mirror of
https://github.com/NVIDIA/nvbench.git
synced 2026-03-14 20:27:24 +00:00
a6df59a9b5
Fixes #95. CPU-only mode is enabled by setting the `is_cpu_only` property while defining a benchmark, e.g. `NVBENCH_BENCH(foo).set_is_cpu_only(true)`. An optional `nvbench::exec_tag::no_gpu` hint can also be passed to `state.exec` to avoid instantiating GPU benchmarking backends. Note that a CUDA compiler and CUDA runtime are always required, even if all benchmarks in a translation unit are CPU-only. Similarly, a new `nvbench::exec_tag::gpu` hint can be used to avoid compiling CPU-only backends for GPU benchmarks.
49 lines
1.6 KiB
CMake
49 lines
1.6 KiB
CMake
set(example_srcs
|
|
auto_throughput.cu
|
|
axes.cu
|
|
custom_criterion.cu
|
|
cpu_only.cu
|
|
enums.cu
|
|
exec_tag_sync.cu
|
|
exec_tag_timer.cu
|
|
skip.cu
|
|
stream.cu
|
|
throughput.cu
|
|
)
|
|
|
|
# Metatarget for all examples:
|
|
add_custom_target(nvbench.example.all)
|
|
add_dependencies(nvbench.all nvbench.example.all)
|
|
|
|
|
|
function (nvbench_add_examples_target target_prefix cuda_std)
|
|
add_custom_target(${target_prefix}.all)
|
|
add_dependencies(nvbench.example.all ${target_prefix}.all)
|
|
|
|
foreach(example_src IN LISTS example_srcs)
|
|
get_filename_component(example_name "${example_src}" NAME_WLE)
|
|
string(PREPEND example_name "${target_prefix}.")
|
|
add_executable(${example_name} "${example_src}")
|
|
nvbench_config_target(${example_name})
|
|
target_include_directories(${example_name} PRIVATE "${CMAKE_CURRENT_LIST_DIR}")
|
|
target_link_libraries(${example_name} PRIVATE nvbench::main)
|
|
set_target_properties(${example_name} PROPERTIES COMPILE_FEATURES cuda_std_${cuda_std})
|
|
add_test(NAME ${example_name}
|
|
COMMAND "$<TARGET_FILE:${example_name}>" --timeout 0.1 --min-time 1e-5
|
|
)
|
|
|
|
# These should not deadlock. If they do, it may be that the CUDA context was created before
|
|
# setting CUDA_MODULE_LOAD=EAGER in main, see NVIDIA/nvbench#136.
|
|
set_tests_properties(${example_name} PROPERTIES
|
|
FAIL_REGULAR_EXPRESSION "Possible Deadlock Detected"
|
|
)
|
|
|
|
add_dependencies(${target_prefix}.all ${example_name})
|
|
endforeach()
|
|
endfunction()
|
|
|
|
|
|
foreach (std IN LISTS NVBench_DETECTED_CUDA_STANDARDS)
|
|
nvbench_add_examples_target(nvbench.example.cpp${std} ${std})
|
|
endforeach()
|