    uint32_t num_lwes, uint32_t message_modulus, uint32_t carry_modulus,
-    PBS_TYPE pbs_type, uint32_t storage_log_modulus, uint32_t body_count,
-    bool allocate_gpu_memory);
-
-void cuda_integer_compress_radix_ciphertext_64(
-    void **streams, uint32_t *gpu_indexes, uint32_t gpu_count,
-    void *glwe_array_out, void *lwe_array_in, void **fp_ksk, uint32_t num_nths,
-    int8_t *mem_ptr);
-
-void cuda_integer_decompress_radix_ciphertext_64(
-    void **streams, uint32_t *gpu_indexes, uint32_t gpu_count,
-    void *lwe_array_out, void *glwe_in, uint32_t *indexes_array,
-    uint32_t indexes_array_size, void **bsks, int8_t *mem_ptr);
-
-void cleanup_cuda_integer_compress_radix_ciphertext_64(void **streams,
-                                                       uint32_t *gpu_indexes,
-                                                       uint32_t gpu_count,
-                                                       int8_t **mem_ptr_void);
-
-void cleanup_cuda_integer_decompress_radix_ciphertext_64(void **streams,
-                                                         uint32_t *gpu_indexes,
-                                                         uint32_t gpu_count,
-                                                         int8_t **mem_ptr_void);
-}
+#include "../integer_utilities.h"
 
 template <typename Torus> struct int_compression {
   int_radix_params compression_params;
@@ -54,7 +15,7 @@ template <typename Torus> struct int_compression {
   Torus *tmp_lwe;
   Torus *tmp_glwe_array_out;
 
-  int_compression(cudaStream_t *streams, uint32_t *gpu_indexes,
+  int_compression(cudaStream_t const *streams, uint32_t const *gpu_indexes,
                   uint32_t gpu_count, int_radix_params compression_params,
                   uint32_t num_radix_blocks, uint32_t lwe_per_glwe,
                   uint32_t storage_log_modulus, bool allocate_gpu_memory) {
@@ -81,7 +42,7 @@ template <typename Torus> struct int_compression {
           num_radix_blocks, true);
     }
   }
-  void release(cudaStream_t *streams, uint32_t *gpu_indexes,
+  void release(cudaStream_t const *streams, uint32_t const *gpu_indexes,
                uint32_t gpu_count) {
     cuda_drop_async(tmp_lwe, streams[0], gpu_indexes[0]);
     cuda_drop_async(tmp_glwe_array_out, streams[0], gpu_indexes[0]);
@@ -96,7 +57,7 @@ template <typename Torus> struct int_decompression {
 
   uint32_t storage_log_modulus;
 
-  uint32_t num_lwes;
+  uint32_t num_radix_blocks;
   uint32_t body_count;
 
   Torus *tmp_extracted_glwe;
@@ -105,7 +66,7 @@ template <typename Torus> struct int_decompression {
 
   int_radix_lut<Torus> *carry_extract_lut;
 
-  int_decompression(cudaStream_t *streams, uint32_t *gpu_indexes,
+  int_decompression(cudaStream_t const *streams, uint32_t const *gpu_indexes,
                     uint32_t gpu_count, int_radix_params encryption_params,
                     int_radix_params compression_params,
                     uint32_t num_radix_blocks, uint32_t body_count,
@@ -113,7 +74,7 @@ template <typename Torus> struct int_decompression {
     this->encryption_params = encryption_params;
     this->compression_params = compression_params;
     this->storage_log_modulus = storage_log_modulus;
-    this->num_lwes = num_radix_blocks;
+    this->num_radix_blocks = num_radix_blocks;
     this->body_count = body_count;
 
     if (allocate_gpu_memory) {
@@ -134,30 +95,29 @@ template <typename Torus> struct int_decompression {
       tmp_extracted_lwe = (Torus *)cuda_malloc_async(
           num_radix_blocks * lwe_accumulator_size * sizeof(Torus), streams[0],
           gpu_indexes[0]);
-      // Decompression
+
       // Carry extract LUT
       auto carry_extract_f = [encryption_params](Torus x) -> Torus {
         return x / encryption_params.message_modulus;
       };
 
       generate_device_accumulator<Torus>(
-          streams[0], gpu_indexes[0],
-          carry_extract_lut->get_lut(gpu_indexes[0], 0),
+          streams[0], gpu_indexes[0], carry_extract_lut->get_lut(0, 0),
           encryption_params.glwe_dimension, encryption_params.polynomial_size,
           encryption_params.message_modulus, encryption_params.carry_modulus,
           carry_extract_f);
 
-      carry_extract_lut->broadcast_lut(streams, gpu_indexes, gpu_indexes[0]);
+      carry_extract_lut->broadcast_lut(streams, gpu_indexes, 0);
     }
   }
-  void release(cudaStream_t *streams, uint32_t *gpu_indexes,
+  void release(cudaStream_t const *streams, uint32_t const *gpu_indexes,
                uint32_t gpu_count) {
     cuda_drop_async(tmp_extracted_glwe, streams[0], gpu_indexes[0]);
     cuda_drop_async(tmp_extracted_lwe, streams[0], gpu_indexes[0]);
     cuda_drop_async(tmp_indexes_array, streams[0], gpu_indexes[0]);
 
     carry_extract_lut->release(streams, gpu_indexes, gpu_count);
-    delete (carry_extract_lut);
+    delete carry_extract_lut;
   }
 };
 #endif

