feat: metal acceleration for MSM solving (#909)

---------

Co-authored-by: dante <45801863+alexander-camuto@users.noreply.github.com>

.github/workflows/benchmarks.yml

@@ -6,22 +6,15 @@ on:
         description: "Test scenario tags"
 
 jobs:
-  bench_elgamal:
-    runs-on: self-hosted
-    steps:
-      - uses: actions/checkout@v4
-      - uses: actions-rs/toolchain@v1
-        with:
-          toolchain: nightly-2023-06-27
-          override: true
-          components: rustfmt, clippy
-      - name: Bench elgamal
-        run: cargo bench --verbose --bench elgamal
 
   bench_poseidon:
+    permissions:
+      contents: read
     runs-on: self-hosted
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: actions-rs/toolchain@v1
         with:
           toolchain: nightly-2023-06-27
@@ -31,10 +24,14 @@ jobs:
         run: cargo bench --verbose --bench poseidon
 
   bench_einsum_accum_matmul:
+    permissions:
+      contents: read
     runs-on: self-hosted
     needs: [bench_poseidon]
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: actions-rs/toolchain@v1
         with:
           toolchain: nightly-2023-06-27
@@ -44,10 +41,14 @@ jobs:
         run: cargo bench --verbose --bench accum_einsum_matmul
 
   bench_accum_matmul_relu:
+    permissions:
+      contents: read
     runs-on: self-hosted
     needs: [bench_poseidon]
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: actions-rs/toolchain@v1
         with:
           toolchain: nightly-2023-06-27
@@ -57,10 +58,14 @@ jobs:
         run: cargo bench --verbose --bench accum_matmul_relu
 
   bench_accum_matmul_relu_overflow:
+    permissions:
+      contents: read
     runs-on: self-hosted
     needs: [bench_poseidon]
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: actions-rs/toolchain@v1
         with:
           toolchain: nightly-2023-06-27
@@ -70,10 +75,14 @@ jobs:
         run: cargo bench --verbose --bench accum_matmul_relu_overflow
 
   bench_relu:
+    permissions:
+      contents: read
     runs-on: self-hosted
     needs: [bench_poseidon]
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: actions-rs/toolchain@v1
         with:
           toolchain: nightly-2023-06-27
@@ -83,10 +92,14 @@ jobs:
         run: cargo bench --verbose --bench relu
 
   bench_accum_dot:
+    permissions:
+      contents: read
     runs-on: self-hosted
     needs: [bench_poseidon]
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: actions-rs/toolchain@v1
         with:
           toolchain: nightly-2023-06-27
@@ -96,10 +109,14 @@ jobs:
         run: cargo bench --verbose --bench accum_dot
 
   bench_accum_conv:
+    permissions:
+      contents: read
     runs-on: self-hosted
     needs: [bench_poseidon]
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: actions-rs/toolchain@v1
         with:
           toolchain: nightly-2023-06-27
@@ -109,10 +126,14 @@ jobs:
         run: cargo bench --verbose --bench accum_conv
 
   bench_accum_sumpool:
+    permissions:
+      contents: read
     runs-on: self-hosted
     needs: [bench_poseidon]
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: actions-rs/toolchain@v1
         with:
           toolchain: nightly-2023-06-27
@@ -122,10 +143,14 @@ jobs:
         run: cargo bench --verbose --bench accum_sumpool
 
   bench_pairwise_add:
+    permissions:
+      contents: read
     runs-on: self-hosted
     needs: [bench_poseidon]
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: actions-rs/toolchain@v1
         with:
           toolchain: nightly-2023-06-27
@@ -135,10 +160,14 @@ jobs:
         run: cargo bench --verbose --bench pairwise_add
 
   bench_accum_sum:
+    permissions:
+      contents: read
     runs-on: self-hosted
     needs: [bench_poseidon]
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: actions-rs/toolchain@v1
         with:
           toolchain: nightly-2023-06-27
@@ -148,10 +177,14 @@ jobs:
         run: cargo bench --verbose --bench accum_sum
 
   bench_pairwise_pow:
+    permissions:
+      contents: read
     runs-on: self-hosted
     needs: [bench_poseidon]
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: actions-rs/toolchain@v1
         with:
           toolchain: nightly-2023-06-27

.github/workflows/engine.yml

@@ -15,11 +15,16 @@ defaults:
     working-directory: .
 jobs:
   publish-wasm-bindings:
+    permissions:
+      contents: read
+      packages: write
     name: publish-wasm-bindings
     runs-on: ubuntu-latest
     if: startsWith(github.ref, 'refs/tags/')
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: actions-rs/toolchain@v1
         with:
           toolchain: nightly-2024-07-18
@@ -51,7 +56,7 @@ jobs:
         run: |
           echo '{
             "name": "@ezkljs/engine",
-            "version": "${{ github.ref_name }}",
+            "version": "${RELEASE_TAG}",
             "dependencies": {
               "@types/json-bigint": "^1.0.1",
               "json-bigint": "^1.0.0"
@@ -184,21 +189,26 @@ jobs:
 
 
   in-browser-evm-ver-publish:
+    permissions:
+      contents: read
+      packages: write
     name: publish-in-browser-evm-verifier-package
     needs: [publish-wasm-bindings]
     runs-on: ubuntu-latest
     if: startsWith(github.ref, 'refs/tags/')
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - name: Update version in package.json
         shell: bash
         env:
           RELEASE_TAG: ${{ github.ref_name }}
         run: |
-          sed -i "s|\"version\": \".*\"|\"version\": \"${{ github.ref_name }}\"|" in-browser-evm-verifier/package.json
+          sed -i "s|\"version\": \".*\"|\"version\": \"${RELEASE_TAG}\"|" in-browser-evm-verifier/package.json
       - name: Prepare tag and fetch package integrity
         run: |
-          CLEANED_TAG=${{ github.ref_name }} # Get the tag from ref_name
+          CLEANED_TAG=${RELEASE_TAG} # Get the tag from ref_name
           CLEANED_TAG="${CLEANED_TAG#v}" # Remove leading 'v'
           echo "CLEANED_TAG=${CLEANED_TAG}" >> $GITHUB_ENV # Set it as an environment variable for later steps
           ENGINE_INTEGRITY=$(npm view @ezkljs/engine@$CLEANED_TAG dist.integrity)

.github/workflows/large-tests.yml

@@ -6,9 +6,13 @@ on:
         description: "Test scenario tags"
 jobs:
   large-tests:
+    permissions:
+      contents: read
     runs-on: kaiju
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: actions-rs/toolchain@v1
         with:
           toolchain: nightly-2024-07-18

.github/workflows/pypi-gpu.yml

@@ -18,12 +18,17 @@ defaults:
 jobs:
 
   linux:
+    permissions:
+      contents: read
+      packages: write
     runs-on: GPU
     strategy:
       matrix:
         target: [x86_64]
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: actions/setup-python@v4
         with:
           python-version: 3.12
@@ -34,6 +39,7 @@ jobs:
         run: |
             mv pyproject.toml pyproject.toml.orig
             sed "s/ezkl/ezkl-gpu/" pyproject.toml.orig >pyproject.toml
+            sed "s/0\\.0\\.0/${RELEASE_TAG//v}/" pyproject.toml.orig >pyproject.toml
 
       - uses: actions-rs/toolchain@v1
         with:

.github/workflows/pypi.yml

@@ -16,6 +16,8 @@ defaults:
 
 jobs:
   macos:
+    permissions:
+      contents: read
     runs-on: macos-latest
     if: startsWith(github.ref, 'refs/tags/')
     strategy:
@@ -23,6 +25,8 @@ jobs:
         target: [x86_64, universal2-apple-darwin]
     steps:
       - uses: actions/checkout@v4
+        with: 
+          persist-credentials: false
       - uses: actions/setup-python@v4
         with:
           python-version: 3.12
@@ -45,6 +49,13 @@ jobs:
           components: rustfmt, clippy
 
       - name: Build wheels
+        if: matrix.target == 'universal2-apple-darwin'
+        uses: PyO3/maturin-action@v1
+        with:
+          target: ${{ matrix.target }}
+          args: --release --out dist --features python-bindings,macos-metal
+      - name: Build wheels
+        if: matrix.target == 'x86_64'
         uses: PyO3/maturin-action@v1
         with:
           target: ${{ matrix.target }}
@@ -62,6 +73,8 @@ jobs:
           path: dist
 
   windows:
+    permissions:
+      contents: read
     runs-on: windows-latest
     if: startsWith(github.ref, 'refs/tags/')
     strategy:
@@ -69,6 +82,8 @@ jobs:
         target: [x64, x86]
     steps:
       - uses: actions/checkout@v4
+        with: 
+          persist-credentials: false
       - uses: actions/setup-python@v4
         with:
           python-version: 3.12
@@ -107,6 +122,8 @@ jobs:
           path: dist
 
   linux:
+    permissions:
+      contents: read
     runs-on: ubuntu-latest
     if: startsWith(github.ref, 'refs/tags/')
     strategy:
@@ -114,6 +131,8 @@ jobs:
         target: [x86_64]
     steps:
       - uses: actions/checkout@v4
+        with: 
+          persist-credentials: false
       - uses: actions/setup-python@v4
         with:
           python-version: 3.12
@@ -220,6 +239,8 @@ jobs:
   #       path: dist
 
   musllinux:
+    permissions:
+      contents: read
     runs-on: ubuntu-latest
     if: startsWith(github.ref, 'refs/tags/')
     strategy:
@@ -228,11 +249,21 @@ jobs:
           - x86_64-unknown-linux-musl
     steps:
       - uses: actions/checkout@v4
+        with: 
+          persist-credentials: false
       - uses: actions/setup-python@v4
         with:
           python-version: 3.12
           architecture: x64
 
+      - name: Set pyproject.toml version to match github tag
+        shell: bash
+        env:
+          RELEASE_TAG: ${{ github.ref_name }}
+        run: |
+          mv pyproject.toml pyproject.toml.orig
+          sed "s/0\\.0\\.0/${RELEASE_TAG//v}/" pyproject.toml.orig >pyproject.toml
+
       - name: Set Cargo.toml version to match github tag
         shell: bash
         env:
@@ -242,7 +273,6 @@ jobs:
           sed "s/0\\.0\\.0/${RELEASE_TAG//v}/" Cargo.toml.orig >Cargo.toml
           mv Cargo.lock Cargo.lock.orig
           sed "s/0\\.0\\.0/${RELEASE_TAG//v}/" Cargo.lock.orig >Cargo.lock
-
       - name: Install required libraries
         shell: bash
         run: |
@@ -276,6 +306,8 @@ jobs:
           path: dist
 
   musllinux-cross:
+    permissions:
+      contents: read
     runs-on: ubuntu-latest
     if: startsWith(github.ref, 'refs/tags/')
     strategy:
@@ -285,6 +317,8 @@ jobs:
             arch: aarch64
     steps:
       - uses: actions/checkout@v4
+        with: 
+          persist-credentials: false
       - uses: actions/setup-python@v4
         with:
           python-version: 3.12
@@ -361,12 +395,15 @@ jobs:
           packages-dir: ./
 
   doc-publish:
+    permissions:
+      contents: read
     name: Trigger ReadTheDocs Build
     runs-on: ubuntu-latest
     needs: pypi-publish
     steps:
       - uses: actions/checkout@v4
-
+        with: 
+          persist-credentials: false
       - name: Trigger RTDs build
         uses: dfm/rtds-action@v1
         with:

.github/workflows/release.yml

@@ -10,6 +10,9 @@ on:
       - "*"
 jobs:
   create-release:
+    permissions:
+      contents: read
+      packages: write
     name: create-release
     runs-on: ubuntu-22.04
     if: startsWith(github.ref, 'refs/tags/')
@@ -33,6 +36,9 @@ jobs:
           tag_name: ${{ env.EZKL_VERSION }}
 
   build-release-gpu:
+    permissions:
+      contents: read
+      packages: write
     name: build-release-gpu
     needs: ["create-release"]
     runs-on: GPU
@@ -50,6 +56,9 @@ jobs:
           components: rustfmt, clippy
       - name: Checkout repo
         uses: actions/checkout@v4
+        with: 
+          persist-credentials: false
+
 
       - name: Get release version from tag
         shell: bash
@@ -91,6 +100,10 @@ jobs:
           asset_content_type: application/octet-stream
 
   build-release:
+    permissions:
+      contents: read
+      packages: write
+      issues: write
     name: build-release
     needs: ["create-release"]
     runs-on: ${{ matrix.os }}
@@ -132,6 +145,8 @@ jobs:
     steps:
       - name: Checkout repo
         uses: actions/checkout@v4
+        with: 
+          persist-credentials: false
 
       - name: Get release version from tag
         shell: bash
@@ -181,14 +196,18 @@ jobs:
           echo "target flag is: ${{ env.TARGET_FLAGS }}"
           echo "target dir is: ${{ env.TARGET_DIR }}"
 
-      - name: Build release binary (no asm)
-        if: matrix.build != 'linux-gnu'
+      - name: Build release binary (no asm or metal) 
+        if: matrix.build != 'linux-gnu' && matrix.build != 'macos-aarch64'
         run: ${{ env.CARGO }} build --release ${{ env.TARGET_FLAGS }} -Z sparse-registry
 
       - name: Build release binary (asm)
         if: matrix.build == 'linux-gnu'
         run: ${{ env.CARGO }} build --release ${{ env.TARGET_FLAGS }} -Z sparse-registry --features asm
 
+      - name: Build release binary (metal)
+        if: matrix.build == 'macos-aarch64'
+        run: ${{ env.CARGO }} build --release ${{ env.TARGET_FLAGS }} -Z sparse-registry --features metal
+
       - name: Strip release binary
         if: matrix.build != 'windows-msvc' && matrix.build != 'linux-aarch64'
         run: strip "target/${{ matrix.target }}/release/ezkl"

.github/workflows/rust.yml

@@ -19,11 +19,31 @@ env:
   CARGO_TERM_COLOR: always
 
 jobs:
-  build:
-    runs-on: ubuntu-latest
 
+  fr-age-test:
+    permissions:
+      contents: read
+    runs-on: large-self-hosted
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
+      - uses: actions-rs/toolchain@v1
+        with:
+          toolchain: nightly-2024-07-18
+          override: true
+          components: rustfmt, clippy
+      - name: fr age Mock
+        run: cargo test --release --verbose tests::large_mock_::large_tests_6_expects -- --include-ignored
+
+  build:
+    permissions:
+      contents: read
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: actions-rs/toolchain@v1
         with:
           toolchain: nightly-2024-07-18
@@ -33,9 +53,13 @@ jobs:
         run: cargo build --verbose
 
   docs:
+    permissions:
+      contents: read
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: actions-rs/toolchain@v1
         with:
           toolchain: nightly-2024-07-18
@@ -45,9 +69,13 @@ jobs:
         run: cargo doc --verbose
 
   library-tests:
+    permissions:
+      contents: read
     runs-on: ubuntu-latest-32-cores
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: actions-rs/toolchain@v1
         with:
           toolchain: nightly-2024-07-18
@@ -71,6 +99,8 @@ jobs:
   #     ENABLE_ICICLE_GPU: true
   #   steps:
   #     - uses: actions/checkout@v4
+        # with:
+        #   persist-credentials: false
   #     - uses: actions-rs/toolchain@v1
   #       with:
   #         toolchain: nightly-2024-07-18
@@ -101,9 +131,13 @@ jobs:
   #       run: cargo nextest run conv_relu_col_ultra_overflow --no-capture --features icicle -- --include-ignored
 
   ultra-overflow-tests_og-lookup:
+    permissions:
+      contents: read
     runs-on: non-gpu
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: actions-rs/toolchain@v1
         with:
           toolchain: nightly-2024-07-18
@@ -134,9 +168,13 @@ jobs:
         run: cargo nextest run  --release conv_relu_col_ultra_overflow --no-capture --no-default-features --features ezkl -- --include-ignored
 
   ultra-overflow-tests:
+    permissions:
+      contents: read
     runs-on: non-gpu
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: actions-rs/toolchain@v1
         with:
           toolchain: nightly-2024-07-18
@@ -167,9 +205,13 @@ jobs:
         run: cargo nextest run  --release conv_relu_col_ultra_overflow --no-capture -- --include-ignored
 
   model-serialization:
+    permissions:
+      contents: read
     runs-on: ubuntu-latest-16-cores
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: actions-rs/toolchain@v1
         with:
           toolchain: nightly-2024-07-18
@@ -183,9 +225,13 @@ jobs:
         run: cargo nextest run native_tests::tests::model_serialization_different_binaries_  --test-threads 1
 
   wasm32-tests:
+    permissions:
+      contents: read
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: actions-rs/toolchain@v1
         with:
           toolchain: nightly-2024-07-18
@@ -208,10 +254,14 @@ jobs:
         run: wasm-pack test --chrome --headless -- -Z build-std="panic_abort,std" --features web
 
   mock-proving-tests:
+    permissions:
+      contents: read
     runs-on: non-gpu
     needs: [build, library-tests, docs, python-tests, python-integration-tests]
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: actions-rs/toolchain@v1
         with:
           toolchain: nightly-2024-07-18
@@ -271,10 +321,14 @@ jobs:
         run: cargo nextest run --release --verbose tests::mock_fixed_params_ --test-threads 32
 
   prove-and-verify-evm-tests:
+    permissions:
+      contents: read
     runs-on: non-gpu
     needs: [build, library-tests, docs, python-tests, python-integration-tests]
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: actions-rs/toolchain@v1
         with:
           toolchain: nightly-2024-07-18
@@ -285,6 +339,8 @@ jobs:
           crate: cargo-nextest
           locked: true
       - uses: actions/checkout@v3
+        with:
+          persist-credentials: false
       - name: Use pnpm 8
         uses: pnpm/action-setup@v2
         with:
@@ -349,11 +405,50 @@ jobs:
       - name: KZG prove and verify tests (EVM + hashed outputs)
         run: cargo nextest run --release --verbose tests_evm::kzg_evm_hashed_output_prove_and_verify --test-threads 1
 
+  # prove-and-verify-tests-metal:
+  #   permissions:
+  #     contents: read
+  #   runs-on: macos-13
+  #   # needs: [build, library-tests, docs]
+  #   steps:
+  #     - uses: actions/checkout@v4
+  #       with:
+  #         persist-credentials: false
+  #     - uses: actions-rs/toolchain@v1
+  #       with:
+  #         toolchain: nightly-2024-07-18
+  #         override: true
+  #         components: rustfmt, clippy
+  #     - uses: jetli/wasm-pack-action@v0.4.0
+  #       with:
+  #         # Pin to version 0.12.1
+  #         version: 'v0.12.1'
+  #     - name: Add rust-src
+  #       run: rustup component add rust-src --toolchain nightly-2024-07-18
+  #     - uses: actions/checkout@v3
+  #       with:
+  #         persist-credentials: false
+  #     - name: Use pnpm 8
+  #       uses: pnpm/action-setup@v2
+  #       with:
+  #         version: 8
+  #     - uses: baptiste0928/cargo-install@v1
+  #       with:
+  #         crate: cargo-nextest
+  #         locked: true
+  #     - name: KZG prove and verify tests (public outputs)
+  #       run: cargo nextest run --release --features macos-metal --verbose tests::kzg_prove_and_verify_::t --no-capture
+
+
   prove-and-verify-tests:
+    permissions:
+      contents: read
     runs-on: non-gpu
     needs: [build, library-tests, docs]
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: actions-rs/toolchain@v1
         with:
           toolchain: nightly-2024-07-18
@@ -369,6 +464,8 @@ jobs:
       - name: Add rust-src
         run: rustup component add rust-src --toolchain nightly-2024-07-18-x86_64-unknown-linux-gnu
       - uses: actions/checkout@v3
+        with:
+          persist-credentials: false
       - name: Use pnpm 8
         uses: pnpm/action-setup@v2
         with:
@@ -431,6 +528,8 @@ jobs:
   #     ENABLE_ICICLE_GPU: true
   #   steps:
   #     - uses: actions/checkout@v4
+        # with:
+        #   persist-credentials: false
   #     - uses: actions-rs/toolchain@v1
   #       with:
   #         toolchain: nightly-2024-07-18
@@ -461,10 +560,14 @@ jobs:
   #       run: cargo nextest run --release --verbose tests::kzg_prove_and_verify_hashed --features icicle  --test-threads 1
 
   prove-and-verify-mock-aggr-tests:
+    permissions:
+      contents: read
     runs-on: self-hosted
     needs: [build, library-tests, docs, python-tests, python-integration-tests]
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: actions-rs/toolchain@v1
         with:
           toolchain: nightly-2024-07-18
@@ -483,6 +586,8 @@ jobs:
   #     ENABLE_ICICLE_GPU: true
   #   steps:
   #     - uses: actions/checkout@v4
+        # with:
+        #   persist-credentials: false
   #     - uses: actions-rs/toolchain@v1
   #       with:
   #         toolchain: nightly-2024-07-18
@@ -496,10 +601,14 @@ jobs:
   #       run: cargo nextest run --verbose tests_aggr::kzg_aggr_prove_and_verify_  --features icicle --test-threads 1 -- --include-ignored
 
   prove-and-verify-aggr-tests:
+    permissions:
+      contents: read
     runs-on: large-self-hosted
     needs: [build, library-tests, docs, python-tests, python-integration-tests]
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: actions-rs/toolchain@v1
         with:
           toolchain: nightly-2024-07-18
@@ -513,10 +622,14 @@ jobs:
         run: cargo nextest run --release --verbose tests_aggr::kzg_aggr_prove_and_verify_  --test-threads 4 -- --include-ignored
 
   prove-and-verify-aggr-evm-tests:
+    permissions:
+      contents: read
     runs-on: large-self-hosted
     needs: [build, library-tests, docs, python-tests, python-integration-tests]
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: actions-rs/toolchain@v1
         with:
           toolchain: nightly-2024-07-18
@@ -534,10 +647,14 @@ jobs:
         run: cargo nextest run  --release --verbose tests_evm::kzg_evm_aggr_prove_and_verify_::t --test-threads 4 -- --include-ignored
 
   examples:
+    permissions:
+      contents: read
     runs-on: ubuntu-latest-32-cores
     needs: [build, library-tests, docs]
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: actions-rs/toolchain@v1
         with:
           toolchain: nightly-2024-07-18
@@ -551,10 +668,14 @@ jobs:
         run: cargo nextest run --release tests_examples
 
   python-tests:
+    permissions:
+      contents: read
     runs-on: non-gpu
     needs: [build, library-tests, docs]
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: actions/setup-python@v4
         with:
           python-version: "3.12"
@@ -577,10 +698,14 @@ jobs:
         run: source .env/bin/activate; pip install pytest-asyncio; pytest -vv
 
   accuracy-measurement-tests:
-    runs-on: ubuntu-latest-32-cores
+    permissions:
+      contents: read
+    runs-on: non-gpu
     needs: [build, library-tests, docs, python-tests, python-integration-tests]
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: actions/setup-python@v4
         with:
           python-version: "3.12"
@@ -607,6 +732,8 @@ jobs:
         run: source .env/bin/activate; cargo nextest run --release --verbose tests::resources_accuracy_measurement_public_outputs_
 
   python-integration-tests:
+    permissions:
+      contents: read
     runs-on: large-self-hosted
     services:
       # Label used to access the service container
@@ -628,6 +755,8 @@ jobs:
           - 5432:5432
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - uses: actions/setup-python@v4
         with:
           python-version: "3.11"
@@ -677,9 +806,13 @@ jobs:
         # run: source .env/bin/activate; cargo nextest run py_tests::tests::reusable_
 
   ios-integration-tests:
+      permissions:
+        contents: read
       runs-on: macos-latest
       steps:
         - uses: actions/checkout@v4
+          with:
+            persist-credentials: false
         - uses: actions-rs/toolchain@v1
           with:
             toolchain: nightly-2024-07-18
@@ -693,11 +826,15 @@ jobs:
           run: CARGO_BUILD_TARGET=aarch64-apple-darwin RUSTUP_TOOLCHAIN=nightly-2024-07-18-aarch64-apple-darwin cargo test --test ios_integration_tests --features ios-bindings-test --no-default-features
 
   swift-package-tests:
+      permissions:
+        contents: read
       runs-on: macos-latest
       needs: [ios-integration-tests]
 
       steps:
         - uses: actions/checkout@v4
+          with:
+            persist-credentials: false
         - uses: actions-rs/toolchain@v1
           with:
             toolchain: nightly-2024-07-18
@@ -715,6 +852,15 @@ jobs:
             rm -rf ezkl-swift-package/Sources/EzklCoreBindings
             cp -r build/EzklCoreBindings ezkl-swift-package/Sources/
 
