feat(evm): enable basic performance check in ci

.ci/run_test_suite.sh

@@ -77,6 +77,9 @@ case $TestSuite in
     "evmfallbacksuite")
         CMAKE_OPTIONS="$CMAKE_OPTIONS -DZEN_ENABLE_SPEC_TEST=ON -DZEN_ENABLE_ASSEMBLYSCRIPT_TEST=ON -DZEN_ENABLE_EVM=ON -DZEN_ENABLE_LIBEVM=ON -DZEN_ENABLE_JIT_FALLBACK_TEST=ON"
         ;;
+    "benchmarksuite")
+        CMAKE_OPTIONS="$CMAKE_OPTIONS -DZEN_ENABLE_EVM=ON -DZEN_ENABLE_LIBEVM=ON -DZEN_ENABLE_SINGLEPASS_JIT=OFF -DZEN_ENABLE_MULTIPASS_JIT=ON -DZEN_ENABLE_JIT_PRECOMPILE_FALLBACK=ON"
+        ;;
 esac
 
 case $CPU_EXCEPTION_TYPE in
@@ -97,6 +100,10 @@ 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"
 
@@ -163,5 +170,90 @@ for STACK_TYPE in ${STACK_TYPES[@]}; do
             python3 tools/run_evm_tests.py -r build/dtvm $EXTRA_EXE_OPTIONS
             ./build/evmFallbackExecutionTests
             ;;
+        "benchmarksuite")
+            # Clone evmone and run performance regression check
+            EVMONE_DIR="evmone"
+            if [ ! -d "$EVMONE_DIR" ]; then
+                git clone --depth 1 --recurse-submodules -b for_test https://github.com/DTVMStack/evmone.git $EVMONE_DIR
+            fi
+
+            BENCHMARK_THRESHOLD=${BENCHMARK_THRESHOLD:-0.15}
+            BENCHMARK_MODE=${BENCHMARK_MODE:-multipass}
+            BENCHMARK_SUMMARY_FILE=${BENCHMARK_SUMMARY_FILE:-/tmp/perf_summary.md}
+
+            cp build/lib/* $EVMONE_DIR/
+
+            cd $EVMONE_DIR
+
+            cp ../tools/check_performance_regression.py ./
+
+            if [ ! -f "build/bin/evmone-bench" ]; then
+                cmake -S . -B build -DEVMONE_TESTING=ON -DCMAKE_BUILD_TYPE=Release
+                cmake --build build --parallel -j 16
+            fi
+
+            BASELINE_CACHE=${BENCHMARK_BASELINE_CACHE:-}
+
+            if [ -n "$BASELINE_CACHE" ] && [ -f "$BASELINE_CACHE" ]; then
+                # Cached baseline available -- only run current benchmarks.
+                echo "Using cached baseline: $BASELINE_CACHE"
+                python3 check_performance_regression.py \
+                    --baseline "$BASELINE_CACHE" \
+                    --threshold "$BENCHMARK_THRESHOLD" \
+                    --output-summary "$BENCHMARK_SUMMARY_FILE" \
+                    --lib ./libdtvmapi.so \
+                    --mode "$BENCHMARK_MODE" \
+                    --benchmark-dir test/evm-benchmarks/benchmarks
+            elif [ -n "$BENCHMARK_BASELINE_LIB" ]; then
+                # No cache -- run baseline benchmarks with the pre-built
+                # baseline library, then run current benchmarks and compare.
+                echo "Running baseline benchmarks with library from base branch..."
+                cp "$BENCHMARK_BASELINE_LIB"/libdtvmapi.so ./libdtvmapi.so
+                SAVE_PATH=${BASELINE_CACHE:-/tmp/perf_baseline.json}
+                python3 check_performance_regression.py \
+                    --save-baseline "$SAVE_PATH" \
+                    --lib ./libdtvmapi.so \
+                    --mode "$BENCHMARK_MODE" \
+                    --benchmark-dir test/evm-benchmarks/benchmarks
+
+                echo "Running current benchmarks with PR library..."
+                cp ../build/lib/libdtvmapi.so ./libdtvmapi.so
+                python3 check_performance_regression.py \
+                    --baseline "$SAVE_PATH" \
+                    --threshold "$BENCHMARK_THRESHOLD" \
+                    --output-summary "$BENCHMARK_SUMMARY_FILE" \
+                    --lib ./libdtvmapi.so \
+                    --mode "$BENCHMARK_MODE" \
+                    --benchmark-dir test/evm-benchmarks/benchmarks
+            elif [ -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