backends/tfhe-cuda-backend/cuda/include/integer/integer.h

@@ -0,0 +1,444 @@
+#ifndef CUDA_INTEGER_H
+#define CUDA_INTEGER_H
+
+#include "../pbs/pbs_enums.h"
+#include <stdint.h>
+
+enum OUTPUT_CARRY { NONE = 0, GENERATED = 1, PROPAGATED = 2 };
+enum SHIFT_OR_ROTATE_TYPE {
+  LEFT_SHIFT = 0,
+  RIGHT_SHIFT = 1,
+  LEFT_ROTATE = 2,
+  RIGHT_ROTATE = 3
+};
+enum BITOP_TYPE {
+  BITAND = 0,
+  BITOR = 1,
+  BITXOR = 2,
+  SCALAR_BITAND = 3,
+  SCALAR_BITOR = 4,
+  SCALAR_BITXOR = 5,
+};
+
+enum COMPARISON_TYPE {
+  EQ = 0,
+  NE = 1,
+  GT = 2,
+  GE = 3,
+  LT = 4,
+  LE = 5,
+  MAX = 6,
+  MIN = 7,
+};
+
+enum CMP_ORDERING { IS_INFERIOR = 0, IS_EQUAL = 1, IS_SUPERIOR = 2 };
+
+enum SIGNED_OPERATION { ADDITION = 1, SUBTRACTION = -1 };
+
+enum outputFlag { FLAG_NONE = 0, FLAG_OVERFLOW = 1, FLAG_CARRY = 2 };
+
+extern "C" {
+void scratch_cuda_apply_univariate_lut_kb_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    int8_t **mem_ptr, void const *input_lut, uint32_t lwe_dimension,
+    uint32_t glwe_dimension, uint32_t polynomial_size, uint32_t ks_level,
+    uint32_t ks_base_log, uint32_t pbs_level, uint32_t pbs_base_log,
+    uint32_t grouping_factor, uint32_t input_lwe_ciphertext_count,
+    uint32_t message_modulus, uint32_t carry_modulus, PBS_TYPE pbs_type,
+    bool allocate_gpu_memory);
+
+void cuda_apply_univariate_lut_kb_64(void *const *streams,
+                                     uint32_t const *gpu_indexes,
+                                     uint32_t gpu_count, void *output_radix_lwe,
+                                     void const *input_radix_lwe,
+                                     int8_t *mem_ptr, void *const *ksks,
+                                     void *const *bsks, uint32_t num_blocks);
+
+void cleanup_cuda_apply_univariate_lut_kb_64(void *const *streams,
+                                             uint32_t const *gpu_indexes,
+                                             uint32_t gpu_count,
+                                             int8_t **mem_ptr_void);
+
+void scratch_cuda_apply_bivariate_lut_kb_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    int8_t **mem_ptr, void const *input_lut, uint32_t lwe_dimension,
+    uint32_t glwe_dimension, uint32_t polynomial_size, uint32_t ks_level,
+    uint32_t ks_base_log, uint32_t pbs_level, uint32_t pbs_base_log,
+    uint32_t grouping_factor, uint32_t input_lwe_ciphertext_count,
+    uint32_t message_modulus, uint32_t carry_modulus, PBS_TYPE pbs_type,
+    bool allocate_gpu_memory);
+
+void cuda_apply_bivariate_lut_kb_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    void *output_radix_lwe, void const *input_radix_lwe_1,
+    void const *input_radix_lwe_2, int8_t *mem_ptr, void *const *ksks,
+    void *const *bsks, uint32_t num_blocks, uint32_t shift);
+
+void cleanup_cuda_apply_bivariate_lut_kb_64(void *const *streams,
+                                            uint32_t const *gpu_indexes,
+                                            uint32_t gpu_count,
+                                            int8_t **mem_ptr_void);
+
+void cuda_apply_many_univariate_lut_kb_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    void *output_radix_lwe, void const *input_radix_lwe, int8_t *mem_ptr,
+    void *const *ksks, void *const *bsks, uint32_t num_blocks,
+    uint32_t num_luts, uint32_t lut_stride);
+
+void scratch_cuda_full_propagation_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    int8_t **mem_ptr, uint32_t lwe_dimension, uint32_t glwe_dimension,
+    uint32_t polynomial_size, uint32_t ks_level, uint32_t ks_base_log,
+    uint32_t pbs_level, uint32_t pbs_base_log, uint32_t grouping_factor,
+    uint32_t message_modulus, uint32_t carry_modulus, PBS_TYPE pbs_type,
+    bool allocate_gpu_memory);
+
+void cuda_full_propagation_64_inplace(void *const *streams,
+                                      uint32_t const *gpu_indexes,
+                                      uint32_t gpu_count, void *input_blocks,
+                                      int8_t *mem_ptr, void *const *ksks,
+                                      void *const *bsks, uint32_t num_blocks);
+
+void cleanup_cuda_full_propagation(void *const *streams,
+                                   uint32_t const *gpu_indexes,
+                                   uint32_t gpu_count, int8_t **mem_ptr_void);
+
+void scratch_cuda_integer_mult_radix_ciphertext_kb_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    int8_t **mem_ptr, bool const is_boolean_left, bool const is_boolean_right,
+    uint32_t message_modulus, uint32_t carry_modulus, uint32_t glwe_dimension,
+    uint32_t lwe_dimension, uint32_t polynomial_size, uint32_t pbs_base_log,
+    uint32_t pbs_level, uint32_t ks_base_log, uint32_t ks_level,
+    uint32_t grouping_factor, uint32_t num_blocks, PBS_TYPE pbs_type,
+    bool allocate_gpu_memory);
+
+void cuda_integer_mult_radix_ciphertext_kb_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    void *radix_lwe_out, void const *radix_lwe_left, bool const is_bool_left,
+    void const *radix_lwe_right, bool const is_bool_right, void *const *bsks,
+    void *const *ksks, int8_t *mem_ptr, uint32_t polynomial_size,
+    uint32_t num_blocks);
+
+void cleanup_cuda_integer_mult(void *const *streams,
+                               uint32_t const *gpu_indexes, uint32_t gpu_count,
+                               int8_t **mem_ptr_void);
+
+void cuda_negate_integer_radix_ciphertext_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    void *lwe_array_out, void const *lwe_array_in, uint32_t lwe_dimension,
+    uint32_t lwe_ciphertext_count, uint32_t message_modulus,
+    uint32_t carry_modulus);
+
+void cuda_scalar_addition_integer_radix_ciphertext_64_inplace(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    void *lwe_array, void const *scalar_input, uint32_t lwe_dimension,
+    uint32_t lwe_ciphertext_count, uint32_t message_modulus,
+    uint32_t carry_modulus);
+
+void scratch_cuda_integer_radix_logical_scalar_shift_kb_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    int8_t **mem_ptr, uint32_t glwe_dimension, uint32_t polynomial_size,
+    uint32_t big_lwe_dimension, uint32_t small_lwe_dimension, uint32_t ks_level,
+    uint32_t ks_base_log, uint32_t pbs_level, uint32_t pbs_base_log,
+    uint32_t grouping_factor, uint32_t num_blocks, uint32_t message_modulus,
+    uint32_t carry_modulus, PBS_TYPE pbs_type, SHIFT_OR_ROTATE_TYPE shift_type,
+    bool allocate_gpu_memory);
+
+void cuda_integer_radix_logical_scalar_shift_kb_64_inplace(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    void *lwe_array, uint32_t shift, int8_t *mem_ptr, void *const *bsks,
+    void *const *ksks, uint32_t num_blocks);
+
+void scratch_cuda_integer_radix_arithmetic_scalar_shift_kb_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    int8_t **mem_ptr, uint32_t glwe_dimension, uint32_t polynomial_size,
+    uint32_t big_lwe_dimension, uint32_t small_lwe_dimension, uint32_t ks_level,
+    uint32_t ks_base_log, uint32_t pbs_level, uint32_t pbs_base_log,
+    uint32_t grouping_factor, uint32_t num_blocks, uint32_t message_modulus,
+    uint32_t carry_modulus, PBS_TYPE pbs_type, SHIFT_OR_ROTATE_TYPE shift_type,
+    bool allocate_gpu_memory);
+
+void cuda_integer_radix_arithmetic_scalar_shift_kb_64_inplace(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    void *lwe_array, uint32_t shift, int8_t *mem_ptr, void *const *bsks,
+    void *const *ksks, uint32_t num_blocks);
+
+void cleanup_cuda_integer_radix_logical_scalar_shift(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    int8_t **mem_ptr_void);
+
+void cleanup_cuda_integer_radix_arithmetic_scalar_shift(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    int8_t **mem_ptr_void);
+
+void scratch_cuda_integer_radix_shift_and_rotate_kb_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    int8_t **mem_ptr, uint32_t glwe_dimension, uint32_t polynomial_size,
+    uint32_t big_lwe_dimension, uint32_t small_lwe_dimension, uint32_t ks_level,
+    uint32_t ks_base_log, uint32_t pbs_level, uint32_t pbs_base_log,
+    uint32_t grouping_factor, uint32_t num_blocks, uint32_t message_modulus,
+    uint32_t carry_modulus, PBS_TYPE pbs_type, SHIFT_OR_ROTATE_TYPE shift_type,
+    bool is_signed, bool allocate_gpu_memory);
+
+void cuda_integer_radix_shift_and_rotate_kb_64_inplace(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    void *lwe_array, void const *lwe_shift, int8_t *mem_ptr, void *const *bsks,
+    void *const *ksks, uint32_t num_blocks);
+
+void cleanup_cuda_integer_radix_shift_and_rotate(void *const *streams,
+                                                 uint32_t const *gpu_indexes,
+                                                 uint32_t gpu_count,
+                                                 int8_t **mem_ptr_void);
+
+void scratch_cuda_integer_radix_comparison_kb_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    int8_t **mem_ptr, uint32_t glwe_dimension, uint32_t polynomial_size,
+    uint32_t big_lwe_dimension, uint32_t small_lwe_dimension, uint32_t ks_level,
+    uint32_t ks_base_log, uint32_t pbs_level, uint32_t pbs_base_log,
+    uint32_t grouping_factor, uint32_t lwe_ciphertext_count,
+    uint32_t message_modulus, uint32_t carry_modulus, PBS_TYPE pbs_type,
+    COMPARISON_TYPE op_type, bool is_signed, bool allocate_gpu_memory);
+
+void cuda_comparison_integer_radix_ciphertext_kb_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    void *lwe_array_out, void const *lwe_array_1, void const *lwe_array_2,
+    int8_t *mem_ptr, void *const *bsks, void *const *ksks,
+    uint32_t lwe_ciphertext_count);
+
+void cuda_scalar_comparison_integer_radix_ciphertext_kb_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    void *lwe_array_out, void const *lwe_array_in, void const *scalar_blocks,
+    int8_t *mem_ptr, void *const *bsks, void *const *ksks,
+    uint32_t lwe_ciphertext_count, uint32_t num_scalar_blocks);
+
+void cleanup_cuda_integer_comparison(void *const *streams,
+                                     uint32_t const *gpu_indexes,
+                                     uint32_t gpu_count, int8_t **mem_ptr_void);
+
+void scratch_cuda_integer_radix_bitop_kb_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    int8_t **mem_ptr, uint32_t glwe_dimension, uint32_t polynomial_size,
+    uint32_t big_lwe_dimension, uint32_t small_lwe_dimension, uint32_t ks_level,
+    uint32_t ks_base_log, uint32_t pbs_level, uint32_t pbs_base_log,
+    uint32_t grouping_factor, uint32_t lwe_ciphertext_count,
+    uint32_t message_modulus, uint32_t carry_modulus, PBS_TYPE pbs_type,
+    BITOP_TYPE op_type, bool allocate_gpu_memory);
+
+void cuda_bitop_integer_radix_ciphertext_kb_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    void *lwe_array_out, void const *lwe_array_1, void const *lwe_array_2,
+    int8_t *mem_ptr, void *const *bsks, void *const *ksks,
+    uint32_t lwe_ciphertext_count);
+
+void cuda_scalar_bitop_integer_radix_ciphertext_kb_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    void *lwe_array_out, void const *lwe_array_input, void const *clear_blocks,
+    uint32_t num_clear_blocks, int8_t *mem_ptr, void *const *bsks,
+    void *const *ksks, uint32_t lwe_ciphertext_count, BITOP_TYPE op);
+
+void cleanup_cuda_integer_bitop(void *const *streams,
+                                uint32_t const *gpu_indexes, uint32_t gpu_count,
+                                int8_t **mem_ptr_void);
+
+void scratch_cuda_integer_radix_cmux_kb_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    int8_t **mem_ptr, uint32_t glwe_dimension, uint32_t polynomial_size,
+    uint32_t big_lwe_dimension, uint32_t small_lwe_dimension, uint32_t ks_level,
+    uint32_t ks_base_log, uint32_t pbs_level, uint32_t pbs_base_log,
+    uint32_t grouping_factor, uint32_t lwe_ciphertext_count,
+    uint32_t message_modulus, uint32_t carry_modulus, PBS_TYPE pbs_type,
+    bool allocate_gpu_memory);
+
+void cuda_cmux_integer_radix_ciphertext_kb_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    void *lwe_array_out, void const *lwe_condition, void const *lwe_array_true,
+    void const *lwe_array_false, int8_t *mem_ptr, void *const *bsks,
+    void *const *ksks, uint32_t lwe_ciphertext_count);
+
+void cleanup_cuda_integer_radix_cmux(void *const *streams,
+                                     uint32_t const *gpu_indexes,
+                                     uint32_t gpu_count, int8_t **mem_ptr_void);
+
+void scratch_cuda_integer_radix_scalar_rotate_kb_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    int8_t **mem_ptr, uint32_t glwe_dimension, uint32_t polynomial_size,
+    uint32_t big_lwe_dimension, uint32_t small_lwe_dimension, uint32_t ks_level,
+    uint32_t ks_base_log, uint32_t pbs_level, uint32_t pbs_base_log,
+    uint32_t grouping_factor, uint32_t num_blocks, uint32_t message_modulus,
+    uint32_t carry_modulus, PBS_TYPE pbs_type, SHIFT_OR_ROTATE_TYPE shift_type,
+    bool allocate_gpu_memory);
+
+void cuda_integer_radix_scalar_rotate_kb_64_inplace(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    void *lwe_array, uint32_t n, int8_t *mem_ptr, void *const *bsks,
+    void *const *ksks, uint32_t num_blocks);
+
+void cleanup_cuda_integer_radix_scalar_rotate(void *const *streams,
+                                              uint32_t const *gpu_indexes,
+                                              uint32_t gpu_count,
+                                              int8_t **mem_ptr_void);
+
+void scratch_cuda_propagate_single_carry_kb_64_inplace(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    int8_t **mem_ptr, uint32_t glwe_dimension, uint32_t polynomial_size,
+    uint32_t big_lwe_dimension, uint32_t small_lwe_dimension, uint32_t ks_level,
+    uint32_t ks_base_log, uint32_t pbs_level, uint32_t pbs_base_log,
+    uint32_t grouping_factor, uint32_t num_blocks, uint32_t message_modulus,
+    uint32_t carry_modulus, PBS_TYPE pbs_type, uint32_t requested_flag,
+    uint32_t uses_carry, bool allocate_gpu_memory);
+
+void scratch_cuda_add_and_propagate_single_carry_kb_64_inplace(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    int8_t **mem_ptr, uint32_t glwe_dimension, uint32_t polynomial_size,
+    uint32_t big_lwe_dimension, uint32_t small_lwe_dimension, uint32_t ks_level,
+    uint32_t ks_base_log, uint32_t pbs_level, uint32_t pbs_base_log,
+    uint32_t grouping_factor, uint32_t num_blocks, uint32_t message_modulus,
+    uint32_t carry_modulus, PBS_TYPE pbs_type, uint32_t requested_flag,
+    uint32_t uses_carry, bool allocate_gpu_memory);
+
+void cuda_propagate_single_carry_kb_64_inplace(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    void *lwe_array, void *carry_out, const void *carry_in, int8_t *mem_ptr,
+    void *const *bsks, void *const *ksks, uint32_t num_blocks,
+    uint32_t requested_flag, uint32_t uses_carry);
+
+void cuda_add_and_propagate_single_carry_kb_64_inplace(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    void *lhs_array, const void *rhs_array, void *carry_out,
+    const void *carry_in, int8_t *mem_ptr, void *const *bsks, void *const *ksks,
+    uint32_t num_blocks, uint32_t requested_flag, uint32_t uses_carry);
+
+void cleanup_cuda_propagate_single_carry(void *const *streams,
+                                         uint32_t const *gpu_indexes,
+                                         uint32_t gpu_count,
+                                         int8_t **mem_ptr_void);
+
+void cleanup_cuda_add_and_propagate_single_carry(void *const *streams,
+                                                 uint32_t const *gpu_indexes,
+                                                 uint32_t gpu_count,
+                                                 int8_t **mem_ptr_void);
+
+void scratch_cuda_integer_overflowing_sub_kb_64_inplace(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    int8_t **mem_ptr, uint32_t glwe_dimension, uint32_t polynomial_size,
+    uint32_t big_lwe_dimension, uint32_t small_lwe_dimension, uint32_t ks_level,
+    uint32_t ks_base_log, uint32_t pbs_level, uint32_t pbs_base_log,
+    uint32_t grouping_factor, uint32_t num_blocks, uint32_t message_modulus,
+    uint32_t carry_modulus, PBS_TYPE pbs_type, uint32_t compute_overflow,
+    bool allocate_gpu_memory);
+
+void cuda_integer_overflowing_sub_kb_64_inplace(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    void *lhs_array, const void *rhs_array, void *overflow_block,
+    const void *input_borrow, int8_t *mem_ptr, void *const *bsks,
+    void *const *ksks, uint32_t num_blocks, uint32_t compute_overflow,
+    uint32_t uses_input_borrow);
+
+void cleanup_cuda_integer_overflowing_sub(void *const *streams,
+                                          uint32_t const *gpu_indexes,
+                                          uint32_t gpu_count,
+                                          int8_t **mem_ptr_void);
+
+void scratch_cuda_integer_radix_partial_sum_ciphertexts_vec_kb_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    int8_t **mem_ptr, uint32_t glwe_dimension, uint32_t polynomial_size,
+    uint32_t lwe_dimension, uint32_t ks_level, uint32_t ks_base_log,
+    uint32_t pbs_level, uint32_t pbs_base_log, uint32_t grouping_factor,
+    uint32_t num_blocks_in_radix, uint32_t max_num_radix_in_vec,
+    uint32_t message_modulus, uint32_t carry_modulus, PBS_TYPE pbs_type,
+    bool allocate_gpu_memory);
+
+void cuda_integer_radix_partial_sum_ciphertexts_vec_kb_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    void *radix_lwe_out, void *radix_lwe_vec, uint32_t num_radix_in_vec,
+    int8_t *mem_ptr, void *const *bsks, void *const *ksks,
+    uint32_t num_blocks_in_radix);
+
+void cleanup_cuda_integer_radix_partial_sum_ciphertexts_vec(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    int8_t **mem_ptr_void);
+
+void scratch_cuda_integer_scalar_mul_kb_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    int8_t **mem_ptr, uint32_t glwe_dimension, uint32_t polynomial_size,
+    uint32_t lwe_dimension, uint32_t ks_level, uint32_t ks_base_log,
+    uint32_t pbs_level, uint32_t pbs_base_log, uint32_t grouping_factor,
+    uint32_t num_blocks, uint32_t message_modulus, uint32_t carry_modulus,
+    PBS_TYPE pbs_type, bool allocate_gpu_memory);
+
+void cuda_scalar_multiplication_integer_radix_ciphertext_64_inplace(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    void *lwe_array, uint64_t const *decomposed_scalar,
+    uint64_t const *has_at_least_one_set, int8_t *mem_ptr, void *const *bsks,
+    void *const *ksks, uint32_t lwe_dimension, uint32_t polynomial_size,
+    uint32_t message_modulus, uint32_t num_blocks, uint32_t num_scalars);
+
+void cleanup_cuda_integer_radix_scalar_mul(void *const *streams,
+                                           uint32_t const *gpu_indexes,
+                                           uint32_t gpu_count,
+                                           int8_t **mem_ptr_void);
+
+void scratch_cuda_integer_div_rem_radix_ciphertext_kb_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    bool is_signed, int8_t **mem_ptr, uint32_t glwe_dimension,
+    uint32_t polynomial_size, uint32_t big_lwe_dimension,
+    uint32_t small_lwe_dimension, uint32_t ks_level, uint32_t ks_base_log,
+    uint32_t pbs_level, uint32_t pbs_base_log, uint32_t grouping_factor,
+    uint32_t num_blocks, uint32_t message_modulus, uint32_t carry_modulus,
+    PBS_TYPE pbs_type, bool allocate_gpu_memory);
+
+void cuda_integer_div_rem_radix_ciphertext_kb_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    void *quotient, void *remainder, void const *numerator, void const *divisor,
+    bool is_signed, int8_t *mem_ptr, void *const *bsks, void *const *ksks,
+    uint32_t num_blocks_in_radix);
+
+void cleanup_cuda_integer_div_rem(void *const *streams,
+                                  uint32_t const *gpu_indexes,
+                                  uint32_t gpu_count, int8_t **mem_ptr_void);
+
+void scratch_cuda_integer_compute_prefix_sum_hillis_steele_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    int8_t **mem_ptr, void const *input_lut, uint32_t lwe_dimension,
+    uint32_t glwe_dimension, uint32_t polynomial_size, uint32_t ks_level,
+    uint32_t ks_base_log, uint32_t pbs_level, uint32_t pbs_base_log,
+    uint32_t grouping_factor, uint32_t num_radix_blocks,
+    uint32_t message_modulus, uint32_t carry_modulus, PBS_TYPE pbs_type,
+    bool allocate_gpu_memory);
+
+void cuda_integer_compute_prefix_sum_hillis_steele_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    void *output_radix_lwe, void *generates_or_propagates, int8_t *mem_ptr,
+    void *const *ksks, void *const *bsks, uint32_t num_blocks, uint32_t shift);
+
+void cleanup_cuda_integer_compute_prefix_sum_hillis_steele_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    int8_t **mem_ptr_void);
+
+void cuda_integer_reverse_blocks_64_inplace(void *const *streams,
+                                            uint32_t const *gpu_indexes,
+                                            uint32_t gpu_count, void *lwe_array,
+                                            uint32_t num_blocks,
+                                            uint32_t lwe_size);
+
+void scratch_cuda_integer_abs_inplace_radix_ciphertext_kb_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    int8_t **mem_ptr, bool is_signed, uint32_t glwe_dimension,
+    uint32_t polynomial_size, uint32_t big_lwe_dimension,
+    uint32_t small_lwe_dimension, uint32_t ks_level, uint32_t ks_base_log,
+    uint32_t pbs_level, uint32_t pbs_base_log, uint32_t grouping_factor,
+    uint32_t num_blocks, uint32_t message_modulus, uint32_t carry_modulus,
+    PBS_TYPE pbs_type, bool allocate_gpu_memory);
+
+void cuda_integer_abs_inplace_radix_ciphertext_kb_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    void *ct, int8_t *mem_ptr, bool is_signed, void *const *bsks,
+    void *const *ksks, uint32_t num_blocks);
+
+void cleanup_cuda_integer_abs_inplace(void *const *streams,
+                                      uint32_t const *gpu_indexes,
+                                      uint32_t gpu_count,
+                                      int8_t **mem_ptr_void);
+
+} // extern C
+#endif // CUDA_INTEGER_H

