Debug with long run tests

- From now on the streams stored in the available cuda server key are the ones to be

.github/actionlint.yaml

@@ -6,6 +6,7 @@ self-hosted-runner:
     - large_windows_16_latest
     - large_ubuntu_16
     - large_ubuntu_16-22.04
+    - v80-desktop
 # Configuration variables in array of strings defined in your repository or
 # organization. `null` means disabling configuration variables check.
 # Empty array means no configuration variable is allowed.

.github/actions/gpu_setup/action.yml

@@ -8,9 +8,6 @@ inputs:
   gcc-version:
     description: Version of GCC to use
     required: true
-  cmake-version:
-    description: Version of cmake to use
-    default: 3.29.6
   github-instance:
     description: Instance is hosted on GitHub
     default: 'false'
@@ -22,41 +19,58 @@ runs:
     - name: Install dependencies
       shell: bash
       run: |
+        wget https://github.com/Kitware/CMake/releases/download/v"${CMAKE_VERSION}"/cmake-"${CMAKE_VERSION}"-linux-x86_64.sh
+        echo "${CMAKE_SCRIPT_SHA} cmake-${CMAKE_VERSION}-linux-x86_64.sh" > checksum
+        sha256sum -c checksum
+        sudo bash cmake-"${CMAKE_VERSION}"-linux-x86_64.sh --skip-license --prefix=/usr/ --exclude-subdir
         sudo apt update
-        curl -fsSL https://apt.kitware.com/keys/kitware-archive-latest.asc | sudo gpg --dearmour -o /etc/apt/trusted.gpg.d/kitware.gpg
-        sudo chmod 644 /etc/apt/trusted.gpg.d/kitware.gpg
-        echo 'deb [signed-by=/etc/apt/trusted.gpg.d/kitware.gpg] https://apt.kitware.com/ubuntu/ jammy main' | sudo tee /etc/apt/sources.list.d/kitware.list >/dev/null
-        sudo apt update
-        sudo apt install -y cmake cmake-format libclang-dev
+        sudo apt install -y cmake-format libclang-dev
+      env:
+        CMAKE_VERSION: 3.29.6
+        CMAKE_SCRIPT_SHA: "6e4fada5cba3472ae503a11232b6580786802f0879cead2741672bf65d97488a"
 
     - name: Install CUDA
       if: inputs.github-instance == 'true'
       shell: bash
       run: |
-        TOOLKIT_VERSION="$(echo ${{ inputs.cuda-version }} | sed 's/\(.*\)\.\(.*\)/\1-\2/')"
-        wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.1-1_all.deb
-        sudo dpkg -i cuda-keyring_1.1-1_all.deb
+        TOOLKIT_VERSION="$(echo ${CUDA_VERSION} | sed 's/\(.*\)\.\(.*\)/\1-\2/')"
+        wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/${env.CUDA_KEYRING_PACKAGE}
+        echo "${CUDA_KEYRING_SHA} ${CUDA_KEYRING_PACKAGE}" > checksum
+        sha256sum -c checksum
+        sudo dpkg -i "${CUDA_KEYRING_PACKAGE}"
         sudo apt update
-        sudo apt -y install cuda-toolkit-${TOOLKIT_VERSION}
+        sudo apt -y install cuda-toolkit-"${TOOLKIT_VERSION}"
+      env:
+        CUDA_VERSION: ${{ inputs.cuda-version }}
+        CUDA_KEYRING_PACKAGE: cuda-keyring_1.1-1_all.deb
+        CUDA_KEYRING_SHA: "d93190d50b98ad4699ff40f4f7af50f16a76dac3bb8da1eaaf366d47898ff8df"
 
     - name: Export CUDA variables
       shell: bash
       run: |
-        CUDA_PATH=/usr/local/cuda-${{ inputs.cuda-version }}
-        echo "CUDA_PATH=$CUDA_PATH" >> "${GITHUB_ENV}"
-        echo "PATH=$PATH:$CUDA_PATH/bin" >> "${GITHUB_PATH}"
-        echo "LD_LIBRARY_PATH=$CUDA_PATH/lib64:$LD_LIBRARY_PATH" >> "${GITHUB_ENV}"
-        echo "CUDA_MODULE_LOADER=EAGER" >> "${GITHUB_ENV}"
+        CUDA_PATH=/usr/local/cuda-"${CUDA_VERSION}"
+        {
+          echo "CUDA_PATH=$CUDA_PATH";
+          echo "LD_LIBRARY_PATH=$CUDA_PATH/lib64:$LD_LIBRARY_PATH";
+          echo "CUDA_MODULE_LOADER=EAGER";
+        } >> "${GITHUB_ENV}"
+        {
+          echo "PATH=$PATH:$CUDA_PATH/bin"; 
+        } >> "${GITHUB_PATH}"
+      env:
+        CUDA_VERSION: ${{ inputs.cuda-version }}
 
     # Specify the correct host compilers
     - name: Export gcc and g++ variables
       shell: bash
       run: |
         {
-          echo "CC=/usr/bin/gcc-${{ inputs.gcc-version }}";
-          echo "CXX=/usr/bin/g++-${{ inputs.gcc-version }}";
-          echo "CUDAHOSTCXX=/usr/bin/g++-${{ inputs.gcc-version }}";
+          echo "CC=/usr/bin/gcc-${GCC_VERSION}";
+          echo "CXX=/usr/bin/g++-${GCC_VERSION}";
+          echo "CUDAHOSTCXX=/usr/bin/g++-${GCC_VERSION}";
         } >> "${GITHUB_ENV}"
+      env:
+        GCC_VERSION: ${{ inputs.gcc-version }}
 
     - name: Check device is detected
       shell: bash

.github/workflows/approve_label.yml

@@ -6,6 +6,9 @@ on:
   pull_request_review:
     types: [submitted]
 
+
+permissions: {}
+
 jobs:
   trigger-tests:
     runs-on: ubuntu-latest
@@ -34,3 +37,10 @@ jobs:
           # We need to use a PAT to be able to trigger `labeled` event for the other workflow.
           github_token: ${{ secrets.FHE_ACTIONS_TOKEN }}
           labels: approved
+
+      - name: Check if maintainer needs to handle label manually
+        if: ${{ failure() }}
+        run: |
+          echo "Pull-request from an external contributor."
+          echo "A maintainer need to manually add/remove the 'approved' label."
+          exit 1

.github/workflows/aws_tfhe_backward_compat_tests.yml

@@ -11,6 +11,8 @@ env:
   SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
   SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
   SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+  SLACKIFY_MARKDOWN: true
+  PULL_REQUEST_MD_LINK: ""
   CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN || secrets.GITHUB_TOKEN }}
   # Secrets will be available only to zama-ai organization members
   SECRETS_AVAILABLE: ${{ secrets.JOB_SECRET != '' }}
@@ -21,6 +23,9 @@ on:
   workflow_dispatch:
   pull_request:
 
+permissions:
+  contents: read
+
 jobs:
   setup-instance:
     name: Setup instance (backward-compat-tests)
@@ -45,13 +50,13 @@ jobs:
         id: start-github-instance
         if: env.SECRETS_AVAILABLE == 'false'
         run: |
-          echo "runner_group=${{ env.EXTERNAL_CONTRIBUTION_RUNNER }}" >> "$GITHUB_OUTPUT"
+          echo "runner_group=${EXTERNAL_CONTRIBUTION_RUNNER}" >> "$GITHUB_OUTPUT"
 
   backward-compat-tests:
     name: Backward compatibility tests
     needs: [ setup-instance ]
     concurrency:
-      group: ${{ github.workflow }}_${{ github.head_ref || github.ref }}
+      group: ${{ github.workflow_ref }}
       cancel-in-progress: true
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     steps:
@@ -62,14 +67,10 @@ jobs:
           token: ${{ env.CHECKOUT_TOKEN }}
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: stable
 
-      - name: Install git-lfs
-        run: |
-          sudo apt update && sudo apt -y install git-lfs
-
       - name: Use specific data branch
         if: ${{ contains(github.event.pull_request.labels.*.name, 'data_PR') }}
         env:
@@ -83,10 +84,28 @@ jobs:
           BRANCH="$(make backward_compat_branch)"
           echo "branch=${BRANCH}" >> "${GITHUB_OUTPUT}"
 
+      - name: Get backward compat branch head SHA
+        id: backward_compat_sha
+        run: |
+          SHA=$(git ls-remote "${REPO_URL}" refs/heads/"${BACKWARD_COMPAT_BRANCH}" | awk '{print $1}')
+          echo "sha=${SHA}" >> "${GITHUB_OUTPUT}"
+        env:
+          REPO_URL: "https://github.com/zama-ai/tfhe-backward-compat-data"
+          BACKWARD_COMPAT_BRANCH: ${{ steps.backward_compat_branch.outputs.branch }}
+
+      - name: Retrieve data from cache
+        id: retrieve-data-cache
+        uses: actions/cache/restore@5a3ec84eff668545956fd18022155c47e93e2684 #v4.2.3
+        with:
+          path: tests/tfhe-backward-compat-data
+          key: ${{ steps.backward_compat_branch.outputs.branch }}_${{ steps.backward_compat_sha.outputs.sha }}
+
       - name: Clone test data
+        if: steps.retrieve-data-cache.outputs.cache-hit != 'true'
         uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           persist-credentials: 'false'
+          token: ${{ env.CHECKOUT_TOKEN }}
           repository: zama-ai/tfhe-backward-compat-data
           path: tests/tfhe-backward-compat-data
           lfs: 'true'
@@ -96,13 +115,28 @@ jobs:
         run: |
           make test_backward_compatibility_ci
 
-      - name: Slack Notification
-        if: ${{ failure() }}
+      - name: Store data in cache
+        if: steps.retrieve-data-cache.outputs.cache-hit != 'true'
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: actions/cache/save@5a3ec84eff668545956fd18022155c47e93e2684 #v4.2.3
+        with:
+          path: tests/tfhe-backward-compat-data
+          key: ${{ steps.backward_compat_branch.outputs.branch }}_${{ steps.backward_compat_sha.outputs.sha }}
+
+      - name: Set pull-request URL
+        if: ${{ failure() && github.event_name == 'pull_request' }}
+        run: |
+          echo "PULL_REQUEST_MD_LINK=[pull-request](${PR_BASE_URL}${{ github.event.pull_request.number }}), "  >> "${GITHUB_ENV}"
+        env:
+          PR_BASE_URL: ${{ vars.PR_BASE_URL }}
+
+      - name: Slack Notification
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
+        continue-on-error: true
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "Backward compatibility tests finished with status: ${{ job.status }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Backward compatibility tests finished with status: ${{ job.status }}. (${{ env.PULL_REQUEST_MD_LINK }}[action run](${{ env.ACTION_RUN_URL }}))"
 
   teardown-instance:
     name: Teardown instance (backward-compat-tests)
@@ -124,7 +158,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "Instance teardown (backward-compat-tests) finished with status: ${{ job.status }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Instance teardown (backward-compat-tests) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/aws_tfhe_fast_tests.yml

@@ -11,7 +11,9 @@ env:
   SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
   SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
   SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+  SLACKIFY_MARKDOWN: true
   IS_PULL_REQUEST: ${{ github.event_name == 'pull_request' }}
+  PULL_REQUEST_MD_LINK: ""
   CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN || secrets.GITHUB_TOKEN }}
   # Secrets will be available only to zama-ai organization members
   SECRETS_AVAILABLE: ${{ secrets.JOB_SECRET != '' }}
@@ -22,6 +24,9 @@ on:
   workflow_dispatch:
   pull_request:
 
+permissions:
+  contents: read
+
 jobs:
   should-run:
     runs-on: ubuntu-latest
@@ -63,7 +68,7 @@ jobs:
 
       - name: Check for file changes
         id: changed-files
-        uses: tj-actions/changed-files@dcc7a0cba800f454d79fff4b993e8c3555bcc0a8
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
         with:
           files_yaml: |
             dependencies:
@@ -152,13 +157,13 @@ jobs:
         id: start-github-instance
         if: env.SECRETS_AVAILABLE == 'false'
         run: |
-          echo "runner_group=${{ env.EXTERNAL_CONTRIBUTION_RUNNER }}" >> "$GITHUB_OUTPUT"
+          echo "runner_group=${EXTERNAL_CONTRIBUTION_RUNNER}" >> "$GITHUB_OUTPUT"
 
   fast-tests:
     name: Fast CPU tests
     needs: [ should-run, setup-instance ]
     concurrency:
-      group: ${{ github.workflow }}_${{ github.head_ref || github.ref }}
+      group: ${{ github.workflow_ref }}
       cancel-in-progress: true
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     steps:
@@ -169,7 +174,7 @@ jobs:
           token: ${{ env.CHECKOUT_TOKEN }}
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: stable
 
@@ -209,7 +214,7 @@ jobs:
 
       - name: Node cache restoration
         id: node-cache
-        uses: actions/cache/restore@1bd1e32a3bdc45362d1e726936510720a7c30a57 #v4.2.0
+        uses: actions/cache/restore@5a3ec84eff668545956fd18022155c47e93e2684 #v4.2.3
         with:
           path: |
             ~/.nvm
@@ -222,7 +227,7 @@ jobs:
           make install_node
 
       - name: Node cache save
-        uses: actions/cache/save@1bd1e32a3bdc45362d1e726936510720a7c30a57 #v4.2.0
+        uses: actions/cache/save@5a3ec84eff668545956fd18022155c47e93e2684 #v4.2.3
         if: steps.node-cache.outputs.cache-hit != 'true'
         with:
           path: |
@@ -264,13 +269,20 @@ jobs:
         run: |
           make test_zk
 
+      - name: Set pull-request URL
+        if: ${{ failure() && github.event_name == 'pull_request' }}
+        run: |
+          echo "PULL_REQUEST_MD_LINK=[pull-request](${PR_BASE_URL}${{ github.event.pull_request.number }}), "  >> "${GITHUB_ENV}"
+        env:
+          PR_BASE_URL: ${{ vars.PR_BASE_URL }}
+
       - name: Slack Notification
         if: ${{ failure() && env.SECRETS_AVAILABLE == 'true' }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "Fast AWS tests finished with status: ${{ job.status }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Fast AWS tests finished with status: ${{ job.status }}. (${{ env.PULL_REQUEST_MD_LINK }}[action run](${{ env.ACTION_RUN_URL }}))"
 
   teardown-instance:
     name: Teardown instance (fast-tests)
@@ -290,9 +302,9 @@ jobs:
           label: ${{ needs.setup-instance.outputs.runner-name }}
 
       - name: Slack Notification
-        if: ${{ failure() }}
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "Instance teardown (fast-tests) finished with status: ${{ job.status }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Instance teardown (fast-tests) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/aws_tfhe_integer_tests.yml

@@ -10,6 +10,8 @@ env:
   SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
   SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
   SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+  SLACKIFY_MARKDOWN: true
+  PULL_REQUEST_MD_LINK: ""
   # We clear the cache to reduce memory pressure because of the numerous processes of cargo
   # nextest
   TFHE_RS_CLEAR_IN_MEMORY_KEY_CACHE: "1"
@@ -28,6 +30,9 @@ on:
     branches:
       - main
 
+permissions:
+  contents: read
+
 jobs:
   should-run:
     if:
@@ -50,7 +55,7 @@ jobs:
 
       - name: Check for file changes
         id: changed-files
-        uses: tj-actions/changed-files@dcc7a0cba800f454d79fff4b993e8c3555bcc0a8
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
         with:
           files_yaml: |
             integer:
@@ -92,13 +97,13 @@ jobs:
         id: start-github-instance
         if: env.SECRETS_AVAILABLE == 'false'
         run: |
-          echo "runner_group=${{ env.EXTERNAL_CONTRIBUTION_RUNNER }}" >> "$GITHUB_OUTPUT"
+          echo "runner_group=${EXTERNAL_CONTRIBUTION_RUNNER}" >> "$GITHUB_OUTPUT"
 
   unsigned-integer-tests:
     name: Unsigned integer tests
     needs: setup-instance
     concurrency:
-      group: ${{ github.workflow }}_${{ github.head_ref || github.ref }}
+      group: ${{ github.workflow_ref }}
       cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     steps:
@@ -109,7 +114,7 @@ jobs:
           token: ${{ env.CHECKOUT_TOKEN }}
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: stable
 
@@ -132,15 +137,22 @@ jobs:
 
       - name: Run unsigned integer tests
         run: |
-          AVX512_SUPPORT=ON NO_BIG_PARAMS=${{ env.NO_BIG_PARAMS }} BIG_TESTS_INSTANCE=TRUE make test_unsigned_integer_ci
+          AVX512_SUPPORT=ON NO_BIG_PARAMS="${NO_BIG_PARAMS}" BIG_TESTS_INSTANCE=TRUE make test_unsigned_integer_ci
+
+      - name: Set pull-request URL
+        if: ${{ failure() && github.event_name == 'pull_request' }}
+        run: |
+          echo "PULL_REQUEST_MD_LINK=[pull-request](${PR_BASE_URL}${{ github.event.pull_request.number }}), "  >> "${GITHUB_ENV}"
+        env:
+          PR_BASE_URL: ${{ vars.PR_BASE_URL }}
 
       - name: Slack Notification
-        if: ${{ failure() }}
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "Unsigned Integer tests finished with status: ${{ job.status }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Unsigned Integer tests finished with status: ${{ job.status }}. (${{ env.PULL_REQUEST_MD_LINK }}[action run](${{ env.ACTION_RUN_URL }}))"
 
   teardown-instance:
     name: Teardown instance (unsigned-integer-tests)
@@ -162,7 +174,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "Instance teardown (unsigned-integer-tests) finished with status: ${{ job.status }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Instance teardown (unsigned-integer-tests) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/aws_tfhe_signed_integer_tests.yml

@@ -10,6 +10,8 @@ env:
   SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
   SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
   SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+  SLACKIFY_MARKDOWN: true
+  PULL_REQUEST_MD_LINK: ""
   # We clear the cache to reduce memory pressure because of the numerous processes of cargo
   # nextest
   TFHE_RS_CLEAR_IN_MEMORY_KEY_CACHE: "1"
@@ -28,6 +30,9 @@ on:
     branches:
       - main
 
+permissions:
+  contents: read
+
 jobs:
   should-run:
     if:
@@ -51,7 +56,7 @@ jobs:
 
       - name: Check for file changes
         id: changed-files
-        uses: tj-actions/changed-files@dcc7a0cba800f454d79fff4b993e8c3555bcc0a8
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
         with:
           files_yaml: |
             integer:
@@ -93,13 +98,13 @@ jobs:
         id: start-github-instance
         if: env.SECRETS_AVAILABLE == 'false'
         run: |
-          echo "runner_group=${{ env.EXTERNAL_CONTRIBUTION_RUNNER }}" >> "$GITHUB_OUTPUT"
+          echo "runner_group=${EXTERNAL_CONTRIBUTION_RUNNER}" >> "$GITHUB_OUTPUT"
 
   signed-integer-tests:
     name: Signed integer tests
     needs: setup-instance
     concurrency:
-      group: ${{ github.workflow }}_${{ github.head_ref || github.ref }}
+      group: ${{ github.workflow_ref }}
       cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     steps:
@@ -110,7 +115,7 @@ jobs:
           token: ${{ env.CHECKOUT_TOKEN }}
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: stable
 
@@ -137,15 +142,22 @@ jobs:
 
       - name: Run signed integer tests
         run: |
-          AVX512_SUPPORT=ON NO_BIG_PARAMS=${{ env.NO_BIG_PARAMS }} BIG_TESTS_INSTANCE=TRUE make test_signed_integer_ci
+          AVX512_SUPPORT=ON NO_BIG_PARAMS="${NO_BIG_PARAMS}" BIG_TESTS_INSTANCE=TRUE make test_signed_integer_ci
+
+      - name: Set pull-request URL
+        if: ${{ failure() && github.event_name == 'pull_request' }}
+        run: |
+          echo "PULL_REQUEST_MD_LINK=[pull-request](${PR_BASE_URL}${{ github.event.pull_request.number }}), "  >> "${GITHUB_ENV}"
+        env:
+          PR_BASE_URL: ${{ vars.PR_BASE_URL }}
 
       - name: Slack Notification
-        if: ${{ failure() }}
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "Signed Integer tests finished with status: ${{ job.status }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Signed Integer tests finished with status: ${{ job.status }}. (${{ env.PULL_REQUEST_MD_LINK }}[action run](${{ env.ACTION_RUN_URL }}))"
 
   teardown-instance:
     name: Teardown instance (signed-integer-tests)
@@ -167,7 +179,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "Instance teardown (signed-integer-tests) finished with status: ${{ job.status }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Instance teardown (signed-integer-tests) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/aws_tfhe_tests.yml

@@ -10,7 +10,9 @@ env:
   SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
   SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
   SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+  SLACKIFY_MARKDOWN: true
   IS_PULL_REQUEST: ${{ github.event_name == 'pull_request' }}
+  PULL_REQUEST_MD_LINK: ""
   CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN || secrets.GITHUB_TOKEN }}
   # Secrets will be available only to zama-ai organization members
   SECRETS_AVAILABLE: ${{ secrets.JOB_SECRET != '' }}
@@ -25,6 +27,9 @@ on:
     # Nightly tests @ 1AM after each work day
     - cron: "0 1 * * MON-FRI"
 
+permissions:
+  contents: read
+
 jobs:
   should-run:
     runs-on: ubuntu-latest
@@ -72,7 +77,7 @@ jobs:
 
       - name: Check for file changes
         id: changed-files
-        uses: tj-actions/changed-files@dcc7a0cba800f454d79fff4b993e8c3555bcc0a8
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
         with:
           files_yaml: |
             dependencies:
@@ -161,7 +166,7 @@ jobs:
         id: start-github-instance
         if: env.SECRETS_AVAILABLE == 'false'
         run: |
-          echo "runner_group=${{ env.EXTERNAL_CONTRIBUTION_RUNNER }}" >> "$GITHUB_OUTPUT"
+          echo "runner_group=${EXTERNAL_CONTRIBUTION_RUNNER}" >> "$GITHUB_OUTPUT"
 
   cpu-tests:
     name: CPU tests
@@ -169,7 +174,7 @@ jobs:
       (github.event_name == 'pull_request' && needs.setup-instance.result != 'skipped')
     needs: [ should-run, setup-instance ]
     concurrency:
-      group: ${{ github.workflow }}_${{github.event_name}}_${{ github.head_ref || github.ref }}
+      group: ${{ github.workflow_ref }}_${{github.event_name}}
       cancel-in-progress: true
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     steps:
@@ -180,7 +185,7 @@ jobs:
           token: ${{ env.CHECKOUT_TOKEN }}
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: stable
 
@@ -246,13 +251,20 @@ jobs:
           make test_trivium
           make test_kreyvium
 
+      - name: Set pull-request URL
+        if: ${{ failure() && github.event_name == 'pull_request' }}
+        run: |
+          echo "PULL_REQUEST_MD_LINK=[pull-request](${PR_BASE_URL}${{ github.event.pull_request.number }}), "  >> "${GITHUB_ENV}"
+        env:
+          PR_BASE_URL: ${{ vars.PR_BASE_URL }}
+
       - name: Slack Notification
-        if: ${{ failure() }}
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "CPU tests finished with status: ${{ job.status }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "CPU tests finished with status: ${{ job.status }}. (${{ env.PULL_REQUEST_MD_LINK }}[action run](${{ env.ACTION_RUN_URL }}))"
 
   teardown-instance:
     name: Teardown instance (cpu-tests)
@@ -274,7 +286,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "Instance teardown (cpu-tests) finished with status: ${{ job.status }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Instance teardown (cpu-tests) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/aws_tfhe_wasm_tests.yml

@@ -10,6 +10,8 @@ env:
   SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
   SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
   SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+  SLACKIFY_MARKDOWN: true
+  PULL_REQUEST_MD_LINK: ""
   CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN || secrets.GITHUB_TOKEN }}
   # Secrets will be available only to zama-ai organization members
   SECRETS_AVAILABLE: ${{ secrets.JOB_SECRET != '' }}
@@ -21,6 +23,9 @@ on:
   pull_request:
     types: [ labeled ]
 
+permissions:
+  contents: read
+
 jobs:
   setup-instance:
     name: Setup instance (wasm-tests)
@@ -46,13 +51,13 @@ jobs:
         id: start-github-instance
         if: env.SECRETS_AVAILABLE == 'false'
         run: |
-          echo "runner_group=${{ env.EXTERNAL_CONTRIBUTION_RUNNER }}" >> "$GITHUB_OUTPUT"
+          echo "runner_group=${EXTERNAL_CONTRIBUTION_RUNNER}" >> "$GITHUB_OUTPUT"
 
   wasm-tests:
     name: WASM tests
     needs: setup-instance
     concurrency:
-      group: ${{ github.workflow }}_${{ github.head_ref || github.ref }}
+      group: ${{ github.workflow_ref }}
       cancel-in-progress: true
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     steps:
@@ -63,7 +68,7 @@ jobs:
           token: ${{ env.CHECKOUT_TOKEN }}
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: stable
 
@@ -73,7 +78,7 @@ jobs:
 
       - name: Node cache restoration
         id: node-cache
-        uses: actions/cache/restore@1bd1e32a3bdc45362d1e726936510720a7c30a57 #v4.2.0
+        uses: actions/cache/restore@5a3ec84eff668545956fd18022155c47e93e2684 #v4.2.3
         with:
           path: |
             ~/.nvm
@@ -86,7 +91,7 @@ jobs:
           make install_node
 
       - name: Node cache save
-        uses: actions/cache/save@1bd1e32a3bdc45362d1e726936510720a7c30a57 #v4.2.0
+        uses: actions/cache/save@5a3ec84eff668545956fd18022155c47e93e2684 #v4.2.3
         if: steps.node-cache.outputs.cache-hit != 'true'
         with:
           path: |
@@ -115,13 +120,20 @@ jobs:
         run: |
           make test_zk_wasm_x86_compat_ci
 
+      - name: Set pull-request URL
+        if: ${{ failure() && github.event_name == 'pull_request' }}
+        run: |
+          echo "PULL_REQUEST_MD_LINK=[pull-request](${PR_BASE_URL}${{ github.event.pull_request.number }}), "  >> "${GITHUB_ENV}"
+        env:
+          PR_BASE_URL: ${{ vars.PR_BASE_URL }}
+
       - name: Slack Notification
-        if: ${{ failure() }}
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "WASM tests finished with status: ${{ job.status }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "WASM tests finished with status: ${{ job.status }}. (${{ env.PULL_REQUEST_MD_LINK }}[action run](${{ env.ACTION_RUN_URL }}))"
 
   teardown-instance:
     name: Teardown instance (wasm-tests)
@@ -143,7 +155,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "Instance teardown (wasm-tests) finished with status: ${{ job.status }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Instance teardown (wasm-tests) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/benchmark_boolean.yml

@@ -18,6 +18,9 @@ env:
   SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
   SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
 
+
+permissions: {}
+
 jobs:
   setup-instance:
     name: Setup instance (boolean-benchmarks)
@@ -43,9 +46,8 @@ jobs:
     needs: setup-instance
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     concurrency:
-      group: ${{ github.workflow }}_${{ github.ref }}
+      group: ${{ github.workflow_ref }}
       cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
-    continue-on-error: true
     steps:
       - name: Checkout tfhe-rs repo with tags
         uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
@@ -63,7 +65,7 @@ jobs:
           } >> "${GITHUB_ENV}"
 
       - name: Install rust
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: nightly
 
@@ -73,15 +75,17 @@ jobs:
 
       - name: Parse results
         run: |
-          python3 ./ci/benchmark_parser.py target/criterion ${{ env.RESULTS_FILENAME }} \
+          python3 ./ci/benchmark_parser.py target/criterion "${RESULTS_FILENAME}" \
           --database tfhe_rs \
           --hardware "hpc7a.96xlarge" \
-          --project-version "${{ env.COMMIT_HASH }}" \
-          --branch ${{ github.ref_name }} \
-          --commit-date "${{ env.COMMIT_DATE }}" \
-          --bench-date "${{ env.BENCH_DATE }}" \
+          --project-version "${COMMIT_HASH}" \
+          --branch "${REF_NAME}" \
+          --commit-date "${COMMIT_DATE}" \
+          --bench-date "${BENCH_DATE}" \
           --walk-subdirs \
           --name-suffix avx512
+        env:
+          REF_NAME: ${{ github.ref_name }}
 
       - name: Measure key sizes
         run: |
@@ -89,12 +93,12 @@ jobs:
 
       - name: Parse key sizes results
         run: |
-          python3 ./ci/benchmark_parser.py tfhe/boolean_key_sizes.csv ${{ env.RESULTS_FILENAME }} \
+          python3 ./ci/benchmark_parser.py tfhe-benchmark/boolean_key_sizes.csv "${RESULTS_FILENAME}" \
           --object-sizes \
           --append-results
 
       - name: Upload parsed results artifact
-        uses: actions/upload-artifact@65c4c4a1ddee5b72f698fdd19549f0f0fb45cf08
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02
         with:
           name: ${{ github.sha }}_boolean
           path: ${{ env.RESULTS_FILENAME }}
@@ -110,13 +114,13 @@ jobs:
       - name: Send data to Slab
         shell: bash
         run: |
-          python3 slab/scripts/data_sender.py ${{ env.RESULTS_FILENAME }} "${{ secrets.JOB_SECRET }}" \
+          python3 slab/scripts/data_sender.py "${RESULTS_FILENAME}" "${{ secrets.JOB_SECRET }}" \
           --slab-url "${{ secrets.SLAB_URL }}"
 
       - name: Slack Notification
-        if: ${{ failure() }}
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Boolean benchmarks finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
@@ -140,7 +144,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         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

@@ -18,6 +18,9 @@ env:
   SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
   SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
 
+
+permissions: {}
+
 jobs:
   setup-instance:
     name: Setup instance (core-crypto-benchmarks)
@@ -43,7 +46,7 @@ jobs:
     needs: setup-instance
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     concurrency:
-      group: ${{ github.workflow }}_${{ github.ref }}
+      group: ${{ github.workflow_ref }}
       cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
     steps:
       - name: Checkout tfhe-rs repo with tags
@@ -62,30 +65,33 @@ jobs:
           } >> "${GITHUB_ENV}"
 
       - name: Install rust
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: nightly
 
       - name: Run benchmarks with AVX512
         run: |
+          make bench_ks_pbs
           make bench_pbs
           make bench_pbs128
           make bench_ks
 
       - name: Parse results
         run: |
-          python3 ./ci/benchmark_parser.py target/criterion ${{ env.RESULTS_FILENAME }} \
+          python3 ./ci/benchmark_parser.py target/criterion "${RESULTS_FILENAME}" \
           --database tfhe_rs \
           --hardware "hpc7a.96xlarge" \
-          --project-version "${{ env.COMMIT_HASH }}" \
-          --branch ${{ github.ref_name }} \
-          --commit-date "${{ env.COMMIT_DATE }}" \
-          --bench-date "${{ env.BENCH_DATE }}" \
+          --project-version "${COMMIT_HASH}" \
+          --branch "${REF_NAME}" \
+          --commit-date "${COMMIT_DATE}" \
+          --bench-date "${BENCH_DATE}" \
           --name-suffix avx512 \
           --walk-subdirs
+        env:
+          REF_NAME: ${{ github.ref_name }}
 
       - name: Upload parsed results artifact
-        uses: actions/upload-artifact@65c4c4a1ddee5b72f698fdd19549f0f0fb45cf08
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02
         with:
           name: ${{ github.sha }}_core_crypto
           path: ${{ env.RESULTS_FILENAME }}
@@ -101,13 +107,13 @@ jobs:
       - name: Send data to Slab
         shell: bash
         run: |
-          python3 slab/scripts/data_sender.py ${{ env.RESULTS_FILENAME }} "${{ secrets.JOB_SECRET }}" \
+          python3 slab/scripts/data_sender.py "${RESULTS_FILENAME}" "${{ secrets.JOB_SECRET }}" \
           --slab-url "${{ secrets.SLAB_URL }}"
 
       - name: Slack Notification
-        if: ${{ failure() }}
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "PBS benchmarks finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
@@ -131,7 +137,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Instance teardown (core-crypto-benchmarks) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/benchmark_dex.yml

@@ -1,26 +1,30 @@
-# Run core crypto benchmarks on an instance with CUDA and return parsed results to Slab CI bot.
-name: Core crypto GPU benchmarks
+# Run all DEX benchmarks on an AWS instance and return parsed results to Slab CI bot.
+name: DEX benchmarks
 
 on:
   workflow_dispatch:
   schedule:
-    # Weekly benchmarks will be triggered each Saturday at 1a.m.
-    - cron: '0 1 * * 6'
+    # 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 }}
 
+permissions: {}
+
 jobs:
   setup-instance:
-    name: Setup instance (cuda-core-crypto-benchmarks)
+    name: Setup instance (dex-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 }}
@@ -33,21 +37,17 @@ jobs:
           github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
           slab-url: ${{ secrets.SLAB_BASE_URL }}
           job-secret: ${{ secrets.JOB_SECRET }}
-          backend: hyperstack
-          profile: single-h100
+          backend: aws
+          profile: bench
 
-  cuda-core-crypto-benchmarks:
-    name: Execute GPU core crypto benchmarks
+  dex-benchmarks:
+    name: Execute DEX 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
+    concurrency:
+      group: ${{ github.workflow_ref }}
+      cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
+    timeout-minutes: 720  # 12 hours
     steps:
       - name: Checkout tfhe-rs repo with tags
         uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
@@ -56,12 +56,6 @@ jobs:
           persist-credentials: 'false'
           token: ${{ secrets.REPO_CHECKOUT_TOKEN }}
 
-      - name: Setup Hyperstack dependencies
-        uses: ./.github/actions/gpu_setup
-        with:
-          cuda-version: ${{ matrix.cuda }}
-          gcc-version: ${{ matrix.gcc }}
-
       - name: Get benchmark details
         run: |
           {
@@ -71,34 +65,10 @@ jobs:
           } >> "${GITHUB_ENV}"
 
       - name: Install rust
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: nightly
 
-      - name: Run benchmarks with AVX512
-        run: |
-          make bench_pbs_gpu
-          make bench_ks_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 }}" \
-          --name-suffix avx512 \
-          --walk-subdirs
-
-      - name: Upload parsed results artifact
-        uses: actions/upload-artifact@65c4c4a1ddee5b72f698fdd19549f0f0fb45cf08
-        with:
-          name: ${{ github.sha }}_core_crypto
-          path: ${{ env.RESULTS_FILENAME }}
-
       - name: Checkout Slab repo
         uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
@@ -107,29 +77,60 @@ jobs:
           persist-credentials: 'false'
           token: ${{ secrets.REPO_CHECKOUT_TOKEN }}
 
+      - name: Run benchmarks
+        run: |
+          make bench_hlapi_dex
+
+      - name: Parse results
+        run: |
+          python3 ./ci/benchmark_parser.py target/criterion "${RESULTS_FILENAME}" \
+          --database tfhe_rs \
+          --hardware "hpc7a.96xlarge" \
+          --project-version "${COMMIT_HASH}" \
+          --branch "${REF_NAME}" \
+          --commit-date "${COMMIT_DATE}" \
+          --bench-date "${BENCH_DATE}" \
+          --walk-subdirs \
+          --name-suffix avx512
+        env:
+          REF_NAME: ${{ github.ref_name }}
+
+      - name: Parse swap request PBS counts
+        run: |
+          python3 ./ci/benchmark_parser.py tfhe-benchmark/dex_swap_request_pbs_count.csv "${RESULTS_FILENAME}" \
+          --object-sizes \
+          --append-results
+
+      - name: Parse swap claim PBS counts
+        run: |
+          python3 ./ci/benchmark_parser.py tfhe-benchmark/dex_swap_claim_pbs_count.csv "${RESULTS_FILENAME}" \
+          --object-sizes \
+          --append-results
+
+      - name: Upload parsed results artifact
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02
+        with:
+          name: ${{ github.sha }}_dex
+          path: ${{ env.RESULTS_FILENAME }}
+
       - name: Send data to Slab
         shell: bash
         run: |
-          python3 slab/scripts/data_sender.py ${{ env.RESULTS_FILENAME }} "${{ secrets.JOB_SECRET }}" \
+          python3 slab/scripts/data_sender.py "${RESULTS_FILENAME}" "${{ secrets.JOB_SECRET }}" \
           --slab-url "${{ secrets.SLAB_URL }}"
 
-  slack-notify:
-    name: Slack Notification
-    needs: [ setup-instance, cuda-core-crypto-benchmarks ]
-    runs-on: ubuntu-latest
-    if: ${{ !success() && !cancelled() }}
-    continue-on-error: true
-    steps:
-      - name: Send message
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+      - name: Slack Notification
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
+        continue-on-error: true
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         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 }})"
+          SLACK_COLOR: ${{ job.status }}
+          SLACK_MESSAGE: "DEX benchmarks finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
 
   teardown-instance:
-    name: Teardown instance (cuda-integer-full-benchmarks)
+    name: Teardown instance (dex-benchmarks)
     if: ${{ always() && needs.setup-instance.result == 'success' }}
-    needs: [ setup-instance, cuda-core-crypto-benchmarks, slack-notify ]
+    needs: [ setup-instance, dex-benchmarks ]
     runs-on: ubuntu-latest
     steps:
       - name: Stop instance
@@ -145,7 +146,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "Instance teardown (cuda-core-crypto-benchmarks) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Instance teardown (dex-benchmarks) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/benchmark_erc20.yml

@@ -18,6 +18,9 @@ env:
   SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
   SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
 
+
+permissions: {}
+
 jobs:
   setup-instance:
     name: Setup instance (erc20-benchmarks)
@@ -43,9 +46,8 @@ jobs:
     needs: setup-instance
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     concurrency:
-      group: ${{ github.workflow }}_${{ github.ref }}
+      group: ${{ github.workflow_ref }}
       cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
-    continue-on-error: true
     timeout-minutes: 720  # 12 hours
     steps:
       - name: Checkout tfhe-rs repo with tags
@@ -64,7 +66,7 @@ jobs:
           } >> "${GITHUB_ENV}"
 
       - name: Install rust
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: nightly
 
@@ -82,24 +84,26 @@ jobs:
 
       - name: Parse results
         run: |
-          python3 ./ci/benchmark_parser.py target/criterion ${{ env.RESULTS_FILENAME }} \
+          python3 ./ci/benchmark_parser.py target/criterion "${RESULTS_FILENAME}" \
           --database tfhe_rs \
           --hardware "hpc7a.96xlarge" \
-          --project-version "${{ env.COMMIT_HASH }}" \
-          --branch ${{ github.ref_name }} \
-          --commit-date "${{ env.COMMIT_DATE }}" \
-          --bench-date "${{ env.BENCH_DATE }}" \
+          --project-version "${COMMIT_HASH}" \
+          --branch "${REF_NAME}" \
+          --commit-date "${COMMIT_DATE}" \
+          --bench-date "${BENCH_DATE}" \
           --walk-subdirs \
           --name-suffix avx512
+        env:
+          REF_NAME: ${{ github.ref_name }}
 
       - name: Parse PBS counts
         run: |
-          python3 ./ci/benchmark_parser.py tfhe/erc20_pbs_count.csv ${{ env.RESULTS_FILENAME }} \
+          python3 ./ci/benchmark_parser.py tfhe-benchmark/erc20_pbs_count.csv "${RESULTS_FILENAME}" \
           --object-sizes \
           --append-results
 
       - name: Upload parsed results artifact
-        uses: actions/upload-artifact@65c4c4a1ddee5b72f698fdd19549f0f0fb45cf08
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02
         with:
           name: ${{ github.sha }}_erc20
           path: ${{ env.RESULTS_FILENAME }}
@@ -107,13 +111,13 @@ jobs:
       - name: Send data to Slab
         shell: bash
         run: |
-          python3 slab/scripts/data_sender.py ${{ env.RESULTS_FILENAME }} "${{ secrets.JOB_SECRET }}" \
+          python3 slab/scripts/data_sender.py "${RESULTS_FILENAME}" "${{ secrets.JOB_SECRET }}" \
           --slab-url "${{ secrets.SLAB_URL }}"
 
       - name: Slack Notification
-        if: ${{ failure() }}
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "ERC20 benchmarks finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
@@ -137,7 +141,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Instance teardown (erc20-benchmarks) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/benchmark_gpu.yml

@@ -10,13 +10,14 @@ on:
         type: choice
         options:
           - "l40 (n3-L40x1)"
+          - "4-l40 (n3-L40x4)"
+          - "multi-a100-nvlink (n3-A100x8-NVLink)"
           - "single-h100 (n3-H100x1)"
           - "2-h100 (n3-H100x2)"
           - "4-h100 (n3-H100x4)"
           - "multi-h100 (n3-H100x8)"
           - "multi-h100-nvlink (n3-H100x8-NVLink)"
           - "multi-h100-sxm5 (n3-H100x8-SXM5)"
-          - "multi-a100-nvlink (n3-A100x8-NVLink)"
       command:
         description: "Benchmark command to run"
         type: choice
@@ -26,7 +27,10 @@ on:
           - integer_multi_bit
           - integer_compression
           - pbs
+          - pbs128
           - ks
+          - ks_pbs
+          - integer_zk
       op_flavor:
         description: "Operations set to run"
         type: choice
@@ -47,6 +51,17 @@ on:
           - latency
           - throughput
           - both
+      params_type:
+        description: "Parameters type"
+        type: choice
+        default: multi_bit
+        options:
+          - classical
+          - multi_bit
+          - both
+
+
+permissions: {}
 
 jobs:
   parse-inputs:
@@ -54,26 +69,43 @@ jobs:
     outputs:
       profile: ${{ steps.parse_profile.outputs.profile }}
       hardware_name: ${{ steps.parse_hardware_name.outputs.name }}
+    env:
+      INPUTS_PROFILE: ${{ inputs.profile }}
     steps:
       - name: Parse profile
         id: parse_profile
         run: |
-          echo "profile=$(echo '${{ inputs.profile }}' | sed 's|\(.*\)[[:space:]](.*)|\1|')" >> "${GITHUB_OUTPUT}"
+          # Use Sed to extract a value from a string, this cannot be done with the ${variable//search/replace} pattern.
+          # shellcheck disable=SC2001
+          PROFILE=$(echo "${INPUTS_PROFILE}" | sed 's|\(.*\)[[:space:]](.*)|\1|')
+          echo "profile=${PROFILE}" >> "${GITHUB_OUTPUT}"
 
       - name: Parse hardware name
         id: parse_hardware_name
         run: |
-          echo "name=$(echo '${{ inputs.profile }}' | sed 's|.*[[:space:]](\(.*\))|\1|')" >> "${GITHUB_OUTPUT}"
+          # Use Sed to extract a value from a string, this cannot be done with the ${variable//search/replace} pattern.
+          # shellcheck disable=SC2001
+          NAME=$(echo "${INPUTS_PROFILE}" | sed 's|.*[[:space:]](\(.*\))|\1|')
+          echo "name=${NAME}" >> "${GITHUB_OUTPUT}"
 
   run-benchmarks:
     name: Run benchmarks
     needs: parse-inputs
-    uses: ./.github/workflows/benchmark_gpu_integer_common.yml
+    uses: ./.github/workflows/benchmark_gpu_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 }}
+      params_type: ${{ inputs.params_type }}
       all_precisions: ${{ inputs.all_precisions }}
-    secrets: inherit
+    secrets:
+      BOT_USERNAME: ${{ secrets.BOT_USERNAME }}
+      SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
+      SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+      REPO_CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN }}
+      JOB_SECRET: ${{ secrets.JOB_SECRET }}
+      SLAB_ACTION_TOKEN: ${{ secrets.SLAB_ACTION_TOKEN }}
+      SLAB_URL: ${{ secrets.SLAB_URL }}
+      SLAB_BASE_URL: ${{ secrets.SLAB_BASE_URL }}

.github/workflows/benchmark_gpu_4090.yml

@@ -22,6 +22,9 @@ on:
     # Weekly benchmarks will be triggered each Friday at 9p.m.
     - cron: "0 21 * * 5"
 
+permissions:
+  contents: read
+
 jobs:
   cuda-integer-benchmarks:
     name: Cuda integer benchmarks (RTX 4090)
@@ -29,7 +32,7 @@ jobs:
       github.event_name == 'schedule' && github.repository == 'zama-ai/tfhe-rs' ||
       contains(github.event.label.name, '4090_bench') }}
     concurrency:
-      group: ${{ github.workflow }}_${{ github.ref }}_cuda_integer_bench
+      group: ${{ github.workflow_ref }}_cuda_integer_bench
       cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
     runs-on: ["self-hosted", "4090-desktop"]
     timeout-minutes: 1440 # 24 hours
@@ -51,7 +54,7 @@ jobs:
           echo "FAST_BENCH=TRUE" >> "${GITHUB_ENV}"
 
       - name: Install rust
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: nightly
 
@@ -69,18 +72,20 @@ jobs:
 
       - name: Parse results
         run: |
-          python3 ./ci/benchmark_parser.py target/criterion ${{ env.RESULTS_FILENAME }} \
+          python3 ./ci/benchmark_parser.py target/criterion "${RESULTS_FILENAME}" \
           --database tfhe_rs \
           --hardware "rtx4090" \
           --backend gpu \
-          --project-version "${{ env.COMMIT_HASH }}" \
-          --branch ${{ github.ref_name }} \
-          --commit-date "${{ env.COMMIT_DATE }}" \
-          --bench-date "${{ env.BENCH_DATE }}" \
+          --project-version "${COMMIT_HASH}" \
+          --branch "${REF_NAME}" \
+          --commit-date "${COMMIT_DATE}" \
+          --bench-date "${BENCH_DATE}" \
           --walk-subdirs
+        env:
+          REF_NAME: ${{ github.ref_name }}
 
       - name: Upload parsed results artifact
-        uses: actions/upload-artifact@65c4c4a1ddee5b72f698fdd19549f0f0fb45cf08
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02
         with:
           name: ${{ github.sha }}_integer_multi_bit_gpu_default
           path: ${{ env.RESULTS_FILENAME }}
@@ -88,23 +93,23 @@ jobs:
       - name: Send data to Slab
         shell: bash
         run: |
-          python3 slab/scripts/data_sender.py ${{ env.RESULTS_FILENAME }} "${{ secrets.JOB_SECRET }}" \
+          python3 slab/scripts/data_sender.py "${RESULTS_FILENAME}" "${{ secrets.JOB_SECRET }}" \
           --slab-url "${{ secrets.SLAB_URL }}"
 
       - name: Slack Notification
-        if: ${{ failure() }}
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "Integer RTX 4090 full benchmarks finished with status: ${{ job.status }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Integer RTX 4090 full benchmarks finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
 
   cuda-core-crypto-benchmarks:
     name: Cuda core crypto benchmarks  (RTX 4090)
     if: ${{ github.event_name == 'workflow_dispatch' || github.event_name == 'schedule' || contains(github.event.label.name, '4090_bench') }}
     needs: cuda-integer-benchmarks
     concurrency:
-      group: ${{ github.workflow }}_${{ github.ref }}_cuda_core_crypto_bench
+      group: ${{ github.workflow_ref }}_cuda_core_crypto_bench
       cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
     runs-on: ["self-hosted", "4090-desktop"]
     timeout-minutes: 1440 # 24 hours
@@ -126,7 +131,7 @@ jobs:
           } >> "${GITHUB_ENV}"
 
       - name: Install rust
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: nightly
 
@@ -145,19 +150,19 @@ jobs:
 
       - name: Parse results
         run: |
-          python3 ./ci/benchmark_parser.py target/criterion ${{ env.RESULTS_FILENAME }} \
+          python3 ./ci/benchmark_parser.py target/criterion "${RESULTS_FILENAME}" \
           --database tfhe_rs \
           --hardware "rtx4090" \
           --backend gpu \
-          --project-version "${{ env.COMMIT_HASH }}" \
-          --branch ${{ github.ref_name }} \
-          --commit-date "${{ env.COMMIT_DATE }}" \
-          --bench-date "${{ env.BENCH_DATE }}" \
+          --project-version "${COMMIT_HASH}" \
+          --branch "${REF_NAME}" \
+          --commit-date "${COMMIT_DATE}" \
+          --bench-date "${BENCH_DATE}" \
           --walk-subdirs \
       
 
       - name: Upload parsed results artifact
-        uses: actions/upload-artifact@65c4c4a1ddee5b72f698fdd19549f0f0fb45cf08
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02
         with:
           name: ${{ github.sha }}_core_crypto
           path: ${{ env.RESULTS_FILENAME }}
@@ -165,24 +170,16 @@ jobs:
       - name: Send data to Slab
         shell: bash
         run: |
-          echo "Computing HMac on results file"
-          SIGNATURE="$(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 }} \
-          ${{ secrets.SLAB_URL }}
+          python3 slab/scripts/data_sender.py "${RESULTS_FILENAME}" "${{ secrets.JOB_SECRET }}" \
+          --slab-url "${{ secrets.SLAB_URL }}"
 
       - name: Slack Notification
-        if: ${{ failure() }}
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "Core crypto RTX 4090 full benchmarks finished with status: ${{ job.status }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Core crypto RTX 4090 full benchmarks finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
 
   remove_github_label:
     name: Remove 4090 bench label

.github/workflows/benchmark_gpu_common.yml

@@ -1,4 +1,4 @@
-# Run integer benchmarks on CUDA instance and return parsed results to Slab CI bot.
+# Run benchmarks on CUDA instance and return parsed results to Slab CI bot.
 name: Cuda benchmarks - common
 
 on:
@@ -18,10 +18,13 @@ on:
         required: true
       op_flavor: # Use a comma separated values to generate an array
         type: string
-        required: true
+        default: default
       bench_type:
         type: string
         default: latency
+      params_type:
+        type: string
+        default: multi_bit
       all_precisions:
         type: boolean
         default: false
@@ -55,6 +58,9 @@ env:
   SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
   FAST_BENCH: TRUE
 
+
+permissions: {}
+
 jobs:
   prepare-matrix:
     name: Prepare operations matrix
@@ -63,36 +69,57 @@ jobs:
       command: ${{ steps.set_command.outputs.command }}
       op_flavor: ${{ steps.set_op_flavor.outputs.op_flavor }}
       bench_type: ${{ steps.set_bench_type.outputs.bench_type }}
+      params_type: ${{ steps.set_params_type.outputs.params_type }}
+    env:
+      INPUTS_COMMAND: ${{ inputs.command }}
+      INPUTS_OP_FLAVOR: ${{ inputs.op_flavor }}
     steps:
       - name: Set single command
         if: ${{ !contains(inputs.command, ',')}}
         run: |
-          echo "COMMAND=[\"${{ inputs.command }}\"]" >> "${GITHUB_ENV}"
+          echo "COMMAND=[\"${INPUTS_COMMAND}\"]" >> "${GITHUB_ENV}"
 
       - name: Set multiple commands
         if: ${{ contains(inputs.command, ',')}}
         run: |
-          PARSED_COMMAND=$(echo "${{ inputs.command }}" | sed 's/[[:space:]]*,[[:space:]]*/\\", \\"/g')
+          # Use Sed to extract a value from a string, this cannot be done with the ${variable//search/replace} pattern.
+          # shellcheck disable=SC2001
+          PARSED_COMMAND=$(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 }}\"]" >> "${GITHUB_ENV}"
+          echo "OP_FLAVOR=[\"${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')
+          # Use Sed to extract a value from a string, this cannot be done with the ${variable//search/replace} pattern.
+          # shellcheck disable=SC2001
+          PARSED_OP_FLAVOR=$(echo "${INPUTS_OP_FLAVOR}" | sed 's/[[:space:]]*,[[:space:]]*/", "/g')
           echo "OP_FLAVOR=[\"${PARSED_OP_FLAVOR}\"]" >> "${GITHUB_ENV}"
 
       - name: Set benchmark types
         run: |
-          if [[ "${{ inputs.bench_type }}" == "both" ]]; then
+          if [[ "${INPUTS_BENCH_TYPE}" == "both" ]]; then
             echo "BENCH_TYPE=[\"latency\", \"throughput\"]" >> "${GITHUB_ENV}"
           else
-            echo "BENCH_TYPE=[\"${{ inputs.bench_type }}\"]" >> "${GITHUB_ENV}"
+            echo "BENCH_TYPE=[\"${INPUTS_BENCH_TYPE}\"]" >> "${GITHUB_ENV}"
           fi
+        env:
+          INPUTS_BENCH_TYPE: ${{ inputs.bench_type }}
+
+      - name: Set parameters types
+        run: |
+          if [[ "${INPUTS_PARAMS_TYPE}" == "both" ]]; then
+            echo "PARAMS_TYPE=[\"classical\", \"multi_bit\"]" >> "${GITHUB_ENV}"
+          else
+            echo "PARAMS_TYPE=[\"${INPUTS_PARAMS_TYPE}\"]" >> "${GITHUB_ENV}"
+          fi
+        env:
+          INPUTS_PARAMS_TYPE: ${{ inputs.params_type }}
+
 
       - name: Set command output
         id: set_command
@@ -109,15 +136,26 @@ jobs:
         run: |
           echo "bench_type=${{ toJSON(env.BENCH_TYPE) }}" >> "${GITHUB_OUTPUT}"
 
+      - name: Set parameters types output
+        id: set_params_type
+        run: |
+          echo "params_type=${{ toJSON(env.PARAMS_TYPE) }}" >> "${GITHUB_OUTPUT}"
+
   setup-instance:
     name: Setup instance (cuda-${{ inputs.profile }}-benchmarks)
     needs: prepare-matrix
     runs-on: ubuntu-latest
     outputs:
-      runner-name: ${{ steps.start-instance.outputs.label }}
+      # Use permanent remote instance label first as on-demand remote instance label output is set before the end of start-remote-instance step.
+      # If the latter fails due to a failed GitHub action runner set up, we have to fallback on the permanent instance.
+      # Since the on-demand remote label is set before failure, we have to do the logical OR in this order,
+      # otherwise we'll try to run the next job on a non-existing on-demand instance.
+      runner-name: ${{ steps.use-permanent-instance.outputs.runner_group || steps.start-remote-instance.outputs.label }}
+      remote-instance-outcome: ${{ steps.start-remote-instance.outcome }}
     steps:
-      - name: Start instance
-        id: start-instance
+      - name: Start remote instance
+        id: start-remote-instance
+        continue-on-error: true
         uses: zama-ai/slab-github-runner@79939325c3c429837c10d6041e4fd8589d328bac
         with:
           mode: start
@@ -127,12 +165,56 @@ jobs:
           backend: ${{ inputs.backend }}
           profile: ${{ inputs.profile }}
 
+      - name: Acknowledge remote instance failure
+        if: steps.start-remote-instance.outcome == 'failure' &&
+          inputs.profile != 'single-h100'
+        run: |
+          echo "Remote instance instance has failed to start (profile provided: '${INPUTS_PROFILE}')"
+          echo "Permanent instance instance cannot be used as a substitute (profile needed: 'single-h100')"
+          exit 1
+        env:
+          INPUTS_PROFILE: ${{ inputs.profile }}
+
+      # This will allow to fallback on permanent instances running on Hyperstack.
+      - name: Use permanent remote instance
+        id: use-permanent-instance
+        if: env.SECRETS_AVAILABLE == 'true' &&
+          steps.start-remote-instance.outcome == 'failure' &&
+          inputs.profile == 'single-h100'
+        run: |
+          echo "runner_group=h100x1" >> "$GITHUB_OUTPUT"
+
+  # Install dependencies only once since cuda-benchmarks uses a matrix strategy, thus running multiple times.
+  install-dependencies:
+    name: Install dependencies
+    needs: [ setup-instance ]
+    runs-on: ${{ needs.setup-instance.outputs.runner-name }}
+    strategy:
+      matrix:
+        # explicit include-based build matrix, of known valid options
+        include:
+          - cuda: "12.2"
+            gcc: 11
+    steps:
+      - name: Checkout tfhe-rs repo
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          fetch-depth: 0
+          persist-credentials: 'false'
+          token: ${{ secrets.REPO_CHECKOUT_TOKEN }}
+
+      - name: Setup Hyperstack dependencies
+        if: needs.setup-instance.outputs.remote-instance-outcome == 'success'
+        uses: ./.github/actions/gpu_setup
+        with:
+          cuda-version: ${{ matrix.cuda }}
+          gcc-version: ${{ matrix.gcc }}
+
   cuda-benchmarks:
     name: Cuda benchmarks (${{ inputs.profile }})
-    needs: [ prepare-matrix, setup-instance ]
+    needs: [ prepare-matrix, setup-instance, install-dependencies ]
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     timeout-minutes: 1440 # 24 hours
-    continue-on-error: true
     strategy:
       fail-fast: false
       max-parallel: 1
@@ -140,10 +222,10 @@ jobs:
         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) }}
+        params_type: ${{ fromJSON(needs.prepare-matrix.outputs.params_type) }}
         # explicit include-based build matrix, of known valid options
         include:
-          - os: ubuntu-22.04
-            cuda: "12.2"
+          - cuda: "12.2"
             gcc: 11
     steps:
       - name: Checkout tfhe-rs repo with tags
@@ -153,12 +235,6 @@ jobs:
           persist-credentials: 'false'
           token: ${{ secrets.REPO_CHECKOUT_TOKEN }}
 
-      - name: Setup Hyperstack dependencies
-        uses: ./.github/actions/gpu_setup
-        with:
-          cuda-version: ${{ matrix.cuda }}
-          gcc-version: ${{ matrix.gcc }}
-
       - name: Get benchmark details
         run: |
           {
@@ -167,8 +243,28 @@ jobs:
             echo "COMMIT_HASH=$(git describe --tags --dirty)";
           } >> "${GITHUB_ENV}"
 
+      # Re-export environment variables as dependencies setup perform this task in the previous job.
+      # Local env variables are cleaned at the end of each job.
+      - name: Export CUDA variables
+        shell: bash
+        run: |
+          CUDA_PATH=/usr/local/cuda-${{ matrix.cuda }}
+          echo "CUDA_PATH=$CUDA_PATH" >> "${GITHUB_ENV}"
+          echo "PATH=$PATH:$CUDA_PATH/bin" >> "${GITHUB_PATH}"
+          echo "LD_LIBRARY_PATH=$CUDA_PATH/lib64:$LD_LIBRARY_PATH" >> "${GITHUB_ENV}"
+          echo "CUDA_MODULE_LOADER=EAGER" >> "${GITHUB_ENV}"
+
+      - name: Export gcc and g++ variables
+        shell: bash
+        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: Install rust
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: nightly
 
@@ -179,26 +275,35 @@ jobs:
 
       - name: Run benchmarks
         run: |
-          make BENCH_OP_FLAVOR=${{ matrix.op_flavor }} BENCH_TYPE=${{ matrix.bench_type }} bench_${{ matrix.command }}_gpu
+          make BENCH_OP_FLAVOR="${OP_FLAVOR}" BENCH_TYPE="${BENCH_TYPE}" BENCH_PARAM_TYPE="${BENCH_PARAMS_TYPE}" bench_"${BENCH_COMMAND}"_gpu
+        env:
+          OP_FLAVOR: ${{ matrix.op_flavor }}
+          BENCH_TYPE: ${{ matrix.bench_type }}
+          BENCH_PARAMS_TYPE: ${{ matrix.params_type }}
+          BENCH_COMMAND: ${{ matrix.command }}
 
       - name: Parse results
         run: |
-          python3 ./ci/benchmark_parser.py target/criterion ${{ env.RESULTS_FILENAME }} \
+          python3 ./ci/benchmark_parser.py target/criterion "${RESULTS_FILENAME}" \
           --database tfhe_rs \
-          --hardware "${{ inputs.hardware_name }}" \
+          --hardware "${INPUTS_HARDWARE_NAME}" \
           --backend gpu \
-          --project-version "${{ env.COMMIT_HASH }}" \
-          --branch ${{ github.ref_name }} \
-          --commit-date "${{ env.COMMIT_DATE }}" \
-          --bench-date "${{ env.BENCH_DATE }}" \
+          --project-version "${COMMIT_HASH}" \
+          --branch "${REF_NAME}" \
+          --commit-date "${COMMIT_DATE}" \
+          --bench-date "${BENCH_DATE}" \
           --walk-subdirs \
           --name-suffix avx512 \
-          --bench-type ${{ matrix.bench_type }}
+          --bench-type "${BENCH_TYPE}"
+        env:
+          INPUTS_HARDWARE_NAME: ${{ inputs.hardware_name }}
+          REF_NAME: ${{ github.ref_name }}
+          BENCH_TYPE: ${{ matrix.bench_type }}
 
       - name: Upload parsed results artifact
-        uses: actions/upload-artifact@65c4c4a1ddee5b72f698fdd19549f0f0fb45cf08
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02
         with:
-          name: ${{ github.sha }}_${{ matrix.command }}_${{ matrix.op_flavor }}_${{ inputs.profile }}
+          name: ${{ github.sha }}_${{ matrix.command }}_${{ matrix.op_flavor }}_${{ inputs.profile }}_${{ matrix.bench_type }}_${{ matrix.params_type }}
           path: ${{ env.RESULTS_FILENAME }}
 
       - name: Checkout Slab repo
@@ -212,7 +317,7 @@ jobs:
       - name: Send data to Slab
         shell: bash
         run: |
-          python3 slab/scripts/data_sender.py ${{ env.RESULTS_FILENAME }} "${{ secrets.JOB_SECRET }}" \
+          python3 slab/scripts/data_sender.py "${RESULTS_FILENAME}" "${{ secrets.JOB_SECRET }}" \
           --slab-url "${{ secrets.SLAB_URL }}"
 
   slack-notify:
@@ -223,14 +328,14 @@ jobs:
     continue-on-error: true
     steps:
       - name: Send message
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           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-${{ inputs.profile }}-benchmarks)
-    if: ${{ always() && needs.setup-instance.result == 'success' }}
+    if: ${{ always() && needs.setup-instance.outputs.remote-instance-outcome == 'success' }}
     needs: [ setup-instance, cuda-benchmarks, slack-notify ]
     runs-on: ubuntu-latest
     steps:
@@ -247,7 +352,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Instance teardown (cuda-${{ inputs.profile }}-benchmarks) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/benchmark_gpu_dex.yml

@@ -0,0 +1,64 @@
+# Run CUDA DEX benchmarks on a Hyperstack VM and return parsed results to Slab CI bot.
+name: Cuda DEX benchmarks
+
+on:
+  workflow_dispatch:
+    inputs:
+      profile:
+        description: "Instance type"
+        required: true
+        type: choice
+        options:
+          - "l40 (n3-L40x1)"
+          - "4-l40 (n3-L40x4)"
+          - "multi-a100-nvlink (n3-A100x8-NVLink)"
+          - "single-h100 (n3-H100x1)"
+          - "2-h100 (n3-H100x2)"
+          - "4-h100 (n3-H100x4)"
+          - "multi-h100 (n3-H100x8)"
+          - "multi-h100-nvlink (n3-H100x8-NVLink)"
+          - "multi-h100-sxm5 (n3-H100x8-SXM5)"
+
+permissions: {}
+
+jobs:
+  parse-inputs:
+    runs-on: ubuntu-latest
+    outputs:
+      profile: ${{ steps.parse_profile.outputs.profile }}
+      hardware_name: ${{ steps.parse_hardware_name.outputs.name }}
+    env:
+      INPUTS_PROFILE: ${{ inputs.profile }}
+    steps:
+      - name: Parse profile
+        id: parse_profile
+        run: |
+          # Use Sed to extract a value from a string, this cannot be done with the ${variable//search/replace} pattern.
+          # shellcheck disable=SC2001
+          PROFILE=$(echo "${INPUTS_PROFILE}" | sed 's|\(.*\)[[:space:]](.*)|\1|')
+          echo "profile=${PROFILE}" >> "${GITHUB_OUTPUT}"
+
+      - name: Parse hardware name
+        id: parse_hardware_name
+        run: |
+          # Use Sed to extract a value from a string, this cannot be done with the ${variable//search/replace} pattern.
+          # shellcheck disable=SC2001
+          NAME=$(echo "${INPUTS_PROFILE}" | sed 's|.*[[:space:]](\(.*\))|\1|')
+          echo "name=${NAME}" >> "${GITHUB_OUTPUT}"
+
+  run-benchmarks:
+    name: Run benchmarks
+    needs: parse-inputs
+    uses: ./.github/workflows/benchmark_gpu_dex_common.yml
+    with:
+      profile: ${{ needs.parse-inputs.outputs.profile }}
+      hardware_name: ${{ needs.parse-inputs.outputs.hardware_name }}
+    secrets:
+      BOT_USERNAME: ${{ secrets.BOT_USERNAME }}
+      SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
+      SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+      REPO_CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN }}
+      JOB_SECRET: ${{ secrets.JOB_SECRET }}
+      SLAB_ACTION_TOKEN: ${{ secrets.SLAB_ACTION_TOKEN }}
+      SLAB_URL: ${{ secrets.SLAB_URL }}
+      SLAB_BASE_URL: ${{ secrets.SLAB_BASE_URL }}

.github/workflows/benchmark_gpu_dex_common.yml

@@ -0,0 +1,208 @@
+# Run DEX benchmarks on an instance with CUDA and return parsed results to Slab CI bot.
+name: Cuda DEX benchmarks - common
+
+on:
+  workflow_call:
+    inputs:
+      backend:
+        type: string
+        default: hyperstack
+      profile:
+        type: string
+        required: true
+      hardware_name:
+        type: string
+        required: true
+    secrets:
+      REPO_CHECKOUT_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"
+  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 }}
+
+permissions: {}
+
+jobs:
+  setup-instance:
+    name: Setup instance (cuda-dex-benchmarks)
+    runs-on: ubuntu-latest
+    if:  github.event_name == 'workflow_dispatch' ||
+      (github.event_name == 'schedule' && github.repository == 'zama-ai/tfhe-rs')
+    outputs:
+      # Use permanent remote instance label first as on-demand remote instance label output is set before the end of start-remote-instance step.
+      # If the latter fails due to a failed GitHub action runner set up, we have to fallback on the permanent instance.
+      # Since the on-demand remote label is set before failure, we have to do the logical OR in this order,
+      # otherwise we'll try to run the next job on a non-existing on-demand instance.
+      runner-name: ${{ steps.use-permanent-instance.outputs.runner_group || steps.start-remote-instance.outputs.label }}
+      remote-instance-outcome: ${{ steps.start-remote-instance.outcome }}
+    steps:
+      - name: Start remote instance
+        id: start-remote-instance
+        continue-on-error: true
+        uses: zama-ai/slab-github-runner@79939325c3c429837c10d6041e4fd8589d328bac
+        with:
+          mode: start
+          github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
+          slab-url: ${{ secrets.SLAB_BASE_URL }}
+          job-secret: ${{ secrets.JOB_SECRET }}
+          backend: ${{ inputs.backend }}
+          profile: ${{ inputs.profile }}
+
+      - name: Acknowledge remote instance failure
+        if: steps.start-remote-instance.outcome == 'failure' &&
+          inputs.profile != 'single-h100'
+        run: |
+          echo "Remote instance instance has failed to start (profile provided: '${INPUTS_PROFILE}')"
+          echo "Permanent instance instance cannot be used as a substitute (profile needed: 'single-h100')"
+          exit 1
+        env:
+          INPUTS_PROFILE: ${{ inputs.profile }}
+
+      # This will allow to fallback on permanent instances running on Hyperstack.
+      - name: Use permanent remote instance
+        id: use-permanent-instance
+        if: env.SECRETS_AVAILABLE == 'true' &&
+          steps.start-remote-instance.outcome == 'failure' &&
+          inputs.profile == 'single-h100'
+        run: |
+          echo "runner_group=h100x1" >> "$GITHUB_OUTPUT"
+
+  cuda-dex-benchmarks:
+    name: Cuda DEX benchmarks (${{ inputs.profile }})
+    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
+    steps:
+      - name: Checkout tfhe-rs repo with tags
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          fetch-depth: 0
+          persist-credentials: 'false'
+          token: ${{ secrets.REPO_CHECKOUT_TOKEN }}
+
+      - name: Setup Hyperstack dependencies
+        if: needs.setup-instance.outputs.remote-instance-outcome == 'success'
+        uses: ./.github/actions/gpu_setup
+        with:
+          cuda-version: ${{ matrix.cuda }}
+          gcc-version: ${{ matrix.gcc }}
+
+      - name: Get benchmark details
+        run: |
+          {
+            echo "BENCH_DATE=$(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)";
+          } >> "${GITHUB_ENV}"
+
+      - name: Install rust
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
+        with:
+          toolchain: nightly
+
+      - name: Run benchmarks
+        run: |
+          make bench_hlapi_dex_gpu
+
+      - name: Parse results
+        run: |
+          python3 ./ci/benchmark_parser.py target/criterion "${RESULTS_FILENAME}" \
+          --database tfhe_rs \
+          --hardware "${INPUTS_HARDWARE_NAME}" \
+          --backend gpu \
+          --project-version "${COMMIT_HASH}" \
+          --branch "${REF_NAME}" \
+          --commit-date "${COMMIT_DATE}" \
+          --bench-date "${BENCH_DATE}" \
+          --walk-subdirs \
+          --name-suffix avx512
+        env:
+          INPUTS_HARDWARE_NAME: ${{ inputs.hardware_name }}
+          REF_NAME: ${{ github.ref_name }}
+
+      - name: Upload parsed results artifact
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02
+        with:
+          name: ${{ github.sha }}_dex_${{ inputs.profile }}
+          path: ${{ env.RESULTS_FILENAME }}
+
+      - name: Checkout Slab repo
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          repository: zama-ai/slab
+          path: slab
+          persist-credentials: 'false'
+          token: ${{ secrets.REPO_CHECKOUT_TOKEN }}
+
+      - name: Send data to Slab
+        shell: bash
+        run: |
+          python3 slab/scripts/data_sender.py "${RESULTS_FILENAME}" "${{ secrets.JOB_SECRET }}" \
+          --slab-url "${{ secrets.SLAB_URL }}"
+
+  slack-notify:
+    name: Slack Notification
+    needs: [ setup-instance, cuda-dex-benchmarks ]
+    runs-on: ubuntu-latest
+    if: ${{ always() && needs.cuda-dex-benchmarks.result != 'skipped' && failure() }}
+    continue-on-error: true
+    steps:
+      - name: Send message
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
+        env:
+          SLACK_COLOR: ${{ needs.cuda-dex-benchmarks.result }}
+          SLACK_MESSAGE: "Cuda DEX benchmarks (${{ inputs.profile }}) finished with status: ${{ needs.cuda-dex-benchmarks.result }}. (${{ env.ACTION_RUN_URL }})"
+
+  teardown-instance:
+    name: Teardown instance (cuda-dex-${{ inputs.profile }}-benchmarks)
+    if: ${{ always() && needs.setup-instance.outputs.remote-instance-outcome == 'success' }}
+    needs: [ setup-instance, cuda-dex-benchmarks, slack-notify ]
+    runs-on: ubuntu-latest
+    steps:
+      - name: Stop instance
+        id: stop-instance
+        uses: zama-ai/slab-github-runner@79939325c3c429837c10d6041e4fd8589d328bac
+        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@e31e87e03dd19038e411e38ae27cbad084a90661
+        env:
+          SLACK_COLOR: ${{ job.status }}
+          SLACK_MESSAGE: "Instance teardown (cuda-dex-${{ inputs.profile }}-benchmarks) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/benchmark_gpu_dex_weekly.yml

@@ -0,0 +1,61 @@
+# Run CUDA DEX benchmarks on multiple Hyperstack VMs and return parsed results to Slab CI bot.
+name: Cuda DEX weekly benchmarks
+
+on:
+  schedule:
+    # Weekly benchmarks will be triggered each Saturday at 9a.m.
+    - cron: '0 9 * * 6'
+
+permissions: {}
+
+jobs:
+  run-benchmarks-1-h100:
+    name: Run benchmarks (1xH100)
+    if: github.repository == 'zama-ai/tfhe-rs'
+    uses: ./.github/workflows/benchmark_gpu_dex_common.yml
+    with:
+      profile: single-h100
+      hardware_name: n3-H100x1
+    secrets:
+      BOT_USERNAME: ${{ secrets.BOT_USERNAME }}
+      SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
+      SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+      REPO_CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN }}
+      JOB_SECRET: ${{ secrets.JOB_SECRET }}
+      SLAB_ACTION_TOKEN: ${{ secrets.SLAB_ACTION_TOKEN }}
+      SLAB_URL: ${{ secrets.SLAB_URL }}
+      SLAB_BASE_URL: ${{ secrets.SLAB_BASE_URL }}
+
+  run-benchmarks-2-h100:
+    name: Run benchmarks (2xH100)
+    if: github.repository == 'zama-ai/tfhe-rs'
+    uses: ./.github/workflows/benchmark_gpu_dex_common.yml
+    with:
+      profile: 2-h100
+      hardware_name: n3-H100x2
+    secrets:
+      BOT_USERNAME: ${{ secrets.BOT_USERNAME }}
+      SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
+      SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+      REPO_CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN }}
+      JOB_SECRET: ${{ secrets.JOB_SECRET }}
+      SLAB_ACTION_TOKEN: ${{ secrets.SLAB_ACTION_TOKEN }}
+      SLAB_URL: ${{ secrets.SLAB_URL }}
+      SLAB_BASE_URL: ${{ secrets.SLAB_BASE_URL }}
+
+  run-benchmarks-8-h100:
+    name: Run benchmarks (8xH100)
+    if: github.repository == 'zama-ai/tfhe-rs'
+    uses: ./.github/workflows/benchmark_gpu_dex_common.yml
+    with:
+      profile: multi-h100
+      hardware_name: n3-H100x8
+    secrets:
+      BOT_USERNAME: ${{ secrets.BOT_USERNAME }}
+      SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
+      SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+      REPO_CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN }}
+      JOB_SECRET: ${{ secrets.JOB_SECRET }}
+      SLAB_ACTION_TOKEN: ${{ secrets.SLAB_ACTION_TOKEN }}
+      SLAB_URL: ${{ secrets.SLAB_URL }}
+      SLAB_BASE_URL: ${{ secrets.SLAB_BASE_URL }}

.github/workflows/benchmark_gpu_erc20.yml

@@ -10,6 +10,8 @@ on:
         type: choice
         options:
           - "l40 (n3-L40x1)"
+          - "4-l40 (n3-L40x4)"
+          - "multi-a100-nvlink (n3-A100x8-NVLink)"
           - "single-h100 (n3-H100x1)"
           - "2-h100 (n3-H100x2)"
           - "4-h100 (n3-H100x4)"
@@ -17,22 +19,33 @@ on:
           - "multi-h100-nvlink (n3-H100x8-NVLink)"
           - "multi-h100-sxm5 (n3-H100x8-SXM5)"
 
+
+permissions: {}
+
 jobs:
   parse-inputs:
     runs-on: ubuntu-latest
     outputs:
       profile: ${{ steps.parse_profile.outputs.profile }}
       hardware_name: ${{ steps.parse_hardware_name.outputs.name }}
+    env:
+      INPUTS_PROFILE: ${{ inputs.profile }}
     steps:
       - name: Parse profile
         id: parse_profile
         run: |
-          echo "profile=$(echo '${{ inputs.profile }}' | sed 's|\(.*\)[[:space:]](.*)|\1|')" >> "${GITHUB_OUTPUT}"
+          # Use Sed to extract a value from a string, this cannot be done with the ${variable//search/replace} pattern.
+          # shellcheck disable=SC2001
+          PROFILE=$(echo "${INPUTS_PROFILE}" | sed 's|\(.*\)[[:space:]](.*)|\1|')
+          echo "profile=${PROFILE}" >> "${GITHUB_OUTPUT}"
 
       - name: Parse hardware name
         id: parse_hardware_name
         run: |
-          echo "name=$(echo '${{ inputs.profile }}' | sed 's|.*[[:space:]](\(.*\))|\1|')" >> "${GITHUB_OUTPUT}"
+          # Use Sed to extract a value from a string, this cannot be done with the ${variable//search/replace} pattern.
+          # shellcheck disable=SC2001
+          NAME=$(echo "${INPUTS_PROFILE}" | sed 's|.*[[:space:]](\(.*\))|\1|')
+          echo "name=${NAME}" >> "${GITHUB_OUTPUT}"
 
   run-benchmarks:
     name: Run benchmarks
@@ -41,4 +54,12 @@ jobs:
     with:
       profile: ${{ needs.parse-inputs.outputs.profile }}
       hardware_name: ${{ needs.parse-inputs.outputs.hardware_name }}
-    secrets: inherit
+    secrets:
+      BOT_USERNAME: ${{ secrets.BOT_USERNAME }}
+      SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
+      SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+      REPO_CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN }}
+      JOB_SECRET: ${{ secrets.JOB_SECRET }}
+      SLAB_ACTION_TOKEN: ${{ secrets.SLAB_ACTION_TOKEN }}
+      SLAB_URL: ${{ secrets.SLAB_URL }}
+      SLAB_BASE_URL: ${{ secrets.SLAB_BASE_URL }}

.github/workflows/benchmark_gpu_erc20_common.yml

@@ -43,6 +43,9 @@ env:
   SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
   SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
 
+
+permissions: {}
+
 jobs:
   setup-instance:
     name: Setup instance (cuda-erc20-benchmarks)
@@ -50,10 +53,16 @@ jobs:
     if:  github.event_name == 'workflow_dispatch' ||
       (github.event_name == 'schedule' && github.repository == 'zama-ai/tfhe-rs')
     outputs:
-      runner-name: ${{ steps.start-instance.outputs.label }}
+      # Use permanent remote instance label first as on-demand remote instance label output is set before the end of start-remote-instance step.
+      # If the latter fails due to a failed GitHub action runner set up, we have to fallback on the permanent instance.
+      # Since the on-demand remote label is set before failure, we have to do the logical OR in this order,
+      # otherwise we'll try to run the next job on a non-existing on-demand instance.
+      runner-name: ${{ steps.use-permanent-instance.outputs.runner_group || steps.start-remote-instance.outputs.label }}
+      remote-instance-outcome: ${{ steps.start-remote-instance.outcome }}
     steps:
-      - name: Start instance
-        id: start-instance
+      - name: Start remote instance
+        id: start-remote-instance
+        continue-on-error: true
         uses: zama-ai/slab-github-runner@79939325c3c429837c10d6041e4fd8589d328bac
         with:
           mode: start
@@ -63,6 +72,25 @@ jobs:
           backend: ${{ inputs.backend }}
           profile: ${{ inputs.profile }}
 
+      - name: Acknowledge remote instance failure
+        if: steps.start-remote-instance.outcome == 'failure' &&
+          inputs.profile != 'single-h100'
+        run: |
+          echo "Remote instance instance has failed to start (profile provided: '${INPUTS_PROFILE}')"
+          echo "Permanent instance instance cannot be used as a substitute (profile needed: 'single-h100')"
+          exit 1
+        env:
+          INPUTS_PROFILE: ${{ inputs.profile }}
+
+      # This will allow to fallback on permanent instances running on Hyperstack.
+      - name: Use permanent remote instance
+        id: use-permanent-instance
+        if: env.SECRETS_AVAILABLE == 'true' &&
+          steps.start-remote-instance.outcome == 'failure' &&
+          inputs.profile == 'single-h100'
+        run: |
+          echo "runner_group=h100x1" >> "$GITHUB_OUTPUT"
+
   cuda-erc20-benchmarks:
     name: Cuda ERC20 benchmarks (${{ inputs.profile }})
     needs: setup-instance
@@ -84,6 +112,7 @@ jobs:
           token: ${{ secrets.REPO_CHECKOUT_TOKEN }}
 
       - name: Setup Hyperstack dependencies
+        if: needs.setup-instance.outputs.remote-instance-outcome == 'success'
         uses: ./.github/actions/gpu_setup
         with:
           cuda-version: ${{ matrix.cuda }}
@@ -98,7 +127,7 @@ jobs:
           } >> "${GITHUB_ENV}"
 
       - name: Install rust
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: nightly
 
@@ -108,19 +137,22 @@ jobs:
 
       - name: Parse results
         run: |
-          python3 ./ci/benchmark_parser.py target/criterion ${{ env.RESULTS_FILENAME }} \
+          python3 ./ci/benchmark_parser.py target/criterion "${RESULTS_FILENAME}" \
           --database tfhe_rs \
-          --hardware "${{ inputs.hardware_name }}" \
+          --hardware "${INPUTS_HARDWARE_NAME}" \
           --backend gpu \
-          --project-version "${{ env.COMMIT_HASH }}" \
-          --branch ${{ github.ref_name }} \
-          --commit-date "${{ env.COMMIT_DATE }}" \
-          --bench-date "${{ env.BENCH_DATE }}" \
+          --project-version "${COMMIT_HASH}" \
+          --branch "${REF_NAME}" \
+          --commit-date "${COMMIT_DATE}" \
+          --bench-date "${BENCH_DATE}" \
           --walk-subdirs \
           --name-suffix avx512
+        env:
+          INPUTS_HARDWARE_NAME: ${{ inputs.hardware_name }}
+          REF_NAME: ${{ github.ref_name }}
 
       - name: Upload parsed results artifact
-        uses: actions/upload-artifact@65c4c4a1ddee5b72f698fdd19549f0f0fb45cf08
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02
         with:
           name: ${{ github.sha }}_erc20_${{ inputs.profile }}
           path: ${{ env.RESULTS_FILENAME }}
@@ -136,7 +168,7 @@ jobs:
       - name: Send data to Slab
         shell: bash
         run: |
-          python3 slab/scripts/data_sender.py ${{ env.RESULTS_FILENAME }} "${{ secrets.JOB_SECRET }}" \
+          python3 slab/scripts/data_sender.py "${RESULTS_FILENAME}" "${{ secrets.JOB_SECRET }}" \
           --slab-url "${{ secrets.SLAB_URL }}"
 
   slack-notify:
@@ -147,14 +179,14 @@ jobs:
     continue-on-error: true
     steps:
       - name: Send message
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           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-erc20-${{ inputs.profile }}-benchmarks)
-    if: ${{ always() && needs.setup-instance.result == 'success' }}
+    if: ${{ always() && needs.setup-instance.outputs.remote-instance-outcome == 'success' }}
     needs: [ setup-instance, cuda-erc20-benchmarks, slack-notify ]
     runs-on: ubuntu-latest
     steps:
@@ -171,7 +203,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Instance teardown (cuda-erc20-${{ inputs.profile }}-benchmarks) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/benchmark_gpu_erc20_weekly.yml

@@ -6,6 +6,9 @@ on:
     # Weekly benchmarks will be triggered each Saturday at 5a.m.
     - cron: '0 5 * * 6'
 
+
+permissions: {}
+
 jobs:
   run-benchmarks-1-h100:
     name: Run benchmarks (1xH100)
@@ -14,7 +17,15 @@ jobs:
     with:
       profile: single-h100
       hardware_name: n3-H100x1
-    secrets: inherit
+    secrets:
+      BOT_USERNAME: ${{ secrets.BOT_USERNAME }}
+      SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
+      SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+      REPO_CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN }}
+      JOB_SECRET: ${{ secrets.JOB_SECRET }}
+      SLAB_ACTION_TOKEN: ${{ secrets.SLAB_ACTION_TOKEN }}
+      SLAB_URL: ${{ secrets.SLAB_URL }}
+      SLAB_BASE_URL: ${{ secrets.SLAB_BASE_URL }}
 
   run-benchmarks-2-h100:
     name: Run benchmarks (2xH100)
@@ -23,7 +34,15 @@ jobs:
     with:
       profile: 2-h100
       hardware_name: n3-H100x2
-    secrets: inherit
+    secrets:
+      BOT_USERNAME: ${{ secrets.BOT_USERNAME }}
+      SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
+      SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+      REPO_CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN }}
+      JOB_SECRET: ${{ secrets.JOB_SECRET }}
+      SLAB_ACTION_TOKEN: ${{ secrets.SLAB_ACTION_TOKEN }}
+      SLAB_URL: ${{ secrets.SLAB_URL }}
+      SLAB_BASE_URL: ${{ secrets.SLAB_BASE_URL }}
 
   run-benchmarks-8-h100:
     name: Run benchmarks (8xH100)
@@ -32,4 +51,12 @@ jobs:
     with:
       profile: multi-h100
       hardware_name: n3-H100x8
-    secrets: inherit
+    secrets:
+      BOT_USERNAME: ${{ secrets.BOT_USERNAME }}
+      SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
+      SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+      REPO_CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN }}
+      JOB_SECRET: ${{ secrets.JOB_SECRET }}
+      SLAB_ACTION_TOKEN: ${{ secrets.SLAB_ACTION_TOKEN }}
+      SLAB_URL: ${{ secrets.SLAB_URL }}
+      SLAB_BASE_URL: ${{ secrets.SLAB_BASE_URL }}

.github/workflows/benchmark_gpu_integer_weekly.yml

@@ -1,60 +0,0 @@
-# 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_weekly.yml