+        - name: Copy Test Files
+          run: |
+            rm -rf ezkl-swift-package/Tests/EzklAssets/
+            mkdir -p ezkl-swift-package/Tests/EzklAssets/
+            cp tests/assets/kzg ezkl-swift-package/Tests/EzklAssets/kzg.srs
+            cp tests/assets/input.json ezkl-swift-package/Tests/EzklAssets/input.json
+            cp tests/assets/model.compiled ezkl-swift-package/Tests/EzklAssets/network.ezkl
+            cp tests/assets/settings.json ezkl-swift-package/Tests/EzklAssets/settings.json
+
         - name: Set up Xcode environment
           run: |
             sudo xcode-select -s /Applications/Xcode.app/Contents/Developer

.github/workflows/static-analysis.yml

@@ -0,0 +1,33 @@
+name: Static Analysis
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  analyze:
+    permissions:
+      contents: read
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
+      - uses: actions-rs/toolchain@v1
+        with:
+          toolchain: nightly-2024-07-18
+          override: true
+          components: rustfmt, clippy
+
+      # Run Zizmor static analysis
+
+      - name: Install Zizmor
+        run: cargo install --locked zizmor
+
+      - name: Run Zizmor Analysis
+        run: zizmor .
+
+
+    

.github/workflows/swift-pm.yml

@@ -0,0 +1,134 @@
+name: Build and Publish EZKL iOS SPM package
+
+on:
+  push:
+    tags:
+      # Only support SemVer versioning tags
+      - 'v[0-9]+.[0-9]+.[0-9]+'
+      - '[0-9]+.[0-9]+.[0-9]+'
+
+jobs:
+  build-and-update:
+    permissions:
+      contents: read
+      packages: write
+    runs-on: macos-latest
+    env:
+      EZKL_SWIFT_PACKAGE_REPO: github.com/zkonduit/ezkl-swift-package.git
+      RELEASE_TAG: ${{ github.ref_name }}
+
+    steps:
+      - name: Checkout EZKL
+        uses: actions/checkout@v3
+        with: 
+          persist-credentials: false
+
+      - name: Extract TAG from github.ref_name
+        run: |
+          # github.ref_name is provided by GitHub Actions and contains the tag name directly.
+          TAG="${RELEASE_TAG}"
+          echo "Original TAG: $TAG"
+          # Remove leading 'v' if present to match the Swift Package Manager version format.
+          NEW_TAG=${TAG#v}
+          echo "Stripped TAG: $NEW_TAG"
+          echo "TAG=$NEW_TAG" >> $GITHUB_ENV
+
+      - name: Install Rust (nightly)
+        uses: actions-rs/toolchain@v1
+        with:
+          toolchain: nightly
+          override: true
+
+      - name: Build EzklCoreBindings
+        run: CONFIGURATION=release cargo run --bin ios_gen_bindings --features "ios-bindings uuid camino uniffi_bindgen" --no-default-features
+
+      - name: Clone ezkl-swift-package repository
+        run: |
+          git clone https://${{ env.EZKL_SWIFT_PACKAGE_REPO }}
+
+      - name: Copy EzklCoreBindings
+        run: |
+          rm -rf ezkl-swift-package/Sources/EzklCoreBindings
+          cp -r build/EzklCoreBindings ezkl-swift-package/Sources/
+
+      - name: Copy Test Files
+        run: |
+          rm -rf ezkl-swift-package/Tests/EzklAssets/
+          mkdir -p ezkl-swift-package/Tests/EzklAssets/
+          cp tests/assets/kzg ezkl-swift-package/Tests/EzklAssets/kzg.srs
+          cp tests/assets/input.json ezkl-swift-package/Tests/EzklAssets/input.json
+          cp tests/assets/model.compiled ezkl-swift-package/Tests/EzklAssets/network.ezkl
+          cp tests/assets/settings.json ezkl-swift-package/Tests/EzklAssets/settings.json
+
+      - name: Check for changes
+        id: check_changes
+        run: |
+          cd ezkl-swift-package
+          if git diff --quiet Sources/EzklCoreBindings Tests/EzklAssets; then
+            echo "no_changes=true" >> $GITHUB_OUTPUT
+          else
+            echo "no_changes=false" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Set up Xcode environment
+        if: steps.check_changes.outputs.no_changes == 'false'
+        run: |
+          sudo xcode-select -s /Applications/Xcode.app/Contents/Developer
+          sudo xcodebuild -license accept
+
+      - name: Run Package Tests
+        if: steps.check_changes.outputs.no_changes == 'false'
+        run: |
+          cd ezkl-swift-package
+          xcodebuild test \
+            -scheme EzklPackage \
+            -destination 'platform=iOS Simulator,name=iPhone 15 Pro,OS=17.5' \
+            -resultBundlePath ../testResults
+
+      - name: Run Example App Tests
+        if: steps.check_changes.outputs.no_changes == 'false'
+        run: |
+          cd ezkl-swift-package/Example
+          xcodebuild test \
+            -project Example.xcodeproj \
+            -scheme EzklApp \
+            -destination 'platform=iOS Simulator,name=iPhone 15 Pro,OS=17.5' \
+            -parallel-testing-enabled NO \
+            -resultBundlePath ../../exampleTestResults \
+            -skip-testing:EzklAppUITests/EzklAppUITests/testButtonClicksInOrder
+
+      - name: Setup Git
+        run: |
+          cd ezkl-swift-package
+          git config user.name "GitHub Action"
+          git config user.email "action@github.com"
+          git remote set-url origin https://zkonduit:${EZKL_SWIFT_PACKAGE_REPO_TOKEN}@${{ env.EZKL_SWIFT_PACKAGE_REPO }}
+        env:
+          EZKL_SWIFT_PACKAGE_REPO_TOKEN: ${{ secrets.EZKL_PORTER_TOKEN }}
+
+      - name: Commit and Push Changes
+        if: steps.check_changes.outputs.no_changes == 'false'
+        run: |
+          cd ezkl-swift-package
+          git add Sources/EzklCoreBindings Tests/EzklAssets
+          git commit -m "Automatically updated EzklCoreBindings for EZKL"
+          if ! git push origin; then
+            echo "::error::Failed to push changes to ${{ env.EZKL_SWIFT_PACKAGE_REPO }}. Please ensure that EZKL_PORTER_TOKEN has the correct permissions."
+            exit 1
+          fi
+
+      - name: Tag the latest commit
+        run: |
+          cd ezkl-swift-package
+          source $GITHUB_ENV
+          # Tag the latest commit on the current branch
+          if git rev-parse "$TAG" >/dev/null 2>&1; then
+            echo "Tag $TAG already exists locally. Skipping tag creation."
+          else
+            git tag "$TAG"
+          fi
+
+          if ! git push origin "$TAG"; then
+            echo "::error::Failed to push tag '$TAG' to ${{ env.EZKL_SWIFT_PACKAGE_REPO }}. Please ensure EZKL_PORTER_TOKEN has correct permissions."
+            exit 1
+          fi

.github/workflows/tagging.yml

@@ -12,6 +12,8 @@ jobs:
 
     steps:
       - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
       - name: Bump version and push tag
         id: tag_version
         uses: mathieudutour/github-tag-action@v6.2

.github/workflows/update-ios-package.yml

@@ -1,85 +0,0 @@
-name: Build and Publish EZKL iOS SPM package
-
-on:
-  workflow_dispatch:
-    inputs:
-      tag:
-        description: "The tag to release"
-        required: true
-  push:
-    tags:
-      - "*"
-
-jobs:
-  build-and-update:
-    runs-on: macos-latest
-
-    steps:
-      - name: Checkout EZKL
-        uses: actions/checkout@v3
-
-      - name: Install Rust
-        uses: actions-rs/toolchain@v1
-        with:
-          toolchain: nightly
-          override: true
-
-      - name: Build EzklCoreBindings
-        run: CONFIGURATION=release cargo run --bin ios_gen_bindings --features "ios-bindings uuid camino uniffi_bindgen" --no-default-features
-
-      - name: Clone ezkl-swift-package repository
-        run: |
-          git clone https://github.com/zkonduit/ezkl-swift-package.git
-
-      - name: Copy EzklCoreBindings
-        run: |
-          rm -rf ezkl-swift-package/Sources/EzklCoreBindings
-          cp -r build/EzklCoreBindings ezkl-swift-package/Sources/
-
-      - name: Copy Test Files
-        run: |
-          rm -rf ezkl-swift-package/Tests/EzklAssets/*
-          
-          cp tests/assets/kzg ezkl-swift-package/Tests/EzklAssets/kzg.srs
-          cp tests/assets/input.json ezkl-swift-package/Tests/EzklAssets/input.json
-          cp tests/assets/model.compiled ezkl-swift-package/Tests/EzklAssets/network.ezkl
-          cp tests/assets/settings.json ezkl-swift-package/Tests/EzklAssets/settings.json
-
-      - name: Set up Xcode environment
-        run: |
-          sudo xcode-select -s /Applications/Xcode.app/Contents/Developer
-          sudo xcodebuild -license accept
-
-      - name: Run Package Tests
-        run: |
-          cd ezkl-swift-package
-          xcodebuild test \
-            -scheme EzklPackage \
-            -destination 'platform=iOS Simulator,name=iPhone 15 Pro,OS=17.5' \
-            -resultBundlePath ../testResults
-
-      - name: Run Example App Tests
-        run: |
-          cd ezkl-swift-package/Example
-          xcodebuild test \
-            -project Example.xcodeproj \
-            -scheme EzklApp \
-            -destination 'platform=iOS Simulator,name=iPhone 15 Pro,OS=17.5' \
-            -parallel-testing-enabled NO \
-            -resultBundlePath ../../exampleTestResults \
-            -skip-testing:EzklAppUITests/EzklAppUITests/testButtonClicksInOrder
-
-      - name: Commit and Push Changes to feat/ezkl-direct-integration
-        run: |
-          cd ezkl-swift-package
-          git config user.name "GitHub Action"
-          git config user.email "action@github.com"
-          git add Sources/EzklCoreBindings
-          git add Tests/EzklAssets
-          git commit -m "Automatically updated EzklCoreBindings for EZKL"
-          git tag ${{ github.event.inputs.tag }}
-          git remote set-url origin https://zkonduit:${EZKL_PORTER_TOKEN}@github.com/zkonduit/ezkl-swift-package.git
-          git push origin
-          git push origin tag ${{ github.event.inputs.tag }}
-        env:
-          EZKL_PORTER_TOKEN: ${{ secrets.EZKL_PORTER_TOKEN }}

Cargo.lock

@@ -1835,6 +1835,16 @@ dependencies = [
  "syn 2.0.90",
 ]
 
+[[package]]
+name = "env_filter"
+version = "0.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "186e05a59d4c50738528153b83b0b0194d3a29507dfec16eccd4b342903397d0"
+dependencies = [
+ "log",
+ "regex",
+]
+
 [[package]]
 name = "env_logger"
 version = "0.10.2"
@@ -1848,6 +1858,19 @@ dependencies = [
  "termcolor",
 ]
 
+[[package]]
+name = "env_logger"
+version = "0.11.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dcaee3d8e3cfc3fd92428d477bc97fc29ec8716d180c0d74c643bb26166660e0"
+dependencies = [
+ "anstream",
+ "anstyle",
+ "env_filter",
+ "humantime",
+ "log",
+]
+
 [[package]]
 name = "equivalent"
 version = "1.0.1"
@@ -1923,7 +1946,7 @@ dependencies = [
  "console_error_panic_hook",
  "criterion 0.5.1",
  "ecc",
- "env_logger",
+ "env_logger 0.10.2",
  "ethabi",
  "foundry-compilers",
  "gag",
@@ -1931,7 +1954,7 @@ dependencies = [
  "halo2_gadgets",
  "halo2_proofs",
  "halo2_solidity_verifier",
- "halo2curves 0.7.0",
+ "halo2curves 0.7.0 (git+https://github.com/privacy-scaling-explorations/halo2curves?rev=b753a832e92d5c86c5c997327a9cf9de86a18851)",
  "hex",
  "indicatif",
  "instant",
@@ -1939,7 +1962,6 @@ dependencies = [
  "lazy_static",
  "log",
  "maybe-rayon",
- "metal",
  "mimalloc",
  "mnist",
  "num",
@@ -2377,7 +2399,7 @@ dependencies = [
 [[package]]
 name = "halo2_gadgets"
 version = "0.2.0"
-source = "git+https://github.com/zkonduit/halo2#0654e92bdf725fd44d849bfef3643870a8c7d50b"
+source = "git+https://github.com/zkonduit/halo2#d7ecad83c7439fa1cb450ee4a89c2d0b45604ceb"
 dependencies = [
  "arrayvec 0.7.4",
  "bitvec",
@@ -2394,14 +2416,14 @@ dependencies = [
 [[package]]
 name = "halo2_proofs"
 version = "0.3.0"
-source = "git+https://github.com/zkonduit/halo2#0654e92bdf725fd44d849bfef3643870a8c7d50b#0654e92bdf725fd44d849bfef3643870a8c7d50b"
+source = "git+https://github.com/zkonduit/halo2#bf9d0057a82443be48c4779bbe14961c18fb5996#bf9d0057a82443be48c4779bbe14961c18fb5996"
 dependencies = [
  "bincode",
  "blake2b_simd",
- "env_logger",
+ "env_logger 0.10.2",
  "ff",
  "group",
- "halo2curves 0.7.0",
+ "halo2curves 0.7.0 (git+https://github.com/privacy-scaling-explorations/halo2curves?rev=b753a832e92d5c86c5c997327a9cf9de86a18851)",
  "icicle-bn254",
  "icicle-core",
  "icicle-cuda-runtime",
@@ -2409,6 +2431,7 @@ dependencies = [
  "lazy_static",
  "log",
  "maybe-rayon",
+ "mopro-msm",
  "rand_chacha",
  "rand_core 0.6.4",
  "rustc-hash 2.0.0",
@@ -2497,13 +2520,14 @@ dependencies = [
 [[package]]
 name = "halo2curves"
 version = "0.7.0"
-source = "git+https://github.com/privacy-scaling-explorations/halo2curves?rev=b753a832e92d5c86c5c997327a9cf9de86a18851#b753a832e92d5c86c5c997327a9cf9de86a18851"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d380afeef3f1d4d3245b76895172018cfb087d9976a7cabcd5597775b2933e07"
 dependencies = [
  "blake2",
  "digest 0.10.7",
  "ff",
  "group",
- "halo2derive",
+ "halo2derive 0.1.0 (registry+https://github.com/rust-lang/crates.io-index)",
  "hex",
  "lazy_static",
  "num-bigint",
@@ -2523,6 +2547,49 @@ dependencies = [
  "unroll",
 ]
 
+[[package]]
+name = "halo2curves"
+version = "0.7.0"
+source = "git+https://github.com/privacy-scaling-explorations/halo2curves?rev=b753a832e92d5c86c5c997327a9cf9de86a18851#b753a832e92d5c86c5c997327a9cf9de86a18851"
+dependencies = [
+ "blake2",
+ "digest 0.10.7",
+ "ff",
+ "group",
+ "halo2derive 0.1.0 (git+https://github.com/privacy-scaling-explorations/halo2curves?rev=b753a832e92d5c86c5c997327a9cf9de86a18851)",
+ "hex",
+ "lazy_static",
+ "num-bigint",
+ "num-integer",
+ "num-traits",
+ "pairing",
+ "pasta_curves",
+ "paste",
+ "rand 0.8.5",
+ "rand_core 0.6.4",
+ "rayon",
+ "serde",
+ "serde_arrays",
+ "sha2",
+ "static_assertions",
+ "subtle",
+ "unroll",
+]
+
+[[package]]
+name = "halo2derive"
+version = "0.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bdb99e7492b4f5ff469d238db464131b86c2eaac814a78715acba369f64d2c76"
+dependencies = [
+ "num-bigint",
+ "num-integer",
+ "num-traits",
+ "proc-macro2",
+ "quote",
+ "syn 1.0.109",
+]
+
 [[package]]
 name = "halo2derive"
 version = "0.1.0"
@@ -3283,7 +3350,8 @@ dependencies = [
 [[package]]
 name = "metal"
 version = "0.29.0"
-source = "git+https://github.com/gfx-rs/metal-rs#0e1918b34689c4b8cd13a43372f9898680547ee9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7ecfd3296f8c56b7c1f6fbac3c71cefa9d78ce009850c45000015f206dc7fa21"
 dependencies = [
  "bitflags 2.5.0",
  "block",
@@ -3354,6 +3422,28 @@ dependencies = [
  "byteorder",
 ]
 
+[[package]]
+name = "mopro-msm"
+version = "0.1.0"
+source = "git+https://github.com/zkonduit/metal-msm-gpu-acceleration.git#be5f647b1a6c1a6ea9024390744a2b4d87f5d002"
+dependencies = [
+ "bincode",
+ "env_logger 0.11.6",
+ "halo2curves 0.7.0 (registry+https://github.com/rust-lang/crates.io-index)",
+ "instant",
+ "itertools 0.13.0",
+ "lazy_static",
+ "log",
+ "metal",
+ "objc",
+ "once_cell",
+ "rand 0.8.5",
+ "rayon",
+ "serde",
+ "thiserror",
+ "walkdir",
+]
+
 [[package]]
 name = "native-tls"
 version = "0.2.11"

Cargo.toml

@@ -91,7 +91,6 @@ pyo3-async-runtimes = { git = "https://github.com/PyO3/pyo3-async-runtimes", ver
 pyo3-log = { version = "0.12.0", default-features = false, optional = true }
 tract-onnx = { git = "https://github.com/sonos/tract/", rev = "37132e0397d0a73e5bd3a8615d932dabe44f6736", default-features = false, optional = true }
 tabled = { version = "0.12.0", optional = true }
-metal = { git = "https://github.com/gfx-rs/metal-rs", optional = true }
 objc = { version = "0.2.4", optional = true }
 mimalloc = { version = "0.1", optional = true }
 pyo3-stub-gen = { version = "0.6.0", optional = true }
@@ -147,6 +146,10 @@ shellexpand = "3.1.0"
 runner = 'wasm-bindgen-test-runner'
 
 
+[[bench]]
+name = "zero_finder"
+harness = false
+
 [[bench]]
 name = "accum_dot"
 harness = false
@@ -273,10 +276,14 @@ icicle = ["halo2_proofs/icicle_gpu"]
 empty-cmd = []
 no-banner = []
 no-update = []
-
+macos-metal = ["halo2_proofs/macos"]
+ios-metal = ["halo2_proofs/ios"]
 
 [patch.'https://github.com/zkonduit/halo2']
-halo2_proofs = { git = "https://github.com/zkonduit/halo2#0654e92bdf725fd44d849bfef3643870a8c7d50b", package = "halo2_proofs" }
+halo2_proofs = { git = "https://github.com/zkonduit/halo2#bf9d0057a82443be48c4779bbe14961c18fb5996", package = "halo2_proofs" }
+
+[patch.'https://github.com/zkonduit/halo2#0654e92bdf725fd44d849bfef3643870a8c7d50b']
+halo2_proofs = { git = "https://github.com/zkonduit/halo2#bf9d0057a82443be48c4779bbe14961c18fb5996", package = "halo2_proofs" }
 
 [patch.crates-io]
 uniffi_testing = { git = "https://github.com/ElusAegis/uniffi-rs", branch = "feat/testing-feature-build-fix" }

benches/zero_finder.rs

@@ -0,0 +1,116 @@
+use std::thread;
+
+use criterion::{black_box, criterion_group, criterion_main, Criterion};
+use halo2curves::{bn256::Fr as F, ff::Field};
+use maybe_rayon::{
+    iter::{IndexedParallelIterator, IntoParallelRefIterator, ParallelIterator},
+    slice::ParallelSlice,
+};
+use rand::Rng;
+
+// Assuming these are your types
+#[derive(Clone)]
+enum ValType {
+    Constant(F),
+    AssignedConstant(usize, F),
+    Other,
+}
+
+// Helper to generate test data
+fn generate_test_data(size: usize, zero_probability: f64) -> Vec<ValType> {
+    let mut rng = rand::thread_rng();
+    (0..size)
+        .map(|_i| {
+            if rng.gen::<f64>() < zero_probability {
+                ValType::Constant(F::ZERO)
+            } else {
+                ValType::Constant(F::ONE) // Or some other non-zero value
+            }
+        })
+        .collect()
+}
+
+fn bench_zero_finding(c: &mut Criterion) {
+    let sizes = [
+        1_000,         // 1K
+        10_000,        // 10K
+        100_000,       // 100K
+        256 * 256 * 2, // Our specific case
+        1_000_000,     // 1M
+        10_000_000,    // 10M
+    ];
+
+    let zero_probability = 0.1; // 10% zeros
+
+    let mut group = c.benchmark_group("zero_finding");
+    group.sample_size(10); // Adjust based on your needs
+
+    for &size in &sizes {
+        let data = generate_test_data(size, zero_probability);
+
+        // Benchmark sequential version
+        group.bench_function(format!("sequential_{}", size), |b| {
+            b.iter(|| {
+                let result = data
+                    .iter()
+                    .enumerate()
+                    .filter_map(|(i, e)| match e {
+                        ValType::Constant(r) | ValType::AssignedConstant(_, r) => {
+                            (*r == F::ZERO).then_some(i)
+                        }
+                        _ => None,
+                    })
+                    .collect::<Vec<_>>();
+                black_box(result)
+            })
+        });
+
+        // Benchmark parallel version
+        group.bench_function(format!("parallel_{}", size), |b| {
+            b.iter(|| {
+                let result = data
+                    .par_iter()
+                    .enumerate()
+                    .filter_map(|(i, e)| match e {
+                        ValType::Constant(r) | ValType::AssignedConstant(_, r) => {
+                            (*r == F::ZERO).then_some(i)
+                        }
+                        _ => None,
+                    })
+                    .collect::<Vec<_>>();
+                black_box(result)
+            })
+        });
+
+        // Benchmark chunked parallel version
+        group.bench_function(format!("chunked_parallel_{}", size), |b| {
+            b.iter(|| {
+                let num_cores = thread::available_parallelism()
+                    .map(|n| n.get())
+                    .unwrap_or(1);
+                let chunk_size = (size / num_cores).max(100);
+
+                let result = data
+                    .par_chunks(chunk_size)
+                    .enumerate()
+                    .flat_map(|(chunk_idx, chunk)| {
+                        chunk
+                            .par_iter() // Make sure we use par_iter() here
+                            .enumerate()
+                            .filter_map(move |(i, e)| match e {
+                                ValType::Constant(r) | ValType::AssignedConstant(_, r) => {
+                                    (*r == F::ZERO).then_some(chunk_idx * chunk_size + i)
+                                }
+                                _ => None,
+                            })
+                    })
+                    .collect::<Vec<_>>();
+                black_box(result)
+            })
+        });
+    }
+    group.finish();
+}
+
+criterion_group!(benches, bench_zero_finding);
+criterion_main!(benches);

examples/notebooks/felt_conversion_test.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -54,7 +54,7 @@
     "    gip_run_args.param_scale = 19\n",
     "    gip_run_args.logrows = 8\n",
     "    run_args = ezkl.gen_settings(py_run_args=gip_run_args)\n",
-    "    ezkl.get_srs(commitment=ezkl.PyCommitments.KZG)\n",
+    "    await ezkl.get_srs(commitment=ezkl.PyCommitments.KZG)\n",
     "    ezkl.compile_circuit()\n",
     "    res = await ezkl.gen_witness()\n",
     "    print(res)\n",

examples/notebooks/linear_regression.ipynb

@@ -1,279 +1,284 @@
 {
-    "cells": [
-        {
-            "cell_type": "markdown",
-            "id": "cf69bb3f-94e6-4dba-92cd-ce08df117d67",
-            "metadata": {},
-            "source": [
-                "## Linear Regression\n",
-                "\n",
-                "\n",
-                "Sklearn based models are slightly finicky to get into a suitable onnx format. \n",
-                "This notebook showcases how to do so using the `hummingbird-ml` python package ! "
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": null,
-            "id": "95613ee9",
-            "metadata": {},
-            "outputs": [],
-            "source": [
-                "# check if notebook is in colab\n",
-                "try:\n",
-                "    # install ezkl\n",
-                "    import google.colab\n",
-                "    import subprocess\n",
-                "    import sys\n",
-                "    subprocess.check_call([sys.executable, \"-m\", \"pip\", \"install\", \"ezkl\"])\n",
-                "    subprocess.check_call([sys.executable, \"-m\", \"pip\", \"install\", \"onnx\"])\n",
-                "    subprocess.check_call([sys.executable, \"-m\", \"pip\", \"install\", \"hummingbird-ml\"])\n",
-                "\n",
-                "# rely on local installation of ezkl if the notebook is not in colab\n",
-                "except:\n",
-                "    pass\n",
-                "\n",
-                "import os\n",
-                "import torch\n",
-                "import ezkl\n",
-                "import json\n",
-                "from hummingbird.ml import convert\n",
-                "\n",
-                "\n",
-                "# here we create and (potentially train a model)\n",
-                "\n",
-                "# make sure you have the dependencies required here already installed\n",
-                "import numpy as np\n",
-                "from sklearn.linear_model import LinearRegression\n",
-                "X = np.array([[1, 1], [1, 2], [2, 2], [2, 3]])\n",
-                "# y = 1 * x_0 + 2 * x_1 + 3\n",
-                "y = np.dot(X, np.array([1, 2])) + 3\n",
-                "reg = LinearRegression().fit(X, y)\n",
-                "reg.score(X, y)\n",
-                "\n",
-                "circuit = convert(reg, \"torch\", X[:1]).model\n",
-                "\n",
-                "\n",
-                "\n"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": null,
-            "id": "b37637c4",
-            "metadata": {},
-            "outputs": [],
-            "source": [
-                "model_path = os.path.join('network.onnx')\n",
-                "compiled_model_path = os.path.join('network.compiled')\n",
-                "pk_path = os.path.join('test.pk')\n",
-                "vk_path = os.path.join('test.vk')\n",
-                "settings_path = os.path.join('settings.json')\n",
-                "\n",
-                "witness_path = os.path.join('witness.json')\n",
-                "data_path = os.path.join('input.json')"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": null,
-            "id": "82db373a",
-            "metadata": {},
-            "outputs": [],
-            "source": [
-                "\n",
-                "\n",
-                "# export to onnx format\n",
-                "# !!!!!!!!!!!!!!!!! This will flash a warning but it is fine !!!!!!!!!!!!!!!!!!!!!\n",
-                "\n",
-                "# Input to the model\n",
-                "shape = X.shape[1:]\n",
-                "x = torch.rand(1, *shape, requires_grad=True)\n",
-                "torch_out = circuit(x)\n",
-                "# Export the model\n",
-                "torch.onnx.export(circuit,               # model being run\n",
-                "                  # model input (or a tuple for multiple inputs)\n",
-                "                  x,\n",
-                "                  # where to save the model (can be a file or file-like object)\n",
-                "                  \"network.onnx\",\n",
-                "                  export_params=True,        # store the trained parameter weights inside the model file\n",
-                "                  opset_version=10,          # the ONNX version to export the model to\n",
-                "                  do_constant_folding=True,  # whether to execute constant folding for optimization\n",
-                "                  input_names=['input'],   # the model's input names\n",
-                "                  output_names=['output'],  # the model's output names\n",
-                "                  dynamic_axes={'input': {0: 'batch_size'},    # variable length axes\n",
-                "                                'output': {0: 'batch_size'}})\n",
-                "\n",
-                "d = ((x).detach().numpy()).reshape([-1]).tolist()\n",
-                "\n",
-                "data = dict(input_shapes=[shape],\n",
-                "            input_data=[d],\n",
-                "            output_data=[((o).detach().numpy()).reshape([-1]).tolist() for o in torch_out])\n",
-                "\n",
-                "# Serialize data into file:\n",
-                "json.dump(data, open(\"input.json\", 'w'))\n"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": null,
-            "id": "d5e374a2",
-            "metadata": {},
-            "outputs": [],
-            "source": [
-                "!RUST_LOG=trace\n",
-                "# TODO: Dictionary outputs\n",
-                "res = ezkl.gen_settings(model_path, settings_path)\n",
-                "assert res == True\n"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": null,
-            "metadata": {},
-            "outputs": [],
-            "source": [
-                "cal_path = os.path.join(\"calibration.json\")\n",
-                "\n",
-                "data_array = (torch.randn(20, *shape).detach().numpy()).reshape([-1]).tolist()\n",
-                "\n",
-                "data = dict(input_data = [data_array])\n",
-                "\n",
-                "# Serialize data into file:\n",
-                "json.dump(data, open(cal_path, 'w'))\n",
-                "\n",
-                "res = await ezkl.calibrate_settings(data_path, model_path, settings_path, \"resources\")\n",
-                "assert res == True\n"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": null,
-            "id": "3aa4f090",
-            "metadata": {},
-            "outputs": [],
-            "source": [
-                "res = ezkl.compile_circuit(model_path, compiled_model_path, settings_path)\n",
-                "assert res == True"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": null,
-            "id": "8b74dcee",
-            "metadata": {},
-            "outputs": [],
-            "source": [
-                "# srs path\n",
-                "res = await ezkl.get_srs( settings_path)"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": null,
-            "id": "18c8b7c7",
-            "metadata": {},
-            "outputs": [],
-            "source": [
-                "# now generate the witness file \n",
-                "\n",
-                "res = await ezkl.gen_witness(data_path, compiled_model_path, witness_path)\n",
-                "assert os.path.isfile(witness_path)"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": null,
-            "id": "b1c561a8",
-            "metadata": {},
-            "outputs": [],
-            "source": [
-                "\n",
-                "# HERE WE SETUP THE CIRCUIT PARAMS\n",
-                "# WE GOT KEYS\n",
-                "# WE GOT CIRCUIT PARAMETERS\n",
-                "# EVERYTHING ANYONE HAS EVER NEEDED FOR ZK\n",
-                "\n",
-                "\n",
-                "\n",
-                "res = ezkl.setup(\n",
-                "        compiled_model_path,\n",
-                "        vk_path,\n",
-                "        pk_path,\n",
-                "        \n",
-                "    )\n",
-                "\n",
-                "assert res == True\n",
-                "assert os.path.isfile(vk_path)\n",
-                "assert os.path.isfile(pk_path)\n",
-                "assert os.path.isfile(settings_path)"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": null,
-            "id": "c384cbc8",
-            "metadata": {},
-            "outputs": [],
-            "source": [
-                "# GENERATE A PROOF\n",
-                "\n",
-                "\n",
-                "proof_path = os.path.join('test.pf')\n",
-                "\n",
-                "res = ezkl.prove(\n",
-                "        witness_path,\n",
-                "        compiled_model_path,\n",
-                "        pk_path,\n",
-                "        proof_path,\n",
-                "        \n",
-                "        \"single\",\n",
-                "    )\n",
-                "\n",
-                "print(res)\n",
-                "assert os.path.isfile(proof_path)"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": null,
-            "id": "76f00d41",
-            "metadata": {},
-            "outputs": [],
-            "source": [
-                "# VERIFY IT\n",
-                "\n",
-                "res = ezkl.verify(\n",
-                "        proof_path,\n",
-                "        settings_path,\n",
-                "        vk_path,\n",
-                "        \n",
-                "    )\n",
-                "\n",
-                "assert res == True\n",
-                "print(\"verified\")"
-            ]
-        }
-    ],
-    "metadata": {
-        "kernelspec": {
-            "display_name": "Python 3 (ipykernel)",
-            "language": "python",
-            "name": "python3"
-        },
-        "language_info": {
-            "codemirror_mode": {
-                "name": "ipython",
-                "version": 3
-            },
-            "file_extension": ".py",
-            "mimetype": "text/x-python",
-            "name": "python",
-            "nbconvert_exporter": "python",
-            "pygments_lexer": "ipython3",
-            "version": "3.9.15"
-        }
-    },
-    "nbformat": 4,
-    "nbformat_minor": 5
-}
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "cf69bb3f-94e6-4dba-92cd-ce08df117d67",
+   "metadata": {},
+   "source": [
+    "## Linear Regression\n",
+    "\n",
+    "\n",
+    "Sklearn based models are slightly finicky to get into a suitable onnx format. \n",
+    "This notebook showcases how to do so using the `hummingbird-ml` python package ! "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "95613ee9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# check if notebook is in colab\n",
+    "try:\n",
+    "    # install ezkl\n",
+    "    import google.colab\n",
+    "    import subprocess\n",
+    "    import sys\n",
+    "    subprocess.check_call([sys.executable, \"-m\", \"pip\", \"install\", \"ezkl\"])\n",
+    "    subprocess.check_call([sys.executable, \"-m\", \"pip\", \"install\", \"onnx\"])\n",
+    "    subprocess.check_call([sys.executable, \"-m\", \"pip\", \"install\", \"hummingbird-ml\"])\n",
+    "\n",
+    "# rely on local installation of ezkl if the notebook is not in colab\n",
+    "except:\n",
+    "    pass\n",
+    "\n",
+    "import os\n",
+    "import torch\n",
+    "import ezkl\n",
+    "import json\n",
+    "from hummingbird.ml import convert\n",
+    "\n",
+    "\n",
+    "# here we create and (potentially train a model)\n",
+    "\n",
+    "# make sure you have the dependencies required here already installed\n",
+    "import numpy as np\n",
+    "from sklearn.linear_model import LinearRegression\n",
+    "X = np.array([[1, 1], [1, 2], [2, 2], [2, 3]])\n",
+    "# y = 1 * x_0 + 2 * x_1 + 3\n",
+    "y = np.dot(X, np.array([1, 2])) + 3\n",
+    "reg = LinearRegression().fit(X, y)\n",
+    "reg.score(X, y)\n",
+    "\n",
+    "circuit = convert(reg, \"torch\", X[:1]).model\n",
+    "\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b37637c4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model_path = os.path.join('network.onnx')\n",
+    "compiled_model_path = os.path.join('network.compiled')\n",
+    "pk_path = os.path.join('test.pk')\n",
+    "vk_path = os.path.join('test.vk')\n",
+    "settings_path = os.path.join('settings.json')\n",
+    "\n",
+    "witness_path = os.path.join('witness.json')\n",
+    "data_path = os.path.join('input.json')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "82db373a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "\n",
+    "# export to onnx format\n",
+    "# !!!!!!!!!!!!!!!!! This will flash a warning but it is fine !!!!!!!!!!!!!!!!!!!!!\n",
+    "\n",
+    "# Input to the model\n",
+    "shape = X.shape[1:]\n",
+    "x = torch.rand(1, *shape, requires_grad=True)\n",
+    "torch_out = circuit(x)\n",
+    "# Export the model\n",
+    "torch.onnx.export(circuit,               # model being run\n",
+    "                  # model input (or a tuple for multiple inputs)\n",
+    "                  x,\n",
+    "                  # where to save the model (can be a file or file-like object)\n",
+    "                  \"network.onnx\",\n",
+    "                  export_params=True,        # store the trained parameter weights inside the model file\n",
+    "                  opset_version=10,          # the ONNX version to export the model to\n",
+    "                  do_constant_folding=True,  # whether to execute constant folding for optimization\n",
+    "                  input_names=['input'],   # the model's input names\n",
+    "                  output_names=['output'],  # the model's output names\n",
+    "                  dynamic_axes={'input': {0: 'batch_size'},    # variable length axes\n",
+    "                                'output': {0: 'batch_size'}})\n",
+    "\n",
+    "d = ((x).detach().numpy()).reshape([-1]).tolist()\n",
+    "\n",
+    "data = dict(input_shapes=[shape],\n",
+    "            input_data=[d],\n",
+    "            output_data=[((o).detach().numpy()).reshape([-1]).tolist() for o in torch_out])\n",
+    "\n",
+    "# Serialize data into file:\n",
+    "json.dump(data, open(\"input.json\", 'w'))\n",
+    "\n",
+    "\n",
+    "# note that you can also call the following function to generate random data for the model\n",
+    "# it is functionally equivalent to the code above\n",
+    "ezkl.gen_random_data()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d5e374a2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!RUST_LOG=trace\n",
+    "# TODO: Dictionary outputs\n",
+    "res = ezkl.gen_settings(model_path, settings_path)\n",
+    "assert res == True\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cal_path = os.path.join(\"calibration.json\")\n",
+    "\n",
+    "data_array = (torch.randn(20, *shape).detach().numpy()).reshape([-1]).tolist()\n",
+    "\n",
+    "data = dict(input_data = [data_array])\n",
+    "\n",
+    "# Serialize data into file:\n",
+    "json.dump(data, open(cal_path, 'w'))\n",
+    "\n",
+    "res = await ezkl.calibrate_settings(data_path, model_path, settings_path, \"resources\")\n",
+    "assert res == True\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3aa4f090",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "res = ezkl.compile_circuit(model_path, compiled_model_path, settings_path)\n",
+    "assert res == True"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8b74dcee",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# srs path\n",
+    "res = await ezkl.get_srs( settings_path)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "18c8b7c7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# now generate the witness file \n",
+    "\n",
+    "res = await ezkl.gen_witness(data_path, compiled_model_path, witness_path)\n",
+    "assert os.path.isfile(witness_path)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b1c561a8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "# HERE WE SETUP THE CIRCUIT PARAMS\n",
+    "# WE GOT KEYS\n",
+    "# WE GOT CIRCUIT PARAMETERS\n",
+    "# EVERYTHING ANYONE HAS EVER NEEDED FOR ZK\n",
+    "\n",
+    "\n",
+    "\n",
+    "res = ezkl.setup(\n",
+    "        compiled_model_path,\n",
+    "        vk_path,\n",
+    "        pk_path,\n",
+    "        \n",
+    "    )\n",
+    "\n",
+    "assert res == True\n",
+    "assert os.path.isfile(vk_path)\n",
+    "assert os.path.isfile(pk_path)\n",
+    "assert os.path.isfile(settings_path)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c384cbc8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# GENERATE A PROOF\n",
+    "\n",
+    "\n",
+    "proof_path = os.path.join('test.pf')\n",
+    "\n",
+    "res = ezkl.prove(\n",
+    "        witness_path,\n",
+    "        compiled_model_path,\n",
+    "        pk_path,\n",
+    "        proof_path,\n",
+    "        \n",
+    "        \"single\",\n",
+    "    )\n",
+    "\n",
+    "print(res)\n",
+    "assert os.path.isfile(proof_path)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "76f00d41",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# VERIFY IT\n",
+    "\n",
+    "res = ezkl.verify(\n",
+    "        proof_path,\n",
+    "        settings_path,\n",
+    "        vk_path,\n",
+    "        \n",
+    "    )\n",
+    "\n",
+    "assert res == True\n",
+    "print(\"verified\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.15"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

