Jonathan R. Madsen
a061b7947f
- hosttrace library automatically collects and merges timestamps for HIP API calls and kernels with the host-side instrumentation - mostly eliminates the need for using external rocprof - added thread_instruction_count in perfetto output - increased hosttrace min_loop_address_range to 512 - disabled instrumenting functions with dynamic callsites by default - miscellaneous cmake updates * roctracer support - fully integrated perfetto + roctracer outputs - thread_instruction_count in perfetto - increased min_loop_address_range to 512 - disabled instrumenting functions with dynamic callsites by default - updated timemory submodule * hosttrace_launch_compiler - support for using an alternative compiler as needed via launch compiler - elfio added as submodule (not currently used) - miscellaneous cmake updates * README update + host/device categories + misc - timemory fix for TIMEMORY_ROCTRACER_ENABLED - transpose fix * papi_tuple_t -> papi_tot_ins - minor fix to Findroctracer.cmake
15 γραμμές
442 B
CMake
15 γραμμές
442 B
CMake
cmake_minimum_required(VERSION 3.13 FATAL_ERROR)
|
|
|
|
project(hosttrace-parallel-overhead
|
|
LANGUAGES CXX)
|
|
|
|
set(CMAKE_BUILD_TYPE "Release")
|
|
find_package(Threads REQUIRED)
|
|
add_executable(parallel-overhead parallel-overhead.cpp)
|
|
target_link_libraries(parallel-overhead Threads::Threads)
|
|
|
|
if(NOT CMAKE_PROJECT_NAME STREQUAL PROJECT_NAME)
|
|
set_target_properties(transpose PROPERTIES
|
|
RUNTIME_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR})
|
|
endif()
|