backends/tfhe-cuda-backend/cuda/include/keyswitch.h

@@ -1,21 +1,23 @@
 #ifndef CNCRT_KS_H_
 #define CNCRT_KS_H_
 
-#include <cstdint>
+#include <stdint.h>
 
 extern "C" {
 
 void cuda_keyswitch_lwe_ciphertext_vector_32(
     void *stream, uint32_t gpu_index, void *lwe_array_out,
-    void *lwe_output_indexes, void *lwe_array_in, void *lwe_input_indexes,
-    void *ksk, uint32_t lwe_dimension_in, uint32_t lwe_dimension_out,
-    uint32_t base_log, uint32_t level_count, uint32_t num_samples);
+    void const *lwe_output_indexes, void const *lwe_array_in,
+    void const *lwe_input_indexes, void const *ksk, uint32_t lwe_dimension_in,
+    uint32_t lwe_dimension_out, uint32_t base_log, uint32_t level_count,
+    uint32_t num_samples);
 
 void cuda_keyswitch_lwe_ciphertext_vector_64(
     void *stream, uint32_t gpu_index, void *lwe_array_out,
-    void *lwe_output_indexes, void *lwe_array_in, void *lwe_input_indexes,
-    void *ksk, uint32_t lwe_dimension_in, uint32_t lwe_dimension_out,
-    uint32_t base_log, uint32_t level_count, uint32_t num_samples);
+    void const *lwe_output_indexes, void const *lwe_array_in,
+    void const *lwe_input_indexes, void const *ksk, uint32_t lwe_dimension_in,
+    uint32_t lwe_dimension_out, uint32_t base_log, uint32_t level_count,
+    uint32_t num_samples);
 
 void scratch_packing_keyswitch_lwe_list_to_glwe_64(
     void *stream, uint32_t gpu_index, int8_t **fp_ks_buffer,
@@ -23,10 +25,11 @@ void scratch_packing_keyswitch_lwe_list_to_glwe_64(
     bool allocate_gpu_memory);
 
 void cuda_packing_keyswitch_lwe_list_to_glwe_64(
-    void *stream, uint32_t gpu_index, void *glwe_array_out, void *lwe_array_in,
-    void *fp_ksk_array, int8_t *fp_ks_buffer, uint32_t input_lwe_dimension,
-    uint32_t output_glwe_dimension, uint32_t output_polynomial_size,
-    uint32_t base_log, uint32_t level_count, uint32_t num_lwes);
+    void *stream, uint32_t gpu_index, void *glwe_array_out,
+    void const *lwe_array_in, void const *fp_ksk_array, int8_t *fp_ks_buffer,
+    uint32_t input_lwe_dimension, uint32_t output_glwe_dimension,
+    uint32_t output_polynomial_size, uint32_t base_log, uint32_t level_count,
+    uint32_t num_lwes);
 
 void cleanup_packing_keyswitch_lwe_list_to_glwe(void *stream,
                                                 uint32_t gpu_index,

backends/tfhe-cuda-backend/cuda/include/linear_algebra.h

@@ -1,50 +1,49 @@
 #ifndef CUDA_LINALG_H_
 #define CUDA_LINALG_H_
 
-#include "programmable_bootstrap.h"
-#include <cstdint>
-#include <device.h>
+#include <stdint.h>
 
 extern "C" {
 
 void cuda_negate_lwe_ciphertext_vector_32(void *stream, uint32_t gpu_index,
                                           void *lwe_array_out,
-                                          void *lwe_array_in,
+                                          void const *lwe_array_in,
                                           uint32_t input_lwe_dimension,
                                           uint32_t input_lwe_ciphertext_count);
 void cuda_negate_lwe_ciphertext_vector_64(void *stream, uint32_t gpu_index,
                                           void *lwe_array_out,
-                                          void *lwe_array_in,
+                                          void const *lwe_array_in,
                                           uint32_t input_lwe_dimension,
                                           uint32_t input_lwe_ciphertext_count);
 void cuda_add_lwe_ciphertext_vector_32(void *stream, uint32_t gpu_index,
                                        void *lwe_array_out,
-                                       void *lwe_array_in_1,
-                                       void *lwe_array_in_2,
+                                       void const *lwe_array_in_1,
+                                       void const *lwe_array_in_2,
                                        uint32_t input_lwe_dimension,
                                        uint32_t input_lwe_ciphertext_count);
 void cuda_add_lwe_ciphertext_vector_64(void *stream, uint32_t gpu_index,
                                        void *lwe_array_out,
-                                       void *lwe_array_in_1,
-                                       void *lwe_array_in_2,
+                                       void const *lwe_array_in_1,
+                                       void const *lwe_array_in_2,
                                        uint32_t input_lwe_dimension,
                                        uint32_t input_lwe_ciphertext_count);
+
 void cuda_add_lwe_ciphertext_vector_plaintext_vector_32(
-    void *stream, uint32_t gpu_index, void *lwe_array_out, void *lwe_array_in,
-    void *plaintext_array_in, uint32_t input_lwe_dimension,
-    uint32_t input_lwe_ciphertext_count);
+    void *stream, uint32_t gpu_index, void *lwe_array_out,
+    void const *lwe_array_in, void const *plaintext_array_in,
+    uint32_t input_lwe_dimension, uint32_t input_lwe_ciphertext_count);
 void cuda_add_lwe_ciphertext_vector_plaintext_vector_64(
-    void *stream, uint32_t gpu_index, void *lwe_array_out, void *lwe_array_in,
-    void *plaintext_array_in, uint32_t input_lwe_dimension,
-    uint32_t input_lwe_ciphertext_count);
+    void *stream, uint32_t gpu_index, void *lwe_array_out,
+    void const *lwe_array_in, void const *plaintext_array_in,
+    uint32_t input_lwe_dimension, uint32_t input_lwe_ciphertext_count);
 void cuda_mult_lwe_ciphertext_vector_cleartext_vector_32(
-    void *stream, uint32_t gpu_index, void *lwe_array_out, void *lwe_array_in,
-    void *cleartext_array_in, uint32_t input_lwe_dimension,
-    uint32_t input_lwe_ciphertext_count);
+    void *stream, uint32_t gpu_index, void *lwe_array_out,
+    void const *lwe_array_in, void const *cleartext_array_in,
+    uint32_t input_lwe_dimension, uint32_t input_lwe_ciphertext_count);
 void cuda_mult_lwe_ciphertext_vector_cleartext_vector_64(
-    void *stream, uint32_t gpu_index, void *lwe_array_out, void *lwe_array_in,
-    void *cleartext_array_in, uint32_t input_lwe_dimension,
-    uint32_t input_lwe_ciphertext_count);
+    void *stream, uint32_t gpu_index, void *lwe_array_out,
+    void const *lwe_array_in, void const *cleartext_array_in,
+    uint32_t input_lwe_dimension, uint32_t input_lwe_ciphertext_count);
 }
 