@@ -0,0 +1,114 @@
+# 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'
+
+
+permissions: {}
+
+jobs:
+  run-benchmarks-1-h100:
+    name: Run integer benchmarks (1xH100)
+    if: github.repository == 'zama-ai/tfhe-rs'
+    uses: ./.github/workflows/benchmark_gpu_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:
+      BOT_USERNAME: ${{ secrets.BOT_USERNAME }}
+      SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
+      SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+      REPO_CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN }}
+      JOB_SECRET: ${{ secrets.JOB_SECRET }}
+      SLAB_ACTION_TOKEN: ${{ secrets.SLAB_ACTION_TOKEN }}
+      SLAB_URL: ${{ secrets.SLAB_URL }}
+      SLAB_BASE_URL: ${{ secrets.SLAB_BASE_URL }}
+
+  run-benchmarks-2-h100:
+    name: Run integer benchmarks (2xH100)
+    if: github.repository == 'zama-ai/tfhe-rs'
+    uses: ./.github/workflows/benchmark_gpu_common.yml
+    with:
+      profile: 2-h100
+      hardware_name: n3-H100x2
+      command: integer_multi_bit
+      op_flavor: default
+      bench_type: latency
+      all_precisions: true
+    secrets:
+      BOT_USERNAME: ${{ secrets.BOT_USERNAME }}
+      SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
+      SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+      REPO_CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN }}
+      JOB_SECRET: ${{ secrets.JOB_SECRET }}
+      SLAB_ACTION_TOKEN: ${{ secrets.SLAB_ACTION_TOKEN }}
+      SLAB_URL: ${{ secrets.SLAB_URL }}
+      SLAB_BASE_URL: ${{ secrets.SLAB_BASE_URL }}
+
+  run-benchmarks-8-h100:
+    name: Run integer benchmarks (8xH100)
+    if: github.repository == 'zama-ai/tfhe-rs'
+    uses: ./.github/workflows/benchmark_gpu_common.yml
+    with:
+      profile: multi-h100
+      hardware_name: n3-H100x8
+      command: integer_multi_bit
+      op_flavor: default
+      bench_type: latency
+      all_precisions: true
+    secrets:
+      BOT_USERNAME: ${{ secrets.BOT_USERNAME }}
+      SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
+      SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+      REPO_CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN }}
+      JOB_SECRET: ${{ secrets.JOB_SECRET }}
+      SLAB_ACTION_TOKEN: ${{ secrets.SLAB_ACTION_TOKEN }}
+      SLAB_URL: ${{ secrets.SLAB_URL }}
+      SLAB_BASE_URL: ${{ secrets.SLAB_BASE_URL }}
+
+  run-benchmarks-l40:
+    name: Run integer benchmarks (L40)
+    if: github.repository == 'zama-ai/tfhe-rs'
+    uses: ./.github/workflows/benchmark_gpu_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:
+      BOT_USERNAME: ${{ secrets.BOT_USERNAME }}
+      SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
+      SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+      REPO_CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN }}
+      JOB_SECRET: ${{ secrets.JOB_SECRET }}
+      SLAB_ACTION_TOKEN: ${{ secrets.SLAB_ACTION_TOKEN }}
+      SLAB_URL: ${{ secrets.SLAB_URL }}
+      SLAB_BASE_URL: ${{ secrets.SLAB_BASE_URL }}
+
+  run-benchmarks-1-h100-core-crypto:
+    name: Run core-crypto benchmarks (1xH100)
+    if: github.repository == 'zama-ai/tfhe-rs'
+    uses: ./.github/workflows/benchmark_gpu_common.yml
+    with:
+      profile: single-h100
+      hardware_name: n3-H100x1
+      command: pbs,pbs128,ks,ks_pbs
+      bench_type: latency
+    secrets:
+      BOT_USERNAME: ${{ secrets.BOT_USERNAME }}
+      SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
+      SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+      REPO_CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN }}
+      JOB_SECRET: ${{ secrets.JOB_SECRET }}
+      SLAB_ACTION_TOKEN: ${{ secrets.SLAB_ACTION_TOKEN }}
+      SLAB_URL: ${{ secrets.SLAB_URL }}
+      SLAB_BASE_URL: ${{ secrets.SLAB_BASE_URL }}

.github/workflows/benchmark_hpu_integer.yml

@@ -0,0 +1,88 @@
+# Run all integer benchmarks on a permanent HPU instance and return parsed results to Slab CI bot.
+name: Hpu Integer Benchmarks
+
+on:
+  workflow_dispatch:
+
+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"
+
+permissions: {}
+
+jobs:
+  integer-benchmarks-hpu:
+    name: Execute integer & erc20 benchmarks for HPU backend
+    runs-on: v80-desktop
+    concurrency:
+      group: ${{ github.workflow }}_${{ github.ref }}
+      cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
+    timeout-minutes: 1440  # 24 hours
+    steps:
+      # Needed as long as hw_regmap repository is private
+      - name: Configure SSH
+        uses: webfactory/ssh-agent@a6f90b1f127823b31d4d4a8d96047790581349bd # v0.9.1
+        with:
+          ssh-private-key: ${{ secrets.SSH_PRIVATE_KEY }}
+
+      - name: Checkout tfhe-rs repo with tags
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          fetch-depth: 0
+          persist-credentials: 'false'
+          token: ${{ secrets.REPO_CHECKOUT_TOKEN }}
+
+      - name: Get benchmark details
+        run: |
+          {
+            echo "BENCH_DATE=$(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@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
+        with:
+          toolchain: nightly
+
+      - name: Checkout Slab repo
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          repository: zama-ai/slab
+          path: slab
+          persist-credentials: 'false'
+          token: ${{ secrets.REPO_CHECKOUT_TOKEN }}
+
+      - name: Run benchmarks
+        run: |
+          make bench_integer_hpu
+          make bench_hlapi_erc20_hpu
+
+      - name: Parse results
+        run: |
+          python3 ./ci/benchmark_parser.py target/criterion "${RESULTS_FILENAME}" \
+          --database tfhe_rs \
+          --hardware "hpu_x1" \
+          --backend hpu \
+          --project-version "${COMMIT_HASH}" \
+          --branch "${REF_NAME}" \
+          --commit-date "${COMMIT_DATE}" \
+          --bench-date "${BENCH_DATE}" \
+          --walk-subdirs
+        env:
+          REF_NAME: ${{ github.ref_name }}
+
+      - name: Upload parsed results artifact
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02
+        with:
+          name: ${{ github.sha }}_integer_benchmarks
+          path: ${{ env.RESULTS_FILENAME }}
+
+      - name: Send data to Slab
+        shell: bash
+        run: |
+          python3 slab/scripts/data_sender.py "${RESULTS_FILENAME}" "${{ secrets.JOB_SECRET }}" \
+          --slab-url "${{ secrets.SLAB_URL }}"

.github/workflows/benchmark_integer.yml

@@ -36,6 +36,9 @@ env:
   SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
   FAST_BENCH: TRUE
 
+
+permissions: {}
+
 jobs:
   prepare-matrix:
     name: Prepare operations matrix
@@ -60,11 +63,13 @@ jobs:
         if: github.event_name == 'workflow_dispatch'
         run: |
           echo "OP_FLAVOR=[\"default\"]" >> "${GITHUB_ENV}"
-          if [[ "${{ inputs.bench_type }}" == "both" ]]; then
+          if [[ "${INPUTS_BENCH_TYPE}" == "both" ]]; then
             echo "BENCH_TYPE=[\"latency\", \"throughput\"]" >> "${GITHUB_ENV}"
           else
-            echo "BENCH_TYPE=[\"${{ inputs.bench_type }}\"]" >> "${GITHUB_ENV}"
+            echo "BENCH_TYPE=[\"${INPUTS_BENCH_TYPE}\"]" >> "${GITHUB_ENV}"
           fi
+        env:
+          INPUTS_BENCH_TYPE: ${{ inputs.bench_type }}
 
       - name: Default benchmark type
         if: github.event_name != 'workflow_dispatch'
@@ -104,9 +109,8 @@ jobs:
     needs: [ prepare-matrix, setup-instance ]
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     concurrency:
-      group: ${{ github.workflow }}_${{ github.ref }}
+      group: ${{ github.workflow_ref }}
       cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
-    continue-on-error: true
     timeout-minutes: 1440  # 24 hours
     strategy:
       max-parallel: 1
@@ -131,7 +135,7 @@ jobs:
           } >> "${GITHUB_ENV}"
 
       - name: Install rust
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: nightly
 
@@ -150,29 +154,38 @@ jobs:
 
       - name: Run benchmarks with AVX512
         run: |
-          make BENCH_OP_FLAVOR=${{ matrix.op_flavor }} BENCH_TYPE=${{ matrix.bench_type }} bench_${{ matrix.command }}
+          make BENCH_OP_FLAVOR="${OP_FLAVOR}" BENCH_TYPE="${BENCH_TYPE}" bench_"${BENCH_COMMAND}"
+        env:
+          OP_FLAVOR: ${{ matrix.op_flavor }}
+          BENCH_TYPE: ${{ matrix.bench_type }}
+          BENCH_COMMAND: ${{ matrix.command }}
 
       # 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_TYPE=${{ matrix.bench_type }} bench_integer_compression
+          make BENCH_TYPE="${BENCH_TYPE}" bench_integer_compression
+        env:
+          BENCH_TYPE: ${{ matrix.bench_type }}
 
       - name: Parse results
         run: |
-          python3 ./ci/benchmark_parser.py target/criterion ${{ env.RESULTS_FILENAME }} \
+          python3 ./ci/benchmark_parser.py target/criterion "${RESULTS_FILENAME}" \
           --database tfhe_rs \
           --hardware "hpc7a.96xlarge" \
-          --project-version "${{ env.COMMIT_HASH }}" \
-          --branch ${{ github.ref_name }} \
-          --commit-date "${{ env.COMMIT_DATE }}" \
-          --bench-date "${{ env.BENCH_DATE }}" \
+          --project-version "${COMMIT_HASH}" \
+          --branch "${REF_NAME}" \
+          --commit-date "${COMMIT_DATE}" \
+          --bench-date "${BENCH_DATE}" \
           --walk-subdirs \
           --name-suffix avx512 \
-          --bench-type ${{ matrix.bench_type }}
+          --bench-type "${BENCH_TYPE}"
+        env:
+          REF_NAME: ${{ github.ref_name }}
+          BENCH_TYPE: ${{ matrix.bench_type }}
 
       - name: Upload parsed results artifact
-        uses: actions/upload-artifact@65c4c4a1ddee5b72f698fdd19549f0f0fb45cf08
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02
         with:
           name: ${{ github.sha }}_${{ matrix.command }}_${{ matrix.op_flavor }}_${{ matrix.bench_type }}
           path: ${{ env.RESULTS_FILENAME }}
@@ -180,13 +193,13 @@ jobs:
       - name: Send data to Slab
         shell: bash
         run: |
-          python3 slab/scripts/data_sender.py ${{ env.RESULTS_FILENAME }} "${{ secrets.JOB_SECRET }}" \
+          python3 slab/scripts/data_sender.py "${RESULTS_FILENAME}" "${{ secrets.JOB_SECRET }}" \
           --slab-url "${{ secrets.SLAB_URL }}"
 
       - name: Slack Notification
-        if: ${{ failure() }}
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Integer full benchmarks finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
@@ -210,7 +223,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         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

@@ -22,6 +22,9 @@ env:
   SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
   SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
 
+
+permissions: {}
+
 jobs:
   prepare-matrix:
     name: Prepare operations matrix
@@ -70,9 +73,8 @@ jobs:
     needs: [ prepare-matrix, setup-instance ]
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     concurrency:
-      group: ${{ github.workflow }}_${{ github.ref }}
+      group: ${{ github.workflow_ref }}
       cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
-    continue-on-error: true
     strategy:
       max-parallel: 1
       matrix:
@@ -94,7 +96,7 @@ jobs:
           } >> "${GITHUB_ENV}"
 
       - name: Install rust
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: nightly
 
@@ -108,21 +110,23 @@ jobs:
 
       - name: Run benchmarks with AVX512
         run: |
-          make BENCH_OP_FLAVOR=${{ matrix.op_flavor }} bench_shortint
+          make BENCH_OP_FLAVOR="${OP_FLAVOR}" bench_shortint
+        env:
+          OP_FLAVOR: ${{ matrix.op_flavor }}
 
       - name: Parse results
         run: |
-          COMMIT_DATE="$(git --no-pager show -s --format=%cd --date=iso8601-strict ${{ github.sha }})"
-          COMMIT_HASH="$(git describe --tags --dirty)"
-          python3 ./ci/benchmark_parser.py target/criterion ${{ env.RESULTS_FILENAME }} \
+          python3 ./ci/benchmark_parser.py target/criterion "${RESULTS_FILENAME}" \
           --database tfhe_rs \
           --hardware "hpc7a.96xlarge" \
           --project-version "${COMMIT_HASH}" \
-          --branch ${{ github.ref_name }} \
+          --branch "${REF_NAME}" \
           --commit-date "${COMMIT_DATE}" \
-          --bench-date "${{ env.BENCH_DATE }}" \
+          --bench-date "${BENCH_DATE}" \
           --walk-subdirs \
           --name-suffix avx512
+        env:
+          REF_NAME: ${{ github.ref_name }}
 
       # This small benchmark needs to be executed only once.
       - name: Measure key sizes
@@ -133,12 +137,12 @@ jobs:
       - name: Parse key sizes results
         if: matrix.op_flavor == 'default'
         run: |
-          python3 ./ci/benchmark_parser.py tfhe/shortint_key_sizes.csv ${{ env.RESULTS_FILENAME }} \
+          python3 ./ci/benchmark_parser.py tfhe-benchmark/shortint_key_sizes.csv "${RESULTS_FILENAME}" \
           --object-sizes \
           --append-results
 
       - name: Upload parsed results artifact
-        uses: actions/upload-artifact@65c4c4a1ddee5b72f698fdd19549f0f0fb45cf08
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02
         with:
           name: ${{ github.sha }}_shortint_${{ matrix.op_flavor }}
           path: ${{ env.RESULTS_FILENAME }}
@@ -146,13 +150,13 @@ jobs:
       - name: Send data to Slab
         shell: bash
         run: |
-          python3 slab/scripts/data_sender.py ${{ env.RESULTS_FILENAME }} "${{ secrets.JOB_SECRET }}" \
+          python3 slab/scripts/data_sender.py "${RESULTS_FILENAME}" "${{ secrets.JOB_SECRET }}" \
           --slab-url "${{ secrets.SLAB_URL }}"
 
       - name: Slack Notification
-        if: ${{ failure() }}
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Shortint full benchmarks finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
@@ -176,7 +180,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         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

@@ -36,6 +36,9 @@ env:
   SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
   FAST_BENCH: TRUE
 
+
+permissions: {}
+
 jobs:
   prepare-matrix:
     name: Prepare operations matrix
@@ -60,11 +63,13 @@ jobs:
         if: github.event_name == 'workflow_dispatch'
         run: |
           echo "OP_FLAVOR=[\"default\"]" >> "${GITHUB_ENV}"
-          if [[ "${{ inputs.bench_type }}" == "both" ]]; then
+          if [[ "${INPUTS_BENCH_TYPE}" == "both" ]]; then
             echo "BENCH_TYPE=[\"latency\", \"throughput\"]" >> "${GITHUB_ENV}"
           else
-            echo "BENCH_TYPE=[\"${{ inputs.bench_type }}\"]" >> "${GITHUB_ENV}"
+            echo "BENCH_TYPE=[\"${INPUTS_BENCH_TYPE}\"]" >> "${GITHUB_ENV}"
           fi
+        env:
+          INPUTS_BENCH_TYPE: ${{ inputs.bench_type }}
 
       - name: Default benchmark type
         if: github.event_name != 'workflow_dispatch'
@@ -104,9 +109,8 @@ jobs:
     needs: [ prepare-matrix, setup-instance ]
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     concurrency:
-      group: ${{ github.workflow }}_${{ github.ref }}
+      group: ${{ github.workflow_ref }}
       cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
-    continue-on-error: true
     timeout-minutes: 1440  # 24 hours
     strategy:
       max-parallel: 1
@@ -131,7 +135,7 @@ jobs:
           } >> "${GITHUB_ENV}"
 
       - name: Install rust
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: nightly
 
@@ -150,23 +154,30 @@ jobs:
 
       - name: Run benchmarks with AVX512
         run: |
-          make BENCH_OP_FLAVOR=${{ matrix.op_flavor }} BENCH_TYPE=${{ matrix.bench_type }} bench_signed_${{ matrix.command }}
+          make BENCH_OP_FLAVOR="${OP_FLAVOR}" BENCH_TYPE="${BENCH_TYPE}" bench_signed_"${BENCH_COMMAND}"
+        env:
+          OP_FLAVOR: ${{ matrix.op_flavor }}
+          BENCH_TYPE: ${{ matrix.bench_type }}
+          BENCH_COMMAND: ${{ matrix.command }}
 
       - name: Parse results
         run: |
-          python3 ./ci/benchmark_parser.py target/criterion ${{ env.RESULTS_FILENAME }} \
+          python3 ./ci/benchmark_parser.py target/criterion "${RESULTS_FILENAME}" \
           --database tfhe_rs \
           --hardware "hpc7a.96xlarge" \
-          --project-version "${{ env.COMMIT_HASH }}" \
-          --branch ${{ github.ref_name }} \
-          --commit-date "${{ env.COMMIT_DATE }}" \
-          --bench-date "${{ env.BENCH_DATE }}" \
+          --project-version "${COMMIT_HASH}" \
+          --branch "${REF_NAME}" \
+          --commit-date "${COMMIT_DATE}" \
+          --bench-date "${BENCH_DATE}" \
           --walk-subdirs \
           --name-suffix avx512 \
-          --bench-type ${{ matrix.bench_type }}
+          --bench-type "${BENCH_TYPE}"
+        env:
+          REF_NAME: ${{ github.ref_name }}
+          BENCH_TYPE: ${{ matrix.bench_type }}
 
       - name: Upload parsed results artifact
-        uses: actions/upload-artifact@65c4c4a1ddee5b72f698fdd19549f0f0fb45cf08
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02
         with:
           name: ${{ github.sha }}_${{ matrix.command }}_${{ matrix.op_flavor }}_${{ matrix.bench_type }}
           path: ${{ env.RESULTS_FILENAME }}
@@ -174,13 +185,13 @@ jobs:
       - name: Send data to Slab
         shell: bash
         run: |
-          python3 slab/scripts/data_sender.py ${{ env.RESULTS_FILENAME }} "${{ secrets.JOB_SECRET }}" \
+          python3 slab/scripts/data_sender.py "${RESULTS_FILENAME}" "${{ secrets.JOB_SECRET }}" \
           --slab-url "${{ secrets.SLAB_URL }}"
 
       - name: Slack Notification
-        if: ${{ failure() }}
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Signed integer full benchmarks finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
@@ -204,7 +215,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         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

@@ -23,6 +23,9 @@ on:
     # Job will be triggered each Thursday at 11p.m.
     - cron: '0 23 * * 4'
 
+
+permissions: {}
+
 jobs:
   setup-ec2:
     name: Setup EC2 instance (fft-benchmarks)
@@ -45,7 +48,7 @@ jobs:
     name: Execute FFT benchmarks in EC2
     needs: setup-ec2
     concurrency:
-      group: ${{ github.workflow }}_${{ github.ref }}
+      group: ${{ github.workflow_ref }}
       cancel-in-progress: true
     runs-on: ${{ needs.setup-ec2.outputs.runner-name }}
     steps:
@@ -53,6 +56,8 @@ jobs:
         uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
+          persist-credentials: 'false'
+          token: ${{ secrets.REPO_CHECKOUT_TOKEN }}
 
       - name: Get benchmark details
         run: |
@@ -74,17 +79,19 @@ jobs:
 
       - name: Parse AVX512 results
         run: |
-          python3 ./ci/fft_benchmark_parser.py target/criterion ${{ env.RESULTS_FILENAME }} \
+          python3 ./ci/fft_benchmark_parser.py target/criterion "${RESULTS_FILENAME}" \
           --database concrete_fft \
           --hardware "hpc7a.96xlarge" \
-          --project-version "${{ env.COMMIT_HASH }}" \
-          --branch ${{ github.ref_name }} \
-          --commit-date "${{ env.COMMIT_DATE }}" \
-          --bench-date "${{ env.BENCH_DATE }}" \
+          --project-version "${COMMIT_HASH}" \
+          --branch "${REF_NAME}" \
+          --commit-date "${COMMIT_DATE}" \
+          --bench-date "${BENCH_DATE}" \
           --name-suffix avx512
+        env:
+          REF_NAME: ${{ github.ref_name }}
 
       - name: Upload parsed results artifact
-        uses: actions/upload-artifact@65c4c4a1ddee5b72f698fdd19549f0f0fb45cf08
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02
         with:
           name: ${{ github.sha }}_fft
           path: ${{ env.RESULTS_FILENAME }}
@@ -100,21 +107,13 @@ jobs:
       - name: Send data to Slab
         shell: bash
         run: |
-          echo "Computing HMac on downloaded artifact"
-          SIGNATURE="$(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 }} \
-          ${{ secrets.SLAB_URL }}
+          python3 slab/scripts/data_sender.py "${RESULTS_FILENAME}" "${{ secrets.JOB_SECRET }}" \
+          --slab-url "${{ secrets.SLAB_URL }}"
 
       - name: Slack Notification
-        if: ${{ failure() }}
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "tfhe-fft benchmarks failed. (${{ env.ACTION_RUN_URL }})"
@@ -138,7 +137,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "EC2 teardown (fft-benchmarks) failed. (${{ env.ACTION_RUN_URL }})"

.github/workflows/benchmark_tfhe_ntt.yml

@@ -23,6 +23,9 @@ on:
     # Job will be triggered each Friday at 11p.m.
     - cron: "0 23 * * 5"
 
+
+permissions: {}
+
 jobs:
   setup-ec2:
     name: Setup EC2 instance (ntt-benchmarks)
@@ -45,7 +48,7 @@ jobs:
     name: Execute NTT benchmarks in EC2
     needs: setup-ec2
     concurrency:
-      group: ${{ github.workflow }}_${{ github.ref }}
+      group: ${{ github.workflow_ref }}
       cancel-in-progress: true
     runs-on: ${{ needs.setup-ec2.outputs.runner-name }}
     steps:
@@ -53,6 +56,8 @@ jobs:
         uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
+          persist-credentials: 'false'
+          token: ${{ secrets.REPO_CHECKOUT_TOKEN }}
 
       - name: Get benchmark details
         run: |
@@ -74,17 +79,19 @@ jobs:
 
       - name: Parse results
         run: |
-          python3 ./ci/ntt_benchmark_parser.py target/criterion ${{ env.RESULTS_FILENAME }} \
+          python3 ./ci/ntt_benchmark_parser.py target/criterion "${RESULTS_FILENAME}" \
           --database concrete_ntt \
           --hardware "hpc7a.96xlarge" \
-          --project-version "${{ env.COMMIT_HASH }}" \
-          --branch ${{ github.ref_name }} \
-          --commit-date "${{ env.COMMIT_DATE }}" \
-          --bench-date "${{ env.BENCH_DATE }}" \
+          --project-version "${COMMIT_HASH}" \
+          --branch "${REF_NAME}" \
+          --commit-date "${COMMIT_DATE}" \
+          --bench-date "${BENCH_DATE}" \
           --name-suffix avx512
+        env:
+          REF_NAME: ${{ github.ref_name }}
 
       - name: Upload parsed results artifact
-        uses: actions/upload-artifact@65c4c4a1ddee5b72f698fdd19549f0f0fb45cf08
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02
         with:
           name: ${{ github.sha }}_ntt
           path: ${{ env.RESULTS_FILENAME }}
@@ -100,21 +107,13 @@ jobs:
       - name: Send data to Slab
         shell: bash
         run: |
-          echo "Computing HMac on downloaded artifact"
-          SIGNATURE="$(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 }} \
-          ${{ secrets.SLAB_URL }}
+          python3 slab/scripts/data_sender.py "${RESULTS_FILENAME}" "${{ secrets.JOB_SECRET }}" \
+          --slab-url "${{ secrets.SLAB_URL }}"
 
       - name: Slack Notification
-        if: ${{ failure() }}
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "tfhe-ntt benchmarks failed. (${{ env.ACTION_RUN_URL }})"
@@ -138,7 +137,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "EC2 teardown (ntt-benchmarks) failed. (${{ env.ACTION_RUN_URL }})"

.github/workflows/benchmark_tfhe_zk_pok.yml

@@ -30,6 +30,9 @@ env:
   SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
   BENCH_TYPE: ${{ inputs.bench_type || 'latency' }}
 
+
+permissions: {}
+
 jobs:
   should-run:
     runs-on: ubuntu-latest
@@ -42,10 +45,12 @@ jobs:
         uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
+          persist-credentials: 'false'
+          token: ${{ secrets.REPO_CHECKOUT_TOKEN }}
 
       - name: Check for file changes
         id: changed-files
-        uses: tj-actions/changed-files@dcc7a0cba800f454d79fff4b993e8c3555bcc0a8
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
         with:
           files_yaml: |
             zk_pok:
@@ -80,7 +85,7 @@ jobs:
     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 || '' }}
+      group: ${{ github.workflow_ref }}_${{github.event_name}}${{ github.ref == 'refs/heads/main' && github.sha || '' }}
       cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     steps:
@@ -100,7 +105,7 @@ jobs:
           } >> "${GITHUB_ENV}"
 
       - name: Install rust
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: nightly
 
@@ -114,25 +119,27 @@ jobs:
 
       - name: Run benchmarks
         run: |
-          make BENCH_TYPE=${{ env.BENCH_TYPE }} bench_tfhe_zk_pok
+          make BENCH_TYPE="${BENCH_TYPE}" bench_tfhe_zk_pok
 
       - name: Parse results
         run: |
-          python3 ./ci/benchmark_parser.py target/criterion ${{ env.RESULTS_FILENAME }} \
+          python3 ./ci/benchmark_parser.py target/criterion "${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 "${{ env.BENCH_DATE }}" \
+          --project-version "${COMMIT_HASH}" \
+          --branch "${REF_NAME}" \
+          --commit-date "${COMMIT_DATE}" \
+          --bench-date "${BENCH_DATE}" \
           --walk-subdirs \
           --name-suffix avx512 \
-          --bench-type ${{ env.BENCH_TYPE }}
+          --bench-type "${BENCH_TYPE}"
+        env:
+          REF_NAME: ${{ github.ref_name }}
 
       - name: Upload parsed results artifact
-        uses: actions/upload-artifact@65c4c4a1ddee5b72f698fdd19549f0f0fb45cf08
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02
         with:
           name: ${{ github.sha }}_tfhe_zk_pok
           path: ${{ env.RESULTS_FILENAME }}
@@ -148,13 +155,13 @@ jobs:
       - name: Send data to Slab
         shell: bash
         run: |
-          python3 slab/scripts/data_sender.py ${{ env.RESULTS_FILENAME }} "${{ secrets.JOB_SECRET }}" \
+          python3 slab/scripts/data_sender.py "${RESULTS_FILENAME}" "${{ secrets.JOB_SECRET }}" \
           --slab-url "${{ secrets.SLAB_URL }}"
 
       - name: Slack Notification
-        if: ${{ failure() }}
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "tfhe-zk-pok benchmarks finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
@@ -178,7 +185,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         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

@@ -21,6 +21,9 @@ env:
   SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
   SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
 
+
+permissions: {}
+
 jobs:
   should-run:
     runs-on: ubuntu-latest
@@ -41,7 +44,7 @@ jobs:
 
       - name: Check for file changes
         id: changed-files
-        uses: tj-actions/changed-files@dcc7a0cba800f454d79fff4b993e8c3555bcc0a8
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
         with:
           files_yaml: |
             wasm_bench:
@@ -100,7 +103,7 @@ jobs:
           } >> "${GITHUB_ENV}"
 
       - name: Install rust
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: nightly
 
@@ -110,7 +113,7 @@ jobs:
 
       - name: Node cache restoration
         id: node-cache
-        uses: actions/cache/restore@1bd1e32a3bdc45362d1e726936510720a7c30a57 #v4.2.0
+        uses: actions/cache/restore@5a3ec84eff668545956fd18022155c47e93e2684 #v4.2.3
         with:
           path: |
             ~/.nvm
@@ -123,7 +126,7 @@ jobs:
           make install_node
 
       - name: Node cache save
-        uses: actions/cache/save@1bd1e32a3bdc45362d1e726936510720a7c30a57 #v4.2.0
+        uses: actions/cache/save@5a3ec84eff668545956fd18022155c47e93e2684 #v4.2.3
         if: steps.node-cache.outputs.cache-hit != 'true'
         with:
           path: |
@@ -143,15 +146,17 @@ jobs:
       - name: Parse results
         run: |
           make parse_wasm_benchmarks
-          python3 ./ci/benchmark_parser.py tfhe/wasm_pk_gen.csv ${{ env.RESULTS_FILENAME }} \
+          python3 ./ci/benchmark_parser.py tfhe-benchmark/wasm_pk_gen.csv "${RESULTS_FILENAME}" \
           --database tfhe_rs \
           --hardware "m6i.4xlarge" \
-          --project-version "${{ env.COMMIT_HASH }}" \
-          --branch ${{ github.ref_name }} \
-          --commit-date "${{ env.COMMIT_DATE }}" \
-          --bench-date "${{ env.BENCH_DATE }}" \
+          --project-version "${COMMIT_HASH}" \
+          --branch "${REF_NAME}" \
+          --commit-date "${COMMIT_DATE}" \
+          --bench-date "${BENCH_DATE}" \
           --key-gen
-          rm tfhe/wasm_pk_gen.csv
+          rm tfhe-benchmark/wasm_pk_gen.csv
+        env:
+          REF_NAME: ${{ github.ref_name }}
 
       # Run these benchmarks only once
       - name: Measure public key and ciphertext sizes in HL Api
@@ -162,12 +167,12 @@ jobs:
       - name: Parse key and ciphertext sizes results
         if:  matrix.browser == 'chrome'
         run: |
-          python3 ./ci/benchmark_parser.py tfhe/hlapi_cpk_and_cctl_sizes.csv ${{ env.RESULTS_FILENAME }} \
+          python3 ./ci/benchmark_parser.py tfhe-benchmark/hlapi_cpk_and_cctl_sizes.csv "${RESULTS_FILENAME}" \
           --key-gen \
           --append-results
 
       - name: Upload parsed results artifact
-        uses: actions/upload-artifact@65c4c4a1ddee5b72f698fdd19549f0f0fb45cf08
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02
         with:
           name: ${{ github.sha }}_wasm_${{ matrix.browser }}
           path: ${{ env.RESULTS_FILENAME }}
@@ -183,13 +188,13 @@ jobs:
       - name: Send data to Slab
         shell: bash
         run: |
-          python3 slab/scripts/data_sender.py ${{ env.RESULTS_FILENAME }} "${{ secrets.JOB_SECRET }}" \
+          python3 slab/scripts/data_sender.py "${RESULTS_FILENAME}" "${{ secrets.JOB_SECRET }}" \
           --slab-url "${{ secrets.SLAB_URL }}"
 
       - name: Slack Notification
-        if: ${{ failure() }}
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "WASM benchmarks (${{ matrix.browser }}) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
@@ -213,7 +218,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         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

@@ -31,6 +31,9 @@ env:
   SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
   SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
 
+
+permissions: {}
+
 jobs:
   should-run:
     runs-on: ubuntu-latest
@@ -48,7 +51,7 @@ jobs:
 
       - name: Check for file changes
         id: changed-files
-        uses: tj-actions/changed-files@dcc7a0cba800f454d79fff4b993e8c3555bcc0a8
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
         with:
           files_yaml: |
             zk_pok:
@@ -74,11 +77,13 @@ jobs:
       - name: Set benchmark types
         if: github.event_name == 'workflow_dispatch'
         run: |
-          if [[ "${{ inputs.bench_type }}" == "both" ]]; then
+          if [[ "${INPUTS_BENCH_TYPE}" == "both" ]]; then
             echo "BENCH_TYPE=[\"latency\", \"throughput\"]" >> "${GITHUB_ENV}"
           else
-            echo "BENCH_TYPE=[\"${{ inputs.bench_type }}\"]" >> "${GITHUB_ENV}"
+            echo "BENCH_TYPE=[\"${INPUTS_BENCH_TYPE}\"]" >> "${GITHUB_ENV}"
           fi
+        env:
+          INPUTS_BENCH_TYPE: ${{ inputs.bench_type }}
 
       - name: Default benchmark type
         if: github.event_name != 'workflow_dispatch'
@@ -118,7 +123,7 @@ jobs:
     if: needs.setup-instance.result != 'skipped'
     needs: [ prepare-matrix, setup-instance ]
     concurrency:
-      group: ${{ github.workflow }}_${{github.event_name}}_${{ github.ref }}${{ github.ref == 'refs/heads/main' && github.sha || '' }}
+      group: ${{ github.workflow_ref }}_${{github.event_name}}${{ github.ref == 'refs/heads/main' && github.sha || '' }}
       cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     strategy:
@@ -142,7 +147,7 @@ jobs:
           } >> "${GITHUB_ENV}"
 
       - name: Install rust
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: nightly
 
@@ -156,30 +161,35 @@ jobs:
 
       - name: Run benchmarks with AVX512
         run: |
-          make BENCH_TYPE=${{ matrix.bench_type }} bench_integer_zk
+          make BENCH_TYPE="${BENCH_TYPE}" bench_integer_zk
+        env:
+          BENCH_TYPE: ${{ matrix.bench_type }}
 
       - name: Parse results
         run: |
-          python3 ./ci/benchmark_parser.py target/criterion ${{ env.RESULTS_FILENAME }} \
+          python3 ./ci/benchmark_parser.py target/criterion "${RESULTS_FILENAME}" \
           --database tfhe_rs \
           --hardware "hpc7a.96xlarge" \
           --backend cpu \
-          --project-version "${{ env.COMMIT_HASH }}" \
-          --branch ${{ github.ref_name }} \
-          --commit-date "${{ env.COMMIT_DATE }}" \
-          --bench-date "${{ env.BENCH_DATE }}" \
+          --project-version "${COMMIT_HASH}" \
+          --branch "${REF_NAME}" \
+          --commit-date "${COMMIT_DATE}" \
+          --bench-date "${BENCH_DATE}" \
           --walk-subdirs \
           --name-suffix avx512 \
-          --bench-type ${{ matrix.bench_type }}
+          --bench-type "${BENCH_TYPE}"
+        env:
+          REF_NAME: ${{ github.ref_name }}
+          BENCH_TYPE: ${{ matrix.bench_type }}
 
       - name: Parse CRS sizes results
         run: |
-          python3 ./ci/benchmark_parser.py tfhe/pke_zk_crs_sizes.csv ${{ env.RESULTS_FILENAME }} \
+          python3 ./ci/benchmark_parser.py tfhe-benchmark/pke_zk_crs_sizes.csv "${RESULTS_FILENAME}" \
           --object-sizes \
           --append-results
 
       - name: Upload parsed results artifact
-        uses: actions/upload-artifact@65c4c4a1ddee5b72f698fdd19549f0f0fb45cf08
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02
         with:
           name: ${{ github.sha }}_integer_zk
           path: ${{ env.RESULTS_FILENAME }}
@@ -195,13 +205,13 @@ jobs:
       - name: Send data to Slab
         shell: bash
         run: |
-          python3 slab/scripts/data_sender.py ${{ env.RESULTS_FILENAME }} "${{ secrets.JOB_SECRET }}" \
+          python3 slab/scripts/data_sender.py "${RESULTS_FILENAME}" "${{ secrets.JOB_SECRET }}" \
           --slab-url "${{ secrets.SLAB_URL }}"
 
       - name: Slack Notification
-        if: ${{ failure() }}
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "PKE ZK benchmarks finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
@@ -225,7 +235,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         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

@@ -8,11 +8,15 @@ env:
   RUSTFLAGS: "-C target-cpu=native"
   RUST_BACKTRACE: "full"
   RUST_MIN_STACK: "8388608"
+  CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN || secrets.GITHUB_TOKEN }}
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.head_ref }}
   cancel-in-progress: true
 
+permissions:
+  contents: read
+
 jobs:
   cargo-builds:
     runs-on: ${{ matrix.os }}
@@ -26,9 +30,12 @@ jobs:
 
     steps:
       - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          persist-credentials: 'false'
+          token: ${{ env.CHECKOUT_TOKEN }}
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: stable
 
@@ -87,5 +94,10 @@ jobs:
         run: |
           make build_tfhe_coverage
 
+      - name: Run Hpu pcc checks
+        if: ${{ contains(matrix.os, 'ubuntu') }}
+        run: |
+          make pcc_hpu
+
       # The wasm build check is a bit annoying to set-up here and is done during the tests in
       # aws_tfhe_tests.yml

.github/workflows/cargo_build_tfhe_fft.yml

@@ -6,11 +6,15 @@ on:
 
 env:
   CARGO_TERM_COLOR: always
+  CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN || secrets.GITHUB_TOKEN }}
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.head_ref }}
   cancel-in-progress: true
 
+permissions:
+  contents: read
+
 jobs:
   cargo-builds-fft:
     runs-on: ${{ matrix.runner_type }}
@@ -22,6 +26,9 @@ jobs:
 
     steps:
       - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          persist-credentials: 'false'
+          token: ${{ env.CHECKOUT_TOKEN }}
 
       - name: Install Rust
         uses: actions-rs/toolchain@16499b5e05bf2e26879000db0c1d13f7e13fa3af

.github/workflows/cargo_build_tfhe_ntt.yml

@@ -6,11 +6,15 @@ on:
 
 env:
   CARGO_TERM_COLOR: always
+  CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN || secrets.GITHUB_TOKEN }}
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.head_ref }}
   cancel-in-progress: true
 
+permissions:
+  contents: read
+
 jobs:
   cargo-builds-ntt:
     runs-on: ${{ matrix.os }}
@@ -20,6 +24,9 @@ jobs:
       fail-fast: false
     steps:
       - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          persist-credentials: 'false'
+          token: ${{ env.CHECKOUT_TOKEN }}
 
       - name: Install Rust
         uses: actions-rs/toolchain@16499b5e05bf2e26879000db0c1d13f7e13fa3af

.github/workflows/cargo_test_fft.yml

@@ -3,23 +3,61 @@ name: Cargo Test tfhe-fft
 
 on:
   pull_request:
+  push:
+    branches:
+      - main
 
 env:
   CARGO_TERM_COLOR: always
+  IS_PULL_REQUEST: ${{ github.event_name == 'pull_request' }}
+  CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN || secrets.GITHUB_TOKEN }}
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.head_ref }}
   cancel-in-progress: true
 
+permissions:
+  contents: read
+
 jobs:
+  should-run:
+    runs-on: ubuntu-latest
+    permissions:
+      pull-requests: read
+    outputs:
+      fft_test: ${{ env.IS_PULL_REQUEST == 'false' || steps.changed-files.outputs.fft_any_changed }}
+    steps:
+      - name: Checkout tfhe-rs
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          fetch-depth: 0
+          persist-credentials: 'false'
+          token: ${{ env.CHECKOUT_TOKEN }}
+
+      - name: Check for file changes
+        id: changed-files
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
+        with:
+          files_yaml: |
+            fft:
+              - tfhe/Cargo.toml
+              - Makefile
+              - tfhe-fft/**
+              - '.github/workflows/cargo_test_fft.yml'
+
   cargo-tests-fft:
+    needs: should-run
+    if: needs.should-run.outputs.fft_test == 'true'
     runs-on: ${{ matrix.runner_type }}
     strategy:
       matrix:
-        runner_type: [ubuntu-latest, macos-latest, windows-latest]
+        runner_type: [ ubuntu-latest, macos-latest, windows-latest ]
       fail-fast: false
     steps:
       - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          persist-credentials: 'false'
+          token: ${{ env.CHECKOUT_TOKEN }}
 
       - name: Install Rust
         uses: actions-rs/toolchain@16499b5e05bf2e26879000db0c1d13f7e13fa3af
@@ -39,12 +77,17 @@ jobs:
           make test_fft_no_std
 
   cargo-tests-fft-nightly:
+    needs: should-run
+    if: needs.should-run.outputs.fft_test == 'true'
     runs-on: ${{ matrix.runner_type }}
     strategy:
       matrix:
-        runner_type: [ubuntu-latest, macos-latest, windows-latest]
+        runner_type: [ ubuntu-latest, macos-latest, windows-latest ]
     steps:
       - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          persist-credentials: 'false'
+          token: ${{ env.CHECKOUT_TOKEN }}
 
       - name: Install Rust
         uses: actions-rs/toolchain@16499b5e05bf2e26879000db0c1d13f7e13fa3af
@@ -61,11 +104,43 @@ jobs:
           make test_fft_no_std_nightly
 
   cargo-tests-fft-node-js:
-    runs-on: "ubuntu-latest"
+    needs: should-run
+    if: needs.should-run.outputs.fft_test == 'true'
+    runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          persist-credentials: 'false'
+          token: ${{ env.CHECKOUT_TOKEN }}
 
       - name: Test node js
         run: |
           make install_node
           make test_fft_node_js_ci
+
+  cargo-tests-fft-successful:
+    needs: [ should-run, cargo-tests-fft, cargo-tests-fft-nightly, cargo-tests-fft-node-js ]
+    if: ${{ always() }}
+    runs-on: ubuntu-latest
+    steps:
+      - name: Tests do not need to run
+        if: needs.should-run.outputs.fft_test == 'false'
+        run: |
+          echo "tfhe-fft files haven't changed tests don't need to run"
+
+      - name: Check all tests passed
+        if: needs.should-run.outputs.fft_test == 'true' &&
+          needs.cargo-tests-fft.result == 'success' &&
+          needs.cargo-tests-fft-nightly.result == 'success' &&
+          needs.cargo-tests-fft-node-js.result == 'success'
+        run: |
+          echo "All tfhe-fft test passed"
+
+      - name: Check tests failure
+        if: needs.should-run.outputs.fft_test == 'true' &&
+          (needs.cargo-tests-fft.result != 'success' ||
+          needs.cargo-tests-fft-nightly.result != 'success' ||
+          needs.cargo-tests-fft-node-js.result != 'success')
+        run: |
+          echo "Some tfhe-fft tests failed"
+          exit 1

.github/workflows/cargo_test_ntt.yml

@@ -3,23 +3,61 @@ name: Cargo Test tfhe-ntt
 
 on:
   pull_request:
+  push:
+    branches:
+      - main
 
 env:
   CARGO_TERM_COLOR: always
+  IS_PULL_REQUEST: ${{ github.event_name == 'pull_request' }}
+  CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN || secrets.GITHUB_TOKEN }}
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.head_ref }}
   cancel-in-progress: true
 
+permissions:
+  contents: read
+
 jobs:
+  should-run:
+    runs-on: ubuntu-latest
+    permissions:
+      pull-requests: read
+    outputs:
+      ntt_test: ${{ env.IS_PULL_REQUEST == 'false' || steps.changed-files.outputs.ntt_any_changed }}
+    steps:
+      - name: Checkout tfhe-rs
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          fetch-depth: 0
+          persist-credentials: 'false'
+          token: ${{ env.CHECKOUT_TOKEN }}
+
+      - name: Check for file changes
+        id: changed-files
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
+        with:
+          files_yaml: |
+            ntt:
+              - tfhe/Cargo.toml
+              - Makefile
+              - tfhe-ntt/**
+              - '.github/workflows/cargo_test_ntt.yml'
+
   cargo-tests-ntt:
+    needs: should-run
+    if: needs.should-run.outputs.ntt_test == 'true'
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [ubuntu-latest, macos-latest, windows-latest]
+        os: [ ubuntu-latest, macos-latest, windows-latest ]
       fail-fast: false
     steps:
       - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          persist-credentials: 'false'
+          token: ${{ env.CHECKOUT_TOKEN }}
 
       - name: Install Rust
         uses: actions-rs/toolchain@16499b5e05bf2e26879000db0c1d13f7e13fa3af
@@ -34,12 +72,17 @@ jobs:
         run: make test_ntt_no_std
 
   cargo-tests-ntt-nightly:
+    needs: should-run
+    if: needs.should-run.outputs.ntt_test == 'true'
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [ubuntu-latest, macos-latest, windows-latest]
+        os: [ ubuntu-latest, macos-latest, windows-latest ]
     steps:
       - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          persist-credentials: 'false'
+          token: ${{ env.CHECKOUT_TOKEN }}
 
       - name: Install Rust
         uses: actions-rs/toolchain@16499b5e05bf2e26879000db0c1d13f7e13fa3af
@@ -52,3 +95,28 @@ jobs:
 
       - name: Test no-std nightly
         run: make test_ntt_no_std_nightly
+
+  cargo-tests-ntt-successful:
+    needs: [ should-run, cargo-tests-ntt, cargo-tests-ntt-nightly ]
+    if: ${{ always() }}
+    runs-on: ubuntu-latest
+    steps:
+      - name: Tests do not need to run
+        if: needs.should-run.outputs.ntt_test == 'false'
+        run: |
+          echo "tfhe-ntt files haven't changed tests don't need to run"
+
+      - name: Check all tests success
+        if: needs.should-run.outputs.ntt_test == 'true' &&
+          needs.cargo-tests-ntt.result == 'success' &&
+          needs.cargo-tests-ntt-nightly.result == 'success'
+        run: |
+          echo "All tfhe-ntt tests passed"
+
+      - name: Check tests failure
+        if: needs.should-run.outputs.ntt_test == 'true' &&
+          (needs.cargo-tests-ntt.result != 'success' ||
+          needs.cargo-tests-ntt-nightly.result != 'success')
+        run: |
+          echo "Some tfhe-ntt tests failed"
+          exit 1

.github/workflows/check_commit.yml

@@ -3,6 +3,10 @@ name: Check commit and PR compliance
 on:
   pull_request:
 
+permissions:
+  contents: read
+  pull-requests: read # Permission needed to scan commits in a pull-request
+
 jobs:
   check-commit-pr:
     name: Check commit and PR

.github/workflows/ci_lint.yml

@@ -5,9 +5,13 @@ on:
   pull_request:
 
 env:
-  ACTIONLINT_VERSION: 1.6.27
+  ACTIONLINT_VERSION: 1.7.7
+  ACTIONLINT_CHECKSUM: "023070a287cd8cccd71515fedc843f1985bf96c436b7effaecce67290e7e0757"
   CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN || secrets.GITHUB_TOKEN }}
 
+permissions:
+  contents: read
+
 jobs:
   lint-check:
     name: Lint and checks
@@ -21,17 +25,24 @@ jobs:
 
       - name: Get actionlint
         run: |
-          bash <(curl https://raw.githubusercontent.com/rhysd/actionlint/main/scripts/download-actionlint.bash) ${{ env.ACTIONLINT_VERSION }}
-          echo "f2ee6d561ce00fa93aab62a7791c1a0396ec7e8876b2a8f2057475816c550782  actionlint" > checksum
+          wget "https://github.com/rhysd/actionlint/releases/download/v${{ env.ACTIONLINT_VERSION }}/actionlint_${{ env.ACTIONLINT_VERSION }}_linux_amd64.tar.gz"
+          echo "${{ env.ACTIONLINT_CHECKSUM }} actionlint_${{ env.ACTIONLINT_VERSION }}_linux_amd64.tar.gz" > checksum
           sha256sum -c checksum
+          tar -xf actionlint_${{ env.ACTIONLINT_VERSION }}_linux_amd64.tar.gz actionlint
           ln -s "$(pwd)/actionlint" /usr/local/bin/
 
       - name: Lint workflows
         run: |
           make lint_workflow
 
+      - name: Check workflows security
+        run: |
+          make check_workflow_security
+        env:
+          GH_TOKEN: ${{ env.CHECKOUT_TOKEN }}
+
       - name: Ensure SHA pinned actions
-        uses: zgosalvez/github-actions-ensure-sha-pinned-actions@25ed13d0628a1601b4b44048e63cc4328ed03633 # v3.0.22
+        uses: zgosalvez/github-actions-ensure-sha-pinned-actions@fc87bb5b5a97953d987372e74478de634726b3e5 # v3.0.25
         with:
           allowlist: |
             slsa-framework/slsa-github-generator

.github/workflows/code_coverage.yml

@@ -10,12 +10,16 @@ env:
   SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
   SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
   SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+  CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN || secrets.GITHUB_TOKEN }}
 
 on:
   # Allows you to run this workflow manually from the Actions tab as an alternative.
   workflow_dispatch:
   # Code coverage workflow is only run via workflow_dispatch event since execution duration is not stabilized yet.
 
