doc improvements for 1.0.0 part 2 (#330)
* update installation steps * Github Issue #50 Adding README's for samples * Making name change to ROCprofiler-SDK for consistency * Fix HIP trace documentation * Fix HSA trace in docs * Fix kernel trace in docs * Fixing memory copy and memory allocation traces * runtime trace and sys trace doc update * Fix scratch memory doc * kernel naming and filtering options * Adding collection period in docs * Perfetto configs update * summary output file * kernel trace format fix * update CHANGELOG * Agent index doc update * rocm-smi output * group by queue option * Updated --group-by-queue description * perfetto visualization --------- Co-authored-by: Ian Trowbridge <Ian.Trowbridge@amd.com>
Este cometimento está contido em:
Bhardwaj, Gopesh
cometido por
GitHub
GitHub
ascendente
4fbcfd142c
cometimento
ca7cce9e81
@@ -1,5 +1,7 @@
|
||||
"Domain","Function","Process_Id","Thread_Id","Correlation_Id","Start_Timestamp","End_Timestamp"
|
||||
"HIP_COMPILER_API","__hipRegisterFatBinary",208,208,1,1508780270085955,1508780270096795
|
||||
"HIP_COMPILER_API","__hipRegisterFunction",208,208,2,1508780270104242,1508780270115355
|
||||
"HIP_COMPILER_API","__hipPushCallConfiguration",208,208,3,1508780613897816,1508780613898701
|
||||
"HIP_COMPILER_API","__hipPopCallConfiguration",208,208,4,1508780613901714,1508780613902200
|
||||
"HIP_COMPILER_API_EXT","__hipRegisterFatBinary",15,15,1,1055015439953054,1055015439976484
|
||||
"HIP_COMPILER_API_EXT","__hipRegisterFunction",15,15,2,1055015439992584,1055015440011104
|
||||
"HIP_COMPILER_API_EXT","__hipRegisterFunction",15,15,3,1055015440011744,1055015440013824
|
||||
"HIP_COMPILER_API_EXT","__hipRegisterFunction",15,15,4,1055015440014244,1055015440014534
|
||||
"HIP_COMPILER_API_EXT","__hipRegisterFunction",15,15,5,1055015440014854,1055015440015524
|
||||
|
||||
|
||||
|
@@ -1,9 +1,9 @@
|
||||
"Domain","Function","Process_Id","Thread_Id","Correlation_Id","Start_Timestamp","End_Timestamp"
|
||||
"HIP_RUNTIME_API","hipGetDevicePropertiesR0600",238,238,1,1191915574691984,1191915687784011
|
||||
"HIP_RUNTIME_API","hipMalloc",238,238,2,1191915691312459,1191915691388696
|
||||
"HIP_RUNTIME_API","hipMalloc",238,238,3,1191915691390637,1191915691423279
|
||||
"HIP_RUNTIME_API","hipMemcpy",238,238,4,1191915691439107,1191916547828448
|
||||
"HIP_RUNTIME_API","hipLaunchKernel",238,238,5,1191916547842972,1191916548408842
|
||||
"HIP_RUNTIME_API","hipMemcpy",238,238,6,1191916548412677,1191916550217834
|
||||
"HIP_RUNTIME_API","hipFree",238,238,7,1191916562618151,1191916562789093
|
||||
"HIP_RUNTIME_API","hipFree",238,238,8,1191916562790923,1191916562836351
|
||||
"HIP_RUNTIME_API_EXT","hipGetDevicePropertiesR0600",238,238,1,1191915574691984,1191915687784011
|
||||
"HIP_RUNTIME_API_EXT","hipMalloc",238,238,2,1191915691312459,1191915691388696
|
||||
"HIP_RUNTIME_API_EXT","hipMalloc",238,238,3,1191915691390637,1191915691423279
|
||||
"HIP_RUNTIME_API_EXT","hipMemcpy",238,238,4,1191915691439107,1191916547828448
|
||||
"HIP_RUNTIME_API_EXT","hipLaunchKernel",238,238,5,1191916547842972,1191916548408842
|
||||
"HIP_RUNTIME_API_EXT","hipMemcpy",238,238,6,1191916548412677,1191916550217834
|
||||
"HIP_RUNTIME_API_EXT","hipFree",238,238,7,1191916562618151,1191916562789093
|
||||
"HIP_RUNTIME_API_EXT","hipFree",238,238,8,1191916562790923,1191916562836351
|
||||
|
||||
|
@@ -0,0 +1,18 @@
|
||||
"Domain","Function","Process_Id","Thread_Id","Correlation_Id","Start_Timestamp","End_Timestamp"
|
||||
"HIP_COMPILER_API_EXT","__hipRegisterFatBinary",15,15,1,1055015439953054,1055015439976484
|
||||
"HIP_COMPILER_API_EXT","__hipRegisterFunction",15,15,2,1055015439992584,1055015440011104
|
||||
"HIP_COMPILER_API_EXT","__hipRegisterFunction",15,15,3,1055015440011744,1055015440013824
|
||||
"HIP_COMPILER_API_EXT","__hipRegisterFunction",15,15,4,1055015440014244,1055015440014534
|
||||
"HIP_COMPILER_API_EXT","__hipRegisterFunction",15,15,5,1055015440014854,1055015440015524
|
||||
"HIP_RUNTIME_API_EXT","hipGetDeviceCount",15,15,6,1055015440617618,1055015539800733
|
||||
"HIP_RUNTIME_API_EXT","hipSetDevice",15,15,7,1055015539819503,1055015539821693
|
||||
