abe35de43a
* omnitrace-run exe - ensure LD_PRELOAD for libomnitrace-dl.so - convert config options into command-line options * Update timemory submodule - updates to tsettings - updates to argparser * common environment update - throw error if get_env<bool> has empty string * config updates - minor tweaks to categories of settings * core lib update - add argparse for common handling of argument parsers * omnitrace-sample update - fix handling of --trace-file (OMNITRACE_PERFETTO_FILE) * omnitrace-run update - updated to use omnitrace::argparse functions * Tests for omnitrace-run * argparse core update - remove choices for --cpu-events and --gpu-events * remove some debugging prints * fix timemory include in argparse.cpp * always provide --hsa-interrupt option * Update source/lib/core/argparse.cpp - fix pedantic warning * Update testing - remove testing args that may not be there in some builds * roctracer/pthread_create fix - disable roctracer_data when roctracer not enabled * omnitrace-causal tweak * omnitrace-instrument: module_function tweak - allow DEFAULT_MODULE and LIBRARY_MODULE * common environment update - support get_env for enums * core: config update - Add "mode" category to OMNITRACE_MODE * Update timemory submodule - remove debug print statement * omnitrace-sample tweak - change var init * omnitrace-run testing update - use --help instead of -? * core: common.hpp - tweak header include style * core: argparser update - add_ld_preload func - launcher and command member variables in parser_data - support launcher * omnitrace-run update - clean up and reworked * libomnitrace-dl updates - require LD_PRELOAD with binary rewrite - dl::InstrumentMode - dl::get_instrumented() - verify_instrumented_preloaded() - omnitrace_set_instrumented(int) - relocated omnitrace_main from main.c to dl.cpp - omnitrace_set_env does not dlopen libomnitrace - omnitrace_set_main(func_ptr) [internal API] - OMNITRACE_HIDDEN_API -> OMNITRACE_INTERNAL_API * Update testing to new LD_PRELOAD requirements * omnitrace-instrument updates - adhere to LD_PRELOAD requirementsa - invoke omnitrace_set_instrumented - binary rewrite does not instrument main - binary rewrite does not instrument call to omnitrace_init - runtime instr does not instrument main - runtime instr does not instrument call to omnitrace_init * Bump to v1.9.0 - LD_PRELOAD requirement necessitates minor version increment * common: environment - fix ambiguous get_env calls * omnitrace-instrument update - fix issue with temporaries * omnitrace-instrument and libomnitrace-dl updates - runtime instrumentation does not work if libomnitrace-dl is preloaded * libomnitrace-dl and libpyomnitrace updates - define dl::InstrumentMode in dl.hpp - handle instrumentation via setprofile libpyomnitrace - do not push trace in omnitrace_init * omnitrace-instrument and libomnitrace-dl updates - move header to dl subdirectory - omnitrace::omnitrace-headers include omnitrace-dl folder - use InstrumentMode in omnitrace-instrument * Update workflows and scripts - Use omnitrace-run on instrumented exes * Update docs - add omnitrace-run to examples of running binary rewritten exes
1428 lines
44 KiB
CMake
1428 lines
44 KiB
CMake
#
|
|
# omnitrace tests
|
|
#
|
|
include_guard(GLOBAL)
|
|
|
|
include(${CMAKE_CURRENT_LIST_DIR}/omnitrace-testing.cmake)
|
|
|
|
# -------------------------------------------------------------------------------------- #
|
|
#
|
|
# general config file tests
|
|
#
|
|
# -------------------------------------------------------------------------------------- #
|
|
|
|
file(
|
|
WRITE ${CMAKE_CURRENT_BINARY_DIR}/invalid.cfg
|
|
"
|
|
OMNITRACE_CONFIG_FILE =
|
|
FOOBAR = ON
|
|
")
|
|
|
|
if(TARGET parallel-overhead)
|
|
set(_CONFIG_TEST_EXE $<TARGET_FILE:parallel-overhead>)
|
|
else()
|
|
set(_CONFIG_TEST_EXE ls)
|
|
endif()
|
|
|
|
add_test(
|
|
NAME omnitrace-invalid-config
|
|
COMMAND $<TARGET_FILE:omnitrace-instrument> -- ${_CONFIG_TEST_EXE}
|
|
WORKING_DIRECTORY ${PROJECT_BINARY_DIR})
|
|
|
|
set_tests_properties(
|
|
omnitrace-invalid-config
|
|
PROPERTIES ENVIRONMENT
|
|
"OMNITRACE_CONFIG_FILE=${CMAKE_CURRENT_BINARY_DIR}/invalid.cfg" TIMEOUT
|
|
120 LABELS "config" WILL_FAIL ON)
|
|
|
|
add_test(
|
|
NAME omnitrace-missing-config
|
|
COMMAND $<TARGET_FILE:omnitrace-instrument> -- ${_CONFIG_TEST_EXE}
|
|
WORKING_DIRECTORY ${PROJECT_BINARY_DIR})
|
|
|
|
set_tests_properties(
|
|
omnitrace-missing-config
|
|
PROPERTIES ENVIRONMENT
|
|
"OMNITRACE_CONFIG_FILE=${CMAKE_CURRENT_BINARY_DIR}/missing.cfg" TIMEOUT
|
|
120 LABELS "config" WILL_FAIL ON)
|
|
|
|
# -------------------------------------------------------------------------------------- #
|
|
#
|
|
# binary-rewrite and runtime-instrumentation tests
|
|
#
|
|
# -------------------------------------------------------------------------------------- #
|
|
|
|
omnitrace_add_test(
|
|
NAME transpose
|
|
TARGET transpose
|
|
MPI ${TRANSPOSE_USE_MPI}
|
|
GPU ON
|
|
NUM_PROCS ${NUM_PROCS}
|
|
REWRITE_ARGS -e -v 2 --print-instructions -E uniform_int_distribution
|
|
RUNTIME_ARGS
|
|
-e
|
|
-v
|
|
1
|
|
--label
|
|
file
|
|
line
|
|
return
|
|
args
|
|
-E
|
|
uniform_int_distribution
|
|
ENVIRONMENT "${_base_environment};OMNITRACE_CRITICAL_TRACE=ON")
|
|
|
|
omnitrace_add_test(
|
|
SKIP_BASELINE SKIP_SAMPLING SKIP_RUNTIME
|
|
NAME transpose-loops
|
|
TARGET transpose
|
|
LABELS "loops"
|
|
MPI ${TRANSPOSE_USE_MPI}
|
|
GPU ON
|
|
NUM_PROCS ${NUM_PROCS}
|
|
REWRITE_ARGS
|
|
-e
|
|
-v
|
|
2
|
|
--label
|
|
return
|
|
args
|
|
-l
|
|
-i
|
|
8
|
|
-E
|
|
uniform_int_distribution
|
|
RUN_ARGS 2 100 50
|
|
ENVIRONMENT "${_base_environment};OMNITRACE_CRITICAL_TRACE=OFF"