+permissions:
+  contents: read
+
 jobs:
   setup-instance:
     name: Setup instance (code-coverage)
@@ -38,22 +42,25 @@ jobs:
     name: Code coverage tests
     needs: setup-instance
     concurrency:
-      group: ${{ github.workflow }}_${{ github.event_name }}_${{ github.ref }}
+      group: ${{ github.workflow_ref }}_${{ github.event_name }}
       cancel-in-progress: true
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     timeout-minutes: 5760 # 4 days
     steps:
       - name: Checkout tfhe-rs
         uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          persist-credentials: 'false'
+          token: ${{ env.CHECKOUT_TOKEN }}
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: stable
 
       - name: Check for file changes
         id: changed-files
-        uses: tj-actions/changed-files@dcc7a0cba800f454d79fff4b993e8c3555bcc0a8
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
         with:
           files_yaml: |
             tfhe:
@@ -83,7 +90,7 @@ jobs:
           make test_shortint_cov
 
       - name: Upload tfhe coverage to Codecov
-        uses: codecov/codecov-action@13ce06bfc6bbe3ecf90edbbf1bc32fe5978ca1d3
+        uses: codecov/codecov-action@18283e04ce6e62d37312384ff67231eb8fd56d24
         if: steps.changed-files.outputs.tfhe_any_changed == 'true'
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
@@ -97,7 +104,7 @@ jobs:
           make test_integer_cov
 
       - name: Upload tfhe coverage to Codecov
-        uses: codecov/codecov-action@13ce06bfc6bbe3ecf90edbbf1bc32fe5978ca1d3
+        uses: codecov/codecov-action@18283e04ce6e62d37312384ff67231eb8fd56d24
         if: steps.changed-files.outputs.tfhe_any_changed == 'true'
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
@@ -106,9 +113,9 @@ jobs:
           files: integer/cobertura.xml
 
       - name: Slack Notification
-        if: ${{ failure() }}
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "Code coverage finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
@@ -132,7 +139,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         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

@@ -21,6 +21,9 @@ on:
   pull_request:
     types: [ labeled ]
 
+permissions:
+  contents: read
+
 jobs:
   setup-instance:
     name: Setup instance (csprng-randomness-tests)
@@ -46,13 +49,13 @@ jobs:
         id: start-github-instance
         if: env.SECRETS_AVAILABLE == 'false'
         run: |
-          echo "runner_group=${{ env.EXTERNAL_CONTRIBUTION_RUNNER }}" >> "$GITHUB_OUTPUT"
+          echo "runner_group=${EXTERNAL_CONTRIBUTION_RUNNER}" >> "$GITHUB_OUTPUT"
 
   csprng-randomness-tests:
     name: CSPRNG randomness tests
     needs: setup-instance
     concurrency:
-      group: ${{ github.workflow }}_${{ github.head_ref || github.ref }}
+      group: ${{ github.workflow_ref }}
       cancel-in-progress: true
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     steps:
@@ -63,7 +66,7 @@ jobs:
           token: ${{ env.CHECKOUT_TOKEN }}
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: stable
 
@@ -72,12 +75,12 @@ jobs:
           make dieharder_csprng
 
       - name: Slack Notification
-        if: ${{ failure() }}
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "tfhe-csprng randomness check finished with status: ${{ job.status }} on '${{ env.BRANCH }}'. (${{ 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)
@@ -99,7 +102,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "Instance teardown (csprng-randomness-tests) finished with status: ${{ job.status }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Instance teardown (csprng-randomness-tests) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/data_pr_close.yml

@@ -25,6 +25,9 @@ on:
 # the script will always return 0 because of the "echo EOF".
 
 
+
+permissions: {}
+
 jobs:
   auto_close_job:
     if: ${{ contains(github.event.pull_request.labels.*.name, 'data_PR') }}
@@ -39,14 +42,17 @@ jobs:
           curl --fail-with-body --no-progress-meter -L -X GET \
           -H "Accept: application/vnd.github+json" \
           -H "X-GitHub-Api-Version: 2022-11-28"  \
-          ${{ env.TARGET_REPO_API_URL }}/pulls\?head=${{ github.repository_owner }}:${{ env.PR_BRANCH }} | jq -e '.[0]' | sed 's/null/{ "message": "corresponding PR not found" }/'
+          "${TARGET_REPO_API_URL}"/pulls\?head="${REPO_OWNER}":"${PR_BRANCH}" | jq -e '.[0]' | sed 's/null/{ "message": "corresponding PR not found" }/'
           RES="$?"
           echo EOF
         } >> "${GITHUB_ENV}"
         exit $RES
+      env:
+        REPO_OWNER: ${{ github.repository_owner }}
 
     - name: Comment on the PR to indicate the reason of the close
       run: |
+        BODY="'{ \"body\": \"PR ${CLOSE_TYPE}d because the corresponding PR in main repo was ${CLOSE_TYPE}d: ${REPO}#${EVENT_NUMBER}\" }'"
         {
           set +e
           set -o pipefail
@@ -55,12 +61,16 @@ jobs:
           -H "Accept: application/vnd.github+json" \
           -H "Authorization: Bearer ${{ secrets.FHE_ACTIONS_TOKEN }}" \
           -H "X-GitHub-Api-Version: 2022-11-28" \
-          ${{ fromJson(env.TARGET_REPO_PR).comments_url }} \
-          -d '{ "body": "PR ${{ env.CLOSE_TYPE }}d because the corresponding PR in main repo was ${{ env.CLOSE_TYPE }}d: ${{ github.repository }}#${{ github.event.number  }}" }'
+          "${COMMENTS_URL}" \
+          -d "${BODY}"
           RES="$?"
           echo EOF
         } >> "${GITHUB_ENV}"
         exit $RES
+      env:
+        REPO: ${{ github.repository }}
+        EVENT_NUMBER: ${{ github.event.number }}
+        COMMENTS_URL: ${{ fromJson(env.TARGET_REPO_PR).comments_url }}
 
     - name: Merge the Pull Request in the data repo
       if: ${{ github.event.pull_request.merged }}
@@ -73,12 +83,14 @@ jobs:
           -H "Accept: application/vnd.github+json" \
           -H "Authorization: Bearer ${{ secrets.FHE_ACTIONS_TOKEN }}" \
           -H "X-GitHub-Api-Version: 2022-11-28" \
-          ${{ fromJson(env.TARGET_REPO_PR).url }}/merge \
+          "${TARGET_REPO_PR_URL}"/merge \
           -d '{ "merge_method": "rebase" }'
           RES="$?"
           echo EOF
         } >> "${GITHUB_ENV}"
         exit $RES
+      env:
+        TARGET_REPO_PR_URL: ${{ fromJson(env.TARGET_REPO_PR).url }}
 
     - name: Close the Pull Request in the data repo
       if: ${{ !github.event.pull_request.merged }}
@@ -91,12 +103,14 @@ jobs:
           -H "Accept: application/vnd.github+json" \
           -H "Authorization: Bearer ${{ secrets.FHE_ACTIONS_TOKEN }}" \
           -H "X-GitHub-Api-Version: 2022-11-28" \
-          ${{ fromJson(env.TARGET_REPO_PR).url }} \
+          "${TARGET_REPO_PR_URL}" \
           -d '{ "state": "closed" }'
           RES="$?"
           echo EOF
         } >> "${GITHUB_ENV}"
         exit $RES
+      env:
+        TARGET_REPO_PR_URL: ${{ fromJson(env.TARGET_REPO_PR).url }}
 
     - name: Delete the associated branch in the data repo
       run: |
@@ -108,7 +122,7 @@ jobs:
           -H "Accept: application/vnd.github+json" \
           -H "Authorization: Bearer ${{ secrets.FHE_ACTIONS_TOKEN }}" \
           -H "X-GitHub-Api-Version: 2022-11-28" \
-          ${{ env.TARGET_REPO_API_URL }}/git/refs/heads/${{ env.PR_BRANCH }}
+          "${TARGET_REPO_API_URL}"/git/refs/heads/"${PR_BRANCH}"
           RES="$?"
           echo EOF
         } >> "${GITHUB_ENV}"
@@ -117,7 +131,7 @@ jobs:
     - name: Slack Notification
       if: ${{ always() && job.status == 'failure' }}
       continue-on-error: true
-      uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+      uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
       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

@@ -22,6 +22,9 @@ on:
     # Nightly tests @ 1AM after each work day
     - cron: "0 1 * * MON-FRI"
 
+permissions:
+  contents: read
+
 jobs:
   cuda-tests-linux:
     name: CUDA tests (RTX 4090)
@@ -29,9 +32,10 @@ jobs:
       contains(github.event.label.name, '4090_test') ||
       (github.event_name == 'schedule' &&  github.repository == 'zama-ai/tfhe-rs')
     concurrency:
-      group: ${{ github.workflow }}_${{ github.head_ref || github.ref }}
+      group: ${{ github.workflow_ref }}
       cancel-in-progress: true
     runs-on: ["self-hosted", "4090-desktop"]
+    timeout-minutes: 1440 # 24 hours
 
     steps:
       - name: Checkout tfhe-rs
@@ -41,7 +45,7 @@ jobs:
           token: ${{ env.CHECKOUT_TOKEN }}
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: stable
 
@@ -76,9 +80,9 @@ jobs:
           github_token: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Slack Notification
-        if: ${{ failure() }}
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "CUDA RTX 4090 tests finished with status: ${{ job.status }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "CUDA RTX 4090 tests finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/gpu_fast_h100_tests.yml

@@ -11,7 +11,9 @@ env:
   SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
   SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
   SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+  SLACKIFY_MARKDOWN: true
   IS_PULL_REQUEST: ${{ github.event_name == 'pull_request' }}
+  PULL_REQUEST_MD_LINK: ""
   CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN || secrets.GITHUB_TOKEN }}
   # Secrets will be available only to zama-ai organization members
   SECRETS_AVAILABLE: ${{ secrets.JOB_SECRET != '' }}
@@ -23,6 +25,9 @@ on:
   pull_request:
     types: [ labeled ]
 
+permissions:
+  contents: read
+
 jobs:
   should-run:
     runs-on: ubuntu-latest
@@ -40,7 +45,7 @@ jobs:
 
       - name: Check for file changes
         id: changed-files
-        uses: tj-actions/changed-files@dcc7a0cba800f454d79fff4b993e8c3555bcc0a8
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
         with:
           files_yaml: |
             gpu:
@@ -68,11 +73,17 @@ jobs:
       (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-remote-instance.outputs.label || steps.start-github-instance.outputs.runner_group }}
+      # Use permanent remote instance label first as on-demand remote instance label output is set before the end of start-remote-instance step.
+      # If the latter fails due to a failed GitHub action runner set up, we have to fallback on the permanent instance.
+      # Since the on-demand remote label is set before failure, we have to do the logical OR in this order,
+      # otherwise we'll try to run the next job on a non-existing on-demand instance.
+      runner-name: ${{ steps.use-permanent-instance.outputs.runner_group || steps.start-remote-instance.outputs.label || steps.start-github-instance.outputs.runner_group }}
+      remote-instance-outcome: ${{ steps.start-remote-instance.outcome }}
     steps:
       - name: Start remote instance
         id: start-remote-instance
         if: env.SECRETS_AVAILABLE == 'true'
+        continue-on-error: true
         uses: zama-ai/slab-github-runner@79939325c3c429837c10d6041e4fd8589d328bac
         with:
           mode: start
@@ -82,12 +93,19 @@ jobs:
           backend: hyperstack
           profile: single-h100
 
+      # This will allow to fallback on permanent instances running on Hyperstack.
+      - name: Use permanent remote instance
+        id: use-permanent-instance
+        if: env.SECRETS_AVAILABLE == 'true' && steps.start-remote-instance.outcome == 'failure'
+        run: |
+          echo "runner_group=h100x1" >> "$GITHUB_OUTPUT"
+
       # This instance will be spawned especially for pull-request from forked repository
       - name: Start GitHub instance
         id: start-github-instance
         if: env.SECRETS_AVAILABLE == 'false'
         run: |
-          echo "runner_group=${{ env.EXTERNAL_CONTRIBUTION_RUNNER }}" >> "$GITHUB_OUTPUT"
+          echo "runner_group=${EXTERNAL_CONTRIBUTION_RUNNER}" >> "$GITHUB_OUTPUT"
 
   cuda-tests-linux:
     name: CUDA H100 tests
@@ -95,7 +113,7 @@ jobs:
     if: github.event_name != 'pull_request' ||
       (github.event_name == 'pull_request' && needs.setup-instance.result != 'skipped')
     concurrency:
-      group: ${{ github.workflow }}_${{ github.head_ref || github.ref }}
+      group: ${{ github.workflow_ref }}
       cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     strategy:
@@ -114,6 +132,7 @@ jobs:
           token: ${{ env.CHECKOUT_TOKEN }}
 
       - name: Setup Hyperstack dependencies
+        if: needs.setup-instance.outputs.remote-instance-outcome == 'success'
         uses: ./.github/actions/gpu_setup
         with:
           cuda-version: ${{ matrix.cuda }}
@@ -121,7 +140,7 @@ jobs:
           github-instance: ${{ env.SECRETS_AVAILABLE == 'false' }}
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: stable
 
@@ -150,16 +169,23 @@ jobs:
     if: ${{ always() && needs.cuda-tests-linux.result != 'skipped' && failure() }}
     continue-on-error: true
     steps:
+      - name: Set pull-request URL
+        if: env.SECRETS_AVAILABLE == 'true' && github.event_name == 'pull_request'
+        run: |
+          echo "PULL_REQUEST_MD_LINK=[pull-request](${PR_BASE_URL}${{ github.event.pull_request.number }}), "  >> "${GITHUB_ENV}"
+        env:
+          PR_BASE_URL: ${{ vars.PR_BASE_URL }}
+
       - name: Send message
         if: env.SECRETS_AVAILABLE == 'true'
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ needs.cuda-tests-linux.result }}
-          SLACK_MESSAGE: "Fast H100 tests finished with status: ${{ needs.cuda-tests-linux.result }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Fast H100 tests finished with status: ${{ needs.cuda-tests-linux.result }}. (${{ env.PULL_REQUEST_MD_LINK }}[action run](${{ env.ACTION_RUN_URL }}))"
 
   teardown-instance:
     name: Teardown instance (cuda-h100-tests)
-    if: ${{ always() && needs.setup-instance.result == 'success' }}
+    if: ${{ always() && needs.setup-instance.outputs.remote-instance-outcome == 'success' }}
     needs: [ setup-instance, cuda-tests-linux ]
     runs-on: ubuntu-latest
     steps:
@@ -177,7 +203,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "Instance teardown (cuda-h100-tests) finished with status: ${{ job.status }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Instance teardown (cuda-h100-tests) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/gpu_fast_tests.yml

@@ -11,7 +11,9 @@ env:
   SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
   SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
   SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+  SLACKIFY_MARKDOWN: true
   IS_PULL_REQUEST: ${{ github.event_name == 'pull_request' }}
+  PULL_REQUEST_MD_LINK: ""
   CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN || secrets.GITHUB_TOKEN }}
   # Secrets will be available only to zama-ai organization members
   SECRETS_AVAILABLE: ${{ secrets.JOB_SECRET != '' }}
@@ -22,6 +24,9 @@ on:
   workflow_dispatch:
   pull_request:
 
+permissions:
+  contents: read
+
 jobs:
   should-run:
     runs-on: ubuntu-latest
@@ -39,7 +44,7 @@ jobs:
 
       - name: Check for file changes
         id: changed-files
-        uses: tj-actions/changed-files@dcc7a0cba800f454d79fff4b993e8c3555bcc0a8
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
         with:
           files_yaml: |
             gpu:
@@ -85,7 +90,7 @@ jobs:
         id: start-github-instance
         if: env.SECRETS_AVAILABLE == 'false'
         run: |
-          echo "runner_group=${{ env.EXTERNAL_CONTRIBUTION_RUNNER }}" >> "$GITHUB_OUTPUT"
+          echo "runner_group=${EXTERNAL_CONTRIBUTION_RUNNER}" >> "$GITHUB_OUTPUT"
 
   cuda-tests-linux:
     name: CUDA tests
@@ -93,7 +98,7 @@ jobs:
     if: github.event_name != 'pull_request' ||
       (github.event_name == 'pull_request' && needs.setup-instance.result != 'skipped')
     concurrency:
-      group: ${{ github.workflow }}_${{ github.head_ref || github.ref }}
+      group: ${{ github.workflow_ref }}
       cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     strategy:
@@ -119,7 +124,7 @@ jobs:
           github-instance: ${{ env.SECRETS_AVAILABLE == 'false' }}
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: stable
 
@@ -148,12 +153,19 @@ jobs:
     if: ${{ always() && needs.cuda-tests-linux.result != 'skipped' && failure() }}
     continue-on-error: true
     steps:
+      - name: Set pull-request URL
+        if: env.SECRETS_AVAILABLE == 'true' && github.event_name == 'pull_request'
+        run: |
+          echo "PULL_REQUEST_MD_LINK=[pull-request](${PR_BASE_URL}${{ github.event.pull_request.number }}), "  >> "${GITHUB_ENV}"
+        env:
+          PR_BASE_URL: ${{ vars.PR_BASE_URL }}
+
       - name: Send message
         if: env.SECRETS_AVAILABLE == 'true'
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ needs.cuda-tests-linux.result }}
-          SLACK_MESSAGE: "Base GPU tests finished with status: ${{ needs.cuda-tests-linux.result }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Base GPU tests finished with status: ${{ needs.cuda-tests-linux.result }}. (${{ env.PULL_REQUEST_MD_LINK }}[action run](${{ env.ACTION_RUN_URL }}))"
 
   teardown-instance:
     name: Teardown instance (cuda-tests)
@@ -175,7 +187,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "Instance teardown (cuda-tests) finished with status: ${{ job.status }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Instance teardown (cuda-tests) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/gpu_full_h100_tests.yml

@@ -15,15 +15,24 @@ env:
 on:
   workflow_dispatch:
 
+
+permissions: {}
+
 jobs:
   setup-instance:
     name: Setup instance (cuda-h100-tests)
     runs-on: ubuntu-latest
     outputs:
-      runner-name: ${{ steps.start-instance.outputs.label }}
+      # Use permanent remote instance label first as on-demand remote instance label output is set before the end of start-remote-instance step.
+      # If the latter fails due to a failed GitHub action runner set up, we have to fallback on the permanent instance.
+      # Since the on-demand remote label is set before failure, we have to do the logical OR in this order,
+      # otherwise we'll try to run the next job on a non-existing on-demand instance.
+      runner-name: ${{ steps.use-permanent-instance.outputs.runner_group || steps.start-remote-instance.outputs.label }}
+      remote-instance-outcome: ${{ steps.start-remote-instance.outcome }}
     steps:
-      - name: Start instance
-        id: start-instance
+      - name: Start remote instance
+        id: start-remote-instance
+        continue-on-error: true
         uses: zama-ai/slab-github-runner@79939325c3c429837c10d6041e4fd8589d328bac
         with:
           mode: start
@@ -33,11 +42,18 @@ jobs:
           backend: hyperstack
           profile: single-h100
 
+      # This will allow to fallback on permanent instances running on Hyperstack.
+      - name: Use permanent remote instance
+        id: use-permanent-instance
+        if: env.SECRETS_AVAILABLE == 'true' && steps.start-remote-instance.outcome == 'failure'
+        run: |
+          echo "runner_group=h100x1" >> "$GITHUB_OUTPUT"
+
   cuda-tests-linux:
     name: CUDA H100 tests
     needs: [ setup-instance ]
     concurrency:
-      group: ${{ github.workflow }}_${{ github.ref }}
+      group: ${{ github.workflow_ref }}
       cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     strategy:
@@ -49,18 +65,6 @@ jobs:
             cuda: "12.2"
             gcc: 11 
     steps:
-      # Mandatory on hyperstack since a bootable volume is not re-usable yet.
-      - name: Install dependencies
-        run: |
-          sudo apt update
-          sudo apt install -y checkinstall zlib1g-dev libssl-dev libclang-dev
-          wget https://github.com/Kitware/CMake/releases/download/v${{ 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
         with:
@@ -68,13 +72,14 @@ jobs:
           token: ${{ secrets.REPO_CHECKOUT_TOKEN }}
 
       - name: Setup Hyperstack dependencies
+        if: needs.setup-instance.outputs.remote-instance-outcome == 'success'
         uses: ./.github/actions/gpu_setup
         with:
           cuda-version: ${{ matrix.cuda }}
           gcc-version: ${{ matrix.gcc }}
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: stable
 
@@ -102,13 +107,14 @@ jobs:
     continue-on-error: true
     steps:
       - name: Send message
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ needs.cuda-tests-linux.result }}
-          SLACK_MESSAGE: "Full H100 tests finished with status: ${{ needs.cuda-tests-linux.result }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Full H100 tests finished with status: ${{ needs.cuda-tests-linux.result }}. (${{ env.ACTION_RUN_URL }})"
 
   teardown-instance:
     name: Teardown instance (cuda-h100-tests)
+    if: ${{ always() && needs.setup-instance.outputs.remote-instance-outcome == 'success' }}
     needs: [ setup-instance, cuda-tests-linux ]
     runs-on: ubuntu-latest
     steps:
@@ -125,7 +131,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "Instance teardown (cuda-h100-tests) finished with status: ${{ job.status }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Instance teardown (cuda-h100-tests) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/gpu_full_multi_gpu_tests.yml

@@ -11,7 +11,9 @@ env:
   SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
   SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
   SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+  SLACKIFY_MARKDOWN: true
   IS_PULL_REQUEST: ${{ github.event_name == 'pull_request' }}
+  PULL_REQUEST_MD_LINK: ""
   CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN || secrets.GITHUB_TOKEN }}
   # Secrets will be available only to zama-ai organization members
   SECRETS_AVAILABLE: ${{ secrets.JOB_SECRET != '' }}
@@ -23,6 +25,9 @@ on:
   pull_request:
     types: [ labeled ]
 
+permissions:
+  contents: read
+
 jobs:
   should-run:
     runs-on: ubuntu-latest
@@ -40,7 +45,7 @@ jobs:
 
       - name: Check for file changes
         id: changed-files
-        uses: tj-actions/changed-files@dcc7a0cba800f454d79fff4b993e8c3555bcc0a8
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
         with:
           files_yaml: |
             gpu:
@@ -87,7 +92,7 @@ jobs:
         id: start-github-instance
         if: env.SECRETS_AVAILABLE == 'false'
         run: |
-          echo "runner_group=${{ env.EXTERNAL_CONTRIBUTION_RUNNER }}" >> "$GITHUB_OUTPUT"
+          echo "runner_group=${EXTERNAL_CONTRIBUTION_RUNNER}" >> "$GITHUB_OUTPUT"
 
   cuda-tests-linux:
     name: CUDA multi-GPU tests
@@ -95,7 +100,7 @@ jobs:
     if: github.event_name != 'pull_request' ||
       (github.event_name == 'pull_request' && needs.setup-instance.result != 'skipped')
     concurrency:
-      group: ${{ github.workflow }}_${{ github.head_ref || github.ref }}
+      group: ${{ github.workflow_ref }}
       cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     strategy:
@@ -121,7 +126,7 @@ jobs:
           github-instance: ${{ env.SECRETS_AVAILABLE == 'false' }}
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: stable
 
@@ -144,7 +149,7 @@ jobs:
 
       - name: Run High Level API Tests
         run: |
-          BIG_TESTS_INSTANCE=TRUE make test_high_level_api_gpu
+          make test_high_level_api_gpu
 
   slack-notify:
     name: Slack Notification
@@ -153,12 +158,19 @@ jobs:
     if: ${{ always() && needs.cuda-tests-linux.result != 'skipped' && failure() }}
     continue-on-error: true
     steps:
+      - name: Set pull-request URL
+        if: env.SECRETS_AVAILABLE == 'true' && github.event_name == 'pull_request'
+        run: |
+          echo "PULL_REQUEST_MD_LINK=[pull-request](${PR_BASE_URL}${{ github.event.pull_request.number }}), "  >> "${GITHUB_ENV}"
+        env:
+          PR_BASE_URL: ${{ vars.PR_BASE_URL }}
+
       - name: Send message
         if: env.SECRETS_AVAILABLE == 'true'
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ needs.cuda-tests-linux.result }}
-          SLACK_MESSAGE: "Multi-GPU tests finished with status: ${{ needs.cuda-tests-linux.result }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Multi-GPU tests finished with status: ${{ needs.cuda-tests-linux.result }}. (${{ env.PULL_REQUEST_MD_LINK }}[action run](${{ env.ACTION_RUN_URL }}))"
 
   teardown-instance:
     name: Teardown instance (cuda-tests-multi-gpu)
@@ -180,7 +192,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "Instance teardown (cuda-tests-multi-gpu) finished with status: ${{ job.status }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          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

@@ -1,4 +1,4 @@
-name: Long Run Tests on GPU
+name: Cuda - Long Run Tests on GPU
 
 env:
   CARGO_TERM_COLOR: always
@@ -10,13 +10,17 @@ env:
   SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
   SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
   SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+  CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN || secrets.GITHUB_TOKEN }}
 
 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 9p.m.
-    - cron: "0 21 * * 5"
+    # Nightly tests will be triggered each evening 8p.m.
+    - cron: "0 20 * * *"
+
+permissions:
+  contents: read
 
 jobs:
   setup-instance:
@@ -42,7 +46,7 @@ jobs:
     name: Long run GPU tests
     needs: [ setup-instance ]
     concurrency:
-      group: ${{ github.workflow }}_${{github.event_name}}_${{ github.ref }}
+      group: ${{ github.workflow_ref }}_${{github.event_name}}
       cancel-in-progress: true
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     strategy:
@@ -57,6 +61,9 @@ jobs:
     steps:
       - name: Checkout tfhe-rs
         uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          persist-credentials: 'false'
+          token: ${{ env.CHECKOUT_TOKEN }}
 
       - name: Setup Hyperstack dependencies
         uses: ./.github/actions/gpu_setup
@@ -65,7 +72,7 @@ jobs:
           gcc-version: ${{ matrix.gcc }}
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: stable
 
@@ -81,7 +88,7 @@ jobs:
     continue-on-error: true
     steps:
       - name: Send message
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ needs.cuda-tests.result }}
           SLACK_MESSAGE: "Integer GPU long run tests finished with status: ${{ needs.cuda-tests.result }}. (${{ env.ACTION_RUN_URL }})"
@@ -105,7 +112,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         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

@@ -1,4 +1,4 @@
-# Perfom tfhe-cuda-backend post-commit checks on an AWS instance
+# Perform tfhe-cuda-backend post-commit checks on an AWS instance
 name: Cuda - Post-commit Checks
 
 env:
@@ -11,14 +11,21 @@ env:
   SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
   SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
   SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+  SLACKIFY_MARKDOWN: true
+  PULL_REQUEST_MD_LINK: ""
   CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN || secrets.GITHUB_TOKEN }}
   # Secrets will be available only to zama-ai organization members
   SECRETS_AVAILABLE: ${{ secrets.JOB_SECRET != '' }}
   EXTERNAL_CONTRIBUTION_RUNNER: "large_ubuntu_16-22.04"
+  CUDA_KEYRING_PACKAGE: cuda-keyring_1.1-1_all.deb
+  CUDA_KEYRING_SHA: "d93190d50b98ad4699ff40f4f7af50f16a76dac3bb8da1eaaf366d47898ff8df"
 
 on:
   pull_request:
 
+permissions:
+  contents: read
+
 jobs:
   setup-instance:
     name: Setup instance (cuda-pcc)
@@ -43,13 +50,13 @@ jobs:
         id: start-github-instance
         if: env.SECRETS_AVAILABLE == 'false'
         run: |
-          echo "runner_group=${{ env.EXTERNAL_CONTRIBUTION_RUNNER }}" >> "$GITHUB_OUTPUT"
+          echo "runner_group=${EXTERNAL_CONTRIBUTION_RUNNER}" >> "$GITHUB_OUTPUT"
 
   cuda-pcc:
     name: CUDA post-commit checks
     needs: setup-instance
     concurrency:
-      group: ${{ github.workflow }}_${{ github.head_ref || github.ref }}
+      group: ${{ github.workflow_ref }}
       cancel-in-progress: true
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     strategy:
@@ -75,13 +82,15 @@ jobs:
         shell: bash
         run: |
           TOOLKIT_VERSION="$(echo ${{ matrix.cuda }} | sed 's/\(.*\)\.\(.*\)/\1-\2/')"
-          wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.1-1_all.deb
-          sudo dpkg -i cuda-keyring_1.1-1_all.deb
+          wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/"${CUDA_KEYRING_PACKAGE}"
+          echo "${CUDA_KEYRING_SHA} ${CUDA_KEYRING_PACKAGE}" > checksum
+          sha256sum -c checksum
+          sudo dpkg -i "${CUDA_KEYRING_PACKAGE}"
           sudo apt update
           sudo apt -y install "cuda-toolkit-${TOOLKIT_VERSION}" cmake-format
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: stable
 
@@ -111,13 +120,24 @@ jobs:
         run: |
           make pcc_gpu
 
+      - name: Check build with hpu enabled
+        run: |
+          make clippy_gpu_hpu
+
+      - name: Set pull-request URL
+        if: ${{ failure() && github.event_name == 'pull_request' }}
+        run: |
+          echo "PULL_REQUEST_MD_LINK=[pull-request](${PR_BASE_URL}${{ github.event.pull_request.number }}), "  >> "${GITHUB_ENV}"
+        env:
+          PR_BASE_URL: ${{ vars.PR_BASE_URL }}
+
       - name: Slack Notification
         if: ${{ failure() && env.SECRETS_AVAILABLE == 'true' }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "CUDA AWS post-commit checks finished with status: ${{ job.status }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "CUDA AWS post-commit checks finished with status: ${{ job.status }}. (${{ env.PULL_REQUEST_MD_LINK }}[action run](${{ env.ACTION_RUN_URL }}))"
 
   teardown-instance:
     name: Teardown instance (cuda-pcc)
@@ -139,7 +159,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "Instance teardown (cuda-pcc) finished with status: ${{ job.status }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Instance teardown (cuda-pcc) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/gpu_signed_integer_classic_tests.yml

@@ -11,7 +11,9 @@ env:
   SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
   SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
   SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+  SLACKIFY_MARKDOWN: true
   IS_PULL_REQUEST: ${{ github.event_name == 'pull_request' }}
+  PULL_REQUEST_MD_LINK: ""
   CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN || secrets.GITHUB_TOKEN }}
   # Secrets will be available only to zama-ai organization members
   SECRETS_AVAILABLE: ${{ secrets.JOB_SECRET != '' }}
@@ -23,6 +25,9 @@ on:
   pull_request:
     types: [ labeled ]
 
+permissions:
+  contents: read
+
 jobs:
   should-run:
     runs-on: ubuntu-latest
@@ -40,7 +45,7 @@ jobs:
 
       - name: Check for file changes
         id: changed-files
-        uses: tj-actions/changed-files@dcc7a0cba800f454d79fff4b993e8c3555bcc0a8
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
         with:
           files_yaml: |
             gpu:
@@ -87,7 +92,7 @@ jobs:
         id: start-github-instance
         if: env.SECRETS_AVAILABLE == 'false'
         run: |
-          echo "runner_group=${{ env.EXTERNAL_CONTRIBUTION_RUNNER }}" >> "$GITHUB_OUTPUT"
+          echo "runner_group=${EXTERNAL_CONTRIBUTION_RUNNER}" >> "$GITHUB_OUTPUT"
 
   cuda-tests-linux:
     name: CUDA signed integer tests with classical PBS
@@ -95,7 +100,7 @@ jobs:
     if: github.event_name != 'pull_request' ||
       (github.event_name == 'pull_request' && needs.setup-instance.result != 'skipped')
     concurrency:
-      group: ${{ github.workflow }}_${{ github.head_ref || github.ref }}
+      group: ${{ github.workflow_ref }}
       cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     strategy:
@@ -121,7 +126,7 @@ jobs:
           github-instance: ${{ env.SECRETS_AVAILABLE == 'false' }}
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: stable
 
@@ -136,12 +141,19 @@ jobs:
     if: ${{ always() && needs.cuda-tests-linux.result != 'skipped' && failure() }}
     continue-on-error: true
     steps:
+      - name: Set pull-request URL
+        if: env.SECRETS_AVAILABLE == 'true' && github.event_name == 'pull_request'
+        run: |
+          echo "PULL_REQUEST_MD_LINK=[pull-request](${PR_BASE_URL}${{ github.event.pull_request.number }}), "  >> "${GITHUB_ENV}"
+        env:
+          PR_BASE_URL: ${{ vars.PR_BASE_URL }}
+
       - name: Send message
         if: env.SECRETS_AVAILABLE == 'true'
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ needs.cuda-tests-linux.result }}
-          SLACK_MESSAGE: "Integer GPU signed integer tests with classical PBS finished with status: ${{ needs.cuda-tests-linux.result }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Integer GPU signed integer tests with classical PBS finished with status: ${{ needs.cuda-tests-linux.result }}. (${{ env.PULL_REQUEST_MD_LINK }}[action run](${{ env.ACTION_RUN_URL }}))"
 
   teardown-instance:
     name: Teardown instance (cuda-signed-classic-tests)
@@ -163,7 +175,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "Instance teardown (cuda-signed-classic-tests) finished with status: ${{ job.status }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          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

@@ -11,7 +11,9 @@ env:
   SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
   SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
   SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+  SLACKIFY_MARKDOWN: true
   IS_PULL_REQUEST: ${{ github.event_name == 'pull_request' }}
+  PULL_REQUEST_MD_LINK: ""
   CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN || secrets.GITHUB_TOKEN }}
   # Secrets will be available only to zama-ai organization members
   SECRETS_AVAILABLE: ${{ secrets.JOB_SECRET != '' }}
@@ -23,6 +25,8 @@ on:
   pull_request:
     types: [ labeled ]
 
+permissions:
+  contents: read
 
 jobs:
   should-run:
@@ -41,7 +45,7 @@ jobs:
 
       - name: Check for file changes
         id: changed-files
-        uses: tj-actions/changed-files@dcc7a0cba800f454d79fff4b993e8c3555bcc0a8
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
         with:
           files_yaml: |
             gpu:
@@ -69,11 +73,17 @@ jobs:
       (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-remote-instance.outputs.label || steps.start-github-instance.outputs.runner_group }}
+      # Use permanent remote instance label first as on-demand remote instance label output is set before the end of start-remote-instance step.
+      # If the latter fails due to a failed GitHub action runner set up, we have to fallback on the permanent instance.
+      # Since the on-demand remote label is set before failure, we have to do the logical OR in this order,
+      # otherwise we'll try to run the next job on a non-existing on-demand instance.
+      runner-name: ${{ steps.use-permanent-instance.outputs.runner_group || steps.start-remote-instance.outputs.label || steps.start-github-instance.outputs.runner_group }}
+      remote-instance-outcome: ${{ steps.start-remote-instance.outcome }}
     steps:
       - name: Start remote instance
         id: start-remote-instance
         if: env.SECRETS_AVAILABLE == 'true'
+        continue-on-error: true
         uses: zama-ai/slab-github-runner@79939325c3c429837c10d6041e4fd8589d328bac
         with:
           mode: start
@@ -83,12 +93,19 @@ jobs:
           backend: hyperstack
           profile: single-h100
 
+      # This will allow to fallback on permanent instances running on Hyperstack.
+      - name: Use permanent remote instance
+        id: use-permanent-instance
+        if: env.SECRETS_AVAILABLE == 'true' && steps.start-remote-instance.outcome == 'failure'
+        run: |
+          echo "runner_group=h100x1" >> "$GITHUB_OUTPUT"
+
       # This instance will be spawned especially for pull-request from forked repository
       - name: Start GitHub instance
         id: start-github-instance
         if: env.SECRETS_AVAILABLE == 'false'
         run: |
-          echo "runner_group=${{ env.EXTERNAL_CONTRIBUTION_RUNNER }}" >> "$GITHUB_OUTPUT"
+          echo "runner_group=${EXTERNAL_CONTRIBUTION_RUNNER}" >> "$GITHUB_OUTPUT"
 
   cuda-tests-linux:
     name: CUDA H100 signed integer tests
@@ -96,7 +113,7 @@ jobs:
     if: github.event_name != 'pull_request' ||
       (github.event_name == 'pull_request' && needs.setup-instance.result != 'skipped')
     concurrency:
-      group: ${{ github.workflow }}_${{ github.head_ref || github.ref }}
+      group: ${{ github.workflow_ref }}
       cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     strategy:
@@ -115,6 +132,7 @@ jobs:
           token: ${{ env.CHECKOUT_TOKEN }}
 
       - name: Setup Hyperstack dependencies
+        if: needs.setup-instance.outputs.remote-instance-outcome == 'success'
         uses: ./.github/actions/gpu_setup
         with:
           cuda-version: ${{ matrix.cuda }}
@@ -122,7 +140,7 @@ jobs:
           github-instance: ${{ env.SECRETS_AVAILABLE == 'false' }}
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: stable
 
