mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-04 05:31:24 +00:00
[CK] [CK_TILE] Improve build and test time of CI with smart dependency parser (#5249) ## Motivation Existing dependency parser needs full build of tests to determine which tests are affected by code changes in a PR. This still takes 2-4 hours for building the tests which slows down the CI as the number of tests grow. To resolve this issue we implemented a smart dependency parser which uses CMake Configure to parse dependencies and build only the affected test cases. We have ensured that two approaches are available 1) CMake pre-build analysis for each PR to ensure fast build and test. 2) Ninja post-build analysis to enable full build for nightly tests. ## Technical Details ```bash ### 1. Configure the project with CMake cmake -G Ninja -DCMAKE_EXPORT_COMPILE_COMMANDS=ON .. ### 2. Analyze dependencies (no build required!) python3 ../script/dependency-parser/main.py cmake-parse compile_commands.json build.ninja \ --workspace-root .. --output cmake_dependency_mapping.json --parallel 8 ### 3. Find tests affected by changes python3 ../script/dependency-parser/main.py select cmake_dependency_mapping.json origin/develop \ HEAD --test-prefix --output tests_to_run.json ### 4. Build only affected tests ninja $(jq -r '.executables[]' tests_to_run.json | tr '\n' ' ') ### 5. Run affected tests ctest -R "$(jq -r '.regex' tests_to_run.json)" ``` ### Jenkins Integration - Added `buildMode` to jenkinsfile to integrate both `selective` and `full` build methods ### Known Limitations ### 1. Build-Time Generated Headers (HIGH RISK) **Problem:** Files generated during the build process (e.g., via `add_custom_command`) cannot be analyzed before building. **Example:** ```cmake add_custom_command( OUTPUT ${CMAKE_BINARY_DIR}/generated/config.hpp COMMAND generate_config.sh DEPENDS template.hpp.in ) ``` **Impact:** If a source file includes `generated/config.hpp`, the dependency won't be detected until after building. **Mitigation:** - CK analysis shows **no generated headers** currently used - If generated headers are added in the future, they must be built first - Recommendation: Generate headers in CMake configure phase (not build phase) when possible ## Test Plan **1. Modified Files:** ``` include/ck_tile/ops/common.hpp include/ck_tile/ops/gemm.hpp include/ck_tile/ops/gemm/warp/warp_gemm.hpp ``` **2. Compare tests selected between `build.ninja` and `cmake-parse` methods** ## Test Result - 1. The test completed in 5-6 minutes finding about 8000+ executables that should be built. - 2. We selected a commit 5ccc1387ea which resulted in same 7 tests with both legacy and new methods. - PR | Legacy tests | Smart tests | Notes -- | -- | -- | -- 5261 | 453 | 455 | Only 2 tests (test_amdgcn_mma and test_amdgcn_sparse_mma) 5168 | 0 | 0 | Changes in dispatcher only. No CK tests invoked. 5249 | 0 | 0 | Changes to dependency parser. No CK tests invoked 5260 | 0 | 0 | Changes in dispatcher only. No CK tests invoked. 5174 | 1 | 1 | One test from FMHA affected by this PR in both cases 5383 | 0 | 0 | Changes are only in benchmark files. Did not trigger any tests 5445 | 1 | 1 | Changes are only to tests/ck_tile/gemm_streamk. Only triggered one streamk test in both cases. 5454 | 3 | 3 | Both methods identified same test_grouped_conv_bwd tests 5427 | 234 | 234 | Core infrastructure header changes. Detected exactly same tests 5388 | 85 | 85 | modifies warp-level GEMM operations (warp_gemm.hpp, warp_gemm_dispatcher.hpp). Correctly identified all the streamK gemm tests ## Submission Checklist - [x ] Look over the contributing guidelines at https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.
135 lines
4.7 KiB
Bash
Executable File
135 lines
4.7 KiB
Bash
Executable File
#!/bin/bash
|
|
# Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
|
|
# SPDX-License-Identifier: MIT
|
|
|
|
# Smart Build and Test Execution Script
|
|
#
|
|
# This script handles the complete smart-build workflow:
|
|
# 1. Runs smart_build_ci.sh to determine build mode and targets
|
|
# 2. Builds only affected targets (selective mode) or everything (full mode)
|
|
# 3. Runs affected tests using ctest with regex filtering
|
|
# 4. Optionally processes ninja build traces
|
|
#
|
|
# Exit codes:
|
|
# 0 = Success
|
|
# 1 = Build or test failure
|
|
#
|
|
# Environment variables:
|
|
# WORKSPACE_ROOT - Path to workspace root
|
