feat(evm): enable basic performance check in ci

.ci/run_test_suite.sh

@@ -74,6 +74,9 @@ case $TestSuite in
     "evmonetestsuite")
         CMAKE_OPTIONS="$CMAKE_OPTIONS -DZEN_ENABLE_EVM=ON -DZEN_ENABLE_LIBEVM=ON"
         ;;
+    "benchmarksuite")
+        CMAKE_OPTIONS="$CMAKE_OPTIONS -DZEN_ENABLE_EVM=ON -DZEN_ENABLE_LIBEVM=ON -DZEN_ENABLE_SINGLEPASS_JIT=OFF -DZEN_ENABLE_MULTIPASS_JIT=ON"
+        ;;
 esac
 
 case $CPU_EXCEPTION_TYPE in
@@ -94,6 +97,10 @@ if [[ $TestSuite == "evmonetestsuite" ]]; then
     STACK_TYPES=("-DZEN_ENABLE_VIRTUAL_STACK=ON")
 fi
 
+if [[ $TestSuite == "benchmarksuite" ]]; then
+    STACK_TYPES=("-DZEN_ENABLE_VIRTUAL_STACK=ON")
+fi
+
 export PATH=$PATH:$PWD/build
 CMAKE_OPTIONS_ORIGIN="$CMAKE_OPTIONS"
 
@@ -153,5 +160,64 @@ for STACK_TYPE in ${STACK_TYPES[@]}; do
             ./run_unittests.sh ../tests/evmone_unittests/EVMOneMultipassUnitTestsRunList.txt "./libdtvmapi.so,mode=multipass"
             ./run_unittests.sh ../tests/evmone_unittests/EVMOneInterpreterUnitTestsRunList.txt "./libdtvmapi.so,mode=interpreter"
             ;;
+        "benchmarksuite")
+            # Clone evmone and run performance regression check
+            EVMONE_DIR="evmone"
+            if [ ! -d "$EVMONE_DIR" ]; then
+                git clone --depth 1 --recurse-submodules -b for_test https://github.com/DTVMStack/evmone.git $EVMONE_DIR
+            fi
+
+            # Set default values for benchmark
+            BENCHMARK_THRESHOLD=${BENCHMARK_THRESHOLD:-0.10}
+            BENCHMARK_MODE=${BENCHMARK_MODE:-multipass}
+
+            # Copy DTVM library to evmone directory
+            cp build/lib/* $EVMONE_DIR/
+
+            cd $EVMONE_DIR
+
+            # Copy check_performance_regression.py from DTVM repo
+            cp ../tools/check_performance_regression.py ./
+
+            # Build evmone if not already built
+            if [ ! -f "build/bin/evmone-bench" ]; then
+                cmake -S . -B build -DEVMONE_TESTING=ON -DCMAKE_BUILD_TYPE=Release
+                cmake --build build --parallel -j 16
+            fi
+
+            # Default summary output path (can be overridden via env)
+            BENCHMARK_SUMMARY_FILE=${BENCHMARK_SUMMARY_FILE:-/tmp/perf_summary.md}
+
+            # Run performance check based on mode
+            if [ -n "$BENCHMARK_SAVE_BASELINE" ]; then
+                echo "Saving performance baseline..."
+                python3 check_performance_regression.py \
+                    --save-baseline "$BENCHMARK_SAVE_BASELINE" \
+                    --output-summary "$BENCHMARK_SUMMARY_FILE" \
+                    --lib ./libdtvmapi.so \
+                    --mode "$BENCHMARK_MODE" \
+                    --benchmark-dir test/evm-benchmarks/benchmarks
+            elif [ -n "$BENCHMARK_BASELINE_FILE" ]; then
+                echo "Checking performance regression against baseline..."
+                python3 check_performance_regression.py \
+                    --baseline "$BENCHMARK_BASELINE_FILE" \
+                    --threshold "$BENCHMARK_THRESHOLD" \
+                    --output-summary "$BENCHMARK_SUMMARY_FILE" \
+                    --lib ./libdtvmapi.so \
+                    --mode "$BENCHMARK_MODE" \
+                    --benchmark-dir test/evm-benchmarks/benchmarks
+            else
+                echo "Running benchmark suite without comparison..."
+                python3 check_performance_regression.py \
+                    --save-baseline benchmark_results.json \
+                    --output-summary "$BENCHMARK_SUMMARY_FILE" \
+                    --lib ./libdtvmapi.so \
+                    --mode "$BENCHMARK_MODE" \
+                    --benchmark-dir test/evm-benchmarks/benchmarks
+                cat benchmark_results.json
+            fi
+
+            cd ..
+            ;;
     esac
 done