"HIP_RUNTIME_API_EXT","hipDeviceSynchronize",15,15,8,1055015539832333,1055015539840903
|
||||
"HIP_RUNTIME_API_EXT","hipStreamCreateWithFlags",15,15,9,1055015539861673,1055015865247140
|
||||
"HIP_RUNTIME_API_EXT","hipHostMalloc",15,15,10,1055015865309761,1055015865849494
|
||||
"HIP_RUNTIME_API_EXT","hipHostMalloc",15,15,11,1055015865850944,1055015866265546
|
||||
"HIP_RUNTIME_API_EXT","hipHostMalloc",15,15,12,1055015866266646,1055015867082900
|
||||
"HIP_RUNTIME_API_EXT","hipMallocAsync",15,15,13,1055015867356542,1055015867662314
|
||||
"HIP_RUNTIME_API_EXT","hipMallocAsync",15,15,14,1055015867664174,1055015867937465
|
||||
"HIP_RUNTIME_API_EXT","hipMallocAsync",15,15,15,1055015867938815,1055015868219987
|
||||
"HIP_RUNTIME_API_EXT","hipMemcpyAsync",15,15,16,1055015868240137,1055015917307652
|
||||
"HIP_RUNTIME_API_EXT","hipMemcpyAsync",15,15,17,1055015917337263,1055015917360493
|
||||
|
@@ -0,0 +1,34 @@
|
||||
"Domain","Function","Process_Id","Thread_Id","Correlation_Id","Start_Timestamp","End_Timestamp"
|
||||
"HSA_CORE_API","hsa_system_get_major_extension_table",57,57,1,1056813747808832,1056813747809252
|
||||
"HSA_CORE_API","hsa_agent_get_info",57,57,3,1056813747826572,1056813747826672
|
||||
"HSA_CORE_API","hsa_agent_get_info",57,57,4,1056813747837582,1056813747837622
|
||||
"HSA_CORE_API","hsa_agent_get_info",57,57,5,1056813747838542,1056813747838582
|
||||
"HSA_CORE_API","hsa_agent_get_info",57,57,6,1056813747839042,1056813747839082
|
||||
"HSA_CORE_API","hsa_agent_get_info",57,57,7,1056813747839512,1056813747839622
|
||||
"HSA_CORE_API","hsa_iterate_agents",57,57,2,1056813747821012,1056813747839832
|
||||
"HSA_CORE_API","hsa_agent_get_info",57,57,8,1056813747843832,1056813747844132
|
||||
"HSA_CORE_API","hsa_agent_get_info",57,57,9,1056813747844482,1056813747844542
|
||||
"HSA_CORE_API","hsa_agent_iterate_isas",57,57,10,1056813747849402,1056813747850422
|
||||
"HSA_CORE_API","hsa_isa_get_info_alt",57,57,11,1056813747853542,1056813747875253
|
||||
"HSA_CORE_API","hsa_isa_get_info_alt",57,57,12,1056813747875883,1056813747878353
|
||||
"HSA_CORE_API","hsa_agent_get_info",57,57,13,1056813747886343,1056813747886403
|
||||
"HSA_CORE_API","hsa_agent_get_info",57,57,54,1056813748282015,1056813748282085
|
||||
"HSA_CORE_API","hsa_system_get_info",57,57,55,1056813748282465,1056813748282505
|
||||
"HSA_CORE_API","hsa_signal_create",57,57,56,1056813749083419,1056813749085399
|
||||
"HSA_CORE_API","hsa_agent_get_info",57,57,57,1056813749741363,1056813749741443
|
||||
"HSA_CORE_API","hsa_queue_create",57,57,58,1056813749744053,1056813856914188
|
||||
"HSA_CORE_API","hsa_signal_create",57,57,59,1056813857149169,1056813857154109
|
||||
"HSA_CORE_API","hsa_signal_create",57,57,60,1056813857154929,1056813857155389
|
||||
"HSA_CORE_API","hsa_signal_create",57,57,61,1056813857155949,1056813857156429
|
||||
"HSA_CORE_API","hsa_signal_create",57,57,62,1056813857157169,1056813857157349
|
||||
"HSA_CORE_API","hsa_executable_create_alt",57,57,63,1056813965439362,1056813965466952
|
||||
"HSA_CORE_API","hsa_code_object_reader_create_from_memory",57,57,64,1056813965476642,1056813965587493
|
||||
"HSA_CORE_API","hsa_executable_load_agent_code_object",57,57,65,1056813965592483,1056813965965295
|
||||
"HSA_CORE_API","hsa_signal_create",57,57,67,1056813966149786,1056813966151706
|
||||
"HSA_CORE_API","hsa_signal_wait_scacquire",57,57,68,1056813966156596,1056813966158646
|
||||
"HSA_CORE_API","hsa_signal_destroy",57,57,69,1056813966162276,1056813966163746
|
||||
"HSA_CORE_API","hsa_executable_freeze",57,57,66,1056813965973105,1056813966778050
|
||||
"HSA_CORE_API","hsa_executable_get_symbol_by_name",57,57,70,1056813966800070,1056813966801880
|
||||
"HSA_CORE_API","hsa_executable_symbol_get_info",57,57,71,1056813966805750,1056813966805980
|
||||
"HSA_CORE_API","hsa_executable_symbol_get_info",57,57,72,1056813966806300,1056813966806340
|
||||
|
||||
|
@@ -1,9 +1,10 @@
|
||||
"Kind","Agent_Id","Queue_Id","Stream_Id","Thread_Id","Dispatch_Id","Kernel_Id","Kernel_Name","Correlation_Id","Start_Timestamp","End_Timestamp","Private_Segment_Size","Group_Segment_Size","Workgroup_Size_X","Workgroup_Size_Y","Workgroup_Size_Z","Grid_Size_X","Grid_Size_Y","Grid_Size_Z"
