# cmd: bash -lc cd tracks/A-gpu-programming/A01.foundations-and-programming-model && make -s profile-hip GPU_ARCH=gfx950 HIP_PATH=/opt/rocm # gpu_arch: gfx950 # captured: 2026-08-10T06:51:42Z --- [rocprofv3] Warning: --ompt-trace: OMPT data is only emitted to the 'rocpd' output format; the requested output format(s) csv will not contain OMPT records. Adding 'rocpd' to --output-format -- use `rocpd convert` to export OMPT to csv/pftrace/otf2. W simple_timer.cpp:55] [rocprofv3] tool initialization :: 0.008419 sec W tool.cpp:3348] HIP (compiler) version ROCm 7 initialized (instance=0) W simple_timer.cpp:55] [rocprofv3] './hip/vector_add.exe' :: 0.000000 sec W tool.cpp:3348] HIP (runtime) version ROCm 7 initialized (instance=0) W tool.cpp:3348] HSA version (ROCm 7 runtime) initialized (instance=0) W queue_controller.cpp:170] [queue-intercept] device-memory ring-buffer requested but profiling requires system-memory InterceptQueue; falling back to system-memory ring for agent (priority and CU-mask from the descriptor are not preserved) W simple_timer.cpp:55] [rocprofv3] './hip/vector_add.exe' :: 0.320845 sec W output_stream.cpp:110] Opened result file: profiling_output//_kernel_trace.csv W output_stream.cpp:110] Opened result file: profiling_output//_hsa_api_trace.csv W output_stream.cpp:110] Opened result file: profiling_output//_hip_api_trace.csv W output_stream.cpp:110] Opened result file: profiling_output//_memory_copy_trace.csv W output_stream.cpp:110] Opened result file: profiling_output//_memory_allocation_trace.csv W output_stream.cpp:110] Opened result file: profiling_output//_agent_info.csv W generateRocpd.cpp:1062] writing SQL database for process 103516 on node W generateRocpd.cpp:1086] Opened result file: profiling_output//_results.db (UUID=) W simple_timer.cpp:55] SQLite3 generation :: rocpd_string :: 0.001386 sec W simple_timer.cpp:55] SQLite3 generation :: rocpd_info_node :: 0.000002 sec W simple_timer.cpp:55] SQLite3 generation :: rocpd_info_process :: 0.000337 sec W simple_timer.cpp:55] SQLite3 generation :: rocpd_info_agent :: 0.003192 sec W simple_timer.cpp:55] SQLite3 generation :: rocpd_info_pmc :: 0.000001 sec W simple_timer.cpp:55] SQLite3 generation :: rocpd kernel info :: 0.000729 sec W simple_timer.cpp:55] SQLite3 generation :: rocpd_region :: 0.007755 sec W simple_timer.cpp:55] SQLite3 generation :: rocpd_kernel_dispatch :: 0.002329 sec W simple_timer.cpp:55] SQLite3 generation :: rocpd_pmc_event :: 0.000003 sec W simple_timer.cpp:55] SQLite3 generation :: rocpd_memory_copy :: 0.001685 sec W simple_timer.cpp:55] SQLite3 generation :: rocpd_graph_launch :: 0.000002 sec W simple_timer.cpp:55] SQLite3 generation :: rocpd_memory_allocate :: 0.001114 sec W simple_timer.cpp:55] SQLite3 generation :: rocpd_info_pmc: kfd :: 0.000262 sec W simple_timer.cpp:55] SQLite3 generation :: rocpd_pmc_event: kfd :: 0.001403 sec W simple_timer.cpp:55] SQLite3 generation :: rocpd_flush_pending :: 0.000249 sec W simple_timer.cpp:55] SQLite3 generation :: SQL indexing :: 0.000345 sec W simple_timer.cpp:55] SQLite3 generation :: total :: 0.040766 sec n = 16777216, block = 256, grid = 65536 kernel time : 0.985 ms effective BW : 204.3 GB/s result : PASSED ROCPROFV3 SUMMARY: | NAME | DOMAIN | CALLS | DURATION (nsec) | AVERAGE (nsec) | PERCENT (INC) | MIN (nsec) | MAX (nsec) | STDDEV | |-----------------------------------------------------|-------------------|-----------------|-----------------|-----------------|---------------|-----------------|-----------------|-----------------| | hipMemcpy | HIP_API | 3 | 208624365 | 6.954e+07 | 60.962548 | 1587652 | 205395320 | 1.177e+08 | | hipMalloc | HIP_API | 3 | 60060586 | 2.002e+07 | 17.550425 | 12430 | 60028066 | 3.465e+07 | | hsa_amd_queue_create | HSA_API | 1 | 41253326 | 4.125e+07 | 12.054718 | 41253326 | 41253326 | 0.000e+00 | | hsa_amd_memory_async_copy_on_engine | HSA_API | 6 | 16286076 | 2.714e+06 | 4.758987 | 2640 | 16268266 | 6.640e+06 | | hsa_amd_memory_lock_to_pool | HSA_API | 6 | 3106576 | 5.178e+05 | 0.907779 | 241830 | 1145062 | 3.275e+05 | | MEMORY_COPY_HOST_TO_DEVICE | MEMORY_COPY | 4 | 2498783 | 6.247e+05 | 0.730174 | 587864 | 730430 | 7.053e+04 | | hsa_signal_wait_scacquire | HSA_API | 6 | 2482463 | 4.137e+05 | 0.725406 | 9520 | 900511 | 4.485e+05 | | MEMORY_COPY_DEVICE_TO_HOST | MEMORY_COPY | 2 | 1225971 | 6.130e+05 | 0.358243 | 599985 | 625986 | 1.839e+04 | | hsa_amd_memory_pool_allocate | HSA_API | 6 | 1031901 | 1.720e+05 | 0.301534 | 11190 | 715221 | 2.745e+05 | | MEMORY_ALLOCATION_ALLOCATE | MEMORY_ALLOCATION | 6 | 1017191 | 1.695e+05 | 0.297235 | 10960 | 710861 | 2.735e+05 | | hipFree | HIP_API | 3 | 745071 | 2.484e+05 | 0.217719 | 198210 | 339921 | 7.942e+04 | | hsa_amd_memory_pool_free | HSA_API | 3 | 687590 | 2.292e+05 | 0.200922 | 196560 | 286030 | 4.940e+04 | | MEMORY_ALLOCATION_FREE | MEMORY_ALLOCATION | 3 | 684160 | 2.281e+05 | 0.199920 | 196270 | 283230 | 4.797e+04 | | hipLaunchKernel | HIP_API | 1 | 659141 | 6.591e+05 | 0.192609 | 659141 | 659141 | 0.000e+00 | | hsa_executable_load_agent_code_object | HSA_API | 2 | 462212 | 2.311e+05 | 0.135064 | 152671 | 309541 | 1.109e+05 | | hsa_executable_freeze | HSA_API | 2 | 447950 | 2.240e+05 | 0.130896 | 107090 | 340860 | 1.653e+05 | | hsa_iterate_agents | HSA_API | 1 | 312930 | 3.129e+05 | 0.091442 | 312930 | 312930 | 0.000e+00 | | hsa_amd_agents_allow_access | HSA_API | 2 | 239031 | 1.195e+05 | 0.069848 | 25650 | 213381 | 1.327e+05 | | hsa_code_object_reader_create_from_memory | HSA_API | 2 | 50460 | 2.523e+04 | 0.014745 | 12630 | 37830 | 1.782e+04 | | vector_add(float const*, float const*, float*, int) | KERNEL_DISPATCH | 1 | 45922 | 4.592e+04 | 0.013419 | 45922 | 45922 | 0.000e+00 | | hsa_amd_signal_create | HSA_API | 84 | 43690 | 5.201e+02 | 0.012767 | 40 | 14910 | 2.285e+03 | | hsa_agent_get_info | HSA_API | 433 | 40040 | 9.247e+01 | 0.011700 | 20 | 11190 | 5.532e+02 | | hipEventRecord | HIP_API | 2 | 31860 | 1.593e+04 | 0.009310 | 5710 | 26150 | 1.445e+04 | | hsa_amd_agent_iterate_memory_pools | HSA_API | 10 | 27801 | 2.780e+03 | 0.008124 | 2160 | 4120 | 5.984e+02 | | hsa_isa_get_info_alt | HSA_API | 16 | 24470 | 1.529e+03 | 0.007150 | 720 | 11240 | 2.606e+03 | | hsa_signal_store_screlease | HSA_API | 3 | 23920 | 7.973e+03 | 0.006990 | 860 | 14560 | 6.865e+03 | | hipEventSynchronize | HIP_API | 1 | 14740 | 1.474e+04 | 0.004307 | 14740 | 14740 | 0.000e+00 | | hsa_amd_memory_copy_engine_status | HSA_API | 17 | 10140 | 5.965e+02 | 0.002963 | 440 | 1730 | 4.174e+02 | | hsa_executable_create_alt | HSA_API | 2 | 9450 | 4.725e+03 | 0.002761 | 1970 | 7480 | 3.896e+03 | | hsa_signal_create | HSA_API | 15 | 9400 | 6.267e+02 | 0.002747 | 60 | 2830 | 7.620e+02 | | __hipRegisterFunction | HIP_API | 1 | 7940 | 7.940e+03 | 0.002320 | 7940 | 7940 | 0.000e+00 | | hipEventElapsedTime | HIP_API | 1 | 6110 | 6.110e+03 | 0.001785 | 6110 | 6110 | 0.000e+00 | | __hipRegisterFatBinary | HIP_API | 1 | 6080 | 6.080e+03 | 0.001777 | 6080 | 6080 | 0.000e+00 | | hipEventDestroy | HIP_API | 2 | 5220 | 2.610e+03 | 0.001525 | 510 | 4710 | 2.970e+03 | | hsa_amd_agent_memory_pool_get_info | HSA_API | 128 | 3910 | 3.055e+01 | 0.001143 | 20 | 330 | 2.736e+01 | | hsa_signal_load_relaxed | HSA_API | 49 | 3760 | 7.673e+01 | 0.001099 | 20 | 1030 | 1.750e+02 | | hsa_executable_get_symbol_by_name | HSA_API | 14 | 3040 | 2.171e+02 | 0.000888 | 100 | 710 | 2.116e+02 | | hsa_amd_memory_pool_get_info | HSA_API | 112 | 3000 | 2.679e+01 | 0.000877 | 20 | 120 | 1.076e+01 | | hsa_amd_pointer_info | HSA_API | 3 | 2820 | 9.400e+02 | 0.000824 | 670 | 1300 | 3.245e+02 | | hipEventCreate | HIP_API | 2 | 2280 | 1.140e+03 | 0.000666 | 130 | 2150 | 1.428e+03 | | hsa_amd_profiling_get_dispatch_time | HSA_API | 4 | 2000 | 5.000e+02 | 0.000584 | 50 | 960 | 5.197e+02 | | hsa_system_get_info | HSA_API | 41 | 1940 | 4.732e+01 | 0.000567 | 20 | 530 | 7.984e+01 | | hsa_amd_memory_unlock | HSA_API | 6 | 1920 | 3.200e+02 | 0.000561 | 80 | 1030 | 3.665e+02 | | hsa_signal_destroy | HSA_API | 2 | 1540 | 7.700e+02 | 0.000450 | 500 | 1040 | 3.818e+02 | | hsa_queue_add_write_index_screlease | HSA_API | 3 | 1300 | 4.333e+02 | 0.000380 | 40 | 1160 | 6.300e+02 | | hsa_executable_symbol_get_info | HSA_API | 28 | 1000 | 3.571e+01 | 0.000292 | 20 | 190 | 3.225e+01 | | __hipPopCallConfiguration | HIP_API | 1 | 980 | 9.800e+02 | 0.000286 | 980 | 980 | 0.000e+00 | | __hipPushCallConfiguration | HIP_API | 1 | 970 | 9.700e+02 | 0.000283 | 970 | 970 | 0.000e+00 | | hsa_agent_iterate_isas | HSA_API | 8 | 940 | 1.175e+02 | 0.000275 | 20 | 710 | 2.402e+02 | | hsa_amd_register_system_event_handler | HSA_API | 1 | 820 | 8.200e+02 | 0.000240 | 820 | 820 | 0.000e+00 | | hipGetLastError | HIP_API | 1 | 770 | 7.700e+02 | 0.000225 | 770 | 770 | 0.000e+00 | | hsa_amd_queue_get_info | HSA_API | 3 | 590 | 1.967e+02 | 0.000172 | 20 | 540 | 2.974e+02 | | hsa_system_get_major_extension_table | HSA_API | 1 | 520 | 5.200e+02 | 0.000152 | 520 | 520 | 0.000e+00 | | hsa_signal_silent_store_relaxed | HSA_API | 8 | 380 | 4.750e+01 | 0.000111 | 20 | 100 | 2.915e+01 | | hsa_amd_memory_get_preferred_copy_engine | HSA_API | 1 | 130 | 1.300e+02 | 0.000038 | 130 | 130 | 0.000e+00 | | hsa_amd_profiling_set_profiler_enabled | HSA_API | 1 | 90 | 9.000e+01 | 0.000026 | 90 | 90 | 0.000e+00 | W simple_timer.cpp:55] [rocprofv3] output generation :: 0.077366 sec W simple_timer.cpp:55] [rocprofv3] tool finalization :: 0.077755 sec