examples/notebooks/mean_postgres.ipynb

@@ -1,456 +1,459 @@
 {
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "## Mean of ERC20 transfer amounts\n",
-        "\n",
-        "This notebook shows how to calculate the mean of ERC20 transfer amounts, pulling data in from a Postgres database. First we install and get the necessary libraries running. \n",
-        "The first of which is [shovel](https://indexsupply.com/shovel/docs/#getting-started), which is a library that allows us to pull data from the Ethereum blockchain into a Postgres database.\n",
-        "\n",
-        "Make sure you install postgres if needed https://indexsupply.com/shovel/docs/#getting-started. \n",
-        "\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "import getpass\n",
-        "import json\n",
-        "import time\n",
-        "import subprocess\n",
-        "\n",
-        "# swap out for the relevant linux/amd64, darwin/arm64, darwin/amd64, windows/amd64\n",
-        "os.system(\"curl -LO https://indexsupply.net/bin/1.0/linux/amd64/shovel\")\n",
-        "os.system(\"chmod +x shovel\")\n",
-        "\n",
-        "\n",
-        "os.environ[\"PG_URL\"] = \"postgres://\" + getpass.getuser() + \":@localhost:5432/shovel\"\n",
-        "\n",
-        "# create a config.json file with the following contents\n",
-        "config = {\n",
-        "  \"pg_url\": \"$PG_URL\",\n",
-        "  \"eth_sources\": [\n",
-        "    {\"name\": \"mainnet\", \"chain_id\": 1, \"url\": \"https://ethereum-rpc.publicnode.com\"},\n",
-        "    {\"name\": \"base\", \"chain_id\": 8453, \"url\": \"https://base-rpc.publicnode.com\"}\n",
-        "  ],\n",
-        "  \"integrations\": [{\n",
-        "    \"name\": \"usdc_transfer\",\n",
-        "    \"enabled\": True,\n",
-        "    \"sources\": [{\"name\": \"mainnet\"}, {\"name\": \"base\"}],\n",
-        "    \"table\": {\n",
-        "      \"name\": \"usdc\",\n",
-        "      \"columns\": [\n",
-        "        {\"name\": \"log_addr\",  \"type\": \"bytea\"},\n",
-        "        {\"name\": \"block_num\", \"type\": \"numeric\"},\n",
-        "        {\"name\": \"f\",         \"type\": \"bytea\"},\n",
-        "        {\"name\": \"t\",         \"type\": \"bytea\"},\n",
-        "        {\"name\": \"v\",         \"type\": \"numeric\"}\n",
-        "      ]\n",
-        "    },\n",
-        "    \"block\": [\n",
-        "      {\"name\": \"block_num\", \"column\": \"block_num\"},\n",
-        "      {\n",
-        "        \"name\": \"log_addr\",\n",
-        "        \"column\": \"log_addr\",\n",
-        "        \"filter_op\": \"contains\",\n",
-        "        \"filter_arg\": [\n",
-        "          \"a0b86991c6218b36c1d19d4a2e9eb0ce3606eb48\",\n",
-        "          \"833589fCD6eDb6E08f4c7C32D4f71b54bdA02913\"\n",
-        "        ]\n",
-        "      }\n",
-        "    ],\n",
-        "    \"event\": {\n",
-        "      \"name\": \"Transfer\",\n",
-        "      \"type\": \"event\",\n",
-        "      \"anonymous\": False,\n",
-        "      \"inputs\": [\n",
-        "        {\"indexed\": True,  \"name\": \"from\",  \"type\": \"address\", \"column\": \"f\"},\n",
-        "        {\"indexed\": True,  \"name\": \"to\",    \"type\": \"address\", \"column\": \"t\"},\n",
-        "        {\"indexed\": False, \"name\": \"value\", \"type\": \"uint256\", \"column\": \"v\"}\n",
-        "      ]\n",
-        "    }\n",
-        "  }]\n",
-        "}\n",
-        "\n",
-        "# write the config to a file\n",
-        "with open(\"config.json\", \"w\") as f:\n",
-        "  f.write(json.dumps(config))\n",
-        "\n",
-        "\n",
-        "# print the two env variables\n",
-        "os.system(\"echo $PG_URL\")\n",
-        "\n",
-        "os.system(\"createdb -h localhost -p 5432 shovel\")\n",
-        "\n",
-        "os.system(\"echo shovel is now installed. starting:\")\n",
-        "\n",
-        "command = [\"./shovel\", \"-config\", \"config.json\"]\n",
-        "proc = subprocess.Popen(command)\n",
-        "\n",
-        "os.system(\"echo shovel started.\")\n",
-        "\n",
-        "time.sleep(10)\n",
-        "\n",
-        "# after we've fetched some data -- kill the process\n",
-        "proc.terminate()\n",
-        "\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "2wIAHwqH2_mo"
-      },
-      "source": [
-        "**Import Dependencies**"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "9Byiv2Nc2MsK"
-      },
-      "outputs": [],
-      "source": [
-        "# check if notebook is in colab\n",
-        "try:\n",
-        "    # install ezkl\n",
-        "    import google.colab\n",
-        "    import subprocess\n",
-        "    import sys\n",
-        "    subprocess.check_call([sys.executable, \"-m\", \"pip\", \"install\", \"ezkl\"])\n",
-        "    subprocess.check_call([sys.executable, \"-m\", \"pip\", \"install\", \"onnx\"])\n",
-        "\n",
-        "# rely on local installation of ezkl if the notebook is not in colab\n",
-        "except:\n",
-        "    pass\n",
-        "\n",
-        "import ezkl\n",
-        "import torch\n",
-        "import datetime\n",
-        "import pandas as pd\n",
-        "import requests\n",
-        "import json\n",
-        "import os\n",
-        "\n",
-        "import logging\n",
-        "# # uncomment for more descriptive logging \n",
-        "FORMAT = '%(levelname)s %(name)s %(asctime)-15s %(filename)s:%(lineno)d %(message)s'\n",
-        "logging.basicConfig(format=FORMAT)\n",
-        "logging.getLogger().setLevel(logging.DEBUG)\n",
-        "\n",
-        "print(\"ezkl version: \", ezkl.__version__)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "osjj-0Ta3E8O"
-      },
-      "source": [
-        "**Create Computational Graph**"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "x1vl9ZXF3EEW",
-        "outputId": "bda21d02-fe5f-4fb2-8106-f51a8e2e67aa"
-      },
-      "outputs": [],
-      "source": [
-        "from torch import nn\n",
-        "import torch\n",
-        "\n",
-        "\n",
-        "class Model(nn.Module):\n",
-        "    def __init__(self):\n",
-        "        super(Model, self).__init__()\n",
-        "\n",
-        "    # x is a time series \n",
-        "    def forward(self, x):\n",
-        "        return [torch.mean(x)]\n",
-        "\n",
-        "\n",
-        "\n",
-        "\n",
-        "circuit = Model()\n",
-        "\n",
-        "\n",
-        "\n",
-        "\n",
-        "x = 0.1*torch.rand(1,*[1,5], requires_grad=True)\n",
-        "\n",
-        "# # print(torch.__version__)\n",
-        "device = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")\n",
-        "\n",
-        "print(device)\n",
-        "\n",
-        "circuit.to(device)\n",
-        "\n",
-        "# Flips the neural net into inference mode\n",
-        "circuit.eval()\n",
-        "\n",
-        "# Export the model\n",
-        "torch.onnx.export(circuit,               # model being run\n",
-        "                      x,                   # model input (or a tuple for multiple inputs)\n",
-        "                      \"lol.onnx\",            # where to save the model (can be a file or file-like object)\n",
-        "                      export_params=True,        # store the trained parameter weights inside the model file\n",
-        "                      opset_version=11,          # the ONNX version to export the model to\n",
-        "                      do_constant_folding=True,  # whether to execute constant folding for optimization\n",
-        "                      input_names = ['input'],   # the model's input names\n",
-        "                      output_names = ['output'], # the model's output names\n",
-        "                      dynamic_axes={'input' : {0 : 'batch_size'},    # variable length axes\n",
-        "                                    'output' : {0 : 'batch_size'}})\n",
-        "\n",
-        "# export(circuit, input_shape=[1, 20])\n",
-        "\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "E3qCeX-X5xqd"
-      },
-      "source": [
-        "**Set Data Source and Get Data**"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "6RAMplxk5xPk",
-        "outputId": "bd2158fe-0c00-44fd-e632-6a3f70cdb7c9"
-      },
-      "outputs": [],
-      "source": [
-        "import getpass\n",
-        "# make an input.json file from the df above\n",
-        "input_filename = os.path.join('input.json')\n",
-        "\n",
-        "pg_input_file = dict(input_data = {\n",
-        "  \"host\": \"localhost\",\n",
-        "  # make sure you replace this with your own username\n",
-        "  \"user\": getpass.getuser(),\n",
-        "  \"dbname\": \"shovel\",\n",
-        "  \"password\": \"\",\n",
-        "  \"query\": \"SELECT v FROM usdc ORDER BY block_num DESC LIMIT 5\",\n",
-        "  \"port\": \"5432\",\n",
-        "})\n",
-        "\n",
-        "json_formatted_str = json.dumps(pg_input_file, indent=2)\n",
-        "print(json_formatted_str)\n",
-        "\n",
-        "\n",
-        "    # Serialize data into file:\n",
-        "json.dump(pg_input_file, open(input_filename, 'w' ))\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "# this corresponds to 4 batches\n",
-        "calibration_filename = os.path.join('calibration.json')\n",
-        "\n",
-        "pg_cal_file = dict(input_data = {\n",
-        "  \"host\": \"localhost\",\n",
-        "  # make sure you replace this with your own username\n",
-        "  \"user\": getpass.getuser(),\n",
-        "  \"dbname\": \"shovel\",\n",
-        "  \"password\": \"\",\n",
-        "  \"query\": \"SELECT v FROM usdc ORDER BY block_num DESC LIMIT 20\",\n",
-        "  \"port\": \"5432\",\n",
-        "})\n",
-        "\n",
-        "    # Serialize data into file:\n",
-        "json.dump( pg_cal_file, open(calibration_filename, 'w' ))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "eLJ7oirQ_HQR"
-      },
-      "source": [
-        "**EZKL Workflow**"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "rNw0C9QL6W88"
-      },
-      "outputs": [],
-      "source": [
-        "import subprocess\n",
-        "import os\n",
-        "\n",
-        "onnx_filename = os.path.join('lol.onnx')\n",
-        "compiled_filename = os.path.join('lol.compiled')\n",
-        "settings_filename = os.path.join('settings.json')\n",
-        "\n",
-        "# Generate settings using ezkl\n",
-        "res = ezkl.gen_settings(onnx_filename, settings_filename)\n",
-        "\n",
-        "assert res == True\n",
-        "\n",
-        "res = await ezkl.calibrate_settings(input_filename, onnx_filename, settings_filename, \"resources\")\n",
-        "\n",
-        "assert res == True"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "\n",
-        "ezkl.compile_circuit(onnx_filename, compiled_filename, settings_filename)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "4MmE9SX66_Il",
-        "outputId": "16403639-66a4-4280-ac7f-6966b75de5a3"
-      },
-      "outputs": [],
-      "source": [
-        "# generate settings\n",
-        "\n",
-        "\n",
-        "# show the settings.json\n",
-        "with open(\"settings.json\") as f:\n",
-        "  data = json.load(f)\n",
-        "  json_formatted_str = json.dumps(data, indent=2)\n",
-        "\n",
-        "  print(json_formatted_str)\n",
-        "\n",
-        "assert os.path.exists(\"settings.json\")\n",
-        "assert os.path.exists(\"input.json\")\n",
-        "assert os.path.exists(\"lol.onnx\")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "fULvvnK7_CMb"
-      },
-      "outputs": [],
-      "source": [
-        "pk_path = os.path.join('test.pk')\n",
-        "vk_path = os.path.join('test.vk')\n",
-        "\n",
-        "\n",
-        "# setup the proof\n",
-        "res = ezkl.setup(\n",
-        "        compiled_filename,\n",
-        "        vk_path,\n",
-        "        pk_path\n",
-        "    )\n",
-        "\n",
-        "assert res == True\n",
-        "assert os.path.isfile(vk_path)\n",
-        "assert os.path.isfile(pk_path)\n",
-        "assert os.path.isfile(settings_filename)\n",
-        "\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "witness_path = \"witness.json\"\n",
-        "\n",
-        "# generate the witness\n",
-        "res = await ezkl.gen_witness(\n",
-        "        input_filename,\n",
-        "        compiled_filename,\n",
-        "        witness_path\n",
-        "    )\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "id": "Oog3j6Kd-Wed",
-        "outputId": "5839d0c1-5b43-476e-c2f8-6707de562260"
-      },
-      "outputs": [],
-      "source": [
-        "# prove the zk circuit\n",
-        "# GENERATE A PROOF\n",
-        "proof_path = os.path.join('test.pf')\n",
-        "\n",
-        "\n",
-        "proof = ezkl.prove(\n",
-        "        witness_path,\n",
-        "        compiled_filename,\n",
-        "        pk_path,\n",
-        "        proof_path,\n",
-        "        \"single\"\n",
-        "    )\n",
-        "\n",
-        "\n",
-        "print(\"proved\")\n",
-        "\n",
-        "assert os.path.isfile(proof_path)\n",
-        "\n"
-      ]
-    }
-  ],
-  "metadata": {
-    "colab": {
-      "provenance": []
-    },
-    "kernelspec": {
-      "display_name": "Python 3",
-      "name": "python3"
-    },
-    "language_info": {
-      "codemirror_mode": {
-        "name": "ipython",
-        "version": 3
-      },
-      "file_extension": ".py",
-      "mimetype": "text/x-python",
-      "name": "python",
-      "nbconvert_exporter": "python",
-      "pygments_lexer": "ipython3",
-      "version": "3.12.2"
-    }
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Mean of ERC20 transfer amounts\n",
+    "\n",
+    "This notebook shows how to calculate the mean of ERC20 transfer amounts, pulling data in from a Postgres database. First we install and get the necessary libraries running. \n",
+    "The first of which is [shovel](https://indexsupply.com/shovel/docs/#getting-started), which is a library that allows us to pull data from the Ethereum blockchain into a Postgres database.\n",
+    "\n",
+    "Make sure you install postgres if needed https://indexsupply.com/shovel/docs/#getting-started. \n",
+    "\n"
+   ]
   },
-  "nbformat": 4,
-  "nbformat_minor": 0
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import getpass\n",
+    "import json\n",
+    "import time\n",
+    "import subprocess\n",
+    "\n",
+    "# swap out for the relevant linux/amd64, darwin/arm64, darwin/amd64, windows/amd64\n",
+    "os.system(\"curl -LO https://indexsupply.net/bin/1.0/linux/amd64/shovel\")\n",
+    "os.system(\"chmod +x shovel\")\n",
+    "\n",
+    "\n",
+    "os.environ[\"PG_URL\"] = \"postgres://\" + getpass.getuser() + \":@localhost:5432/shovel\"\n",
+    "\n",
+    "# create a config.json file with the following contents\n",
+    "config = {\n",
+    "  \"pg_url\": \"$PG_URL\",\n",
+    "  \"eth_sources\": [\n",
+    "    {\"name\": \"mainnet\", \"chain_id\": 1, \"url\": \"https://ethereum-rpc.publicnode.com\"},\n",
+    "    {\"name\": \"base\", \"chain_id\": 8453, \"url\": \"https://base-rpc.publicnode.com\"}\n",
+    "  ],\n",
+    "  \"integrations\": [{\n",
+    "    \"name\": \"usdc_transfer\",\n",
+    "    \"enabled\": True,\n",
+    "    \"sources\": [{\"name\": \"mainnet\"}, {\"name\": \"base\"}],\n",
+    "    \"table\": {\n",
+    "      \"name\": \"usdc\",\n",
+    "      \"columns\": [\n",
+    "        {\"name\": \"log_addr\",  \"type\": \"bytea\"},\n",
+    "        {\"name\": \"block_num\", \"type\": \"numeric\"},\n",
+    "        {\"name\": \"f\",         \"type\": \"bytea\"},\n",
+    "        {\"name\": \"t\",         \"type\": \"bytea\"},\n",
+    "        {\"name\": \"v\",         \"type\": \"numeric\"}\n",
+    "      ]\n",
+    "    },\n",
+    "    \"block\": [\n",
+    "      {\"name\": \"block_num\", \"column\": \"block_num\"},\n",
+    "      {\n",
+    "        \"name\": \"log_addr\",\n",
+    "        \"column\": \"log_addr\",\n",
+    "        \"filter_op\": \"contains\",\n",
+    "        \"filter_arg\": [\n",
+    "          \"a0b86991c6218b36c1d19d4a2e9eb0ce3606eb48\",\n",
+    "          \"833589fCD6eDb6E08f4c7C32D4f71b54bdA02913\"\n",
+    "        ]\n",
+    "      }\n",
+    "    ],\n",
+    "    \"event\": {\n",
+    "      \"name\": \"Transfer\",\n",
+    "      \"type\": \"event\",\n",
+    "      \"anonymous\": False,\n",
+    "      \"inputs\": [\n",
+    "        {\"indexed\": True,  \"name\": \"from\",  \"type\": \"address\", \"column\": \"f\"},\n",
+    "        {\"indexed\": True,  \"name\": \"to\",    \"type\": \"address\", \"column\": \"t\"},\n",
+    "        {\"indexed\": False, \"name\": \"value\", \"type\": \"uint256\", \"column\": \"v\"}\n",
+    "      ]\n",
+    "    }\n",
+    "  }]\n",
+    "}\n",
+    "\n",
+    "# write the config to a file\n",
+    "with open(\"config.json\", \"w\") as f:\n",
+    "  f.write(json.dumps(config))\n",
+    "\n",
+    "\n",
+    "# print the two env variables\n",
+    "os.system(\"echo $PG_URL\")\n",
+    "\n",
+    "os.system(\"createdb -h localhost -p 5432 shovel\")\n",
+    "\n",
+    "os.system(\"echo shovel is now installed. starting:\")\n",
+    "\n",
+    "command = [\"./shovel\", \"-config\", \"config.json\"]\n",
+    "proc = subprocess.Popen(command)\n",
+    "\n",
+    "os.system(\"echo shovel started.\")\n",
+    "\n",
+    "time.sleep(10)\n",
+    "\n",
+    "# after we've fetched some data -- kill the process\n",
+    "proc.terminate()\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "2wIAHwqH2_mo"
+   },
+   "source": [
+    "**Import Dependencies**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "9Byiv2Nc2MsK"
+   },
+   "outputs": [],
+   "source": [
+    "# check if notebook is in colab\n",
+    "try:\n",
+    "    # install ezkl\n",
+    "    import google.colab\n",
+    "    import subprocess\n",
+    "    import sys\n",
+    "    subprocess.check_call([sys.executable, \"-m\", \"pip\", \"install\", \"ezkl\"])\n",
+    "    subprocess.check_call([sys.executable, \"-m\", \"pip\", \"install\", \"onnx\"])\n",
+    "\n",
+    "# rely on local installation of ezkl if the notebook is not in colab\n",
+    "except:\n",
+    "    pass\n",
+    "\n",
+    "import ezkl\n",
+    "import torch\n",
+    "import datetime\n",
+    "import pandas as pd\n",
+    "import requests\n",
+    "import json\n",
+    "import os\n",
+    "\n",
+    "import logging\n",
+    "# # uncomment for more descriptive logging \n",
+    "FORMAT = '%(levelname)s %(name)s %(asctime)-15s %(filename)s:%(lineno)d %(message)s'\n",
+    "logging.basicConfig(format=FORMAT)\n",
+    "logging.getLogger().setLevel(logging.DEBUG)\n",
+    "\n",
+    "print(\"ezkl version: \", ezkl.__version__)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "osjj-0Ta3E8O"
+   },
+   "source": [
+    "**Create Computational Graph**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "x1vl9ZXF3EEW",
+    "outputId": "bda21d02-fe5f-4fb2-8106-f51a8e2e67aa"
+   },
+   "outputs": [],
+   "source": [
+    "from torch import nn\n",
+    "import torch\n",
+    "\n",
+    "\n",
+    "class Model(nn.Module):\n",
+    "    def __init__(self):\n",
+    "        super(Model, self).__init__()\n",
+    "\n",
+    "    # x is a time series \n",
+    "    def forward(self, x):\n",
+    "        return [torch.mean(x)]\n",
+    "\n",
+    "\n",
+    "\n",
+    "\n",
+    "circuit = Model()\n",
+    "\n",
+    "\n",
+    "\n",
+    "\n",
+    "x = 0.1*torch.rand(1,*[1,5], requires_grad=True)\n",
+    "\n",
+    "# # print(torch.__version__)\n",
+    "device = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")\n",
+    "\n",
+    "print(device)\n",
+    "\n",
+    "circuit.to(device)\n",
+    "\n",
+    "# Flips the neural net into inference mode\n",
+    "circuit.eval()\n",
+    "\n",
+    "# Export the model\n",
+    "torch.onnx.export(circuit,               # model being run\n",
+    "                      x,                   # model input (or a tuple for multiple inputs)\n",
+    "                      \"lol.onnx\",            # where to save the model (can be a file or file-like object)\n",
+    "                      export_params=True,        # store the trained parameter weights inside the model file\n",
+    "                      opset_version=11,          # the ONNX version to export the model to\n",
+    "                      do_constant_folding=True,  # whether to execute constant folding for optimization\n",
+    "                      input_names = ['input'],   # the model's input names\n",
+    "                      output_names = ['output'], # the model's output names\n",
+    "                      dynamic_axes={'input' : {0 : 'batch_size'},    # variable length axes\n",
+    "                                    'output' : {0 : 'batch_size'}})\n",
+    "\n",
+    "# export(circuit, input_shape=[1, 20])\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "E3qCeX-X5xqd"
+   },
+   "source": [
+    "**Set Data Source and Get Data**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "6RAMplxk5xPk",
+    "outputId": "bd2158fe-0c00-44fd-e632-6a3f70cdb7c9"
+   },
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "# make an input.json file from the df above\n",
+    "input_filename = os.path.join('input.json')\n",
+    "\n",
+    "pg_input_file = dict(input_data = {\n",
+    "  \"host\": \"localhost\",\n",
+    "  # make sure you replace this with your own username\n",
+    "  \"user\": getpass.getuser(),\n",
+    "  \"dbname\": \"shovel\",\n",
+    "  \"password\": \"\",\n",
+    "  \"query\": \"SELECT v FROM usdc ORDER BY block_num DESC LIMIT 5\",\n",
+    "  \"port\": \"5432\",\n",
+    "})\n",
+    "\n",
+    "json_formatted_str = json.dumps(pg_input_file, indent=2)\n",
+    "print(json_formatted_str)\n",
+    "\n",
+    "\n",
+    "    # Serialize data into file:\n",
+    "json.dump(pg_input_file, open(input_filename, 'w' ))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# this corresponds to 4 batches\n",
+    "calibration_filename = os.path.join('calibration.json')\n",
+    "\n",
+    "pg_cal_file = dict(input_data = {\n",
+    "  \"host\": \"localhost\",\n",
+    "  # make sure you replace this with your own username\n",
+    "  \"user\": getpass.getuser(),\n",
+    "  \"dbname\": \"shovel\",\n",
+    "  \"password\": \"\",\n",
+    "  \"query\": \"SELECT v FROM usdc ORDER BY block_num DESC LIMIT 20\",\n",
+    "  \"port\": \"5432\",\n",
+    "})\n",
+    "\n",
+    "    # Serialize data into file:\n",
+    "json.dump( pg_cal_file, open(calibration_filename, 'w' ))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "eLJ7oirQ_HQR"
+   },
+   "source": [
+    "**EZKL Workflow**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "rNw0C9QL6W88"
+   },
+   "outputs": [],
+   "source": [
+    "import subprocess\n",
+    "import os\n",
+    "\n",
+    "onnx_filename = os.path.join('lol.onnx')\n",
+    "compiled_filename = os.path.join('lol.compiled')\n",
+    "settings_filename = os.path.join('settings.json')\n",
+    "\n",
+    "# Generate settings using ezkl\n",
+    "res = ezkl.gen_settings(onnx_filename, settings_filename)\n",
+    "\n",
+    "assert res == True\n",
+    "\n",
+    "res = await ezkl.calibrate_settings(input_filename, onnx_filename, settings_filename, \"resources\")\n",
+    "\n",
+    "assert res == True\n",
+    "\n",
+    "await ezkl.get_srs(settings_filename)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "ezkl.compile_circuit(onnx_filename, compiled_filename, settings_filename)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "4MmE9SX66_Il",
+    "outputId": "16403639-66a4-4280-ac7f-6966b75de5a3"
+   },
+   "outputs": [],
+   "source": [
+    "# generate settings\n",
+    "\n",
+    "\n",
+    "# show the settings.json\n",
+    "with open(\"settings.json\") as f:\n",
+    "  data = json.load(f)\n",
+    "  json_formatted_str = json.dumps(data, indent=2)\n",
+    "\n",
+    "  print(json_formatted_str)\n",
+    "\n",
+    "assert os.path.exists(\"settings.json\")\n",
+    "assert os.path.exists(\"input.json\")\n",
+    "assert os.path.exists(\"lol.onnx\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "fULvvnK7_CMb"
+   },
+   "outputs": [],
+   "source": [
+    "pk_path = os.path.join('test.pk')\n",
+    "vk_path = os.path.join('test.vk')\n",
+    "\n",
+    "\n",
+    "# setup the proof\n",
+    "res = ezkl.setup(\n",
+    "        compiled_filename,\n",
+    "        vk_path,\n",
+    "        pk_path\n",
+    "    )\n",
+    "\n",
+    "assert res == True\n",
+    "assert os.path.isfile(vk_path)\n",
+    "assert os.path.isfile(pk_path)\n",
+    "assert os.path.isfile(settings_filename)\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "witness_path = \"witness.json\"\n",
+    "\n",
+    "# generate the witness\n",
+    "res = await ezkl.gen_witness(\n",
+    "        input_filename,\n",
+    "        compiled_filename,\n",
+    "        witness_path\n",
+    "    )\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "Oog3j6Kd-Wed",
+    "outputId": "5839d0c1-5b43-476e-c2f8-6707de562260"
+   },
+   "outputs": [],
+   "source": [
+    "# prove the zk circuit\n",
+    "# GENERATE A PROOF\n",
+    "proof_path = os.path.join('test.pf')\n",
+    "\n",
+    "\n",
+    "proof = ezkl.prove(\n",
+    "        witness_path,\n",
+    "        compiled_filename,\n",
+    "        pk_path,\n",
+    "        proof_path,\n",
+    "        \"single\"\n",
+    "    )\n",
+    "\n",
+    "\n",
+    "print(\"proved\")\n",
+    "\n",
+    "assert os.path.isfile(proof_path)\n",
+    "\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": ".env",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
 }

examples/notebooks/mnist_gan_proof_splitting.ipynb

@@ -453,18 +453,18 @@
             "outputs": [],
             "source": [
                 "# now mock aggregate the proofs\n",
-                "proofs = []\n",
-                "for i in range(3):\n",
-                "    proof_path = os.path.join('proof_split_'+str(i)+'.json')\n",
-                "    proofs.append(proof_path)\n",
+                "# proofs = []\n",
+                "# for i in range(3):\n",
+                "#     proof_path = os.path.join('proof_split_'+str(i)+'.json')\n",
+                "#     proofs.append(proof_path)\n",
                 "\n",
-                "ezkl.mock_aggregate(proofs, logrows=23, split_proofs = True)"
+                "# ezkl.mock_aggregate(proofs, logrows=26, split_proofs = True)"
             ]
         }
     ],
     "metadata": {
         "kernelspec": {
-            "display_name": "ezkl",
+            "display_name": ".env",
             "language": "python",
             "name": "python3"
         },
@@ -478,7 +478,7 @@
             "name": "python",
             "nbconvert_exporter": "python",
             "pygments_lexer": "ipython3",
-            "version": "3.12.5"
+            "version": "3.12.7"
         },
         "orig_nbformat": 4
     },

pyproject.toml

@@ -12,6 +12,7 @@ asyncio_mode = "auto"
 
