llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT--> @llvm/pr-subscribers-clang Author: Amir Ayupov (aaupov) <details> <summary>Changes</summary> Build on Clang-BOLT infrastructure to collect sample profiles for CSSPGO. Add clang/cmake/caches/CSSPGO.cmake to automate CSSPGO Clang build. Differential Revision: https://reviews.llvm.org/D155419 Test Plan: Added CSSPGO.cmake with same use as PGO.cmake, e.g. for bootstrapped ThinLTO+CSSPGO: ``` cmake -B csspgo -S /path/to/llvm-project/llvm \ -DLLVM_ENABLE_LLD=ON -DBOOTSTRAP_LLVM_ENABLE_LLD=ON \ -DBOOTSTRAP_BOOTSTRAP_LLVM_ENABLE_LLD=ON \ -DPGO_INSTRUMENT_LTO=Thin \ -GNinja -C/path/to/llvm-project/clang/cmake/caches/CSSPGO.cmake ninja stage2 ``` --- Full diff: https://github.com/llvm/llvm-project/pull/79942.diff 8 Files Affected: - (modified) clang/CMakeLists.txt (+11-1) - (added) clang/cmake/caches/CSSPGO.cmake (+3) - (modified) clang/utils/perf-training/CMakeLists.txt (+30-2) - (modified) clang/utils/perf-training/lit.cfg (+6) - (modified) clang/utils/perf-training/lit.site.cfg.in (+1) - (modified) clang/utils/perf-training/perf-helper.py (+44-10) - (modified) llvm/CMakeLists.txt (+3) - (modified) llvm/cmake/modules/HandleLLVMOptions.cmake (+25-1) ``````````diff diff --git a/clang/CMakeLists.txt b/clang/CMakeLists.txt index 47fc2e4886cfc..5d16442ac7bc3 100644 --- a/clang/CMakeLists.txt +++ b/clang/CMakeLists.txt @@ -741,11 +741,21 @@ if (CLANG_ENABLE_BOOTSTRAP) if(BOOTSTRAP_LLVM_BUILD_INSTRUMENTED) add_dependencies(clang-bootstrap-deps llvm-profdata) set(PGO_OPT -DLLVM_PROFDATA=${LLVM_RUNTIME_OUTPUT_INTDIR}/llvm-profdata) + string(TOUPPER "${BOOTSTRAP_LLVM_BUILD_INSTRUMENTED}" BOOTSTRAP_LLVM_BUILD_INSTRUMENTED) + if (BOOTSTRAP_LLVM_BUILD_INSTRUMENTED STREQUAL "CSSPGO") + add_dependencies(clang-bootstrap-deps llvm-profgen) + list(APPEND PGO_OPT -DLLVM_PROFGEN=${LLVM_RUNTIME_OUTPUT_INTDIR}/llvm-profgen) + endif() endif() if(LLVM_BUILD_INSTRUMENTED) + string(TOUPPER "${LLVM_BUILD_INSTRUMENTED}" LLVM_BUILD_INSTRUMENTED) add_dependencies(clang-bootstrap-deps generate-profdata) - set(PGO_OPT -DLLVM_PROFDATA_FILE=${CMAKE_CURRENT_BINARY_DIR}/utils/perf-training/clang.profdata) + if (LLVM_BUILD_INSTRUMENTED STREQUAL "CSSPGO") + set(PGO_OPT -DLLVM_SPROFDATA_FILE=${CMAKE_CURRENT_BINARY_DIR}/utils/perf-training/clang.profdata) + else() + set(PGO_OPT -DLLVM_PROFDATA_FILE=${CMAKE_CURRENT_BINARY_DIR}/utils/perf-training/clang.profdata) + endif() # Use the current tools for LTO instead of the instrumented ones list(APPEND _BOOTSTRAP_DEFAULT_PASSTHROUGH CMAKE_CXX_COMPILER diff --git a/clang/cmake/caches/CSSPGO.cmake b/clang/cmake/caches/CSSPGO.cmake new file mode 100644 index 0000000000000..34159068d5ea3 --- /dev/null +++ b/clang/cmake/caches/CSSPGO.cmake @@ -0,0 +1,3 @@ +set(CMAKE_BUILD_TYPE RelWithDebInfo CACHE STRING "") +set(BOOTSTRAP_LLVM_BUILD_INSTRUMENTED "CSSPGO" CACHE STRING "") +include(${CMAKE_CURRENT_LIST_DIR}/PGO.cmake) diff --git a/clang/utils/perf-training/CMakeLists.txt b/clang/utils/perf-training/CMakeLists.txt index 601f40902fa34..489a097cd49c8 100644 --- a/clang/utils/perf-training/CMakeLists.txt +++ b/clang/utils/perf-training/CMakeLists.txt @@ -14,8 +14,33 @@ if(LLVM_BUILD_INSTRUMENTED) DEPENDS