|
|
REWRITE_FAIL_REGEX "0 instrumented loops in procedure transpose")
|
|
|
|
omnitrace_add_test(
|
|
SKIP_PRELOAD SKIP_RUNTIME SKIP_SAMPLING
|
|
NAME rewrite-caller
|
|
TARGET rewrite-caller
|
|
LABELS "caller-include"
|
|
REWRITE_ARGS
|
|
-e
|
|
-i
|
|
256
|
|
--caller-include
|
|
"^inner"
|
|
-v
|
|
2
|
|
--print-instrumented
|
|
functions
|
|
RUN_ARGS 17
|
|
ENVIRONMENT "${_base_environment};OMNITRACE_COUT_OUTPUT=ON"
|
|
BASELINE_PASS_REGEX "number of calls made = 17"
|
|
REWRITE_PASS_REGEX "\\[function\\]\\[Forcing\\] caller-include-regex :: 'outer'"
|
|
REWRITE_RUN_PASS_REGEX ">>> ._outer ([ \\|]+) 17")
|
|
|
|
set(OMNITRACE_ROCM_EVENTS_TEST
|
|
"GRBM_COUNT,GPUBusy,SQ_WAVES,SQ_INSTS_VALU,VALUInsts,TCC_HIT_sum,TA_TA_BUSY[0]:device=0,TA_TA_BUSY[11]:device=0"
|
|
)
|
|
|
|
if(OMNITRACE_USE_ROCPROFILER)
|
|
omnitrace_add_test(
|
|
SKIP_BASELINE SKIP_SAMPLING SKIP_RUNTIME
|
|
NAME transpose-rocprofiler
|
|
TARGET transpose
|
|
LABELS "rocprofiler"
|
|
MPI ${TRANSPOSE_USE_MPI}
|
|
GPU ON
|
|
NUM_PROCS ${NUM_PROCS}
|
|
REWRITE_ARGS -e -v 2 -E uniform_int_distribution
|
|
ENVIRONMENT
|
|
"${_base_environment};OMNITRACE_CRITICAL_TRACE=OFF;OMNITRACE_ROCM_EVENTS=${OMNITRACE_ROCM_EVENTS_TEST}"
|
|
REWRITE_RUN_PASS_REGEX
|
|
"rocprof-device-0-GRBM_COUNT.txt(.*)rocprof-device-0-GPUBusy.txt(.*)rocprof-device-0-SQ_WAVES.txt(.*)rocprof-device-0-SQ_INSTS_VALU.txt(.*)rocprof-device-0-VALUInsts.txt(.*)rocprof-device-0-TCC_HIT_sum.txt(.*)rocprof-device-0-TA_TA_BUSY_0.txt(.*)rocprof-device-0-TA_TA_BUSY_11.txt"
|
|
)
|
|
|
|
omnitrace_add_test(
|
|
SKIP_BASELINE SKIP_SAMPLING SKIP_RUNTIME
|
|
NAME transpose-rocprofiler-no-roctracer
|
|
TARGET transpose
|
|
LABELS "rocprofiler"
|
|
MPI ${TRANSPOSE_USE_MPI}
|
|
GPU ON
|
|
NUM_PROCS ${NUM_PROCS}
|
|
REWRITE_ARGS -e -v 2 -E uniform_int_distribution
|
|
ENVIRONMENT
|
|
"${_base_environment};OMNITRACE_CRITICAL_TRACE=OFF;OMNITRACE_USE_ROCTRACER=OFF;OMNITRACE_ROCM_EVENTS=${OMNITRACE_ROCM_EVENTS_TEST}"
|
|
REWRITE_RUN_PASS_REGEX
|
|
"rocprof-device-0-GRBM_COUNT.txt(.*)rocprof-device-0-GPUBusy.txt(.*)rocprof-device-0-SQ_WAVES.txt(.*)rocprof-device-0-SQ_INSTS_VALU.txt(.*)rocprof-device-0-VALUInsts.txt(.*)rocprof-device-0-TCC_HIT_sum.txt(.*)rocprof-device-0-TA_TA_BUSY_0.txt(.*)rocprof-device-0-TA_TA_BUSY_11.txt"
|
|
REWRITE_RUN_FAIL_REGEX "roctracer.txt")
|
|
endif()
|
|
|
|
omnitrace_add_test(
|
|
NAME parallel-overhead
|
|
TARGET parallel-overhead
|
|
REWRITE_ARGS -e -v 2 --min-instructions=8
|
|
RUNTIME_ARGS
|
|
-e
|
|
-v
|
|
1
|
|
--min-instructions=8
|
|
--label
|
|
file
|
|
line
|
|
return
|
|
args
|
|
RUN_ARGS 10 ${NUM_THREADS} 1000
|
|
ENVIRONMENT "${_base_environment};OMNITRACE_CRITICAL_TRACE=OFF")
|
|
|
|
omnitrace_add_test(
|
|
NAME parallel-overhead-locks
|
|
TARGET parallel-overhead-locks
|
|
LABELS "locks"
|
|
REWRITE_ARGS -e -i 256
|
|
RUNTIME_ARGS -e -i 256
|
|
RUN_ARGS 30 4 1000
|
|
ENVIRONMENT
|
|
"${_lock_environment};OMNITRACE_USE_TIMEMORY=ON;OMNITRACE_USE_PERFETTO=ON;OMNITRACE_COLLAPSE_THREADS=OFF;OMNITRACE_SAMPLING_REALTIME=ON;OMNITRACE_SAMPLING_REALTIME_FREQ=10;OMNITRACE_SAMPLING_REALTIME_TIDS=0;OMNITRACE_SAMPLING_KEEP_INTERNAL=OFF"
|
|
REWRITE_RUN_PASS_REGEX
|
|
"wall_clock .*\\|_pthread_create .* 4 .*\\|_pthread_mutex_lock .* 1000 .*\\|_pthread_mutex_unlock .* 1000 .*\\|_pthread_mutex_lock .* 1000 .*\\|_pthread_mutex_unlock .* 1000 .*\\|_pthread_mutex_lock .* 1000 .*\\|_pthread_mutex_unlock .* 1000 .*\\|_pthread_mutex_lock .* 1000 .*\\|_pthread_mutex_unlock .* 1000"
|
|
RUNTIME_PASS_REGEX
|
|
"wall_clock .*\\|_pthread_create .* 4 .*\\|_pthread_mutex_lock .* 1000 .*\\|_pthread_mutex_unlock .* 1000 .*\\|_pthread_mutex_lock .* 1000 .*\\|_pthread_mutex_unlock .* 1000 .*\\|_pthread_mutex_lock .* 1000 .*\\|_pthread_mutex_unlock .* 1000 .*\\|_pthread_mutex_lock .* 1000 .*\\|_pthread_mutex_unlock .* 1000"
|
|
)
|
|
|
|
omnitrace_add_test(
|
|
SKIP_RUNTIME SKIP_SAMPLING
|
|
NAME parallel-overhead-locks-timemory
|
|
TARGET parallel-overhead-locks
|
|
LABELS "locks"
|
|
REWRITE_ARGS -e -v 2 --min-instructions=32 --dyninst-options InstrStackFrames SaveFPR
|
|
TrampRecursive
|
|
RUN_ARGS 10 4 1000
|
|
ENVIRONMENT
|
|
"${_lock_environment};OMNITRACE_FLAT_PROFILE=ON;OMNITRACE_USE_TIMEMORY=ON;OMNITRACE_USE_PERFETTO=OFF;OMNITRACE_SAMPLING_KEEP_INTERNAL=OFF"
|
|
REWRITE_RUN_PASS_REGEX
|
|
"start_thread (.*) 4 (.*) pthread_mutex_lock (.*) 4000 (.*) pthread_mutex_unlock (.*) 4000"
|
|
)
|
|
|
|
omnitrace_add_test(
|
|
SKIP_BASELINE SKIP_RUNTIME SKIP_SAMPLING
|
|
NAME parallel-overhead-locks-perfetto
|
|
TARGET parallel-overhead-locks
|
|
LABELS "locks"
|
|
REWRITE_ARGS -e -v 2 --min-instructions=8
|
|
RUN_ARGS 10 4 1000
|
|
ENVIRONMENT
|
|
"${_lock_environment};OMNITRACE_FLAT_PROFILE=ON;OMNITRACE_USE_TIMEMORY=OFF;OMNITRACE_USE_PERFETTO=ON;OMNITRACE_SAMPLING_KEEP_INTERNAL=OFF"
|
|
)
|
|
|
|
omnitrace_add_test(
|
|
NAME user-api
|
|
TARGET user-api
|
|
LABELS "loops"
|
|
REWRITE_ARGS -e -v 2 -l --min-instructions=8 -E custom_push_region
|
|
RUNTIME_ARGS
|
|
-e
|
|
-v
|
|
1
|
|
-l
|
|
--min-instructions=8
|
|
-E
|
|
custom_push_region
|
|
--label
|
|
file
|
|
line
|
|
return
|
|
args
|
|
RUN_ARGS 10 ${NUM_THREADS} 1000
|
|
ENVIRONMENT "${_base_environment};OMNITRACE_CRITICAL_TRACE=OFF"
|
|
REWRITE_RUN_PASS_REGEX "Pushing custom region :: run.10. x 1000"
|
|
RUNTIME_PASS_REGEX "Pushing custom region :: run.10. x 1000"
|
|
PRELOAD_PASS_REGEX "Pushing custom region :: run.10. x 1000"
|
|
BASELINE_FAIL_REGEX "Pushing custom region"
|
|
REWRITE_FAIL_REGEX "0 instrumented loops in procedure")
|
|
|
|
if(OMNITRACE_USE_MPI OR OMNITRACE_USE_MPI_HEADERS)
|
|
omnitrace_add_test(