 [project]
 name = "ezkl"
+version = "0.0.0"
 requires-python = ">=3.7"
 classifiers = [
     "Programming Language :: Rust",

src/bindings/python.rs

@@ -938,6 +938,45 @@ fn gen_settings(
     Ok(true)
 }
 
+/// Generates random data for the model
+///
+/// Arguments
+/// ---------
+/// model: str
+///     Path to the onnx file
+///
+/// output: str
+///     Path to create the data file
+///
+/// seed: int
+///     Random seed to use for generated data
+///
+/// variables
+/// Returns
+/// -------
+/// bool
+///
+#[pyfunction(signature = (
+    model=PathBuf::from(DEFAULT_MODEL),
+    output=PathBuf::from(DEFAULT_SETTINGS),
+    variables=Vec::from([("batch_size".to_string(), 1)]),
+    seed=DEFAULT_SEED.parse().unwrap(),
+))]
+#[gen_stub_pyfunction]
+fn gen_random_data(
+    model: PathBuf,
+    output: PathBuf,
+    variables: Vec<(String, usize)>,
+    seed: u64,
+) -> Result<bool, PyErr> {
+    crate::execute::gen_random_data(model, output, variables, seed).map_err(|e| {
+        let err_str = format!("Failed to generate settings: {}", e);
+        PyRuntimeError::new_err(err_str)
+    })?;
+
+    Ok(true)
+}
+
 /// Calibrates the circuit settings
 ///
 /// Arguments
@@ -2055,6 +2094,7 @@ fn ezkl(m: &Bound<'_, PyModule>) -> PyResult<()> {
     m.add_function(wrap_pyfunction!(get_srs, m)?)?;
     m.add_function(wrap_pyfunction!(gen_witness, m)?)?;
     m.add_function(wrap_pyfunction!(gen_settings, m)?)?;
+    m.add_function(wrap_pyfunction!(gen_random_data, m)?)?;
     m.add_function(wrap_pyfunction!(calibrate_settings, m)?)?;
     m.add_function(wrap_pyfunction!(aggregate, m)?)?;
     m.add_function(wrap_pyfunction!(mock_aggregate, m)?)?;

src/bindings/universal.rs

@@ -141,10 +141,11 @@ pub(crate) fn gen_vk(
     .map_err(|e| EZKLError::InternalError(format!("Failed to create verifying key: {}", e)))?;
 
     let mut serialized_vk = Vec::new();
-    vk.write(&mut serialized_vk, halo2_proofs::SerdeFormat::RawBytes)
-        .map_err(|e| {
-            EZKLError::InternalError(format!("Failed to serialize verifying key: {}", e))
-        })?;
+    vk.write(
+        &mut serialized_vk,
+        halo2_proofs::SerdeFormat::RawBytesUnchecked,
+    )
+    .map_err(|e| EZKLError::InternalError(format!("Failed to serialize verifying key: {}", e)))?;
 
     Ok(serialized_vk)
 }
@@ -165,7 +166,7 @@ pub(crate) fn gen_pk(
     let mut reader = BufReader::new(&vk[..]);
     let vk = VerifyingKey::<G1Affine>::read::<_, GraphCircuit>(
         &mut reader,
-        halo2_proofs::SerdeFormat::RawBytes,
+        halo2_proofs::SerdeFormat::RawBytesUnchecked,
         circuit.settings().clone(),
     )
     .map_err(|e| EZKLError::InternalError(format!("Failed to deserialize verifying key: {}", e)))?;
@@ -197,7 +198,7 @@ pub(crate) fn verify(
     let mut reader = BufReader::new(&vk[..]);
     let vk = VerifyingKey::<G1Affine>::read::<_, GraphCircuit>(
         &mut reader,
-        halo2_proofs::SerdeFormat::RawBytes,
+        halo2_proofs::SerdeFormat::RawBytesUnchecked,
         circuit_settings.clone(),
     )
     .map_err(|e| EZKLError::InternalError(format!("Failed to deserialize vk: {}", e)))?;
@@ -277,7 +278,7 @@ pub(crate) fn verify_aggr(
     let mut reader = BufReader::new(&vk[..]);
     let vk = VerifyingKey::<G1Affine>::read::<_, AggregationCircuit>(
         &mut reader,
-        halo2_proofs::SerdeFormat::RawBytes,
+        halo2_proofs::SerdeFormat::RawBytesUnchecked,
         (),
     )
     .map_err(|e| EZKLError::InternalError(format!("Failed to deserialize vk: {}", e)))?;
@@ -365,7 +366,7 @@ pub(crate) fn prove(
     let mut reader = BufReader::new(&pk[..]);
     let pk = ProvingKey::<G1Affine>::read::<_, GraphCircuit>(
         &mut reader,
-        halo2_proofs::SerdeFormat::RawBytes,
+        halo2_proofs::SerdeFormat::RawBytesUnchecked,
         circuit.settings().clone(),
     )
     .map_err(|e| EZKLError::InternalError(format!("Failed to deserialize proving key: {}", e)))?;
@@ -487,7 +488,7 @@ pub(crate) fn vk_validation(vk: Vec<u8>, settings: Vec<u8>) -> Result<bool, EZKL
     let mut reader = BufReader::new(&vk[..]);
     let _ = VerifyingKey::<G1Affine>::read::<_, GraphCircuit>(
         &mut reader,
-        halo2_proofs::SerdeFormat::RawBytes,
+        halo2_proofs::SerdeFormat::RawBytesUnchecked,
         circuit_settings,
     )
     .map_err(|e| EZKLError::InternalError(format!("Failed to deserialize verifying key: {}", e)))?;
@@ -504,7 +505,7 @@ pub(crate) fn pk_validation(pk: Vec<u8>, settings: Vec<u8>) -> Result<bool, EZKL
     let mut reader = BufReader::new(&pk[..]);
     let _ = ProvingKey::<G1Affine>::read::<_, GraphCircuit>(
         &mut reader,
-        halo2_proofs::SerdeFormat::RawBytes,
+        halo2_proofs::SerdeFormat::RawBytesUnchecked,
         circuit_settings,
     )
     .map_err(|e| EZKLError::InternalError(format!("Failed to deserialize proving key: {}", e)))?;

src/circuit/modules/poseidon.rs

@@ -100,9 +100,6 @@ impl<S: Spec<Fp, WIDTH, RATE> + Sync, const WIDTH: usize, const RATE: usize, con
         let rc_a = (0..WIDTH).map(|_| meta.fixed_column()).collect::<Vec<_>>();
         let rc_b = (0..WIDTH).map(|_| meta.fixed_column()).collect::<Vec<_>>();
 
-        for input in hash_inputs.iter().take(WIDTH) {
-            meta.enable_equality(*input);
-        }
         meta.enable_constant(rc_b[0]);
 
         Self::configure_with_cols(
@@ -152,9 +149,6 @@ impl<S: Spec<Fp, WIDTH, RATE> + Sync, const WIDTH: usize, const RATE: usize, con
         let rc_a = (0..WIDTH).map(|_| meta.fixed_column()).collect::<Vec<_>>();
         let rc_b = (0..WIDTH).map(|_| meta.fixed_column()).collect::<Vec<_>>();
 
-        for input in hash_inputs.iter().take(WIDTH) {
-            meta.enable_equality(*input);
-        }
         meta.enable_constant(rc_b[0]);
 
         let instance = meta.instance_column();

src/circuit/ops/chip.rs

@@ -75,6 +75,16 @@ impl FromStr for CheckMode {
     }
 }
 
+impl CheckMode {
+    /// Returns the value of the check mode
+    pub fn is_safe(&self) -> bool {
+        match self {
+            CheckMode::SAFE => true,
+            CheckMode::UNSAFE => false,
+        }
+    }
+}
+
 #[allow(missing_docs)]
 /// An enum representing the tolerance we can accept for the accumulated arguments, either absolute or percentage
 #[derive(Clone, Default, Debug, PartialEq, PartialOrd, Serialize, Deserialize, Copy)]
@@ -205,15 +215,16 @@ impl DynamicLookups {
 
 /// A struct representing the selectors for the dynamic lookup tables
 #[derive(Clone, Debug, Default)]
+
 pub struct Shuffles {
     /// [Selector]s generated when configuring the layer. We use a [BTreeMap] as we expect to configure many dynamic lookup ops.
     pub input_selectors: BTreeMap<(usize, (usize, usize)), Selector>,
     /// Selectors for the dynamic lookup tables
-    pub reference_selectors: Vec<Selector>,
+    pub output_selectors: Vec<Selector>,
     /// Inputs:
     pub inputs: Vec<VarTensor>,
     /// tables
-    pub references: Vec<VarTensor>,
+    pub outputs: Vec<VarTensor>,
 }
 
 impl Shuffles {
@@ -224,9 +235,13 @@ impl Shuffles {
 
         Self {
             input_selectors: BTreeMap::new(),
-            reference_selectors: vec![],
-            inputs: vec![dummy_var.clone(), dummy_var.clone()],
-            references: vec![single_col_dummy_var.clone(), single_col_dummy_var.clone()],
+            output_selectors: vec![],
+            inputs: vec![dummy_var.clone(), dummy_var.clone(), dummy_var.clone()],
+            outputs: vec![
+                single_col_dummy_var.clone(),
+                single_col_dummy_var.clone(),
+                single_col_dummy_var.clone(),
+            ],
         }
     }
 }
@@ -364,6 +379,12 @@ impl<F: PrimeField + TensorType + PartialOrd + std::hash::Hash> BaseConfig<F> {
         if inputs[0].num_cols() != output.num_cols() {
             log::warn!("input and output shapes do not match");
         }
+        if inputs[0].num_inner_cols() != inputs[1].num_inner_cols() {
+            log::warn!("input number of inner columns do not match");
+        }
+        if inputs[0].num_inner_cols() != output.num_inner_cols() {
+            log::warn!("input and output number of inner columns do not match");
+        }
 
         for i in 0..output.num_blocks() {
             for j in 0..output.num_inner_cols() {
@@ -730,8 +751,8 @@ impl<F: PrimeField + TensorType + PartialOrd + std::hash::Hash> BaseConfig<F> {
     pub fn configure_shuffles(
         &mut self,
         cs: &mut ConstraintSystem<F>,
-        inputs: &[VarTensor; 2],
-        references: &[VarTensor; 2],
+        inputs: &[VarTensor; 3],
+        outputs: &[VarTensor; 3],
     ) -> Result<(), CircuitError>
     where
         F: Field,
@@ -742,14 +763,14 @@ impl<F: PrimeField + TensorType + PartialOrd + std::hash::Hash> BaseConfig<F> {
             }
         }
 
-        for t in references.iter() {
+        for t in outputs.iter() {
             if !t.is_advice() || t.num_inner_cols() > 1 {
                 return Err(CircuitError::WrongDynamicColumnType(t.name().to_string()));
             }
         }
 
         // assert all tables have the same number of blocks
-        if references
+        if outputs
             .iter()
             .map(|t| t.num_blocks())
             .collect::<Vec<_>>()
@@ -757,23 +778,23 @@ impl<F: PrimeField + TensorType + PartialOrd + std::hash::Hash> BaseConfig<F> {
             .any(|w| w[0] != w[1])
         {
             return Err(CircuitError::WrongDynamicColumnType(
-                "references inner cols".to_string(),
+                "outputs inner cols".to_string(),
             ));
         }
 
         let one = Expression::Constant(F::ONE);
 
-        for q in 0..references[0].num_blocks() {
-            let s_reference = cs.complex_selector();
+        for q in 0..outputs[0].num_blocks() {
+            let s_output = cs.complex_selector();
 
             for x in 0..inputs[0].num_blocks() {
                 for y in 0..inputs[0].num_inner_cols() {
                     let s_input = cs.complex_selector();
 
-                    cs.lookup_any("lookup", |cs| {
+                    cs.lookup_any("shuffle", |cs| {
                         let s_inputq = cs.query_selector(s_input);
                         let mut expression = vec![];
-                        let s_referenceq = cs.query_selector(s_reference);
+                        let s_outputq = cs.query_selector(s_output);
                         let mut input_queries = vec![one.clone()];
 
                         for input in inputs {
@@ -785,9 +806,9 @@ impl<F: PrimeField + TensorType + PartialOrd + std::hash::Hash> BaseConfig<F> {
                             });
                         }
 
-                        let mut ref_queries = vec![one.clone()];
-                        for reference in references {
-                            ref_queries.push(match reference {
+                        let mut output_queries = vec![one.clone()];
+                        for output in outputs {
+                            output_queries.push(match output {
                                 VarTensor::Advice { inner: advices, .. } => {
                                     cs.query_advice(advices[q][0], Rotation(0))
                                 }
@@ -796,7 +817,7 @@ impl<F: PrimeField + TensorType + PartialOrd + std::hash::Hash> BaseConfig<F> {
                         }
 
                         let lhs = input_queries.into_iter().map(|c| c * s_inputq.clone());
-                        let rhs = ref_queries.into_iter().map(|c| c * s_referenceq.clone());
+                        let rhs = output_queries.into_iter().map(|c| c * s_outputq.clone());
                         expression.extend(lhs.zip(rhs));
 
                         expression
@@ -807,13 +828,13 @@ impl<F: PrimeField + TensorType + PartialOrd + std::hash::Hash> BaseConfig<F> {
                         .or_insert(s_input);
                 }
             }
-            self.shuffles.reference_selectors.push(s_reference);
+            self.shuffles.output_selectors.push(s_output);
         }
 
         // if we haven't previously initialized the input/output, do so now
-        if self.shuffles.references.is_empty() {
-            debug!("assigning shuffles reference");
-            self.shuffles.references = references.to_vec();
+        if self.shuffles.outputs.is_empty() {
+            debug!("assigning shuffles output");
+            self.shuffles.outputs = outputs.to_vec();
         }
         if self.shuffles.inputs.is_empty() {
             debug!("assigning shuffles input");

src/circuit/ops/errors.rs

@@ -100,4 +100,7 @@ pub enum CircuitError {
     #[error("invalid input type {0}")]
     /// Invalid input type
     InvalidInputType(String),
+    #[error("an element is missing from the shuffled version of the tensor")]
+    /// An element is missing from the shuffled version of the tensor
+    MissingShuffleElement,
 }

src/circuit/ops/hybrid.rs

@@ -1,7 +1,7 @@
 use super::*;
 use crate::{
     circuit::{layouts, utils, Tolerance},
-    fieldutils::integer_rep_to_felt,
+    fieldutils::{integer_rep_to_felt, IntegerRep},
     graph::multiplier_to_scale,
     tensor::{self, Tensor, TensorType, ValTensor},
 };
@@ -250,8 +250,8 @@ impl<F: PrimeField + TensorType + PartialOrd + std::hash::Hash> Op<F> for Hybrid
                 config,
                 region,
                 values[..].try_into()?,
-                integer_rep_to_felt(input_scale.0 as i128),
-                integer_rep_to_felt(output_scale.0 as i128),
+                integer_rep_to_felt(input_scale.0 as IntegerRep),
+                integer_rep_to_felt(output_scale.0 as IntegerRep),
             )?,
             HybridOp::Div { denom, .. } => {
                 if denom.0.fract() == 0.0 {
@@ -259,7 +259,7 @@ impl<F: PrimeField + TensorType + PartialOrd + std::hash::Hash> Op<F> for Hybrid
                         config,
                         region,
                         values[..].try_into()?,
-                        integer_rep_to_felt(denom.0 as i128),
+                        integer_rep_to_felt(denom.0 as IntegerRep),
                     )?
                 } else {
                     layouts::nonlinearity(

src/circuit/ops/region.rs

@@ -671,22 +671,17 @@ impl<'a, F: PrimeField + TensorType + PartialOrd + std::hash::Hash> RegionCtx<'a
     }
 
     /// Assign a valtensor to a vartensor with duplication
-    pub fn assign_with_duplication(
+    pub fn assign_with_duplication_unconstrained(
         &mut self,
         var: &VarTensor,
         values: &ValTensor<F>,
-        check_mode: &crate::circuit::CheckMode,
-        single_inner_col: bool,
     ) -> Result<(ValTensor<F>, usize), Error> {
         if let Some(region) = &self.region {
             // duplicates every nth element to adjust for column overflow
-            let (res, len) = var.assign_with_duplication(
+            let (res, len) = var.assign_with_duplication_unconstrained(
                 &mut region.borrow_mut(),
-                self.row,
                 self.linear_coord,
                 values,
-                check_mode,
-                single_inner_col,
                 &mut self.assigned_constants,
             )?;
             Ok((res, len))
@@ -695,7 +690,37 @@ impl<'a, F: PrimeField + TensorType + PartialOrd + std::hash::Hash> RegionCtx<'a
                 self.row,
                 self.linear_coord,
                 values,
-                single_inner_col,
+                false,
+                &mut self.assigned_constants,
+            )?;
+            Ok((values.clone(), len))
+        }
+    }
+
+    /// Assign a valtensor to a vartensor with duplication
+    pub fn assign_with_duplication_constrained(
+        &mut self,
+        var: &VarTensor,
+        values: &ValTensor<F>,
+        check_mode: &crate::circuit::CheckMode,
+    ) -> Result<(ValTensor<F>, usize), Error> {
+        if let Some(region) = &self.region {
+            // duplicates every nth element to adjust for column overflow
+            let (res, len) = var.assign_with_duplication_constrained(
+                &mut region.borrow_mut(),
+                self.row,
+                self.linear_coord,
+                values,
+                check_mode,
+                &mut self.assigned_constants,
+            )?;
+            Ok((res, len))
+        } else {
+            let (_, len) = var.dummy_assign_with_duplication(
+                self.row,
+                self.linear_coord,
+                values,
+                true,
                 &mut self.assigned_constants,
             )?;
             Ok((values.clone(), len))

src/circuit/tests.rs

@@ -1040,6 +1040,10 @@ mod conv {
             let a = VarTensor::new_advice(cs, K, 1, (LEN + 1) * LEN);
             let b = VarTensor::new_advice(cs, K, 1, (LEN + 1) * LEN);
             let output = VarTensor::new_advice(cs, K, 1, (LEN + 1) * LEN);
+
+            // column for constants
+            let _constant = VarTensor::constant_cols(cs, K, 8, false);
+
             Self::Config::configure(cs, &[a, b], &output, CheckMode::SAFE)
         }
 
@@ -1171,7 +1175,7 @@ mod conv_col_ultra_overflow {
 
     use super::*;
 
-    const K: usize = 4;
+    const K: usize = 6;
     const LEN: usize = 10;
 
     #[derive(Clone)]
@@ -1191,9 +1195,10 @@ mod conv_col_ultra_overflow {
         }
 
         fn configure(cs: &mut ConstraintSystem<F>) -> Self::Config {
-            let a = VarTensor::new_advice(cs, K, 1, LEN * LEN * LEN);
-            let b = VarTensor::new_advice(cs, K, 1, LEN * LEN * LEN);
-            let output = VarTensor::new_advice(cs, K, 1, LEN * LEN * LEN);
+            let a = VarTensor::new_advice(cs, K, 1, LEN * LEN * LEN * LEN);
+            let b = VarTensor::new_advice(cs, K, 1, LEN * LEN * LEN * LEN);
+            let output = VarTensor::new_advice(cs, K, 1, LEN * LEN * LEN * LEN);
+            let _constant = VarTensor::constant_cols(cs, K, LEN * LEN * LEN * LEN, false);
             Self::Config::configure(cs, &[a, b], &output, CheckMode::SAFE)
         }
 
@@ -1776,13 +1781,18 @@ mod shuffle {
 
             let d = VarTensor::new_advice(cs, K, 1, LEN);
             let e = VarTensor::new_advice(cs, K, 1, LEN);
+            let f: VarTensor = VarTensor::new_advice(cs, K, 1, LEN);
 
             let _constant = VarTensor::constant_cols(cs, K, LEN * NUM_LOOP, false);
 
             let mut config =
                 Self::Config::configure(cs, &[a.clone(), b.clone()], &c, CheckMode::SAFE);
             config
-                .configure_shuffles(cs, &[a.clone(), b.clone()], &[d.clone(), e.clone()])
+                .configure_shuffles(
+                    cs,
+                    &[a.clone(), b.clone(), c.clone()],
+                    &[d.clone(), e.clone(), f.clone()],
+                )
                 .unwrap();
             config
         }

src/commands.rs

@@ -83,13 +83,15 @@ pub const DEFAULT_VK_SOL: &str = "vk.sol";
 /// Default VK abi path
 pub const DEFAULT_VK_ABI: &str = "vk.abi";
 /// Default scale rebase multipliers for calibration
-pub const DEFAULT_SCALE_REBASE_MULTIPLIERS: &str = "1,2,10";
+pub const DEFAULT_SCALE_REBASE_MULTIPLIERS: &str = "1,10";
 /// Default use reduced srs for verification
 pub const DEFAULT_USE_REDUCED_SRS_FOR_VERIFICATION: &str = "false";
 /// Default only check for range check rebase
 pub const DEFAULT_ONLY_RANGE_CHECK_REBASE: &str = "false";
 /// Default commitment
 pub const DEFAULT_COMMITMENT: &str = "kzg";
+/// Default seed used to generate random data
+pub const DEFAULT_SEED: &str = "21242";
 