 #endif // CUDA_LINALG_H_

backends/tfhe-cuda-backend/cuda/include/pbs/pbs_enums.h

@@ -0,0 +1,7 @@
+#ifndef CUDA_PBS_ENUMS_H
+#define CUDA_PBS_ENUMS_H
+
+enum PBS_TYPE { MULTI_BIT = 0, CLASSICAL = 1 };
+enum PBS_VARIANT { DEFAULT = 0, CG = 1, TBC = 2 };
+
+#endif // CUDA_PBS_ENUMS_H

backends/tfhe-cuda-backend/cuda/include/pbs/pbs_multibit_utilities.h

@@ -1,38 +1,7 @@
-#ifndef CUDA_MULTI_BIT_H
-#define CUDA_MULTI_BIT_H
+#ifndef CUDA_MULTI_BIT_UTILITIES_H
+#define CUDA_MULTI_BIT_UTILITIES_H
 
-#include "programmable_bootstrap.h"
-#include <cstdint>
-
-extern "C" {
-
-bool has_support_to_cuda_programmable_bootstrap_cg_multi_bit(
-    uint32_t glwe_dimension, uint32_t polynomial_size, uint32_t level_count,
-    uint32_t num_samples);
-
-void cuda_convert_lwe_multi_bit_programmable_bootstrap_key_64(
-    void *stream, uint32_t gpu_index, void *dest, void *src,
-    uint32_t input_lwe_dim, uint32_t glwe_dim, uint32_t level_count,
-    uint32_t polynomial_size, uint32_t grouping_factor);
-
-void scratch_cuda_multi_bit_programmable_bootstrap_64(
-    void *stream, uint32_t gpu_index, int8_t **pbs_buffer,
-    uint32_t glwe_dimension, uint32_t polynomial_size, uint32_t level_count,
-    uint32_t input_lwe_ciphertext_count, bool allocate_gpu_memory);
-
-void cuda_multi_bit_programmable_bootstrap_lwe_ciphertext_vector_64(
-    void *stream, uint32_t gpu_index, void *lwe_array_out,
-    void *lwe_output_indexes, void *lut_vector, void *lut_vector_indexes,
-    void *lwe_array_in, void *lwe_input_indexes, void *bootstrapping_key,
-    int8_t *buffer, uint32_t lwe_dimension, uint32_t glwe_dimension,
-    uint32_t polynomial_size, uint32_t grouping_factor, uint32_t base_log,
-    uint32_t level_count, uint32_t num_samples, uint32_t lut_count,
-    uint32_t lut_stride);
-
-void cleanup_cuda_multi_bit_programmable_bootstrap(void *stream,
-                                                   uint32_t gpu_index,
-                                                   int8_t **pbs_buffer);
-}
+#include "pbs_utilities.h"
 
 template <typename Torus>
 bool supports_distributed_shared_memory_on_multibit_programmable_bootstrap(
@@ -53,12 +22,13 @@ void scratch_cuda_tbc_multi_bit_programmable_bootstrap(
 template <typename Torus>
 void cuda_tbc_multi_bit_programmable_bootstrap_lwe_ciphertext_vector(
     void *stream, uint32_t gpu_index, Torus *lwe_array_out,
-    Torus *lwe_output_indexes, Torus *lut_vector, Torus *lut_vector_indexes,
-    Torus *lwe_array_in, Torus *lwe_input_indexes, Torus *bootstrapping_key,
+    Torus const *lwe_output_indexes, Torus const *lut_vector,
+    Torus const *lut_vector_indexes, Torus const *lwe_array_in,
+    Torus const *lwe_input_indexes, Torus const *bootstrapping_key,
     pbs_buffer<Torus, MULTI_BIT> *pbs_buffer, uint32_t lwe_dimension,
     uint32_t glwe_dimension, uint32_t polynomial_size, uint32_t grouping_factor,
     uint32_t base_log, uint32_t level_count, uint32_t num_samples,
-    uint32_t lut_count, uint32_t lut_stride);
+    uint32_t num_many_lut, uint32_t lut_stride);
 #endif
 
 template <typename Torus>
@@ -70,12 +40,13 @@ void scratch_cuda_cg_multi_bit_programmable_bootstrap(
 template <typename Torus>
 void cuda_cg_multi_bit_programmable_bootstrap_lwe_ciphertext_vector(
     void *stream, uint32_t gpu_index, Torus *lwe_array_out,
-    Torus *lwe_output_indexes, Torus *lut_vector, Torus *lut_vector_indexes,
-    Torus *lwe_array_in, Torus *lwe_input_indexes, Torus *bootstrapping_key,
+    Torus const *lwe_output_indexes, Torus const *lut_vector,
+    Torus const *lut_vector_indexes, Torus const *lwe_array_in,
+    Torus const *lwe_input_indexes, Torus const *bootstrapping_key,
     pbs_buffer<Torus, MULTI_BIT> *pbs_buffer, uint32_t lwe_dimension,
     uint32_t glwe_dimension, uint32_t polynomial_size, uint32_t grouping_factor,
     uint32_t base_log, uint32_t level_count, uint32_t num_samples,
-    uint32_t lut_count, uint32_t lut_stride);
+    uint32_t num_many_lut, uint32_t lut_stride);
 
 template <typename Torus>
 void scratch_cuda_multi_bit_programmable_bootstrap(
@@ -86,12 +57,13 @@ void scratch_cuda_multi_bit_programmable_bootstrap(
 template <typename Torus>
 void cuda_multi_bit_programmable_bootstrap_lwe_ciphertext_vector(
     void *stream, uint32_t gpu_index, Torus *lwe_array_out,
-    Torus *lwe_output_indexes, Torus *lut_vector, Torus *lut_vector_indexes,
-    Torus *lwe_array_in, Torus *lwe_input_indexes, Torus *bootstrapping_key,
+    Torus const *lwe_output_indexes, Torus const *lut_vector,
+    Torus const *lut_vector_indexes, Torus const *lwe_array_in,
+    Torus const *lwe_input_indexes, Torus const *bootstrapping_key,
     pbs_buffer<Torus, MULTI_BIT> *pbs_buffer, uint32_t lwe_dimension,
     uint32_t glwe_dimension, uint32_t polynomial_size, uint32_t grouping_factor,
     uint32_t base_log, uint32_t level_count, uint32_t num_samples,
-    uint32_t lut_count, uint32_t lut_stride);
+    uint32_t num_many_lut, uint32_t lut_stride);
 
 template <typename Torus>
 uint64_t get_buffer_size_full_sm_multibit_programmable_bootstrap_keybundle(
@@ -121,6 +93,10 @@ template <typename Torus>
 uint64_t get_buffer_size_full_sm_tbc_multibit_programmable_bootstrap(
     uint32_t polynomial_size);
 
+template <typename Torus, class params>
+uint32_t get_lwe_chunk_size(uint32_t gpu_index, uint32_t max_num_pbs,
+                            uint32_t polynomial_size);
+
 template <typename Torus> struct pbs_buffer<Torus, PBS_TYPE::MULTI_BIT> {
   int8_t *d_mem_keybundle = NULL;
   int8_t *d_mem_acc_step_one = NULL;
@@ -130,7 +106,7 @@ template <typename Torus> struct pbs_buffer<Torus, PBS_TYPE::MULTI_BIT> {
   uint32_t lwe_chunk_size;
   double2 *keybundle_fft;
   Torus *global_accumulator;
-  double2 *global_accumulator_fft;
+  double2 *global_join_buffer;
 
   PBS_VARIANT pbs_variant;
 
@@ -249,10 +225,12 @@ template <typename Torus> struct pbs_buffer<Torus, PBS_TYPE::MULTI_BIT> {
           num_blocks_keybundle * (polynomial_size / 2) * sizeof(double2),
           stream, gpu_index);
       global_accumulator = (Torus *)cuda_malloc_async(
-          num_blocks_acc_step_one * polynomial_size * sizeof(Torus), stream,
-          gpu_index);
-      global_accumulator_fft = (double2 *)cuda_malloc_async(
-          num_blocks_acc_step_one * (polynomial_size / 2) * sizeof(double2),
+          input_lwe_ciphertext_count * (glwe_dimension + 1) * polynomial_size *
+              sizeof(Torus),
+          stream, gpu_index);
+      global_join_buffer = (double2 *)cuda_malloc_async(
+          level_count * (glwe_dimension + 1) * input_lwe_ciphertext_count *
+              (polynomial_size / 2) * sizeof(double2),
           stream, gpu_index);
     }
   }
@@ -284,12 +262,8 @@ template <typename Torus> struct pbs_buffer<Torus, PBS_TYPE::MULTI_BIT> {
 
     cuda_drop_async(keybundle_fft, stream, gpu_index);
     cuda_drop_async(global_accumulator, stream, gpu_index);
-    cuda_drop_async(global_accumulator_fft, stream, gpu_index);
+    cuda_drop_async(global_join_buffer, stream, gpu_index);
   }
 };
 
-template <typename Torus, class params>
-uint32_t get_lwe_chunk_size(uint32_t gpu_index, uint32_t max_num_pbs,
-                            uint32_t polynomial_size);
-
-#endif // CUDA_MULTI_BIT_H
+#endif // CUDA_MULTI_BIT_UTILITIES_H

backends/tfhe-cuda-backend/cuda/include/pbs/pbs_utilities.h

@@ -1,87 +1,10 @@
-#ifndef CUDA_BOOTSTRAP_H
-#define CUDA_BOOTSTRAP_H
+#ifndef CUDA_BOOTSTRAP_UTILITIES_H
+#define CUDA_BOOTSTRAP_UTILITIES_H
 