|
||||
"KERNEL_DISPATCH",2,1,1,21228,1,11,"void addition_kernel<float>(float*, float const*, float const*, int, int)",1937,2414192765353337,2414192765369494,0,0,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH",2,1,1,21228,2,14,"subtract_kernel(float*, float const*, float const*, int, int)",1945,2414192765424862,2414192765435326,0,0,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH",2,1,1,21228,3,13,"multiply_kernel(float*, float const*, float const*, int, int)",1953,2414192765487486,2414192765497669,0,0,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH",2,1,1,21228,4,12,"divide_kernel(float*, float const*, float const*, int, int)",1961,2414192765545619,2414192765555722,0,0,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH",2,2,2,21228,5,11,"void addition_kernel<float>(float*, float const*, float const*, int, int)",1969,2414192765608844,2414192765621674,0,0,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH",2,2,2,21228,6,14,"subtract_kernel(float*, float const*, float const*, int, int)",1977,2414192765658519,2414192765669424,0,0,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH",2,2,2,21228,7,13,"multiply_kernel(float*, float const*, float const*, int, int)",1985,2414192765715650,2414192765726795,0,0,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH",2,2,2,21228,8,12,"divide_kernel(float*, float const*, float const*, int, int)",1993,2414192765773422,2414192765784969,0,0,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH","Agent 4",3,4,77,9,12,"void addition_kernel<float>(float*, float const*, float const*, int, int)",9,1057678125307992,1057678125319352,0,0,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH","Agent 4",2,3,77,8,11,"divide_kernel(float*, float const*, float const*, int, int)",8,1057678125310912,1057678125319952,0,0,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH","Agent 4",2,3,77,7,13,"multiply_kernel(float*, float const*, float const*, int, int)",7,1057678125298952,1057678125310912,0,0,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH","Agent 4",2,3,77,6,14,"subtract_kernel(float*, float const*, float const*, int, int)",6,1057678125288912,1057678125298952,0,0,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH","Agent 4",2,3,77,5,12,"void addition_kernel<float>(float*, float const*, float const*, int, int)",5,1057678125279112,1057678125288912,0,0,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH","Agent 4",3,4,77,10,14,"subtract_kernel(float*, float const*, float const*, int, int)",10,1057678125319352,1057678125328912,0,0,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH","Agent 4",3,4,77,12,11,"divide_kernel(float*, float const*, float const*, int, int)",12,1057678125356832,1057678125366712,0,0,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH","Agent 4",3,4,77,11,13,"multiply_kernel(float*, float const*, float const*, int, int)",11,1057678125344352,1057678125356832,0,0,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH","Agent 4",4,5,77,13,12,"void addition_kernel<float>(float*, float const*, float const*, int, int)",13,1057678125382792,1057678125394032,0,0,64,1,1,1024,1024,1
|
||||
|
||||
|
@@ -0,0 +1,5 @@
|
||||
"Kind","Agent_Id","Queue_Id","Stream_Id","Thread_Id","Dispatch_Id","Kernel_Id","Kernel_Name","Correlation_Id","Start_Timestamp","End_Timestamp","Private_Segment_Size","Group_Segment_Size","Workgroup_Size_X","Workgroup_Size_Y","Workgroup_Size_Z","Grid_Size_X","Grid_Size_Y","Grid_Size_Z"
|
||||
"KERNEL_DISPATCH","Agent 4",1,2,123,1,11,"addition_kernel",1,1143263119836160,1143263119848360,0,0,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH","Agent 4",2,3,123,6,14,"subtract_kernel",6,1143263119886120,1143263119896040,0,0,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH","Agent 4",2,3,123,5,11,"addition_kernel",5,1143263119876240,1143263119886120,0,0,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH","Agent 4",1,2,123,4,12,"divide_kernel",4,1143263119866920,1143263119878960,0,0,64,1,1,1024,1024,1
|
||||
|
@@ -1,7 +1,7 @@
|
||||
"Kind","Operation","Agent_Id","Allocation_Size","Address","Correlation_Id","Start_Timestamp","End_Timestamp"
|
||||