|
# BUILD_DIR - Build directory (defaults to current directory)
|
|
# PARALLEL - Number of parallel jobs for dependency analysis (default: 32)
|
|
# NINJA_JOBS - Number of ninja parallel jobs (required)
|
|
# ARCH_NAME - Architecture name for trace files (required if PROCESS_NINJA_TRACE=true)
|
|
# PROCESS_NINJA_TRACE - Set to "true" to process ninja build traces (default: false)
|
|
# NINJA_FTIME_TRACE - Set to "true" to run ClangBuildAnalyzer (default: false)
|
|
|
|
set -e
|
|
|
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
|
BUILD_DIR="${BUILD_DIR:-$(pwd)}"
|
|
WORKSPACE_ROOT="${WORKSPACE_ROOT:-$(cd ${BUILD_DIR}/.. && pwd)}"
|
|
PARALLEL="${PARALLEL:-32}"
|
|
PROCESS_NINJA_TRACE="${PROCESS_NINJA_TRACE:-false}"
|
|
NINJA_FTIME_TRACE="${NINJA_FTIME_TRACE:-false}"
|
|
|
|
# Validate required parameters
|
|
if [ -z "$NINJA_JOBS" ]; then
|
|
echo "Error: NINJA_JOBS environment variable is required"
|
|
exit 1
|
|
fi
|
|
|
|
if [ "$PROCESS_NINJA_TRACE" = "true" ] && [ -z "$ARCH_NAME" ]; then
|
|
echo "Error: ARCH_NAME environment variable is required when PROCESS_NINJA_TRACE=true"
|
|
exit 1
|
|
fi
|
|
|
|
echo "========================================="
|
|
echo "Smart Build and Test Execution"
|
|
echo "========================================="
|
|
echo "BUILD_DIR: ${BUILD_DIR}"
|
|
echo "WORKSPACE_ROOT: ${WORKSPACE_ROOT}"
|
|
echo "NINJA_JOBS: ${NINJA_JOBS}"
|
|
echo "PROCESS_NINJA_TRACE: ${PROCESS_NINJA_TRACE}"
|
|
echo "NINJA_FTIME_TRACE: ${NINJA_FTIME_TRACE}"
|
|
echo "-----------------------------------------"
|
|
|
|
cd "${BUILD_DIR}"
|
|
|
|
# Step 1: Run smart-build CI script
|
|
echo "🚀 Using Smart Build System"
|
|
echo ""
|
|
|
|
export WORKSPACE_ROOT
|
|
export PARALLEL
|
|
|
|
if ! bash "${SCRIPT_DIR}/smart_build_ci.sh"; then
|
|
# Full build required (exit code 1 from smart_build_ci.sh)
|
|
echo "⚠ Full build mode - building and testing everything"
|
|
ninja -j${NINJA_JOBS} check
|
|
|
|
# Process ninja build trace if requested
|
|
if [ "$PROCESS_NINJA_TRACE" = "true" ]; then
|
|
echo ""
|
|
echo "Processing ninja build trace..."
|
|
python3 ../script/ninja_json_converter.py .ninja_log --legacy-format --output ck_build_trace_${ARCH_NAME}.json
|
|
python3 ../script/parse_ninja_trace.py ck_build_trace_${ARCH_NAME}.json
|
|
|
|
if [ "$NINJA_FTIME_TRACE" = "true" ]; then
|
|
echo "Running ClangBuildAnalyzer..."
|
|
/ClangBuildAnalyzer/build/ClangBuildAnalyzer --all . clang_build.log
|
|
/ClangBuildAnalyzer/build/ClangBuildAnalyzer --analyze clang_build.log > clang_build_analysis_${ARCH_NAME}.log
|
|
fi
|
|
fi
|
|
|
|
exit 0
|
|
fi
|
|
|
|
# Step 2: Selective build mode - read targets
|
|
BUILD_TARGETS=$(cat build_targets.txt)
|
|
|
|
if [ "$BUILD_TARGETS" = "none" ]; then
|
|
echo "✓ No tests affected by changes - skipping build and test execution"
|
|
exit 0
|
|
fi
|
|
|
|
# Step 3: Build only affected targets
|
|
echo "✓ Selective build - building only affected targets"
|
|
echo "Building targets: ${BUILD_TARGETS}"
|
|
ninja -j${NINJA_JOBS} ${BUILD_TARGETS}
|
|
|
|
# Process ninja build trace if requested
|
|
if [ "$PROCESS_NINJA_TRACE" = "true" ]; then
|
|
echo ""
|
|
echo "Processing ninja build trace..."
|
|
python3 ../script/ninja_json_converter.py .ninja_log --legacy-format --output ck_build_trace_${ARCH_NAME}.json
|
|
python3 ../script/parse_ninja_trace.py ck_build_trace_${ARCH_NAME}.json
|
|
|
|
if [ "$NINJA_FTIME_TRACE" = "true" ]; then
|
|
echo "Running ClangBuildAnalyzer..."
|
|
/ClangBuildAnalyzer/build/ClangBuildAnalyzer --all . clang_build.log
|
|
/ClangBuildAnalyzer/build/ClangBuildAnalyzer --analyze clang_build.log > clang_build_analysis_${ARCH_NAME}.log
|
|
fi
|
|
fi
|
|
|
|
# Step 4: Run affected tests using regex_chunks
|
|
echo ""
|
|
echo "Running affected tests..."
|
|
|
|
NUM_CHUNKS=$(jq -r '.regex_chunks | length' tests_to_run.json)
|
|
echo "Running ${NUM_CHUNKS} test chunk(s)"
|
|
|
|
if [ "$NUM_CHUNKS" -eq 1 ]; then
|
|
TEST_REGEX=$(jq -r '.regex_chunks[0]' tests_to_run.json)
|
|
CTEST_PARALLEL_LEVEL=4 ctest --output-on-failure -R "${TEST_REGEX}"
|
|
else
|
|
for ((i=0; i<NUM_CHUNKS; i++)); do
|
|
TEST_REGEX=$(jq -r ".regex_chunks[$i]" tests_to_run.json)
|
|
echo "Running test chunk $((i+1))/${NUM_CHUNKS}"
|
|
CTEST_PARALLEL_LEVEL=4 ctest --output-on-failure -R "${TEST_REGEX}"
|
|
done
|
|
fi
|
|
|
|
echo ""
|
|
echo "✓ Smart build and test execution complete"
|
|
exit 0
|