|
|
SKIP_RUNTIME
|
|
NAME "mpi"
|
|
TARGET mpi-example
|
|
MPI ON
|
|
NUM_PROCS 4
|
|
REWRITE_ARGS
|
|
-e
|
|
-v
|
|
2
|
|
--label
|
|
file
|
|
line
|
|
return
|
|
args
|
|
--min-instructions
|
|
0
|
|
ENVIRONMENT "${_base_environment};OMNITRACE_VERBOSE=1"
|
|
REWRITE_RUN_PASS_REGEX
|
|
"(/[A-Za-z-]+/perfetto-trace-0.proto).*(/[A-Za-z-]+/wall_clock-0.txt')"
|
|
REWRITE_RUN_FAIL_REGEX
|
|
"(perfetto-trace|trip_count|sampling_percent|sampling_cpu_clock|sampling_wall_clock|wall_clock)-[0-9][0-9]+.(json|txt|proto)"
|
|
)
|
|
|
|
omnitrace_add_test(
|
|
SKIP_RUNTIME SKIP_SAMPLING
|
|
NAME "mpi-flat-mpip"
|
|
TARGET mpi-example
|
|
MPI ON
|
|
NUM_PROCS 4
|
|
LABELS "mpip"
|
|
REWRITE_ARGS
|
|
-e
|
|
-v
|
|
2
|
|
--label
|
|
file
|
|
line
|
|
args
|
|
--min-instructions
|
|
0
|
|
ENVIRONMENT
|
|
"${_flat_environment};OMNITRACE_USE_SAMPLING=OFF;OMNITRACE_STRICT_CONFIG=OFF;OMNITRACE_USE_MPIP=ON"
|
|
REWRITE_RUN_PASS_REGEX
|
|
">>> mpi-flat-mpip.inst(.*\n.*)>>> MPI_Init_thread(.*\n.*)>>> pthread_create(.*\n.*)>>> MPI_Comm_size(.*\n.*)>>> MPI_Comm_rank(.*\n.*)>>> MPI_Barrier(.*\n.*)>>> MPI_Alltoall"
|
|
)
|
|
|
|
omnitrace_add_test(
|
|
SKIP_RUNTIME SKIP_SAMPLING
|
|
NAME "mpi-flat"
|
|
TARGET mpi-example
|
|
MPI ON
|
|
NUM_PROCS 4
|
|
LABELS "mpip"
|
|
REWRITE_ARGS
|
|
-e
|
|
-v
|
|
2
|
|
--label
|
|
file
|
|
line
|
|
args
|
|
--min-instructions
|
|
0
|
|
ENVIRONMENT "${_flat_environment};OMNITRACE_USE_SAMPLING=OFF"
|
|
REWRITE_RUN_PASS_REGEX
|
|
">>> mpi-flat.inst(.*\n.*)>>> MPI_Init_thread(.*\n.*)>>> pthread_create(.*\n.*)>>> MPI_Comm_size(.*\n.*)>>> MPI_Comm_rank(.*\n.*)>>> MPI_Barrier(.*\n.*)>>> MPI_Alltoall"
|
|
)
|
|
|
|
set(_mpip_environment
|
|
"OMNITRACE_USE_PERFETTO=ON"
|
|
"OMNITRACE_USE_TIMEMORY=ON"
|
|
"OMNITRACE_USE_SAMPLING=OFF"
|
|
"OMNITRACE_USE_PROCESS_SAMPLING=OFF"
|
|
"OMNITRACE_TIME_OUTPUT=OFF"
|
|
"OMNITRACE_FILE_OUTPUT=ON"
|
|
"OMNITRACE_USE_MPIP=ON"
|
|
"OMNITRACE_DEBUG=OFF"
|
|
"OMNITRACE_VERBOSE=2"
|
|
"OMNITRACE_DL_VERBOSE=2"
|
|
"${_test_openmp_env}"
|
|
"${_test_library_path}")
|
|
|
|
set(_mpip_all2all_environment
|
|
"OMNITRACE_USE_PERFETTO=ON"
|
|
"OMNITRACE_USE_TIMEMORY=ON"
|
|
"OMNITRACE_USE_SAMPLING=OFF"
|
|
"OMNITRACE_USE_PROCESS_SAMPLING=OFF"
|
|
"OMNITRACE_TIME_OUTPUT=OFF"
|
|
"OMNITRACE_FILE_OUTPUT=ON"
|
|
"OMNITRACE_USE_MPIP=ON"
|
|
"OMNITRACE_DEBUG=ON"
|
|
"OMNITRACE_VERBOSE=3"
|
|
"OMNITRACE_DL_VERBOSE=3"
|
|
"${_test_openmp_env}"
|
|
"${_test_library_path}")
|
|
|
|
foreach(_EXAMPLE all2all allgather allreduce bcast reduce scatter-gather send-recv)
|
|
if("${_mpip_${_EXAMPLE}_environment}" STREQUAL "")
|
|
set(_mpip_${_EXAMPLE}_environment "${_mpip_environment}")
|
|
endif()
|
|
omnitrace_add_test(
|
|
SKIP_RUNTIME SKIP_SAMPLING SKIP_PRELOAD
|
|
NAME "mpi-${_EXAMPLE}"
|
|
TARGET mpi-${_EXAMPLE}
|
|
MPI ON
|
|
NUM_PROCS 2
|
|
LABELS "mpip"
|
|
REWRITE_ARGS -e -v 2 --label file line --min-instructions 0
|
|
RUN_ARGS 30
|
|
ENVIRONMENT "${_mpip_${_EXAMPLE}_environment}")
|
|
endforeach()
|
|
endif()
|
|
|
|
omnitrace_add_test(
|
|
NAME lulesh
|
|
TARGET lulesh
|
|
MPI ${LULESH_USE_MPI}
|
|
GPU ${LULESH_USE_GPU}
|
|
NUM_PROCS 8
|
|
LABELS "kokkos"
|
|
REWRITE_ARGS -e -v 2 --label file line return args
|
|
RUNTIME_ARGS
|
|
-e
|
|
-v
|
|
1
|
|
--label
|
|
file
|
|
line
|
|
return
|
|
args
|
|
-ME
|
|
[==[lib(gomp|m-)]==]
|
|
LABELS "kokkos;kokkos-profile-library"
|
|
RUN_ARGS -i 25 -s 20 -p
|
|
ENVIRONMENT
|
|
"${_base_environment};OMNITRACE_CRITICAL_TRACE=OFF;OMNITRACE_USE_KOKKOSP=ON;OMNITRACE_COUT_OUTPUT=ON;OMNITRACE_SAMPLING_FREQ=50;OMNITRACE_KOKKOSP_PREFIX=[kokkos];KOKKOS_PROFILE_LIBRARY=libomnitrace-dl.so"
|
|
REWRITE_RUN_PASS_REGEX "\\|_\\[kokkos\\] [a-zA-Z]"
|
|
RUNTIME_PASS_REGEX "\\|_\\[kokkos\\] [a-zA-Z]")
|
|
|
|
omnitrace_add_test(
|
|
SKIP_RUNTIME SKIP_REWRITE
|
|
NAME lulesh-baseline-kokkosp-libomnitrace
|
|
TARGET lulesh
|
|
MPI ${LULESH_USE_MPI}
|
|
GPU ${LULESH_USE_GPU}
|
|
NUM_PROCS 8
|
|
LABELS "kokkos;kokkos-profile-library"
|
|
RUN_ARGS -i 10 -s 20 -p
|
|
ENVIRONMENT
|
|
"${_base_environment};OMNITRACE_CRITICAL_TRACE=OFF;OMNITRACE_USE_KOKKOSP=ON;OMNITRACE_COUT_OUTPUT=ON;OMNITRACE_SAMPLING_FREQ=50;OMNITRACE_KOKKOSP_PREFIX=[kokkos];KOKKOS_PROFILE_LIBRARY=libomnitrace.so"
|
|
BASELINE_PASS_REGEX "\\|_\\[kokkos\\] [a-zA-Z]")
|
|
|
|
omnitrace_add_test(
|
|
SKIP_RUNTIME SKIP_REWRITE
|
|
NAME lulesh-baseline-kokkosp-libomnitrace-dl
|
|
TARGET lulesh
|
|
MPI ${LULESH_USE_MPI}
|
|
GPU ${LULESH_USE_GPU}
|
|
NUM_PROCS 8
|
|
LABELS "kokkos;kokkos-profile-library"
|
|
RUN_ARGS -i 10 -s 20 -p
|
|
ENVIRONMENT
|
|
"${_base_environment};OMNITRACE_CRITICAL_TRACE=OFF;OMNITRACE_USE_KOKKOSP=ON;OMNITRACE_COUT_OUTPUT=ON;OMNITRACE_SAMPLING_FREQ=50;OMNITRACE_KOKKOSP_PREFIX=[kokkos];KOKKOS_PROFILE_LIBRARY=libomnitrace-dl.so"
|
|
BASELINE_PASS_REGEX "\\|_\\[kokkos\\] [a-zA-Z]")
|
|
|
|
omnitrace_add_test(
|
|
SKIP_BASELINE
|
|
NAME lulesh-kokkosp
|
|
TARGET lulesh
|
|
MPI ${LULESH_USE_MPI}
|
|
GPU ${LULESH_USE_GPU}
|
|
NUM_PROCS 8
|
|
LABELS "kokkos"
|
|
REWRITE_ARGS -e -v 2
|
|
RUNTIME_ARGS
|
|
-e
|
|
-v
|
|
1
|
|
--label
|
|
file
|
|
line
|
|
return
|
|
args
|
|
-ME
|
|
[==[lib(gomp|m-)]==]
|
|
RUN_ARGS -i 10 -s 20 -p
|
|
ENVIRONMENT
|
|
"${_base_environment};OMNITRACE_CRITICAL_TRACE=OFF;OMNITRACE_USE_KOKKOSP=ON")
|
|
|
|
omnitrace_add_test(
|
|
SKIP_BASELINE SKIP_SAMPLING
|
|
NAME lulesh-perfetto
|
|
TARGET lulesh
|
|
MPI ${LULESH_USE_MPI}
|
|
GPU ${LULESH_USE_GPU}
|
|
NUM_PROCS 8
|
|
LABELS "kokkos;loops"
|
|
REWRITE_ARGS -e -v 2
|
|
RUNTIME_ARGS
|
|
-e
|
|
-v
|
|
1
|
|
-l
|
|
--dynamic-callsites
|
|
--traps
|
|
--allow-overlapping
|
|
-ME
|
|
[==[libgomp]==]
|
|
RUN_ARGS -i 10 -s 20 -p