 #[cfg(feature = "python-bindings")]
 /// Converts TranscriptType into a PyObject (Required for TranscriptType to be compatible with Python)
@@ -422,7 +424,21 @@ pub enum Commands {
         #[clap(flatten)]
         args: RunArgs,
     },
-
+    /// Generate random data for a model
+    GenRandomData {
+        /// The path to the .onnx model file
+        #[arg(short = 'M', long, default_value = DEFAULT_MODEL, value_hint = clap::ValueHint::FilePath)]
+        model: Option<PathBuf>,
+        /// The path to the .json data file
+        #[arg(short = 'D', long, default_value = DEFAULT_DATA, value_hint = clap::ValueHint::FilePath)]
+        data: Option<PathBuf>,
+        /// Hand-written parser for graph variables, eg. batch_size=1
+        #[cfg_attr(all(feature = "ezkl", not(target_arch = "wasm32")), arg(short = 'V', long, value_parser = crate::parse_key_val::<String, usize>, default_value = "batch_size->1", value_delimiter = ',', value_hint = clap::ValueHint::Other))]
+        variables: Vec<(String, usize)>,
+        /// random seed for reproducibility (optional)
+        #[arg(long, value_hint = clap::ValueHint::Other, default_value = DEFAULT_SEED)]
+        seed: u64,
+    },
     /// Calibrates the proving scale, lookup bits and logrows from a circuit settings file.
     CalibrateSettings {
         /// The path to the .json calibration data file.

src/eth.rs

@@ -488,7 +488,7 @@ pub async fn deploy_da_verifier_via_solidity(
         }
     }
 
-    let contract = match call_to_account {
+    match call_to_account {
         Some(call) => {
             deploy_single_da_contract(
                 client,
@@ -514,8 +514,7 @@ pub async fn deploy_da_verifier_via_solidity(
             )
             .await
         }
-    };
-    return contract;
+    }
 }
 
 async fn deploy_multi_da_contract(
@@ -630,7 +629,7 @@ async fn deploy_single_da_contract(
             // bytes memory _callData,
             PackedSeqToken(call_data.as_ref()),
             // uint256 _decimals,
-            WordToken(B256::from(decimals).into()),
+            WordToken(B256::from(decimals)),
             // uint[] memory _scales,
             DynSeqToken(
                 scales

src/execute.rs

@@ -65,6 +65,8 @@ use std::str::FromStr;
 use std::time::Duration;
 use tabled::Tabled;
 use thiserror::Error;
+use tract_onnx::prelude::IntoTensor;
+use tract_onnx::prelude::Tensor as TractTensor;
 
 use lazy_static::lazy_static;
 
@@ -134,6 +136,17 @@ pub async fn run(command: Commands) -> Result<String, EZKLError> {
             settings_path.unwrap_or(DEFAULT_SETTINGS.into()),
             args,
         ),
+        Commands::GenRandomData {
+            model,
+            data,
+            variables,
+            seed,
+        } => gen_random_data(
+            model.unwrap_or(DEFAULT_MODEL.into()),
+            data.unwrap_or(DEFAULT_DATA.into()),
+            variables,
+            seed,
+        ),
         Commands::CalibrateSettings {
             model,
             settings_path,
@@ -828,6 +841,71 @@ pub(crate) fn gen_circuit_settings(
     Ok(String::new())
 }
 
+/// Generate a circuit settings file
+pub(crate) fn gen_random_data(
+    model_path: PathBuf,
+    data_path: PathBuf,
+    variables: Vec<(String, usize)>,
+    seed: u64,
+) -> Result<String, EZKLError> {
+    let mut file = std::fs::File::open(&model_path).map_err(|e| {
+        crate::graph::errors::GraphError::ReadWriteFileError(
+            model_path.display().to_string(),
+            e.to_string(),
+        )
+    })?;
+
+    let (tract_model, _symbol_values) = Model::load_onnx_using_tract(&mut file, &variables)?;
+
+    let input_facts = tract_model
+        .input_outlets()
+        .map_err(|e| EZKLError::from(e.to_string()))?
+        .iter()
+        .map(|&i| tract_model.outlet_fact(i))
+        .collect::<tract_onnx::prelude::TractResult<Vec<_>>>()
+        .map_err(|e| EZKLError::from(e.to_string()))?;
+
+    /// Generates a random tensor of a given size and type.
+    fn random(
+        sizes: &[usize],
+        datum_type: tract_onnx::prelude::DatumType,
+        seed: u64,
+    ) -> TractTensor {
+        use rand::{Rng, SeedableRng};
+        let mut rng = rand::rngs::StdRng::seed_from_u64(seed);
+
+        let mut tensor = TractTensor::zero::<f32>(sizes).unwrap();
+        let slice = tensor.as_slice_mut::<f32>().unwrap();
+        slice.iter_mut().for_each(|x| *x = rng.gen());
+        tensor.cast_to_dt(datum_type).unwrap().into_owned()
+    }
+
+    fn tensor_for_fact(fact: &tract_onnx::prelude::TypedFact, seed: u64) -> TractTensor {
+        if let Some(value) = &fact.konst {
+            return value.clone().into_tensor();
+        }
+
+        random(
+            fact.shape
+                .as_concrete()
+                .expect("Expected concrete shape, found: {fact:?}"),
+            fact.datum_type,
+            seed,
+        )
+    }
+
+    let generated = input_facts
+        .iter()
+        .map(|v| tensor_for_fact(v, seed))
+        .collect_vec();
+
+    let data = GraphData::from_tract_data(&generated)?;
+
+    data.save(data_path)?;
+
+    Ok(String::new())
+}
+
 // not for wasm targets
 pub(crate) fn init_spinner() -> ProgressBar {
     let pb = indicatif::ProgressBar::new_spinner();

src/fieldutils.rs

@@ -5,7 +5,7 @@ use halo2curves::ff::PrimeField;
 /// Integer representation of a PrimeField element.
 pub type IntegerRep = i128;
 
-/// Converts an i64 to a PrimeField element.
+/// Converts an integer rep to a PrimeField element.
 pub fn integer_rep_to_felt<F: PrimeField>(x: IntegerRep) -> F {
     if x >= 0 {
         F::from_u128(x as u128)
@@ -69,7 +69,7 @@ mod test {
     fn felttointegerrep() {
         for x in -(2_i128.pow(16))..(2_i128.pow(16)) {
             let fieldx: F = integer_rep_to_felt::<F>(x);
-            let xf: i128 = felt_to_integer_rep::<F>(fieldx);
+            let xf: IntegerRep = felt_to_integer_rep::<F>(fieldx);
             assert_eq!(x, xf);
         }
     }

src/graph/input.rs

@@ -14,7 +14,6 @@ use pyo3::prelude::*;
 use pyo3::types::PyDict;
 #[cfg(feature = "python-bindings")]
 use pyo3::ToPyObject;
-use serde::ser::SerializeStruct;
 use serde::{Deserialize, Deserializer, Serialize, Serializer};
 use std::io::BufReader;
 use std::io::BufWriter;
@@ -515,7 +514,7 @@ impl<'de> Deserialize<'de> for DataSource {
 
 /// Input to graph as a datasource
 /// Always use JSON serialization for GraphData. Seriously.
-#[derive(Clone, Debug, Deserialize, Default, PartialEq)]
+#[derive(Clone, Debug, Deserialize, Default, PartialEq, Serialize)]
 pub struct GraphData {
     /// Inputs to the model / computational graph (can be empty vectors if inputs are coming from on-chain).
     pub input_data: DataSource,
@@ -557,6 +556,34 @@ impl GraphData {
         Ok(inputs)
     }
 
+    // not wasm
+    #[cfg(all(feature = "ezkl", not(target_arch = "wasm32")))]
+    /// Convert the tract data to tract data
+    pub fn from_tract_data(tensors: &[TractTensor]) -> Result<Self, GraphError> {
+        use tract_onnx::prelude::DatumType;
+
+        let mut input_data = vec![];
+        for tensor in tensors {
+            match tensor.datum_type() {
+                tract_onnx::prelude::DatumType::Bool => {
+                    let tensor = tensor.to_array_view::<bool>()?;
+                    let tensor = tensor.iter().map(|e| FileSourceInner::Bool(*e)).collect();
+                    input_data.push(tensor);
+                }
+                _ => {
+                    let cast_tensor = tensor.cast_to_dt(DatumType::F64)?;
+                    let tensor = cast_tensor.to_array_view::<f64>()?;
+                    let tensor = tensor.iter().map(|e| FileSourceInner::Float(*e)).collect();
+                    input_data.push(tensor);
+                }
+            }
+        }
+        Ok(GraphData {
+            input_data: DataSource::File(input_data),
+            output_data: None,
+        })
+    }
+
     ///
     pub fn new(input_data: DataSource) -> Self {
         GraphData {
@@ -741,18 +768,6 @@ impl ToPyObject for FileSourceInner {
     }
 }
 
-impl Serialize for GraphData {
-    fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>
-    where
-        S: Serializer,
-    {
-        let mut state = serializer.serialize_struct("GraphData", 4)?;
-        state.serialize_field("input_data", &self.input_data)?;
-        state.serialize_field("output_data", &self.output_data)?;
-        state.end()
-    }
-}
-
 #[cfg(test)]
 mod tests {
     use super::*;

src/graph/mod.rs

@@ -280,7 +280,13 @@ impl GraphWitness {
         })?;
 
         let reader = std::io::BufReader::with_capacity(*EZKL_BUF_CAPACITY, file);
-        serde_json::from_reader(reader).map_err(|e| e.into())
+        let witness: GraphWitness =
+            serde_json::from_reader(reader).map_err(Into::<GraphError>::into)?;
+
+        // check versions match
+        crate::check_version_string_matches(witness.version.as_deref().unwrap_or(""));
+
+        Ok(witness)
     }
 
     /// Save the model input to a file
@@ -572,10 +578,14 @@ impl GraphSettings {
         // buf reader
         let reader =
             std::io::BufReader::with_capacity(*EZKL_BUF_CAPACITY, std::fs::File::open(path)?);
-        serde_json::from_reader(reader).map_err(|e| {
+        let settings: GraphSettings = serde_json::from_reader(reader).map_err(|e| {
             error!("failed to load settings file at {}", e);
             std::io::Error::new(std::io::ErrorKind::Other, e)
-        })
+        })?;
+
+        crate::check_version_string_matches(&settings.version);
+
+        Ok(settings)
     }
 
     /// Export the ezkl configuration as json
@@ -697,6 +707,9 @@ impl GraphCircuit {
         let reader = std::io::BufReader::with_capacity(*EZKL_BUF_CAPACITY, f);
         let result: GraphCircuit = bincode::deserialize_from(reader)?;
 
+        // check the versions matche
+        crate::check_version_string_matches(&result.core.settings.version);
+
         Ok(result)
     }
 }

src/graph/model.rs

@@ -621,16 +621,16 @@ impl Model {
     /// * `scale` - The scale to use for quantization.
     /// * `public_params` - Whether to make the params public.
     #[cfg(all(feature = "ezkl", not(target_arch = "wasm32")))]
-    fn load_onnx_using_tract(
+    pub(crate) fn load_onnx_using_tract(
         reader: &mut dyn std::io::Read,
-        run_args: &RunArgs,
+        variables: &[(String, usize)],
     ) -> Result<TractResult, GraphError> {
         use tract_onnx::tract_hir::internal::GenericFactoid;
 
         let mut model = tract_onnx::onnx().model_for_read(reader)?;
 
         let variables: std::collections::HashMap<String, usize> =
-            std::collections::HashMap::from_iter(run_args.variables.clone());
+            std::collections::HashMap::from_iter(variables.iter().map(|(k, v)| (k.clone(), *v)));
 
         for (i, id) in model.clone().inputs.iter().enumerate() {
             let input = model.node_mut(id.node);
@@ -655,7 +655,7 @@ impl Model {
         }
 
         let mut symbol_values = SymbolValues::default();
-        for (symbol, value) in run_args.variables.iter() {
+        for (symbol, value) in variables.iter() {
             let symbol = model.symbols.sym(symbol);
             symbol_values = symbol_values.with(&symbol, *value as i64);
             debug!("set {} to {}", symbol, value);
@@ -683,7 +683,7 @@ impl Model {
     ) -> Result<ParsedNodes, GraphError> {
         let start_time = instant::Instant::now();
 
-        let (model, symbol_values) = Self::load_onnx_using_tract(reader, run_args)?;
+        let (model, symbol_values) = Self::load_onnx_using_tract(reader, &run_args.variables)?;
 
         let scales = VarScales::from_args(run_args);
         let nodes = Self::nodes_from_graph(
@@ -964,7 +964,7 @@ impl Model {
             GraphError::ReadWriteFileError(model_path.display().to_string(), e.to_string())
         })?;
 
-        let (model, _) = Model::load_onnx_using_tract(&mut file, run_args)?;
+        let (model, _) = Model::load_onnx_using_tract(&mut file, &run_args.variables)?;
 
         let datum_types: Vec<DatumType> = model
             .input_outlets()?
@@ -1045,8 +1045,8 @@ impl Model {
         if settings.requires_shuffle() {
             base_gate.configure_shuffles(
                 meta,
-                vars.advices[0..2].try_into()?,
-                vars.advices[3..5].try_into()?,
+                vars.advices[0..3].try_into()?,
+                vars.advices[3..6].try_into()?,
             )?;
         }
 
@@ -1226,6 +1226,7 @@ impl Model {
                 values.iter().map(|v| v.dims()).collect_vec()
             );
 
+            let start = instant::Instant::now();
             match &node {
                 NodeType::Node(n) => {
                     let res = if node.is_constant() && node.num_uses() == 1 {
@@ -1363,6 +1364,7 @@ impl Model {
                     results.insert(*idx, full_results);
                 }
             }
+            debug!("------------ layout of {} took {:?}", idx, start.elapsed());
         }
 
         // we do this so we can support multiple passes of the same model and have deterministic results (Non-assigned inputs etc... etc...)

src/graph/utilities.rs

@@ -142,8 +142,6 @@ use tract_onnx::prelude::SymbolValues;
 pub fn extract_tensor_value(
     input: Arc<tract_onnx::prelude::Tensor>,
 ) -> Result<Tensor<f32>, GraphError> {
-    use maybe_rayon::prelude::{IntoParallelRefIterator, ParallelIterator};
-
     let dt = input.datum_type();
     let dims = input.shape().to_vec();
 
@@ -156,7 +154,7 @@ pub fn extract_tensor_value(
     match dt {
         DatumType::F16 => {
             let vec = input.as_slice::<tract_onnx::prelude::f16>()?.to_vec();
-            let cast: Vec<f32> = vec.par_iter().map(|x| (*x).into()).collect();
+            let cast: Vec<f32> = vec.iter().map(|x| (*x).into()).collect();
             const_value = Tensor::<f32>::new(Some(&cast), &dims)?;
         }
         DatumType::F32 => {
@@ -165,61 +163,61 @@ pub fn extract_tensor_value(
         }
         DatumType::F64 => {
             let vec = input.as_slice::<f64>()?.to_vec();
-            let cast: Vec<f32> = vec.par_iter().map(|x| *x as f32).collect();
+            let cast: Vec<f32> = vec.iter().map(|x| *x as f32).collect();
             const_value = Tensor::<f32>::new(Some(&cast), &dims)?;
         }
         DatumType::I64 => {
             // Generally a shape or hyperparam
             let vec = input.as_slice::<i64>()?.to_vec();
-            let cast: Vec<f32> = vec.par_iter().map(|x| *x as f32).collect();
+            let cast: Vec<f32> = vec.iter().map(|x| *x as f32).collect();
             const_value = Tensor::<f32>::new(Some(&cast), &dims)?;
         }
         DatumType::I32 => {
             // Generally a shape or hyperparam
             let vec = input.as_slice::<i32>()?.to_vec();
-            let cast: Vec<f32> = vec.par_iter().map(|x| *x as f32).collect();
+            let cast: Vec<f32> = vec.iter().map(|x| *x as f32).collect();
             const_value = Tensor::<f32>::new(Some(&cast), &dims)?;
         }
         DatumType::I16 => {
             // Generally a shape or hyperparam
             let vec = input.as_slice::<i16>()?.to_vec();
-            let cast: Vec<f32> = vec.par_iter().map(|x| *x as f32).collect();
+            let cast: Vec<f32> = vec.iter().map(|x| *x as f32).collect();
             const_value = Tensor::<f32>::new(Some(&cast), &dims)?;
         }
         DatumType::I8 => {
             // Generally a shape or hyperparam
             let vec = input.as_slice::<i8>()?.to_vec();
-            let cast: Vec<f32> = vec.par_iter().map(|x| *x as f32).collect();
+            let cast: Vec<f32> = vec.iter().map(|x| *x as f32).collect();
             const_value = Tensor::<f32>::new(Some(&cast), &dims)?;
         }
         DatumType::U8 => {
             // Generally a shape or hyperparam
             let vec = input.as_slice::<u8>()?.to_vec();
-            let cast: Vec<f32> = vec.par_iter().map(|x| *x as f32).collect();
+            let cast: Vec<f32> = vec.iter().map(|x| *x as f32).collect();
             const_value = Tensor::<f32>::new(Some(&cast), &dims)?;
         }
         DatumType::U16 => {
             // Generally a shape or hyperparam
             let vec = input.as_slice::<u16>()?.to_vec();
-            let cast: Vec<f32> = vec.par_iter().map(|x| *x as f32).collect();
+            let cast: Vec<f32> = vec.iter().map(|x| *x as f32).collect();
             const_value = Tensor::<f32>::new(Some(&cast), &dims)?;
         }
         DatumType::U32 => {
             // Generally a shape or hyperparam
             let vec = input.as_slice::<u32>()?.to_vec();
-            let cast: Vec<f32> = vec.par_iter().map(|x| *x as f32).collect();
+            let cast: Vec<f32> = vec.iter().map(|x| *x as f32).collect();
             const_value = Tensor::<f32>::new(Some(&cast), &dims)?;
         }
         DatumType::U64 => {
             // Generally a shape or hyperparam
             let vec = input.as_slice::<u64>()?.to_vec();
-            let cast: Vec<f32> = vec.par_iter().map(|x| *x as f32).collect();
+            let cast: Vec<f32> = vec.iter().map(|x| *x as f32).collect();
             const_value = Tensor::<f32>::new(Some(&cast), &dims)?;
         }
         DatumType::Bool => {
             // Generally a shape or hyperparam
             let vec = input.as_slice::<bool>()?.to_vec();
-            let cast: Vec<f32> = vec.par_iter().map(|x| *x as usize as f32).collect();
+            let cast: Vec<f32> = vec.iter().map(|x| *x as usize as f32).collect();
             const_value = Tensor::<f32>::new(Some(&cast), &dims)?;
         }
         DatumType::TDim => {
@@ -227,7 +225,7 @@ pub fn extract_tensor_value(
             let vec = input.as_slice::<tract_onnx::prelude::TDim>()?.to_vec();
 
             let cast: Result<Vec<f32>, GraphError> = vec
-                .par_iter()
+                .iter()
                 .map(|x| match x.to_i64() {
                     Ok(v) => Ok(v as f32),
                     Err(_) => match x.to_i64() {
@@ -1136,23 +1134,21 @@ pub fn new_op_from_onnx(
                         a: crate::circuit::utils::F32(exponent),
                     })
                 }
-            } else {
-                if let Some(c) = inputs[0].opkind().get_mutable_constant() {
-                    inputs[0].decrement_use();
-                    deleted_indices.push(0);
-                    if c.raw_values.len() > 1 {
-                        unimplemented!("only support scalar base")
-                    }
-
-                    let base = c.raw_values[0];
-
-                    SupportedOp::Nonlinear(LookupOp::Exp {
-                        scale: scale_to_multiplier(input_scales[1]).into(),
-                        base: base.into(),
-                    })
-                } else {
-                    unimplemented!("only support constant base or pow for now")
+            } else if let Some(c) = inputs[0].opkind().get_mutable_constant() {
+                inputs[0].decrement_use();
+                deleted_indices.push(0);
+                if c.raw_values.len() > 1 {
+                    unimplemented!("only support scalar base")
                 }
+
+                let base = c.raw_values[0];
+
+                SupportedOp::Nonlinear(LookupOp::Exp {
+                    scale: scale_to_multiplier(input_scales[1]).into(),
+                    base: base.into(),
+                })
+            } else {
+                unimplemented!("only support constant base or pow for now")
             }
         }
         "Div" => {

src/graph/vars.rs

@@ -435,7 +435,7 @@ impl<F: PrimeField + TensorType + PartialOrd + std::hash::Hash> ModelVars<F> {
             .collect_vec();
 
         if requires_dynamic_lookup || requires_shuffle {
-            let num_cols = if requires_dynamic_lookup { 3 } else { 2 };
+            let num_cols = 3;
             for _ in 0..num_cols {
                 let dynamic_lookup =
                     VarTensor::new_advice(cs, logrows, 1, dynamic_lookup_and_shuffle_size);

src/lib.rs

@@ -420,3 +420,30 @@ where
     let b = s[pos + 2..].parse()?;
     Ok((a, b))
 }
+
+/// Check if the version string matches the artifact version
+/// If the version string does not match the artifact version, log a warning
+pub fn check_version_string_matches(artifact_version: &str) {
+    if artifact_version == "0.0.0"
+        || artifact_version == "source - no compatibility guaranteed"
+        || artifact_version.is_empty()
+    {
+        log::warn!("Artifact version is 0.0.0, skipping version check");
+        return;
+    }
+
+    let version = crate::version();
+
+    if version == "source - no compatibility guaranteed" {
+        log::warn!("Compiled source version is not guaranteed to match artifact version");
+        return;
+    }
+
+    if version != artifact_version {
+        log::warn!(
+            "Version mismatch: CLI version is {} but artifact version is {}",
+            version,
+            artifact_version
+        );
+    }
+}

src/pfsys/mod.rs

@@ -822,6 +822,7 @@ where
     Scheme::Scalar: PrimeField + SerdeObject + FromUniformBytes<64>,
 {
     debug!("loading proving key from {:?}", path);
+    let start = instant::Instant::now();
     let f = File::open(path.clone()).map_err(|e| PfsysError::LoadPk(format!("{}", e)))?;
     let mut reader = BufReader::with_capacity(*EZKL_BUF_CAPACITY, f);
     let pk = ProvingKey::<Scheme::Curve>::read::<_, C>(
@@ -830,7 +831,8 @@ where
         params,
     )
     .map_err(|e| PfsysError::LoadPk(format!("{}", e)))?;
-    info!("loaded proving key ✅");
+    let elapsed = start.elapsed();
+    info!("loaded proving key in {:?}", elapsed);
     Ok(pk)
 }
 

src/tensor/mod.rs

@@ -24,9 +24,6 @@ use std::path::PathBuf;
 pub use val::*;
 pub use var::*;
 