@@ -201,3 +201,169 @@ jobs:
           export ENABLE_GAS_METER=true
 
           bash .ci/run_test_suite.sh
+
+  performance_regression_check:
+    name: Performance Regression Check (${{ matrix.mode }})
+    if: github.event_name == 'pull_request'
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: write
+      issues: write
+    strategy:
+      fail-fast: false
+      matrix:
+        mode: [interpreter, multipass]
+    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: ${{ github.workspace }}"
+          git config --global --add safe.directory /__w/DTVM/DTVM
+
+      - name: Code Format Check
+        run: |
+          ./tools/format.sh check
+
+      - name: Restore baseline cache
+        id: baseline-cache
+        uses: actions/cache@v4
+        with:
+          path: /tmp/perf_baseline_${{ matrix.mode }}.json
+          key: perf-baseline-${{ matrix.mode }}-${{ github.event.pull_request.base.sha }}
+
+      - name: Build baseline library (${{ github.base_ref }})
+        if: steps.baseline-cache.outputs.cache-hit != 'true'
+        run: |
+          echo "Building baseline library from 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
+
+          git stash push -u -m "perf-check-stash"
+          git checkout ${{ github.base_ref }}
+
+          cmake -S . -B build \
+            -DCMAKE_BUILD_TYPE=Release \
+            -DZEN_ENABLE_SINGLEPASS_JIT=OFF \
+            -DZEN_ENABLE_MULTIPASS_JIT=ON \
+            -DZEN_ENABLE_EVM=ON \
+            -DZEN_ENABLE_LIBEVM=ON \
+            -DZEN_ENABLE_JIT_PRECOMPILE_FALLBACK=ON \
+            -DZEN_ENABLE_CPU_EXCEPTION=ON \
+            -DZEN_ENABLE_VIRTUAL_STACK=ON
+          cmake --build build -j 16
+
+          mkdir -p /tmp/baseline_lib
+          cp build/lib/* /tmp/baseline_lib/
+
+          rm -rf build
+          git checkout ${{ github.sha }}
+          git stash pop || true
+
+      - 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
+
+          rm -rf build evmone
+
+          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=${{ matrix.mode }}
+          export BENCHMARK_THRESHOLD=0.20
+          export BENCHMARK_BASELINE_CACHE=/tmp/perf_baseline_${{ matrix.mode }}.json
+          export BENCHMARK_BASELINE_LIB=/tmp/baseline_lib
+          export BENCHMARK_SUMMARY_FILE=/tmp/perf_summary_${{ matrix.mode }}.md
+
+          bash .ci/run_test_suite.sh
+        continue-on-error: true
+
+      - name: Write Performance Summary
+        if: always()
+        run: |
+          MODE="${{ matrix.mode }}"
+          OUTCOME="${{ steps.perf-check.outcome }}"
+          SUMMARY_FILE="/tmp/perf_summary_${MODE}.md"
+          if [ "$OUTCOME" = "success" ]; then
+            echo "✅ **Performance Check Passed (${MODE})**" >> $GITHUB_STEP_SUMMARY
+          else
+            echo "⚠️ **Performance Regression Detected (${MODE})**" >> $GITHUB_STEP_SUMMARY
+          fi
+          echo "" >> $GITHUB_STEP_SUMMARY
+          if [ -f "$SUMMARY_FILE" ]; then
+            cat "$SUMMARY_FILE" >> $GITHUB_STEP_SUMMARY
+          else
+            echo "_No benchmark summary available._" >> $GITHUB_STEP_SUMMARY
+          fi
+
+      - name: Save performance artifacts
+        if: always()
+        run: |
+          mkdir -p /tmp/perf-artifacts
+          echo "${{ github.event.pull_request.number }}" > /tmp/perf-artifacts/pr_number
+          echo "${{ steps.perf-check.outcome }}" > /tmp/perf-artifacts/outcome
+          cp "/tmp/perf_summary_${{ matrix.mode }}.md" /tmp/perf-artifacts/summary.md 2>/dev/null || \
+            echo "_No benchmark summary available._" > /tmp/perf-artifacts/summary.md
+
+      - name: Upload performance results
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: perf-results-${{ matrix.mode }}
+          path: /tmp/perf-artifacts/
+          retention-days: 7
+
+      - name: Comment on PR
+        if: always()
+        uses: actions/github-script@v6
+        continue-on-error: true
+        with:
+          script: |
+            const fs = require('fs');
+            const mode = '${{ matrix.mode }}';
+            const passed = '${{ steps.perf-check.outcome }}' === 'success';
+            let summary = '';
+            try {
+              summary = fs.readFileSync(`/tmp/perf_summary_${mode}.md`, 'utf8');
+            } catch (e) {
+              summary = '_No benchmark summary available._';
+            }
+            const icon = passed ? '✅' : '⚠️';
+            const title = passed
+              ? `Performance Check Passed (${mode})`
+              : `Performance Regression Detected (${mode})`;
+            const body = `${icon} **${title}**\n\n${summary}`;
+            try {
+              await github.rest.issues.createComment({
+                issue_number: context.issue.number,
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                body: body
+              });
+            } catch (error) {
+              core.warning(`Could not comment on PR (expected for fork PRs): ${error.message}. Results are available in the job summary above.`);
+            }
+
+      - name: Fail on regression
+        if: steps.perf-check.outcome == 'failure'
+        run: |
+          echo "::error::Performance regression detected in ${{ matrix.mode }} mode. See logs for details."
+          exit 1