|
|
ENVIRONMENT
|
|
"${_perfetto_environment};OMNITRACE_CRITICAL_TRACE=OFF;OMNITRACE_USE_KOKKOSP=OFF")
|
|
|
|
omnitrace_add_test(
|
|
SKIP_SAMPLING
|
|
NAME lulesh-timemory
|
|
TARGET lulesh
|
|
MPI ${LULESH_USE_MPI}
|
|
GPU ${LULESH_USE_GPU}
|
|
NUM_PROCS 8
|
|
LABELS "kokkos;loops"
|
|
REWRITE_ARGS -e -v 2 -l --dynamic-callsites --traps --allow-overlapping
|
|
RUNTIME_ARGS
|
|
-e
|
|
-v
|
|
1
|
|
-l
|
|
--dynamic-callsites
|
|
-ME
|
|
[==[libgomp]==]
|
|
-d
|
|
wall_clock
|
|
peak_rss
|
|
RUN_ARGS -i 10 -s 20 -p
|
|
ENVIRONMENT
|
|
"${_timemory_environment};OMNITRACE_CRITICAL_TRACE=OFF;OMNITRACE_USE_KOKKOSP=OFF"
|
|
REWRITE_FAIL_REGEX "0 instrumented loops in procedure")
|
|
|
|
if(OMNITRACE_OPENMP_USING_LIBOMP_LIBRARY AND OMNITRACE_USE_OMPT)
|
|
set(_OMPT_PASS_REGEX "\\|_ompt_")
|
|
else()
|
|
set(_OMPT_PASS_REGEX "")
|
|
endif()
|
|
|
|
omnitrace_add_test(
|
|
SKIP_SAMPLING
|
|
NAME openmp-cg
|
|
TARGET openmp-cg
|
|
LABELS "openmp"
|
|
REWRITE_ARGS -e -v 2 --instrument-loops
|
|
RUNTIME_ARGS -e -v 1 --label return args
|
|
REWRITE_TIMEOUT 180
|
|
RUNTIME_TIMEOUT 360
|
|
ENVIRONMENT "${_ompt_environment};OMNITRACE_USE_SAMPLING=OFF;OMNITRACE_COUT_OUTPUT=ON"
|
|
REWRITE_RUN_PASS_REGEX "${_OMPT_PASS_REGEX}"
|
|
RUNTIME_PASS_REGEX "${_OMPT_PASS_REGEX}"
|
|
REWRITE_FAIL_REGEX "0 instrumented loops in procedure")
|
|
|
|
omnitrace_add_test(
|
|
SKIP_RUNTIME
|
|
NAME openmp-lu
|
|
TARGET openmp-lu
|
|
LABELS "openmp"
|
|
REWRITE_ARGS -e -v 2 --instrument-loops
|
|
RUNTIME_ARGS -e -v 1 --label return args -E ^GOMP
|
|
REWRITE_TIMEOUT 180
|
|
RUNTIME_TIMEOUT 360
|
|
ENVIRONMENT
|
|
"${_ompt_environment};OMNITRACE_USE_SAMPLING=ON;OMNITRACE_SAMPLING_FREQ=50;OMNITRACE_COUT_OUTPUT=ON"
|
|
REWRITE_RUN_PASS_REGEX "${_OMPT_PASS_REGEX}"
|
|
REWRITE_FAIL_REGEX "0 instrumented loops in procedure")
|
|
|
|
set(_ompt_preload_environ
|
|
"${_ompt_environment}"
|
|
"OMNITRACE_VERBOSE=2"
|
|
"OMNITRACE_USE_OMPT=OFF"
|
|
"OMNITRACE_USE_SAMPLING=ON"
|
|
"OMNITRACE_USE_PROCESS_SAMPLING=OFF"
|
|
"OMNITRACE_SAMPLING_FREQ=100"
|
|
"OMNITRACE_SAMPLING_DELAY=0.1"
|
|
"OMNITRACE_SAMPLING_DURATION=0.25"
|
|
"OMNITRACE_SAMPLING_CPUTIME=ON"
|
|
"OMNITRACE_SAMPLING_REALTIME=ON"
|
|
"OMNITRACE_SAMPLING_CPUTIME_FREQ=1000"
|
|
"OMNITRACE_SAMPLING_REALTIME_FREQ=500"
|
|
"OMNITRACE_MONOCHROME=ON")
|
|
|
|
set(_ompt_sample_no_tmpfiles_environ
|
|
"${_ompt_environment}"
|
|
"OMNITRACE_VERBOSE=2"
|
|
"OMNITRACE_USE_OMPT=OFF"
|
|
"OMNITRACE_USE_SAMPLING=ON"
|
|
"OMNITRACE_USE_PROCESS_SAMPLING=OFF"
|
|
"OMNITRACE_SAMPLING_CPUTIME=ON"
|
|
"OMNITRACE_SAMPLING_REALTIME=OFF"
|
|
"OMNITRACE_SAMPLING_CPUTIME_FREQ=700"
|
|
"OMNITRACE_USE_TEMPORARY_FILES=OFF"
|
|
"OMNITRACE_MONOCHROME=ON")
|
|
|
|
set(_ompt_preload_samp_regex
|
|
"Sampler for thread 0 will be triggered 1000.0x per second of CPU-time(.*)Sampler for thread 0 will be triggered 500.0x per second of wall-time(.*)Sampling will be disabled after 0.250000 seconds(.*)Sampling duration of 0.250000 seconds has elapsed. Shutting down sampling"
|
|
)
|
|
set(_ompt_preload_file_regex
|
|
"sampling-duration-preload/sampling_percent.(json|txt)(.*)sampling-duration-preload/sampling_cpu_clock.(json|txt)(.*)sampling-duration-preload/sampling_wall_clock.(json|txt)"
|
|
)
|
|
set(_notmp_preload_file_regex
|
|
"sampling-no-tmp-files-preload/sampling_percent.(json|txt)(.*)sampling-no-tmp-files-preload/sampling_cpu_clock.(json|txt)(.*)sampling-no-tmp-files-preload/sampling_wall_clock.(json|txt)"
|
|
)
|
|
|
|
omnitrace_add_test(
|
|
SKIP_BASELINE SKIP_RUNTIME SKIP_REWRITE SKIP_SAMPLING
|
|
NAME openmp-cg-sampling-duration
|
|
TARGET openmp-cg
|
|
LABELS "openmp;sampling-duration"
|
|
ENVIRONMENT "${_ompt_preload_environ}"
|
|
PRELOAD_PASS_REGEX "${_ompt_preload_samp_regex}(.*)${_ompt_preload_file_regex}")
|
|
|
|
omnitrace_add_test(
|
|
SKIP_BASELINE SKIP_RUNTIME SKIP_REWRITE SKIP_SAMPLING
|
|
NAME openmp-lu-sampling-duration
|
|
TARGET openmp-lu
|
|
LABELS "openmp;sampling-duration"
|
|
ENVIRONMENT "${_ompt_preload_environ}"
|
|
PRELOAD_PASS_REGEX "${_ompt_preload_samp_regex}(.*)${_ompt_preload_file_regex}")
|
|
|
|
omnitrace_add_test(
|
|
SKIP_BASELINE SKIP_RUNTIME SKIP_REWRITE SKIP_SAMPLING
|
|
NAME openmp-cg-sampling-no-tmp-files
|
|
TARGET openmp-cg
|
|
LABELS "openmp;no-tmp-files"
|
|
ENVIRONMENT "${_ompt_sample_no_tmpfiles_environ}"
|
|
PRELOAD_PASS_REGEX "${_notmp_preload_file_regex}")
|
|
|
|
omnitrace_add_test(
|
|
SKIP_BASELINE SKIP_SAMPLING SKIP_PRELOAD
|
|
NAME code-coverage
|
|
TARGET code-coverage
|
|
REWRITE_ARGS
|
|
-e
|
|
-v
|
|
2
|
|
--min-instructions=4
|
|
-E
|
|
^std::
|
|
-M
|
|
coverage
|
|
--coverage
|
|
function
|
|
RUNTIME_ARGS
|
|
-e
|
|
-v
|
|
1
|
|
--min-instructions=4
|
|
-E
|
|
^std::
|
|
--label
|
|
file
|
|
line
|
|
return
|
|
args
|
|
-M
|
|
coverage
|
|
--coverage
|
|
function
|
|
--module-restrict
|
|
code.coverage
|
|
LABELS "coverage;function-coverage"
|
|
RUN_ARGS 10 ${NUM_THREADS} 1000
|
|
ENVIRONMENT "${_base_environment}"
|
|
RUNTIME_PASS_REGEX "(\\\[[0-9]+\\\]) code coverage :: 66.67%"
|
|
REWRITE_RUN_PASS_REGEX "(\\\[[0-9]+\\\]) code coverage :: 66.67%")
|
|
|
|
omnitrace_add_test(
|
|
SKIP_BASELINE SKIP_SAMPLING SKIP_PRELOAD
|
|
NAME code-coverage-hybrid
|
|
TARGET code-coverage
|
|
REWRITE_ARGS -e -v 2 --min-instructions=4 -E ^std:: --coverage function
|
|
RUNTIME_ARGS
|
|
-e
|
|
-v
|
|
1
|
|
--min-instructions=4
|
|
-E
|
|
^std::
|
|
--label
|
|
file
|
|
line
|
|
return
|
|
args
|
|
--coverage
|
|
function
|
|
--module-restrict
|
|
code.coverage
|
|
LABELS "coverage;function-coverage;hybrid-coverage"
|
|
RUN_ARGS 10 ${NUM_THREADS} 1000
|
|
ENVIRONMENT "${_base_environment}"