"MEMORY_ALLOCATION","MEMORY_ALLOCATION_ALLOCATE",0,1024,0x7fb2d0005000,11,3721742710532634,3721742710584854
|
||||
"MEMORY_ALLOCATION","MEMORY_ALLOCATION_FREE",0,0,0x7fb2d0005000,12,3721742710596404,3721742710933366
|
||||
"MEMORY_ALLOCATION","MEMORY_ALLOCATION_ALLOCATE",0,1024,0x7fb2d0005000,13,3721742710941416,3721742710960916
|
||||
"MEMORY_ALLOCATION","MEMORY_ALLOCATION_FREE",0,0,0x7fb2d0005000,14,3721742710967236,3721742711197647
|
||||
"MEMORY_ALLOCATION","MEMORY_ALLOCATION_ALLOCATE",0,1024,0x7fb2d0005000,15,3721742711204077,3721742711219717
|
||||
"MEMORY_ALLOCATION","MEMORY_ALLOCATION_FREE",0,0,0x7fb2d0005000,16,3721742711225857,3721742711466018
|
||||
"MEMORY_ALLOCATION","MEMORY_ALLOCATION_ALLOCATE",Agent 0,1024,0x7fb2d0005000,11,3721742710532634,3721742710584854
|
||||
"MEMORY_ALLOCATION","MEMORY_ALLOCATION_FREE",Agent 0,0,0x7fb2d0005000,12,3721742710596404,3721742710933366
|
||||
"MEMORY_ALLOCATION","MEMORY_ALLOCATION_ALLOCATE",Agent 0,1024,0x7fb2d0005000,13,3721742710941416,3721742710960916
|
||||
"MEMORY_ALLOCATION","MEMORY_ALLOCATION_FREE",Agent 0,0,0x7fb2d0005000,14,3721742710967236,3721742711197647
|
||||
"MEMORY_ALLOCATION","MEMORY_ALLOCATION_ALLOCATE",Agent 0,1024,0x7fb2d0005000,15,3721742711204077,3721742711219717
|
||||
"MEMORY_ALLOCATION","MEMORY_ALLOCATION_FREE",Agent 0,0,0x7fb2d0005000,16,3721742711225857,3721742711466018
|
||||
|
||||
|
@@ -1,5 +1,5 @@
|
||||
"Kind","Direction","Stream_Id","Source_Agent_Id","Destination_Agent_Id","Correlation_Id","Start_Timestamp","End_Timestamp"
|
||||
"MEMORY_COPY","MEMORY_COPY_HOST_TO_DEVICE",1,0,2,952,2414192684609085,2414192684710679
|
||||
"MEMORY_COPY","MEMORY_COPY_HOST_TO_DEVICE",1,0,2,960,2414192684873841,2414192684973470
|
||||
"MEMORY_COPY","MEMORY_COPY_HOST_TO_DEVICE",2,0,2,1066,2414192706436949,2414192706538622
|
||||
"MEMORY_COPY","MEMORY_COPY_HOST_TO_DEVICE",2,0,2,1074,2414192706592442,2414192706692312
|
||||
"MEMORY_COPY","MEMORY_COPY_HOST_TO_DEVICE",0,"Agent 0","Agent 4",1,1057963336487172,1057963336564212
|
||||
"MEMORY_COPY","MEMORY_COPY_HOST_TO_DEVICE",0,"Agent 0","Agent 4",2,1057963336783973,1057963336859334
|
||||
"MEMORY_COPY","MEMORY_COPY_DEVICE_TO_HOST",0,"Agent 4","Agent 0",23,1057963497396292,1057963497471732
|
||||
"MEMORY_COPY","MEMORY_COPY_DEVICE_TO_HOST",0,"Agent 4","Agent 0",24,1057963498099125,1057963498200446
|
||||
|
||||
|
Ficheiro binário não mostrado.
|
Depois Largura: | Altura: | Tamanho: 174 KiB |
Ficheiro binário não mostrado.
|
Depois Largura: | Altura: | Tamanho: 124 KiB |
Ficheiro binário não mostrado.
|
Depois Largura: | Altura: | Tamanho: 124 KiB |
@@ -0,0 +1,11 @@
|
||||
============================================ ROCm System Management Interface ============================================
|
||||
====================================================== Concise Info ======================================================
|
||||
Device Node IDs Temp Power Partitions SCLK MCLK Fan Perf PwrCap VRAM% GPU%
|
||||
(DID, GUID) (Junction) (Socket) (Mem, Compute, ID)
|
||||
==========================================================================================================================
|
||||
0 4 0x74a0, 50375 48.0°C 110.0W NPS1, SPX, 0 98Mhz 1300Mhz 0% auto 550.0W 0% 0%
|
||||
1 5 0x74a0, 20890 53.0°C 113.0W NPS1, SPX, 0 99Mhz 1200Mhz 0% auto 550.0W 0% 0%
|
||||
2 6 0x74a0, 44670 52.0°C 125.0W NPS1, SPX, 0 100Mhz 1300Mhz 0% auto 550.0W 0% 0%
|
||||
3 7 0x74a0, 15139 47.0°C 115.0W NPS1, SPX, 0 100Mhz 1300Mhz 0% auto 550.0W 0% 0%
|
||||
==========================================================================================================================
|
||||
================================================== End of ROCm SMI Log ===================================================
|
||||
@@ -0,0 +1,3 @@
|
||||
"Kind","Operation","Agent_Id","Queue_Id","Thread_Id","Alloc_Flags","Start_Timestamp","End_Timestamp"
|
||||
"SCRATCH_MEMORY","SCRATCH_MEMORY_ALLOC","Agent 4",1,113,0,1124926523146168,1124926554133606
|
||||
"SCRATCH_MEMORY","SCRATCH_MEMORY_ALLOC","Agent 4",1,113,0,1124926554522025,1124927132642186
|
||||
|
Ficheiro binário não mostrado.
|
Depois Largura: | Altura: | Tamanho: 148 KiB |
Ficheiro binário não mostrado.