.github/workflows/perf_pr_comment.yml

@@ -0,0 +1,96 @@
+name: Post Performance Check Results
+
+on:
+  workflow_run:
+    workflows: ["DTVM-EVM test CI in x86-64"]
+    types:
+      - completed
+
+permissions:
+  pull-requests: write
+  actions: read
+
+jobs:
+  comment:
+    if: github.event.workflow_run.event == 'pull_request'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Download interpreter results
+        uses: actions/download-artifact@v4
+        with:
+          name: perf-results-interpreter
+          path: /tmp/perf-interpreter
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          run-id: ${{ github.event.workflow_run.id }}
+        continue-on-error: true
+
+      - name: Download multipass results
+        uses: actions/download-artifact@v4
+        with:
+          name: perf-results-multipass
+          path: /tmp/perf-multipass
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          run-id: ${{ github.event.workflow_run.id }}
+        continue-on-error: true
+
+      - name: Post PR comment
+        uses: actions/github-script@v6
+        with:
+          script: |
+            const fs = require('fs');
+            let prNumber = null;
+            let body = '<!-- perf-check-results -->\n## ⚡ Performance Regression Check Results\n\n';
+            let hasResults = false;
+
+            for (const mode of ['interpreter', 'multipass']) {
+              const dir = `/tmp/perf-${mode}`;
+              try {
+                if (!prNumber) {
+                  prNumber = parseInt(fs.readFileSync(`${dir}/pr_number`, 'utf8').trim());
+                }
+                const outcome = fs.readFileSync(`${dir}/outcome`, 'utf8').trim();
+                const summary = fs.readFileSync(`${dir}/summary.md`, 'utf8');
+                const passed = outcome === 'success';
+                const icon = passed ? '✅' : '⚠️';
+                const title = passed
+                  ? `Performance Check Passed (${mode})`
+                  : `Performance Regression Detected (${mode})`;
+                body += `### ${icon} ${title}\n\n${summary}\n\n---\n\n`;
+                hasResults = true;
+              } catch (e) {
+                core.info(`No results for ${mode}: ${e.message}`);
+              }
+            }
+
+            if (!prNumber || !hasResults) {
+              core.info('No performance results to post');
+              return;
+            }
+
+            const { data: comments } = await github.rest.issues.listComments({
+              issue_number: prNumber,
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+            });
+
+            const existing = comments.find(c =>
+              c.body && c.body.includes('<!-- perf-check-results -->')
+            );
+
+            if (existing) {
+              await github.rest.issues.updateComment({
+                comment_id: existing.id,
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                body: body.trim()
+              });
+              core.info(`Updated existing comment ${existing.id}`);
+            } else {
+              await github.rest.issues.createComment({
+                issue_number: prNumber,
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                body: body.trim()
+              });
+              core.info('Created new PR comment');
+            }