|
|
RUNTIME_PASS_REGEX "(\\\[[0-9]+\\\]) code coverage :: 66.67%"
|
|
REWRITE_RUN_PASS_REGEX "(\\\[[0-9]+\\\]) code coverage :: 66.67%")
|
|
|
|
omnitrace_add_test(
|
|
SKIP_BASELINE SKIP_SAMPLING SKIP_PRELOAD
|
|
NAME code-coverage-basic-blocks
|
|
TARGET code-coverage
|
|
REWRITE_ARGS
|
|
-e
|
|
-v
|
|
2
|
|
--min-instructions=4
|
|
-E
|
|
^std::
|
|
-M
|
|
coverage
|
|
--coverage
|
|
basic_block
|
|
RUNTIME_ARGS
|
|
-e
|
|
-v
|
|
1
|
|
--min-instructions=4
|
|
-E
|
|
^std::
|
|
--label
|
|
file
|
|
line
|
|
return
|
|
args
|
|
-M
|
|
coverage
|
|
--coverage
|
|
basic_block
|
|
--module-restrict
|
|
code.coverage
|
|
LABELS "coverage;bb-coverage"
|
|
RUN_ARGS 10 ${NUM_THREADS} 1000
|
|
ENVIRONMENT "${_base_environment}"
|
|
RUNTIME_PASS_REGEX "(\\\[[0-9]+\\\]) function coverage :: 66.67%"
|
|
REWRITE_RUN_PASS_REGEX "(\\\[[0-9]+\\\]) function coverage :: 66.67%")
|
|
|
|
omnitrace_add_test(
|
|
SKIP_BASELINE SKIP_SAMPLING SKIP_PRELOAD
|
|
NAME code-coverage-basic-blocks-hybrid
|
|
TARGET code-coverage
|
|
REWRITE_ARGS -e -v 2 --min-instructions=4 -E ^std:: --coverage basic_block
|
|
RUNTIME_ARGS
|
|
-e
|
|
-v
|
|
1
|
|
--min-instructions=4
|
|
-E
|
|
^std::
|
|
--label
|
|
file
|
|
line
|
|
return
|
|
args
|
|
--coverage
|
|
basic_block
|
|
--module-restrict
|
|
code.coverage
|
|
LABELS "coverage;bb-coverage;hybrid-coverage"
|
|
RUN_ARGS 10 ${NUM_THREADS} 1000
|
|
ENVIRONMENT "${_base_environment}"
|
|
RUNTIME_PASS_REGEX "(\\\[[0-9]+\\\]) function coverage :: 66.67%"
|
|
REWRITE_RUN_PASS_REGEX "(\\\[[0-9]+\\\]) function coverage :: 66.67%")
|
|
|
|
if(_OS_RELEASE STREQUAL "ubuntu-18.04")
|
|
set(_TRACE_WINDOW_SKIP SKIP_RUNTIME)
|
|
endif()
|
|
|
|
omnitrace_add_test(
|
|
SKIP_BASELINE SKIP_SAMPLING SKIP_PRELOAD ${_TRACE_WINDOW_SKIP}
|
|
NAME trace-time-window
|
|
TARGET trace-time-window
|
|
REWRITE_ARGS -e -v 2 --caller-include inner -i 4096
|
|
RUNTIME_ARGS -e -v 1 --caller-include inner -i 4096
|
|
LABELS "time-window"
|
|
ENVIRONMENT "${_window_environment};OMNITRACE_TRACE_DURATION=1.25")
|
|
|
|
omnitrace_add_validation_test(
|
|
NAME trace-time-window-binary-rewrite
|
|
TIMEMORY_METRIC "wall_clock"
|
|
TIMEMORY_FILE "wall_clock.json"
|
|
PERFETTO_METRIC "host"
|
|
PERFETTO_FILE "perfetto-trace.proto"
|
|
LABELS "time-window"
|
|
FAIL_REGEX "outer_d"
|
|
ARGS -l
|
|
trace-time-window.inst
|
|
outer_a
|
|
outer_b
|
|
outer_c
|
|
-c
|
|
1
|
|
1
|
|
1
|
|
1
|
|
-d
|
|
0
|
|
1
|
|
1
|
|
1
|
|
-p)
|
|
|
|
omnitrace_add_validation_test(
|
|
NAME trace-time-window-runtime-instrument
|
|
TIMEMORY_METRIC "wall_clock"
|
|
TIMEMORY_FILE "wall_clock.json"
|
|
PERFETTO_METRIC "host"
|
|
PERFETTO_FILE "perfetto-trace.proto"
|
|
LABELS "time-window"
|
|
FAIL_REGEX "outer_d"
|
|
ARGS -l
|
|
trace-time-window
|
|
outer_a
|
|
outer_b
|
|
outer_c
|
|
-c
|
|
1
|
|
1
|
|
1
|
|
1
|
|
-d
|
|
0
|
|
1
|
|
1
|
|
1
|
|
-p)
|
|
|
|
omnitrace_add_test(
|
|
SKIP_BASELINE SKIP_SAMPLING SKIP_PRELOAD ${_TRACE_WINDOW_SKIP}
|
|
NAME trace-time-window-delay
|
|
TARGET trace-time-window
|
|
REWRITE_ARGS -e -v 2 --caller-include inner -i 4096
|
|
RUNTIME_ARGS -e -v 1 --caller-include inner -i 4096
|
|
LABELS "time-window"
|
|
ENVIRONMENT
|
|
"${_window_environment};OMNITRACE_TRACE_DELAY=0.75;OMNITRACE_TRACE_DURATION=0.75")
|
|
|
|
omnitrace_add_validation_test(
|
|
NAME trace-time-window-delay-binary-rewrite
|
|
TIMEMORY_METRIC "wall_clock"
|
|
TIMEMORY_FILE "wall_clock.json"
|
|
PERFETTO_METRIC "host"
|
|
PERFETTO_FILE "perfetto-trace.proto"
|
|
LABELS "time-window"
|
|
ARGS -l
|
|
outer_c
|
|
outer_d
|
|
-c
|
|
1
|
|
1
|
|
-d
|
|
0
|
|
0
|
|
-p)
|
|
|
|
omnitrace_add_validation_test(
|
|
NAME trace-time-window-delay-runtime-instrument
|
|
TIMEMORY_METRIC "wall_clock"
|
|
TIMEMORY_FILE "wall_clock.json"
|
|
PERFETTO_METRIC "host"
|
|
PERFETTO_FILE "perfetto-trace.proto"
|
|
LABELS "time-window"
|
|
ARGS -l
|
|
outer_c
|
|
outer_d
|
|
-c
|
|
1
|
|
1
|
|
-d
|
|
0
|
|
0
|
|
-p)
|
|
|
|
omnitrace_add_test(
|
|
NAME fork
|
|
TARGET fork-example
|
|
REWRITE_ARGS -e -v 2 --print-instrumented modules -i 16
|
|
RUNTIME_ARGS -e -v 1 --label file -i 16
|
|
ENVIRONMENT
|
|
"${_base_environment};OMNITRACE_CRITICAL_TRACE=ON;OMNITRACE_SAMPLING_FREQ=250;OMNITRACE_SAMPLING_REALTIME=ON"
|
|
PRELOAD_PASS_REGEX "fork.. called on PID"
|
|
RUNTIME_PASS_REGEX "fork.. called on PID"
|
|
REWRITE_RUN_PASS_REGEX "fork.. called on PID"
|
|
PRELOAD_FAIL_REGEX
|
|
"(terminate called after throwing an instance|calling abort.. in |Exit code: [1-9])"
|
|
RUNTIME_FAIL_REGEX
|
|
"(terminate called after throwing an instance|calling abort.. in |Exit code: [1-9])"
|
|
REWRITE_RUN_FAIL_REGEX
|
|
"(terminate called after throwing an instance|calling abort.. in |Exit code: [1-9])"
|
|
)
|
|
|
|
# -------------------------------------------------------------------------------------- #
|
|
#
|
|
# critical-trace tests
|
|
#
|
|
# -------------------------------------------------------------------------------------- #
|
|
|
|
omnitrace_add_test(
|
|
SKIP_BASELINE SKIP_RUNTIME SKIP_SAMPLING SKIP_PRELOAD
|
|
NAME parallel-overhead-critical-trace
|
|
TARGET parallel-overhead
|
|
LABELS "critical-trace"
|
|
REWRITE_ARGS
|
|
-e
|
|
-i
|
|
8
|
|
-E
|
|
"^fib"
|
|
-v
|
|
2
|
|
--print-instrumented
|
|
functions
|
|
RUN_ARGS 10 4 100
|
|
ENVIRONMENT "${_critical_trace_environment}")
|
|
|
|
add_test(
|
|
NAME parallel-overhead-process-critical-trace
|
|
COMMAND
|
|
$<TARGET_FILE:omnitrace-critical-trace>
|
|
${PROJECT_BINARY_DIR}/omnitrace-tests-output/parallel-overhead-critical-trace-binary-rewrite/call-chain.json
|
|
WORKING_DIRECTORY ${PROJECT_BINARY_DIR})
|
|
|
|