-#[cfg(feature = "metal")]
-use instant::Instant;
-
 use crate::{
     circuit::utils,
     fieldutils::{integer_rep_to_felt, IntegerRep},
@@ -40,8 +37,6 @@ use halo2_proofs::{
     poly::Rotation,
 };
 use itertools::Itertools;
-#[cfg(feature = "metal")]
-use metal::{Device, MTLResourceOptions, MTLSize};
 use std::error::Error;
 use std::fmt::Debug;
 use std::io::Read;
@@ -49,31 +44,6 @@ use std::iter::Iterator;
 use std::ops::{Add, Deref, DerefMut, Div, Mul, Neg, Range, Sub};
 use std::{cmp::max, ops::Rem};
 
-#[cfg(feature = "metal")]
-use std::collections::HashMap;
-
-#[cfg(feature = "metal")]
-const LIB_DATA: &[u8] = include_bytes!("metal/tensor_ops.metallib");
-
-#[cfg(feature = "metal")]
-lazy_static::lazy_static! {
-    static ref DEVICE: Device = Device::system_default().expect("no device found");
-
-    static ref LIB: metal::Library = DEVICE.new_library_with_data(LIB_DATA).unwrap();
-
-    static ref QUEUE: metal::CommandQueue = DEVICE.new_command_queue();
-
-    static ref PIPELINES: HashMap<String, metal::ComputePipelineState> = {
-        let mut map = HashMap::new();
-        for name in ["add", "sub", "mul"] {
-            let function = LIB.get_function(name, None).unwrap();
-            let pipeline = DEVICE.new_compute_pipeline_state_with_function(&function).unwrap();
-            map.insert(name.to_string(), pipeline);
-        }
-        map
-    };
-}
-
 /// The (inner) type of tensor elements.
 pub trait TensorType: Clone + Debug + 'static {
     /// Returns the zero value.
@@ -638,42 +608,44 @@ impl<T: Clone + TensorType> Tensor<T> {
     where
         T: Send + Sync,
     {
-        if indices.is_empty() {
+        // Fast path: empty indices or full tensor slice
+        if indices.is_empty()
+            || indices.iter().map(|x| x.end - x.start).collect::<Vec<_>>() == self.dims
+        {
             return Ok(self.clone());
         }
+
+        // Validate dimensions
         if self.dims.len() < indices.len() {
             return Err(TensorError::DimError(format!(
                 "The dimensionality of the slice {:?} is greater than the tensor's {:?}",
                 indices, self.dims
             )));
-        } else if indices.iter().map(|x| x.end - x.start).collect::<Vec<_>>() == self.dims {
-            // else if slice is the same as dims, return self
-            return Ok(self.clone());
         }
 
-        // if indices weren't specified we fill them in as required
-        let mut full_indices = indices.to_vec();
+        // Pre-allocate the full indices vector with capacity
+        let mut full_indices = Vec::with_capacity(self.dims.len());
+        full_indices.extend_from_slice(indices);
 
-        for i in 0..(self.dims.len() - indices.len()) {
-            full_indices.push(0..self.dims()[indices.len() + i])
-        }
+        // Fill remaining dimensions
+        full_indices.extend((indices.len()..self.dims.len()).map(|i| 0..self.dims[i]));
 
-        let cartesian_coord: Vec<Vec<usize>> = full_indices
+        // Pre-calculate total size and allocate result vector
+        let total_size: usize = full_indices
             .iter()
-            .cloned()
-            .multi_cartesian_product()
-            .collect();
-
-        let res: Vec<T> = cartesian_coord
-            .par_iter()
-            .map(|e| {
-                let index = self.get_index(e);
-                self[index].clone()
-            })
-            .collect();
+            .map(|range| range.end - range.start)
+            .product();
+        let mut res = Vec::with_capacity(total_size);
 
+        // Calculate new dimensions once
         let dims: Vec<usize> = full_indices.iter().map(|e| e.end - e.start).collect();
 
+        // Use iterator directly without collecting into intermediate Vec
+        for coord in full_indices.iter().cloned().multi_cartesian_product() {
+            let index = self.get_index(&coord);
+            res.push(self[index].clone());
+        }
+
         Tensor::new(Some(&res), &dims)
     }
 
@@ -831,7 +803,7 @@ impl<T: Clone + TensorType> Tensor<T> {
         num_repeats: usize,
         initial_offset: usize,
     ) -> Result<Tensor<T>, TensorError> {
-        let mut inner: Vec<T> = vec![];
+        let mut inner: Vec<T> = Vec::with_capacity(self.inner.len());
         let mut offset = initial_offset;
         for (i, elem) in self.inner.clone().into_iter().enumerate() {
             if (i + offset + 1) % n == 0 {
@@ -860,20 +832,22 @@ impl<T: Clone + TensorType> Tensor<T> {
         num_repeats: usize,
         initial_offset: usize,
     ) -> Result<Tensor<T>, TensorError> {
-        let mut inner: Vec<T> = vec![];
-        let mut indices_to_remove = std::collections::HashSet::new();
-        for i in 0..self.inner.len() {
-            if (i + initial_offset + 1) % n == 0 {
-                for j in 1..(1 + num_repeats) {
-                    indices_to_remove.insert(i + j);
-                }
-            }
-        }
+        // Pre-calculate capacity to avoid reallocations
+        let estimated_size = self.inner.len() - (self.inner.len() / n) * num_repeats;
+        let mut inner = Vec::with_capacity(estimated_size);
 
-        let old_inner = self.inner.clone();
-        for (i, elem) in old_inner.into_iter().enumerate() {
-            if !indices_to_remove.contains(&i) {
-                inner.push(elem.clone());
+        // Use iterator directly instead of creating intermediate collections
+        let mut i = 0;
+        while i < self.inner.len() {
+            // Add the current element
+            inner.push(self.inner[i].clone());
+
+            // If this is an nth position (accounting for offset)
+            if (i + initial_offset + 1) % n == 0 {
+                // Skip the next num_repeats elements
+                i += num_repeats + 1;
+            } else {
+                i += 1;
             }
         }
 
@@ -1400,10 +1374,6 @@ impl<T: TensorType + Add<Output = T> + std::marker::Send + std::marker::Sync> Ad
         let lhs = self.expand(&broadcasted_shape).unwrap();
         let rhs = rhs.expand(&broadcasted_shape).unwrap();
 
-        #[cfg(feature = "metal")]
-        let res = metal_tensor_op(&lhs, &rhs, "add");
-
-        #[cfg(not(feature = "metal"))]
         let res = {
             let mut res: Tensor<T> = lhs
                 .par_iter()
@@ -1501,10 +1471,6 @@ impl<T: TensorType + Sub<Output = T> + std::marker::Send + std::marker::Sync> Su
         let lhs = self.expand(&broadcasted_shape).unwrap();
         let rhs = rhs.expand(&broadcasted_shape).unwrap();
 
-        #[cfg(feature = "metal")]
-        let res = metal_tensor_op(&lhs, &rhs, "sub");
-
-        #[cfg(not(feature = "metal"))]
         let res = {
             let mut res: Tensor<T> = lhs
                 .par_iter()
@@ -1572,10 +1538,6 @@ impl<T: TensorType + Mul<Output = T> + std::marker::Send + std::marker::Sync> Mu
         let lhs = self.expand(&broadcasted_shape).unwrap();
         let rhs = rhs.expand(&broadcasted_shape).unwrap();
 
-        #[cfg(feature = "metal")]
-        let res = metal_tensor_op(&lhs, &rhs, "mul");
-
-        #[cfg(not(feature = "metal"))]
         let res = {
             let mut res: Tensor<T> = lhs
                 .par_iter()
@@ -1807,66 +1769,4 @@ mod tests {
         let b = Tensor::<IntegerRep>::new(Some(&[1, 4]), &[2, 1]).unwrap();
         assert_eq!(a.get_slice(&[0..2, 0..1]).unwrap(), b);
     }
-
-    #[test]
-    #[cfg(feature = "metal")]
-    fn tensor_metal_int() {
-        let a = Tensor::<i64>::new(Some(&[1, 2, 3, 4]), &[2, 2]).unwrap();
-        let b = Tensor::<i64>::new(Some(&[1, 2, 3, 4]), &[2, 2]).unwrap();
-        let c = metal_tensor_op(&a, &b, "add");
-        assert_eq!(c, Tensor::new(Some(&[2, 4, 6, 8]), &[2, 2]).unwrap());
-
-        let c = metal_tensor_op(&a, &b, "sub");
-        assert_eq!(c, Tensor::new(Some(&[0, 0, 0, 0]), &[2, 2]).unwrap());
-
-        let c = metal_tensor_op(&a, &b, "mul");
-        assert_eq!(c, Tensor::new(Some(&[1, 4, 9, 16]), &[2, 2]).unwrap());
-    }
-
-    #[test]
-    #[cfg(feature = "metal")]
-    fn tensor_metal_felt() {
-        use halo2curves::bn256::Fr;
-
-        let a = Tensor::<Fr>::new(
-            Some(&[Fr::from(1), Fr::from(2), Fr::from(3), Fr::from(4)]),
-            &[2, 2],
-        )
-        .unwrap();
-        let b = Tensor::<Fr>::new(
-            Some(&[Fr::from(1), Fr::from(2), Fr::from(3), Fr::from(4)]),
-            &[2, 2],
-        )
-        .unwrap();
-
-        let c = metal_tensor_op(&a, &b, "add");
-        assert_eq!(
-            c,
-            Tensor::<Fr>::new(
-                Some(&[Fr::from(2), Fr::from(4), Fr::from(6), Fr::from(8)]),
-                &[2, 2],
-            )
-            .unwrap()
-        );
-
-        let c = metal_tensor_op(&a, &b, "sub");
-        assert_eq!(
-            c,
-            Tensor::<Fr>::new(
-                Some(&[Fr::from(0), Fr::from(0), Fr::from(0), Fr::from(0)]),
-                &[2, 2],
-            )
-            .unwrap()
-        );
-
-        let c = metal_tensor_op(&a, &b, "mul");
-        assert_eq!(
-            c,
-            Tensor::<Fr>::new(
-                Some(&[Fr::from(1), Fr::from(4), Fr::from(9), Fr::from(16)]),
-                &[2, 2],
-            )
-            .unwrap()
-        );
-    }
 }

src/tensor/ops.rs

@@ -27,7 +27,7 @@ pub fn get_rep(
     n: usize,
 ) -> Result<Vec<IntegerRep>, DecompositionError> {
     // check if x is too large
-    if x.abs() > (base.pow(n as u32) as IntegerRep) - 1 {
+    if (*x).abs() > ((base as i128).pow(n as u32)) - 1 {
         return Err(DecompositionError::TooLarge(*x, base, n));
     }
     let mut rep = vec![0; n + 1];
@@ -43,8 +43,8 @@ pub fn get_rep(
     let mut x = x.abs();
     //
     for i in (1..rep.len()).rev() {
-        rep[i] = x % base as i128;
-        x /= base as i128;
+        rep[i] = x % base as IntegerRep;
+        x /= base as IntegerRep;
     }
 
     Ok(rep)
@@ -127,7 +127,7 @@ pub fn decompose(
         .flatten()
         .collect::<Vec<IntegerRep>>();
 
-    let output = Tensor::<i128>::new(Some(&resp), &dims)?;
+    let output = Tensor::<IntegerRep>::new(Some(&resp), &dims)?;
 
     Ok(output)
 }

src/tensor/val.rs

@@ -1,12 +1,12 @@
 use crate::{circuit::region::ConstantsMap, fieldutils::felt_to_integer_rep};
-use maybe_rayon::slice::Iter;
+use maybe_rayon::slice::{Iter, ParallelSlice};
 
 use super::{
     ops::{intercalate_values, pad, resize},
     *,
 };
 use halo2_proofs::{arithmetic::Field, circuit::Cell, plonk::Instance};
-use maybe_rayon::iter::{FilterMap, IntoParallelIterator, ParallelIterator};
+use maybe_rayon::iter::{FilterMap, ParallelIterator};
 
 pub(crate) fn create_constant_tensor<
     F: PrimeField + TensorType + std::marker::Send + std::marker::Sync + PartialOrd,
@@ -455,7 +455,7 @@ impl<F: PrimeField + TensorType + PartialOrd + std::hash::Hash> ValTensor<F> {
         }
     }
 
-    /// Returns the number of constants in the [ValTensor].
+    /// Returns an iterator over the [ValTensor]'s constants.
     pub fn create_constants_map_iterator(
         &self,
     ) -> FilterMap<Iter<'_, ValType<F>>, fn(&ValType<F>) -> Option<(F, ValType<F>)>> {
@@ -473,20 +473,48 @@ impl<F: PrimeField + TensorType + PartialOrd + std::hash::Hash> ValTensor<F> {
         }
     }
 
-    /// Returns the number of constants in the [ValTensor].
+    /// Returns a map of the constants in the [ValTensor].
     pub fn create_constants_map(&self) -> ConstantsMap<F> {
-        match self {
-            ValTensor::Value { inner, .. } => inner
-                .par_iter()
-                .filter_map(|x| {
-                    if let ValType::Constant(v) = x {
-                        Some((*v, x.clone()))
-                    } else {
-                        None
-                    }
-                })
-                .collect(),
-            ValTensor::Instance { .. } => ConstantsMap::new(),
+        let threshold = 1_000_000; // Tuned using the benchmarks
+
+        if self.len() < threshold {
+            match self {
+                ValTensor::Value { inner, .. } => inner
+                    .par_iter()
+                    .filter_map(|x| {
+                        if let ValType::Constant(v) = x {
+                            Some((*v, x.clone()))
+                        } else {
+                            None
+                        }
+                    })
+                    .collect(),
+                ValTensor::Instance { .. } => ConstantsMap::new(),
+            }
+        } else {
+            // Use parallel for larger arrays
+            let num_cores = std::thread::available_parallelism()
+                .map(|n| n.get())
+                .unwrap_or(1);
+            let chunk_size = (self.len() / num_cores).max(100_000);
+
+            match self {
+                ValTensor::Value { inner, .. } => inner
+                    .par_chunks(chunk_size)
+                    .flat_map(|chunk| {
+                        chunk
+                            .par_iter() // Make sure we use par_iter() here
+                            .filter_map(|x| {
+                                if let ValType::Constant(v) = x {
+                                    Some((*v, x.clone()))
+                                } else {
+                                    None
+                                }
+                            })
+                    })
+                    .collect(),
+                ValTensor::Instance { .. } => ConstantsMap::new(),
+            }
         }
     }
 
@@ -878,70 +906,161 @@ impl<F: PrimeField + TensorType + PartialOrd + std::hash::Hash> ValTensor<F> {
 
     /// remove constant zero values constants
     pub fn remove_const_zero_values(&mut self) {
-        match self {
-            ValTensor::Value { inner: v, dims, .. } => {
-                *v = v
-                    .clone()
-                    .into_par_iter()
-                    .filter_map(|e| {
-                        if let ValType::Constant(r) = e {
-                            if r == F::ZERO {
-                                return None;
+        let size_threshold = 1_000_000; // Tuned using the benchmarks
+
+        if self.len() < size_threshold {
+            match self {
+                ValTensor::Value { inner: v, dims, .. } => {
+                    *v = v
+                        .clone()
+                        .into_iter()
+                        .filter_map(|e| {
+                            if let ValType::Constant(r) = e {
+                                if r == F::ZERO {
+                                    return None;
+                                }
+                            } else if let ValType::AssignedConstant(_, r) = e {
+                                if r == F::ZERO {
+                                    return None;
+                                }
                             }
-                        } else if let ValType::AssignedConstant(_, r) = e {
-                            if r == F::ZERO {
-                                return None;
-                            }
-                        }
-                        Some(e)
-                    })
-                    .collect();
-                *dims = v.dims().to_vec();
+                            Some(e)
+                        })
+                        .collect();
+                    *dims = v.dims().to_vec();
+                }
+                ValTensor::Instance { .. } => {}
+            }
+        } else {
+            // Use parallel for larger arrays
+            let num_cores = std::thread::available_parallelism()
+                .map(|n| n.get())
+                .unwrap_or(1);
+            let chunk_size = (self.len() / num_cores).max(100_000);
+
+            match self {
+                ValTensor::Value { inner: v, dims, .. } => {
+                    *v = v
+                        .par_chunks_mut(chunk_size)
+                        .flat_map(|chunk| {
+                            chunk
+                                .par_iter_mut() // Make sure we use par_iter() here
+                                .filter_map(|e| {
+                                    if let ValType::Constant(r) = e {
+                                        if *r == F::ZERO {
+                                            return None;
+                                        }
+                                    } else if let ValType::AssignedConstant(_, r) = e {
+                                        if *r == F::ZERO {
+                                            return None;
+                                        }
+                                    }
+                                    Some(e.clone())
+                                })
+                        })
+                        .collect();
+                    *dims = v.dims().to_vec();
+                }
+                ValTensor::Instance { .. } => {}
             }
-            ValTensor::Instance { .. } => {}
         }
     }
 
-    /// gets constants
+    /// filter constant zero values constants
     pub fn get_const_zero_indices(&self) -> Vec<usize> {
-        match self {
-            ValTensor::Value { inner: v, .. } => v
-                .par_iter()
-                .enumerate()
-                .filter_map(|(i, e)| {
-                    if let ValType::Constant(r) = e {
-                        if *r == F::ZERO {
-                            return Some(i);
+        let size_threshold = 1_000_000; // Tuned using the benchmarks
+
+        if self.len() < size_threshold {
+            // Use single-threaded for smaller arrays
+            match &self {
+                ValTensor::Value { inner: v, .. } => v
+                    .iter()
+                    .enumerate()
+                    .filter_map(|(i, e)| {
+                        match e {
+                            // Combine both match arms to reduce branching
+                            ValType::Constant(r) | ValType::AssignedConstant(_, r) => {
+                                (*r == F::ZERO).then_some(i)
+                            }
+                            _ => None,
                         }
-                    } else if let ValType::AssignedConstant(_, r) = e {
-                        if *r == F::ZERO {
-                            return Some(i);
-                        }
-                    }
-                    None
-                })
-                .collect(),
-            ValTensor::Instance { .. } => vec![],
+                    })
+                    .collect(),
+                ValTensor::Instance { .. } => vec![],
+            }
+        } else {
+            // Use parallel for larger arrays
+            let num_cores = std::thread::available_parallelism()
+                .map(|n| n.get())
+                .unwrap_or(1);
+            let chunk_size = (self.len() / num_cores).max(100_000);
+
+            match &self {
+                ValTensor::Value { inner: v, .. } => v
+                    .par_chunks(chunk_size)
+                    .enumerate()
+                    .flat_map(|(chunk_idx, chunk)| {
+                        chunk
+                            .par_iter() // Make sure we use par_iter() here
+                            .enumerate()
+                            .filter_map(move |(i, e)| match e {
+                                ValType::Constant(r) | ValType::AssignedConstant(_, r) => {
+                                    (*r == F::ZERO).then_some(chunk_idx * chunk_size + i)
+                                }
+                                _ => None,
+                            })
+                    })
+                    .collect::<Vec<_>>(),
+                ValTensor::Instance { .. } => vec![],
+            }
         }
     }
 
-    /// gets constants
+    /// gets constant indices
     pub fn get_const_indices(&self) -> Vec<usize> {
-        match self {
-            ValTensor::Value { inner: v, .. } => v
-                .par_iter()
-                .enumerate()
-                .filter_map(|(i, e)| {
-                    if let ValType::Constant(_) = e {
-                        Some(i)
-                    } else if let ValType::AssignedConstant(_, _) = e {
-                        Some(i)
-                    } else {
-                        None
-                    }
-                })
-                .collect(),
-            ValTensor::Instance { .. } => vec![],
+        let size_threshold = 1_000_000; // Tuned using the benchmarks
+
+        if self.len() < size_threshold {
+            // Use single-threaded for smaller arrays
+            match &self {
+                ValTensor::Value { inner: v, .. } => v
+                    .iter()
+                    .enumerate()
+                    .filter_map(|(i, e)| {
+                        match e {
+                            // Combine both match arms to reduce branching
+                            ValType::Constant(_) | ValType::AssignedConstant(_, _) => Some(i),
+                            _ => None,
+                        }
+                    })
+                    .collect(),
+                ValTensor::Instance { .. } => vec![],
+            }
+        } else {
+            // Use parallel for larger arrays
+            let num_cores = std::thread::available_parallelism()
+                .map(|n| n.get())
+                .unwrap_or(1);
+            let chunk_size = (self.len() / num_cores).max(100_000);
+
+            match &self {
+                ValTensor::Value { inner: v, .. } => v
+                    .par_chunks(chunk_size)
+                    .enumerate()
+                    .flat_map(|(chunk_idx, chunk)| {
+                        chunk
+                            .par_iter() // Make sure we use par_iter() here
+                            .enumerate()
+                            .filter_map(move |(i, e)| match e {
+                                ValType::Constant(_) | ValType::AssignedConstant(_, _) => {
+                                    Some(chunk_idx * chunk_size + i)
+                                }
+                                _ => None,
+                            })
+                    })
+                    .collect::<Vec<_>>(),
+                ValTensor::Instance { .. } => vec![],
+            }
         }
     }
 

src/tensor/var.rs

@@ -494,16 +494,56 @@ impl VarTensor {
         }
     }
 
+    /// Assigns specific values (`ValTensor`) to the columns of the inner tensor but allows for column wrapping for accumulated operations.
+    pub fn assign_with_duplication_unconstrained<
+        F: PrimeField + TensorType + PartialOrd + std::hash::Hash,
+    >(
+        &self,
+        region: &mut Region<F>,
+        offset: usize,
+        values: &ValTensor<F>,
+        constants: &mut ConstantsMap<F>,
+    ) -> Result<(ValTensor<F>, usize), halo2_proofs::plonk::Error> {
+        match values {
+            ValTensor::Instance { .. } => unimplemented!("duplication is not supported on instance columns. increase K if you require more rows."),
+            ValTensor::Value { inner: v, dims , ..} => {
+
+                let duplication_freq = self.block_size();
+
+                let num_repeats = self.num_inner_cols();
+
+                let duplication_offset = offset;
+
+                // duplicates every nth element to adjust for column overflow
+                let v = v.duplicate_every_n(duplication_freq, num_repeats, duplication_offset).unwrap();
+                let mut res: ValTensor<F> = {
+                    v.enum_map(|coord, k| {
+                    let cell = self.assign_value(region, offset, k.clone(), coord, constants)?;
+                    Ok::<_, halo2_proofs::plonk::Error>(cell)
+
+                })?.into()};
+                let total_used_len = res.len();
+                res.remove_every_n(duplication_freq, num_repeats, duplication_offset).unwrap();
+
+                res.reshape(dims).unwrap();
+                res.set_scale(values.scale());
+
+                Ok((res, total_used_len))
+            }
+        }
+    }
+
     /// Assigns specific values (`ValTensor`) to the columns of the inner tensor but allows for column wrapping for accumulated operations.
     /// Duplication occurs by copying the last cell of the column to the first cell next column and creating a copy constraint between the two.
-    pub fn assign_with_duplication<F: PrimeField + TensorType + PartialOrd + std::hash::Hash>(
+    pub fn assign_with_duplication_constrained<
+        F: PrimeField + TensorType + PartialOrd + std::hash::Hash,
+    >(
         &self,
         region: &mut Region<F>,
         row: usize,
         offset: usize,
         values: &ValTensor<F>,
         check_mode: &CheckMode,
-        single_inner_col: bool,
         constants: &mut ConstantsMap<F>,
     ) -> Result<(ValTensor<F>, usize), halo2_proofs::plonk::Error> {
         let mut prev_cell = None;
@@ -512,34 +552,16 @@ impl VarTensor {
             ValTensor::Instance { .. } => unimplemented!("duplication is not supported on instance columns. increase K if you require more rows."),
             ValTensor::Value { inner: v, dims , ..} => {
 