 #include "device.h"
-#include <cstdint>
-
-enum PBS_TYPE { MULTI_BIT = 0, CLASSICAL = 1 };
-enum PBS_VARIANT { DEFAULT = 0, CG = 1, TBC = 2 };
-
-extern "C" {
-void cuda_fourier_polynomial_mul(cudaStream_t stream, uint32_t gpu_index,
-                                 void *input1, void *input2, void *output,
-                                 uint32_t polynomial_size,
-                                 uint32_t total_polynomials);
-
-void cuda_convert_lwe_programmable_bootstrap_key_32(
-    void *stream, uint32_t gpu_index, void *dest, void *src,
-    uint32_t input_lwe_dim, uint32_t glwe_dim, uint32_t level_count,
-    uint32_t polynomial_size);
-
-void cuda_convert_lwe_programmable_bootstrap_key_64(
-    void *stream, uint32_t gpu_index, void *dest, void *src,
-    uint32_t input_lwe_dim, uint32_t glwe_dim, uint32_t level_count,
-    uint32_t polynomial_size);
-
-void scratch_cuda_programmable_bootstrap_amortized_32(
-    void *stream, uint32_t gpu_index, int8_t **pbs_buffer,
-    uint32_t glwe_dimension, uint32_t polynomial_size,
-    uint32_t input_lwe_ciphertext_count, bool allocate_gpu_memory);
-
-void scratch_cuda_programmable_bootstrap_amortized_64(
-    void *stream, uint32_t gpu_index, int8_t **pbs_buffer,
-    uint32_t glwe_dimension, uint32_t polynomial_size,
-    uint32_t input_lwe_ciphertext_count, bool allocate_gpu_memory);
-
-void cuda_programmable_bootstrap_amortized_lwe_ciphertext_vector_32(
-    void *stream, uint32_t gpu_index, void *lwe_array_out,
-    void *lwe_output_indexes, void *lut_vector, void *lut_vector_indexes,
-    void *lwe_array_in, void *lwe_input_indexes, void *bootstrapping_key,
-    int8_t *pbs_buffer, uint32_t lwe_dimension, uint32_t glwe_dimension,
-    uint32_t polynomial_size, uint32_t base_log, uint32_t level_count,
-    uint32_t num_samples);
-
-void cuda_programmable_bootstrap_amortized_lwe_ciphertext_vector_64(
-    void *stream, uint32_t gpu_index, void *lwe_array_out,
-    void *lwe_output_indexes, void *lut_vector, void *lut_vector_indexes,
-    void *lwe_array_in, void *lwe_input_indexes, void *bootstrapping_key,
-    int8_t *pbs_buffer, uint32_t lwe_dimension, uint32_t glwe_dimension,
-    uint32_t polynomial_size, uint32_t base_log, uint32_t level_count,
-    uint32_t num_samples);
-
-void cleanup_cuda_programmable_bootstrap_amortized(void *stream,
-                                                   uint32_t gpu_index,
-                                                   int8_t **pbs_buffer);
-
-void scratch_cuda_programmable_bootstrap_32(
-    void *stream, uint32_t gpu_index, int8_t **buffer, uint32_t glwe_dimension,
-    uint32_t polynomial_size, uint32_t level_count,
-    uint32_t input_lwe_ciphertext_count, bool allocate_gpu_memory);
-
-void scratch_cuda_programmable_bootstrap_64(
-    void *stream, uint32_t gpu_index, int8_t **buffer, uint32_t glwe_dimension,
-    uint32_t polynomial_size, uint32_t level_count,
-    uint32_t input_lwe_ciphertext_count, bool allocate_gpu_memory);
-
-void cuda_programmable_bootstrap_lwe_ciphertext_vector_32(
-    void *stream, uint32_t gpu_index, void *lwe_array_out,
-    void *lwe_output_indexes, void *lut_vector, void *lut_vector_indexes,
-    void *lwe_array_in, void *lwe_input_indexes, void *bootstrapping_key,
-    int8_t *buffer, uint32_t lwe_dimension, uint32_t glwe_dimension,
-    uint32_t polynomial_size, uint32_t base_log, uint32_t level_count,
-    uint32_t num_samples, uint32_t lut_count, uint32_t lut_stride);
-
-void cuda_programmable_bootstrap_lwe_ciphertext_vector_64(
-    void *stream, uint32_t gpu_index, void *lwe_array_out,
-    void *lwe_output_indexes, void *lut_vector, void *lut_vector_indexes,
-    void *lwe_array_in, void *lwe_input_indexes, void *bootstrapping_key,
-    int8_t *buffer, uint32_t lwe_dimension, uint32_t glwe_dimension,
-    uint32_t polynomial_size, uint32_t base_log, uint32_t level_count,
-    uint32_t num_samples, uint32_t lut_count, uint32_t lut_stride);
-
-void cleanup_cuda_programmable_bootstrap(void *stream, uint32_t gpu_index,
-                                         int8_t **pbs_buffer);
-}
+#include "pbs_enums.h"
+#include "vector_types.h"
+#include <stdint.h>
 
 template <typename Torus>
 uint64_t get_buffer_size_full_sm_programmable_bootstrap_step_one(
@@ -146,7 +69,7 @@ template <typename Torus> struct pbs_buffer<Torus, PBS_TYPE::CLASSICAL> {
   int8_t *d_mem;
 
   Torus *global_accumulator;
-  double2 *global_accumulator_fft;
+  double2 *global_join_buffer;
 
   PBS_VARIANT pbs_variant;
 
@@ -191,7 +114,7 @@ template <typename Torus> struct pbs_buffer<Torus, PBS_TYPE::CLASSICAL> {
         // Otherwise, both kernels run all in shared memory
         d_mem = (int8_t *)cuda_malloc_async(device_mem, stream, gpu_index);
 
-        global_accumulator_fft = (double2 *)cuda_malloc_async(
+        global_join_buffer = (double2 *)cuda_malloc_async(
             (glwe_dimension + 1) * level_count * input_lwe_ciphertext_count *
                 (polynomial_size / 2) * sizeof(double2),
             stream, gpu_index);
@@ -224,7 +147,7 @@ template <typename Torus> struct pbs_buffer<Torus, PBS_TYPE::CLASSICAL> {
         // Otherwise, both kernels run all in shared memory
         d_mem = (int8_t *)cuda_malloc_async(device_mem, stream, gpu_index);
 
-        global_accumulator_fft = (double2 *)cuda_malloc_async(
+        global_join_buffer = (double2 *)cuda_malloc_async(
             (glwe_dimension + 1) * level_count * input_lwe_ciphertext_count *
                 polynomial_size / 2 * sizeof(double2),
             stream, gpu_index);
@@ -271,7 +194,7 @@ template <typename Torus> struct pbs_buffer<Torus, PBS_TYPE::CLASSICAL> {
         // Otherwise, both kernels run all in shared memory
         d_mem = (int8_t *)cuda_malloc_async(device_mem, stream, gpu_index);
 
-        global_accumulator_fft = (double2 *)cuda_malloc_async(
+        global_join_buffer = (double2 *)cuda_malloc_async(
             (glwe_dimension + 1) * level_count * input_lwe_ciphertext_count *
                 polynomial_size / 2 * sizeof(double2),
             stream, gpu_index);
@@ -285,7 +208,7 @@ template <typename Torus> struct pbs_buffer<Torus, PBS_TYPE::CLASSICAL> {
 
   void release(cudaStream_t stream, uint32_t gpu_index) {
     cuda_drop_async(d_mem, stream, gpu_index);
-    cuda_drop_async(global_accumulator_fft, stream, gpu_index);
+    cuda_drop_async(global_join_buffer, stream, gpu_index);
 
     if (pbs_variant == DEFAULT)
       cuda_drop_async(global_accumulator, stream, gpu_index);
@@ -327,32 +250,35 @@ bool has_support_to_cuda_programmable_bootstrap_cg(uint32_t glwe_dimension,
 template <typename Torus>
 void cuda_programmable_bootstrap_cg_lwe_ciphertext_vector(
     void *stream, uint32_t gpu_index, Torus *lwe_array_out,
-    Torus *lwe_output_indexes, Torus *lut_vector, Torus *lut_vector_indexes,
-    Torus *lwe_array_in, Torus *lwe_input_indexes, double2 *bootstrapping_key,
+    Torus const *lwe_output_indexes, Torus const *lut_vector,
+    Torus const *lut_vector_indexes, Torus const *lwe_array_in,
+    Torus const *lwe_input_indexes, double2 const *bootstrapping_key,
     pbs_buffer<Torus, CLASSICAL> *buffer, uint32_t lwe_dimension,
     uint32_t glwe_dimension, uint32_t polynomial_size, uint32_t base_log,
-    uint32_t level_count, uint32_t num_samples, uint32_t lut_count,
+    uint32_t level_count, uint32_t num_samples, uint32_t num_many_lut,
     uint32_t lut_stride);
 
 template <typename Torus>
 void cuda_programmable_bootstrap_lwe_ciphertext_vector(
     void *stream, uint32_t gpu_index, Torus *lwe_array_out,
-    Torus *lwe_output_indexes, Torus *lut_vector, Torus *lut_vector_indexes,
-    Torus *lwe_array_in, Torus *lwe_input_indexes, double2 *bootstrapping_key,
+    Torus const *lwe_output_indexes, Torus const *lut_vector,
+    Torus const *lut_vector_indexes, Torus const *lwe_array_in,
+    Torus const *lwe_input_indexes, double2 const *bootstrapping_key,
     pbs_buffer<Torus, CLASSICAL> *buffer, uint32_t lwe_dimension,
     uint32_t glwe_dimension, uint32_t polynomial_size, uint32_t base_log,
-    uint32_t level_count, uint32_t num_samples, uint32_t lut_count,
+    uint32_t level_count, uint32_t num_samples, uint32_t num_many_lut,
     uint32_t lut_stride);
 
 #if (CUDA_ARCH >= 900)
 template <typename Torus>
 void cuda_programmable_bootstrap_tbc_lwe_ciphertext_vector(
     void *stream, uint32_t gpu_index, Torus *lwe_array_out,
-    Torus *lwe_output_indexes, Torus *lut_vector, Torus *lut_vector_indexes,
-    Torus *lwe_array_in, Torus *lwe_input_indexes, double2 *bootstrapping_key,
+    Torus const *lwe_output_indexes, Torus const *lut_vector,
+    Torus const *lut_vector_indexes, Torus const *lwe_array_in,
+    Torus const *lwe_input_indexes, double2 const *bootstrapping_key,
     pbs_buffer<Torus, CLASSICAL> *buffer, uint32_t lwe_dimension,
     uint32_t glwe_dimension, uint32_t polynomial_size, uint32_t base_log,
-    uint32_t level_count, uint32_t num_samples, uint32_t lut_count,
+    uint32_t level_count, uint32_t num_samples, uint32_t num_many_lut,
     uint32_t lut_stride);
 
 template <typename Torus>
@@ -408,4 +334,4 @@ __device__ const T *get_multi_bit_ith_lwe_gth_group_kth_block(
 
 #endif
 
-#endif // CUDA_BOOTSTRAP_H
+#endif // CUDA_BOOTSTRAP_UTILITIES_H

backends/tfhe-cuda-backend/cuda/include/pbs/programmable_bootstrap.h

@@ -0,0 +1,86 @@
+#ifndef CUDA_BOOTSTRAP_H
+#define CUDA_BOOTSTRAP_H
+
+#include "pbs_enums.h"
+#include <stdint.h>
+
+extern "C" {
+void cuda_fourier_polynomial_mul(void *stream, uint32_t gpu_index,
+                                 void const *input1, void const *input2,
+                                 void *output, uint32_t polynomial_size,
+                                 uint32_t total_polynomials);
+
+void cuda_convert_lwe_programmable_bootstrap_key_32(
+    void *stream, uint32_t gpu_index, void *dest, void const *src,
+    uint32_t input_lwe_dim, uint32_t glwe_dim, uint32_t level_count,
+    uint32_t polynomial_size);
+
+void cuda_convert_lwe_programmable_bootstrap_key_64(
+    void *stream, uint32_t gpu_index, void *dest, void const *src,
+    uint32_t input_lwe_dim, uint32_t glwe_dim, uint32_t level_count,
+    uint32_t polynomial_size);
+
+void scratch_cuda_programmable_bootstrap_amortized_32(
+    void *stream, uint32_t gpu_index, int8_t **pbs_buffer,
+    uint32_t glwe_dimension, uint32_t polynomial_size,
+    uint32_t input_lwe_ciphertext_count, bool allocate_gpu_memory);
+
+void scratch_cuda_programmable_bootstrap_amortized_64(
+    void *stream, uint32_t gpu_index, int8_t **pbs_buffer,
+    uint32_t glwe_dimension, uint32_t polynomial_size,
+    uint32_t input_lwe_ciphertext_count, bool allocate_gpu_memory);
+
+void cuda_programmable_bootstrap_amortized_lwe_ciphertext_vector_32(
+    void *stream, uint32_t gpu_index, void *lwe_array_out,
+    void const *lwe_output_indexes, void const *lut_vector,
+    void const *lut_vector_indexes, void const *lwe_array_in,
+    void const *lwe_input_indexes, void const *bootstrapping_key,
+    int8_t *pbs_buffer, uint32_t lwe_dimension, uint32_t glwe_dimension,
+    uint32_t polynomial_size, uint32_t base_log, uint32_t level_count,
+    uint32_t num_samples);
+
+void cuda_programmable_bootstrap_amortized_lwe_ciphertext_vector_64(
+    void *stream, uint32_t gpu_index, void *lwe_array_out,
+    void const *lwe_output_indexes, void const *lut_vector,
+    void const *lut_vector_indexes, void const *lwe_array_in,
+    void const *lwe_input_indexes, void const *bootstrapping_key,
+    int8_t *pbs_buffer, uint32_t lwe_dimension, uint32_t glwe_dimension,
+    uint32_t polynomial_size, uint32_t base_log, uint32_t level_count,
+    uint32_t num_samples);
+
+void cleanup_cuda_programmable_bootstrap_amortized(void *stream,
+                                                   uint32_t gpu_index,
+                                                   int8_t **pbs_buffer);
+
+void scratch_cuda_programmable_bootstrap_32(
+    void *stream, uint32_t gpu_index, int8_t **buffer, uint32_t glwe_dimension,
+    uint32_t polynomial_size, uint32_t level_count,
+    uint32_t input_lwe_ciphertext_count, bool allocate_gpu_memory);
+
+void scratch_cuda_programmable_bootstrap_64(
+    void *stream, uint32_t gpu_index, int8_t **buffer, uint32_t glwe_dimension,
+    uint32_t polynomial_size, uint32_t level_count,
+    uint32_t input_lwe_ciphertext_count, bool allocate_gpu_memory);
+
+void cuda_programmable_bootstrap_lwe_ciphertext_vector_32(
+    void *stream, uint32_t gpu_index, void *lwe_array_out,
+    void const *lwe_output_indexes, void const *lut_vector,
+    void const *lut_vector_indexes, void const *lwe_array_in,
+    void const *lwe_input_indexes, void const *bootstrapping_key,
+    int8_t *buffer, uint32_t lwe_dimension, uint32_t glwe_dimension,
+    uint32_t polynomial_size, uint32_t base_log, uint32_t level_count,
+    uint32_t num_samples, uint32_t num_many_lut, uint32_t lut_stride);
+
+void cuda_programmable_bootstrap_lwe_ciphertext_vector_64(
+    void *stream, uint32_t gpu_index, void *lwe_array_out,
+    void const *lwe_output_indexes, void const *lut_vector,
+    void const *lut_vector_indexes, void const *lwe_array_in,
+    void const *lwe_input_indexes, void const *bootstrapping_key,
+    int8_t *buffer, uint32_t lwe_dimension, uint32_t glwe_dimension,
+    uint32_t polynomial_size, uint32_t base_log, uint32_t level_count,
+    uint32_t num_samples, uint32_t num_many_lut, uint32_t lut_stride);
+
+void cleanup_cuda_programmable_bootstrap(void *stream, uint32_t gpu_index,
+                                         int8_t **pbs_buffer);
+}
+#endif // CUDA_BOOTSTRAP_H