set(_parallel_overhead_critical_trace_environ
|
|
"OMNITRACE_OUTPUT_PATH=omnitrace-tests-output"
|
|
"OMNITRACE_OUTPUT_PREFIX=parallel-overhead-critical-trace/"
|
|
"OMNITRACE_CRITICAL_TRACE_DEBUG=ON"
|
|
"OMNITRACE_VERBOSE=4"
|
|
"OMNITRACE_USE_PID=OFF"
|
|
"OMNITRACE_TIME_OUTPUT=OFF")
|
|
|
|
set_tests_properties(
|
|
parallel-overhead-process-critical-trace
|
|
PROPERTIES
|
|
ENVIRONMENT
|
|
"${_parallel_overhead_critical_trace_environ}"
|
|
TIMEOUT
|
|
300
|
|
LABELS
|
|
"parallel-overhead;critical-trace"
|
|
PASS_REGULAR_EXPRESSION
|
|
"Outputting.*(critical-trace-cpu.json).*Outputting.*(critical-trace-any.json)"
|
|
DEPENDS
|
|
parallel-overhead-critical-trace-binary-rewrite-run)
|
|
|
|
# -------------------------------------------------------------------------------------- #
|
|
#
|
|
# attach tests
|
|
#
|
|
# -------------------------------------------------------------------------------------- #
|
|
|
|
set(_VALID_PTRACE_SCOPE OFF)
|
|
if(EXISTS "/proc/sys/kernel/yama/ptrace_scope")
|
|
file(READ "/proc/sys/kernel/yama/ptrace_scope" _PTRACE_SCOPE LIMIT 1)
|
|
if("${_PTRACE_SCOPE}" EQUAL 0)
|
|
set(_VALID_PTRACE_SCOPE ON)
|
|
endif()
|
|
else()
|
|
omnitrace_message(
|
|
AUTHOR_WARNING
|
|
"Disabling attach tests. Run 'echo 0 | sudo tee /proc/sys/kernel/yama/ptrace_scope' to enable attaching to process"
|
|
)
|
|
endif()
|
|
|
|
if(TARGET parallel-overhead AND _VALID_PTRACE_SCOPE)
|
|
add_test(
|
|
NAME parallel-overhead-attach
|
|
COMMAND
|
|
${CMAKE_CURRENT_LIST_DIR}/run-omnitrace-pid.sh
|
|
$<TARGET_FILE:omnitrace-instrument> -ME "\.c$" -E fib -e -v 1 --label return
|
|
args file -l -- $<TARGET_FILE:parallel-overhead> 30 8 1000
|
|
WORKING_DIRECTORY ${PROJECT_BINARY_DIR})
|
|
|
|
set(_parallel_overhead_attach_environ
|
|
"${_attach_environment}" "OMNITRACE_OUTPUT_PATH=omnitrace-tests-output"
|
|
"OMNITRACE_OUTPUT_PREFIX=parallel-overhead-attach/")
|
|
|
|
set_tests_properties(
|
|
parallel-overhead-attach
|
|
PROPERTIES ENVIRONMENT
|
|
"${_parallel_overhead_attach_environ}"
|
|
TIMEOUT
|
|
300
|
|
LABELS
|
|
"parallel-overhead;attach"
|
|
PASS_REGULAR_EXPRESSION
|
|
"Outputting.*(perfetto-trace.proto).*Outputting.*(wall_clock.txt)"
|
|
FAIL_REGULAR_EXPRESSION
|
|
"Dyninst was unable to attach to the specified process")
|
|
endif()
|
|
|
|
# -------------------------------------------------------------------------------------- #
|
|
#
|
|
# rccl tests
|
|
#
|
|
# -------------------------------------------------------------------------------------- #
|
|
|
|
foreach(_TARGET ${RCCL_TEST_TARGETS})
|
|
string(REPLACE "rccl-tests::" "" _NAME "${_TARGET}")
|
|
string(REPLACE "_" "-" _NAME "${_NAME}")
|
|
omnitrace_add_test(
|
|
SKIP_SAMPLING
|
|
NAME rccl-test-${_NAME}
|
|
TARGET ${_TARGET}
|
|
LABELS "rccl-tests;rcclp"
|
|
MPI ON
|
|
GPU ON
|
|
NUM_PROCS 1
|
|
REWRITE_ARGS
|
|
-e
|
|
-v
|
|
2
|
|
-i
|
|
8
|
|
--label
|
|
file
|
|
line
|
|
return
|
|
args
|
|
RUNTIME_ARGS
|
|
-e
|
|
-v
|
|
1
|
|
-i
|
|
8
|
|
--label
|
|
file
|
|
line
|
|
return
|
|
args
|
|
-ME
|
|
sysdeps
|
|
--log-file
|
|
rccl-test-${_NAME}.log
|
|
RUN_ARGS -t
|
|
1
|
|
-g
|
|
1
|
|
-i
|
|
10
|
|
-w
|
|
2
|
|
-m
|
|
2
|
|
-p
|
|
-c
|
|
1
|
|
-z
|
|
-s
|
|
1
|
|
ENVIRONMENT "${_rccl_environment}")
|
|
endforeach()
|
|
|
|
# -------------------------------------------------------------------------------------- #
|
|
#
|
|
# causal profiling tests
|
|
#
|
|
# -------------------------------------------------------------------------------------- #
|
|
|
|
omnitrace_add_causal_test(
|
|
NAME cpu-omni-func
|
|
TARGET causal-cpu-omni
|
|
RUN_ARGS 70 10 432525 1000000000
|
|
CAUSAL_MODE "function"
|
|
CAUSAL_PASS_REGEX
|
|
"Starting causal experiment #1(.*)causal/experiments.json(.*)causal/experiments.coz"
|
|
)
|
|
|
|
omnitrace_add_causal_test(
|
|
SKIP_BASELINE
|
|
NAME cpu-omni-func-ndebug
|
|
TARGET causal-cpu-omni-ndebug
|
|
RUN_ARGS 70 10 432525 1000000000
|
|
CAUSAL_MODE "function"
|
|
CAUSAL_PASS_REGEX
|
|
"Starting causal experiment #1(.*)causal/experiments.json(.*)causal/experiments.coz"
|
|
)
|
|
|
|
omnitrace_add_causal_test(
|
|
SKIP_BASELINE
|
|
NAME cpu-omni-line
|
|
TARGET causal-cpu-omni
|
|
RUN_ARGS 70 10 432525 1000000000
|
|
CAUSAL_MODE "line"
|
|
CAUSAL_PASS_REGEX
|
|
"Starting causal experiment #1(.*)causal/experiments.json(.*)causal/experiments.coz"
|
|
)
|
|
|
|
omnitrace_add_causal_test(
|
|
NAME both-omni-func
|
|
TARGET causal-both-omni
|
|
RUN_ARGS 70 10 432525 400000000
|
|
CAUSAL_MODE "function"
|
|
CAUSAL_ARGS
|
|
-w
|
|
1
|
|
-d
|
|
3
|
|
--monochrome
|
|
-g
|
|
${CMAKE_BINARY_DIR}/omnitrace-tests-config/causal-both-omni-func
|
|
-l
|
|
causal-both-omni
|
|
-v
|
|
3
|
|
ENVIRONMENT "OMNITRACE_STRICT_CONFIG=OFF"
|
|
CAUSAL_PASS_REGEX
|
|
"Starting causal experiment #1(.*)causal/experiments.json(.*)causal/experiments.coz"
|
|
)
|
|
|
|
omnitrace_add_causal_test(
|
|
NAME lulesh-func
|
|
TARGET lulesh-omni
|
|
RUN_ARGS -i 35 -s 50 -p
|
|
CAUSAL_MODE "function"
|
|
CAUSAL_ARGS -s 0,10,25,50,75
|
|
CAUSAL_PASS_REGEX
|
|
"Starting causal experiment #1(.*)causal/experiments.json(.*)causal/experiments.coz"
|
|
)
|
|
|
|
omnitrace_add_causal_test(
|
|
SKIP_BASELINE
|
|
NAME lulesh-func-ndebug
|
|
TARGET lulesh-omni-ndebug
|
|
RUN_ARGS -i 35 -s 50 -p
|
|
CAUSAL_MODE "function"
|
|
CAUSAL_ARGS -s 0,10,25,50,75
|
|
CAUSAL_PASS_REGEX
|
|
"Starting causal experiment #1(.*)causal/experiments.json(.*)causal/experiments.coz"
|
|
)
|
|
|
|
omnitrace_add_causal_test(
|
|
SKIP_BASELINE
|
|
NAME lulesh-line
|
|
TARGET lulesh-omni
|
|
RUN_ARGS -i 35 -s 50 -p
|
|
CAUSAL_MODE "line"
|
|
CAUSAL_ARGS -s 0,10,25,50,75 -S lulesh.cc
|
|
CAUSAL_PASS_REGEX
|