@@ -137,16 +155,23 @@ jobs:
     if: ${{ always() && needs.cuda-tests-linux.result != 'skipped' && failure() }}
     continue-on-error: true
     steps:
+      - name: Set pull-request URL
+        if: env.SECRETS_AVAILABLE == 'true' && github.event_name == 'pull_request'
+        run: |
+          echo "PULL_REQUEST_MD_LINK=[pull-request](${PR_BASE_URL}${{ github.event.pull_request.number }}), "  >> "${GITHUB_ENV}"
+        env:
+          PR_BASE_URL: ${{ vars.PR_BASE_URL }}
+
       - name: Send message
         if: env.SECRETS_AVAILABLE == 'true'
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ needs.cuda-tests-linux.result }}
-          SLACK_MESSAGE: "Integer GPU H100 tests finished with status: ${{ needs.cuda-tests-linux.result }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Integer GPU H100 tests finished with status: ${{ needs.cuda-tests-linux.result }}. (${{ env.PULL_REQUEST_MD_LINK }}[action run](${{ env.ACTION_RUN_URL }}))"
 
   teardown-instance:
     name: Teardown instance (cuda-h100-tests)
-    if: ${{ always() && needs.setup-instance.result == 'success' }}
+    if: ${{ always() && needs.setup-instance.outputs.remote-instance-outcome == 'success' }}
     needs: [ setup-instance, cuda-tests-linux ]
     runs-on: ubuntu-latest
     steps:
@@ -164,7 +189,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "Instance teardown (cuda-h100-tests) finished with status: ${{ job.status }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Instance teardown (cuda-h100-tests) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/gpu_signed_integer_tests.yml

@@ -11,9 +11,11 @@ env:
   SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
   SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
   SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+  SLACKIFY_MARKDOWN: true
   FAST_TESTS: TRUE
   NIGHTLY_TESTS: FALSE
   IS_PULL_REQUEST: ${{ github.event_name == 'pull_request' }}
+  PULL_REQUEST_MD_LINK: ""
   CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN || secrets.GITHUB_TOKEN }}
   # Secrets will be available only to zama-ai organization members
   SECRETS_AVAILABLE: ${{ secrets.JOB_SECRET != '' }}
@@ -27,6 +29,9 @@ on:
     # Nightly tests @ 1AM after each work day
     - cron: "0 1 * * MON-FRI"
 
+permissions:
+  contents: read
+
 jobs:
   should-run:
     runs-on: ubuntu-latest
@@ -44,7 +49,7 @@ jobs:
 
       - name: Check for file changes
         id: changed-files
-        uses: tj-actions/changed-files@dcc7a0cba800f454d79fff4b993e8c3555bcc0a8
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
         with:
           files_yaml: |
             gpu:
@@ -63,6 +68,7 @@ jobs:
               - '.github/workflows/gpu_signed_integer_tests.yml'
               - scripts/integer-tests.sh
               - ci/slab.toml
+
   setup-instance:
     name: Setup instance (cuda-signed-integer-tests)
     runs-on: ubuntu-latest
@@ -90,7 +96,7 @@ jobs:
         id: start-github-instance
         if: env.SECRETS_AVAILABLE == 'false'
         run: |
-          echo "runner_group=${{ env.EXTERNAL_CONTRIBUTION_RUNNER }}" >> "$GITHUB_OUTPUT"
+          echo "runner_group=${EXTERNAL_CONTRIBUTION_RUNNER}" >> "$GITHUB_OUTPUT"
 
   cuda-signed-integer-tests:
     name: CUDA signed integer tests
@@ -98,7 +104,7 @@ jobs:
     if: github.event_name != 'pull_request' ||
       (github.event_name == 'pull_request' && needs.setup-instance.result != 'skipped')
     concurrency:
-      group: ${{ github.workflow }}_${{ github.head_ref || github.ref }}
+      group: ${{ github.workflow_ref }}
       cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     strategy:
@@ -108,7 +114,7 @@ jobs:
         include:
           - os: ubuntu-22.04
             cuda: "12.2"
-            gcc: 11 
+            gcc: 11
     steps:
       - name: Checkout tfhe-rs
         uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
@@ -124,7 +130,7 @@ jobs:
           github-instance: ${{ env.SECRETS_AVAILABLE == 'false' }}
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: stable
 
@@ -147,11 +153,19 @@ jobs:
     if: ${{ always() && needs.cuda-signed-integer-tests.result != 'skipped' && failure() }}
     continue-on-error: true
     steps:
+      - name: Set pull-request URL
+        if: env.SECRETS_AVAILABLE == 'true' && github.event_name == 'pull_request'
+        run: |
+          echo "PULL_REQUEST_MD_LINK=[pull-request](${PR_BASE_URL}${{ github.event.pull_request.number }}), "  >> "${GITHUB_ENV}"
+        env:
+          PR_BASE_URL: ${{ vars.PR_BASE_URL }}
+
       - name: Send message
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        if: env.SECRETS_AVAILABLE == 'true'
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ needs.cuda-signed-integer-tests.result }}
-          SLACK_MESSAGE: "Base GPU tests finished with status: ${{ needs.cuda-signed-integer-tests.result }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Signed GPU tests finished with status: ${{ needs.cuda-signed-integer-tests.result }}. (${{ env.PULL_REQUEST_MD_LINK }}[action run](${{ env.ACTION_RUN_URL }}))"
 
   teardown-instance:
     name: Teardown instance (cuda-tests)
@@ -173,7 +187,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "Instance teardown (cuda-signed-integer-tests) finished with status: ${{ job.status }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          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

@@ -11,7 +11,9 @@ env:
   SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
   SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
   SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+  SLACKIFY_MARKDOWN: true
   IS_PULL_REQUEST: ${{ github.event_name == 'pull_request' }}
+  PULL_REQUEST_MD_LINK: ""
   CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN || secrets.GITHUB_TOKEN }}
   # Secrets will be available only to zama-ai organization members
   SECRETS_AVAILABLE: ${{ secrets.JOB_SECRET != '' }}
@@ -23,6 +25,8 @@ on:
   pull_request:
     types: [ labeled ]
 
+permissions:
+  contents: read
 
 jobs:
   should-run:
@@ -41,7 +45,7 @@ jobs:
 
       - name: Check for file changes
         id: changed-files
-        uses: tj-actions/changed-files@dcc7a0cba800f454d79fff4b993e8c3555bcc0a8
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
         with:
           files_yaml: |
             gpu:
@@ -88,7 +92,7 @@ jobs:
         id: start-github-instance
         if: env.SECRETS_AVAILABLE == 'false'
         run: |
-          echo "runner_group=${{ env.EXTERNAL_CONTRIBUTION_RUNNER }}" >> "$GITHUB_OUTPUT"
+          echo "runner_group=${EXTERNAL_CONTRIBUTION_RUNNER}" >> "$GITHUB_OUTPUT"
 
   cuda-tests-linux:
     name: CUDA unsigned integer tests with classical PBS
@@ -96,7 +100,7 @@ jobs:
     if: github.event_name != 'pull_request' ||
       (github.event_name == 'pull_request' && needs.setup-instance.result != 'skipped')
     concurrency:
-      group: ${{ github.workflow }}_${{ github.head_ref || github.ref }}
+      group: ${{ github.workflow_ref }}
       cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     strategy:
@@ -122,7 +126,7 @@ jobs:
           github-instance: ${{ env.SECRETS_AVAILABLE == 'false' }}
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: stable
 
@@ -137,12 +141,19 @@ jobs:
     if: ${{ always() && needs.cuda-tests-linux.result != 'skipped' && failure() }}
     continue-on-error: true
     steps:
+      - name: Set pull-request URL
+        if: env.SECRETS_AVAILABLE == 'true' && github.event_name == 'pull_request'
+        run: |
+          echo "PULL_REQUEST_MD_LINK=[pull-request](${PR_BASE_URL}${{ github.event.pull_request.number }}), "  >> "${GITHUB_ENV}"
+        env:
+          PR_BASE_URL: ${{ vars.PR_BASE_URL }}
+
       - name: Send message
         if: env.SECRETS_AVAILABLE == 'true'
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ needs.cuda-tests-linux.result }}
-          SLACK_MESSAGE: "Unsigned integer GPU classic tests finished with status: ${{ needs.cuda-tests-linux.result }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Unsigned integer GPU classic tests finished with status: ${{ needs.cuda-tests-linux.result }}. (${{ env.PULL_REQUEST_MD_LINK }}[action run](${{ env.ACTION_RUN_URL }}))"
 
   teardown-instance:
     name: Teardown instance (cuda-unsigned-classic-tests)
@@ -164,7 +175,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "Instance teardown (cuda-unsigned-classic-tests) finished with status: ${{ job.status }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          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

@@ -11,7 +11,9 @@ env:
   SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
   SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
   SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+  SLACKIFY_MARKDOWN: true
   IS_PULL_REQUEST: ${{ github.event_name == 'pull_request' }}
+  PULL_REQUEST_MD_LINK: ""
   CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN || secrets.GITHUB_TOKEN }}
   # Secrets will be available only to zama-ai organization members
   SECRETS_AVAILABLE: ${{ secrets.JOB_SECRET != '' }}
@@ -23,6 +25,9 @@ on:
   pull_request:
     types: [ labeled ]
 
+permissions:
+  contents: read
+
 jobs:
   should-run:
     runs-on: ubuntu-latest
@@ -40,7 +45,7 @@ jobs:
 
       - name: Check for file changes
         id: changed-files
-        uses: tj-actions/changed-files@dcc7a0cba800f454d79fff4b993e8c3555bcc0a8
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
         with:
           files_yaml: |
             gpu:
@@ -68,11 +73,17 @@ jobs:
       (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-remote-instance.outputs.label || steps.start-github-instance.outputs.runner_group }}
+      # Use permanent remote instance label first as on-demand remote instance label output is set before the end of start-remote-instance step.
+      # If the latter fails due to a failed GitHub action runner set up, we have to fallback on the permanent instance.
+      # Since the on-demand remote label is set before failure, we have to do the logical OR in this order,
+      # otherwise we'll try to run the next job on a non-existing on-demand instance.
+      runner-name: ${{ steps.use-permanent-instance.outputs.runner_group || steps.start-remote-instance.outputs.label || steps.start-github-instance.outputs.runner_group }}
+      remote-instance-outcome: ${{ steps.start-remote-instance.outcome }}
     steps:
       - name: Start remote instance
         id: start-remote-instance
         if: env.SECRETS_AVAILABLE == 'true'
+        continue-on-error: true
         uses: zama-ai/slab-github-runner@79939325c3c429837c10d6041e4fd8589d328bac
         with:
           mode: start
@@ -82,12 +93,19 @@ jobs:
           backend: hyperstack
           profile: single-h100
 
+      # This will allow to fallback on permanent instances running on Hyperstack.
+      - name: Use permanent remote instance
+        id: use-permanent-instance
+        if: env.SECRETS_AVAILABLE == 'true' && steps.start-remote-instance.outcome == 'failure'
+        run: |
+          echo "runner_group=h100x1" >> "$GITHUB_OUTPUT"
+
       # This instance will be spawned especially for pull-request from forked repository
       - name: Start GitHub instance
         id: start-github-instance
         if: env.SECRETS_AVAILABLE == 'false'
         run: |
-          echo "runner_group=${{ env.EXTERNAL_CONTRIBUTION_RUNNER }}" >> "$GITHUB_OUTPUT"
+          echo "runner_group=${EXTERNAL_CONTRIBUTION_RUNNER}" >> "$GITHUB_OUTPUT"
 
   cuda-tests-linux:
     name: CUDA H100 unsigned integer tests
@@ -95,7 +113,7 @@ jobs:
     if: github.event_name != 'pull_request' ||
       (github.event_name == 'pull_request' && needs.setup-instance.result != 'skipped')
     concurrency:
-      group: ${{ github.workflow }}_${{ github.head_ref || github.ref }}
+      group: ${{ github.workflow_ref }}
       cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     strategy:
@@ -114,6 +132,7 @@ jobs:
           token: ${{ env.CHECKOUT_TOKEN }}
 
       - name: Setup Hyperstack dependencies
+        if: needs.setup-instance.outputs.remote-instance-outcome == 'success'
         uses: ./.github/actions/gpu_setup
         with:
           cuda-version: ${{ matrix.cuda }}
@@ -121,7 +140,7 @@ jobs:
           github-instance: ${{ env.SECRETS_AVAILABLE == 'false' }}
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: stable
 
@@ -136,16 +155,23 @@ jobs:
     if: ${{ always() && needs.cuda-tests-linux.result != 'skipped' && failure() }}
     continue-on-error: true
     steps:
+      - name: Set pull-request URL
+        if: env.SECRETS_AVAILABLE == 'true' && github.event_name == 'pull_request'
+        run: |
+          echo "PULL_REQUEST_MD_LINK=[pull-request](${PR_BASE_URL}${{ github.event.pull_request.number }}), "  >> "${GITHUB_ENV}"
+        env:
+          PR_BASE_URL: ${{ vars.PR_BASE_URL }}
+
       - name: Send message
         if: env.SECRETS_AVAILABLE == 'true'
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ needs.cuda-tests-linux.result }}
-          SLACK_MESSAGE: "Unsigned integer GPU H100 tests finished with status: ${{ needs.cuda-tests-linux.result }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Unsigned integer GPU H100 tests finished with status: ${{ needs.cuda-tests-linux.result }}. (${{ env.PULL_REQUEST_MD_LINK }}[action run](${{ env.ACTION_RUN_URL }}))"
 
   teardown-instance:
     name: Teardown instance (cuda-h100-tests)
-    if: ${{ always() && needs.setup-instance.result == 'success' }}
+    if: ${{ always() && needs.setup-instance.outputs.remote-instance-outcome == 'success' }}
     needs: [ setup-instance, cuda-tests-linux ]
     runs-on: ubuntu-latest
     steps:
@@ -163,7 +189,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "Instance teardown (cuda-h100-tests) finished with status: ${{ job.status }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Instance teardown (cuda-h100-tests) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/gpu_unsigned_integer_tests.yml

@@ -11,8 +11,11 @@ env:
   SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
   SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
   SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+  SLACKIFY_MARKDOWN: true
   FAST_TESTS: TRUE
   NIGHTLY_TESTS: FALSE
+  IS_PULL_REQUEST: ${{ github.event_name == 'pull_request' }}
+  PULL_REQUEST_MD_LINK: ""
   CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN || secrets.GITHUB_TOKEN }}
   # Secrets will be available only to zama-ai organization members
   SECRETS_AVAILABLE: ${{ secrets.JOB_SECRET != '' }}
@@ -22,11 +25,13 @@ on:
   # Allows you to run this workflow manually from the Actions tab as an alternative.
   workflow_dispatch:
   pull_request:
-    types: [ labeled ]
   schedule:
     # Nightly tests @ 1AM after each work day
     - cron: "0 1 * * MON-FRI"
 
+permissions:
+  contents: read
+
 jobs:
   should-run:
     runs-on: ubuntu-latest
@@ -44,7 +49,7 @@ jobs:
 
       - name: Check for file changes
         id: changed-files
-        uses: tj-actions/changed-files@dcc7a0cba800f454d79fff4b993e8c3555bcc0a8
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
         with:
           files_yaml: |
             gpu:
@@ -66,11 +71,11 @@ jobs:
 
   setup-instance:
     name: Setup instance (cuda-unsigned-integer-tests)
+    runs-on: ubuntu-latest
     needs: should-run
     if: (github.event_name == 'schedule' && github.repository == 'zama-ai/tfhe-rs') ||
       github.event_name == 'workflow_dispatch' ||
       needs.should-run.outputs.gpu_test == 'true'
-    runs-on: ubuntu-latest
     outputs:
       runner-name: ${{ steps.start-remote-instance.outputs.label || steps.start-github-instance.outputs.runner_group }}
     steps:
@@ -91,7 +96,7 @@ jobs:
         id: start-github-instance
         if: env.SECRETS_AVAILABLE == 'false'
         run: |
-          echo "runner_group=${{ env.EXTERNAL_CONTRIBUTION_RUNNER }}" >> "$GITHUB_OUTPUT"
+          echo "runner_group=${EXTERNAL_CONTRIBUTION_RUNNER}" >> "$GITHUB_OUTPUT"
 
   cuda-unsigned-integer-tests:
     name: CUDA unsigned integer tests
@@ -99,7 +104,7 @@ jobs:
     if: github.event_name != 'pull_request' ||
       (github.event_name == 'pull_request' && needs.setup-instance.result != 'skipped')
     concurrency:
-      group: ${{ github.workflow }}_${{ github.head_ref || github.ref }}
+      group: ${{ github.workflow_ref }}
       cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     strategy:
@@ -125,7 +130,7 @@ jobs:
           github-instance: ${{ env.SECRETS_AVAILABLE == 'false' }}
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: stable
 
@@ -148,12 +153,19 @@ jobs:
     if: ${{ always() && needs.cuda-unsigned-integer-tests.result != 'skipped' && failure() }}
     continue-on-error: true
     steps:
+      - name: Set pull-request URL
+        if: env.SECRETS_AVAILABLE == 'true' && github.event_name == 'pull_request'
+        run: |
+          echo "PULL_REQUEST_MD_LINK=[pull-request](${PR_BASE_URL}${{ github.event.pull_request.number }}), "  >> "${GITHUB_ENV}"
+        env:
+          PR_BASE_URL: ${{ vars.PR_BASE_URL }}
+
       - name: Send message
         if: env.SECRETS_AVAILABLE == 'true'
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ needs.cuda-unsigned-integer-tests.result }}
-          SLACK_MESSAGE: "Unsigned integer GPU tests finished with status: ${{ needs.cuda-unsigned-integer-tests.result }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Unsigned integer GPU tests finished with status: ${{ needs.cuda-unsigned-integer-tests.result }}. (${{ env.PULL_REQUEST_MD_LINK }}[action run](${{ env.ACTION_RUN_URL }}))"
 
   teardown-instance:
     name: Teardown instance (cuda-tests)
@@ -175,7 +187,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_MESSAGE: "Instance teardown (cuda-unsigned-integer-tests) finished with status: ${{ job.status }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"
+          SLACK_MESSAGE: "Instance teardown (cuda-unsigned-integer-tests) finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"

.github/workflows/hpu_hlapi_tests.yml

@@ -0,0 +1,73 @@
+# Test tfhe-fft
+name: Cargo Test HLAPI HPU
+
+on:
+  pull_request:
+  push:
+    branches:
+      - main
+
+env:
+  CARGO_TERM_COLOR: always
+  IS_PULL_REQUEST: ${{ github.event_name == 'pull_request' }}
+  CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN || secrets.GITHUB_TOKEN }}
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref }}
+  cancel-in-progress: true
+
+
+permissions: { }
+
+jobs:
+  should-run:
+    runs-on: ubuntu-latest
+    permissions:
+      pull-requests: read
+    outputs:
+      hpu_test: ${{ env.IS_PULL_REQUEST == 'false' || steps.changed-files.outputs.hpu_any_changed }}
+    steps:
+      - name: Checkout tfhe-rs
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          fetch-depth: 0
+          persist-credentials: 'false'
+          token: ${{ env.CHECKOUT_TOKEN }}
+
+      - name: Check for file changes
+        id: changed-files
+        uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
+        with:
+          files_yaml: |
+            hpu:
+              - tfhe/Cargo.toml
+              - Makefile
+              - backends/tfhe-hpu-backend/**
+              - mockups/tfhe-hpu-mockup/**
+
+  cargo-tests-hpu:
+    needs: should-run
+    if: needs.should-run.outputs.hpu_test == 'true'
+    runs-on: large_ubuntu_16
+    steps:
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          persist-credentials: 'false'
+          token: ${{ env.CHECKOUT_TOKEN }}
+
+      - name: Install Rust
+        uses: actions-rs/toolchain@16499b5e05bf2e26879000db0c1d13f7e13fa3af
+        with:
+          toolchain: stable
+          override: true
+
+      - name: Install Just
+        run: |
+          cargo install just
+
+      - name: Test HLAPI HPU
+        run: |
+          source setup_hpu.sh
+          just -f mockups/tfhe-hpu-mockup/Justfile  BUILD_PROFILE=release mockup &
+          make HPU_CONFIG=sim test_high_level_api_hpu
+     

.github/workflows/integer_long_run_tests.yml

@@ -18,6 +18,9 @@ on:
     # Weekly tests will be triggered each Friday at 9p.m.
     - cron: "0 21 * * 5"
 
+
+permissions: {}
+
 jobs:
   setup-instance:
     name: Setup instance (cpu-tests)
@@ -42,7 +45,7 @@ jobs:
     name: Long run CPU tests
     needs: [ setup-instance ]
     concurrency:
-      group: ${{ github.workflow }}_${{github.event_name}}_${{ github.ref }}
+      group: ${{ github.workflow_ref }}_${{github.event_name}}
       cancel-in-progress: true
     runs-on: ${{ needs.setup-instance.outputs.runner-name }}
     timeout-minutes: 4320 # 72 hours
@@ -54,7 +57,7 @@ jobs:
           token: ${{ secrets.REPO_CHECKOUT_TOKEN }}
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: stable
 
@@ -63,9 +66,9 @@ jobs:
           make test_integer_long_run
 
       - name: Slack Notification
-        if: ${{ failure() }}
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "CPU long run tests finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
@@ -89,7 +92,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         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

@@ -24,9 +24,12 @@ env:
   CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN || secrets.GITHUB_TOKEN }}
 
 concurrency:
-  group: ${{ github.workflow }}_${{ github.head_ref || github.ref }}
+  group: ${{ github.workflow_ref }}
   cancel-in-progress: true
 
+permissions:
+  contents: read
+
 jobs:
   cargo-builds-m1:
     if: ${{ (github.event_name == 'schedule' &&  github.repository == 'zama-ai/tfhe-rs') ||
@@ -43,7 +46,7 @@ jobs:
           token: ${{ env.CHECKOUT_TOKEN }}
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: stable
 
@@ -190,12 +193,12 @@ jobs:
       - name: Slack Notification
         if: ${{ needs.cargo-builds-m1.result != 'skipped' }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           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: ${{ needs.cargo-builds-m1.result }} on '${{ env.BRANCH }}'. (${{ 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 }}
           MSG_MINIMAL: event,action url,commit

.github/workflows/make_release.yml

@@ -28,6 +28,12 @@ on:
 env:
   ACTION_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
   NPM_TAG: ""
+  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 }}
+
+permissions: {}
 
 jobs:
   verify_tag:
@@ -51,7 +57,7 @@ jobs:
       - name: Prepare package
         run: |
           cargo package -p tfhe
-      - uses: actions/upload-artifact@65c4c4a1ddee5b72f698fdd19549f0f0fb45cf08 # v4.6.0
+      - uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
         with:
           name: crate
           path: target/package/*.crate
@@ -62,7 +68,7 @@ jobs:
   provenance:
     if: ${{ !inputs.dry_run  }}
     needs: [package]
-    uses: slsa-framework/slsa-github-generator/.github/workflows/generator_generic_slsa3.yml@v2.0.0
+    uses: slsa-framework/slsa-github-generator/.github/workflows/generator_generic_slsa3.yml@v2.1.0
     permissions:
       # Needed to detect the GitHub Actions environment
       actions: read
@@ -94,7 +100,7 @@ jobs:
         run: |
           echo "NPM_TAG=latest" >> "${GITHUB_ENV}"
       - name: Download artifact
-        uses: actions/download-artifact@fa0a91b85d4f404e444e00e005971372dc801d16 # v4.1.8
+        uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
         with:
           name: crate
           path: target/package
@@ -104,7 +110,10 @@ jobs:
           CRATES_TOKEN: ${{ secrets.CARGO_REGISTRY_TOKEN }}
           DRY_RUN: ${{ inputs.dry_run && '--dry-run' || '' }}
         run: |
-          cargo publish -p tfhe --token ${{ env.CRATES_TOKEN }} ${{ env.DRY_RUN }}
+          # DRY_RUN expansion cannot be double quoted when variable contains empty string otherwise cargo publish 
+          # would fail. This is safe since DRY_RUN is handled in the env section above.
+          # shellcheck disable=SC2086
+          cargo publish -p tfhe --token "${CRATES_TOKEN}" ${DRY_RUN}
 
       - name: Generate hash
         id: published_hash
@@ -113,14 +122,10 @@ 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@c33737706dea87cd7784c687dadc9adf1be59990 # v2.3.2
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661 # v2.3.3
         env:
           SLACK_COLOR: failure
-          SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
-          SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
           SLACK_MESSAGE: "SLSA tfhe crate - hash comparison failure: (${{ env.ACTION_RUN_URL }})"
-          SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
-          SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
 
       - name: Build web package
         if: ${{ inputs.push_web_package }}
@@ -156,13 +161,9 @@ jobs:
           provenance: true
 
       - name: Slack Notification
-        if: ${{ failure() }}
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990 # v2.3.2
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661 # v2.3.3
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
-          SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
           SLACK_MESSAGE: "tfhe release failed: (${{ env.ACTION_RUN_URL }})"
-          SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
-          SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}

.github/workflows/make_release_cuda.yml

@@ -15,6 +15,8 @@ env:
   SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
   SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
 
+permissions: {}
+
 jobs:
   verify_tag:
     uses: ./.github/workflows/verify_tagged_commit.yml
@@ -65,7 +67,7 @@ jobs:
           token: ${{ secrets.REPO_CHECKOUT_TOKEN }}
 
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: stable
 
@@ -99,7 +101,7 @@ jobs:
   provenance:
     if: ${{ !inputs.dry_run  }}
     needs: [package]
-    uses: slsa-framework/slsa-github-generator/.github/workflows/generator_generic_slsa3.yml@v2.0.0
+    uses: slsa-framework/slsa-github-generator/.github/workflows/generator_generic_slsa3.yml@v2.1.0
     permissions:
       # Needed to detect the GitHub Actions environment
       actions: read
@@ -127,7 +129,7 @@ jobs:
       CUDA_PATH: /usr/local/cuda-${{ matrix.cuda }}
     steps:
       - name: Install latest stable
-        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
+        uses: dtolnay/rust-toolchain@888c2e1ea69ab0d4330cbf0af1ecc7b68f368cc1
         with:
           toolchain: stable
 
@@ -157,7 +159,10 @@ jobs:
           CRATES_TOKEN: ${{ secrets.CARGO_REGISTRY_TOKEN }}
           DRY_RUN: ${{ inputs.dry_run && '--dry-run' || '' }}
         run: |
-          cargo publish -p tfhe-cuda-backend --token ${{ env.CRATES_TOKEN }} ${{ env.DRY_RUN }}
+          # DRY_RUN expansion cannot be double quoted when variable contains empty string otherwise cargo publish 
+          # would fail. This is safe since DRY_RUN is handled in the env section above.
+          # shellcheck disable=SC2086
+          cargo publish -p tfhe-cuda-backend --token "${CRATES_TOKEN}" ${DRY_RUN}
 
       - name: Generate hash
         id: published_hash
@@ -166,19 +171,15 @@ 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@c33737706dea87cd7784c687dadc9adf1be59990 # v2.3.2
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661 # v2.3.3
         env:
           SLACK_COLOR: failure
-          SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
-          SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
           SLACK_MESSAGE: "SLSA tfhe-cuda-backend crate - hash comparison failure: (${{ env.ACTION_RUN_URL }})"
-          SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
-          SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
 
       - name: Slack Notification
-        if: ${{ failure() }}
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990 # v2.3.2
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661 # v2.3.3
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_MESSAGE: "tfhe-cuda-backend release finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
@@ -202,7 +203,7 @@ jobs:
       - name: Slack Notification
         if: ${{ failure() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         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_hpu.yml

@@ -0,0 +1,105 @@
+name: Publish HPU 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 }}
+  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 }}
+
+permissions: {}
+
+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@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        with:
+          fetch-depth: 0
+          persist-credentials: 'false'
+          token: ${{ secrets.REPO_CHECKOUT_TOKEN }}
+      - name: Prepare package
+        run: |
+          cargo package -p tfhe-hpu-backend
+      - uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
+        with:
+          name: crate
+          path: target/package/*.crate
+      - name: generate hash
+        id: hash
+        run: cd target/package && echo "hash=$(sha256sum ./*.crate | base64 -w0)" >> "${GITHUB_OUTPUT}"
+
+  provenance:
+    if: ${{ !inputs.dry_run  }}
+    needs: [package]
+    uses: slsa-framework/slsa-github-generator/.github/workflows/generator_generic_slsa3.yml@v2.1.0
+    permissions:
+      # Needed to detect the GitHub Actions environment
+      actions: read
+      # Needed to create the provenance via GitHub OIDC
+      id-token: write
+      # Needed to upload assets/artifacts
+      contents: write
+    with:
+      # SHA-256 hashes of the Crate package.
+      base64-subjects: ${{ needs.package.outputs.hash }}
+
+  publish_release:
+    name: Publish tfhe-hpu-backend Release
+    runs-on: ubuntu-latest
+    needs: [verify_tag, package] # for comparing hashes
+    steps:
+      - name: Checkout
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        with:
+          fetch-depth: 0
+          persist-credentials: 'false'
+          token: ${{ secrets.REPO_CHECKOUT_TOKEN }}
+
+      - name: Publish crate.io package
+        env:
+          CRATES_TOKEN: ${{ secrets.CARGO_REGISTRY_TOKEN }}
+          DRY_RUN: ${{ inputs.dry_run && '--dry-run' || '' }}
+        run: |
+          # DRY_RUN expansion cannot be double quoted when variable contains empty string otherwise cargo publish 
+          # would fail. This is safe since DRY_RUN is handled in the env section above.
+          # shellcheck disable=SC2086
+          cargo publish -p tfhe-hpu-backend --token "${CRATES_TOKEN}" ${DRY_RUN}
+
+      - name: Generate hash
+        id: published_hash
+        run: cd target/package && echo "pub_hash=$(sha256sum ./*.crate | base64 -w0)" >> "${GITHUB_OUTPUT}"
+
+      - name: Slack notification (hashes comparison)
+        if: ${{ needs.package.outputs.hash != steps.published_hash.outputs.pub_hash }}
+        continue-on-error: true
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661 # v2.3.3
+        env:
+          SLACK_COLOR: failure
+          SLACK_MESSAGE: "SLSA tfhe-hpu-backend crate - hash comparison failure: (${{ env.ACTION_RUN_URL }})"
+
+      - name: Slack Notification
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
+        continue-on-error: true
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661 # v2.3.3
+        env:
+          SLACK_COLOR: ${{ job.status }}
+          SLACK_MESSAGE: "tfhe-hpu-backend release failed: (${{ env.ACTION_RUN_URL }})"

.github/workflows/make_release_tfhe_csprng.yml

@@ -10,6 +10,12 @@ on:
 
 env:
   ACTION_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
+  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 }}
+
+permissions: {}
 
 jobs:
   verify_tag:
@@ -27,10 +33,12 @@ jobs:
         uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
           fetch-depth: 0
+          persist-credentials: 'false'
+          token: ${{ secrets.REPO_CHECKOUT_TOKEN }}
       - name: Prepare package
         run: |
           cargo package -p tfhe-csprng
-      - uses: actions/upload-artifact@65c4c4a1ddee5b72f698fdd19549f0f0fb45cf08 # v4.6.0
+      - uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
         with:
           name: crate-tfhe-csprng
           path: target/package/*.crate
@@ -42,7 +50,7 @@ jobs:
   provenance:
     if: ${{ !inputs.dry_run  }}
     needs: [package]
-    uses: slsa-framework/slsa-github-generator/.github/workflows/generator_generic_slsa3.yml@v2.0.0
+    uses: slsa-framework/slsa-github-generator/.github/workflows/generator_generic_slsa3.yml@v2.1.0
     permissions:
       # Needed to detect the GitHub Actions environment
       actions: read
@@ -64,9 +72,10 @@ jobs:
         uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
           fetch-depth: 0
-          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
+          persist-credentials: 'false'
+          token: ${{ secrets.REPO_CHECKOUT_TOKEN }}
       - name: Download artifact
-        uses: actions/download-artifact@fa0a91b85d4f404e444e00e005971372dc801d16 # v4.1.8
+        uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
         with:
           name: crate-tfhe-csprng
           path: target/package
@@ -75,29 +84,24 @@ jobs:
           CRATES_TOKEN: ${{ secrets.CARGO_REGISTRY_TOKEN }}
           DRY_RUN: ${{ inputs.dry_run && '--dry-run' || '' }}
         run: |
-          cargo publish -p tfhe-csprng --token ${{ env.CRATES_TOKEN }} ${{ env.DRY_RUN }}
+          # DRY_RUN expansion cannot be double quoted when variable contains empty string otherwise cargo publish 
+          # would fail. This is safe since DRY_RUN is handled in the env section above.
+          # shellcheck disable=SC2086
+          cargo publish -p tfhe-csprng --token "${CRATES_TOKEN}" ${DRY_RUN}
       - name: Generate hash
         id: published_hash
         run: cd target/package && echo "pub_hash=$(sha256sum ./*.crate | base64 -w0)" >> "${GITHUB_OUTPUT}"
       - 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@c33737706dea87cd7784c687dadc9adf1be59990 # v2.3.2
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661 # v2.3.3
         env:
           SLACK_COLOR: failure
-          SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
-          SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
           SLACK_MESSAGE: "SLSA tfhe-csprng - hash comparison failure: (${{ env.ACTION_RUN_URL }})"
-          SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
-          SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
       - name: Slack Notification
-        if: ${{ failure() }}
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990 # v2.3.2
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661 # v2.3.3
         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-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_tfhe_fft.yml

@@ -11,6 +11,12 @@ on:
 
 env:
   ACTION_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
+  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 }}
+
+permissions: {}
 
 jobs:
   verify_tag:
@@ -29,11 +35,12 @@ jobs:
         uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
           fetch-depth: 0
-          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
+          persist-credentials: 'false'
+          token: ${{ secrets.REPO_CHECKOUT_TOKEN }}
       - name: Prepare package
         run: |
           cargo package -p tfhe-fft
-      - uses: actions/upload-artifact@65c4c4a1ddee5b72f698fdd19549f0f0fb45cf08 # v4.6.0
+      - uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
         with:
           name: crate
           path: target/package/*.crate
@@ -44,7 +51,7 @@ jobs:
   provenance:
     if: ${{ !inputs.dry_run  }}
     needs: [package]
-    uses: slsa-framework/slsa-github-generator/.github/workflows/generator_generic_slsa3.yml@v2.0.0
+    uses: slsa-framework/slsa-github-generator/.github/workflows/generator_generic_slsa3.yml@v2.1.0
     permissions:
       # Needed to detect the GitHub Actions environment
       actions: read
@@ -65,14 +72,18 @@ jobs:
         uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
           fetch-depth: 0
-          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
+          persist-credentials: 'false'
+          token: ${{ secrets.REPO_CHECKOUT_TOKEN }}
 
       - 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 }} ${{ env.DRY_RUN }}
+          # DRY_RUN expansion cannot be double quoted when variable contains empty string otherwise cargo publish 
+          # would fail. This is safe since DRY_RUN is handled in the env section above.
+          # shellcheck disable=SC2086
+          cargo publish -p tfhe-fft --token "${CRATES_TOKEN}" ${DRY_RUN}
 
       - name: Generate hash
         id: published_hash
@@ -81,23 +92,15 @@ 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@c33737706dea87cd7784c687dadc9adf1be59990 # v2.3.2
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661 # v2.3.3
         env:
           SLACK_COLOR: failure
-          SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
-          SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
           SLACK_MESSAGE: "SLSA tfhe-fft crate - hash comparison failure: (${{ env.ACTION_RUN_URL }})"
-          SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
-          SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
 
       - name: Slack Notification
-        if: ${{ failure() }}
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990 # v2.3.2
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661 # v2.3.3
         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

@@ -11,6 +11,12 @@ on:
 
 env:
   ACTION_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
+  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 }}
+
+permissions: {}
 
 jobs:
   verify_tag:
@@ -29,11 +35,12 @@ jobs:
         uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
           fetch-depth: 0
-          token: ${{ secrets.FHE_ACTIONS_TOKEN }}
+          persist-credentials: 'false'
+          token: ${{ secrets.REPO_CHECKOUT_TOKEN }}
       - name: Prepare package
         run: |
           cargo package -p tfhe-ntt
-      - uses: actions/upload-artifact@65c4c4a1ddee5b72f698fdd19549f0f0fb45cf08 # v4.6.0
+      - uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
         with:
           name: crate
           path: target/package/*.crate
@@ -44,7 +51,7 @@ jobs:
   provenance:
     if: ${{ !inputs.dry_run  }}
     needs: [package]
-    uses: slsa-framework/slsa-github-generator/.github/workflows/generator_generic_slsa3.yml@v2.0.0
+    uses: slsa-framework/slsa-github-generator/.github/workflows/generator_generic_slsa3.yml@v2.1.0
     permissions:
       # Needed to detect the GitHub Actions environment
       actions: read
@@ -65,13 +72,18 @@ jobs:
         uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
           fetch-depth: 0
+          persist-credentials: 'false'
+          token: ${{ secrets.REPO_CHECKOUT_TOKEN }}
 
       - 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 }} ${{ env.DRY_RUN }}
+          # DRY_RUN expansion cannot be double quoted when variable contains empty string otherwise cargo publish 
+          # would fail. This is safe since DRY_RUN is handled in the env section above.
+          # shellcheck disable=SC2086
+          cargo publish -p tfhe-ntt --token "${CRATES_TOKEN}" ${DRY_RUN}
 
       - name: Generate hash
         id: published_hash
@@ -80,23 +92,15 @@ 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@c33737706dea87cd7784c687dadc9adf1be59990 # v2.3.2
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661 # v2.3.3
         env:
           SLACK_COLOR: failure
-          SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
-          SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
           SLACK_MESSAGE: "SLSA tfhe-ntt crate - hash comparison failure: (${{ env.ACTION_RUN_URL }})"
-          SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
-          SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
 
       - name: Slack Notification
-        if: ${{ failure() }}
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990 # v2.3.2
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661 # v2.3.3
         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

@@ -2,14 +2,15 @@ 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 }}
+  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 }}
+
+permissions: {}
 
 jobs:
   verify_tag:
@@ -19,6 +20,7 @@ jobs:
       READ_ORG_TOKEN: ${{ secrets.READ_ORG_TOKEN }}
 
   package-derive:
+    name: Package tfhe-versionable-derive Release
     runs-on: ubuntu-latest
     outputs:
       hash: ${{ steps.hash.outputs.hash }}
@@ -27,10 +29,12 @@ jobs:
         uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
           fetch-depth: 0
+          persist-credentials: 'false'
+          token: ${{ secrets.REPO_CHECKOUT_TOKEN }}
       - name: Prepare package
         run: |
           cargo package -p tfhe-versionable-derive
-      - uses: actions/upload-artifact@65c4c4a1ddee5b72f698fdd19549f0f0fb45cf08 # v4.6.0
+      - uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
         with:
           name: crate-tfhe-versionable-derive
           path: target/package/*.crate
@@ -40,7 +44,7 @@ jobs:
 
   provenance-derive:
     needs: [package-derive]
-    uses: slsa-framework/slsa-github-generator/.github/workflows/generator_generic_slsa3.yml@v2.0.0
+    uses: slsa-framework/slsa-github-generator/.github/workflows/generator_generic_slsa3.yml@v2.1.0
     permissions:
       # Needed to detect the GitHub Actions environment
       actions: read
@@ -53,8 +57,8 @@ jobs:
       base64-subjects: ${{ needs.package-derive.outputs.hash }}
 
   publish_release-derive:
-    name: Publish tfhe-versionable Release
-    needs: [verify_tag, package-derive] # for comparing hashes
+    name: Publish tfhe-versionable-derive Release
+    needs: [ verify_tag, package-derive ] # for comparing hashes
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
@@ -64,7 +68,7 @@ jobs:
           persist-credentials: 'false'
           token: ${{ secrets.REPO_CHECKOUT_TOKEN }}
       - name: Download artifact
-        uses: actions/download-artifact@fa0a91b85d4f404e444e00e005971372dc801d16 # v4.1.8
+        uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
         with:
           name: crate-tfhe-versionable-derive
           path: target/package
@@ -72,34 +76,28 @@ jobs:
         env:
           CRATES_TOKEN: ${{ secrets.CARGO_REGISTRY_TOKEN }}
         run: |
-          cargo publish -p tfhe-versionable-derive --token ${{ env.CRATES_TOKEN }} ${{ env.DRY_RUN }}
+          cargo publish -p tfhe-versionable-derive --token "${CRATES_TOKEN}"
       - name: Generate hash
         id: published_hash
         run: cd target/package && echo "pub_hash=$(sha256sum ./*.crate | base64 -w0)" >> "${GITHUB_OUTPUT}"
       - name: Slack notification (hashes comparison)
         if: ${{ needs.package-derive.outputs.hash != steps.published_hash.outputs.pub_hash }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990 # v2.3.2
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661 # v2.3.3
         env:
           SLACK_COLOR: failure
-          SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
-          SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
           SLACK_MESSAGE: "SLSA tfhe-versionable-derive - hash comparison failure: (${{ env.ACTION_RUN_URL }})"
-          SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
-          SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
       - name: Slack Notification
-        if: ${{ failure() }}
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990 # v2.3.2
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661 # v2.3.3
         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-versionable-derive release finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
-          SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
-          SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
 
   package:
+    name: Package tfhe-versionable Release
+    needs: publish_release-derive
     runs-on: ubuntu-latest
     outputs:
       hash: ${{ steps.hash.outputs.hash }}
@@ -108,10 +106,12 @@ jobs:
         uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
+          persist-credentials: 'false'
+          token: ${{ secrets.REPO_CHECKOUT_TOKEN }}
       - name: Prepare package
         run: |
           cargo package -p tfhe-versionable
-      - uses: actions/upload-artifact@65c4c4a1ddee5b72f698fdd19549f0f0fb45cf08 # v4.6.0
+      - uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
         with:
           name: crate-tfhe-versionable
           path: target/package/*.crate
@@ -120,8 +120,8 @@ jobs:
         run: cd target/package && echo "hash=$(sha256sum ./*.crate | base64 -w0)" >> "${GITHUB_OUTPUT}"
 
   provenance:
-    needs: [package]
-    uses: slsa-framework/slsa-github-generator/.github/workflows/generator_generic_slsa3.yml@v2.0.0
+    needs: package
+    uses: slsa-framework/slsa-github-generator/.github/workflows/generator_generic_slsa3.yml@v2.1.0
     permissions:
       # Needed to detect the GitHub Actions environment
       actions: read
@@ -135,15 +135,17 @@ jobs:
 
   publish_release:
     name: Publish tfhe-versionable Release
-    needs: [package] # for comparing hashes
+    needs: package # for comparing hashes
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
         uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
           fetch-depth: 0
+          persist-credentials: 'false'
+          token: ${{ secrets.REPO_CHECKOUT_TOKEN }}
       - name: Download artifact
-        uses: actions/download-artifact@fa0a91b85d4f404e444e00e005971372dc801d16 # v4.1.8
+        uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
         with:
           name: crate-tfhe-versionable
           path: target/package
@@ -151,32 +153,21 @@ jobs:
         env:
           CRATES_TOKEN: ${{ secrets.CARGO_REGISTRY_TOKEN }}
         run: |
-          cargo publish -p tfhe-versionable --token ${{ env.CRATES_TOKEN }} ${{ env.DRY_RUN }}
-
+          cargo publish -p tfhe-versionable --token "${CRATES_TOKEN}"
       - name: Generate hash
         id: published_hash
         run: cd target/package && echo "pub_hash=$(sha256sum ./*.crate | base64 -w0)" >> "${GITHUB_OUTPUT}"
-
       - 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@c33737706dea87cd7784c687dadc9adf1be59990 # v2.3.2
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661 # v2.3.3
         env:
           SLACK_COLOR: failure
-          SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
-          SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
           SLACK_MESSAGE: "SLSA tfhe-versionable - hash comparison failure: (${{ env.ACTION_RUN_URL }})"
-          SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
-          SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
-
       - name: Slack Notification
-        if: ${{ failure() }}
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990 # v2.3.2
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661 # v2.3.3
         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-versionable release finished with status: ${{ job.status }}. (${{ env.ACTION_RUN_URL }})"
-          SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
-          SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}