|
Depois Largura: | Altura: | Tamanho: 124 KiB |
@@ -0,0 +1,154 @@
|
||||
|
||||
ROCPROFV3 HSA_API SUMMARY:
|
||||
|
||||
| NAME | DOMAIN | CALLS | DURATION (nsec) | AVERAGE (nsec) | PERCENT (INC) | MIN (nsec) | MAX (nsec) | STDDEV |
|
||||
|-------------------------------------------|--------------|-----------------|-----------------|-----------------|---------------|-----------------|-----------------|-----------------|
|
||||
| hsa_queue_create | HSA_API | 4 | 280077621 | 7.002e+07 | 75.372632 | 55026812 | 113288760 | 2.885e+07 |
|
||||
| hsa_amd_memory_async_copy_on_engine | HSA_API | 24 | 55617052 | 2.317e+06 | 14.967292 | 7580 | 55195188 | 1.126e+07 |
|
||||
| hsa_amd_memory_pool_allocate | HSA_API | 67 | 26428438 | 3.945e+05 | 7.112246 | 1510 | 857592 | 1.782e+05 |
|
||||
| hsa_amd_memory_pool_free | HSA_API | 72 | 5176173 | 7.189e+04 | 1.392977 | 290 | 170374 | 3.903e+04 |
|
||||
| hsa_executable_freeze | HSA_API | 2 | 964125 | 4.821e+05 | 0.259459 | 437471 | 526654 | 6.306e+04 |
|
||||
| hsa_signal_wait_scacquire | HSA_API | 26 | 853122 | 3.281e+04 | 0.229587 | 2530 | 100782 | 3.394e+04 |
|
||||
| hsa_executable_load_agent_code_object | HSA_API | 2 | 616175 | 3.081e+05 | 0.165821 | 254476 | 361699 | 7.582e+04 |
|
||||
| hsa_amd_agents_allow_access | HSA_API | 35 | 430680 | 1.231e+04 | 0.115902 | 4830 | 55182 | 9.939e+03 |
|
||||
| hsa_signal_store_screlease | HSA_API | 56 | 381491 | 6.812e+03 | 0.102664 | 1560 | 41831 | 7.895e+03 |
|
||||
| hsa_signal_create | HSA_API | 107 | 160889 | 1.504e+03 | 0.043297 | 80 | 5650 | 1.475e+03 |
|
||||
| hsa_code_object_reader_create_from_memory | HSA_API | 2 | 151314 | 7.566e+04 | 0.040721 | 32121 | 119193 | 6.157e+04 |
|
||||
| hsa_signal_load_relaxed | HSA_API | 1296 | 137626 | 1.062e+02 | 0.037037 | 20 | 2930 | 2.712e+02 |
|
||||
| hsa_signal_destroy | HSA_API | 618 | 111224 | 1.800e+02 | 0.029932 | 40 | 1540 | 2.429e+02 |
|
||||
| hsa_agent_get_info | HSA_API | 65 | 77472 | 1.192e+03 | 0.020849 | 30 | 47121 | 6.341e+03 |
|
||||
| hsa_amd_signal_create | HSA_API | 512 | 61290 | 1.197e+02 | 0.016494 | 40 | 930 | 1.559e+02 |
|
||||
| hsa_amd_signal_async_handler | HSA_API | 24 | 52641 | 2.193e+03 | 0.014166 | 1180 | 4020 | 9.252e+02 |
|
||||
| hsa_executable_iterate_symbols | HSA_API | 14 | 52521 | 3.752e+03 | 0.014134 | 2740 | 6940 | 1.105e+03 |
|
||||
| hsa_amd_memory_copy_engine_status | HSA_API | 18 | 47370 | 2.632e+03 | 0.012748 | 260 | 7990 | 2.274e+03 |
|
||||
| hsa_iterate_agents | HSA_API | 1 | 41391 | 4.139e+04 | 0.011139 | 41391 | 41391 | 0.000e+00 |
|
||||
| hsa_executable_create_alt | HSA_API | 2 | 40470 | 2.024e+04 | 0.010891 | 7530 | 32940 | 1.797e+04 |
|
||||
| hsa_isa_get_info_alt | HSA_API | 2 | 30391 | 1.520e+04 | 0.008179 | 2490 | 27901 | 1.797e+04 |
|
||||
| hsa_signal_silent_store_relaxed | HSA_API | 48 | 24920 | 5.192e+02 | 0.006706 | 20 | 4570 | 7.120e+02 |
|
||||
| hsa_amd_agent_iterate_memory_pools | HSA_API | 5 | 20221 | 4.044e+03 | 0.005442 | 2561 | 8600 | 2.574e+03 |
|
||||
| hsa_queue_add_write_index_screlease | HSA_API | 56 | 7270 | 1.298e+02 | 0.001956 | 30 | 2310 | 3.471e+02 |
|
||||
| hsa_amd_profiling_set_profiler_enabled | HSA_API | 4 | 5600 | 1.400e+03 | 0.001507 | 1370 | 1470 | 4.690e+01 |
|
||||
| hsa_executable_symbol_get_info | HSA_API | 152 | 5470 | 3.599e+01 | 0.001472 | 30 | 340 | 3.563e+01 |
|
||||
| hsa_queue_load_read_index_relaxed | HSA_API | 56 | 4560 | 8.143e+01 | 0.001227 | 20 | 1310 | 1.863e+02 |
|
||||
| hsa_executable_get_symbol_by_name | HSA_API | 14 | 4500 | 3.214e+02 | 0.001211 | 110 | 1510 | 4.732e+02 |
|
||||
| hsa_queue_load_read_index_scacquire | HSA_API | 56 | 3040 | 5.429e+01 | 0.000818 | 30 | 690 | 8.705e+01 |
|
||||
| hsa_amd_memory_pool_get_info | HSA_API | 43 | 1770 | 4.116e+01 | 0.000476 | 30 | 270 | 3.640e+01 |
|
||||
| hsa_system_get_info | HSA_API | 4 | 1750 | 4.375e+02 | 0.000471 | 40 | 830 | 3.544e+02 |
|
||||
