[rocprofiler-sdk] Update rocprofiler-sdk CONTRIBUTING.md (#1371)

This commit is contained in:
Jonathan R. Madsen
2025-10-20 21:46:24 -05:00
committed by GitHub
parent 32f9fa6ca5
commit 4cca398b56
23 changed files with 348 additions and 106 deletions
@@ -67,7 +67,7 @@ set_tests_properties(
add_executable(pcs_bench_test)
target_compile_options(pcs_bench_test PRIVATE "-Ofast")
target_compile_options(pcs_bench_test PRIVATE "-O3" "-ffast-math")
target_sources(pcs_bench_test
PRIVATE ${ROCPROFILER_LIB_PC_SAMPLING_PARSER_BENCH_TEST_SOURCES})
target_include_directories(pcs_bench_test PRIVATE ${PCTEST_INCLUDE_DIR})
@@ -79,7 +79,7 @@ target_link_libraries(
GTest::gtest_main)
add_executable(pcs_thread_test)
target_compile_options(pcs_thread_test PRIVATE "-Ofast")
target_compile_options(pcs_thread_test PRIVATE "-O3" "-ffast-math")
target_sources(pcs_thread_test
PRIVATE ${ROCPROFILER_LIB_PC_SAMPLING_PARSER_MULTIGPU_TEST_SOURCES})
@@ -30,7 +30,8 @@
/**
* Benchmarks how fast the parser can process samples on a single threaded case
* Current: 5600X with -Ofast, up to >140 million samples/s or ~9GB/s R/W (18GB/s bidirectional)
* Current: 5600X with -O3 -ffast-math, up to >140 million samples/s or ~9GB/s R/W (18GB/s
* bidirectional)
*/
template <typename PcSamplingRecordT>
static bool
@@ -156,7 +156,8 @@ multithread_queue_hammer(size_t tid, Latch* latch)
/**
* Benchmarks how fast the parser can process samples on a single threaded case
* Current: 5600X with -Ofast, up to >140 million samples/s or ~9GB/s R/W (18GB/s bidirectional)
* Current: 5600X with -O3 -ffast-math, up to >140 million samples/s or ~9GB/s R/W (18GB/s
* bidirectional)
*/
template <typename PcSamplingRecordT>
static std::pair<size_t, size_t>