.github/workflows/make_release_zk_pok.yml

@@ -10,6 +10,12 @@ on:
 
 env:
   ACTION_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
+  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 }}
+
+permissions: {}
 
 jobs:
   package:
@@ -21,10 +27,12 @@ jobs:
           uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
           with:
             fetch-depth: 0
+            persist-credentials: 'false'
+            token: ${{ secrets.REPO_CHECKOUT_TOKEN }}
         - name: Prepare package
           run: |
             cargo package -p tfhe-zk-pok
-        - uses: actions/upload-artifact@65c4c4a1ddee5b72f698fdd19549f0f0fb45cf08 # v4.6.0
+        - uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
           with:
             name: crate-zk-pok
             path: target/package/*.crate
@@ -34,7 +42,7 @@ jobs:
   provenance:
     if: ${{ !inputs.dry_run  }}
     needs: [package]
-    uses: slsa-framework/slsa-github-generator/.github/workflows/generator_generic_slsa3.yml@v2.0.0
+    uses: slsa-framework/slsa-github-generator/.github/workflows/generator_generic_slsa3.yml@v2.1.0
     permissions:
       # Needed to detect the GitHub Actions environment
       actions: read
@@ -64,7 +72,7 @@ jobs:
           persist-credentials: 'false'
           token: ${{ secrets.REPO_CHECKOUT_TOKEN }}
       - name: Download artifact
-        uses: actions/download-artifact@fa0a91b85d4f404e444e00e005971372dc801d16 # v4.1.8
+        uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
         with:
           name: crate-zk-pok
           path: target/package
@@ -73,29 +81,24 @@ jobs:
           CRATES_TOKEN: ${{ secrets.CARGO_REGISTRY_TOKEN }}
           DRY_RUN: ${{ inputs.dry_run && '--dry-run' || '' }}
         run: |
-          cargo publish -p tfhe-zk-pok --token ${{ env.CRATES_TOKEN }} ${{ env.DRY_RUN }}
+          # DRY_RUN expansion cannot be double quoted when variable contains empty string otherwise cargo publish 
+          # would fail. This is safe since DRY_RUN is handled in the env section above.
+          # shellcheck disable=SC2086
+          cargo publish -p tfhe-zk-pok --token "${CRATES_TOKEN}" ${DRY_RUN}
       - name: Verify hash
         id: published_hash
         run: cd target/package && echo "pub_hash=$(sha256sum ./*.crate | base64 -w0)" >> "${GITHUB_OUTPUT}"
       - 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@c33737706dea87cd7784c687dadc9adf1be59990 # v2.3.2
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661 # v2.3.3
         env:
           SLACK_COLOR: failure
-          SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
-          SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
           SLACK_MESSAGE: "SLSA tfhe-zk-pok crate - hash comparison failure: (${{ env.ACTION_RUN_URL }})"
-          SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
-          SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
       - name: Slack Notification
-        if: ${{ failure() }}
+        if: ${{ failure() || (cancelled() && github.event_name != 'pull_request') }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990 # v2.3.2
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661 # v2.3.3
         env:
           SLACK_COLOR: ${{ job.status }}
-          SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
-          SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
           SLACK_MESSAGE: "tfhe-zk-pok release failed: (${{ env.ACTION_RUN_URL }})"
-          SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
-          SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}

.github/workflows/parameters_check.yml

@@ -12,12 +12,17 @@ on:
       - "main"
   workflow_dispatch:
 
+permissions: {}
+
 jobs:
   params-curves-security-check:
     runs-on: large_ubuntu_16-22.04
     steps:
       - name: Checkout tfhe-rs
         uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          persist-credentials: 'false'
+          token: ${{ secrets.REPO_CHECKOUT_TOKEN }}
 
       - name: Checkout lattice-estimator
         uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
@@ -25,6 +30,7 @@ jobs:
           repository: malb/lattice-estimator
           path: lattice_estimator
           ref: 'e80ec6bbbba212428b0e92d0467c18629cf9ed67'
+          persist-credentials: 'false'
 
       - name: Install Sage
         run: |
@@ -42,7 +48,7 @@ jobs:
       - name: Slack Notification
         if: ${{ always() }}
         continue-on-error: true
-        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
+        uses: rtCamp/action-slack-notify@e31e87e03dd19038e411e38ae27cbad084a90661
         env:
           SLACK_COLOR: ${{ job.status }}
           SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}

.github/workflows/placeholder_workflow.yml

@@ -4,6 +4,8 @@ name: Placeholder Workflow
 on:
   workflow_dispatch:
 
+permissions: {}
+
 jobs:
   placeholder:
     name: Placeholder

.github/workflows/sync_on_push.yml

@@ -7,6 +7,8 @@ on:
       - 'main'
   workflow_dispatch:
 
+permissions: {}
+
 jobs:
   sync-repo:
     if: ${{ github.repository == 'zama-ai/tfhe-rs' }}

.github/workflows/verify_tagged_commit.yml

@@ -9,6 +9,8 @@ on:
       READ_ORG_TOKEN:
         required: true
 
+permissions: {}
+
 jobs:
   checks:
     runs-on: ubuntu-latest
@@ -26,7 +28,10 @@ jobs:
 
       - name: Actor authorized
         run: |
-          if [ "${{ steps.actor_check.outputs.authorized }}" == "false" ]; then
-            echo "Actor '${{ github.triggering_actor }}' is not authorized to perform release"
+          if [ "${ACTOR_CHECK_OUTPUT}" == "false" ]; then
+            echo "Actor '${TRIGGERING_ACTOR}' is not authorized to perform release"
             exit 1
           fi
+        env:
+          TRIGGERING_ACTOR: ${{ github.triggering_actor }}
+          ACTOR_CHECK_OUTPUT: ${{ steps.actor_check.outputs.authorized }}

.gitignore

@@ -34,6 +34,9 @@ package-lock.json
 
 # Python .env
 .env
+__pycache__
 
 # Dir used for backward compatibility test data
-tests/tfhe-backward-compat-data/
+# First directive is to ignore symlinks
+tests/tfhe-backward-compat-data
+ci/

.lfsconfig

@@ -0,0 +1,2 @@
+[lfs]
+  fetchexclude = *

CODEOWNERS

@@ -0,0 +1,18 @@
+# Specifying a path without code owners means that path won't have owners and is akin to a negation
+# i.e. the `core_crypto` dir is owned and needs owner approval/review, but not the `gpu` sub dir
+# See https://docs.github.com/en/repositories/managing-your-repositorys-settings-and-features/customizing-your-repository/about-code-owners#example-of-a-codeowners-file
+/tfhe/src/core_crypto/                  @IceTDrinker
+/tfhe/src/core_crypto/gpu
+
+/tfhe/src/shortint/                     @mayeul-zama
+
+/tfhe/src/integer/                      @tmontaigu
+/tfhe/src/integer/gpu
+
+/tfhe/src/high_level_api/               @tmontaigu
+
+/Makefile                               @IceTDrinker @soonum
+
+/.github/                               @soonum
+
+/CODEOWNERS                             @IceTDrinker

CONTRIBUTING.md

@@ -0,0 +1,235 @@
+# Contributing to TFHE-rs
+
+This document provides guidance on how to contribute to **TFHE-rs**.
+
+There are two ways to contribute:
+
+- **Report issues:** Open issues on GitHub to report bugs, suggest improvements, or note typos.
+- **Submit codes**: To become an official contributor, you must sign our Contributor License Agreement (CLA). Our CLA-bot will guide you through this process when you open your first pull request.
+
+## 1. Setting up the project
+
+Start by [forking](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/fork-a-repo) the **TFHE-rs** repository.
+
+{% hint style="info" %}
+- **Rust version**:  Ensure that you use a Rust version >= 1.81 to compile **TFHE-rs**.
+- **Incompatibility**: 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**.
+- **Performance**: For optimal performance, it is highly recommended to run **TFHE-rs** code in release mode with cargo's `--release` flag.
+{% endhint %}
+
+To get more details about the library, please refer to the [documentation](https://docs.zama.ai/tfhe-rs).
+
+## 2. Creating a new branch
+
+When creating your branch, make sure to use the following format :
+
+```
+git checkout -b {feat|fix|docs|chore…}/short_description
+```
+
+For example:
+
+```
+git checkout -b feat/new_feature_X
+```
+
+## 3. Before committing
+
+### 3.1 Linting
+
+Each commit to **TFHE-rs** should conform to the standards of the project. In particular, every source code, docker or workflows files should be linted to prevent programmatic and stylistic errors.
+
+- Rust source code linters: `clippy`
+- Typescript/Javascript source code linters: `eslint`, `prettier`
+
+To apply automatic code formatting, run:
+
+```
+make fmt
+```
+
+You can perform linting of all Cargo targets with:
+
+```
+make clippy_all_targets
+```
+
+### 3.2 Testing
+
+Your contributions must include comprehensive documentation and tests without breaking existing tests. To run pre-commit checks, execute:
+
+```
+make pcc
+```
+
+This command ensure that all the targets in the library are building correctly.
+For a faster check, use:
+
+```
+make fpcc
+```
+
+If you're contributing to GPU code, run also:
+
+```
+make pcc_gpu
+```
+
+Unit testing suites are heavy and can require a lot of computing power and RAM availability.
+Whilst tests are run automatically in continuous integration pipeline, you can run tests locally.
+
+All unit tests have a command formatted as:
+
+```
+make test_*
+```
+
+Run `make help` to display a list of all the commands available.
+
+To quickly test your changes locally, follow these steps:
+ 1. Locate where the code has changed.
+ 2. Add (or modify) a Cargo test filter to the corresponding `make` target in Makefile.
+ 3. Run the target.
+
+{% hint style="success" %}
+`make test_<something>` will print the underlying cargo command in STDOUT. You can quickly test your changes by copy/pasting the command and then modify it to suit your needs.
+{% endhint %}
+
+For example, if you made changes in `tfhe/src/integer/*`, you can test them with the following steps:
+ 1. In `test_integer` target, replace the filter `-- integer::` by `-- my_new_test`.
+ 2. Run `make test_integer`.
+
+## 4. Committing
+
+**TFHE-rs** follows the conventional commit specification to maintain a consistent commit history, essential for Semantic Versioning ([semver.org](https://semver.org/)).
+Commit messages are automatically checked in CI and will be rejected if they do not comply, so make sure that you follow the commit conventions detailed on [this page](https://www.conventionalcommits.org/en/v1.0.0/).
+
+## 5. Rebasing
+
+Before creating a pull request, rebase your branch on the repository's `main` branch. Merge commits are not permitted, thus rebasing ensures fewer conflicts and a smoother PR review process.
+
+## 6. Opening a Pull Request
+
+Once your changes are ready, open a pull request.
+
+For instructions on creating a PR from a fork, refer to GitHub's [official documentation](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/creating-a-pull-request-from-a-fork).
+
+## 7. Continuous integration
+
+Before a pull request can be merged, several test suites run automatically. Below is an overview of the CI process:
+
+```mermaid
+---
+title: Continuous Integration Process
+---
+sequenceDiagram
+    autonumber
+
+    participant Contributor
+    participant GitHub
+    participant Reviewer
+    participant CI-pipeline
+
+    Contributor ->> GitHub: Open pull-request
+    GitHub -->> Contributor: Ask for CLA signing (once)
+    loop
+        Reviewer ->> GitHub: Review code
+        Reviewer ->> CI-pipeline: Approve workflows (short-run)
+        CI-pipeline -->> GitHub: Send checks results
+        Contributor ->> GitHub: Make changes
+    end
+    Reviewer ->> GitHub: Pull-request approval
+    Reviewer ->> CI-pipeline: Approve workflows (long-run)
+    CI-pipeline -->> GitHub: Send checks results
+    Reviewer -->> GitHub: Merge if pipeline green
+```
+
+{% hint style="info" %}
+
+## Useful details:
+
+- pipeline is triggered by humans
+- review team is located in Paris timezone, pipeline launch will most likely happen during office hours
+- direct changes to CI related files are not allowed for external contributors
+- run `make pcc` to fix any build errors before pushing commits
+{% endhint %}
+
+## 8. Data versioning
+
+Data serialized with TFHE-rs must remain backward compatible. This is done using the [tfhe-versionable](https://crates.io/crates/tfhe-versionable) crate.
+
+If you modify a type that derives `Versionize` in a backward-incompatible way, an upgrade implementation must be provided.
+
+For example, these changes are data breaking:
+ * Adding a field to a struct.
+ * Changing the order of the fields within a struct or the variants within an enum.
+ * Renaming a field of a struct or a variant of an enum.
+ * Changing the type of field in a struct or a variant in an enum.
+
+On the contrary, these changes are *not* data breaking:
+ * Renaming a type (unless it implements the `Named` trait).
+ * Adding a variant to the end of an enum.
+
+## Example: adding a field
+
+Suppose you want to add an i32 field to a type named `MyType`. The original type is defined as:
+```rust
+#[derive(Serialize, Deserialize, Versionize)]
+#[versionize(MyTypeVersions)]
+struct MyType {
+  val: u64,
+}
+```
+And you want to change it to:
+```rust
+#[derive(Serialize, Deserialize, Versionize)]
+#[versionize(MyTypeVersions)]
+struct MyType {
+  val: u64,
+  other_val: i32
+}
+```
+
+Follow these steps:
+
+ 1. Navigate to the definition of the dispatch enum of this type. This is the type inside the `#[versionize(MyTypeVersions)]` macro attribute. In general, this type has the same name as the base type with a `Versions` suffix. You should find something like
+
+```rust
+#[derive(VersionsDispatch)]
+enum MyTypeVersions {
+  V0(MyTypeV0),
+  V1(MyType)
+}
+```
+
+ 2. Add a new variant to the enum to preserve the previous version of the type. You can simply copy and paste the previous definition of the type and add a version suffix:
+
+```rust
+#[derive(Version)]
+struct MyTypeV1 {
+  val: u64,
+}
+
+#[derive(VersionsDispatch)]
+enum MyTypeVersions {
+  V0(MyTypeV0),
+  V1(MyTypeV1),
+  V2(MyType) // Here this points to your modified type
+}
+```
+
+ 3. Implement the `Upgrade` trait to define how we should go from the previous version to the current version:
+```rust
+impl Upgrade<MyType> for MyTypeV1 {
+  type Error = Infallible;
+
+   fn upgrade(self) -> Result<MyType, Self::Error> {
+       Ok(MyType {
+           val: self.val,
+           other_val: 0
+        })
+   }
+}
+```
+
+ 4. Fix the upgrade target of the previous version. In this example, `impl Upgrade<MyType> for MyTypeV0 {` should simply be changed to `impl Upgrade<MyTypeV1> for MyTypeV0 {`

Cargo.toml

@@ -2,26 +2,33 @@
 resolver = "2"
 members = [
     "tfhe",
+    "tfhe-benchmark",
     "tfhe-fft",
     "tfhe-ntt",
     "tfhe-zk-pok",
     "tasks",
-    "apps/trivium",
     "tfhe-csprng",
     "backends/tfhe-cuda-backend",
+    "backends/tfhe-hpu-backend",
     "utils/tfhe-versionable",
     "utils/tfhe-versionable-derive",
+    "utils/param_dedup",
     "tests",
+    "mockups/tfhe-hpu-mockup",
 ]
 
-exclude = ["tests/backward_compatibility_tests", "utils/tfhe-lints"]
+exclude = [
+    "tests/backward_compatibility_tests",
+    "utils/tfhe-lints",
+    "apps/trivium",
+]
 [workspace.dependencies]
 aligned-vec = { version = "0.6", default-features = false }
 bytemuck = "1.14.3"
 dyn-stack = { version = "0.11", default-features = false }
 itertools = "0.14"
 num-complex = "0.4"
-pulp = { version = "0.20", default-features = false }
+pulp = { version = "0.21", default-features = false }
 rand = "0.8"
 rayon = "1"
 serde = { version = "1.0", default-features = false }

Makefile

@@ -2,6 +2,7 @@ SHELL:=$(shell /usr/bin/env which bash)
 OS:=$(shell uname)
 RS_CHECK_TOOLCHAIN:=$(shell cat toolchain.txt | tr -d '\n')
 CARGO_RS_CHECK_TOOLCHAIN:=+$(RS_CHECK_TOOLCHAIN)
+CARGO_BUILD_JOBS=default
 CPU_COUNT=$(shell ./scripts/cpu_count.sh)
 RS_BUILD_TOOLCHAIN:=stable
 CARGO_RS_BUILD_TOOLCHAIN:=+$(RS_BUILD_TOOLCHAIN)
@@ -18,6 +19,8 @@ FAST_BENCH?=FALSE
 NIGHTLY_TESTS?=FALSE
 BENCH_OP_FLAVOR?=DEFAULT
 BENCH_TYPE?=latency
+BENCH_PARAM_TYPE?=classical
+BENCH_PARAMS_SET?=default
 NODE_VERSION=22.6
 BACKWARD_COMPAT_DATA_URL=https://github.com/zama-ai/tfhe-backward-compat-data.git
 BACKWARD_COMPAT_DATA_BRANCH?=$(shell ./scripts/backward_compat_data_version.py)
@@ -53,6 +56,9 @@ REGEX_PATTERN?=''
 TFHECUDA_SRC=backends/tfhe-cuda-backend/cuda
 TFHECUDA_BUILD=$(TFHECUDA_SRC)/build
 
+# tfhe-hpu-backend
+HPU_CONFIG=v80
+
 # Exclude these files from coverage reports
 define COVERAGE_EXCLUDED_FILES
 --exclude-files apps/trivium/src/trivium/* \
@@ -161,6 +167,12 @@ install_typos_checker: install_rs_build_toolchain
 	cargo $(CARGO_RS_BUILD_TOOLCHAIN) install typos-cli || \
 	( echo "Unable to install typos-cli, unknown error." && exit 1 )
 
+.PHONY: install_zizmor # Install zizmor workflow security checker
+install_zizmor: install_rs_build_toolchain
+	@zizmor --version > /dev/null 2>&1 || \
+	cargo $(CARGO_RS_BUILD_TOOLCHAIN) install zizmor || \
+	( echo "Unable to install zizmor, unknown error." && exit 1 )
+
 .PHONY: setup_venv # Setup Python virtualenv for wasm tests
 setup_venv:
 	python3 -m venv venv
@@ -282,17 +294,31 @@ check_typos: install_typos_checker
 .PHONY: clippy_gpu # Run clippy lints on tfhe with "gpu" enabled
 clippy_gpu: install_rs_check_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" clippy \
-		--features=boolean,shortint,integer,internal-keycache,gpu \
+		--features=boolean,shortint,integer,internal-keycache,gpu,pbs-stats,extended-types,zk-pok \
 		--all-targets \
 		-p $(TFHE_SPEC) -- --no-deps -D warnings
 
 .PHONY: check_gpu # Run check on tfhe with "gpu" enabled
 check_gpu: install_rs_check_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" check \
-		--features=boolean,shortint,integer,internal-keycache,gpu \
+		--features=boolean,shortint,integer,internal-keycache,gpu,pbs-stats \
 		--all-targets \
 		-p $(TFHE_SPEC)
 
+.PHONY: clippy_hpu # Run clippy lints on tfhe with "hpu" enabled
+clippy_hpu: install_rs_check_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" clippy \
+		--features=boolean,shortint,integer,internal-keycache,hpu,pbs-stats,extended-types \
+		--all-targets \
+		-p $(TFHE_SPEC) -- --no-deps -D warnings
+
+.PHONY: clippy_gpu_hpu # Run clippy lints on tfhe with "gpu" and "hpu" enabled
+clippy_gpu_hpu: install_rs_check_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" clippy \
+		--features=boolean,shortint,integer,internal-keycache,gpu,hpu,pbs-stats,extended-types,zk-pok \
+		--all-targets \
+		-p $(TFHE_SPEC) -- --no-deps -D warnings
+
 .PHONY: fix_newline # Fix newline at end of file issues to be UNIX compliant
 fix_newline: check_linelint_installed
 	linelint -a .
@@ -305,6 +331,10 @@ check_newline: check_linelint_installed
 lint_workflow: check_actionlint_installed
 	actionlint
 
+.PHONY: check_workflow_security # Run zizmor security checker on GitHub workflows
+check_workflow_security: install_zizmor
+	zizmor --persona pedantic .
+
 .PHONY: clippy_core # Run clippy lints on core_crypto with and without experimental features
 clippy_core: install_rs_check_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" clippy \
@@ -348,6 +378,9 @@ clippy_integer: install_rs_check_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" clippy \
 		--features=integer,experimental \
 		-p $(TFHE_SPEC) -- --no-deps -D warnings
+	RUSTFLAGS="$(RUSTFLAGS)" cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" clippy \
+		--features=integer,experimental,extended-types \
+		-p $(TFHE_SPEC) -- --no-deps -D warnings
 
 .PHONY: clippy # Run clippy lints enabling the boolean, shortint, integer
 clippy: install_rs_check_toolchain
@@ -361,7 +394,7 @@ clippy_rustdoc: install_rs_check_toolchain
 		echo "WARNING: skipped clippy_rustdoc, unsupported OS $(OS)"; \
 		exit 0; \
 	fi && \
-	CLIPPYFLAGS="-D warnings" RUSTDOCFLAGS="--no-run --nocapture --test-builder ./scripts/clippy_driver.sh -Z unstable-options" \
+	CARGO_TERM_QUIET=true CLIPPYFLAGS="-D warnings" RUSTDOCFLAGS="--no-run --nocapture --test-builder ./scripts/clippy_driver.sh -Z unstable-options" \
 		cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" test --doc \
 		--features=boolean,shortint,integer,zk-pok,pbs-stats,strings,experimental \
 		-p $(TFHE_SPEC)
@@ -372,7 +405,7 @@ clippy_rustdoc_gpu: install_rs_check_toolchain
 		echo "WARNING: skipped clippy_rustdoc_gpu, unsupported OS $(OS)"; \
 		exit 0; \
 	fi && \
-	CLIPPYFLAGS="-D warnings" RUSTDOCFLAGS="--no-run --nocapture --test-builder ./scripts/clippy_driver.sh -Z unstable-options" \
+	CARGO_TERM_QUIET=true CLIPPYFLAGS="-D warnings" RUSTDOCFLAGS="--no-run --nocapture --test-builder ./scripts/clippy_driver.sh -Z unstable-options" \
 		cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" test --doc \
 		--features=boolean,shortint,integer,zk-pok,pbs-stats,strings,experimental,gpu \
 		-p $(TFHE_SPEC)
@@ -380,16 +413,16 @@ clippy_rustdoc_gpu: install_rs_check_toolchain
 .PHONY: clippy_c_api # Run clippy lints enabling the boolean, shortint and the C API
 clippy_c_api: install_rs_check_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" clippy \
-		--features=boolean-c-api,shortint-c-api,high-level-c-api \
+		--features=boolean-c-api,shortint-c-api,high-level-c-api,extended-types \
 		-p $(TFHE_SPEC) -- --no-deps -D warnings
 
 .PHONY: clippy_js_wasm_api # Run clippy lints enabling the boolean, shortint, integer and the js wasm API
 clippy_js_wasm_api: install_rs_check_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" clippy \
-		--features=boolean-client-js-wasm-api,shortint-client-js-wasm-api,integer-client-js-wasm-api,high-level-client-js-wasm-api,zk-pok \
+		--features=boolean-client-js-wasm-api,shortint-client-js-wasm-api,integer-client-js-wasm-api,high-level-client-js-wasm-api,zk-pok,extended-types \
 		-p $(TFHE_SPEC) -- --no-deps -D warnings
 	RUSTFLAGS="$(RUSTFLAGS)" cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" clippy \
-		--features=boolean-client-js-wasm-api,shortint-client-js-wasm-api,integer-client-js-wasm-api,high-level-client-js-wasm-api \
+		--features=boolean-client-js-wasm-api,shortint-client-js-wasm-api,integer-client-js-wasm-api,high-level-client-js-wasm-api,extended-types \
 		-p $(TFHE_SPEC) -- --no-deps -D warnings
 
 .PHONY: clippy_tasks # Run clippy lints on helper tasks crate.
@@ -399,16 +432,21 @@ clippy_tasks: install_rs_check_toolchain
 
 .PHONY: clippy_trivium # Run clippy lints on Trivium app
 clippy_trivium: install_rs_check_toolchain
-	RUSTFLAGS="$(RUSTFLAGS)" cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" clippy --all-targets \
+	cd apps/trivium; RUSTFLAGS="$(RUSTFLAGS)" cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" clippy --all-targets \
 		-p tfhe-trivium -- --no-deps -D warnings
 
+.PHONY: clippy_ws_tests # Run clippy on the workspace level tests
+clippy_ws_tests: install_rs_check_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" clippy --tests \
+		-p tests --features=shortint,integer,zk-pok -- --no-deps -D warnings
+
 .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=boolean,shortint,integer,internal-keycache,zk-pok,strings \
+		--features=boolean,shortint,integer,internal-keycache,zk-pok,strings,pbs-stats,extended-types \
 		-p $(TFHE_SPEC) -- --no-deps -D warnings
 	RUSTFLAGS="$(RUSTFLAGS)" cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" clippy --all-targets \
-		--features=boolean,shortint,integer,internal-keycache,zk-pok,strings,experimental \
+		--features=boolean,shortint,integer,internal-keycache,zk-pok,strings,pbs-stats,extended-types,experimental \
 		-p $(TFHE_SPEC) -- --no-deps -D warnings
 
 .PHONY: clippy_tfhe_csprng # Run clippy lints on tfhe-csprng
@@ -431,12 +469,18 @@ clippy_versionable: install_rs_check_toolchain
 .PHONY: clippy_tfhe_lints # Run clippy lints on tfhe-lints
 clippy_tfhe_lints: install_cargo_dylint # the toolchain is selected with toolchain.toml
 	cd utils/tfhe-lints && \
+	rustup toolchain install && \
 	cargo clippy --all-targets -- --no-deps -D warnings
 
+.PHONY: clippy_param_dedup # Run clippy lints on param_dedup tool
+clippy_param_dedup: install_rs_check_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" clippy --all-targets \
+		-p param_dedup -- --no-deps -D warnings
+
 .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_tfhe_csprng clippy_zk_pok clippy_trivium \
-clippy_versionable clippy_tfhe_lints
+clippy_versionable clippy_tfhe_lints clippy_ws_tests clippy_bench clippy_param_dedup
 
 .PHONY: clippy_fast # Run main clippy targets
 clippy_fast: clippy_rustdoc clippy clippy_all_targets clippy_c_api clippy_js_wasm_api clippy_tasks \
@@ -447,6 +491,11 @@ 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: clippy_hpu_backend # Run clippy lints on the tfhe-hpu-backend
+clippy_hpu_backend: install_rs_check_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" clippy --all-targets \
+		-p tfhe-hpu-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 && "$(MAKE)" fmt_gpu && \
@@ -506,13 +555,13 @@ build_tfhe_coverage: install_rs_build_toolchain
 .PHONY: build_c_api # Build the C API for boolean, shortint and integer
 build_c_api: install_rs_check_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_CHECK_TOOLCHAIN) build --profile $(CARGO_PROFILE) \
-		--features=boolean-c-api,shortint-c-api,high-level-c-api,zk-pok \
+		--features=boolean-c-api,shortint-c-api,high-level-c-api,zk-pok,extended-types \
 		-p $(TFHE_SPEC)
 
 .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=boolean-c-api,shortint-c-api,high-level-c-api,zk-pok,gpu \
+		--features=boolean-c-api,shortint-c-api,high-level-c-api,zk-pok,extended-types,gpu \
 		-p $(TFHE_SPEC)
 
 .PHONY: build_c_api_experimental_deterministic_fft # Build the C API for boolean, shortint and integer with experimental deterministic FFT
@@ -526,7 +575,7 @@ build_web_js_api: install_rs_build_toolchain install_wasm_pack
 	cd tfhe && \
 	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
+		-- --features=boolean-client-js-wasm-api,shortint-client-js-wasm-api,integer-client-js-wasm-api,zk-pok,extended-types
 
 .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
@@ -534,7 +583,7 @@ build_web_js_api_parallel: install_rs_check_toolchain install_wasm_pack
 	rustup component add rust-src --toolchain $(RS_CHECK_TOOLCHAIN) && \
 	RUSTFLAGS="$(WASM_RUSTFLAGS) -C target-feature=+atomics,+bulk-memory" rustup run $(RS_CHECK_TOOLCHAIN) \
 		wasm-pack build --release --target=web \
-		-- --features=boolean-client-js-wasm-api,shortint-client-js-wasm-api,integer-client-js-wasm-api,parallel-wasm-api,zk-pok \
+		-- --features=boolean-client-js-wasm-api,shortint-client-js-wasm-api,integer-client-js-wasm-api,parallel-wasm-api,zk-pok,extended-types \
 		-Z build-std=panic_abort,std && \
 	find pkg/snippets -type f -iname workerHelpers.js -exec sed -i "s|const pkg = await import('..\/..\/..');|const pkg = await import('..\/..\/..\/tfhe.js');|" {} \;
 	jq '.files += ["snippets"]' tfhe/pkg/package.json > tmp_pkg.json && mv -f tmp_pkg.json tfhe/pkg/package.json
@@ -544,7 +593,7 @@ build_node_js_api: install_rs_build_toolchain install_wasm_pack
 	cd tfhe && \
 	RUSTFLAGS="$(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
+		-- --features=boolean-client-js-wasm-api,shortint-client-js-wasm-api,integer-client-js-wasm-api,zk-pok,extended-types
 
 .PHONY: build_tfhe_csprng # Build tfhe_csprng
 build_tfhe_csprng: install_rs_build_toolchain
@@ -596,7 +645,7 @@ test_core_crypto_gpu: install_rs_build_toolchain
 .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=integer,gpu -p $(TFHE_SPEC) -- integer::gpu::server_key:: --test-threads=6
+		--features=integer,gpu -p $(TFHE_SPEC) -- integer::gpu::server_key:: --test-threads=4
 	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --doc --profile $(CARGO_PROFILE) \
 		--features=integer,gpu -p $(TFHE_SPEC) -- integer::gpu::server_key::
 
@@ -676,6 +725,28 @@ test_signed_integer_multi_bit_gpu_ci: install_rs_check_toolchain install_cargo_n
 		--cargo-profile "$(CARGO_PROFILE)" --multi-bit --backend "gpu" \
 		--signed-only --tfhe-package "$(TFHE_SPEC)"
 
+.PHONY: test_integer_hpu_ci # Run the tests for integer ci on hpu backend
+test_integer_hpu_ci: install_rs_check_toolchain install_cargo_nextest
+	cargo test --release -p $(TFHE_SPEC) --features hpu-v80 --test hpu
+
+.PHONY: test_integer_hpu_mockup_ci # Run the tests for integer ci on hpu backend and mockup
+test_integer_hpu_mockup_ci: install_rs_check_toolchain install_cargo_nextest
+	source ./setup_hpu.sh --config sim ; \
+	cargo build --release --bin hpu_mockup; \
+    coproc target/release/hpu_mockup --params mockups/tfhe-hpu-mockup/params/tuniform_64b_pfail64_psi64.toml > mockup.log; \
+	HPU_TEST_ITER=1 \
+	cargo test --profile devo -p $(TFHE_SPEC) --features hpu --test hpu -- u32 && \
+	kill %1
+
+.PHONY: test_integer_hpu_mockup_ci_fast # Run the quick tests for integer ci on hpu backend and mockup.
+test_integer_hpu_mockup_ci_fast: install_rs_check_toolchain install_cargo_nextest
+	source ./setup_hpu.sh --config sim ; \
+	cargo build --profile devo --bin hpu_mockup; \
+    coproc target/devo/hpu_mockup --params mockups/tfhe-hpu-mockup/params/tuniform_64b_fast.toml > mockup.log; \
+	HPU_TEST_ITER=1 \
+	cargo test --profile devo -p $(TFHE_SPEC) --features hpu --test hpu -- u32 && \
+	kill %1
+
 .PHONY: test_boolean # Run the tests of the boolean module
 test_boolean: install_rs_build_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --profile $(CARGO_PROFILE) \
@@ -828,9 +899,25 @@ test_high_level_api: install_rs_build_toolchain
 
 test_high_level_api_gpu: install_rs_build_toolchain install_cargo_nextest
 	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) nextest run --cargo-profile $(CARGO_PROFILE) \
-		--features=integer,internal-keycache,gpu -p $(TFHE_SPEC) \
+		--test-threads=4 --features=integer,internal-keycache,gpu,zk-pok -p $(TFHE_SPEC) \
 		-E "test(/high_level_api::.*gpu.*/)"
 
+test_high_level_api_hpu: install_rs_build_toolchain install_cargo_nextest
+ifeq ($(HPU_CONFIG), v80)
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) nextest run --cargo-profile $(CARGO_PROFILE) \
+		--build-jobs=$(CARGO_BUILD_JOBS) \
+		--test-threads=1 \
+		--features=integer,internal-keycache,hpu,hpu-v80 -p $(TFHE_SPEC) \
+		-E "test(/high_level_api::.*hpu.*/)"
+else
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) nextest run --cargo-profile $(CARGO_PROFILE) \
+		--build-jobs=$(CARGO_BUILD_JOBS) \
+		--test-threads=1 \
+		--features=integer,internal-keycache,hpu -p $(TFHE_SPEC) \
+		-E "test(/high_level_api::.*hpu.*/)"
+endif
+
+
 .PHONY: test_strings # Run the tests for strings ci
 test_strings: install_rs_build_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --profile $(CARGO_PROFILE) \
@@ -868,12 +955,12 @@ test_examples: test_sha256_bool test_regex_engine
 
 .PHONY: test_trivium # Run tests for trivium
 test_trivium: install_rs_build_toolchain
-	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --profile $(CARGO_PROFILE) \
+	cd apps/trivium; RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --profile $(CARGO_PROFILE) \
 		-p tfhe-trivium -- --test-threads=1 trivium::
 
 .PHONY: test_kreyvium # Run tests for kreyvium
 test_kreyvium: install_rs_build_toolchain
-	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --profile $(CARGO_PROFILE) \
+	cd apps/trivium; RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --profile $(CARGO_PROFILE) \
 		-p tfhe-trivium -- --test-threads=1 kreyvium::
 
 .PHONY: test_tfhe_csprng # Run tfhe-csprng tests
@@ -907,6 +994,7 @@ test_versionable: install_rs_build_toolchain
 .PHONY: test_tfhe_lints # Run test on tfhe-lints
 test_tfhe_lints: install_cargo_dylint
 	cd utils/tfhe-lints && \
+	rustup toolchain install && \
 	cargo test
 
 # The backward compat data repo holds historical binary data but also rust code to generate and load them.
@@ -947,8 +1035,8 @@ lint_doc: install_rs_check_toolchain
 lint_docs: lint_doc
 
 .PHONY: format_doc_latex # Format the documentation latex equations to avoid broken rendering.
-format_doc_latex:
-	RUSTFLAGS="" cargo xtask format_latex_doc
+format_doc_latex: install_rs_build_toolchain
+	RUSTFLAGS="" cargo "$(CARGO_RS_BUILD_TOOLCHAIN)" xtask format_latex_doc
 	@"$(MAKE)" --no-print-directory fmt
 	@printf "\n===============================\n\n"
 	@printf "Please manually inspect changes made by format_latex_doc, rustfmt can break equations \
@@ -956,8 +1044,8 @@ format_doc_latex:
 	@printf "\n===============================\n"
 
 .PHONY: check_md_docs_are_tested # Checks that the rust codeblocks in our .md files are tested
-check_md_docs_are_tested:
-	RUSTFLAGS="" cargo xtask check_tfhe_docs_are_tested
+check_md_docs_are_tested: install_rs_build_toolchain
+	RUSTFLAGS="" cargo "$(CARGO_RS_BUILD_TOOLCHAIN)" xtask check_tfhe_docs_are_tested
 
 .PHONY: check_intra_md_links # Checks broken internal links in Markdown docs
 check_intra_md_links: install_mlc
@@ -985,7 +1073,7 @@ check_compile_tests: install_rs_build_toolchain
 .PHONY: check_compile_tests_benches_gpu # Build tests in debug without running them
 check_compile_tests_benches_gpu: install_rs_build_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_BUILD_TOOLCHAIN) test --no-run \
-		--features=experimental,boolean,shortint,integer,internal-keycache,gpu \
+		--features=experimental,boolean,shortint,integer,internal-keycache,gpu,zk-pok \
 		-p $(TFHE_SPEC)
 	mkdir -p "$(TFHECUDA_BUILD)" && \
 		cd "$(TFHECUDA_BUILD)" && \
@@ -1061,6 +1149,24 @@ dieharder_csprng: install_dieharder build_tfhe_csprng
 # Benchmarks
 #
 
+.PHONY: clippy_bench # Run clippy lints on tfhe-benchmark
+clippy_bench: install_rs_check_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" clippy --all-targets \
+		--features=boolean,shortint,integer,internal-keycache,nightly-avx512,pbs-stats,zk-pok \
+		-p tfhe-benchmark -- --no-deps -D warnings
+
+.PHONY: clippy_bench_gpu # Run clippy lints on tfhe-benchmark
+clippy_bench_gpu: install_rs_check_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" clippy --all-targets \
+		--features=gpu,shortint,integer,internal-keycache,nightly-avx512,pbs-stats,zk-pok \
+		-p tfhe-benchmark -- --no-deps -D warnings
+
+.PHONY: clippy_bench_hpu # Run clippy lints on tfhe-benchmark
+clippy_bench_hpu: install_rs_check_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" cargo "$(CARGO_RS_CHECK_TOOLCHAIN)" clippy --all-targets \
+		--features=hpu,shortint,integer,internal-keycache,pbs-stats\
+		-p tfhe-benchmark -- --no-deps -D warnings
+
 .PHONY: print_doc_bench_parameters # Print parameters used in doc benchmarks
 print_doc_bench_parameters:
 	RUSTFLAGS="" cargo run --example print_doc_bench_parameters \
@@ -1071,35 +1177,57 @@ bench_integer: install_rs_check_toolchain
 	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=integer,internal-keycache,nightly-avx512 -p $(TFHE_SPEC) --
+	--features=integer,internal-keycache,nightly-avx512,pbs-stats -p tfhe-benchmark --
 
 .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=$(FAST_BENCH) __TFHE_RS_BENCH_TYPE=$(BENCH_TYPE) \
 	cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
 	--bench integer-signed-bench \
-	--features=integer,internal-keycache,nightly-avx512 -p $(TFHE_SPEC) --
+	--features=integer,internal-keycache,nightly-avx512,pbs-stats -p tfhe-benchmark --
 
 .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=$(FAST_BENCH) __TFHE_RS_BENCH_TYPE=$(BENCH_TYPE) \
 	cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
 	--bench integer-bench \
-	--features=integer,gpu,internal-keycache,nightly-avx512 -p $(TFHE_SPEC) --
+	--features=integer,gpu,internal-keycache,nightly-avx512,pbs-stats -p tfhe-benchmark --
+
+.PHONY: bench_signed_integer_gpu # Run benchmarks for signed integer on GPU backend
+bench_signed_integer_gpu: install_rs_check_toolchain
+	RUSTFLAGS="$(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=integer,gpu,internal-keycache,nightly-avx512,pbs-stats -p tfhe-benchmark --
+
+.PHONY: bench_integer_hpu # Run benchmarks for integer on HPU backend
+bench_integer_hpu: install_rs_check_toolchain
+	source ./setup_hpu.sh --config $(HPU_CONFIG) ; \
+	RUSTFLAGS="$(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=integer,internal-keycache,pbs-stats,hpu,hpu-v80 -p tfhe-benchmark -- --quick
 
 .PHONY: bench_integer_compression # Run benchmarks for unsigned integer compression
 bench_integer_compression: install_rs_check_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_BENCH_TYPE=$(BENCH_TYPE) \
 	cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
 	--bench	glwe_packing_compression-integer-bench \
-	--features=integer,internal-keycache,nightly-avx512 -p $(TFHE_SPEC) --
+	--features=integer,internal-keycache,nightly-avx512,pbs-stats -p tfhe-benchmark --
 
 .PHONY: bench_integer_compression_gpu
 bench_integer_compression_gpu: install_rs_check_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_BENCH_TYPE=$(BENCH_TYPE) \
 	cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
 	--bench	glwe_packing_compression-integer-bench \
-	--features=integer,internal-keycache,gpu -p $(TFHE_SPEC) --
+	--features=integer,internal-keycache,gpu,pbs-stats -p tfhe-benchmark --
+
+.PHONY: bench_integer_zk_gpu
+bench_integer_zk_gpu: install_rs_check_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_BENCH_TYPE=$(BENCH_TYPE) \
+	cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
+	--bench zk-pke-bench \
+	--features=integer,internal-keycache,gpu,pbs-stats,zk-pok -p tfhe-benchmark --
 
 .PHONY: bench_integer_multi_bit # Run benchmarks for unsigned integer using multi-bit parameters
 bench_integer_multi_bit: install_rs_check_toolchain
@@ -1107,7 +1235,7 @@ bench_integer_multi_bit: install_rs_check_toolchain
 	__TFHE_RS_BENCH_OP_FLAVOR=$(BENCH_OP_FLAVOR) __TFHE_RS_FAST_BENCH=$(FAST_BENCH) \
 	cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
 	--bench integer-bench \
-	--features=integer,internal-keycache,nightly-avx512 -p $(TFHE_SPEC) --
+	--features=integer,internal-keycache,nightly-avx512,pbs-stats -p tfhe-benchmark --
 
 .PHONY: bench_signed_integer_multi_bit # Run benchmarks for signed integer using multi-bit parameters
 bench_signed_integer_multi_bit: install_rs_check_toolchain
@@ -1115,7 +1243,7 @@ bench_signed_integer_multi_bit: install_rs_check_toolchain
 	__TFHE_RS_BENCH_OP_FLAVOR=$(BENCH_OP_FLAVOR) __TFHE_RS_FAST_BENCH=$(FAST_BENCH) \
 	cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
 	--bench integer-signed-bench \
-	--features=integer,internal-keycache,nightly-avx512 -p $(TFHE_SPEC) --
+	--features=integer,internal-keycache,nightly-avx512,pbs-stats -p tfhe-benchmark --
 
 .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
@@ -1123,81 +1251,99 @@ bench_integer_multi_bit_gpu: install_rs_check_toolchain
 	__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=integer,gpu,internal-keycache,nightly-avx512 -p $(TFHE_SPEC) --
+	--features=integer,gpu,internal-keycache,nightly-avx512,pbs-stats -p tfhe-benchmark --
 
-.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
+.PHONY: bench_signed_integer_multi_bit_gpu # Run benchmarks for signed integer on GPU backend using multi-bit parameters
+bench_signed_integer_multi_bit_gpu: install_rs_check_toolchain
 	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=integer,gpu,internal-keycache,nightly-avx512 -p $(TFHE_SPEC) -- ::unsigned
+	--bench integer-signed-bench \
+	--features=integer,gpu,internal-keycache,nightly-avx512,pbs-stats -p tfhe-benchmark --
 
 .PHONY: bench_integer_zk # Run benchmarks for integer encryption with ZK proofs
 bench_integer_zk: install_rs_check_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_BENCH_TYPE=$(BENCH_TYPE) \
 	cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
 	--bench zk-pke-bench \
-	--features=integer,internal-keycache,zk-pok,nightly-avx512 \
-	-p $(TFHE_SPEC) --
+	--features=integer,internal-keycache,zk-pok,nightly-avx512,pbs-stats \
+	-p tfhe-benchmark --
 
 .PHONY: bench_shortint # Run benchmarks for shortint
 bench_shortint: install_rs_check_toolchain
-	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_BENCH_OP_FLAVOR=$(BENCH_OP_FLAVOR) \
+	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_BENCH_OP_FLAVOR=$(BENCH_OP_FLAVOR) __TFHE_RS_PARAMS_SET=$(BENCH_PARAMS_SET) __TFHE_RS_BENCH_TYPE=$(BENCH_TYPE) \
 	cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
 	--bench shortint-bench \
-	--features=shortint,internal-keycache,nightly-avx512 -p $(TFHE_SPEC)
+	--features=shortint,internal-keycache,nightly-avx512 -p tfhe-benchmark
 
 .PHONY: bench_shortint_oprf # Run benchmarks for shortint
 bench_shortint_oprf: install_rs_check_toolchain
-	RUSTFLAGS="$(RUSTFLAGS)" \
+	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_PARAMS_SET=$(BENCH_PARAMS_SET) \
 	cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
 	--bench oprf-shortint-bench \
-	--features=shortint,internal-keycache,nightly-avx512 -p $(TFHE_SPEC)
-
-.PHONY: bench_shortint_multi_bit # Run benchmarks for shortint using multi-bit parameters
-bench_shortint_multi_bit: install_rs_check_toolchain
-	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_PARAM_TYPE=MULTI_BIT \
-	__TFHE_RS_BENCH_OP_FLAVOR=$(BENCH_OP_FLAVOR) \
-	cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
-	--bench shortint-bench \
-	--features=shortint,internal-keycache,nightly-avx512 -p $(TFHE_SPEC) --
+	--features=shortint,internal-keycache,nightly-avx512 -p tfhe-benchmark
 
 .PHONY: bench_boolean # Run benchmarks for boolean
 bench_boolean: install_rs_check_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
 	--bench boolean-bench \
-	--features=boolean,internal-keycache,nightly-avx512 -p $(TFHE_SPEC)
-
-.PHONY: bench_pbs # Run benchmarks for PBS
-bench_pbs: install_rs_check_toolchain
-	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
-	--bench pbs-bench \
-	--features=boolean,shortint,internal-keycache,nightly-avx512 -p $(TFHE_SPEC)
-
-.PHONY: bench_pbs128 # Run benchmarks for PBS using FFT 128 bits
-bench_pbs128: install_rs_check_toolchain
-	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
-	--bench pbs128-bench \
-	--features=boolean,shortint,internal-keycache,nightly-avx512 -p $(TFHE_SPEC)
-
-.PHONY: bench_pbs_gpu # Run benchmarks for PBS on GPU backend
-bench_pbs_gpu: install_rs_check_toolchain
-	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_FAST_BENCH=$(FAST_BENCH) cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
-	--bench pbs-bench \
-	--features=boolean,shortint,gpu,internal-keycache,nightly-avx512 -p $(TFHE_SPEC)
+	--features=boolean,internal-keycache,nightly-avx512 -p tfhe-benchmark
 
 .PHONY: bench_ks # Run benchmarks for keyswitch
 bench_ks: install_rs_check_toolchain
-	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
+	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_PARAM_TYPE=$(BENCH_PARAM_TYPE) __TFHE_RS_PARAMS_SET=$(BENCH_PARAMS_SET) __TFHE_RS_BENCH_TYPE=$(BENCH_TYPE) \
+	cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
 	--bench ks-bench \
-	--features=boolean,shortint,internal-keycache,nightly-avx512 -p $(TFHE_SPEC)
+	--features=boolean,shortint,internal-keycache,nightly-avx512 -p tfhe-benchmark
 
-.PHONY: bench_ks_gpu # Run benchmarks for PBS on GPU backend
+.PHONY: bench_ks_gpu # Run benchmarks for keyswitch on GPU backend
 bench_ks_gpu: install_rs_check_toolchain
-	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
+	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_PARAM_TYPE=$(BENCH_PARAM_TYPE) __TFHE_RS_PARAMS_SET=$(BENCH_PARAMS_SET) __TFHE_RS_BENCH_TYPE=$(BENCH_TYPE) \
+	cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
 	--bench ks-bench \
-	--features=boolean,shortint,gpu,internal-keycache,nightly-avx512 -p $(TFHE_SPEC)
+	--features=boolean,shortint,gpu,internal-keycache,nightly-avx512 -p tfhe-benchmark
+
+.PHONY: bench_pbs # Run benchmarks for PBS
+bench_pbs: install_rs_check_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_PARAM_TYPE=$(BENCH_PARAM_TYPE) __TFHE_RS_PARAMS_SET=$(BENCH_PARAMS_SET) __TFHE_RS_BENCH_TYPE=$(BENCH_TYPE) \
+	cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
+	--bench pbs-bench \
+	--features=boolean,shortint,internal-keycache,nightly-avx512 -p tfhe-benchmark
+
+.PHONY: bench_pbs_gpu # Run benchmarks for PBS on GPU backend
+bench_pbs_gpu: install_rs_check_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_PARAM_TYPE=$(BENCH_PARAM_TYPE) __TFHE_RS_FAST_BENCH=$(FAST_BENCH) __TFHE_RS_PARAMS_SET=$(BENCH_PARAMS_SET) __TFHE_RS_BENCH_TYPE=$(BENCH_TYPE) \
+	cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
+	--bench pbs-bench \
+	--features=boolean,shortint,gpu,internal-keycache,nightly-avx512 -p tfhe-benchmark
+
+.PHONY: bench_ks_pbs # Run benchmarks for KS-PBS
+bench_ks_pbs: install_rs_check_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_PARAM_TYPE=$(BENCH_PARAM_TYPE) __TFHE_RS_PARAMS_SET=$(BENCH_PARAMS_SET) __TFHE_RS_BENCH_TYPE=$(BENCH_TYPE) \
+	cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
+	--bench ks-pbs-bench \
+	--features=boolean,shortint,internal-keycache,nightly-avx512 -p tfhe-benchmark
+
+.PHONY: bench_ks_pbs_gpu # Run benchmarks for KS-PBS on GPU backend
+bench_ks_pbs_gpu: install_rs_check_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_PARAM_TYPE=$(BENCH_PARAM_TYPE) __TFHE_RS_PARAMS_SET=$(BENCH_PARAMS_SET) __TFHE_RS_BENCH_TYPE=$(BENCH_TYPE) \
+	cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
+	--bench ks-pbs-bench \
+	--features=boolean,shortint,gpu,internal-keycache,nightly-avx512 -p tfhe-benchmark
+
+.PHONY: bench_pbs128 # Run benchmarks for PBS using FFT 128 bits
+bench_pbs128: install_rs_check_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_BENCH_TYPE=$(BENCH_TYPE) \
+	cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
+	--bench pbs128-bench \
+	--features=boolean,shortint,internal-keycache,nightly-avx512 -p tfhe-benchmark
+
+.PHONY: bench_pbs128_gpu # Run benchmarks for PBS using FFT 128 bits on GPU
+bench_pbs128_gpu: install_rs_check_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" __TFHE_RS_BENCH_TYPE=$(BENCH_TYPE) \
+	cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
+	--bench pbs128-bench \
+	--features=boolean,shortint,gpu,internal-keycache,nightly-avx512 -p tfhe-benchmark
 
 bench_web_js_api_parallel_chrome: browser_path = "$(WEB_RUNNER_DIR)/chrome/chrome-linux64/chrome"
 bench_web_js_api_parallel_chrome: driver_path = "$(WEB_RUNNER_DIR)/chrome/chromedriver-linux64/chromedriver"
@@ -1229,17 +1375,37 @@ bench_web_js_api_parallel_firefox_ci: setup_venv
 	nvm use $(NODE_VERSION) && \
 	$(MAKE) bench_web_js_api_parallel_firefox
 
-.PHONY: bench_hlapi_erc20 # Run benchmarks for ECR20 operations
+.PHONY: bench_hlapi_erc20 # Run benchmarks for ERC20 operations
 bench_hlapi_erc20: install_rs_check_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
 	--bench hlapi-erc20 \
-	--features=integer,internal-keycache,pbs-stats,nightly-avx512 -p $(TFHE_SPEC) --
+	--features=integer,internal-keycache,pbs-stats,nightly-avx512 -p tfhe-benchmark --
 
-.PHONY: bench_hlapi_erc20_gpu # Run benchmarks for ECR20 operations on GPU
+.PHONY: bench_hlapi_erc20_gpu # Run benchmarks for ERC20 operations on GPU
 bench_hlapi_erc20_gpu: install_rs_check_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
 	--bench hlapi-erc20 \
-	--features=integer,gpu,internal-keycache,pbs-stats,nightly-avx512 -p $(TFHE_SPEC) --
+	--features=integer,gpu,internal-keycache,pbs-stats,nightly-avx512 -p tfhe-benchmark --
+
+.PHONY: bench_hlapi_dex # Run benchmarks for DEX operations
+bench_hlapi_dex: install_rs_check_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
+	--bench hlapi-dex \
+	--features=integer,internal-keycache,pbs-stats,nightly-avx512 -p tfhe-benchmark --
+
+.PHONY: bench_hlapi_dex_gpu # Run benchmarks for DEX operations on GPU
+bench_hlapi_dex_gpu: install_rs_check_toolchain
+	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
+	--bench hlapi-dex \
+	--features=integer,gpu,internal-keycache,pbs-stats,nightly-avx512 -p tfhe-benchmark --
+
+.PHONY: bench_hlapi_erc20_hpu # Run benchmarks for ECR20 operations on HPU
+bench_hlapi_erc20_hpu: install_rs_check_toolchain
+	source ./setup_hpu.sh --config $(HPU_CONFIG) ; \
+	RUSTFLAGS="$(RUSTFLAGS)" \
+	cargo $(CARGO_RS_CHECK_TOOLCHAIN) bench \
+	--bench hlapi-erc20 \
+	--features=integer,internal-keycache,hpu,hpu-v80 -p tfhe-benchmark -- --quick
 
 .PHONY: bench_tfhe_zk_pok # Run benchmarks for the tfhe_zk_pok crate
 bench_tfhe_zk_pok: install_rs_check_toolchain
@@ -1266,20 +1432,23 @@ gen_key_cache_core_crypto: install_rs_build_toolchain
 .PHONY: measure_hlapi_compact_pk_ct_sizes # Measure sizes of public keys and ciphertext for high-level API
 measure_hlapi_compact_pk_ct_sizes: install_rs_check_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_CHECK_TOOLCHAIN) run --profile $(CARGO_PROFILE) \
-	--example hlapi_compact_pk_ct_sizes \
-	--features=integer,internal-keycache
+	--bin hlapi_compact_pk_ct_sizes \
+	--features=integer,internal-keycache \
+	-p tfhe-benchmark
 
 .PHONY: measure_shortint_key_sizes # Measure sizes of bootstrapping and key switching keys for shortint
 measure_shortint_key_sizes: install_rs_check_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_CHECK_TOOLCHAIN) run --profile $(CARGO_PROFILE) \
-	--example shortint_key_sizes \
-	--features=shortint,internal-keycache
+	--bin shortint_key_sizes \
+	--features=shortint,internal-keycache \
+	-p tfhe-benchmark
 
 .PHONY: measure_boolean_key_sizes # Measure sizes of bootstrapping and key switching keys for boolean
 measure_boolean_key_sizes: install_rs_check_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_CHECK_TOOLCHAIN) run --profile $(CARGO_PROFILE) \
-	--example boolean_key_sizes \
-	--features=boolean,internal-keycache
+	--bin boolean_key_sizes \
+	--features=boolean,internal-keycache \
+	-p tfhe-benchmark
 
 .PHONY: parse_integer_benches # Run python parser to output a csv containing integer benches data
 parse_integer_benches:
@@ -1290,8 +1459,9 @@ parse_integer_benches:
 .PHONY: parse_wasm_benchmarks # Parse benchmarks performed with WASM web client into a CSV file
 parse_wasm_benchmarks: install_rs_check_toolchain
 	RUSTFLAGS="$(RUSTFLAGS)" cargo $(CARGO_RS_CHECK_TOOLCHAIN) run --profile $(CARGO_PROFILE) \
-	--example wasm_benchmarks_parser \
+	--bin wasm_benchmarks_parser \
 	--features=shortint,internal-keycache \
+	-p tfhe-benchmark \
 	-- wasm_benchmark_results.json
 
 .PHONY: write_params_to_file # Gather all crypto parameters into a file with a Sage readable format.
@@ -1334,7 +1504,10 @@ tfhe_lints
 
 .PHONY: pcc_gpu # pcc stands for pre commit checks for GPU compilation
 pcc_gpu: check_rust_bindings_did_not_change clippy_rustdoc_gpu \
-clippy_gpu clippy_cuda_backend check_compile_tests_benches_gpu
+clippy_gpu clippy_cuda_backend clippy_bench_gpu check_compile_tests_benches_gpu
+
+.PHONY: pcc_hpu # pcc stands for pre commit checks for HPU compilation
+pcc_hpu: clippy_hpu clippy_hpu_backend test_integer_hpu_mockup_ci_fast
 
 .PHONY: fpcc # pcc stands for pre commit checks, the f stands for fast
 fpcc: no_tfhe_typo no_dbg_log check_parameter_export_ok check_fmt check_typos lint_doc \

README.md

@@ -10,7 +10,7 @@
 <hr/>
 
 <p align="center">
-  <a href="https://docs.zama.ai/tfhe-rs"> 📒 Documentation</a> | <a href="https://zama.ai/community"> 💛 Community support</a> | <a href="https://github.com/zama-ai/awesome-zama"> 📚 FHE resources by Zama</a>
+  <a href="https://github.com/zama-ai/tfhe-rs-handbook/blob/main/tfhe-rs-handbook.pdf"> 📃 Read Handbook</a> |<a href="https://docs.zama.ai/tfhe-rs"> 📒 Documentation</a> | <a href="https://zama.ai/community"> 💛 Community support</a> | <a href="https://github.com/zama-ai/awesome-zama"> 📚 FHE resources by Zama</a>
 </p>
 
 
@@ -67,6 +67,9 @@ production-ready library for all the advanced features of TFHE.
 
 ## Getting started
 
+> [!Important]
+> **TFHE-rs** released its first stable version v1.0.0 in February 2025, stabilizing the high-level API for the x86 CPU backend.
+
 ### Cargo.toml configuration
 To use the latest version of `TFHE-rs` in your project, you first need to add it as a dependency in your `Cargo.toml`:
 
@@ -75,13 +78,13 @@ tfhe = { version = "*", features = ["boolean", "shortint", "integer"] }
 ```
 
 > [!Note]
-> Note: You need to use a Rust version >= 1.81 to compile TFHE-rs.
+> Note: You need to use Rust version >= 1.84 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.
+> Note: AArch64-based machines are not 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.
 
 <p align="right">
-  <a href="#about" > ↑ Back to top </a> 
+  <a href="#about" > ↑ Back to top </a>
 </p>
 
 ### A simple example
@@ -138,7 +141,7 @@ fn main() -> Result<(), Box<dyn std::error::Error>> {
 }
 ```
 
-To run this code, use the following command: 
+To run this code, use the following command:
 <p align="center"> <code> cargo run --release </code> </p>
 
 > [!Note]
@@ -148,12 +151,15 @@ to run in release mode with cargo's `--release` flag to have the best performanc
 *Find an example with more explanations in [this part of the documentation](https://docs.zama.ai/tfhe-rs/get-started/quick_start)*
 
 <p align="right">
-  <a href="#about" > ↑ Back to top </a> 
+  <a href="#about" > ↑ Back to top </a>
 </p>
 
 
 
-## Resources 
+## Resources
+
+### TFHE-rs Handbook
+A document containing scientific and technical details about algorithms implemented into the library is available here: [TFHE-rs: A (Practical) Handbook](https://github.com/zama-ai/tfhe-rs-handbook/blob/main/tfhe-rs-handbook.pdf).
 
 ### TFHE deep dive
 - [TFHE Deep Dive - Part I - Ciphertext types](https://www.zama.ai/post/tfhe-deep-dive-part-1)
@@ -176,7 +182,7 @@ to run in release mode with cargo's `--release` flag to have the best performanc
 
 Full, comprehensive documentation is available here: [https://docs.zama.ai/tfhe-rs](https://docs.zama.ai/tfhe-rs).
 <p align="right">
-  <a href="#about" > ↑ Back to top </a> 
+  <a href="#about" > ↑ Back to top </a>
 </p>
 
 
@@ -194,9 +200,14 @@ When a new update is published in the Lattice Estimator, we update parameters ac
 
 ### Security model
 
-The default parameters for the TFHE-rs library are chosen considering the IND-CPA security model, and are selected with a bootstrapping failure probability fixed at p_error = $2^{-64}$. In particular, it is assumed that the results of decrypted computations are not shared by the secret key owner with any third parties, as such an action can lead to leakage of the secret encryption key. If you are designing an application where decryptions must be shared, you will need to craft custom encryption parameters which are chosen in consideration of the IND-CPA^D security model [1]. 
+By default, the parameter sets used in the High-Level API with the x86 CPU backend have a failure probability $\le 2^{128}$ to securely work in the IND-CPA^D model using the algorithmic techniques provided in our code base [1].
+If you want to work within the IND-CPA security model, which is less strict than the IND-CPA-D model, the parameter sets can easily be changed and would have slightly better performance. More details can be found in the [TFHE-rs documentation](https://docs.zama.ai/tfhe-rs).
 
-[1] Li, Baiyu, et al. "Securing approximate homomorphic encryption using differential privacy." Annual International Cryptology Conference. Cham: Springer Nature Switzerland, 2022. https://eprint.iacr.org/2022/816.pdf
+The default parameters used in the High-Level API with the GPU backend are chosen considering the IND-CPA security model, and are selected with a bootstrapping failure probability fixed at $p_{error} \le 2^{-64}$. In particular, it is assumed that the results of decrypted computations are not shared by the secret key owner with any third parties, as such an action can lead to leakage of the secret encryption key. If you are designing an application where decryptions must be shared, you will need to craft custom encryption parameters which are chosen in consideration of the IND-CPA^D security model [2].
+
+[1] Bernard, Olivier, et al. "Drifting Towards Better Error Probabilities in Fully Homomorphic Encryption Schemes". https://eprint.iacr.org/2024/1718.pdf
+
+[2] Li, Baiyu, et al. "Securing approximate homomorphic encryption using differential privacy." Annual International Cryptology Conference. Cham: Springer Nature Switzerland, 2022. https://eprint.iacr.org/2022/816.pdf
 
 #### Side-channel attacks
 
@@ -245,7 +256,7 @@ This software is distributed under the **BSD-3-Clause-Clear** license. Read [thi
 >We are open to collaborating and advancing the FHE space with our partners. If you have specific needs, please email us at hello@zama.ai.
 
 <p align="right">
-  <a href="#about" > ↑ Back to top </a> 
+  <a href="#about" > ↑ Back to top </a>
 </p>
 
 
@@ -259,8 +270,8 @@ This software is distributed under the **BSD-3-Clause-Clear** license. Read [thi
 </picture>
 </a>
 
-🌟 If you find this project helpful or interesting, please consider giving it a star on GitHub! Your support helps to grow the community and motivates further development. 
+🌟 If you find this project helpful or interesting, please consider giving it a star on GitHub! Your support helps to grow the community and motivates further development.
 
 <p align="right">
-  <a href="#about" > ↑ Back to top </a> 
+  <a href="#about" > ↑ Back to top </a>
 </p>

_typos.toml

@@ -11,5 +11,13 @@ extend-ignore-identifiers-re = [
     # Example with string replacing "hello" with "herlo"
     "herlo",
     # Example in trivium
-    "C9217BA0D762ACA1"
+    "C9217BA0D762ACA1",
+    "0x[0-9a-fA-F]+"
+]
+
+[files]
+extend-exclude = [
+    "backends/tfhe-cuda-backend/cuda/src/fft128/twiddles.cu",
+    "backends/tfhe-cuda-backend/cuda/src/fft/twiddles.cu",
+    "backends/tfhe-hpu-backend/config_store/**/*.link_summary",
 ]

apps/trivium/Cargo.toml

@@ -6,11 +6,17 @@ edition = "2021"
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
-rayon = { workspace = true }
-tfhe = { path = "../../tfhe", features = [ "boolean", "shortint", "integer" ] }
+rayon = "1"
+tfhe = { path = "../../tfhe", features = ["boolean", "shortint", "integer"] }
 
 [dev-dependencies]
-criterion = { version = "0.5.1", features = [ "html_reports" ]}
+criterion = { version = "0.5.1", features = ["html_reports"] }
+
+[profile.devo]
+inherits = "dev"
+opt-level = 3
+lto = "off"
+debug-assertions = false
 
 [[bench]]
 name = "trivium"

apps/trivium/README.md

@@ -129,7 +129,7 @@ Other sizes than 64 bit are expected to be available in the future.
 
 # FHE shortint Trivium implementation
 
-The same implementation is also available for generic Ciphertexts representing bits (meant to be used with parameters `V1_0_PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M128`).
+The same implementation is also available for generic Ciphertexts representing bits (meant to be used with parameters `V1_2_PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M128`).
 It uses a lower level API of tfhe-rs, so the syntax is a little bit different. It also implements the `TransCiphering` trait. For optimization purposes, it does not internally run
 on the same cryptographic parameters as the high level API of tfhe-rs. As such, it requires the usage of a casting key, to switch from one parameter space to another, which makes
 its setup a little more intricate.
@@ -137,10 +137,10 @@ its setup a little more intricate.
 Example code:
 ```rust
 use tfhe::shortint::prelude::*;
-use tfhe::shortint::parameters::v1_0::{
-    V1_0_PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M128,
-    V1_0_PARAM_MESSAGE_2_CARRY_2_KS_PBS_GAUSSIAN_2M128,
-    V1_0_PARAM_KEYSWITCH_1_1_KS_PBS_TO_2_2_KS_PBS_GAUSSIAN_2M128,
+use tfhe::shortint::parameters::v1_2::{
+    V1_2_PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M128,
+    V1_2_PARAM_MESSAGE_2_CARRY_2_KS_PBS_GAUSSIAN_2M128,
+    V1_2_PARAM_KEYSWITCH_1_1_KS_PBS_TO_2_2_KS_PBS_GAUSSIAN_2M128,
 };
 use tfhe::{ConfigBuilder, generate_keys, FheUint64};
 use tfhe::prelude::*;
@@ -148,17 +148,17 @@ use tfhe_trivium::TriviumStreamShortint;
 
 fn test_shortint() {
     let config = ConfigBuilder::default()
-        .use_custom_parameters(V1_0_PARAM_MESSAGE_2_CARRY_2_KS_PBS_GAUSSIAN_2M128)
+        .use_custom_parameters(V1_2_PARAM_MESSAGE_2_CARRY_2_KS_PBS_GAUSSIAN_2M128)
         .build();
     let (hl_client_key, hl_server_key) = generate_keys(config);
     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(V1_0_PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M128);
+    let (client_key, server_key): (ClientKey, ServerKey) = gen_keys(V1_2_PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M128);
     let ksk = KeySwitchingKey::new(
         (&client_key, Some(&server_key)),
         (&underlying_ck, &underlying_sk),
-        V1_0_PARAM_KEYSWITCH_1_1_KS_PBS_TO_2_2_KS_PBS_GAUSSIAN_2M128_2M128,
+        V1_2_PARAM_KEYSWITCH_1_1_KS_PBS_TO_2_2_KS_PBS_GAUSSIAN_2M128_2M128,
     );
 
     let key_string = "0053A6F94C9FF24598EB".to_string();

apps/trivium/benches/kreyvium_shortint.rs

@@ -1,9 +1,9 @@
 use criterion::Criterion;
 use tfhe::prelude::*;
-use tfhe::shortint::parameters::v1_0::{
-    V1_0_PARAM_KEYSWITCH_1_1_KS_PBS_TO_2_2_KS_PBS_GAUSSIAN_2M128,
-    V1_0_PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M128,
-    V1_0_PARAM_MESSAGE_2_CARRY_2_KS_PBS_GAUSSIAN_2M128,
+use tfhe::shortint::parameters::v1_2::{
+    V1_2_PARAM_KEYSWITCH_1_1_KS_PBS_TO_2_2_KS_PBS_GAUSSIAN_2M128,
+    V1_2_PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M128,
+    V1_2_PARAM_MESSAGE_2_CARRY_2_KS_PBS_GAUSSIAN_2M128,
 };
 use tfhe::shortint::prelude::*;
 use tfhe::{generate_keys, ConfigBuilder, FheUint64};
@@ -11,19 +11,19 @@ use tfhe_trivium::{KreyviumStreamShortint, TransCiphering};
 
 pub fn kreyvium_shortint_warmup(c: &mut Criterion) {
     let config = ConfigBuilder::default()
-        .use_custom_parameters(V1_0_PARAM_MESSAGE_2_CARRY_2_KS_PBS_GAUSSIAN_2M128)
+        .use_custom_parameters(V1_2_PARAM_MESSAGE_2_CARRY_2_KS_PBS_GAUSSIAN_2M128)
         .build();
     let (hl_client_key, hl_server_key) = generate_keys(config);
     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(V1_0_PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M128);
+        gen_keys(V1_2_PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M128);
 
     let ksk = KeySwitchingKey::new(
         (&client_key, Some(&server_key)),
         (&underlying_ck, &underlying_sk),
-        V1_0_PARAM_KEYSWITCH_1_1_KS_PBS_TO_2_2_KS_PBS_GAUSSIAN_2M128,
+        V1_2_PARAM_KEYSWITCH_1_1_KS_PBS_TO_2_2_KS_PBS_GAUSSIAN_2M128,
     );
 
     let key_string = "0053A6F94C9FF24598EB000000000000".to_string();
@@ -64,19 +64,19 @@ pub fn kreyvium_shortint_warmup(c: &mut Criterion) {
 
 pub fn kreyvium_shortint_gen(c: &mut Criterion) {
     let config = ConfigBuilder::default()
-        .use_custom_parameters(V1_0_PARAM_MESSAGE_2_CARRY_2_KS_PBS_GAUSSIAN_2M128)
+        .use_custom_parameters(V1_2_PARAM_MESSAGE_2_CARRY_2_KS_PBS_GAUSSIAN_2M128)
         .build();
     let (hl_client_key, hl_server_key) = generate_keys(config);
     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(V1_0_PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M128);
+        gen_keys(V1_2_PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M128);
 
     let ksk = KeySwitchingKey::new(
         (&client_key, Some(&server_key)),
         (&underlying_ck, &underlying_sk),
-        V1_0_PARAM_KEYSWITCH_1_1_KS_PBS_TO_2_2_KS_PBS_GAUSSIAN_2M128,
+        V1_2_PARAM_KEYSWITCH_1_1_KS_PBS_TO_2_2_KS_PBS_GAUSSIAN_2M128,
     );
 
     let key_string = "0053A6F94C9FF24598EB000000000000".to_string();
@@ -112,19 +112,19 @@ pub fn kreyvium_shortint_gen(c: &mut Criterion) {
 
 pub fn kreyvium_shortint_trans(c: &mut Criterion) {
     let config = ConfigBuilder::default()
-        .use_custom_parameters(V1_0_PARAM_MESSAGE_2_CARRY_2_KS_PBS_GAUSSIAN_2M128)
+        .use_custom_parameters(V1_2_PARAM_MESSAGE_2_CARRY_2_KS_PBS_GAUSSIAN_2M128)
         .build();
     let (hl_client_key, hl_server_key) = generate_keys(config);
     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(V1_0_PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M128);
+        gen_keys(V1_2_PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M128);
 
     let ksk = KeySwitchingKey::new(
         (&client_key, Some(&server_key)),
         (&underlying_ck, &underlying_sk),
-        V1_0_PARAM_KEYSWITCH_1_1_KS_PBS_TO_2_2_KS_PBS_GAUSSIAN_2M128,
+        V1_2_PARAM_KEYSWITCH_1_1_KS_PBS_TO_2_2_KS_PBS_GAUSSIAN_2M128,
     );
 
     let key_string = "0053A6F94C9FF24598EB000000000000".to_string();

apps/trivium/benches/trivium_shortint.rs

@@ -1,9 +1,9 @@
 use criterion::Criterion;
 use tfhe::prelude::*;
-use tfhe::shortint::parameters::v1_0::{
-    V1_0_PARAM_KEYSWITCH_1_1_KS_PBS_TO_2_2_KS_PBS_GAUSSIAN_2M128,
-    V1_0_PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M128,
-    V1_0_PARAM_MESSAGE_2_CARRY_2_KS_PBS_GAUSSIAN_2M128,
+use tfhe::shortint::parameters::v1_2::{
+    V1_2_PARAM_KEYSWITCH_1_1_KS_PBS_TO_2_2_KS_PBS_GAUSSIAN_2M128,
+    V1_2_PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M128,
+    V1_2_PARAM_MESSAGE_2_CARRY_2_KS_PBS_GAUSSIAN_2M128,
 };
 use tfhe::shortint::prelude::*;
 use tfhe::{generate_keys, ConfigBuilder, FheUint64};
@@ -11,19 +11,19 @@ use tfhe_trivium::{TransCiphering, TriviumStreamShortint};
 
 pub fn trivium_shortint_warmup(c: &mut Criterion) {
     let config = ConfigBuilder::default()
-        .use_custom_parameters(V1_0_PARAM_MESSAGE_2_CARRY_2_KS_PBS_GAUSSIAN_2M128)
+        .use_custom_parameters(V1_2_PARAM_MESSAGE_2_CARRY_2_KS_PBS_GAUSSIAN_2M128)
         .build();
     let (hl_client_key, hl_server_key) = generate_keys(config);
     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(V1_0_PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M128);
+        gen_keys(V1_2_PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M128);
 
     let ksk = KeySwitchingKey::new(
         (&client_key, Some(&server_key)),
         (&underlying_ck, &underlying_sk),
-        V1_0_PARAM_KEYSWITCH_1_1_KS_PBS_TO_2_2_KS_PBS_GAUSSIAN_2M128,
+        V1_2_PARAM_KEYSWITCH_1_1_KS_PBS_TO_2_2_KS_PBS_GAUSSIAN_2M128,
     );
 
     let key_string = "0053A6F94C9FF24598EB".to_string();
@@ -64,19 +64,19 @@ pub fn trivium_shortint_warmup(c: &mut Criterion) {
 
 pub fn trivium_shortint_gen(c: &mut Criterion) {
     let config = ConfigBuilder::default()
-        .use_custom_parameters(V1_0_PARAM_MESSAGE_2_CARRY_2_KS_PBS_GAUSSIAN_2M128)
+        .use_custom_parameters(V1_2_PARAM_MESSAGE_2_CARRY_2_KS_PBS_GAUSSIAN_2M128)
         .build();
     let (hl_client_key, hl_server_key) = generate_keys(config);
     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(V1_0_PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M128);
+        gen_keys(V1_2_PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M128);
 
     let ksk = KeySwitchingKey::new(
         (&client_key, Some(&server_key)),
         (&underlying_ck, &underlying_sk),
-        V1_0_PARAM_KEYSWITCH_1_1_KS_PBS_TO_2_2_KS_PBS_GAUSSIAN_2M128,
+        V1_2_PARAM_KEYSWITCH_1_1_KS_PBS_TO_2_2_KS_PBS_GAUSSIAN_2M128,
     );
 
     let key_string = "0053A6F94C9FF24598EB".to_string();
@@ -112,19 +112,19 @@ pub fn trivium_shortint_gen(c: &mut Criterion) {
 
 pub fn trivium_shortint_trans(c: &mut Criterion) {
     let config = ConfigBuilder::default()
-        .use_custom_parameters(V1_0_PARAM_MESSAGE_2_CARRY_2_KS_PBS_GAUSSIAN_2M128)
+        .use_custom_parameters(V1_2_PARAM_MESSAGE_2_CARRY_2_KS_PBS_GAUSSIAN_2M128)
         .build();
     let (hl_client_key, hl_server_key) = generate_keys(config);
     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(V1_0_PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M128);
+        gen_keys(V1_2_PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M128);
 
     let ksk = KeySwitchingKey::new(
         (&client_key, Some(&server_key)),
         (&underlying_ck, &underlying_sk),
-        V1_0_PARAM_KEYSWITCH_1_1_KS_PBS_TO_2_2_KS_PBS_GAUSSIAN_2M128,
+        V1_2_PARAM_KEYSWITCH_1_1_KS_PBS_TO_2_2_KS_PBS_GAUSSIAN_2M128,
     );
 
     let key_string = "0053A6F94C9FF24598EB".to_string();

apps/trivium/src/kreyvium/test.rs

@@ -1,9 +1,9 @@
 use crate::{KreyviumStream, KreyviumStreamByte, KreyviumStreamShortint, TransCiphering};
 use tfhe::prelude::*;
-use tfhe::shortint::parameters::v1_0::{
-    V1_0_PARAM_KEYSWITCH_1_1_KS_PBS_TO_2_2_KS_PBS_GAUSSIAN_2M128,
-    V1_0_PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M128,
-    V1_0_PARAM_MESSAGE_2_CARRY_2_KS_PBS_GAUSSIAN_2M128,
+use tfhe::shortint::parameters::v1_2::{
+    V1_2_PARAM_KEYSWITCH_1_1_KS_PBS_TO_2_2_KS_PBS_GAUSSIAN_2M128,
+    V1_2_PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M128,
+    V1_2_PARAM_MESSAGE_2_CARRY_2_KS_PBS_GAUSSIAN_2M128,
 };
 use tfhe::{generate_keys, ConfigBuilder, FheBool, FheUint64, FheUint8};
 // Values for these tests come from the github repo renaud1239/Kreyvium,
@@ -66,7 +66,7 @@ fn get_hexagonal_string_from_bytes(a: Vec<u8>) -> String {
     assert!(a.len() % 8 == 0);
     let mut hexadecimal: String = "".to_string();
     for test in a {
-        hexadecimal.push_str(&format!("{:02X?}", test));
+        hexadecimal.push_str(&format!("{test:02X?}"));
     }
     hexadecimal
 }
@@ -74,7 +74,7 @@ fn get_hexagonal_string_from_bytes(a: Vec<u8>) -> String {
 fn get_hexagonal_string_from_u64(a: Vec<u64>) -> String {
     let mut hexadecimal: String = "".to_string();
     for test in a {
-        hexadecimal.push_str(&format!("{:016X?}", test));
+        hexadecimal.push_str(&format!("{test:016X?}"));
     }
     hexadecimal
 }
@@ -221,19 +221,19 @@ use tfhe::shortint::prelude::*;
 #[test]
 fn kreyvium_test_shortint_long() {
     let config = ConfigBuilder::default()
-        .use_custom_parameters(V1_0_PARAM_MESSAGE_2_CARRY_2_KS_PBS_GAUSSIAN_2M128)
+        .use_custom_parameters(V1_2_PARAM_MESSAGE_2_CARRY_2_KS_PBS_GAUSSIAN_2M128)
         .build();
     let (hl_client_key, hl_server_key) = generate_keys(config);
     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(V1_0_PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M128);
+        gen_keys(V1_2_PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M128);
 
     let ksk = KeySwitchingKey::new(
         (&client_key, Some(&server_key)),
         (&underlying_ck, &underlying_sk),
-        V1_0_PARAM_KEYSWITCH_1_1_KS_PBS_TO_2_2_KS_PBS_GAUSSIAN_2M128,
+        V1_2_PARAM_KEYSWITCH_1_1_KS_PBS_TO_2_2_KS_PBS_GAUSSIAN_2M128,
     );
 
     let key_string = "0053A6F94C9FF24598EB000000000000".to_string();

apps/trivium/src/static_deque/static_deque.rs

@@ -55,7 +55,7 @@ impl<const N: usize, T> Index<usize> for StaticDeque<N, T> {
     /// 0 is youngest
     fn index(&self, i: usize) -> &T {
         if i >= N {
-            panic!("Index {:?} too high for size {:?}", i, N);
+            panic!("Index {i:?} too high for size {N:?}");
         }
         &self.arr[(N + self.cursor - i - 1) % N]
     }
@@ -66,7 +66,7 @@ impl<const N: usize, T> IndexMut<usize> for StaticDeque<N, T> {
     /// 0 is youngest
     fn index_mut(&mut self, i: usize) -> &mut T {
         if i >= N {
-            panic!("Index {:?} too high for size {:?}", i, N);
+            panic!("Index {i:?} too high for size {N:?}");
         }
         &mut self.arr[(N + self.cursor - i - 1) % N]
     }

apps/trivium/src/trans_ciphering/mod.rs

@@ -48,6 +48,8 @@ fn transcipher_from_1_1_stream(
 ) -> FheUint64 {
     assert_eq!(stream.len(), 64);
 
+    let id_lut = internal_server_key.generate_lookup_table(|x| x);
+
     let pairs = (0..32)
         .into_par_iter()
         .map(|i| {
@@ -57,10 +59,11 @@ fn transcipher_from_1_1_stream(
             let b0 = &stream[8 * byte_idx + 2 * pair_idx];
             let b1 = &stream[8 * byte_idx + 2 * pair_idx + 1];
 
-            casting_key.cast(
-                &internal_server_key
-                    .unchecked_add(b0, &internal_server_key.unchecked_scalar_mul(b1, 2)),
-            )
+            let mut combined = internal_server_key
+                .unchecked_add(b0, &internal_server_key.unchecked_scalar_mul(b1, 2));
+            internal_server_key.apply_lookup_table_assign(&mut combined, &id_lut);
+
+            casting_key.cast(&combined)
         })
         .collect::<Vec<_>>();
 

apps/trivium/src/trivium/test.rs

@@ -1,9 +1,9 @@
 use crate::{TransCiphering, TriviumStream, TriviumStreamByte, TriviumStreamShortint};
 use tfhe::prelude::*;
-use tfhe::shortint::parameters::v1_0::{
-    V1_0_PARAM_KEYSWITCH_1_1_KS_PBS_TO_2_2_KS_PBS_GAUSSIAN_2M128,
-    V1_0_PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M128,
-    V1_0_PARAM_MESSAGE_2_CARRY_2_KS_PBS_GAUSSIAN_2M128,
+use tfhe::shortint::parameters::v1_2::{
+    V1_2_PARAM_KEYSWITCH_1_1_KS_PBS_TO_2_2_KS_PBS_GAUSSIAN_2M128,
+    V1_2_PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M128,
+    V1_2_PARAM_MESSAGE_2_CARRY_2_KS_PBS_GAUSSIAN_2M128,
 };
 use tfhe::{generate_keys, ConfigBuilder, FheBool, FheUint64, FheUint8};
 // Values for these tests come from the github repo cantora/avr-crypto-lib, commit 2a5b018,
@@ -66,7 +66,7 @@ fn get_hexagonal_string_from_bytes(a: Vec<u8>) -> String {
     assert!(a.len() % 8 == 0);
     let mut hexadecimal: String = "".to_string();
     for test in a {
-        hexadecimal.push_str(&format!("{:02X?}", test));
+        hexadecimal.push_str(&format!("{test:02X?}"));
     }
     hexadecimal
 }
@@ -74,7 +74,7 @@ fn get_hexagonal_string_from_bytes(a: Vec<u8>) -> String {
 fn get_hexagonal_string_from_u64(a: Vec<u64>) -> String {
     let mut hexadecimal: String = "".to_string();
     for test in a {
-        hexadecimal.push_str(&format!("{:016X?}", test));
+        hexadecimal.push_str(&format!("{test:016X?}"));
     }
     hexadecimal
 }
@@ -357,19 +357,19 @@ use tfhe::shortint::prelude::*;
 #[test]
 fn trivium_test_shortint_long() {
     let config = ConfigBuilder::default()
-        .use_custom_parameters(V1_0_PARAM_MESSAGE_2_CARRY_2_KS_PBS_GAUSSIAN_2M128)
+        .use_custom_parameters(V1_2_PARAM_MESSAGE_2_CARRY_2_KS_PBS_GAUSSIAN_2M128)
         .build();
     let (hl_client_key, hl_server_key) = generate_keys(config);
     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(V1_0_PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M128);
+        gen_keys(V1_2_PARAM_MESSAGE_1_CARRY_1_KS_PBS_GAUSSIAN_2M128);
 
     let ksk = KeySwitchingKey::new(
         (&client_key, Some(&server_key)),
         (&underlying_ck, &underlying_sk),
-        V1_0_PARAM_KEYSWITCH_1_1_KS_PBS_TO_2_2_KS_PBS_GAUSSIAN_2M128,
+        V1_2_PARAM_KEYSWITCH_1_1_KS_PBS_TO_2_2_KS_PBS_GAUSSIAN_2M128,
     );
 
     let key_string = "0053A6F94C9FF24598EB".to_string();

backends/tfhe-cuda-backend/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "tfhe-cuda-backend"
-version = "0.8.0"
+version = "0.10.0"
 edition = "2021"
 authors = ["Zama team"]
 license = "BSD-3-Clause-Clear"
@@ -15,3 +15,7 @@ keywords = ["fully", "homomorphic", "encryption", "fhe", "cryptography"]
 cmake = { version = "0.1" }
 pkg-config = { version = "0.3" }
 bindgen = "0.71"
+
+[features]
+experimental-multi-arch = []
+profile = []

backends/tfhe-cuda-backend/README.md

@@ -13,24 +13,26 @@ and forth between the CPU and the GPU, to create and destroy Cuda streams, etc.:
 - `cuda_get_number_of_gpus`
 - `cuda_synchronize_device`
 The cryptographic operations it provides are:
-- an amortized implementation of the TFHE programmable bootstrap: `cuda_bootstrap_amortized_lwe_ciphertext_vector_32` and `cuda_bootstrap_amortized_lwe_ciphertext_vector_64`
-- a low latency implementation of the TFHE programmable bootstrap: `cuda_bootstrap_low latency_lwe_ciphertext_vector_32` and `cuda_bootstrap_low_latency_lwe_ciphertext_vector_64`
-- the keyswitch: `cuda_keyswitch_lwe_ciphertext_vector_32` and `cuda_keyswitch_lwe_ciphertext_vector_64`
-- the larger precision programmable bootstrap (wop PBS, which supports up to 16 bits of message while the classical PBS only supports up to 8 bits of message) and its sub-components: `cuda_wop_pbs_64`, `cuda_extract_bits_64`, `cuda_circuit_bootstrap_64`, `cuda_cmux_tree_64`, `cuda_blind_rotation_sample_extraction_64`
-- acceleration for leveled operations: `cuda_negate_lwe_ciphertext_vector_64`, `cuda_add_lwe_ciphertext_vector_64`, `cuda_add_lwe_ciphertext_vector_plaintext_vector_64`, `cuda_mult_lwe_ciphertext_vector_cleartext_vector`.
+- an implementation of the classical TFHE programmable bootstrap,
+- an implementation of the multi-bit TFHE programmable bootstrap,
+- the keyswitch,
+- acceleration for leveled operations,
+- acceleration for arithmetics over encrypted integers of arbitrary size, 
+- acceleration for integer compression/decompression.
 
 ## Dependencies
 
 **Disclaimer**: Compilation on Windows/Mac is not supported yet. Only Nvidia GPUs are supported. 
 
-- nvidia driver - for example, if you're running Ubuntu 20.04 check this [page](https://linuxconfig.org/how-to-install-the-nvidia-drivers-on-ubuntu-20-04-focal-fossa-linux) for installation
+- nvidia driver - for example, if you're running Ubuntu 20.04 check this [page](https://linuxconfig.org/how-to-install-the-nvidia-drivers-on-ubuntu-20-04-focal-fossa-linux) for installation. You need an Nvidia GPU with Compute Capability >= 3.0
 - [nvcc](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html) >= 10.0
 - [gcc](https://gcc.gnu.org/) >= 8.0 - check this [page](https://gist.github.com/ax3l/9489132) for more details about nvcc/gcc compatible versions
 - [cmake](https://cmake.org/) >= 3.24
+- libclang, to match Rust bingen [requirements](https://rust-lang.github.io/rust-bindgen/requirements.html) >= 9.0
 
 ## Build
 
-The Cuda project held in `tfhe-cuda-backend` can be compiled independently from TFHE-rs in the following way:
+The Cuda project held in `tfhe-cuda-backend` can be compiled independently of TFHE-rs in the following way:
 ```
 git clone git@github.com:zama-ai/tfhe-rs
 cd backends/tfhe-cuda-backend/cuda

backends/tfhe-cuda-backend/build.rs

@@ -37,7 +37,24 @@ fn main() {
             );
         }
 
-        let dest = cmake::build("cuda");
+        let mut cmake_config = cmake::Config::new("cuda");
+
+        // Conditionally pass the "MULTI_ARCH" variable to CMake if the feature is enabled
+        if cfg!(feature = "experimental-multi-arch") {
+            cmake_config.define("MULTI_ARCH", "ON");
+        } else {
+            cmake_config.define("MULTI_ARCH", "OFF");
+        }
+        // Conditionally pass the "USE_NVTOOLS" variable to CMake if the feature is enabled
+        if cfg!(feature = "profile") {
+            cmake_config.define("USE_NVTOOLS", "ON");
+            println!("cargo:rustc-link-lib=nvToolsExt");
+        } else {
+            cmake_config.define("USE_NVTOOLS", "OFF");
+        }
+
+        // Build the CMake project
+        let dest = cmake_config.build();
         println!("cargo:rustc-link-search=native={}", dest.display());
         println!("cargo:rustc-link-lib=static=tfhe_cuda_backend");
 
