Author: Tom Stellard Date: 2024-11-08T15:23:23-08:00 New Revision: 738250989ce516f02f809bdfde474a039c77e81f
URL: https://github.com/llvm/llvm-project/commit/738250989ce516f02f809bdfde474a039c77e81f DIFF: https://github.com/llvm/llvm-project/commit/738250989ce516f02f809bdfde474a039c77e81f.diff LOG: [Clang][perf-training] Do build of libLLVMSupport for perf training (#111625) This adds a build of the libLLVMSupport to the lit suite that is used for generating profile data. This helps to improve both PGO and BOLT optimization of clang over the existing hello world training program. I considered building all of LLVM instead of just libLLVMSupport, but there is only a marginal increase in performance for PGO only builds when training with a build of all of LLVM, and I didn't think it was enough to justify the increased build times given that it is the default configuration. The benchmark[1] I did showed that using libLLVMSupport for training gives a 1.35 +- 0.02 speed up for clang optimized with PGO + BOLT vs just 1.05 +- 0.01 speed up when training with hello world. For comparison, training with a full LLVM build gave a speed up of 1.35 +- 0.1. Raw data: | PGO Training | BOLT Training | Speed Up | Error Range | | ------------ | ------------- | -------- | ----------- | | LLVM Support | LLVM Support | 1.35 | 0.02 | | LLVM All | LLVM All | 1.34 | 0.01 | | LLVM Support | Hello World | 1.29 | 0.02 | | LLVM All | PGO-ONLY | 1.27 | 0.02 | | LLVM Support | PGO-ONLY | 1.22 | 0.02 | | Hello World | Hello World | 1.05 | 0.01 | | Hello World | PGO-ONLY | 1.03 | 0.01 | Time it takes to generate profile data (on a 64-core system): | Training Data | PGO | BOLT | | ------------- | ----- | ----- | | LLVM All | 1090s | 3239s | | LLVM Support | 91s | 655s | | Hello World | 2s | 9s | [1] Benchmark was compiling SemaDecl.cpp Added: clang/utils/perf-training/llvm-support/build.test Modified: clang/utils/perf-training/bolt.lit.cfg clang/utils/perf-training/bolt.lit.site.cfg.in clang/utils/perf-training/lit.cfg clang/utils/perf-training/lit.site.cfg.in Removed: ################################################################################ diff --git a/clang/utils/perf-training/bolt.lit.cfg b/clang/utils/perf-training/bolt.lit.cfg index 0e81a5501e9fcf..1d0cf9a8a17a8e 100644 --- a/clang/utils/perf-training/bolt.lit.cfg +++ b/clang/utils/perf-training/bolt.lit.cfg @@ -49,3 +49,6 @@ config.substitutions.append(("%clang_cpp", f" {config.clang} --driver-mode=g++ " config.substitutions.append(("%clang_skip_driver", config.clang)) config.substitutions.append(("%clang", config.clang)) config.substitutions.append(("%test_root", config.test_exec_root)) +config.substitutions.append(('%cmake_generator', config.cmake_generator)) +config.substitutions.append(('%cmake', config.cmake_exe)) +config.substitutions.append(('%llvm_src_dir', config.llvm_src_dir)) diff --git a/clang/utils/perf-training/bolt.lit.site.cfg.in b/clang/utils/perf-training/bolt.lit.site.cfg.in index 54de12701c1ae9..3de5026e4792ae 100644 --- a/clang/utils/perf-training/bolt.lit.site.cfg.in +++ b/clang/utils/perf-training/bolt.lit.site.cfg.in @@ -11,6 +11,9 @@ config.python_exe = "@Python3_EXECUTABLE@" config.clang_obj_root = path(r"@CLANG_BINARY_DIR@") config.clang_bolt_mode = "@CLANG_BOLT@" config.clang_bolt_name = "@CLANG_BOLT_INSTRUMENTED@" +config.cmake_exe = "@CMAKE_COMMAND@" +config.llvm_src_dir ="@CMAKE_SOURCE_DIR@" +config.cmake_generator ="@CMAKE_GENERATOR@" # Let the main config do the real work. lit_config.load_config(config, "@CLANG_SOURCE_DIR@/utils/perf-training/bolt.lit.cfg") diff --git a/clang/utils/perf-training/lit.cfg b/clang/utils/perf-training/lit.cfg index 0bd06c0d44f650..654961e215da68 100644 --- a/clang/utils/perf-training/lit.cfg +++ b/clang/utils/perf-training/lit.cfg @@ -34,8 +34,11 @@ config.test_format = lit.formats.ShTest(use_lit_shell == "0") config.substitutions.append( ('%clang_cpp_skip_driver', ' %s %s %s ' % (cc1_wrapper, config.clang, sysroot_flags))) config.substitutions.append( ('%clang_cpp', ' %s --driver-mode=g++ %s ' % (config.clang, sysroot_flags))) config.substitutions.append( ('%clang_skip_driver', ' %s %s %s ' % (cc1_wrapper, config.clang, sysroot_flags))) -config.substitutions.append( ('%clang', ' %s %s ' % (config.clang, sysroot_flags) ) ) +config.substitutions.append( ('%clang', '%s %s ' % (config.clang, sysroot_flags) ) ) config.substitutions.append( ('%test_root', config.test_exec_root ) ) +config.substitutions.append( ('%cmake_generator', config.cmake_generator ) ) +config.substitutions.append( ('%cmake', config.cmake_exe ) ) +config.substitutions.append( ('%llvm_src_dir', config.llvm_src_dir ) ) config.environment['LLVM_PROFILE_FILE'] = 'perf-training-%4m.profraw' diff --git a/clang/utils/perf-training/lit.site.cfg.in b/clang/utils/perf-training/lit.site.cfg.in index fae93065a4edf2..9d279d552919ac 100644 --- a/clang/utils/perf-training/lit.site.cfg.in +++ b/clang/utils/perf-training/lit.site.cfg.in @@ -8,6 +8,9 @@ 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.cmake_exe = "@CMAKE_COMMAND@" +config.llvm_src_dir ="@CMAKE_SOURCE_DIR@" +config.cmake_generator ="@CMAKE_GENERATOR@" # 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/llvm-support/build.test b/clang/utils/perf-training/llvm-support/build.test new file mode 100644 index 00000000000000..f29a594c846869 --- /dev/null +++ b/clang/utils/perf-training/llvm-support/build.test @@ -0,0 +1,2 @@ +RUN: %cmake -G %cmake_generator -B %t -S %llvm_src_dir -DCMAKE_C_COMPILER=%clang -DCMAKE_CXX_COMPILER=%clang -DCMAKE_CXX_FLAGS="--driver-mode=g++" -DCMAKE_BUILD_TYPE=Release +RUN: %cmake --build %t -v --target LLVMSupport _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