backends/tfhe-cuda-backend/cuda/include/pbs/programmable_bootstrap_multibit.h

@@ -0,0 +1,38 @@
+#ifndef CUDA_MULTI_BIT_H
+#define CUDA_MULTI_BIT_H
+
+#include "pbs_enums.h"
+#include "stdint.h"
+
+extern "C" {
+
+bool has_support_to_cuda_programmable_bootstrap_cg_multi_bit(
+    uint32_t glwe_dimension, uint32_t polynomial_size, uint32_t level_count,
+    uint32_t num_samples);
+
+void cuda_convert_lwe_multi_bit_programmable_bootstrap_key_64(
+    void *stream, uint32_t gpu_index, void *dest, void const *src,
+    uint32_t input_lwe_dim, uint32_t glwe_dim, uint32_t level_count,
+    uint32_t polynomial_size, uint32_t grouping_factor);
+
+void scratch_cuda_multi_bit_programmable_bootstrap_64(
+    void *stream, uint32_t gpu_index, int8_t **pbs_buffer,
+    uint32_t glwe_dimension, uint32_t polynomial_size, uint32_t level_count,
+    uint32_t input_lwe_ciphertext_count, bool allocate_gpu_memory);
+
+void cuda_multi_bit_programmable_bootstrap_lwe_ciphertext_vector_64(
+    void *stream, uint32_t gpu_index, void *lwe_array_out,
+    void const *lwe_output_indexes, void const *lut_vector,
+    void const *lut_vector_indexes, void const *lwe_array_in,
+    void const *lwe_input_indexes, void const *bootstrapping_key,
+    int8_t *buffer, uint32_t lwe_dimension, uint32_t glwe_dimension,
+    uint32_t polynomial_size, uint32_t grouping_factor, uint32_t base_log,
+    uint32_t level_count, uint32_t num_samples, uint32_t num_many_lut,
+    uint32_t lut_stride);
+
+void cleanup_cuda_multi_bit_programmable_bootstrap(void *stream,
+                                                   uint32_t gpu_index,
+                                                   int8_t **pbs_buffer);
+}
+
+#endif // CUDA_MULTI_BIT_H

backends/tfhe-cuda-backend/cuda/src/crypto/ciphertext.cu

@@ -22,8 +22,8 @@ void cuda_convert_lwe_ciphertext_vector_to_cpu_64(void *stream,
 }
 
 void cuda_glwe_sample_extract_64(void *stream, uint32_t gpu_index,
-                                 void *lwe_array_out, void *glwe_array_in,
-                                 uint32_t *nth_array, uint32_t num_glwes,
+                                 void *lwe_array_out, void const *glwe_array_in,
+                                 uint32_t const *nth_array, uint32_t num_nths,
                                  uint32_t glwe_dimension,
                                  uint32_t polynomial_size) {
 
@@ -31,43 +31,43 @@ void cuda_glwe_sample_extract_64(void *stream, uint32_t gpu_index,
   case 256:
     host_sample_extract<uint64_t, AmortizedDegree<256>>(
         static_cast<cudaStream_t>(stream), gpu_index, (uint64_t *)lwe_array_out,
-        (uint64_t *)glwe_array_in, (uint32_t *)nth_array, num_glwes,
+        (uint64_t const *)glwe_array_in, (uint32_t const *)nth_array, num_nths,
         glwe_dimension);
     break;
   case 512:
     host_sample_extract<uint64_t, AmortizedDegree<512>>(
         static_cast<cudaStream_t>(stream), gpu_index, (uint64_t *)lwe_array_out,
-        (uint64_t *)glwe_array_in, (uint32_t *)nth_array, num_glwes,
+        (uint64_t const *)glwe_array_in, (uint32_t const *)nth_array, num_nths,
         glwe_dimension);
     break;
   case 1024:
     host_sample_extract<uint64_t, AmortizedDegree<1024>>(
         static_cast<cudaStream_t>(stream), gpu_index, (uint64_t *)lwe_array_out,
-        (uint64_t *)glwe_array_in, (uint32_t *)nth_array, num_glwes,
+        (uint64_t const *)glwe_array_in, (uint32_t const *)nth_array, num_nths,
         glwe_dimension);
     break;
   case 2048:
     host_sample_extract<uint64_t, AmortizedDegree<2048>>(
         static_cast<cudaStream_t>(stream), gpu_index, (uint64_t *)lwe_array_out,
-        (uint64_t *)glwe_array_in, (uint32_t *)nth_array, num_glwes,
+        (uint64_t const *)glwe_array_in, (uint32_t const *)nth_array, num_nths,
         glwe_dimension);
     break;
   case 4096:
     host_sample_extract<uint64_t, AmortizedDegree<4096>>(
         static_cast<cudaStream_t>(stream), gpu_index, (uint64_t *)lwe_array_out,
-        (uint64_t *)glwe_array_in, (uint32_t *)nth_array, num_glwes,
+        (uint64_t const *)glwe_array_in, (uint32_t const *)nth_array, num_nths,
         glwe_dimension);
     break;
   case 8192:
     host_sample_extract<uint64_t, AmortizedDegree<8192>>(
         static_cast<cudaStream_t>(stream), gpu_index, (uint64_t *)lwe_array_out,
-        (uint64_t *)glwe_array_in, (uint32_t *)nth_array, num_glwes,
+        (uint64_t const *)glwe_array_in, (uint32_t const *)nth_array, num_nths,
         glwe_dimension);
     break;
   case 16384:
     host_sample_extract<uint64_t, AmortizedDegree<16384>>(
         static_cast<cudaStream_t>(stream), gpu_index, (uint64_t *)lwe_array_out,
-        (uint64_t *)glwe_array_in, (uint32_t *)nth_array, num_glwes,
+        (uint64_t const *)glwe_array_in, (uint32_t const *)nth_array, num_nths,
         glwe_dimension);
     break;
   default:

backends/tfhe-cuda-backend/cuda/src/crypto/ciphertext.cuh

@@ -27,8 +27,9 @@ void cuda_convert_lwe_ciphertext_vector_to_cpu(cudaStream_t stream,
 }
 
 template <typename Torus, class params>
-__global__ void sample_extract(Torus *lwe_array_out, Torus *glwe_array_in,
-                               uint32_t *nth_array, uint32_t glwe_dimension) {
+__global__ void sample_extract(Torus *lwe_array_out, Torus const *glwe_array_in,
+                               uint32_t const *nth_array,
+                               uint32_t glwe_dimension) {
 
   const int input_id = blockIdx.x;
 
@@ -50,8 +51,9 @@ __global__ void sample_extract(Torus *lwe_array_out, Torus *glwe_array_in,
 
 template <typename Torus, class params>
 __host__ void host_sample_extract(cudaStream_t stream, uint32_t gpu_index,
-                                  Torus *lwe_array_out, Torus *glwe_array_in,
-                                  uint32_t *nth_array, uint32_t num_nths,
+                                  Torus *lwe_array_out,
+                                  Torus const *glwe_array_in,
+                                  uint32_t const *nth_array, uint32_t num_nths,
                                   uint32_t glwe_dimension) {
   cudaSetDevice(gpu_index);
 

backends/tfhe-cuda-backend/cuda/src/crypto/gadget.cuh

@@ -1,6 +1,7 @@
 #ifndef CNCRT_CRYPTO_CUH
 #define CNCRT_CRPYTO_CUH
 
+#include "crypto/torus.cuh"
 #include "device.h"
 #include <cstdint>
 
@@ -21,7 +22,6 @@ private:
   uint32_t base_log;
   uint32_t mask;
   uint32_t num_poly;
-  int current_level;
   T mask_mod_b;
   T *state;
 
@@ -32,13 +32,6 @@ public:
         state(state) {
 
     mask_mod_b = (1ll << base_log) - 1ll;
-    current_level = level_count;
-    int tid = threadIdx.x;
-    for (int i = 0; i < num_poly * params::opt; i++) {
-      state[tid] >>= (sizeof(T) * 8 - base_log * level_count);
-      tid += params::degree / params::opt;
-    }
-    synchronize_threads_in_block();
   }
 
   // Decomposes all polynomials at once
@@ -52,28 +45,30 @@ public:
   // Decomposes a single polynomial
   __device__ void decompose_and_compress_next_polynomial(double2 *result,
                                                          int j) {
-    if (j == 0)
-      current_level -= 1;
-
-    int tid = threadIdx.x;
-    auto state_slice = state + j * params::degree;
+    uint32_t tid = threadIdx.x;
+    auto state_slice = &state[j * params::degree];
     for (int i = 0; i < params::opt / 2; i++) {
-      T res_re = state_slice[tid] & mask_mod_b;
-      T res_im = state_slice[tid + params::degree / 2] & mask_mod_b;
-      state_slice[tid] >>= base_log;
-      state_slice[tid + params::degree / 2] >>= base_log;
-      T carry_re = ((res_re - 1ll) | state_slice[tid]) & res_re;
-      T carry_im =
-          ((res_im - 1ll) | state_slice[tid + params::degree / 2]) & res_im;
+      auto input1 = &state_slice[tid];
+      auto input2 = &state_slice[tid + params::degree / 2];
+      T res_re = *input1 & mask_mod_b;
+      T res_im = *input2 & mask_mod_b;
+
+      *input1 >>= base_log; // Update state
+      *input2 >>= base_log; // Update state
+
+      T carry_re = ((res_re - 1ll) | *input1) & res_re;
+      T carry_im = ((res_im - 1ll) | *input2) & res_im;
       carry_re >>= (base_log - 1);
       carry_im >>= (base_log - 1);
-      state_slice[tid] += carry_re;
-      state_slice[tid + params::degree / 2] += carry_im;
+
+      *input1 += carry_re; // Update state
+      *input2 += carry_im; // Update state
+
       res_re -= carry_re << base_log;
       res_im -= carry_im << base_log;
 