-                let duplication_freq = if single_inner_col {
-                    self.col_size()
-                } else {
-                    self.block_size()
-                };
-
-                let num_repeats = if single_inner_col {
-                    1
-                } else {
-                    self.num_inner_cols()
-                };
-
-                let duplication_offset = if single_inner_col {
-                    row
-                } else {
-                    offset
-                };
+                let duplication_freq = self.col_size();
+                let num_repeats = 1;
+                let duplication_offset = row;
 
                 // duplicates every nth element to adjust for column overflow
                 let v = v.duplicate_every_n(duplication_freq, num_repeats, duplication_offset).unwrap();
-                let mut res: ValTensor<F> = {
+                let mut res: ValTensor<F> =
                     v.enum_map(|coord, k| {
 
-                    let step = if !single_inner_col {
-                        1
-                    } else {
-                        self.num_inner_cols()
-                    };
+                    let step = self.num_inner_cols();
 
                     let (x, y, z) = self.cartesian_coord(offset + coord * step);
                     if matches!(check_mode, CheckMode::SAFE) && coord > 0 && z == 0 && y == 0 {
@@ -549,48 +571,43 @@ impl VarTensor {
 
                     let cell = self.assign_value(region, offset, k.clone(), coord * step, constants)?;
 
-                    if single_inner_col {
-                    if z == 0 {
+                    let at_end_of_column = z == duplication_freq - 1;
+                    let at_beginning_of_column = z == 0;
+
+                    if at_end_of_column {
                         // if we are at the end of the column, we need to copy the cell to the next column
                         prev_cell = Some(cell.clone());
-                    } else if coord > 0 && z == 0 && single_inner_col {
+                    } else if coord > 0 && at_beginning_of_column  {
                         if let Some(prev_cell) = prev_cell.as_ref() {
-                            let cell = cell.cell().ok_or({
+                            let cell = if let Some(cell) = cell.cell() {
+                                cell
+                            } else {
                                 error!("Error getting cell: {:?}", (x,y));
-                                halo2_proofs::plonk::Error::Synthesis})?;
-                            let prev_cell = prev_cell.cell().ok_or({
-                                error!("Error getting cell: {:?}", (x,y));
-                                halo2_proofs::plonk::Error::Synthesis})?;
+                                return Err(halo2_proofs::plonk::Error::Synthesis);
+                            };
+                            let prev_cell = if let Some(prev_cell) = prev_cell.cell() {
+                                prev_cell
+                            } else {
+                                error!("Error getting prev cell: {:?}", (x,y));
+                                return Err(halo2_proofs::plonk::Error::Synthesis);
+                            };
                             region.constrain_equal(prev_cell,cell)?;
                         } else {
-                            error!("Error copy-constraining previous value: {:?}", (x,y));
+                            error!("Previous cell was not set");
                             return Err(halo2_proofs::plonk::Error::Synthesis);
                         }
-                    }}
+                    }
 
                     Ok(cell)
 
-                })?.into()};
+                })?.into();
+
                 let total_used_len = res.len();
                 res.remove_every_n(duplication_freq, num_repeats, duplication_offset).unwrap();
 
                 res.reshape(dims).unwrap();
                 res.set_scale(values.scale());
 
-                if matches!(check_mode, CheckMode::SAFE) {
-                     // during key generation this will be 0 so we use this as a flag to check
-                     // TODO: this isn't very safe and would be better to get the phase directly
-                    let res_evals = res.int_evals().unwrap();
-                    let is_assigned = res_evals
-                    .iter()
-                    .all(|&x| x == 0);
-                    if !is_assigned {
-                        assert_eq!(
-                           values.int_evals().unwrap(),
-                           res_evals
-                    )};
-                }
-
                 Ok((res, total_used_len))
             }
         }

tests/integration_tests.rs

@@ -187,13 +187,14 @@ mod native_tests {
 
     const PF_FAILURE_AGGR: &str = "examples/test_failure_aggr_proof.json";
 
-    const LARGE_TESTS: [&str; 6] = [
+    const LARGE_TESTS: [&str; 7] = [
         "self_attention",
         "nanoGPT",
         "multihead_attention",
         "mobilenet",
         "mnist_gan",
         "smallworm",
+        "fr_age",
     ];
 
     const ACCURACY_CAL_TESTS: [&str; 6] = [
@@ -395,29 +396,29 @@ mod native_tests {
     const TESTS_AGGR: [&str; 3] = ["1l_mlp", "1l_flatten", "1l_average"];
 
     const TESTS_EVM: [&str; 23] = [
-        "1l_mlp",
-        "1l_flatten",
-        "1l_average",
-        "1l_reshape",
-        "1l_sigmoid",
-        "1l_div",
-        "1l_sqrt",
-        "1l_prelu",
-        "1l_var",
-        "1l_leakyrelu",
-        "1l_gelu_noappx",
-        "1l_relu",
-        "1l_tanh",
-        "2l_relu_sigmoid_small",
-        "2l_relu_small",
-        "min",
-        "max",
-        "1l_max_pool",
-        "idolmodel",
-        "1l_identity",
-        "lstm",
-        "rnn",
-        "quantize_dequantize",
+        "1l_mlp",                // 0
+        "1l_flatten",            // 1
+        "1l_average",            // 2
+        "1l_reshape",            // 3
+        "1l_sigmoid",            // 4
+        "1l_div",                // 5
+        "1l_sqrt",               // 6
+        "1l_prelu",              // 7
+        "1l_var",                // 8
+        "1l_leakyrelu",          // 9
+        "1l_gelu_noappx",        // 10
+        "1l_relu",               // 11
+        "1l_tanh",               // 12
+        "2l_relu_sigmoid_small", // 13
+        "2l_relu_small",         // 14
+        "min",                   // 15
+        "max",                   // 16
+        "1l_max_pool",           // 17
+        "idolmodel",             // 18
+        "1l_identity",           // 19
+        "lstm",                  // 20
+        "rnn",                   // 21
+        "quantize_dequantize",   // 22
     ];
 
     const TESTS_EVM_AGGR: [&str; 18] = [
@@ -541,7 +542,7 @@ mod native_tests {
                 crate::native_tests::init_binary();
                 let test_dir = TempDir::new(test).unwrap();
                 let path = test_dir.path().to_str().unwrap(); crate::native_tests::mv_test_(path, test);
-                mock(path, test.to_string(), "public", "fixed", "public", 1, "accuracy", None, 0.0, false);
+                mock(path, test.to_string(), "public", "fixed", "public", 1, "accuracy", None, 0.0, false, None, None);
                 test_dir.close().unwrap();
             }
         });
@@ -606,7 +607,7 @@ mod native_tests {
                 crate::native_tests::init_binary();
                 let test_dir = TempDir::new(test).unwrap();
                 let path = test_dir.path().to_str().unwrap(); crate::native_tests::mv_test_(path, test);
-                mock(path, test.to_string(), "private", "private", "public", 1, "resources", None, 0.0, false);
+                mock(path, test.to_string(), "private", "private", "public", 1, "resources", None, 0.0, false, None, None);
                 test_dir.close().unwrap();
             }
 
@@ -616,7 +617,7 @@ mod native_tests {
                 crate::native_tests::init_binary();
                 let test_dir = TempDir::new(test).unwrap();
                 let path = test_dir.path().to_str().unwrap(); crate::native_tests::mv_test_(path, test);
-                mock(path, test.to_string(), "private", "private", "public", 1, "resources", None, 0.0, true);
+                mock(path, test.to_string(), "private", "private", "public", 1, "resources", None, 0.0, true, Some(8194), Some(4));
                 test_dir.close().unwrap();
             }
 
@@ -627,7 +628,7 @@ mod native_tests {
                 let path = test_dir.path().to_str().unwrap(); crate::native_tests::mv_test_(path, test);
                 // gen random number between 0.0 and 1.0
                 let tolerance = rand::thread_rng().gen_range(0.0..1.0) * 100.0;
-                mock(path, test.to_string(), "private", "private", "public", 1, "resources", None, tolerance, false);
+                mock(path, test.to_string(), "private", "private", "public", 1, "resources", None, tolerance, false, Some(8194), Some(5));
                 test_dir.close().unwrap();
             }
 
@@ -642,7 +643,7 @@ mod native_tests {
                     let path = test_dir.path().to_str().unwrap(); crate::native_tests::mv_test_(path, test);
                     let large_batch_dir = &format!("large_batches_{}", test);
                     crate::native_tests::mk_data_batches_(path, test, &large_batch_dir, 10);
-                    mock(path, large_batch_dir.to_string(), "private", "private", "public", 10, "resources", None, 0.0, false);
+                    mock(path, large_batch_dir.to_string(), "private", "private", "public", 10, "resources", None, 0.0, false, None, None);
                     test_dir.close().unwrap();
                 }
             }
@@ -652,7 +653,7 @@ mod native_tests {
                 crate::native_tests::init_binary();
                 let test_dir = TempDir::new(test).unwrap();
                 let path = test_dir.path().to_str().unwrap(); crate::native_tests::mv_test_(path, test);
-                mock(path, test.to_string(), "public", "private", "private", 1, "resources", None, 0.0, false);
+                mock(path, test.to_string(), "public", "private", "private", 1, "resources", None, 0.0, false, None, None);
                 test_dir.close().unwrap();
             }
 
@@ -661,7 +662,7 @@ mod native_tests {
                 crate::native_tests::init_binary();
                 let test_dir = TempDir::new(test).unwrap();
                 let path = test_dir.path().to_str().unwrap(); crate::native_tests::mv_test_(path, test);
-                mock(path, test.to_string(), "public", "hashed", "private", 1, "resources", None, 0.0, false);
+                mock(path, test.to_string(), "public", "hashed", "private", 1, "resources", None, 0.0, false, None, None);
                 test_dir.close().unwrap();
             }
 
@@ -670,7 +671,7 @@ mod native_tests {
                 crate::native_tests::init_binary();
                 let test_dir = TempDir::new(test).unwrap();
                 let path = test_dir.path().to_str().unwrap(); crate::native_tests::mv_test_(path, test);
-                mock(path, test.to_string(), "fixed", "private", "private", 1, "resources", None, 0.0, false);
+                mock(path, test.to_string(), "fixed", "private", "private", 1, "resources", None, 0.0, false, None, None);
                 test_dir.close().unwrap();
             }
 
@@ -679,7 +680,7 @@ mod native_tests {
                 crate::native_tests::init_binary();
                 let test_dir = TempDir::new(test).unwrap();
                 let path = test_dir.path().to_str().unwrap(); crate::native_tests::mv_test_(path, test);
-                mock(path, test.to_string(), "private", "private", "fixed", 1, "resources", None, 0.0, false);
+                mock(path, test.to_string(), "private", "private", "fixed", 1, "resources", None, 0.0, false, None, None);
                 test_dir.close().unwrap();
             }
 
@@ -688,7 +689,7 @@ mod native_tests {
                 crate::native_tests::init_binary();
                 let test_dir = TempDir::new(test).unwrap();
                 let path = test_dir.path().to_str().unwrap(); crate::native_tests::mv_test_(path, test);
-                mock(path, test.to_string(), "private", "fixed", "private", 1, "resources", None, 0.0, false);
+                mock(path, test.to_string(), "private", "fixed", "private", 1, "resources", None, 0.0, false, None, None);
                 test_dir.close().unwrap();
             }
 
@@ -697,7 +698,7 @@ mod native_tests {
                 crate::native_tests::init_binary();
                 let test_dir = TempDir::new(test).unwrap();
                 let path = test_dir.path().to_str().unwrap(); crate::native_tests::mv_test_(path, test);
-                mock(path, test.to_string(), "hashed", "private", "public", 1, "resources", None, 0.0, false);
+                mock(path, test.to_string(), "hashed", "private", "public", 1, "resources", None, 0.0, false, None, None);
                 test_dir.close().unwrap();
             }
 
@@ -706,7 +707,7 @@ mod native_tests {
                 crate::native_tests::init_binary();
                 let test_dir = TempDir::new(test).unwrap();
                 let path = test_dir.path().to_str().unwrap(); crate::native_tests::mv_test_(path, test);
-                mock(path, test.to_string(), "polycommit", "private", "public", 1, "resources", None, 0.0, false);
+                mock(path, test.to_string(), "polycommit", "private", "public", 1, "resources", None, 0.0, false, None, None);
                 test_dir.close().unwrap();
             }
 
@@ -716,7 +717,7 @@ mod native_tests {
                 crate::native_tests::init_binary();
                 let test_dir = TempDir::new(test).unwrap();
                 let path = test_dir.path().to_str().unwrap(); crate::native_tests::mv_test_(path, test);
-                mock(path, test.to_string(), "private", "hashed", "public", 1, "resources", None, 0.0, false);
+                mock(path, test.to_string(), "private", "hashed", "public", 1, "resources", None, 0.0, false, None, None);
                 test_dir.close().unwrap();
             }
 
@@ -726,7 +727,7 @@ mod native_tests {
                 crate::native_tests::init_binary();
                 let test_dir = TempDir::new(test).unwrap();
                 let path = test_dir.path().to_str().unwrap(); crate::native_tests::mv_test_(path, test);
-                mock(path, test.to_string(), "private", "polycommit", "public", 1, "resources", None, 0.0, false);
+                mock(path, test.to_string(), "private", "polycommit", "public", 1, "resources", None, 0.0, false, None, None);
                 test_dir.close().unwrap();
             }
 
@@ -735,7 +736,7 @@ mod native_tests {
                 crate::native_tests::init_binary();
                 let test_dir = TempDir::new(test).unwrap();
                 let path = test_dir.path().to_str().unwrap(); crate::native_tests::mv_test_(path, test);
-                mock(path, test.to_string(), "public", "private", "hashed", 1, "resources", None, 0.0, false);
+                mock(path, test.to_string(), "public", "private", "hashed", 1, "resources", None, 0.0, false, None, None);
                 test_dir.close().unwrap();
             }
 
@@ -745,7 +746,7 @@ mod native_tests {
                 crate::native_tests::init_binary();
                 let test_dir = TempDir::new(test).unwrap();
                 let path = test_dir.path().to_str().unwrap(); crate::native_tests::mv_test_(path, test);
-                mock(path, test.to_string(), "public", "private", "polycommit", 1, "resources", None, 0.0, false);
+                mock(path, test.to_string(), "public", "private", "polycommit", 1, "resources", None, 0.0, false, None, None);
                 test_dir.close().unwrap();
             }
 
@@ -754,7 +755,7 @@ mod native_tests {
                 crate::native_tests::init_binary();
                 let test_dir = TempDir::new(test).unwrap();
                 let path = test_dir.path().to_str().unwrap(); crate::native_tests::mv_test_(path, test);
-                mock(path, test.to_string(), "public", "fixed", "hashed", 1, "resources", None, 0.0, false);
+                mock(path, test.to_string(), "public", "fixed", "hashed", 1, "resources", None, 0.0, false, None, None);
                 test_dir.close().unwrap();
             }
 
@@ -764,7 +765,7 @@ mod native_tests {
                 crate::native_tests::init_binary();
                 let test_dir = TempDir::new(test).unwrap();
                 let path = test_dir.path().to_str().unwrap(); crate::native_tests::mv_test_(path, test);
-                mock(path, test.to_string(), "public", "polycommit", "hashed", 1, "resources", None, 0.0, false);
+                mock(path, test.to_string(), "public", "polycommit", "hashed", 1, "resources", None, 0.0, false, None, None);
                 test_dir.close().unwrap();
             }
 
@@ -774,7 +775,7 @@ mod native_tests {
                 crate::native_tests::init_binary();
                 let test_dir = TempDir::new(test).unwrap();
                 let path = test_dir.path().to_str().unwrap(); crate::native_tests::mv_test_(path, test);
-                mock(path, test.to_string(), "polycommit", "polycommit", "polycommit", 1, "resources", None, 0.0, false);
+                mock(path, test.to_string(), "polycommit", "polycommit", "polycommit", 1, "resources", None, 0.0, false, None, None);
                 test_dir.close().unwrap();
             }
 
@@ -784,7 +785,7 @@ mod native_tests {
                 crate::native_tests::init_binary();
                 let test_dir = TempDir::new(test).unwrap();
                 let path = test_dir.path().to_str().unwrap(); crate::native_tests::mv_test_(path, test);
-                mock(path, test.to_string(), "hashed", "private", "hashed", 1, "resources", None, 0.0, false);
+                mock(path, test.to_string(), "hashed", "private", "hashed", 1, "resources", None, 0.0, false, None, None);
                 test_dir.close().unwrap();
             }
 
@@ -794,7 +795,7 @@ mod native_tests {
                 let test_dir = TempDir::new(test).unwrap();
                 let path = test_dir.path().to_str().unwrap(); crate::native_tests::mv_test_(path, test);
                 // needs an extra row for the large model
-                mock(path, test.to_string(),"hashed", "hashed", "public", 1, "resources", None, 0.0, false);
+                mock(path, test.to_string(),"hashed", "hashed", "public", 1, "resources", None, 0.0, false, None, None);
                 test_dir.close().unwrap();
             }
 
@@ -804,7 +805,7 @@ mod native_tests {
                 let test_dir = TempDir::new(test).unwrap();
                 let path = test_dir.path().to_str().unwrap(); crate::native_tests::mv_test_(path, test);
                 // needs an extra row for the large model
-                mock(path, test.to_string(),"hashed", "hashed", "hashed", 1, "resources", None, 0.0, false);
+                mock(path, test.to_string(),"hashed", "hashed", "hashed", 1, "resources", None, 0.0, false, None, None);
                 test_dir.close().unwrap();
             }
 
@@ -963,7 +964,7 @@ mod native_tests {
 
             });
 
-            seq!(N in 0..=5 {
+            seq!(N in 0..=6 {
 
             #(#[test_case(LARGE_TESTS[N])])*
             #[ignore]
@@ -981,7 +982,7 @@ mod native_tests {
                 crate::native_tests::init_binary();
                 let test_dir = TempDir::new(test).unwrap();
                 let path = test_dir.path().to_str().unwrap(); crate::native_tests::mv_test_(path, test);
-                mock(path, test.to_string(), "private", "fixed", "public", 1, "resources", None, 0.0, false);
+                mock(path, test.to_string(), "private", "fixed", "public", 1, "resources", None, 0.0, false, None, None);
                 test_dir.close().unwrap();
             }
         });
@@ -1459,6 +1460,8 @@ mod native_tests {
         scales_to_use: Option<Vec<u32>>,
         tolerance: f32,
         bounded_lookup_log: bool,
+        decomp_base: Option<usize>,
+        decomp_legs: Option<usize>,
     ) {
         let mut tolerance = tolerance;
         gen_circuit_settings_and_witness(
@@ -1475,6 +1478,8 @@ mod native_tests {
             Commitments::KZG,
             2,
             bounded_lookup_log,
+            decomp_base,
+            decomp_legs,
         );
 
         if tolerance > 0.0 {
@@ -1616,6 +1621,8 @@ mod native_tests {
         commitment: Commitments,
         lookup_safety_margin: usize,
         bounded_lookup_log: bool,
+        decomp_base: Option<usize>,
+        decomp_legs: Option<usize>,
     ) {
         let mut args = vec![
             "gen-settings".to_string(),
@@ -1634,6 +1641,14 @@ mod native_tests {
             format!("--commitment={}", commitment),
         ];
 
+        if let Some(decomp_base) = decomp_base {
+            args.push(format!("--decomp-base={}", decomp_base));
+        }
+
+        if let Some(decomp_legs) = decomp_legs {
+            args.push(format!("--decomp-legs={}", decomp_legs));
+        }
+
         if bounded_lookup_log {
             args.push("--bounded-log-lookup".to_string());
         }
@@ -1751,6 +1766,8 @@ mod native_tests {
             Commitments::KZG,
             2,
             false,
+            None,
+            None,
         );
 
         println!(
@@ -2035,6 +2052,8 @@ mod native_tests {
             commitment,
             lookup_safety_margin,
             false,
+            None,
+            None,
         );
 
         let settings_path = format!("{}/{}/settings.json", test_dir, example_name);
@@ -2467,6 +2486,8 @@ mod native_tests {
             Commitments::KZG,
             2,
             false,
+            None,
+            None,
         );
 
         let model_path = format!("{}/{}/network.compiled", test_dir, example_name);
@@ -2774,7 +2795,10 @@ mod native_tests {
             "--features",
             "icicle",
         ];
-        #[cfg(not(feature = "icicle"))]
+        #[cfg(feature = "macos-metal")]
+        let args = ["build", "--release", "--bin", "ezkl", "--features", "macos-metal"];
+        // not macos-metal and not icicle
+        #[cfg(all(not(feature = "icicle"), not(feature = "macos-metal")))]
         let args = ["build", "--release", "--bin", "ezkl"];
         #[cfg(not(feature = "mv-lookup"))]
         let args = [

tests/python/binding_tests.py

@@ -873,6 +873,7 @@ def get_examples():
         'linear_regression',
         "mnist_gan",
         "smallworm",
+        "fr_age"
     ]
     examples = []
     for subdir, _, _ in os.walk(os.path.join(examples_path, "onnx")):