|
"Starting causal experiment #1(.*)causal/experiments.json(.*)causal/experiments.coz"
|
|
)
|
|
|
|
set(_causal_common_args
|
|
"-n 5 -e -s 0 10 20 30 -B $<TARGET_FILE_BASE_NAME:causal-cpu-omni>")
|
|
|
|
macro(
|
|
causal_e2e_args_and_validation
|
|
_NAME
|
|
_TEST
|
|
_MODE
|
|
_EXPER
|
|
_V10 # expected value for virtual speedup of 10
|
|
_V20
|
|
_V30
|
|
_TOL # tolerance for virtual speedup
|
|
)
|
|
# arguments to omnitrace-causal
|
|
set(${_NAME}_args "${_causal_common_args} ${_MODE} ${_EXPER}")
|
|
|
|
# arguments to validate-causal-json.py
|
|
set(${_NAME}_valid
|
|
"-n 0 -i omnitrace-tests-output/causal-cpu-omni-${_TEST}-e2e/causal/experiments.json -v ${_EXPER} $<TARGET_FILE_BASE_NAME:causal-cpu-omni> 10 ${_V10} ${_TOL} ${_EXPER} $<TARGET_FILE_BASE_NAME:causal-cpu-omni> 20 ${_V20} ${_TOL} ${_EXPER} $<TARGET_FILE_BASE_NAME:causal-cpu-omni> 30 ${_V30} ${_TOL}"
|
|
)
|
|
# patch string for command-line
|
|
string(REPLACE " " ";" ${_NAME}_args "${${_NAME}_args}")
|
|
string(REPLACE " " ";" ${_NAME}_valid "${${_NAME}_valid}")
|
|
endmacro()
|
|
|
|
causal_e2e_args_and_validation(_causal_slow_func slow-func "-F" "cpu_slow_func" 10 20 20
|
|
5)
|
|
causal_e2e_args_and_validation(_causal_fast_func fast-func "-F" "cpu_fast_func" 0 0 0 5)
|
|
causal_e2e_args_and_validation(_causal_line_155 line-155 "-S" "causal.cpp:155" 10 20 20 5)
|
|
causal_e2e_args_and_validation(_causal_line_165 line-165 "-S" "causal.cpp:165" 0 0 0 5)
|
|
|
|
omnitrace_add_causal_test(
|
|
SKIP_BASELINE
|
|
NAME cpu-omni-slow-func-e2e
|
|
TARGET causal-cpu-omni
|
|
RUN_ARGS 80 12 432525 500000000
|
|
CAUSAL_MODE "func"
|
|
CAUSAL_ARGS ${_causal_slow_func_args}
|
|
CAUSAL_VALIDATE_ARGS ${_causal_slow_func_valid}
|
|
CAUSAL_PASS_REGEX
|
|
"Starting causal experiment #1(.*)causal/experiments.json(.*)causal/experiments.coz"
|
|
PROPERTIES PROCESSORS 2 PROCESSOR_AFFINITY ON)
|
|
|
|
omnitrace_add_causal_test(
|
|
SKIP_BASELINE
|
|
NAME cpu-omni-fast-func-e2e
|
|
TARGET causal-cpu-omni
|
|
RUN_ARGS 80 12 432525 500000000
|
|
CAUSAL_MODE "func"
|
|
CAUSAL_ARGS ${_causal_fast_func_args}
|
|
CAUSAL_VALIDATE_ARGS ${_causal_fast_func_valid}
|
|
CAUSAL_PASS_REGEX
|
|
"Starting causal experiment #1(.*)causal/experiments.json(.*)causal/experiments.coz"
|
|
PROPERTIES PROCESSORS 2 PROCESSOR_AFFINITY OFF)
|
|
|
|
omnitrace_add_causal_test(
|
|
SKIP_BASELINE
|
|
NAME cpu-omni-line-155-e2e
|
|
TARGET causal-cpu-omni
|
|
RUN_ARGS 80 12 432525 500000000
|
|
CAUSAL_MODE "line"
|
|
CAUSAL_ARGS ${_causal_line_155_args}
|
|
CAUSAL_VALIDATE_ARGS ${_causal_line_155_valid}
|
|
CAUSAL_PASS_REGEX
|
|
"Starting causal experiment #1(.*)causal/experiments.json(.*)causal/experiments.coz"
|
|
PROPERTIES PROCESSORS 2 PROCESSOR_AFFINITY ON)
|
|
|
|
omnitrace_add_causal_test(
|
|
SKIP_BASELINE
|
|
NAME cpu-omni-line-165-e2e
|
|
TARGET causal-cpu-omni
|
|
RUN_ARGS 80 12 432525 500000000
|
|
CAUSAL_MODE "line"
|
|
CAUSAL_ARGS ${_causal_line_165_args}
|
|
CAUSAL_VALIDATE_ARGS ${_causal_line_165_valid}
|
|
CAUSAL_PASS_REGEX
|
|
"Starting causal experiment #1(.*)causal/experiments.json(.*)causal/experiments.coz"
|
|
PROPERTIES PROCESSORS 2 PROCESSOR_AFFINITY OFF)
|
|
|
|
# -------------------------------------------------------------------------------------- #
|
|
#
|
|
# python tests
|
|
#
|
|
# -------------------------------------------------------------------------------------- #
|
|
|
|
set(_INDEX 0)
|
|
foreach(_VERSION ${OMNITRACE_PYTHON_VERSIONS})
|
|
if(NOT OMNITRACE_USE_PYTHON)
|
|
continue()
|
|
endif()
|
|
|
|
list(GET OMNITRACE_PYTHON_ROOT_DIRS ${_INDEX} _PYTHON_ROOT_DIR)
|
|
|
|
omnitrace_find_python(
|
|
_PYTHON
|
|
ROOT_DIR "${_PYTHON_ROOT_DIR}"
|
|
COMPONENTS Interpreter)
|
|
|
|
# ---------------------------------------------------------------------------------- #
|
|
# python tests
|
|
# ---------------------------------------------------------------------------------- #
|
|
omnitrace_add_python_test(
|
|
NAME python-external
|
|
PYTHON_EXECUTABLE ${_PYTHON_EXECUTABLE}
|
|
PYTHON_VERSION ${_VERSION}
|
|
FILE ${CMAKE_SOURCE_DIR}/examples/python/external.py
|
|
PROFILE_ARGS "--label" "file"
|
|
RUN_ARGS -v 10 -n 5
|
|
ENVIRONMENT "${_python_environment}")
|
|
|
|
omnitrace_add_python_test(
|
|
NAME python-external-exclude-inefficient
|
|
PYTHON_EXECUTABLE ${_PYTHON_EXECUTABLE}
|
|
PYTHON_VERSION ${_VERSION}
|
|
FILE ${CMAKE_SOURCE_DIR}/examples/python/external.py
|
|
PROFILE_ARGS -E "^inefficient$"
|
|
RUN_ARGS -v 10 -n 5
|
|
ENVIRONMENT "${_python_environment}")
|
|
|
|
omnitrace_add_python_test(
|
|
NAME python-builtin
|
|
PYTHON_EXECUTABLE ${_PYTHON_EXECUTABLE}
|
|
PYTHON_VERSION ${_VERSION}
|
|
FILE ${CMAKE_SOURCE_DIR}/examples/python/builtin.py
|
|
PROFILE_ARGS "-b" "--label" "file" "line"
|
|
RUN_ARGS -v 10 -n 5
|
|
ENVIRONMENT "${_python_environment}")
|
|
|
|
omnitrace_add_python_test(
|
|
NAME python-builtin-noprofile
|
|
PYTHON_EXECUTABLE ${_PYTHON_EXECUTABLE}
|
|
PYTHON_VERSION ${_VERSION}
|
|
FILE ${CMAKE_SOURCE_DIR}/examples/python/noprofile.py
|
|
PROFILE_ARGS "-b" "--label" "file"
|
|
RUN_ARGS -v 15 -n 5
|
|
ENVIRONMENT "${_python_environment}")
|
|
|
|
omnitrace_add_python_test(
|
|
STANDALONE
|
|
NAME python-source
|
|
PYTHON_EXECUTABLE ${_PYTHON_EXECUTABLE}
|
|
PYTHON_VERSION ${_VERSION}
|
|
FILE ${CMAKE_SOURCE_DIR}/examples/python/source.py
|
|
RUN_ARGS -v 5 -n 5 -s 3
|
|
ENVIRONMENT "${_python_environment}")
|
|
|
|
omnitrace_add_python_test(
|
|
STANDALONE
|
|
NAME python-code-coverage
|
|
PYTHON_EXECUTABLE ${_PYTHON_EXECUTABLE}
|
|
PYTHON_VERSION ${_VERSION}
|
|
FILE ${CMAKE_SOURCE_DIR}/examples/code-coverage/code-coverage.py
|
|
RUN_ARGS
|
|