-      result[tid].x = (int32_t)res_re;
-      result[tid].y = (int32_t)res_im;
+      typecast_torus_to_double(res_re, result[tid].x);
+      typecast_torus_to_double(res_im, result[tid].y);
 
       tid += params::degree / params::opt;
     }

backends/tfhe-cuda-backend/cuda/src/crypto/keyswitch.cu

@@ -37,16 +37,18 @@ void cuda_keyswitch_lwe_ciphertext_vector_32(
  */
 void cuda_keyswitch_lwe_ciphertext_vector_64(
     void *stream, uint32_t gpu_index, void *lwe_array_out,
-    void *lwe_output_indexes, void *lwe_array_in, void *lwe_input_indexes,
-    void *ksk, uint32_t lwe_dimension_in, uint32_t lwe_dimension_out,
-    uint32_t base_log, uint32_t level_count, uint32_t num_samples) {
+    void const *lwe_output_indexes, void const *lwe_array_in,
+    void const *lwe_input_indexes, void const *ksk, uint32_t lwe_dimension_in,
+    uint32_t lwe_dimension_out, uint32_t base_log, uint32_t level_count,
+    uint32_t num_samples) {
   host_keyswitch_lwe_ciphertext_vector<uint64_t>(
       static_cast<cudaStream_t>(stream), gpu_index,
       static_cast<uint64_t *>(lwe_array_out),
-      static_cast<uint64_t *>(lwe_output_indexes),
-      static_cast<uint64_t *>(lwe_array_in),
-      static_cast<uint64_t *>(lwe_input_indexes), static_cast<uint64_t *>(ksk),
-      lwe_dimension_in, lwe_dimension_out, base_log, level_count, num_samples);
+      static_cast<const uint64_t *>(lwe_output_indexes),
+      static_cast<const uint64_t *>(lwe_array_in),
+      static_cast<const uint64_t *>(lwe_input_indexes),
+      static_cast<const uint64_t *>(ksk), lwe_dimension_in, lwe_dimension_out,
+      base_log, level_count, num_samples);
 }
 
 void scratch_packing_keyswitch_lwe_list_to_glwe_64(
@@ -61,18 +63,19 @@ void scratch_packing_keyswitch_lwe_list_to_glwe_64(
  * ciphertexts.
  */
 void cuda_packing_keyswitch_lwe_list_to_glwe_64(
-    void *stream, uint32_t gpu_index, void *glwe_array_out, void *lwe_array_in,
-    void *fp_ksk_array, int8_t *fp_ks_buffer, uint32_t input_lwe_dimension,
-    uint32_t output_glwe_dimension, uint32_t output_polynomial_size,
-    uint32_t base_log, uint32_t level_count, uint32_t num_lwes) {
+    void *stream, uint32_t gpu_index, void *glwe_array_out,
+    void const *lwe_array_in, void const *fp_ksk_array, int8_t *fp_ks_buffer,
+    uint32_t input_lwe_dimension, uint32_t output_glwe_dimension,
+    uint32_t output_polynomial_size, uint32_t base_log, uint32_t level_count,
+    uint32_t num_lwes) {
 
   host_packing_keyswitch_lwe_list_to_glwe<uint64_t>(
       static_cast<cudaStream_t>(stream), gpu_index,
       static_cast<uint64_t *>(glwe_array_out),
-      static_cast<uint64_t *>(lwe_array_in),
-      static_cast<uint64_t *>(fp_ksk_array), fp_ks_buffer, input_lwe_dimension,
-      output_glwe_dimension, output_polynomial_size, base_log, level_count,
-      num_lwes);
+      static_cast<const uint64_t *>(lwe_array_in),
+      static_cast<const uint64_t *>(fp_ksk_array), fp_ks_buffer,
+      input_lwe_dimension, output_glwe_dimension, output_polynomial_size,
+      base_log, level_count, num_lwes);
 }
 
 void cleanup_packing_keyswitch_lwe_list_to_glwe(void *stream,

backends/tfhe-cuda-backend/cuda/src/crypto/keyswitch.cuh

@@ -71,9 +71,8 @@ keyswitch(Torus *lwe_array_out, const Torus *__restrict__ lwe_output_indexes,
 
     // This loop distribution seems to benefit the global mem reads
     for (int i = start_i; i < end_i; i++) {
-      Torus a_i = round_to_closest_multiple(block_lwe_array_in[i], base_log,
-                                            level_count);
-      Torus state = a_i >> (sizeof(Torus) * 8 - base_log * level_count);
+      Torus state =
+          init_decomposer_state(block_lwe_array_in[i], base_log, level_count);
 
       for (int j = 0; j < level_count; j++) {
         auto ksk_block =
@@ -101,9 +100,10 @@ keyswitch(Torus *lwe_array_out, const Torus *__restrict__ lwe_output_indexes,
 template <typename Torus>
 __host__ void host_keyswitch_lwe_ciphertext_vector(
     cudaStream_t stream, uint32_t gpu_index, Torus *lwe_array_out,
-    Torus *lwe_output_indexes, Torus *lwe_array_in, Torus *lwe_input_indexes,
-    Torus *ksk, uint32_t lwe_dimension_in, uint32_t lwe_dimension_out,
-    uint32_t base_log, uint32_t level_count, uint32_t num_samples) {
+    Torus const *lwe_output_indexes, Torus const *lwe_array_in,
+    Torus const *lwe_input_indexes, Torus const *ksk, uint32_t lwe_dimension_in,
+    uint32_t lwe_dimension_out, uint32_t base_log, uint32_t level_count,
+    uint32_t num_samples) {
 
   cudaSetDevice(gpu_index);
 
@@ -124,13 +124,13 @@ __host__ void host_keyswitch_lwe_ciphertext_vector(
 }
 
 template <typename Torus>
-void execute_keyswitch_async(cudaStream_t *streams, uint32_t *gpu_indexes,
-                             uint32_t gpu_count,
+void execute_keyswitch_async(cudaStream_t const *streams,
+                             uint32_t const *gpu_indexes, uint32_t gpu_count,
                              const LweArrayVariant<Torus> &lwe_array_out,
                              const LweArrayVariant<Torus> &lwe_output_indexes,
                              const LweArrayVariant<Torus> &lwe_array_in,
                              const LweArrayVariant<Torus> &lwe_input_indexes,
-                             Torus **ksks, uint32_t lwe_dimension_in,
+                             Torus *const *ksks, uint32_t lwe_dimension_in,
                              uint32_t lwe_dimension_out, uint32_t base_log,
                              uint32_t level_count, uint32_t num_samples) {
 
@@ -176,9 +176,9 @@ __host__ void scratch_packing_keyswitch_lwe_list_to_glwe(
 // different thread blocks at the x-axis to work on that input.
 template <typename Torus>
 __device__ void packing_keyswitch_lwe_ciphertext_into_glwe_ciphertext(
-    Torus *glwe_out, Torus *lwe_in, Torus *fp_ksk, uint32_t lwe_dimension_in,
-    uint32_t glwe_dimension, uint32_t polynomial_size, uint32_t base_log,
-    uint32_t level_count) {
+    Torus *glwe_out, Torus const *lwe_in, Torus const *fp_ksk,
+    uint32_t lwe_dimension_in, uint32_t glwe_dimension,
+    uint32_t polynomial_size, uint32_t base_log, uint32_t level_count) {
 
   const int tid = threadIdx.x + blockIdx.x * blockDim.x;
   size_t glwe_size = (glwe_dimension + 1);
@@ -200,9 +200,8 @@ __device__ void packing_keyswitch_lwe_ciphertext_into_glwe_ciphertext(
     // Iterate through all lwe elements
     for (int i = 0; i < lwe_dimension_in; i++) {
       // Round and prepare decomposition
-      Torus a_i = round_to_closest_multiple(lwe_in[i], base_log, level_count);
+      Torus state = init_decomposer_state(lwe_in[i], base_log, level_count);
 
-      Torus state = a_i >> (sizeof(Torus) * 8 - base_log * level_count);
       Torus mod_b_mask = (1ll << base_log) - 1ll;
 
       // block of key for current lwe coefficient (cur_input_lwe[i])
@@ -225,12 +224,11 @@ __device__ void packing_keyswitch_lwe_ciphertext_into_glwe_ciphertext(
 // Assumes there are (glwe_dimension+1) * polynomial_size threads split through
 // different thread blocks at the x-axis to work on that input.
 template <typename Torus>
-__global__ void
-packing_keyswitch_lwe_list_to_glwe(Torus *glwe_array_out, Torus *lwe_array_in,
-                                   Torus *fp_ksk, uint32_t lwe_dimension_in,
-                                   uint32_t glwe_dimension,
-                                   uint32_t polynomial_size, uint32_t base_log,
-                                   uint32_t level_count, Torus *d_mem) {
+__global__ void packing_keyswitch_lwe_list_to_glwe(
+    Torus *glwe_array_out, Torus const *lwe_array_in, Torus const *fp_ksk,
+    uint32_t lwe_dimension_in, uint32_t glwe_dimension,
+    uint32_t polynomial_size, uint32_t base_log, uint32_t level_count,
+    Torus *d_mem) {
   const int tid = threadIdx.x + blockIdx.x * blockDim.x;
 
   const int glwe_accumulator_size = (glwe_dimension + 1) * polynomial_size;
@@ -244,16 +242,16 @@ packing_keyswitch_lwe_list_to_glwe(Torus *glwe_array_out, Torus *lwe_array_in,
   auto ks_glwe_out = d_mem + input_id * glwe_accumulator_size;
   auto glwe_out = glwe_array_out + input_id * glwe_accumulator_size;
   // KS LWE to GLWE
-  packing_keyswitch_lwe_ciphertext_into_glwe_ciphertext(
+  packing_keyswitch_lwe_ciphertext_into_glwe_ciphertext<Torus>(
       ks_glwe_out, lwe_in, fp_ksk, lwe_dimension_in, glwe_dimension,
       polynomial_size, base_log, level_count);
 
   // P * x ^degree
   auto in_poly = ks_glwe_out + (tid / polynomial_size) * polynomial_size;
   auto out_result = glwe_out + (tid / polynomial_size) * polynomial_size;
-  polynomial_accumulate_monic_monomial_mul(out_result, in_poly, degree,
-                                           tid % polynomial_size,
-                                           polynomial_size, 1, true);
+  polynomial_accumulate_monic_monomial_mul<Torus>(out_result, in_poly, degree,
+                                                  tid % polynomial_size,
+                                                  polynomial_size, 1, true);
 }
 
 /// To-do: Rewrite this kernel for efficiency
@@ -276,7 +274,7 @@ __global__ void accumulate_glwes(Torus *glwe_out, Torus *glwe_array_in,
 template <typename Torus>
 __host__ void host_packing_keyswitch_lwe_list_to_glwe(
     cudaStream_t stream, uint32_t gpu_index, Torus *glwe_out,
-    Torus *lwe_array_in, Torus *fp_ksk_array, int8_t *fp_ks_buffer,
+    Torus const *lwe_array_in, Torus const *fp_ksk_array, int8_t *fp_ks_buffer,
     uint32_t lwe_dimension_in, uint32_t glwe_dimension,
     uint32_t polynomial_size, uint32_t base_log, uint32_t level_count,
     uint32_t num_lwes) {
@@ -299,13 +297,13 @@ __host__ void host_packing_keyswitch_lwe_list_to_glwe(
   auto d_tmp_glwe_array_out = d_mem + num_lwes * glwe_accumulator_size;
 
   // individually keyswitch each lwe
-  packing_keyswitch_lwe_list_to_glwe<<<grid, threads, 0, stream>>>(
+  packing_keyswitch_lwe_list_to_glwe<Torus><<<grid, threads, 0, stream>>>(
       d_tmp_glwe_array_out, lwe_array_in, fp_ksk_array, lwe_dimension_in,
       glwe_dimension, polynomial_size, base_log, level_count, d_mem);
   check_cuda_error(cudaGetLastError());
 
   // accumulate to a single glwe
-  accumulate_glwes<<<num_blocks, threads, 0, stream>>>(
+  accumulate_glwes<Torus><<<num_blocks, threads, 0, stream>>>(
       glwe_out, d_tmp_glwe_array_out, glwe_dimension, polynomial_size,
       num_lwes);
   check_cuda_error(cudaGetLastError());

backends/tfhe-cuda-backend/cuda/src/crypto/torus.cuh

@@ -1,10 +1,22 @@
 #ifndef CNCRT_TORUS_CUH
 #define CNCRT_TORUS_CUH
 
+#include "device.h"
+#include "polynomial/parameters.cuh"
 #include "types/int128.cuh"
 #include "utils/kernel_dimensions.cuh"
 #include <limits>
 