| hsa_amd_agent_memory_pool_get_info | HSA_API | 13 | 1140 | 8.769e+01 | 0.000307 | 30 | 640 | 1.664e+02 |
|
||||
| hsa_agent_iterate_isas | HSA_API | 1 | 700 | 7.000e+02 | 0.000188 | 700 | 700 | 0.000e+00 |
|
||||
| hsa_system_get_major_extension_table | HSA_API | 1 | 190 | 1.900e+02 | 0.000051 | 190 | 190 | 0.000e+00 |
|
||||
|
||||
|
||||
ROCPROFV3 HIP_API SUMMARY:
|
||||
|
||||
| NAME | DOMAIN | CALLS | DURATION (nsec) | AVERAGE (nsec) | PERCENT (INC) | MIN (nsec) | MAX (nsec) | STDDEV |
|
||||
|------------------------------------------|--------------|-----------------|-----------------|-----------------|---------------|-----------------|-----------------|-----------------|
|
||||
| hipStreamCreateWithFlags | HIP_API | 8 | 406507215 | 5.081e+07 | 71.307804 | 735979 | 233800881 | 7.889e+07 |
|
||||
| hipGetDeviceCount | HIP_API | 1 | 76707894 | 7.671e+07 | 13.455780 | 76707894 | 76707894 | 0.000e+00 |
|
||||
| hipMemcpyAsync | HIP_API | 24 | 56109444 | 2.338e+06 | 9.842485 | 11640 | 55299811 | 1.128e+07 |
|
||||
| hipHostMalloc | HIP_API | 24 | 13007523 | 5.420e+05 | 2.281726 | 416631 | 866382 | 1.206e+05 |
|
||||
| hipMallocAsync | HIP_API | 24 | 7304847 | 3.044e+05 | 1.281386 | 275397 | 353719 | 2.207e+04 |
|
||||
| hipHostFree | HIP_API | 24 | 2786484 | 1.161e+05 | 0.488793 | 72242 | 221646 | 4.606e+04 |
|
||||
| hipStreamDestroy | HIP_API | 8 | 2137924 | 2.672e+05 | 0.375026 | 221596 | 377469 | 5.489e+04 |
|
||||
| hipLaunchKernel | HIP_API | 32 | 2080214 | 6.501e+04 | 0.364902 | 8850 | 1608721 | 2.819e+05 |
|
||||
| hipFree | HIP_API | 24 | 1572948 | 6.554e+04 | 0.275920 | 2130 | 186994 | 4.815e+04 |
|
||||
| hipStreamSynchronize | HIP_API | 24 | 1452706 | 6.053e+04 | 0.254828 | 20810 | 135803 | 3.469e+04 |
|
||||
| __hipRegisterFunction | HIP_API | 4 | 294207 | 7.355e+04 | 0.051609 | 210 | 291807 | 1.455e+05 |
|
||||
| hipDeviceSynchronize | HIP_API | 4 | 50663 | 1.267e+04 | 0.008887 | 510 | 23621 | 9.554e+03 |
|
||||
| __hipRegisterFatBinary | HIP_API | 1 | 43811 | 4.381e+04 | 0.007685 | 43811 | 43811 | 0.000e+00 |
|
||||
| __hipPushCallConfiguration | HIP_API | 32 | 6250 | 1.953e+02 | 0.001096 | 60 | 3640 | 6.308e+02 |
|
||||
| __hipPopCallConfiguration | HIP_API | 32 | 4780 | 1.494e+02 | 0.000838 | 60 | 2520 | 4.340e+02 |
|
||||
| hipGetLastError | HIP_API | 32 | 4471 | 1.397e+02 | 0.000784 | 60 | 2381 | 4.092e+02 |
|
||||
| hipSetDevice | HIP_API | 1 | 2570 | 2.570e+03 | 0.000451 | 2570 | 2570 | 0.000e+00 |
|
||||
|
||||
|
||||
ROCPROFV3 KERNEL_DISPATCH SUMMARY:
|
||||
|
||||
| NAME | DOMAIN | CALLS | DURATION (nsec) | AVERAGE (nsec) | PERCENT (INC) | MIN (nsec) | MAX (nsec) | STDDEV |
|
||||
|---------------------------------------------------------------------------|-----------------|-----------------|-----------------|-----------------|---------------|-----------------|-----------------|-----------------|
|
||||
| void addition_kernel<float>(float*, float const*, float const*, int, int) | KERNEL_DISPATCH | 8 | 184324 | 2.304e+04 | 40.681542 | 11200 | 98802 | 3.062e+04 |
|
||||
| divide_kernel(float*, float const*, float const*, int, int) | KERNEL_DISPATCH | 8 | 94482 | 1.181e+04 | 20.852811 | 10240 | 13520 | 1.061e+03 |
|
||||
| multiply_kernel(float*, float const*, float const*, int, int) | KERNEL_DISPATCH | 8 | 91763 | 1.147e+04 | 20.252709 | 9800 | 12800 | 9.417e+02 |
|
||||
| subtract_kernel(float*, float const*, float const*, int, int) | KERNEL_DISPATCH | 8 | 82521 | 1.032e+04 | 18.212938 | 8320 | 12920 | 1.436e+03 |
|
||||
|
||||
|
||||
ROCPROFV3 MEMORY_COPY SUMMARY:
|
||||
|
||||
| NAME | DOMAIN | CALLS | DURATION (nsec) | AVERAGE (nsec) | PERCENT (INC) | MIN (nsec) | MAX (nsec) | STDDEV |
|
||||
|------------------------------------------|--------------|-----------------|-----------------|-----------------|---------------|-----------------|-----------------|-----------------|
|
||||
| MEMORY_COPY_HOST_TO_DEVICE | MEMORY_COPY | 16 | 3691929 | 2.307e+05 | 85.494053 | 74842 | 284487 | 6.265e+04 |
|
||||
| MEMORY_COPY_DEVICE_TO_HOST | MEMORY_COPY | 8 | 626417 | 7.830e+04 | 14.505947 | 74842 | 98603 | 8.207e+03 |
|
||||
|
||||
|
||||
ROCPROFV3 MEMORY_ALLOCATION SUMMARY:
|
||||
|
||||
| NAME | DOMAIN | CALLS | DURATION (nsec) | AVERAGE (nsec) | PERCENT (INC) | MIN (nsec) | MAX (nsec) | STDDEV |
|
||||
|------------------------------------------|-------------------|-----------------|-----------------|-----------------|---------------|-----------------|-----------------|-----------------|
|
||||
| MEMORY_ALLOCATION_ALLOCATE | MEMORY_ALLOCATION | 67 | 26314096 | 3.927e+05 | 83.661617 | 950 | 856812 | 1.785e+05 |
|
||||
| MEMORY_ALLOCATION_FREE | MEMORY_ALLOCATION | 72 | 5138913 | 7.137e+04 | 16.338383 | 20 | 166234 | 3.882e+04 |
|
||||
|
||||
|
||||
ROCPROFV3 SUMMARY:
|
||||
|
||||
| NAME | DOMAIN | CALLS | DURATION (nsec) | AVERAGE (nsec) | PERCENT (INC) | MIN (nsec) | MAX (nsec) | STDDEV |
|
||||
|---------------------------------------------------------------------------|-------------------|-----------------|-----------------|-----------------|---------------|-----------------|-----------------|-----------------|
|
||||
| hipStreamCreateWithFlags | HIP_API | 8 | 406507215 | 5.081e+07 | 41.569873 | 735979 | 233800881 | 7.889e+07 |
|
||||
| hsa_queue_create | HSA_API | 4 | 280077621 | 7.002e+07 | 28.641044 | 55026812 | 113288760 | 2.885e+07 |
|
||||
| hipGetDeviceCount | HIP_API | 1 | 76707894 | 7.671e+07 | 7.844233 | 76707894 | 76707894 | 0.000e+00 |
|
||||
| hipMemcpyAsync | HIP_API | 24 | 56109444 | 2.338e+06 | 5.737813 | 11640 | 55299811 | 1.128e+07 |
|
||||
| hsa_amd_memory_async_copy_on_engine | HSA_API | 24 | 55617052 | 2.317e+06 | 5.687461 | 7580 | 55195188 | 1.126e+07 |
|
||||
| hsa_amd_memory_pool_allocate | HSA_API | 67 | 26428438 | 3.945e+05 | 2.702601 | 1510 | 857592 | 1.782e+05 |
|
||||
| MEMORY_ALLOCATION_ALLOCATE | MEMORY_ALLOCATION | 67 | 26314096 | 3.927e+05 | 2.690908 | 950 | 856812 | 1.785e+05 |
|
||||
| hipHostMalloc | HIP_API | 24 | 13007523 | 5.420e+05 | 1.330164 | 416631 | 866382 | 1.206e+05 |
|
||||
| hipMallocAsync | HIP_API | 24 | 7304847 | 3.044e+05 | 0.747002 | 275397 | 353719 | 2.207e+04 |
|
||||
| hsa_amd_memory_pool_free | HSA_API | 72 | 5176173 | 7.189e+04 | 0.529321 | 290 | 170374 | 3.903e+04 |
|
||||
| MEMORY_ALLOCATION_FREE | MEMORY_ALLOCATION | 72 | 5138913 | 7.137e+04 | 0.525511 | 20 | 166234 | 3.882e+04 |
|
||||
| MEMORY_COPY_HOST_TO_DEVICE | MEMORY_COPY | 16 | 3691929 | 2.307e+05 | 0.377541 | 74842 | 284487 | 6.265e+04 |
|
||||
| hipHostFree | HIP_API | 24 | 2786484 | 1.161e+05 | 0.284949 | 72242 | 221646 | 4.606e+04 |
|
||||
| hipStreamDestroy | HIP_API | 8 | 2137924 | 2.672e+05 | 0.218626 | 221596 | 377469 | 5.489e+04 |
|
||||
| hipLaunchKernel | HIP_API | 32 | 2080214 | 6.501e+04 | 0.212725 | 8850 | 1608721 | 2.819e+05 |
|
||||
| hipFree | HIP_API | 24 | 1572948 | 6.554e+04 | 0.160851 | 2130 | 186994 | 4.815e+04 |
|
||||
| hipStreamSynchronize | HIP_API | 24 | 1452706 | 6.053e+04 | 0.148555 | 20810 | 135803 | 3.469e+04 |
|
||||
| hsa_executable_freeze | HSA_API | 2 | 964125 | 4.821e+05 | 0.098592 | 437471 | 526654 | 6.306e+04 |
|
||||
| hsa_signal_wait_scacquire | HSA_API | 26 | 853122 | 3.281e+04 | 0.087241 | 2530 | 100782 | 3.394e+04 |
|
||||
| MEMORY_COPY_DEVICE_TO_HOST | MEMORY_COPY | 8 | 626417 | 7.830e+04 | 0.064058 | 74842 | 98603 | 8.207e+03 |
|
||||
| hsa_executable_load_agent_code_object | HSA_API | 2 | 616175 | 3.081e+05 | 0.063011 | 254476 | 361699 | 7.582e+04 |
|
||||
| hsa_amd_agents_allow_access | HSA_API | 35 | 430680 | 1.231e+04 | 0.044042 | 4830 | 55182 | 9.939e+03 |
|
||||
| hsa_signal_store_screlease | HSA_API | 56 | 381491 | 6.812e+03 | 0.039012 | 1560 | 41831 | 7.895e+03 |
|
||||
| __hipRegisterFunction | HIP_API | 4 | 294207 | 7.355e+04 | 0.030086 | 210 | 291807 | 1.455e+05 |
|
||||
| void addition_kernel<float>(float*, float const*, float const*, int, int) | KERNEL_DISPATCH | 8 | 184324 | 2.304e+04 | 0.018849 | 11200 | 98802 | 3.062e+04 |
|
||||
| hsa_signal_create | HSA_API | 107 | 160889 | 1.504e+03 | 0.016453 | 80 | 5650 | 1.475e+03 |
|
||||
| hsa_code_object_reader_create_from_memory | HSA_API | 2 | 151314 | 7.566e+04 | 0.015474 | 32121 | 119193 | 6.157e+04 |
|
||||
| hsa_signal_load_relaxed | HSA_API | 1296 | 137626 | 1.062e+02 | 0.014074 | 20 | 2930 | 2.712e+02 |
|
||||
| hsa_signal_destroy | HSA_API | 618 | 111224 | 1.800e+02 | 0.011374 | 40 | 1540 | 2.429e+02 |
|
||||
| divide_kernel(float*, float const*, float const*, int, int) | KERNEL_DISPATCH | 8 | 94482 | 1.181e+04 | 0.009662 | 10240 | 13520 | 1.061e+03 |
|
||||
| multiply_kernel(float*, float const*, float const*, int, int) | KERNEL_DISPATCH | 8 | 91763 | 1.147e+04 | 0.009384 | 9800 | 12800 | 9.417e+02 |
|
||||
| subtract_kernel(float*, float const*, float const*, int, int) | KERNEL_DISPATCH | 8 | 82521 | 1.032e+04 | 0.008439 | 8320 | 12920 | 1.436e+03 |
|
||||
| hsa_agent_get_info | HSA_API | 65 | 77472 | 1.192e+03 | 0.007922 | 30 | 47121 | 6.341e+03 |
|
||||
| hsa_amd_signal_create | HSA_API | 512 | 61290 | 1.197e+02 | 0.006268 | 40 | 930 | 1.559e+02 |
|
||||
| hsa_amd_signal_async_handler | HSA_API | 24 | 52641 | 2.193e+03 | 0.005383 | 1180 | 4020 | 9.252e+02 |
|
||||
| hsa_executable_iterate_symbols | HSA_API | 14 | 52521 | 3.752e+03 | 0.005371 | 2740 | 6940 | 1.105e+03 |
|
||||
| hipDeviceSynchronize | HIP_API | 4 | 50663 | 1.267e+04 | 0.005181 | 510 | 23621 | 9.554e+03 |
|
||||
| hsa_amd_memory_copy_engine_status | HSA_API | 18 | 47370 | 2.632e+03 | 0.004844 | 260 | 7990 | 2.274e+03 |
|
||||
| __hipRegisterFatBinary | HIP_API | 1 | 43811 | 4.381e+04 | 0.004480 | 43811 | 43811 | 0.000e+00 |
|
||||
| hsa_iterate_agents | HSA_API | 1 | 41391 | 4.139e+04 | 0.004233 | 41391 | 41391 | 0.000e+00 |
|
||||
| hsa_executable_create_alt | HSA_API | 2 | 40470 | 2.024e+04 | 0.004139 | 7530 | 32940 | 1.797e+04 |
|
||||
| hsa_isa_get_info_alt | HSA_API | 2 | 30391 | 1.520e+04 | 0.003108 | 2490 | 27901 | 1.797e+04 |
|
||||
| hsa_signal_silent_store_relaxed | HSA_API | 48 | 24920 | 5.192e+02 | 0.002548 | 20 | 4570 | 7.120e+02 |
|
||||
| hsa_amd_agent_iterate_memory_pools | HSA_API | 5 | 20221 | 4.044e+03 | 0.002068 | 2561 | 8600 | 2.574e+03 |
|
||||
| hsa_queue_add_write_index_screlease | HSA_API | 56 | 7270 | 1.298e+02 | 0.000743 | 30 | 2310 | 3.471e+02 |
|
||||
| __hipPushCallConfiguration | HIP_API | 32 | 6250 | 1.953e+02 | 0.000639 | 60 | 3640 | 6.308e+02 |
|
||||
| hsa_amd_profiling_set_profiler_enabled | HSA_API | 4 | 5600 | 1.400e+03 | 0.000573 | 1370 | 1470 | 4.690e+01 |
|
||||
| hsa_executable_symbol_get_info | HSA_API | 152 | 5470 | 3.599e+01 | 0.000559 | 30 | 340 | 3.563e+01 |
|
||||
| __hipPopCallConfiguration | HIP_API | 32 | 4780 | 1.494e+02 | 0.000489 | 60 | 2520 | 4.340e+02 |
|
||||
| hsa_queue_load_read_index_relaxed | HSA_API | 56 | 4560 | 8.143e+01 | 0.000466 | 20 | 1310 | 1.863e+02 |
|
||||
| hsa_executable_get_symbol_by_name | HSA_API | 14 | 4500 | 3.214e+02 | 0.000460 | 110 | 1510 | 4.732e+02 |
|
||||
| hipGetLastError | HIP_API | 32 | 4471 | 1.397e+02 | 0.000457 | 60 | 2381 | 4.092e+02 |
|
||||
| hsa_queue_load_read_index_scacquire | HSA_API | 56 | 3040 | 5.429e+01 | 0.000311 | 30 | 690 | 8.705e+01 |
|
||||
| hipSetDevice | HIP_API | 1 | 2570 | 2.570e+03 | 0.000263 | 2570 | 2570 | 0.000e+00 |
|
||||
| hsa_amd_memory_pool_get_info | HSA_API | 43 | 1770 | 4.116e+01 | 0.000181 | 30 | 270 | 3.640e+01 |
|
||||
| hsa_system_get_info | HSA_API | 4 | 1750 | 4.375e+02 | 0.000179 | 40 | 830 | 3.544e+02 |
|
||||
| hsa_amd_agent_memory_pool_get_info | HSA_API | 13 | 1140 | 8.769e+01 | 0.000117 | 30 | 640 | 1.664e+02 |
|
||||
| hsa_agent_iterate_isas | HSA_API | 1 | 700 | 7.000e+02 | 0.000072 | 700 | 700 | 0.000e+00 |
|
||||
| hsa_system_get_major_extension_table | HSA_API | 1 | 190 | 1.900e+02 | 0.000019 | 190 | 190 | 0.000e+00 |
|
||||
|
||||
Criar uma nova questão referindo esta
Bloquear um utilizador