.github/workflows/dtvm_evm_test_x86.yml

@@ -169,3 +169,116 @@ jobs:
           export TestSuite=evmonetestsuite
 
           bash .ci/run_test_suite.sh
+
+  performance_regression_check:
+    name: Performance Regression Check (10% threshold)
+    if: github.event_name == 'pull_request'
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: write
+    container:
+      image: dtvmdev1/dtvm-dev-x64:main
+    steps:
+      - name: Check out code
+        uses: actions/checkout@v3
+        with:
+          submodules: "true"
+          fetch-depth: 0
+
+      - name: Setup git safe directory
+        run: |
+          echo "Configuring git safe directory: ${{ github.workspace }}"
+          git config --global --add safe.directory /__w/DTVM/DTVM
+
+      - name: Code Format Check
+        run: |
+          ./tools/format.sh check
+
+      - name: Build baseline (${{ github.base_ref }})
+        run: |
+          echo "Building baseline on branch: ${{ github.base_ref }}"
+
+          export LLVM_SYS_150_PREFIX=/opt/llvm15
+          export LLVM_DIR=$LLVM_SYS_150_PREFIX/lib/cmake/llvm
+          export PATH=$LLVM_SYS_150_PREFIX/bin:$PATH
+
+          # Save current state (including untracked files)
+          git stash push -u -m "perf-check-stash"
+          git checkout ${{ github.base_ref }}
+
+          # Build baseline
+          export CMAKE_BUILD_TARGET=Release
+          export ENABLE_ASAN=false
+          export RUN_MODE=multipass
+          export ENABLE_LAZY=false
+          export ENABLE_MULTITHREAD=true
+          export TestSuite=benchmarksuite
+          export CPU_EXCEPTION_TYPE='cpu'
+          export BENCHMARK_MODE=interpreter
+          export BENCHMARK_SAVE_BASELINE=/tmp/perf_baseline.json
+
+          bash .ci/run_test_suite.sh
+
+      - name: Build current PR and check regression
+        id: perf-check
+        run: |
+          echo "Building PR branch: ${{ github.sha }}"
+
+          export LLVM_SYS_150_PREFIX=/opt/llvm15
+          export LLVM_DIR=$LLVM_SYS_150_PREFIX/lib/cmake/llvm
+          export PATH=$LLVM_SYS_150_PREFIX/bin:$PATH
+
+          # Switch back to PR branch
+          git checkout ${{ github.sha }}
+          git stash pop || true
+
+          # Clean and rebuild for current PR
+          rm -rf build evmone
+
+          # Build and check
+          export CMAKE_BUILD_TARGET=Release
+          export ENABLE_ASAN=false
+          export RUN_MODE=multipass
+          export ENABLE_LAZY=false
+          export ENABLE_MULTITHREAD=true
+          export TestSuite=benchmarksuite
+          export CPU_EXCEPTION_TYPE='cpu'
+          export BENCHMARK_MODE=interpreter
+          export BENCHMARK_THRESHOLD=0.10
+          export BENCHMARK_BASELINE_FILE=/tmp/perf_baseline.json
+          export BENCHMARK_SUMMARY_FILE=/tmp/perf_summary.md
+
+          bash .ci/run_test_suite.sh
+        continue-on-error: true
+
+      - name: Comment on PR
+        if: always()
+        uses: actions/github-script@v6
+        with:
+          script: |
+            const fs = require('fs');
+            const passed = '${{ steps.perf-check.outcome }}' === 'success';
+            let summary = '';
+            try {
+              summary = fs.readFileSync('/tmp/perf_summary.md', 'utf8');
+            } catch (e) {
+              summary = '_No benchmark summary available._';
+            }
+            const icon = passed ? '✅' : '⚠️';
+            const title = passed
+              ? 'Performance Check Passed'
+              : 'Performance Regression Detected';
+            const body = `${icon} **${title}**\n\n${summary}`;
+            github.rest.issues.createComment({
+              issue_number: context.issue.number,
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              body: body
+            });
+
+      - name: Fail on regression
+        if: steps.perf-check.outcome == 'failure'
+        run: |
+          echo "::error::Performance regression detected. See logs for details."
+          exit 1