@@ -60,8 +77,11 @@ fn main() {
             "cuda/include/ciphertext.h",
             "cuda/include/integer/compression/compression.h",
             "cuda/include/integer/integer.h",
-            "cuda/include/keyswitch.h",
+            "cuda/include/zk/zk.h",
+            "cuda/include/keyswitch/keyswitch.h",
+            "cuda/include/keyswitch/ks_enums.h",
             "cuda/include/linear_algebra.h",
+            "cuda/include/fft/fft128.h",
             "cuda/include/pbs/programmable_bootstrap.h",
             "cuda/include/pbs/programmable_bootstrap_multibit.h",
         ];
@@ -73,7 +93,7 @@ fn main() {
         };
         let mut headers_modified = bindings_modified;
         for header in headers {
-            println!("cargo:rerun-if-changed={}", header);
+            println!("cargo:rerun-if-changed={header}");
             // Check modification times
             let header_modified = std::fs::metadata(header).unwrap().modified().unwrap();
             if header_modified > headers_modified {

backends/tfhe-cuda-backend/cuda/CMakeLists.txt

@@ -34,7 +34,13 @@ else()
   set(CUDA_SUCCESS "FALSE")
 endif()
 
-if(${CUDA_SUCCESS})
+if(${MULTI_ARCH})
+  message(STATUS "Multi-architecture GPU build enabled, 75, 80, 86, 89")
+  message(STATUS "CUDA Version: ${CUDA_VERSION_STRING}")
+  message(STATUS "CUDA Path: ${CUDA_TOOLKIT_ROOT_DIR}")
+  message(STATUS "CUDA Libraries: ${CUDA_LIBRARIES}")
+  message(STATUS "CUDA Performance Primitives: ${CUDA_npp_LIBRARY}")
+elseif(${CUDA_SUCCESS})
   message(STATUS "CUDA Architecture: ${ARCH}")
   message(STATUS "CUDA Version: ${CUDA_VERSION_STRING}")
   message(STATUS "CUDA Path: ${CUDA_TOOLKIT_ROOT_DIR}")
@@ -56,7 +62,10 @@ set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wall -Wextra")
 set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS}  -g")
 set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${OpenMP_CXX_FLAGS}")
 set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -Xcompiler ${OpenMP_CXX_FLAGS}")
-if(${CUDA_SUCCESS})
+if(${MULTI_ARCH})
+  set(CUDA_ARCH "750")
+  set(CMAKE_CUDA_ARCHITECTURES 75 80 86 89)
+elseif(${CUDA_SUCCESS})
   set(CMAKE_CUDA_ARCHITECTURES native)
   string(REPLACE "-arch=sm_" "" CUDA_ARCH "${ARCH}")
   set(CUDA_ARCH "${CUDA_ARCH}0")
@@ -79,11 +88,18 @@ else()
   set(OPTIMIZATION_FLAGS "${OPTIMIZATION_FLAGS} -O3")
 endif()
 
-# in production, should use -arch=sm_70 --ptxas-options=-v to see register spills -lineinfo for better debugging
+# Check if the USE_NVTOOLS environment variable is set
+if(${USE_NVTOOLS})
+  message(STATUS "USE_NVTOOLS is enabled")
+  add_definitions(-DUSE_NVTOOLS)
+endif()
+
+# in production, should use -arch=sm_70 --ptxas-options=-v to see register spills -lineinfo for better debugging to use
+# nvtx when profiling -lnvToolsExt
 set(CMAKE_CUDA_FLAGS
     "${CMAKE_CUDA_FLAGS} -ccbin ${CMAKE_CXX_COMPILER} ${OPTIMIZATION_FLAGS}\
   -std=c++17 --no-exceptions  --expt-relaxed-constexpr -rdc=true \
-  --use_fast_math -Xcompiler -fPIC")
+  --use_fast_math -Xcompiler -fPIC ")
 
 set(INCLUDE_DIR include)
 

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

@@ -4,6 +4,7 @@
 #include "stdint.h"
 
 extern "C" {
+
 void cuda_convert_lwe_ciphertext_vector_to_gpu_64(void *stream,
                                                   uint32_t gpu_index,
                                                   void *dest, void const *src,
@@ -18,7 +19,24 @@ 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 const *glwe_array_in,
                                  uint32_t const *nth_array, uint32_t num_nths,
-                                 uint32_t glwe_dimension,
+                                 uint32_t lwe_per_glwe, uint32_t glwe_dimension,
                                  uint32_t polynomial_size);
+
+void cuda_modulus_switch_inplace_64(void *stream, uint32_t gpu_index,
+                                    void *lwe_array_out, uint32_t size,
+                                    uint32_t log_modulus);
+
+void cuda_improve_noise_modulus_switch_64(
+    void *stream, uint32_t gpu_index, void *lwe_array_out,
+    void const *lwe_array_in, void const *lwe_array_indexes,
+    void const *encrypted_zeros, uint32_t lwe_size, uint32_t num_lwes,
+    uint32_t num_zeros, double input_variance, double r_sigma, double bound,
+    uint32_t log_modulus);
+
+void cuda_glwe_sample_extract_128(
+    void *stream, uint32_t gpu_index, void *lwe_array_out,
+    void const *glwe_array_in, uint32_t const *nth_array, uint32_t num_nths,
+    uint32_t lwe_per_glwe, uint32_t glwe_dimension, uint32_t polynomial_size);
 }
+
 #endif

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

@@ -8,7 +8,6 @@
 #include <cuda_runtime.h>
 #include <vector>
 
-#define synchronize_threads_in_block() __syncthreads()
 extern "C" {
 
 #define check_cuda_error(ans)                                                  \
@@ -48,22 +47,42 @@ uint32_t cuda_is_available();
 
 void *cuda_malloc(uint64_t size, uint32_t gpu_index);
 
+void *cuda_malloc_with_size_tracking_async(uint64_t size, cudaStream_t stream,
+                                           uint32_t gpu_index,
+                                           uint64_t *size_tracker,
+                                           bool allocate_gpu_memory);
+
 void *cuda_malloc_async(uint64_t size, cudaStream_t stream, uint32_t gpu_index);
 
-void cuda_check_valid_malloc(uint64_t size, uint32_t gpu_index);
+bool cuda_check_valid_malloc(uint64_t size, uint32_t gpu_index);
 
-void cuda_memcpy_async_to_gpu(void *dest, void *src, uint64_t size,
+void cuda_memcpy_with_size_tracking_async_to_gpu(void *dest, const void *src,
+                                                 uint64_t size,
+                                                 cudaStream_t stream,
+                                                 uint32_t gpu_index,
+                                                 bool gpu_memory_allocated);
+
+void cuda_memcpy_async_to_gpu(void *dest, const void *src, uint64_t size,
                               cudaStream_t stream, uint32_t gpu_index);
 
+void cuda_memcpy_with_size_tracking_async_gpu_to_gpu(
+    void *dest, void const *src, uint64_t size, cudaStream_t stream,
+    uint32_t gpu_index, bool gpu_memory_allocated);
+
 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,
+void cuda_memcpy_gpu_to_gpu(void *dest, void const *src, uint64_t size,
                             uint32_t gpu_index);
 
 void cuda_memcpy_async_to_cpu(void *dest, const void *src, uint64_t size,
                               cudaStream_t stream, uint32_t gpu_index);
 
+void cuda_memset_with_size_tracking_async(void *dest, uint64_t val,
+                                          uint64_t size, cudaStream_t stream,
+                                          uint32_t gpu_index,
+                                          bool gpu_memory_allocated);
+
 void cuda_memset_async(void *dest, uint64_t val, uint64_t size,
                        cudaStream_t stream, uint32_t gpu_index);
 
@@ -73,10 +92,14 @@ void cuda_synchronize_device(uint32_t gpu_index);
 
 void cuda_drop(void *ptr, uint32_t gpu_index);
 
+void cuda_drop_with_size_tracking_async(void *ptr, cudaStream_t stream,
+                                        uint32_t gpu_index,
+                                        bool gpu_memory_allocated);
+
 void cuda_drop_async(void *ptr, cudaStream_t stream, uint32_t gpu_index);
 }
 
-int cuda_get_max_shared_memory(uint32_t gpu_index);
+uint32_t cuda_get_max_shared_memory(uint32_t gpu_index);
 
 bool cuda_check_support_cooperative_groups();
 

backends/tfhe-cuda-backend/cuda/include/fft/fft128.h

@@ -0,0 +1,17 @@
+#include <stdint.h>
+extern "C" {
+void cuda_fourier_transform_forward_as_torus_f128_async(
+    void *stream, uint32_t gpu_index, void *re0, void *re1, void *im0,
+    void *im1, void const *standard, uint32_t const N,
+    const uint32_t number_of_samples);
+
+void cuda_fourier_transform_forward_as_integer_f128_async(
+    void *stream, uint32_t gpu_index, void *re0, void *re1, void *im0,
+    void *im1, void const *standard, uint32_t const N,
+    const uint32_t number_of_samples);
+
+void cuda_fourier_transform_backward_as_torus_f128_async(
+    void *stream, uint32_t gpu_index, void *standard, void const *re0,
+    void const *re1, void const *im0, void const *im1, uint32_t const N,
+    const uint32_t number_of_samples);
+}

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

@@ -8,7 +8,7 @@ extern std::mutex m;
 extern bool p2p_enabled;
 
 extern "C" {
-int32_t cuda_setup_multi_gpu();
+int32_t cuda_setup_multi_gpu(int device_0_id);
 }
 
 // Define a variant type that can be either a vector or a single pointer

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

@@ -4,7 +4,7 @@
 #include "../../pbs/pbs_enums.h"
 
 extern "C" {
-void scratch_cuda_integer_compress_radix_ciphertext_64(
+uint64_t 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,
@@ -13,15 +13,15 @@ void scratch_cuda_integer_compress_radix_ciphertext_64(
     uint32_t lwe_per_glwe, uint32_t storage_log_modulus,
     bool allocate_gpu_memory);
 
-void scratch_cuda_integer_decompress_radix_ciphertext_64(
+uint64_t 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);
+    uint32_t storage_log_modulus, uint32_t body_count, bool allocate_gpu_memory,
+    bool allocate_ms_array);
 
 void cuda_integer_compress_radix_ciphertext_64(
     void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,

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

@@ -14,41 +14,44 @@ template <typename Torus> struct int_compression {
   int8_t *fp_ks_buffer;
   Torus *tmp_lwe;
   Torus *tmp_glwe_array_out;
+  bool gpu_memory_allocated;
 
   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) {
+                  uint32_t storage_log_modulus, bool allocate_gpu_memory,
+                  uint64_t *size_tracker) {
+    gpu_memory_allocated = allocate_gpu_memory;
     this->compression_params = compression_params;
     this->lwe_per_glwe = lwe_per_glwe;
     this->storage_log_modulus = storage_log_modulus;
     this->body_count = num_radix_blocks;
 
-    if (allocate_gpu_memory) {
-      Torus glwe_accumulator_size = (compression_params.glwe_dimension + 1) *
-                                    compression_params.polynomial_size;
+    Torus glwe_accumulator_size = (compression_params.glwe_dimension + 1) *
+                                  compression_params.polynomial_size;
 
-      tmp_lwe = (Torus *)cuda_malloc_async(
-          num_radix_blocks * (compression_params.small_lwe_dimension + 1) *
-              sizeof(Torus),
-          streams[0], gpu_indexes[0]);
-      tmp_glwe_array_out = (Torus *)cuda_malloc_async(
-          lwe_per_glwe * glwe_accumulator_size * sizeof(Torus), streams[0],
-          gpu_indexes[0]);
+    tmp_lwe = (Torus *)cuda_malloc_with_size_tracking_async(
+        num_radix_blocks * (compression_params.small_lwe_dimension + 1) *
+            sizeof(Torus),
+        streams[0], gpu_indexes[0], size_tracker, allocate_gpu_memory);
+    tmp_glwe_array_out = (Torus *)cuda_malloc_with_size_tracking_async(
+        lwe_per_glwe * glwe_accumulator_size * sizeof(Torus), streams[0],
+        gpu_indexes[0], size_tracker, allocate_gpu_memory);
 
-      scratch_packing_keyswitch_lwe_list_to_glwe_64(
-          streams[0], gpu_indexes[0], &fp_ks_buffer,
-          compression_params.small_lwe_dimension,
-          compression_params.glwe_dimension, compression_params.polynomial_size,
-          num_radix_blocks, true);
-    }
+    *size_tracker += scratch_packing_keyswitch_lwe_list_to_glwe_64(
+        streams[0], gpu_indexes[0], &fp_ks_buffer,
+        compression_params.small_lwe_dimension,
+        compression_params.glwe_dimension, compression_params.polynomial_size,
+        num_radix_blocks, allocate_gpu_memory);
   }
   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]);
-    cleanup_packing_keyswitch_lwe_list_to_glwe(streams[0], gpu_indexes[0],
-                                               &fp_ks_buffer);
+    cuda_drop_with_size_tracking_async(tmp_lwe, streams[0], gpu_indexes[0],
+                                       gpu_memory_allocated);
+    cuda_drop_with_size_tracking_async(tmp_glwe_array_out, streams[0],
+                                       gpu_indexes[0], gpu_memory_allocated);
+    cleanup_packing_keyswitch_lwe_list_to_glwe(
+        streams[0], gpu_indexes[0], &fp_ks_buffer, gpu_memory_allocated);
   }
 };
 
@@ -66,68 +69,71 @@ template <typename Torus> struct int_decompression {
   uint32_t *tmp_indexes_array;
 
   int_radix_lut<Torus> *decompression_rescale_lut;
+  bool gpu_memory_allocated;
 
   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,
-                    uint32_t storage_log_modulus, bool allocate_gpu_memory) {
+                    uint32_t storage_log_modulus, bool allocate_gpu_memory,
+                    uint64_t *size_tracker) {
+    gpu_memory_allocated = allocate_gpu_memory;
     this->encryption_params = encryption_params;
     this->compression_params = compression_params;
     this->storage_log_modulus = storage_log_modulus;
     this->num_radix_blocks = num_radix_blocks;
     this->body_count = body_count;
 
-    if (allocate_gpu_memory) {
-      Torus glwe_accumulator_size = (compression_params.glwe_dimension + 1) *
-                                    compression_params.polynomial_size;
-      Torus lwe_accumulator_size = (compression_params.glwe_dimension *
-                                        compression_params.polynomial_size +
-                                    1);
-      decompression_rescale_lut = new int_radix_lut<Torus>(
-          streams, gpu_indexes, gpu_count, encryption_params, 1,
-          num_radix_blocks, allocate_gpu_memory);
+    Torus glwe_accumulator_size = (compression_params.glwe_dimension + 1) *
+                                  compression_params.polynomial_size;
+    Torus lwe_accumulator_size = (compression_params.glwe_dimension *
+                                      compression_params.polynomial_size +
+                                  1);
+    decompression_rescale_lut = new int_radix_lut<Torus>(
+        streams, gpu_indexes, gpu_count, encryption_params, 1, num_radix_blocks,
+        allocate_gpu_memory, size_tracker);
 
-      tmp_extracted_glwe = (Torus *)cuda_malloc_async(
-          num_radix_blocks * glwe_accumulator_size * sizeof(Torus), streams[0],
-          gpu_indexes[0]);
-      tmp_indexes_array = (uint32_t *)cuda_malloc_async(
-          num_radix_blocks * sizeof(uint32_t), streams[0], gpu_indexes[0]);
-      tmp_extracted_lwe = (Torus *)cuda_malloc_async(
-          num_radix_blocks * lwe_accumulator_size * sizeof(Torus), streams[0],
-          gpu_indexes[0]);
+    tmp_extracted_glwe = (Torus *)cuda_malloc_with_size_tracking_async(
+        num_radix_blocks * glwe_accumulator_size * sizeof(Torus), streams[0],
+        gpu_indexes[0], size_tracker, allocate_gpu_memory);
+    tmp_indexes_array = (uint32_t *)cuda_malloc_with_size_tracking_async(
+        num_radix_blocks * sizeof(uint32_t), streams[0], gpu_indexes[0],
+        size_tracker, allocate_gpu_memory);
+    tmp_extracted_lwe = (Torus *)cuda_malloc_with_size_tracking_async(
+        num_radix_blocks * lwe_accumulator_size * sizeof(Torus), streams[0],
+        gpu_indexes[0], size_tracker, allocate_gpu_memory);
 
-      // Rescale is done using an identity LUT
-      // Here we do not divide by message_modulus
-      // Example: in the 2_2 case we are mapping a 2 bits message onto a 4 bits
-      // space, we want to keep the original 2 bits value in the 4 bits space,
-      // so we apply the identity and the encoding will rescale it for us.
-      auto decompression_rescale_f = [encryption_params](Torus x) -> Torus {
-        return x;
-      };
+    // Rescale is done using an identity LUT
+    // Here we do not divide by message_modulus
+    // Example: in the 2_2 case we are mapping a 2 bits message onto a 4 bits
+    // space, we want to keep the original 2 bits value in the 4 bits space,
+    // so we apply the identity and the encoding will rescale it for us.
+    auto decompression_rescale_f = [](Torus x) -> Torus { return x; };
 
-      auto effective_compression_message_modulus =
-          encryption_params.carry_modulus;
-      auto effective_compression_carry_modulus = 1;
+    auto effective_compression_message_modulus =
+        encryption_params.carry_modulus;
+    auto effective_compression_carry_modulus = 1;
 
-      generate_device_accumulator_with_encoding<Torus>(
-          streams[0], gpu_indexes[0], decompression_rescale_lut->get_lut(0, 0),
-          decompression_rescale_lut->get_degree(0),
-          decompression_rescale_lut->get_max_degree(0),
-          encryption_params.glwe_dimension, encryption_params.polynomial_size,
-          effective_compression_message_modulus,
-          effective_compression_carry_modulus,
-          encryption_params.message_modulus, encryption_params.carry_modulus,
-          decompression_rescale_f);
+    generate_device_accumulator_with_encoding<Torus>(
+        streams[0], gpu_indexes[0], decompression_rescale_lut->get_lut(0, 0),
+        decompression_rescale_lut->get_degree(0),
+        decompression_rescale_lut->get_max_degree(0),
+        encryption_params.glwe_dimension, encryption_params.polynomial_size,
+        effective_compression_message_modulus,
+        effective_compression_carry_modulus, encryption_params.message_modulus,
+        encryption_params.carry_modulus, decompression_rescale_f,
+        gpu_memory_allocated);
 
-      decompression_rescale_lut->broadcast_lut(streams, gpu_indexes, 0);
-    }
+    decompression_rescale_lut->broadcast_lut(streams, gpu_indexes, 0);
   }
   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]);
+    cuda_drop_with_size_tracking_async(tmp_extracted_glwe, streams[0],
+                                       gpu_indexes[0], gpu_memory_allocated);
+    cuda_drop_with_size_tracking_async(tmp_extracted_lwe, streams[0],
+                                       gpu_indexes[0], gpu_memory_allocated);
+    cuda_drop_with_size_tracking_async(tmp_indexes_array, streams[0],
+                                       gpu_indexes[0], gpu_memory_allocated);
 
     decompression_rescale_lut->release(streams, gpu_indexes, gpu_count);
     delete decompression_rescale_lut;

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

@@ -44,52 +44,57 @@ typedef struct {
   uint64_t *degrees;
   uint64_t *noise_levels;
   uint32_t num_radix_blocks;
+  uint32_t max_num_radix_blocks;
   uint32_t lwe_dimension;
 } CudaRadixCiphertextFFI;
 
-void scratch_cuda_apply_univariate_lut_kb_64(
+uint64_t 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,
-    uint64_t lut_degree, bool allocate_gpu_memory);
-void scratch_cuda_apply_many_univariate_lut_kb_64(
+    uint64_t lut_degree, bool allocate_gpu_memory, bool allocate_ms_array);
+uint64_t scratch_cuda_apply_many_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 num_radix_blocks,
     uint32_t message_modulus, uint32_t carry_modulus, PBS_TYPE pbs_type,
-    uint32_t num_many_lut, uint64_t lut_degree, bool allocate_gpu_memory);
+    uint32_t num_many_lut, uint64_t lut_degree, bool allocate_gpu_memory,
+    bool allocate_ms_array);
 void cuda_apply_univariate_lut_kb_64(
     void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
     CudaRadixCiphertextFFI *output_radix_lwe,
     CudaRadixCiphertextFFI const *input_radix_lwe, int8_t *mem_ptr,
-    void *const *ksks, void *const *bsks);
+    void *const *ksks,
+    CudaModulusSwitchNoiseReductionKeyFFI const *ms_noise_reduction_key,
+    void *const *bsks);
 
 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(
+uint64_t 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,
-    uint64_t lut_degree, bool allocate_gpu_memory);
+    uint64_t lut_degree, bool allocate_gpu_memory, bool allocate_ms_array);
 
 void cuda_apply_bivariate_lut_kb_64(
     void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
     CudaRadixCiphertextFFI *output_radix_lwe,
     CudaRadixCiphertextFFI const *input_radix_lwe_1,
     CudaRadixCiphertextFFI const *input_radix_lwe_2, int8_t *mem_ptr,
-    void *const *ksks, void *const *bsks, uint32_t num_radix_blocks,
-    uint32_t shift);
+    void *const *ksks,
+    CudaModulusSwitchNoiseReductionKeyFFI const *ms_noise_reduction_key,
+    void *const *bsks, uint32_t num_radix_blocks, uint32_t shift);
 
 void cleanup_cuda_apply_bivariate_lut_kb_64(void *const *streams,
                                             uint32_t const *gpu_indexes,
@@ -100,42 +105,45 @@ void cuda_apply_many_univariate_lut_kb_64(
     void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
     CudaRadixCiphertextFFI *output_radix_lwe,
     CudaRadixCiphertextFFI const *input_radix_lwe, int8_t *mem_ptr,
-    void *const *ksks, void *const *bsks, uint32_t num_luts,
-    uint32_t lut_stride);
+    void *const *ksks,
+    CudaModulusSwitchNoiseReductionKeyFFI const *ms_noise_reduction_key,
+    void *const *bsks, uint32_t num_luts, uint32_t lut_stride);
 
-void scratch_cuda_full_propagation_64(
+uint64_t 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);
+    bool allocate_gpu_memory, bool allocate_ms_array);
 
-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 cuda_full_propagation_64_inplace(
+    void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
+    CudaRadixCiphertextFFI *input_blocks, int8_t *mem_ptr, void *const *ksks,
+    CudaModulusSwitchNoiseReductionKeyFFI const *ms_noise_reduction_key,
+    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(
+uint64_t 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);
+    bool allocate_gpu_memory, bool allocate_ms_array);
 
 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);
+    CudaRadixCiphertextFFI *radix_lwe_out,
+    CudaRadixCiphertextFFI const *radix_lwe_left, bool const is_bool_left,
+    CudaRadixCiphertextFFI const *radix_lwe_right, bool const is_bool_right,
+    void *const *bsks, void *const *ksks,
+    CudaModulusSwitchNoiseReductionKeyFFI const *ms_noise_reduction_key,
+    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,
@@ -145,40 +153,43 @@ void cuda_negate_integer_radix_ciphertext_64(
     void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
     CudaRadixCiphertextFFI *lwe_array_out,
     CudaRadixCiphertextFFI const *lwe_array_in, uint32_t message_modulus,
-    uint32_t carry_modulus);
+    uint32_t carry_modulus, uint32_t num_radix_blocks);
 
 void cuda_scalar_addition_integer_radix_ciphertext_64_inplace(
     void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
     CudaRadixCiphertextFFI *lwe_array, void const *scalar_input,
-    uint32_t num_scalars, uint32_t message_modulus, uint32_t carry_modulus);
+    void const *h_scalar_input, uint32_t num_scalars, uint32_t message_modulus,
+    uint32_t carry_modulus);
 
-void scratch_cuda_integer_radix_logical_scalar_shift_kb_64(
+uint64_t 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);
+    bool allocate_gpu_memory, bool allocate_ms_array);
 
 void cuda_integer_radix_logical_scalar_shift_kb_64_inplace(
     void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
     CudaRadixCiphertextFFI *lwe_array, uint32_t shift, int8_t *mem_ptr,
-    void *const *bsks, void *const *ksks);
+    void *const *bsks, void *const *ksks,
+    CudaModulusSwitchNoiseReductionKeyFFI const *ms_noise_reduction_key);
 
-void scratch_cuda_integer_radix_arithmetic_scalar_shift_kb_64(
+uint64_t 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);
+    bool allocate_gpu_memory, bool allocate_ms_array);
 
 void cuda_integer_radix_arithmetic_scalar_shift_kb_64_inplace(
     void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
     CudaRadixCiphertextFFI *lwe_array, uint32_t shift, int8_t *mem_ptr,
-    void *const *bsks, void *const *ksks);
+    void *const *bsks, void *const *ksks,
+    CudaModulusSwitchNoiseReductionKeyFFI const *ms_noise_reduction_key);
 
 void cleanup_cuda_integer_radix_logical_scalar_shift(
     void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
@@ -188,85 +199,94 @@ 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(
+uint64_t 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);
+    bool is_signed, bool allocate_gpu_memory, bool allocate_ms_array);
 
 void cuda_integer_radix_shift_and_rotate_kb_64_inplace(
     void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
     CudaRadixCiphertextFFI *lwe_array, CudaRadixCiphertextFFI const *lwe_shift,
-    int8_t *mem_ptr, void *const *bsks, void *const *ksks);
+    int8_t *mem_ptr, void *const *bsks, void *const *ksks,
+    CudaModulusSwitchNoiseReductionKeyFFI const *ms_noise_reduction_key);
 
 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(
+uint64_t 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);
+    COMPARISON_TYPE op_type, bool is_signed, bool allocate_gpu_memory,
+    bool allocate_ms_array);
 
 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);
+    CudaRadixCiphertextFFI *lwe_array_out,
+    CudaRadixCiphertextFFI const *lwe_array_1,
+    CudaRadixCiphertextFFI const *lwe_array_2, int8_t *mem_ptr,
+    void *const *bsks, void *const *ksks,
+    CudaModulusSwitchNoiseReductionKeyFFI const *ms_noise_reduction_key);
 
 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);
+    CudaRadixCiphertextFFI *lwe_array_out,
+    CudaRadixCiphertextFFI const *lwe_array_in, void const *scalar_blocks,
+    void const *h_scalar_blocks, int8_t *mem_ptr, void *const *bsks,
+    void *const *ksks,
+    CudaModulusSwitchNoiseReductionKeyFFI const *ms_noise_reduction_key,
+    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(
+uint64_t 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);
+    BITOP_TYPE op_type, bool allocate_gpu_memory, bool allocate_ms_array);
 
 void cuda_bitop_integer_radix_ciphertext_kb_64(
     void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
     CudaRadixCiphertextFFI *lwe_array_out,
     CudaRadixCiphertextFFI const *lwe_array_1,
     CudaRadixCiphertextFFI const *lwe_array_2, int8_t *mem_ptr,
-    void *const *bsks, void *const *ksks);
+    void *const *bsks, void *const *ksks,
+    CudaModulusSwitchNoiseReductionKeyFFI const *ms_noise_reduction_key);
 
 void cuda_scalar_bitop_integer_radix_ciphertext_kb_64(
     void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
     CudaRadixCiphertextFFI *lwe_array_out,
     CudaRadixCiphertextFFI const *lwe_array_input, void const *clear_blocks,
-    uint32_t num_clear_blocks, int8_t *mem_ptr, void *const *bsks,
-    void *const *ksks);
+    void const *h_clear_blocks, uint32_t num_clear_blocks, int8_t *mem_ptr,
+    void *const *bsks, void *const *ksks,
+    CudaModulusSwitchNoiseReductionKeyFFI const *ms_noise_reduction_key);
 
 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(
+uint64_t 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);
+    bool allocate_gpu_memory, bool allocate_ms_array);
 
 void cuda_cmux_integer_radix_ciphertext_kb_64(
     void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
@@ -274,60 +294,65 @@ void cuda_cmux_integer_radix_ciphertext_kb_64(
     CudaRadixCiphertextFFI const *lwe_condition,
     CudaRadixCiphertextFFI const *lwe_array_true,
     CudaRadixCiphertextFFI const *lwe_array_false, int8_t *mem_ptr,
-    void *const *bsks, void *const *ksks);
+    void *const *bsks, void *const *ksks,
+    CudaModulusSwitchNoiseReductionKeyFFI const *ms_noise_reduction_key);
 
 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(
+uint64_t 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);
+    bool allocate_gpu_memory, bool allocate_ms_array);
 
 void cuda_integer_radix_scalar_rotate_kb_64_inplace(
     void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
     CudaRadixCiphertextFFI *lwe_array, uint32_t n, int8_t *mem_ptr,
-    void *const *bsks, void *const *ksks);
+    void *const *bsks, void *const *ksks,
+    CudaModulusSwitchNoiseReductionKeyFFI const *ms_noise_reduction_key);
 
 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(
+uint64_t 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);
+    uint32_t uses_carry, bool allocate_gpu_memory, bool allocate_ms_array);
 
-void scratch_cuda_add_and_propagate_single_carry_kb_64_inplace(
+uint64_t 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);
+    uint32_t uses_carry, bool allocate_gpu_memory, bool allocate_ms_array);
 
 void cuda_propagate_single_carry_kb_64_inplace(
     void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
     CudaRadixCiphertextFFI *lwe_array, CudaRadixCiphertextFFI *carry_out,
     const CudaRadixCiphertextFFI *carry_in, int8_t *mem_ptr, void *const *bsks,
-    void *const *ksks, uint32_t requested_flag, uint32_t uses_carry);
+    void *const *ksks,
+    CudaModulusSwitchNoiseReductionKeyFFI const *ms_noise_reduction_key,
+    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,
     CudaRadixCiphertextFFI *lhs_array, const CudaRadixCiphertextFFI *rhs_array,
     CudaRadixCiphertextFFI *carry_out, const CudaRadixCiphertextFFI *carry_in,
     int8_t *mem_ptr, void *const *bsks, void *const *ksks,
+    CudaModulusSwitchNoiseReductionKeyFFI const *ms_noise_reduction_key,
     uint32_t requested_flag, uint32_t uses_carry);
 
 void cleanup_cuda_propagate_single_carry(void *const *streams,
@@ -340,100 +365,107 @@ void cleanup_cuda_add_and_propagate_single_carry(void *const *streams,
                                                  uint32_t gpu_count,
                                                  int8_t **mem_ptr_void);
 
-void scratch_cuda_integer_overflowing_sub_kb_64_inplace(
+uint64_t 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);
+    bool allocate_gpu_memory, bool allocate_ms_array);
 
 void cuda_integer_overflowing_sub_kb_64_inplace(
     void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
     CudaRadixCiphertextFFI *lhs_array, const CudaRadixCiphertextFFI *rhs_array,
     CudaRadixCiphertextFFI *overflow_block,
     const CudaRadixCiphertextFFI *input_borrow, int8_t *mem_ptr,
-    void *const *bsks, void *const *ksks, uint32_t compute_overflow,
-    uint32_t uses_input_borrow);
+    void *const *bsks, void *const *ksks,
+    CudaModulusSwitchNoiseReductionKeyFFI const *ms_noise_reduction_key,
+    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(
+uint64_t 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);
+    bool allocate_gpu_memory, bool allocate_ms_array);
 
 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);
+    CudaRadixCiphertextFFI *radix_lwe_out,
+    CudaRadixCiphertextFFI *radix_lwe_vec, int8_t *mem_ptr, void *const *bsks,
+    void *const *ksks,
+    CudaModulusSwitchNoiseReductionKeyFFI const *ms_noise_reduction_key);
 
 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(
+uint64_t 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);
+    PBS_TYPE pbs_type, bool allocate_gpu_memory, bool allocate_ms_array);
 
 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,
+    CudaRadixCiphertextFFI *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 *const *ksks,
+    CudaModulusSwitchNoiseReductionKeyFFI const *ms_noise_reduction_key,
+    uint32_t polynomial_size, uint32_t message_modulus, 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(
+uint64_t 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);
+    PBS_TYPE pbs_type, bool allocate_gpu_memory, bool allocate_ms_array);
 
 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);
+    CudaRadixCiphertextFFI *quotient, CudaRadixCiphertextFFI *remainder,
+    CudaRadixCiphertextFFI const *numerator,
+    CudaRadixCiphertextFFI const *divisor, bool is_signed, int8_t *mem_ptr,
+    void *const *bsks, void *const *ksks,
+    CudaModulusSwitchNoiseReductionKeyFFI const *ms_noise_reduction_key);
 
 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(
+uint64_t 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,
-    uint64_t lut_degree, bool allocate_gpu_memory);
+    uint64_t lut_degree, bool allocate_gpu_memory, bool allocate_ms_array);
 
 void cuda_integer_compute_prefix_sum_hillis_steele_64(
     void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
     CudaRadixCiphertextFFI *output_radix_lwe,
     CudaRadixCiphertextFFI *generates_or_propagates, int8_t *mem_ptr,
-    void *const *ksks, void *const *bsks, uint32_t num_blocks);
+    void *const *ksks,
+    CudaModulusSwitchNoiseReductionKeyFFI const *ms_noise_reduction_key,
+    void *const *bsks, uint32_t num_blocks);
 
 void cleanup_cuda_integer_compute_prefix_sum_hillis_steele_64(
     void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
@@ -444,56 +476,63 @@ void cuda_integer_reverse_blocks_64_inplace(void *const *streams,
                                             uint32_t gpu_count,
                                             CudaRadixCiphertextFFI *lwe_array);
 
-void scratch_cuda_integer_abs_inplace_radix_ciphertext_kb_64(
+uint64_t 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);
+    PBS_TYPE pbs_type, bool allocate_gpu_memory, bool allocate_ms_array);
 
 void cuda_integer_abs_inplace_radix_ciphertext_kb_64(
     void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
     CudaRadixCiphertextFFI *ct, int8_t *mem_ptr, bool is_signed,
-    void *const *bsks, void *const *ksks);
+    void *const *bsks, void *const *ksks,
+    CudaModulusSwitchNoiseReductionKeyFFI const *ms_noise_reduction_key);
 
 void cleanup_cuda_integer_abs_inplace(void *const *streams,
                                       uint32_t const *gpu_indexes,
                                       uint32_t gpu_count,
                                       int8_t **mem_ptr_void);
 
-void scratch_cuda_integer_are_all_comparisons_block_true_kb_64(
+uint64_t scratch_cuda_integer_are_all_comparisons_block_true_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_radix_blocks,
     uint32_t message_modulus, uint32_t carry_modulus, PBS_TYPE pbs_type,
-    bool allocate_gpu_memory);
+    bool allocate_gpu_memory, bool allocate_ms_array);
 
 void cuda_integer_are_all_comparisons_block_true_kb_64(
     void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
-    void *lwe_array_out, void const *lwe_array_in, int8_t *mem_ptr,
-    void *const *bsks, void *const *ksks, uint32_t num_radix_blocks);
+    CudaRadixCiphertextFFI *lwe_array_out,
+    CudaRadixCiphertextFFI const *lwe_array_in, int8_t *mem_ptr,
+    void *const *bsks, void *const *ksks,
+    CudaModulusSwitchNoiseReductionKeyFFI const *ms_noise_reduction_key,
+    uint32_t num_radix_blocks);
 
 void cleanup_cuda_integer_are_all_comparisons_block_true(
     void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
     int8_t **mem_ptr_void);
 
-void scratch_cuda_integer_is_at_least_one_comparisons_block_true_kb_64(
+uint64_t scratch_cuda_integer_is_at_least_one_comparisons_block_true_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_radix_blocks,
     uint32_t message_modulus, uint32_t carry_modulus, PBS_TYPE pbs_type,
-    bool allocate_gpu_memory);
+    bool allocate_gpu_memory, bool allocate_ms_array);
 
 void cuda_integer_is_at_least_one_comparisons_block_true_kb_64(
     void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,
-    void *lwe_array_out, void const *lwe_array_in, int8_t *mem_ptr,
-    void *const *bsks, void *const *ksks, uint32_t num_radix_blocks);
+    CudaRadixCiphertextFFI *lwe_array_out,
+    CudaRadixCiphertextFFI const *lwe_array_in, int8_t *mem_ptr,
+    void *const *bsks, void *const *ksks,
+    CudaModulusSwitchNoiseReductionKeyFFI const *ms_noise_reduction_key,
+    uint32_t num_radix_blocks);
 
 void cleanup_cuda_integer_is_at_least_one_comparisons_block_true(
     void *const *streams, uint32_t const *gpu_indexes, uint32_t gpu_count,

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

@@ -1,8 +1,15 @@
 #ifndef CUDA_RADIX_CIPHERTEXT_H
 #define CUDA_RADIX_CIPHERTEXT_H
 
-void release_radix_ciphertext(cudaStream_t const stream,
-                              uint32_t const gpu_index,
-                              CudaRadixCiphertextFFI *data);
+void release_radix_ciphertext_async(cudaStream_t const stream,
+                                    uint32_t const gpu_index,
+                                    CudaRadixCiphertextFFI *data,
+                                    const bool gpu_memory_allocated);
 
+void reset_radix_ciphertext_blocks(CudaRadixCiphertextFFI *data,
+                                   uint32_t new_num_blocks);
+
+void into_radix_ciphertext(CudaRadixCiphertextFFI *radix, void *lwe_array,
+                           const uint32_t num_radix_blocks,
+                           const uint32_t lwe_dimension);
 #endif