+template <typename T>
+__host__ __device__ __forceinline__ constexpr double get_two_pow_torus_bits() {
+  return (sizeof(T) == 4) ? 4294967296.0 : 18446744073709551616.0;
+}
+
+template <typename T>
+__host__ __device__ __forceinline__ constexpr T scalar_max() {
+  return std::numeric_limits<T>::max();
+}
+
 template <typename T>
 __device__ inline void typecast_double_to_torus(double x, T &r) {
   r = T(x);
@@ -28,14 +40,46 @@ __device__ inline void typecast_double_to_torus<uint64_t>(double x,
 }
 
 template <typename T>
-__device__ inline T round_to_closest_multiple(T x, uint32_t base_log,
-                                              uint32_t level_count) {
-  const T non_rep_bit_count = sizeof(T) * 8 - level_count * base_log;
-  const T shift = non_rep_bit_count - 1;
-  T res = x >> shift;
-  res += 1;
-  res &= (T)(-2);
-  return res << shift;
+__device__ inline void typecast_double_round_to_torus(double x, T &r) {
+  constexpr double mx = get_two_pow_torus_bits<T>();
+  // floor must be used here because round has an issue with rounding .5,
+  // as it rounds away from zero.
+  double frac = x - floor(x);
+  frac *= mx;
+  typecast_double_to_torus(round(frac), r);
+}
+
+template <typename T>
+__device__ inline void typecast_torus_to_double(T x, double &r);
+
+template <>
+__device__ inline void typecast_torus_to_double<uint32_t>(uint32_t x,
+                                                          double &r) {
+  r = __int2double_rn(x);
+}
+
+template <>
+__device__ inline void typecast_torus_to_double<uint64_t>(uint64_t x,
+                                                          double &r) {
+  r = __ll2double_rn(x);
+}
+
+template <typename T>
+__device__ inline T init_decomposer_state(T input, uint32_t base_log,
+                                          uint32_t level_count) {
+  const T rep_bit_count = level_count * base_log;
+  const T non_rep_bit_count = sizeof(T) * 8 - rep_bit_count;
+  T res = input >> (non_rep_bit_count - 1);
+  T rounding_bit = res & (T)(1);
+  res++;
+  res >>= 1;
+  T torus_max = scalar_max<T>();
+  T mod_mask = torus_max >> non_rep_bit_count;
+  res &= mod_mask;
+  T shifted_random = rounding_bit << (rep_bit_count - 1);
+  T need_balance =
+      (((res - (T)(1)) | shifted_random) & res) >> (rep_bit_count - 1);
+  return res - (need_balance << rep_bit_count);
 }
 
 template <typename T>

backends/tfhe-cuda-backend/cuda/src/device.cu

@@ -2,6 +2,30 @@
 #include <cstdint>
 #include <cuda_runtime.h>
 
+cudaEvent_t cuda_create_event(uint32_t gpu_index) {
+  check_cuda_error(cudaSetDevice(gpu_index));
+  cudaEvent_t event;
+  check_cuda_error(cudaEventCreate(&event));
+  return event;
+}
+
+void cuda_event_record(cudaEvent_t event, cudaStream_t stream,
+                       uint32_t gpu_index) {
+  check_cuda_error(cudaSetDevice(gpu_index));
+  check_cuda_error(cudaEventRecord(event, stream));
+}
+
+void cuda_stream_wait_event(cudaStream_t stream, cudaEvent_t event,
+                            uint32_t gpu_index) {
+  check_cuda_error(cudaSetDevice(gpu_index));
+  check_cuda_error(cudaStreamWaitEvent(stream, event, 0));
+}
+
+void cuda_event_destroy(cudaEvent_t event, uint32_t gpu_index) {
+  check_cuda_error(cudaSetDevice(gpu_index));
+  check_cuda_error(cudaEventDestroy(event));
+}
+
 /// Unsafe function to create a CUDA stream, must check first that GPU exists
 cudaStream_t cuda_create_stream(uint32_t gpu_index) {
   check_cuda_error(cudaSetDevice(gpu_index));
@@ -21,6 +45,9 @@ void cuda_synchronize_stream(cudaStream_t stream, uint32_t gpu_index) {
   check_cuda_error(cudaStreamSynchronize(stream));
 }
 
+// Determine if a CUDA device is available at runtime
+uint32_t cuda_is_available() { return cudaSetDevice(0) == cudaSuccess; }
+
 /// Unsafe function that will try to allocate even if gpu_index is invalid
 /// or if there's not enough memory. A safe wrapper around it must call
 /// cuda_check_valid_malloc() first
@@ -113,7 +140,7 @@ void cuda_memcpy_async_to_gpu(void *dest, void *src, uint64_t size,
 }
 
 /// Copy memory within a GPU asynchronously
-void cuda_memcpy_async_gpu_to_gpu(void *dest, void *src, uint64_t size,
+void cuda_memcpy_async_gpu_to_gpu(void *dest, void const *src, uint64_t size,
                                   cudaStream_t stream, uint32_t gpu_index) {
   if (size == 0)
     return;
@@ -268,8 +295,20 @@ void cuda_drop_async(void *ptr, cudaStream_t stream, uint32_t gpu_index) {
 /// Get the maximum size for the shared memory
 int cuda_get_max_shared_memory(uint32_t gpu_index) {
   int max_shared_memory = 0;
+#if CUDA_ARCH == 900
+  max_shared_memory = 226000;
+#elif CUDA_ARCH == 890
+  max_shared_memory = 100000;
+#elif CUDA_ARCH == 860
+  max_shared_memory = 100000;
+#elif CUDA_ARCH == 800
+  max_shared_memory = 163000;
+#elif CUDA_ARCH == 700
+  max_shared_memory = 95000;
+#else
   cudaDeviceGetAttribute(&max_shared_memory, cudaDevAttrMaxSharedMemoryPerBlock,
                          gpu_index);
   check_cuda_error(cudaGetLastError());
+#endif
   return max_shared_memory;
 }

backends/tfhe-cuda-backend/cuda/src/integer/abs.cu

@@ -0,0 +1,43 @@
+#include "integer/abs.cuh"
+
+void scratch_cuda_integer_abs_inplace_radix_ciphertext_kb_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    int8_t **mem_ptr, bool is_signed, uint32_t glwe_dimension,
+    uint32_t polynomial_size, uint32_t big_lwe_dimension,
+    uint32_t small_lwe_dimension, uint32_t ks_level, uint32_t ks_base_log,
+    uint32_t pbs_level, uint32_t pbs_base_log, uint32_t grouping_factor,
+    uint32_t num_blocks, uint32_t message_modulus, uint32_t carry_modulus,
+    PBS_TYPE pbs_type, bool allocate_gpu_memory) {
+
+  int_radix_params params(pbs_type, glwe_dimension, polynomial_size,
+                          big_lwe_dimension, small_lwe_dimension, ks_level,
+                          ks_base_log, pbs_level, pbs_base_log, grouping_factor,
+                          message_modulus, carry_modulus);
+
+  scratch_cuda_integer_abs_kb<uint64_t>(
+      (cudaStream_t *)(streams), gpu_indexes, gpu_count,
+      (int_abs_buffer<uint64_t> **)mem_ptr, is_signed, num_blocks, params,
+      allocate_gpu_memory);
+}
+
+void cuda_integer_abs_inplace_radix_ciphertext_kb_64(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    void *ct, int8_t *mem_ptr, bool is_signed, void *const *bsks,
+    void *const *ksks, uint32_t num_blocks) {
+
+  auto mem = (int_abs_buffer<uint64_t> *)mem_ptr;
+
+  host_integer_abs_kb<uint64_t>((cudaStream_t *)(streams), gpu_indexes,
+                                gpu_count, static_cast<uint64_t *>(ct), bsks,
+                                (uint64_t **)(ksks), mem, is_signed,
+                                num_blocks);
+}
+
+void cleanup_cuda_integer_abs_inplace(void *const *streams,
+                                      uint32_t const *gpu_indexes,
+                                      uint32_t gpu_count,
+                                      int8_t **mem_ptr_void) {
+  int_abs_buffer<uint64_t> *mem_ptr =
+      (int_abs_buffer<uint64_t> *)(*mem_ptr_void);
+  mem_ptr->release((cudaStream_t *)(streams), gpu_indexes, gpu_count);
+}

backends/tfhe-cuda-backend/cuda/src/integer/abs.cuh

@@ -0,0 +1,71 @@
+#ifndef TFHE_RS_ABS_CUH
+#define TFHE_RS_ABS_CUH
+
+#include "crypto/keyswitch.cuh"
+#include "device.h"
+#include "integer/bitwise_ops.cuh"
+#include "integer/comparison.cuh"
+#include "integer/integer.cuh"
+#include "integer/integer_utilities.h"
+#include "integer/negation.cuh"
+#include "integer/scalar_shifts.cuh"
+#include "linear_algebra.h"
+#include "pbs/programmable_bootstrap.h"
+#include "utils/helper.cuh"
+#include "utils/kernel_dimensions.cuh"
+#include <fstream>
+#include <iostream>
+#include <sstream>
+#include <string>
+#include <vector>
+
+template <typename Torus>
+__host__ void scratch_cuda_integer_abs_kb(
+    cudaStream_t const *streams, uint32_t const *gpu_indexes,
+    uint32_t gpu_count, int_abs_buffer<Torus> **mem_ptr, bool is_signed,
+    uint32_t num_blocks, int_radix_params params, bool allocate_gpu_memory) {
+
+  if (is_signed)
+    *mem_ptr =
+        new int_abs_buffer<Torus>(streams, gpu_indexes, gpu_count, params,
+                                  num_blocks, allocate_gpu_memory);
+}
+
+template <typename Torus>
+__host__ void
+host_integer_abs_kb(cudaStream_t const *streams, uint32_t const *gpu_indexes,
+                    uint32_t gpu_count, Torus *ct, void *const *bsks,
+                    uint64_t *const *ksks, int_abs_buffer<uint64_t> *mem_ptr,
+                    bool is_signed, uint32_t num_blocks) {
+  if (!is_signed)
+    return;
+
+  auto radix_params = mem_ptr->params;
+  auto mask = mem_ptr->mask;
+
+  auto big_lwe_dimension = radix_params.big_lwe_dimension;
+  auto big_lwe_size = big_lwe_dimension + 1;
+  auto big_lwe_size_bytes = big_lwe_size * sizeof(Torus);
+  uint32_t num_bits_in_ciphertext =
+      (31 - __builtin_clz(radix_params.message_modulus)) * num_blocks;
+
+  cuda_memcpy_async_gpu_to_gpu(mask, ct, num_blocks * big_lwe_size_bytes,
+                               streams[0], gpu_indexes[0]);
+
+  host_integer_radix_arithmetic_scalar_shift_kb_inplace(
+      streams, gpu_indexes, gpu_count, mask, num_bits_in_ciphertext - 1,
+      mem_ptr->arithmetic_scalar_shift_mem, bsks, ksks, num_blocks);
+  host_addition<Torus>(streams[0], gpu_indexes[0], ct, mask, ct,
+                       radix_params.big_lwe_dimension, num_blocks);
+
+  uint32_t requested_flag = outputFlag::FLAG_NONE;
+  uint32_t uses_carry = 0;
+  host_propagate_single_carry<Torus>(
+      streams, gpu_indexes, gpu_count, ct, nullptr, nullptr, mem_ptr->scp_mem,
+      bsks, ksks, num_blocks, requested_flag, uses_carry);
+
+  host_integer_radix_bitop_kb(streams, gpu_indexes, gpu_count, ct, mask, ct,
+                              mem_ptr->bitxor_mem, bsks, ksks, num_blocks);
+}
+
+#endif // TFHE_RS_ABS_CUH