clang clear-profraw ${CLANG_PERF_TRAINING_DEPS} ) + add_custom_target(generate-profdata-deps) + string(TOUPPER "${LLVM_BUILD_INSTRUMENTED}" uppercase_LLVM_BUILD_INSTRUMENTED) + if (uppercase_LLVM_BUILD_INSTRUMENTED STREQUAL "CSSPGO") + set(PROFDATA_SAMPLE "--sample") + if(NOT LLVM_PROFGEN) + find_program(LLVM_PROFGEN llvm-profgen) + endif() + + if(NOT LLVM_PROFGEN) + message(STATUS "To enable converting CSSPGO samples LLVM_PROFGEN has to point to llvm-profgen") + endif() + + # Convert perf profiles into profraw + add_custom_target(convert-perf-profraw + COMMAND "${Python3_EXECUTABLE}" + ${CMAKE_CURRENT_SOURCE_DIR}/perf-helper.py perf2prof ${LLVM_PROFGEN} + $<TARGET_FILE:clang> ${CMAKE_CURRENT_BINARY_DIR} + COMMENT "Converting perf profiles into profraw" + DEPENDS generate-profraw) + add_dependencies(generate-profdata-deps convert-perf-profraw) + else() + add_dependencies(generate-profdata-deps generate-profraw) + endif() + add_custom_target(clear-profraw COMMAND "${Python3_EXECUTABLE}" ${CMAKE_CURRENT_SOURCE_DIR}/perf-helper.py clean ${CMAKE_CURRENT_BINARY_DIR} profraw + COMMAND "${Python3_EXECUTABLE}" ${CMAKE_CURRENT_SOURCE_DIR}/perf-helper.py clean ${CMAKE_CURRENT_BINARY_DIR} perf.data COMMENT "Clearing old profraw data") if(NOT LLVM_PROFDATA) @@ -26,9 +51,12 @@ if(LLVM_BUILD_INSTRUMENTED) message(STATUS "To enable merging PGO data LLVM_PROFDATA has to point to llvm-profdata") else() add_custom_target(generate-profdata - COMMAND "${Python3_EXECUTABLE}" ${CMAKE_CURRENT_SOURCE_DIR}/perf-helper.py merge ${LLVM_PROFDATA} ${CMAKE_CURRENT_BINARY_DIR}/clang.profdata ${CMAKE_CURRENT_BINARY_DIR} + COMMAND "${Python3_EXECUTABLE}" + ${CMAKE_CURRENT_SOURCE_DIR}/perf-helper.py merge ${LLVM_PROFDATA} + ${CMAKE_CURRENT_BINARY_DIR}/clang.profdata ${CMAKE_CURRENT_BINARY_DIR} + ${PROFDATA_SAMPLE} COMMENT "Merging profdata" - DEPENDS generate-profraw) + DEPENDS generate-profdata-deps) endif() endif() diff --git a/clang/utils/perf-training/lit.cfg b/clang/utils/perf-training/lit.cfg index 0bd06c0d44f65..c6b54f461f1e2 100644 --- a/clang/utils/perf-training/lit.cfg +++ b/clang/utils/perf-training/lit.cfg @@ -28,6 +28,12 @@ config.name = 'Clang Perf Training' config.suffixes = ['.c', '.cc', '.cpp', '.m', '.mm', '.cu', '.ll', '.cl', '.s', '.S', '.modulemap', '.test'] cc1_wrapper = '%s %s/perf-helper.py cc1' % (config.python_exe, config.perf_helper_dir) +if config.llvm_build_instrumented.upper() == "CSSPGO": + perf_wrapper = "%s %s/perf-helper.py perf --lbr --call-graph --event=br_inst_retired.near_taken:uppp -- " % ( + config.python_exe, + config.perf_helper_dir, + ) + cc1_wrapper = perf_wrapper use_lit_shell = os.environ.get("LIT_USE_INTERNAL_SHELL") config.test_format = lit.formats.ShTest(use_lit_shell == "0") diff --git a/clang/utils/perf-training/lit.site.cfg.in b/clang/utils/perf-training/lit.site.cfg.in index fae93065a4edf..0ae05c10b6d88 100644 --- a/clang/utils/perf-training/lit.site.cfg.in +++ b/clang/utils/perf-training/lit.site.cfg.in @@ -8,6 +8,7 @@ config.test_exec_root = "@CMAKE_CURRENT_BINARY_DIR@" config.test_source_root = "@CLANG_PGO_TRAINING_DATA@" config.target_triple = "@LLVM_TARGET_TRIPLE@" config.python_exe = "@Python3_EXECUTABLE@" +config.llvm_build_instrumented = "@LLVM_BUILD_INSTRUMENTED@" # Let the main config do the real work. lit_config.load_config(config, "@CLANG_SOURCE_DIR@/utils/perf-training/lit.cfg") diff --git a/clang/utils/perf-training/perf-helper.py b/clang/utils/perf-training/perf-helper.py index 959bdba5c98cc..96fe571966b9e 100644 --- a/clang/utils/perf-training/perf-helper.py +++ b/clang/utils/perf-training/perf-helper.py @@ -42,14 +42,20 @@ def clean(args): def merge(args): - if len(args) != 3: - print( - "Usage: %s merge <llvm-profdata> <output> <path>\n" % __file__ - + "\tMerges all profraw files from path into output." - ) - return 1 - cmd = [args[0], "merge", "-o", args[1]] - cmd.extend(findFilesWithExtension(args[2], "profraw")) + parser = argparse.ArgumentParser( + prog="perf-helper merge", + description="Merges all profraw files from path into output" + ) + parser.add_argument("profdata", help="Path to llvm-profdata tool") + parser.add_argument("output", help="Output filename") + parser.add_argument("path", help="Folder containing input profraw files") + parser.add_argument("--sample", action="store_true", help="Sample profile") + opts = parser.parse_args(args) + + cmd = [opts.profdata, "merge", "-o", opts.output] + if opts.sample: + cmd += ["--sample"] + cmd.extend(findFilesWithExtension(opts.path, "profraw")) subprocess.check_call(cmd) return 0 @@ -69,11 +75,19 @@ def merge_fdata(args): def perf(args): parser = argparse.ArgumentParser( - prog="perf-helper perf", description="perf wrapper for BOLT profile collection" + prog="perf-helper perf", + description="perf wrapper for BOLT/CSSPGO profile collection" ) parser.add_argument( "--lbr", action="store_true", help="Use perf with branch stacks" ) + parser.add_argument( + "--call-graph", action="store_true", help="Collect call graph" + ) + parser.add_argument( + "--event", help="PMU event name, defaults to cycles:u", + default="cycles:u" + ) parser.add_argument("cmd", nargs=argparse.REMAINDER, help="") opts = parser.parse_args(args) @@ -82,12 +96,14 @@ def perf(args): perf_args = [ "perf", "record", - "--event=cycles:u", + f"--event={opts.event}", "--freq=max", "--output=%d.perf.data" % os.getpid(), ] if opts.lbr: perf_args += ["--branch-filter=any,u"] + if opts.call_graph: + perf_args += ["-g", "--call-graph=fp"] perf_args.extend(cmd) start_time = time.time() @@ -123,6 +139,23 @@ def perf2bolt(args): return 0 +def perf2prof(args): + parser = argparse.ArgumentParser( + prog="perf-helper perf2prof", + description="perf to CSSPGO prof conversion wrapper", + ) + parser.add_argument("profgen", help="Path to llvm-profgen binary") + parser.add_argument("binary", help="Input binary") + parser.add_argument("path", help="Path containing perf.data files") + opts = parser.parse_args(args) + + profgen_args = [opts.profgen, f"--binary={opts.binary}"] + for filename in findFilesWithExtension(opts.path, "perf.data"): + subprocess.check_call(profgen_args + [f"--perfdata={filename}", + f"--output={filename}.profraw"]) + return 0 + + def dtrace(args): parser = argparse.ArgumentParser( prog="perf-helper dtrace", @@ -565,6 +598,7 @@ def genOrderFile(args): "merge-fdata": merge_fdata, "perf": perf, "perf2bolt": perf2bolt, + "perf2prof": perf2prof, } diff --git a/llvm/CMakeLists.txt b/llvm/CMakeLists.txt index 485c76b8bb936..4421ce7e59b92 100644 --- a/llvm/CMakeLists.txt +++ b/llvm/CMakeLists.txt @@ -879,6 +879,9 @@ set(LLVM_ENABLE_PER_TARGET_RUNTIME_DIR ${LLVM_ENABLE_PER_TARGET_RUNTIME_DIR_defa set(LLVM_PROFDATA_FILE "" CACHE FILEPATH "Profiling data file to use when compiling in order to improve runtime performance.") +set(LLVM_SPROFDATA_FILE "" CACHE FILEPATH + "Sampling profiling data file to use when compiling in order to improve runtime performance.") + if(LLVM_INCLUDE_TESTS) # Lit test suite requires at least python 3.6 set(LLVM_MINIMUM_PYTHON_VERSION 3.6) diff --git a/llvm/cmake/modules/HandleLLVMOptions.cmake b/llvm/cmake/modules/HandleLLVMOptions.cmake index 0699a8586fcc7..3754dff598451 100644 --- a/llvm/cmake/modules/HandleLLVMOptions.cmake +++ b/llvm/cmake/modules/HandleLLVMOptions.cmake @@ -1116,7 +1116,7 @@ endif() option(LLVM_ENABLE_IR_PGO "Build LLVM and tools with IR PGO instrumentation (deprecated)" Off) mark_as_advanced(LLVM_ENABLE_IR_PGO) -set(LLVM_BUILD_INSTRUMENTED OFF CACHE STRING "Build LLVM and tools with PGO instrumentation. May be specified as IR or Frontend") +set(LLVM_BUILD_INSTRUMENTED OFF CACHE STRING "Build LLVM and tools with PGO instrumentation. May be specified as IR, Frontend, CSIR, CSSPGO") set(LLVM_VP_COUNTERS_PER_SITE "1.5" CACHE STRING "Value profile counters to use per site for IR PGO with Clang") mark_as_advanced(LLVM_BUILD_INSTRUMENTED LLVM_VP_COUNTERS_PER_SITE) string(TOUPPER "${LLVM_BUILD_INSTRUMENTED}" uppercase_LLVM_BUILD_INSTRUMENTED) @@ -1149,6 +1149,15 @@ if (LLVM_BUILD_INSTRUMENTED) CMAKE_EXE_LINKER_FLAGS CMAKE_SHARED_LINKER_FLAGS) endif() + elseif(uppercase_LLVM_BUILD_INSTRUMENTED STREQUAL "CSSPGO") + append("-fno-omit-frame-pointer -mno-omit-leaf-frame-pointer -fno-optimize-sibling-calls -fpseudo-probe-for-profiling" + CMAKE_CXX_FLAGS + CMAKE_C_FLAGS) + if(NOT LINKER_IS_LLD_LINK) + append("-fno-omit-frame-pointer -mno-omit-leaf-frame-pointer -fno-optimize-sibling-calls -fpseudo-probe-for-profiling" + CMAKE_EXE_LINKER_FLAGS + CMAKE_SHARED_LINKER_FLAGS) + endif() else() append("-fprofile-instr-generate=\"${LLVM_PROFILE_FILE_PATTERN}\"" CMAKE_CXX_FLAGS @@ -1199,6 +1208,21 @@ if(LLVM_PROFDATA_FILE AND EXISTS ${LLVM_PROFDATA_FILE}) endif() endif() +if(LLVM_SPROFDATA_FILE AND EXISTS ${LLVM_SPROFDATA_FILE}) + if ("${CMAKE_CXX_COMPILER_ID}" MATCHES "Clang" ) + append("-fpseudo-probe-for-profiling -fprofile-sample-use=\"${LLVM_SPROFDATA_FILE}\"" + CMAKE_CXX_FLAGS + CMAKE_C_FLAGS) + if(NOT LINKER_IS_LLD_LINK) + append("-fpseudo-probe-for-profiling -fprofile-sample-use=\"${LLVM_SPROFDATA_FILE}\"" + CMAKE_EXE_LINKER_FLAGS + CMAKE_SHARED_LINKER_FLAGS) + endif() + else() + message(FATAL_ERROR "LLVM_SPROFDATA_FILE can only be specified when compiling with clang") + endif() +endif() + option(LLVM_BUILD_INSTRUMENTED_COVERAGE "Build LLVM and tools with Code Coverage instrumentation" Off) option(LLVM_INDIVIDUAL_TEST_COVERAGE "Emit individual coverage file for each test case." OFF) mark_as_advanced(LLVM_BUILD_INSTRUMENTED_COVERAGE) `````````` </details> https://github.com/llvm/llvm-project/pull/79942 _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits