================ @@ -26,9 +30,23 @@ 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} ${CMAKE_BINARY_DIR}/profiles/ COMMENT "Merging profdata" DEPENDS generate-profraw) + if (CLANG_PGO_TRAINING_DATA_SOURCE_DIR) + llvm_ExternalProject_Add(generate-profraw-external ${CLANG_PGO_TRAINING_DATA_SOURCE_DIR} + USE_TOOLCHAIN EXLUDE_FROM_ALL NO_INSTALL DEPENDS generate-profraw) + add_dependencies(generate-profdata generate-profraw-external) + else() + # Default to compiling a file from clang. This also builds all the + # dependencies needed to build this file, like TableGen. + set(generate_profraw_clang_sema tools/clang/lib/Sema/CMakeFiles/obj.clangSema.dir/Sema.cpp.o) + llvm_ExternalProject_Add(generate-profraw-clang ${CMAKE_CURRENT_SOURCE_DIR}/../../../llvm + USE_TOOLCHAIN EXLUDE_FROM_ALL NO_INSTALL DEPENDS generate-profraw + EXTRA_TARGETS generate_profraw_clang_sema ---------------- tstellar wrote:
> If you're not concerned about the efficacy of the PGO build, I'm not sure why > the existing single hello_world is a bad default. It isn't great but it is > stable and something. If you want something that gives better performance > then you must care about the efficacy, and I think you need to be somewhat > concerned about the stability of those results, otherwise what's the point? I'm concerned about the efficacy if it is 0%, but not really concerned if it bounces around between say 10 and 25 % based on updates to the file we are using to train. I tested with the existing default (hello_world) and I didn't see any performance improvements from that. We also did some manual builds (not using the 2-stage PGO cache) and could not get any performance gains for using a hello world source. How certain are we that hello_world is enough to get performance improvements from PGO? Has anyone tested this recently? I will re-run my tests just to double check. https://github.com/llvm/llvm-project/pull/77347 _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits