Add 'projects/rocprofiler-sdk/' from commit 'bf0fad1d5406fbc51403ba1aa9621a9d4a9bce2b'
git-subtree-dir: projects/rocprofiler-sdk git-subtree-mainline:50a90550e9git-subtree-split:bf0fad1d54
@@ -0,0 +1,5 @@
|
||||
"Correlation_Id","Dispatch_Id","Agent_Id","Queue_Id","Process_Id","Thread_Id","Grid_Size","Kernel_Id","Kernel_Name","Workgroup_Size","LDS_Block_Size","Scratch_Size","VGPR_Count","Accum_VGPR_Count","SGPR_Count","Counter_Name","Counter_Value","Start_Timestamp","End_Timestamp"
|
||||
1,1,"Agent 1",1,15606,15606,1048576,17,"void addition_kernel<float>(float*, float const*, float const*, int, int)",64,0,0,8,0,16,"SQ_WAVES",16384.000000,3200098838431081,3200098838483232
|
||||
2,2,"Agent 1",1,15606,15606,1048576,20,"subtract_kernel(float*, float const*, float const*, int, int)",64,0,0,8,0,16,"SQ_WAVES",16384.000000,3200098838589014,3200098838638794
|
||||
3,3,"Agent 1",1,15606,15606,1048576,19,"multiply_kernel(float*, float const*, float const*, int, int)",64,0,0,8,0,16,"SQ_WAVES",16384.000000,3200098838746207,3200098838793025
|
||||
4,4,"Agent 1",1,15606,15606,1048576,18,"divide_kernel(float*, float const*, float const*, int, int)",64,0,0,12,0,16,"SQ_WAVES",16384.000000,3200098838879399,3200098838927550
|
||||
|
@@ -0,0 +1,18 @@
|
||||
"Name","Calls","TotalDurationNs","AverageNs","Percentage","MinNs","MaxNs","StdDev"
|
||||
"hipStreamCreateWithFlags",4,262497406,65624351.500000,85.15,3991286,249121840,122332531.343496
|
||||
"hipGetDeviceCount",1,32505687,32505687.000000,10.54,32505687,32505687,0.00000000e+00
|
||||
"hipHostMalloc",12,6096409,508034.083333,1.98,443793,548024,39236.753678
|
||||
"hipFree",12,1994421,166201.750000,0.6470,7790,1036046,299086.860470
|
||||
"hipMemcpyAsync",12,1368378,114031.500000,0.4439,2490,764044,249308.051619
|
||||
"hipMallocAsync",12,927255,77271.250000,0.3008,51540,107671,20487.475966
|
||||
"hipStreamSynchronize",12,870486,72540.500000,0.2824,140,866606,250065.900069
|
||||
"hipLaunchKernel",16,692734,43295.875000,0.2247,1000,670044,167133.656647
|
||||
"hipStreamDestroy",4,619905,154976.250000,0.2011,92901,339252,122852.320356
|
||||
"hipDeviceSynchronize",4,404252,101063.000000,0.1311,570,385212,189518.505401
|
||||
"hipHostFree",12,271202,22600.166667,0.0880,11950,34950,7480.268600
|
||||
"__hipRegisterFatBinary",1,9000,9000.000000,2.920e-03,9000,9000,0.00000000e+00
|
||||
"__hipRegisterFunction",4,6150,1537.500000,1.995e-03,230,5370,2555.091323
|
||||
"__hipPushCallConfiguration",16,2460,153.750000,7.980e-04,70,1140,267.503894
|
||||
"__hipPopCallConfiguration",16,2000,125.000000,6.488e-04,70,680,151.613544
|
||||
"hipGetLastError",16,1270,79.375000,4.120e-04,50,440,96.295985
|
||||
"hipSetDevice",1,660,660.000000,2.141e-04,660,660,0.00000000e+00
|
||||
|
@@ -0,0 +1,7 @@
|
||||
"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
|
||||
|
||||
|
@@ -0,0 +1,2 @@
|
||||
"Name","Calls","TotalDurationNs","AverageNs","Percentage","MinNs","MaxNs","StdDev"
|
||||
"HIP_API",13,458514859,35270373.769231,100.00,2300,352276613,99315857.546240
|
||||
|
@@ -0,0 +1,9 @@
|
||||
"Domain","Function","Process_Id","Thread_Id","Correlation_Id","Start_Timestamp","End_Timestamp"
|
||||
"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 +1,11 @@
|
||||
"Domain","Function","Process_Id","Thread_Id","Correlation_Id","Start_Timestamp","End_Timestamp"
|
||||
"HSA_CORE_API","hsa_system_get_major_extension_table",197,197,1,1507843974724237,1507843974724947
|
||||
"HSA_CORE_API","hsa_agent_get_info",197,197,3,1507843974754471,1507843974755014
|
||||
"HSA_AMD_EXT_API","hsa_amd_memory_pool_get_info",197,197,5,1507843974761705,1507843974762398
|
||||
"HSA_AMD_EXT_API","hsa_amd_memory_pool_get_info",197,197,6,1507843974763901,1507843974764030
|
||||
"HSA_AMD_EXT_API","hsa_amd_memory_pool_get_info",197,197,7,1507843974765121,1507843974765224
|
||||
"HSA_AMD_EXT_API","hsa_amd_memory_pool_get_info",197,197,8,1507843974766196,1507843974766328
|
||||
"HSA_AMD_EXT_API","hsa_amd_memory_pool_get_info",197,197,9,1507843974767534,1507843974767641
|
||||
"HSA_AMD_EXT_API","hsa_amd_memory_pool_get_info",197,197,10,1507843974768639,1507843974768779
|
||||
"HSA_AMD_EXT_API","hsa_amd_agent_iterate_memory_pools",197,197,4,1507843974758768,1507843974769238
|
||||
"HSA_CORE_API","hsa_agent_get_info",197,197,11,1507843974771091,1507843974771537
|
||||
|
@@ -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
|
||||
|
||||
|
@@ -0,0 +1,5 @@
|
||||
"Correlation_Id","Dispatch_Id","Agent_Id","Queue_Id","Process_Id","Thread_Id","Grid_Size","Kernel_Name","Workgroup_Size","LDS_Block_Size","Scratch_Size","VGPR_Count","SGPR_Count","Counter_Name","Counter_Value"
|
||||
4,4,1,1,36499,36499,1048576,"divide_kernel(float*, float const*, float const*, int, int)",64,0,0,12,16,"SQ_WAVES",16384
|
||||
8,8,1,2,36499,36499,1048576,"divide_kernel(float*, float const*, float const*, int, int)",64,0,0,12,16,"SQ_WAVES",16384
|
||||
12,12,1,3,36499,36499,1048576,"divide_kernel(float*, float const*, float const*, int, int)",64,0,0,12,16,"SQ_WAVES",16384
|
||||
16,16,1,4,36499,36499,1048576,"divide_kernel(float*, float const*, float const*, int, int)",64,0,0,12,16,"SQ_WAVES",16384
|
||||
|
@@ -0,0 +1,10 @@
|
||||
"Kind","Agent_Id","Queue_Id","Stream_Id","Thread_Id","Dispatch_Id","Kernel_Id","Kernel_Name","Correlation_Id","Start_Timestamp","End_Timestamp","LDS_Block_Size","Scratch_Size","VGPR_Count","Accum_VGPR_Count","SGPR_Count","Workgroup_Size_X","Workgroup_Size_Y","Workgroup_Size_Z","Grid_Size_X","Grid_Size_Y","Grid_Size_Z"
|
||||
"KERNEL_DISPATCH","Agent 4",1,1,834304,1,10,"void addition_kernel<float>(float*, float const*, float const*, int, int)",1,1550151853029637,1550151853042437,0,0,8,0,16,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH","Agent 4",1,1,834304,4,11,"divide_kernel(float*, float const*, float const*, int, int)",4,1550151853064037,1550151853075237,0,0,12,4,16,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH","Agent 4",1,1,834304,3,12,"multiply_kernel(float*, float const*, float const*, int, int)",3,1550151853052877,1550151853064037,0,0,8,0,16,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH","Agent 4",1,1,834304,2,13,"subtract_kernel(float*, float const*, float const*, int, int)",2,1550151853042437,1550151853050677,0,0,8,0,16,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH","Agent 4",2,2,834304,5,10,"void addition_kernel<float>(float*, float const*, float const*, int, int)",5,1550151853082957,1550151853094357,0,0,8,0,16,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH","Agent 4",2,2,834304,6,13,"subtract_kernel(float*, float const*, float const*, int, int)",6,1550151853094357,1550151853103517,0,0,8,0,16,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH","Agent 4",4,4,834304,13,10,"void addition_kernel<float>(float*, float const*, float const*, int, int)",13,1550151853164197,1550151853174037,0,0,8,0,16,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH","Agent 4",3,3,834304,12,11,"divide_kernel(float*, float const*, float const*, int, int)",12,1550151853148397,1550151853160837,0,0,12,4,16,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH","Agent 4",3,3,834304,11,12,"multiply_kernel(float*, float const*, float const*, int, int)",11,1550151853138477,1550151853148397,0,0,8,0,16,64,1,1,1024,1024,1
|
||||
|
@@ -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","LDS_Block_Size","Scratch_Size","VGPR_Count","Accum_VGPR_Count","SGPR_Count","Workgroup_Size_X","Workgroup_Size_Y","Workgroup_Size_Z","Grid_Size_X","Grid_Size_Y","Grid_Size_Z"
|
||||
"KERNEL_DISPATCH","Agent 4",1,1,855217,1,10,"addition_kernel",1,1552082594648838,1552082594660478,0,0,8,0,16,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH","Agent 4",1,1,855217,4,11,"divide_kernel",4,1552082594696598,1552082594709678,0,0,12,4,16,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH","Agent 4",1,1,855217,3,12,"multiply_kernel",3,1552082594685158,1552082594696598,0,0,8,0,16,64,1,1,1024,1024,1
|
||||
"KERNEL_DISPATCH","Agent 4",1,1,855217,2,13,"subtract_kernel",2,1552082594660478,1552082594669158,0,0,8,0,16,64,1,1,1024,1024,1
|
||||
|
@@ -0,0 +1,26 @@
|
||||
GPU : 0
|
||||
Name : gfx90a
|
||||
configs :
|
||||
Method : host_trap
|
||||
Unit : time
|
||||
Min_Interval : 1
|
||||
Max_Interval : 18446744073709551615
|
||||
Flags : none
|
||||
|
||||
GPU:0
|
||||
Name:gfx90a
|
||||
Counter_Name : processor_id_low
|
||||
Description : Constant value processor_id_low from agent properties
|
||||
|
||||
|
||||
Counter_Name : ALUStalledByLDS
|
||||
Description : The percentage of GPUTime ALU units are stalled by the LDS input queue being full or the output queue being not ready. If there are LDS bank conflicts, reduce them. Otherwise, try reducing the number of LDS accesses if possible. Value range: 0% (optimal) to 100% (bad).
|
||||
Expression : 400*reduce(SQ_WAIT_INST_LDS,sum)/reduce(SQ_WAVES,sum)/reduce(GRBM_GUI_ACTIVE,max)
|
||||
Dimensions : DIMENSION_INSTANCE[0:0]
|
||||
|
||||
Counter_Name : SQ_WAVES
|
||||
Description : Count number of waves sent to distributed sequencers (SQs). This value represents the number of waves that are sent to each SQ. This only counts new waves sent since the start of collection (for dispatch profiling this is the timeframe of kernel execution, for agent profiling it is the timeframe between start_context and read counter data). A sum of all SQ_WAVES values will give the total number of waves started by the application during the collection timeframe. Returns one value per-SE (aggregates of SIMD values).
|
||||
Block : SQ
|
||||
Dimensions : DIMENSION_INSTANCE[0:0] DIMENSION_SHADER_ENGINE[0:7]
|
||||
|
||||
...
|
||||
@@ -0,0 +1,6 @@
|
||||
"Domain","Function","Process_Id","Thread_Id","Correlation_Id","Start_Timestamp","End_Timestamp"
|
||||
"MARKER_CORE_API","before hipLaunchKernel",717,717,1,1520113899312225,1520113899312225
|
||||
"MARKER_CORE_API","after hipLaunchKernel",717,717,4,1520113900128482,1520113900128482
|
||||
"MARKER_CORE_API","hipMemcpy",717,717,5,1520113900141100,1520113901483408
|
||||
"MARKER_CORE_API","hipLaunchKernel",717,717,3,1520113899684965,1520113901491622
|
||||
"MARKER_CORE_API","hipLaunchKernel range",717,0,2,1520113899682208,1520113901495882
|
||||
|
@@ -0,0 +1,7 @@
|
||||
"Kind","Operation","Agent_Id","Allocation_Size","Address","Correlation_Id","Start_Timestamp","End_Timestamp"
|
||||
"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
|
||||
|
@@ -0,0 +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",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
|
||||
|
@@ -0,0 +1,80 @@
|
||||
"Sample_Timestamp","Exec_Mask","Dispatch_Id","Instruction","Instruction_Comment","Correlation_Id"
|
||||
3464444413017201,65535,1,"s_endpgm","",1
|
||||
3464444413017201,65535,1,"s_waitcnt vmcnt(0)","",1
|
||||
3464444413018481,65535,1,"s_waitcnt vmcnt(0)","",1
|
||||
3464444413018481,65535,1,"s_endpgm","",1
|
||||
3464444413018481,65535,1,"s_waitcnt vmcnt(0)","",1
|
||||
3464444413018481,65535,1,"s_waitcnt vmcnt(0)","",1
|
||||
3464444413018481,65535,1,"s_endpgm","",1
|
||||
3464444413018481,65535,1,"s_endpgm","",1
|
||||
3464444413019601,65535,1,"s_waitcnt vmcnt(0)","",1
|
||||
3464444413019761,65535,1,"s_load_dword s8, s[4:5], 0x24","",1
|
||||
3464444413019761,65535,1,"s_waitcnt vmcnt(0)","",1
|
||||
3464444413019761,65535,1,"s_endpgm","",1
|
||||
3464444413019761,65535,1,"s_load_dword s8, s[4:5], 0x24","",1
|
||||
3464444413019761,65535,1,"s_endpgm","",1
|
||||
3464444413019761,65535,1,"s_endpgm","",1
|
||||
3464444413020881,65535,1,"s_endpgm","",1
|
||||
3464444413020881,65535,1,"s_endpgm","",1
|
||||
3464444413020881,65535,1,"s_endpgm","",1
|
||||
3464444413020881,65535,1,"s_waitcnt lgkmcnt(0)","",1
|
||||
3464444413020881,65535,1,"v_addc_co_u32_e32 v5, vcc, v1, v5, vcc","",1
|
||||
3464444413020881,65535,1,"s_endpgm","",1
|
||||
3464444413020881,65535,1,"s_waitcnt vmcnt(0)","",1
|
||||
3464444413020881,65535,1,"s_endpgm","",1
|
||||
3464444413020881,65535,1,"s_waitcnt vmcnt(0)","",1
|
||||
3464444413021041,65535,1,"s_endpgm","",1
|
||||
3464444413020881,65535,1,"v_bfe_u32 v0, v0, 10, 10","",1
|
||||
3464444413021041,65535,1,"s_endpgm","",1
|
||||
3464444413021041,65535,1,"s_endpgm","",1
|
||||
3464444413021041,65535,1,"s_waitcnt vmcnt(0)","",1
|
||||
3464444413021041,65535,1,"s_endpgm","",1
|
||||
3464444413021041,65535,1,"s_waitcnt vmcnt(0)","",1
|
||||
3464444413021041,65535,1,"s_endpgm","",1
|
||||
3464444413022001,65535,1,"s_waitcnt vmcnt(0)","",1
|
||||
3464444413022001,65535,1,"s_endpgm","",1
|
||||
3464444413022001,65535,1,"s_endpgm","",1
|
||||
3464444413022001,65535,1,"s_endpgm","",1
|
||||
3464444413022001,65535,1,"s_endpgm","",1
|
||||
3464444413022001,65535,1,"s_waitcnt vmcnt(0)","",1
|
||||
3464444413022001,65535,1,"s_endpgm","",1
|
||||
3464444413022001,65535,1,"s_waitcnt vmcnt(0)","",1
|
||||
3464444413022001,65535,1,"s_waitcnt lgkmcnt(0)","",1
|
||||
3464444413022161,65535,1,"s_endpgm","",1
|
||||
3464444413022161,65535,1,"s_waitcnt vmcnt(0)","",1
|
||||
3464444413022161,65535,1,"s_endpgm","",1
|
||||
3464444413022161,65535,1,"s_load_dword s8, s[4:5], 0x24","",1
|
||||
3464444413022161,65535,1,"global_store_dword v[0:1], v3, off","",1
|
||||
3464444413022161,65535,1,"s_endpgm","",1
|
||||
3464444413022161,65535,1,"s_endpgm","",1
|
||||
3464444413022161,65535,1,"s_waitcnt vmcnt(0)","",1
|
||||
3464444413022161,65535,1,"s_endpgm","",1
|
||||
3464444413022161,65535,1,"s_endpgm","",1
|
||||
3464444413022161,65535,1,"s_waitcnt vmcnt(0)","",1
|
||||
3464444413022161,65535,1,"s_endpgm","",1
|
||||
3464444413022321,65535,1,"s_load_dwordx4 s[0:3], s[4:5], 0x0","",1
|
||||
3464444413022161,65535,1,"s_waitcnt vmcnt(0)","",1
|
||||
3464444413022321,65535,1,"s_endpgm","",1
|
||||
3464444413022161,65535,1,"s_waitcnt vmcnt(0)","",1
|
||||
3464444413023281,65535,1,"s_endpgm","",1
|
||||
3464444413023281,65535,1,"s_endpgm","",1
|
||||
3464444413023281,65535,1,"v_ashrrev_i32_e32 v1, 31, v0","",1
|
||||
3464444413024561,65535,1,"s_waitcnt vmcnt(0)","",1
|
||||
3464444413023281,65535,1,"s_endpgm","",1
|
||||
3464444413024561,65535,1,"s_endpgm","",1
|
||||
3464444413023761,65535,1,"s_waitcnt vmcnt(0)","",1
|
||||
3464444413026321,65535,1,"s_waitcnt vmcnt(0)","",1
|
||||
3464444413024401,65535,1,"global_store_dword v[0:1], v3, off","",1
|
||||
3464444413027121,65535,1,"s_waitcnt vmcnt(0)","",1
|
||||
3464444413025041,65535,1,"v_add_co_u32_e32 v0, vcc, s0, v0","",1
|
||||
3464444413027761,65535,1,"s_waitcnt vmcnt(0)","",1
|
||||
3464444413025361,65535,1,"s_endpgm","",1
|
||||
3464444413027601,65535,1,"s_waitcnt vmcnt(0)","",1
|
||||
3464444413026321,65535,1,"s_waitcnt vmcnt(0)","",1
|
||||
3464444413028401,65535,1,"s_waitcnt vmcnt(0)","",1
|
||||
3464444413026481,65535,1,"s_waitcnt vmcnt(0)","",1
|
||||
3464444413028881,65535,1,"s_waitcnt vmcnt(0)","",1
|
||||
3464444413026641,65535,1,"s_waitcnt vmcnt(0)","",1
|
||||
3464444413028401,65535,1,"s_load_dword s8, s[4:5], 0x24","",1
|
||||
3464444413027281,65535,1,"s_waitcnt vmcnt(0)","",1
|
||||
3464444413029681,65535,1,"s_endpgm","",1
|
||||
|
@@ -0,0 +1,22 @@
|
||||
"Sample_Timestamp","Exec_Mask","Dispatch_Id","Instruction","Instruction_Comment","Correlation_Id"
|
||||
54155306462675,65535,1,"s_waitcnt lgkmcnt(0)","/opt/rocm/include/hip/amd_detail/amd_hip_runtime.h:275",1
|
||||
54155306462715,65535,1,"s_waitcnt vmcnt(0)","/opt/rocm-6.4.0/share/hip/samples/2_Cookbook/0_MatrixTranspose/MatrixTranspose.cpp:44",1
|
||||
54155306462755,65535,1,"s_endpgm","/opt/rocm-6.4.0/share/hip/samples/2_Cookbook/0_MatrixTranspose/MatrixTranspose.cpp:45",1
|
||||
54155306462755,65535,1,"s_endpgm","/opt/rocm-6.4.0/share/hip/samples/2_Cookbook/0_MatrixTranspose/MatrixTranspose.cpp:45",1
|
||||
54155306462955,65535,1,"s_endpgm","/opt/rocm-6.4.0/share/hip/samples/2_Cookbook/0_MatrixTranspose/MatrixTranspose.cpp:45",1
|
||||
54155306463035,65535,1,"s_waitcnt vmcnt(0)","/opt/rocm-6.4.0/share/hip/samples/2_Cookbook/0_MatrixTranspose/MatrixTranspose.cpp:44",1
|
||||
54155306463235,65535,1,"s_waitcnt vmcnt(0)","/opt/rocm-6.4.0/share/hip/samples/2_Cookbook/0_MatrixTranspose/MatrixTranspose.cpp:44",1
|
||||
54155306463315,65535,1,"s_waitcnt vmcnt(0)","/opt/rocm-6.4.0/share/hip/samples/2_Cookbook/0_MatrixTranspose/MatrixTranspose.cpp:44",1
|
||||
54155306463515,65535,1,"s_endpgm","/opt/rocm-6.4.0/share/hip/samples/2_Cookbook/0_MatrixTranspose/MatrixTranspose.cpp:45",1
|
||||
54155306463755,65535,1,"s_waitcnt vmcnt(0)","/opt/rocm-6.4.0/share/hip/samples/2_Cookbook/0_MatrixTranspose/MatrixTranspose.cpp:44",1
|
||||
54155306463875,65535,1,"s_waitcnt vmcnt(0)","/opt/rocm-6.4.0/share/hip/samples/2_Cookbook/0_MatrixTranspose/MatrixTranspose.cpp:44",1
|
||||
54155306464075,65535,1,"v_mov_b32_e32 v2, s4","/opt/rocm/include/hip/amd_detail/amd_hip_runtime.h:275",1
|
||||
54155306464155,65535,1,"s_waitcnt vmcnt(0)","/opt/rocm-6.4.0/share/hip/samples/2_Cookbook/0_MatrixTranspose/MatrixTranspose.cpp:44",1
|
||||
54155306464155,65535,1,"s_waitcnt vmcnt(0)","/opt/rocm-6.4.0/share/hip/samples/2_Cookbook/0_MatrixTranspose/MatrixTranspose.cpp:44",1
|
||||
54155306464275,65535,1,"s_endpgm","/opt/rocm-6.4.0/share/hip/samples/2_Cookbook/0_MatrixTranspose/MatrixTranspose.cpp:45",1
|
||||
54155306464395,65535,1,"s_waitcnt vmcnt(0)","/opt/rocm-6.4.0/share/hip/samples/2_Cookbook/0_MatrixTranspose/MatrixTranspose.cpp:44",1
|
||||
54155306464515,65535,1,"s_waitcnt lgkmcnt(0)","/opt/rocm/include/hip/amd_detail/amd_hip_runtime.h:275",1
|
||||
54155306464555,65535,1,"s_waitcnt vmcnt(0)","/opt/rocm-6.4.0/share/hip/samples/2_Cookbook/0_MatrixTranspose/MatrixTranspose.cpp:44",1
|
||||
54155306464595,65535,1,"s_waitcnt vmcnt(0)","/opt/rocm-6.4.0/share/hip/samples/2_Cookbook/0_MatrixTranspose/MatrixTranspose.cpp:44",1
|
||||
54155306464595,65535,1,"v_mov_b32_e32 v2, s6","/opt/rocm/include/hip/amd_detail/amd_hip_runtime.h:275",1
|
||||
54155306464595,65535,1,"s_waitcnt lgkmcnt(0)","/opt/rocm/include/hip/amd_detail/amd_hip_runtime.h:275",1
|
||||
|
@@ -0,0 +1,98 @@
|
||||
"Sample_Timestamp","Exec_Mask","Dispatch_Id","Instruction","Instruction_Comment","Correlation_Id","Wave_Issued_Instruction","Instruction_Type","Stall_Reason","Wave_Count"
|
||||
390705261841337,18446744073709551615,24,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:133",24,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",4
|
||||
390705261924637,18446744073709551615,29,"v_max_i32_e32 v1, v2, v0","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:77",29,1,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_VALU","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_OTHER_WAIT",6
|
||||
390705694732429,18446744073709551615,53,"v_mad_u64_u32 v[0:1], s[2:3], v0, s2, v[2:3]","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:80",53,1,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_VALU","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_OTHER_WAIT",6
|
||||
390705694744189,18446744073709551615,54,"v_lshl_add_u64 v[0:1], s[4:5], 0, v[0:1]","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:99",54,1,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_VALU","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_OTHER_WAIT",4
|
||||
390705694769549,18446744073709551615,56,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:133",56,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",6
|
||||
390705694772089,18446744073709551615,56,"s_waitcnt lgkmcnt(0)","/usr/include/hip/amd_detail/amd_hip_runtime.h:275",56,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",5
|
||||
390705694810449,18446744073709551615,58,"v_cmp_gt_i32_e32 vcc, s2, v1","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:94",58,1,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_VALU","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_OTHER_WAIT",3
|
||||
390705694820489,18446744073709551615,59,"s_waitcnt vmcnt(1)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:116",59,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",4
|
||||
390705694840850,18446744073709551615,60,"s_and_b32 s5, s4, 0xffff","/usr/include/hip/amd_detail/amd_hip_runtime.h:275",60,1,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_SCALAR","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_OTHER_WAIT",5
|
||||
390705694856630,18446744073709551615,61,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:82",61,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",5
|
||||
390706112944694,18446744073709551615,65,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:82",65,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",7
|
||||
390706112965404,18446744073709551615,66,"global_store_dword v[0:1], v2, off","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:99",66,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_ALU_DEPENDENCY",3
|
||||
390706112966284,18446744073709551615,66,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:99",66,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",6
|
||||
390706112966644,18446744073709551615,66,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:99",66,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",3
|
||||
390706112967404,18446744073709551615,66,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:99",66,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",4
|
||||
390706112971414,18446744073709551615,66,"s_load_dwordx4 s[4:7], s[0:1], 0x0","/usr/include/hip/amd_detail/amd_hip_runtime.h:275",66,1,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_SCALAR","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_OTHER_WAIT",5
|
||||
390706112984885,18446744073709551615,67,"s_waitcnt vmcnt(1)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:116",67,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",5
|
||||
390706112988655,18446744073709551615,67,"s_waitcnt vmcnt(1)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:116",67,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",4
|
||||
390706113000775,18446744073709551615,68,"v_add_u32_e32 v0, s3, v0","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:128",68,1,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_VALU","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_OTHER_WAIT",5
|
||||
390706113004375,18446744073709551615,68,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:133",68,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",4
|
||||
390706113053815,18446744073709551615,69,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:82",69,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",7
|
||||
390706113059125,18446744073709551615,69,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:82",69,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",6
|
||||
390706113080805,18446744073709551615,70,"s_load_dwordx4 s[4:7], s[0:1], 0x0","/usr/include/hip/amd_detail/amd_hip_runtime.h:275",70,1,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_SCALAR","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_OTHER_WAIT",3
|
||||
390706113097725,18446744073709551615,71,"s_waitcnt vmcnt(1)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:116",71,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",3
|
||||
390706113101805,18446744073709551615,71,"s_waitcnt vmcnt(1)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:116",71,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",4
|
||||
390706113111775,18446744073709551615,72,"v_sub_f32_e32 v4, v2, v3","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:133",72,1,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_VALU","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_OTHER_WAIT",5
|
||||
390706113115735,18446744073709551615,72,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:133",72,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",5
|
||||
390706113134725,18446744073709551615,73,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:82",73,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",7
|
||||
390706113147605,18446744073709551615,74,"s_waitcnt lgkmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:97",74,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",4
|
||||
390706113149485,18446744073709551615,74,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:99",74,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",4
|
||||
390706113153735,18446744073709551615,74,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:99",74,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",5
|
||||
390706113179326,18446744073709551615,76,"s_waitcnt lgkmcnt(0)","/usr/include/hip/amd_detail/amd_hip_runtime.h:275",76,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",2
|
||||
390706113184086,18446744073709551615,76,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:133",76,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",5
|
||||
390706113184406,18446744073709551615,76,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:133",76,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",4
|
||||
390706113206736,18446744073709551615,77,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:82",77,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",10
|
||||
390706113209216,18446744073709551615,77,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:82",77,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",11
|
||||
390706113220016,18446744073709551615,78,"s_load_dword s4, s[0:1], 0x2c","/usr/include/hip/amd_detail/amd_hip_runtime.h:275",78,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_NO_INSTRUCTION_AVAILABLE",1
|
||||
390706113221566,18446744073709551615,78,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:99",78,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",4
|
||||
390706113227816,18446744073709551615,78,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:99",78,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",5
|
||||
390706113234976,18446744073709551615,79,"s_waitcnt vmcnt(1)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:116",79,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",4
|
||||
390706113235016,18446744073709551615,79,"s_load_dwordx2 s[0:1], s[0:1], 0x10","/usr/include/hip/amd_detail/amd_hip_runtime.h:275",79,1,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_SCALAR","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_OTHER_WAIT",3
|
||||
390706113236806,18446744073709551615,79,"s_and_saveexec_b64 s[2:3], vcc","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:113",79,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_ALU_DEPENDENCY",3
|
||||
390706113250926,18446744073709551615,80,"s_waitcnt lgkmcnt(0)","/usr/include/hip/amd_detail/amd_hip_runtime.h:275",80,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",1
|
||||
390706113253456,18446744073709551615,80,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:133",80,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",5
|
||||
390706113255496,18446744073709551615,80,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:133",80,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",6
|
||||
390706113257566,18446744073709551615,80,"v_add_f32_e32 v2, 1.0, v2","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:133",80,1,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_VALU","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_OTHER_WAIT",4
|
||||
390706113270176,18446744073709551615,81,"s_waitcnt lgkmcnt(0)","/usr/include/hip/amd_detail/amd_hip_runtime.h:275",81,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",3
|
||||
390706113278256,18446744073709551615,81,"s_load_dword s2, s[0:1], 0x18","/usr/include/hip/amd_detail/amd_hip_runtime.h:275",81,1,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_SCALAR","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_OTHER_WAIT",8
|
||||
390706113292776,18446744073709551615,82,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:99",82,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",3
|
||||
390706113301126,18446744073709551615,83,"s_waitcnt lgkmcnt(0)","/usr/include/hip/amd_detail/amd_hip_runtime.h:275",83,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",1
|
||||
390706113301606,18446744073709551615,83,"s_and_saveexec_b64 s[2:3], vcc","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:113",83,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_ALU_DEPENDENCY",3
|
||||
390706113303846,18446744073709551615,83,"s_and_saveexec_b64 s[2:3], vcc","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:113",83,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_ALU_DEPENDENCY",3
|
||||
390706113305086,18446744073709551615,83,"v_lshlrev_b64 v[0:1], 2, v[0:1]","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:116",83,1,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_VALU","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_OTHER_WAIT",3
|
||||
390706113317256,18446744073709551615,84,"v_div_fmas_f32 v3, v3, v6, v7","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:133",84,1,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_VALU","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_OTHER_WAIT",5
|
||||
390706113318166,18446744073709551615,84,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:133",84,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",6
|
||||
390706113336687,18446744073709551615,85,"global_load_dword v2, v[2:3], off","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:82",85,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_ALU_DEPENDENCY",11
|
||||
390706113351087,18446744073709551615,86,"s_mul_i32 s2, s2, s5","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:93",86,1,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_SCALAR","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_OTHER_WAIT",3
|
||||
390706113352487,18446744073709551615,86,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:99",86,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",5
|
||||
390706113369607,18446744073709551615,87,"s_waitcnt vmcnt(1)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:116",87,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",6
|
||||
390706113373647,18446744073709551615,87,"s_waitcnt vmcnt(1)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:116",87,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",5
|
||||
390706113387017,18446744073709551615,88,"s_waitcnt lgkmcnt(0)","/usr/include/hip/amd_detail/amd_hip_runtime.h:275",88,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",1
|
||||
390706113390207,18446744073709551615,88,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:133",88,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",5
|
||||
390706113408977,18446744073709551615,89,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:82",89,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",5
|
||||
390706113409057,18446744073709551615,89,"v_add_f32_e32 v2, v2, v3","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:82",89,1,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_VALU","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_OTHER_WAIT",10
|
||||
390706113411607,18446744073709551615,89,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:82",89,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",9
|
||||
390706113411737,18446744073709551615,89,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:82",89,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",7
|
||||
390706113412777,18446744073709551615,89,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:82",89,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",7
|
||||
390706113415847,18446744073709551615,89,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:82",89,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",9
|
||||
390706113424217,18446744073709551615,90,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:99",90,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",4
|
||||
390706113443127,18446744073709551615,91,"v_add_f32_e32 v2, -1.0, v2","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:116",91,1,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_VALU","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_OTHER_WAIT",2
|
||||
390706113444857,18446744073709551615,91,"v_add_f32_e32 v3, -1.0, v3","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:116",91,1,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_VALU","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_OTHER_WAIT",3
|
||||
390706113459367,18446744073709551615,92,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:133",92,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",6
|
||||
390706113459767,18446744073709551615,92,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:133",92,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",6
|
||||
390706113462927,18446744073709551615,92,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:133",92,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",4
|
||||
390706113480097,18446744073709551615,93,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:82",93,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",15
|
||||
390706113484087,18446744073709551615,93,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:82",93,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",7
|
||||
390706113496167,18446744073709551615,93,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:82",93,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",6
|
||||
390706113500167,18446744073709551615,93,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:82",93,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",9
|
||||
390706113506057,18446744073709551615,93,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:82",93,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",14
|
||||
390706113506327,18446744073709551615,93,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:82",93,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",6
|
||||
390706113508577,18446744073709551615,93,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:82",93,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",17
|
||||
390706113522058,18446744073709551615,93,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:82",93,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",15
|
||||
390706113561378,18446744073709551615,94,"s_waitcnt lgkmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:97",94,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",3
|
||||
390706113573138,18446744073709551615,95,"s_waitcnt vmcnt(1)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:116",95,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",5
|
||||
390706526501642,18446744073709551615,112,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:133",112,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",6
|
||||
390706526582893,18446744073709551615,117,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:82",117,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",8
|
||||
390706526594683,18446744073709551615,118,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:99",118,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",4
|
||||
390706526629813,18446744073709551615,120,"s_waitcnt lgkmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:131",120,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",5
|
||||
390706526629803,18446744073709551615,120,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:133",120,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",5
|
||||
390706526633683,18446744073709551615,120,"v_mul_f32_e32 v7, v3, v6","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:133",120,1,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_VALU","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_OTHER_WAIT",4
|
||||
390706526634933,18446744073709551615,120,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:133",120,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",4
|
||||
390706526665053,18446744073709551615,122,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:99",122,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",4
|
||||
390706526677283,18446744073709551615,123,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:116",123,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",6
|
||||
390706526695733,18446744073709551615,124,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:133",124,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",5
|
||||
390706526809694,18446744073709551615,126,"v_and_b32_e32 v2, 0x7fffffff, v2","/opt/rocm-6.4.0/lib/llvm/lib/clang/19/include/__clang_hip_math.h:427",126,1,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_VALU","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_OTHER_WAIT",5
|
||||
390706526810014,18446744073709551615,126,"s_waitcnt vmcnt(0)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:99",126,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",5
|
||||
390706526821284,18446744073709551615,127,"s_waitcnt vmcnt(1)","/home/vlaindic/git/rocprofiler-sdk-internal/tests/bin/vector-operations/vector-ops.cpp:116",127,0,"ROCPROFILER_PC_SAMPLING_INSTRUCTION_TYPE_NO_INST","ROCPROFILER_PC_SAMPLING_INSTRUCTION_NOT_ISSUED_REASON_WAITCNT",5
|
||||
|
|
После Ширина: | Высота: | Размер: 174 KiB |
|
После Ширина: | Высота: | Размер: 124 KiB |
|
После Ширина: | Высота: | Размер: 124 KiB |
|
После Ширина: | Высота: | Размер: 62 KiB |
@@ -0,0 +1,7 @@
|
||||
"Domain","Function","Process_Id","Thread_Id","Correlation_Id","Start_Timestamp","End_Timestamp"
|
||||
"MARKER_CORE_API","MatrixTranspose: rows=4, cols=5",15964,15964,1,1392141764711512,1392141764711512
|
||||
"MARKER_CORE_API","generate_matrix(rows=4, cols=5)",15964,15964,4,1392141765500646,1392141765523276
|
||||
"MARKER_CORE_API","transpose(nrows=4, ncols=5)",15964,15964,7,1392141765527536,1392141765531786
|
||||
"MARKER_CORE_API","matrix_transpose",15964,15964,6,1392141765525156,1392141765532696
|
||||
"MARKER_CORE_API","run(rows=4, cols=5)",15964,15964,3,1392141765498106,1392141765534186
|
||||
"MARKER_CORE_API","main",15964,15964,2,1392141765494795,1392141765574506
|
||||
|
@@ -0,0 +1,22 @@
|
||||
"Domain","Function","Process_Id","Thread_Id","Correlation_Id","Start_Timestamp","End_Timestamp"
|
||||
"RCCL_API","ncclGetVersion",1834151,1834151,416,18413845573432,18413845577374
|
||||
"RCCL_API","ncclGetUniqueId",1834151,1834151,1116,18413961300878,18413963267869
|
||||
"RCCL_API","ncclGetUniqueId",1834151,1834151,1481,18414166449182,18414166720831
|
||||
"RCCL_API","ncclGroupStart",1834151,1834151,1482,18414166723772,18414166726834
|
||||
"RCCL_API","ncclGroupEnd",1834151,1834151,1490,18414166823575,18414380520973
|
||||
"RCCL_API","ncclCommInitAll",1834151,1834151,1477,18414166402665,18414380522536
|
||||
"RCCL_API","ncclCommGetAsyncError",1834151,1834151,89098,18414380660695,18414380661652
|
||||
"RCCL_API","ncclAllReduce",1834151,1834151,89097,18414380653860,18414380693574
|
||||
"RCCL_API","ncclCommGetAsyncError",1834151,1834151,89108,18414380694631,18414380694659
|
||||
"RCCL_API","ncclAllReduce",1834151,1834151,89107,18414380694212,18414380704722
|
||||
"RCCL_API","ncclCommGetAsyncError",1834151,1834151,89117,18414380706650,18414380706677
|
||||
"RCCL_API","ncclAllReduce",1834151,1834151,89116,18414380705574,18414380715055
|
||||
"RCCL_API","ncclCommGetAsyncError",1834151,1834151,89126,18414380715749,18414380715774
|
||||
"RCCL_API","ncclAllReduce",1834151,1834151,89125,18414380715463,18414380723944
|
||||
"RCCL_API","ncclCommGetAsyncError",1834151,1834151,89135,18414380724688,18414380724715
|
||||
"RCCL_API","ncclAllReduce",1834151,1834151,89134,18414380724395,18414380732209
|
||||
"RCCL_API","ncclCommGetAsyncError",1834151,1834151,89154,18414380746383,18414380746411
|
||||
"RCCL_API","ncclCommGetAsyncError",1834151,1834151,89157,18414380749863,18414380749889
|
||||
"RCCL_API","ncclCommGetAsyncError",1834151,1834151,89160,18414380751671,18414380751696
|
||||
"RCCL_API","ncclCommGetAsyncError",1834151,1834151,89163,18414380753326,18414380753353
|
||||
"RCCL_API","ncclCommGetAsyncError",1834151,1834151,89166,18414380755128,18414380755154
|
||||
|
@@ -0,0 +1,7 @@
|
||||
"Domain","Function","Process_Id","Thread_Id","Correlation_Id","Start_Timestamp","End_Timestamp"
|
||||
"ROCDECODE_API","rocDecCreateVideoParser",41688,41688,583,615449881677279,615449882001583
|
||||
"ROCDECODE_API","rocDecGetDecoderCaps",41688,41688,584,615449882016054,615449882163756
|
||||
"ROCDECODE_API","rocDecGetDecoderCaps",41688,41688,588,615449886038750,615449886050880
|
||||
"ROCDECODE_API","rocDecCreateDecoder",41688,41688,591,615449886084210,615450756910310
|
||||
"ROCDECODE_API","rocDecDecodeFrame",41688,41688,595,615450757036042,615450767147413
|
||||
"ROCDECODE_API","rocDecGetDecodeStatus",41688,41688,812,615450836779385,615450836779575
|
||||
|
@@ -0,0 +1,5 @@
|
||||
"Domain","Function","Process_Id","Thread_Id","Correlation_Id","Start_Timestamp","End_Timestamp"
|
||||
"ROCJPEG_API","rocJpegCreate",41884,41884,105,1286306029650499,1286306248201233
|
||||
"ROCJPEG_API","rocJpegStreamCreate",41884,41884,502,1286306248250747,1286306248268715
|
||||
"ROCJPEG_API","rocJpegStreamParse",41884,41884,503,1286306248421385,1286306248680757
|
||||
"ROCJPEG_API","rocJpegGetImageInfo",41884,41884,504,1286306248684203,1286306248686556
|
||||
|
@@ -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 +1,14 @@
|
||||
"Guid","Domain","Function","Process_Id","Thread_Id","Correlation_Id","Start_Timestamp","End_Timestamp"
|
||||
"0000ddb5-8903-7903-b269-cd8d3745bb8a","HIP_COMPILER_API_EXT","__hipRegisterFatBinary",137,137,1,3719662243949943,3719662243977763
|
||||
"0000ddb5-8903-7903-b269-cd8d3745bb8a","HIP_COMPILER_API_EXT","__hipRegisterFunction",137,137,2,3719662243992513,3719662244013373
|
||||
"0000ddb5-8903-7903-b269-cd8d3745bb8a","HIP_RUNTIME_API_EXT","hipGetDevicePropertiesR0600",137,137,3,3719662244489885,3719662300657772
|
||||
"0000ddb5-8903-7903-b269-cd8d3745bb8a","HIP_RUNTIME_API_EXT","hipMalloc",137,137,4,3719662301007843,3719662301139564
|
||||
"0000ddb5-8903-7903-b269-cd8d3745bb8a","HIP_RUNTIME_API_EXT","hipMalloc",137,137,5,3719662301140994,3719662301221024
|
||||
"0000ddb5-8903-7903-b269-cd8d3745bb8a","HIP_RUNTIME_API_EXT","hipMemcpy",137,137,6,3719662301228614,3719662416709451
|
||||
"0000ddb5-8903-7903-b269-cd8d3745bb8a","HIP_RUNTIME_API_EXT","hipMemcpy",137,137,7,3719662416720791,3719662416728291
|
||||
"0000ddb5-8903-7903-b269-cd8d3745bb8a","HIP_COMPILER_API_EXT","__hipPushCallConfiguration",137,137,8,3719662416731301,3719662416733001
|
||||
"0000ddb5-8903-7903-b269-cd8d3745bb8a","HIP_COMPILER_API_EXT","__hipPopCallConfiguration",137,137,9,3719662416734631,3719662416735421
|
||||
"0000ddb5-8903-7903-b269-cd8d3745bb8a","HIP_RUNTIME_API_EXT","hipLaunchKernel",137,137,10,3719662416752501,3719662417325443
|
||||
"0000ddb5-8903-7903-b269-cd8d3745bb8a","HIP_RUNTIME_API_EXT","hipMemcpy",137,137,11,3719662417327973,3719662418667169
|
||||
"0000ddb5-8903-7903-b269-cd8d3745bb8a","HIP_RUNTIME_API_EXT","hipFree",137,137,12,3719662428427823,3719662428488874
|
||||
"0000ddb5-8903-7903-b269-cd8d3745bb8a","HIP_RUNTIME_API_EXT","hipFree",137,137,13,3719662428491354,3719662428514084
|
||||
|
|
После Ширина: | Высота: | Размер: 35 KiB |
|
После Ширина: | Высота: | Размер: 11 KiB |
|
После Ширина: | Высота: | Размер: 51 KiB |
@@ -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
|
||||
|
|
После Ширина: | Высота: | Размер: 148 KiB |
|
После Ширина: | Высота: | Размер: 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 |
|
||||
|
||||