-i
|
|
${PROJECT_BINARY_DIR}/omnitrace-tests-output/code-coverage-basic-blocks-binary-rewrite/coverage.json
|
|
${PROJECT_BINARY_DIR}/omnitrace-tests-output/code-coverage-basic-blocks-hybrid-runtime-instrument/coverage.json
|
|
-o
|
|
${PROJECT_BINARY_DIR}/omnitrace-tests-output/code-coverage-basic-blocks-summary/coverage.json
|
|
DEPENDS code-coverage-basic-blocks-binary-rewrite
|
|
code-coverage-basic-blocks-binary-rewrite-run
|
|
code-coverage-basic-blocks-hybrid-runtime-instrument
|
|
LABELS "code-coverage"
|
|
ENVIRONMENT "${_python_environment}")
|
|
|
|
# ---------------------------------------------------------------------------------- #
|
|
# python output tests
|
|
# ---------------------------------------------------------------------------------- #
|
|
|
|
if(CMAKE_VERSION VERSION_LESS "3.18.0")
|
|
find_program(
|
|
OMNITRACE_CAT_EXE
|
|
NAMES cat
|
|
PATH_SUFFIXES bin)
|
|
if(OMNITRACE_CAT_EXE)
|
|
set(OMNITRACE_CAT_COMMAND ${OMNITRACE_CAT_EXE})
|
|
endif()
|
|
else()
|
|
set(OMNITRACE_CAT_COMMAND ${CMAKE_COMMAND} -E cat)
|
|
endif()
|
|
|
|
if(OMNITRACE_CAT_COMMAND)
|
|
omnitrace_add_python_test(
|
|
NAME python-external-check
|
|
COMMAND ${OMNITRACE_CAT_COMMAND}
|
|
PYTHON_VERSION ${_VERSION}
|
|
FILE omnitrace-tests-output/python-external/${_VERSION}/trip_count.txt
|
|
PASS_REGEX
|
|
"(\\\[compile\\\]).*(\\\| \\\|0>>> \\\[run\\\]\\\[external.py\\\]).*(\\\| \\\|0>>> \\\|_\\\[fib\\\]\\\[external.py\\\]).*(\\\| \\\|0>>> \\\|_\\\[inefficient\\\]\\\[external.py\\\])"
|
|
DEPENDS python-external-${_VERSION}
|
|
ENVIRONMENT "${_python_environment}")
|
|
|
|
omnitrace_add_python_test(
|
|
NAME python-external-exclude-inefficient-check
|
|
COMMAND ${OMNITRACE_CAT_COMMAND}
|
|
PYTHON_VERSION ${_VERSION}
|
|
FILE omnitrace-tests-output/python-external-exclude-inefficient/${_VERSION}/trip_count.txt
|
|
FAIL_REGEX "(\\\|_inefficient).*(\\\|_sum)"
|
|
DEPENDS python-external-exclude-inefficient-${_VERSION}
|
|
ENVIRONMENT "${_python_environment}")
|
|
|
|
omnitrace_add_python_test(
|
|
NAME python-builtin-check
|
|
COMMAND ${OMNITRACE_CAT_COMMAND}
|
|
PYTHON_VERSION ${_VERSION}
|
|
FILE omnitrace-tests-output/python-builtin/${_VERSION}/trip_count.txt
|
|
PASS_REGEX "\\\[inefficient\\\]\\\[builtin.py:14\\\]"
|
|
DEPENDS python-builtin-${_VERSION}
|
|
ENVIRONMENT "${_python_environment}")
|
|
|
|
omnitrace_add_python_test(
|
|
NAME python-builtin-noprofile-check
|
|
COMMAND ${OMNITRACE_CAT_COMMAND}
|
|
PYTHON_VERSION ${_VERSION}
|
|
FILE omnitrace-tests-output/python-builtin-noprofile/${_VERSION}/trip_count.txt
|
|
PASS_REGEX ".(run)..(noprofile.py)."
|
|
FAIL_REGEX ".(fib|inefficient)..(noprofile.py)."
|
|
DEPENDS python-builtin-noprofile-${_VERSION}
|
|
ENVIRONMENT "${_python_environment}")
|
|
else()
|
|
omnitrace_message(
|
|
WARNING
|
|
"Neither 'cat' nor 'cmake -E cat' are available. Python source checks are disabled"
|
|
)
|
|
endif()
|
|
|
|
function(OMNITRACE_ADD_PYTHON_VALIDATION_TEST)
|
|
cmake_parse_arguments(
|
|
TEST "" "NAME;TIMEMORY_METRIC;TIMEMORY_FILE;PERFETTO_METRIC;PERFETTO_FILE"
|
|
"ARGS" ${ARGN})
|
|
|
|
omnitrace_add_python_test(
|
|
NAME ${TEST_NAME}-validate-timemory
|
|
COMMAND
|
|
${_PYTHON_EXECUTABLE} ${CMAKE_CURRENT_LIST_DIR}/validate-timemory-json.py
|
|
-m ${TEST_TIMEMORY_METRIC} ${TEST_ARGS} -i
|
|
PYTHON_VERSION ${_VERSION}
|
|
FILE omnitrace-tests-output/${TEST_NAME}/${_VERSION}/${TEST_TIMEMORY_FILE}
|
|
DEPENDS ${TEST_NAME}-${_VERSION}
|
|
PASS_REGEX
|
|
"omnitrace-tests-output/${TEST_NAME}/${_VERSION}/${TEST_TIMEMORY_FILE} validated"
|
|
ENVIRONMENT "${_python_environment}")
|
|
|
|
omnitrace_add_python_test(
|
|
NAME ${TEST_NAME}-validate-perfetto
|
|
COMMAND
|
|
${_PYTHON_EXECUTABLE} ${CMAKE_CURRENT_LIST_DIR}/validate-perfetto-proto.py
|
|
-m ${TEST_PERFETTO_METRIC} ${TEST_ARGS} -p -i
|
|
PYTHON_VERSION ${_VERSION}
|
|
FILE omnitrace-tests-output/${TEST_NAME}/${_VERSION}/${TEST_PERFETTO_FILE}
|
|
DEPENDS ${TEST_NAME}-${_VERSION}
|
|
PASS_REGEX
|
|
"omnitrace-tests-output/${TEST_NAME}/${_VERSION}/${TEST_PERFETTO_FILE} validated"
|
|
ENVIRONMENT "${_python_environment}")
|
|
endfunction()
|
|
|
|
set(python_source_labels
|
|
main_loop
|
|
run
|
|
fib
|
|
fib
|
|
fib
|
|
fib
|
|
fib
|
|
inefficient
|
|
_sum)
|
|
set(python_source_count
|
|
5
|
|
3
|
|
3
|
|
6
|
|
12
|
|
18
|
|
6
|
|
3
|
|
3)
|
|
set(python_source_depth
|
|
0
|
|
1
|
|
2
|
|
3
|
|
4
|
|
5
|
|
6
|
|
2
|
|
3)
|
|
|
|
omnitrace_add_python_validation_test(
|
|
NAME python-source
|
|
TIMEMORY_METRIC "trip_count"
|
|
TIMEMORY_FILE "trip_count.json"
|
|
PERFETTO_METRIC "host;user"
|
|
PERFETTO_FILE "perfetto-trace.proto"
|
|
ARGS -l ${python_source_labels} -c ${python_source_count} -d
|
|
${python_source_depth})
|
|
|
|
set(python_builtin_labels
|
|
[run][builtin.py:28]
|
|
[fib][builtin.py:10]
|
|
[fib][builtin.py:10]
|
|
[fib][builtin.py:10]
|
|
[fib][builtin.py:10]
|
|
[fib][builtin.py:10]
|
|
[fib][builtin.py:10]
|
|
[fib][builtin.py:10]
|
|
[fib][builtin.py:10]
|
|
[fib][builtin.py:10]
|
|
[fib][builtin.py:10]
|
|
[inefficient][builtin.py:14])
|
|
set(python_builtin_count
|
|
5
|
|
5
|
|
10
|
|
20
|
|
40
|
|
80
|
|
160
|
|
260
|
|
220
|
|
80
|
|
10
|
|
5)
|
|
set(python_builtin_depth
|
|
0
|
|
1
|
|
2
|
|
3
|
|
4
|
|
5
|
|
6
|
|
7
|
|
8
|
|
9
|
|
10
|
|
1)
|
|
|
|
omnitrace_add_python_validation_test(
|
|
NAME python-builtin
|
|
TIMEMORY_METRIC "trip_count"
|
|
TIMEMORY_FILE "trip_count.json"
|
|
PERFETTO_METRIC "host;user"
|
|
PERFETTO_FILE "perfetto-trace.proto"
|
|
ARGS -l ${python_builtin_labels} -c ${python_builtin_count} -d
|
|
${python_builtin_depth})
|
|
math(EXPR _INDEX "${_INDEX} + 1")
|
|
endforeach()
|