Buckets:
| { | |
| "schemaVersion": 1, | |
| "deviceProperties": [ | |
| { | |
| "id": 0, "name": "NVIDIA A100-SXM4-80GB", "totalGlobalMem": 85094825984, | |
| "computeMajor": 8, "computeMinor": 0, | |
| "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, | |
| "regsPerBlock": 65536, "warpSize": 32, | |
| "sharedMemPerBlock": 49152, "numSms": 108 | |
| , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 166912, "sharedMemPerMultiprocessor": 167936 | |
| }], | |
| "trace_id": "CB95205FCE4F44DFB8D734233D9CAF1D", | |
| "cuda_driver_version": 12090, | |
| "cuda_runtime_version": 12090, | |
| "cupti_version": 28, | |
| "host_name": "hf-dgx-01", | |
| "displayTimeUnit": "ms", | |
| "baseTimeNanoseconds": 1782967788000000000, | |
| "traceEvents": [ | |
| { | |
| "ph": "M", | |
| "name": "process_name", | |
| "ts": 1851334766831.743, | |
| "pid": 2487845, | |
| "tid": 0, | |
| "args": { | |
| "name": "python3" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_labels", | |
| "ts": 1851334766831.743, | |
| "pid": 2487845, | |
| "tid": 0, | |
| "args": { | |
| "labels": "CPU" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_sort_index", | |
| "ts": 1851334766831.743, | |
| "pid": 2487845, | |
| "tid": 0, | |
| "args": { | |
| "sort_index": 2487845 | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_name", | |
| "ts": 1851334766831.743, | |
| "pid": 0, | |
| "tid": 0, | |
| "args": { | |
| "name": "python3" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_labels", | |
| "ts": 1851334766831.743, | |
| "pid": 0, | |
| "tid": 0, | |
| "args": { | |
| "labels": "GPU 0" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_sort_index", | |
| "ts": 1851334766831.743, | |
| "pid": 0, | |
| "tid": 0, | |
| "args": { | |
| "sort_index": 5000000 | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_name", | |
| "ts": 1851334766831.743, | |
| "pid": 1, | |
| "tid": 0, | |
| "args": { | |
| "name": "python3" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_labels", | |
| "ts": 1851334766831.743, | |
| "pid": 1, | |
| "tid": 0, | |
| "args": { | |
| "labels": "GPU 1" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_sort_index", | |
| "ts": 1851334766831.743, | |
| "pid": 1, | |
| "tid": 0, | |
| "args": { | |
| "sort_index": 5000001 | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_name", | |
| "ts": 1851334766831.743, | |
| "pid": 2, | |
| "tid": 0, | |
| "args": { | |
| "name": "python3" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_labels", | |
| "ts": 1851334766831.743, | |
| "pid": 2, | |
| "tid": 0, | |
| "args": { | |
| "labels": "GPU 2" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_sort_index", | |
| "ts": 1851334766831.743, | |
| "pid": 2, | |
| "tid": 0, | |
| "args": { | |
| "sort_index": 5000002 | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_name", | |
| "ts": 1851334766831.743, | |
| "pid": 3, | |
| "tid": 0, | |
| "args": { | |
| "name": "python3" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_labels", | |
| "ts": 1851334766831.743, | |
| "pid": 3, | |
| "tid": 0, | |
| "args": { | |
| "labels": "GPU 3" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_sort_index", | |
| "ts": 1851334766831.743, | |
| "pid": 3, | |
| "tid": 0, | |
| "args": { | |
| "sort_index": 5000003 | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_name", | |
| "ts": 1851334766831.743, | |
| "pid": 4, | |
| "tid": 0, | |
| "args": { | |
| "name": "python3" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_labels", | |
| "ts": 1851334766831.743, | |
| "pid": 4, | |
| "tid": 0, | |
| "args": { | |
| "labels": "GPU 4" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_sort_index", | |
| "ts": 1851334766831.743, | |
| "pid": 4, | |
| "tid": 0, | |
| "args": { | |
| "sort_index": 5000004 | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_name", | |
| "ts": 1851334766831.743, | |
| "pid": 5, | |
| "tid": 0, | |
| "args": { | |
| "name": "python3" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_labels", | |
| "ts": 1851334766831.743, | |
| "pid": 5, | |
| "tid": 0, | |
| "args": { | |
| "labels": "GPU 5" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_sort_index", | |
| "ts": 1851334766831.743, | |
| "pid": 5, | |
| "tid": 0, | |
| "args": { | |
| "sort_index": 5000005 | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_name", | |
| "ts": 1851334766831.743, | |
| "pid": 6, | |
| "tid": 0, | |
| "args": { | |
| "name": "python3" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_labels", | |
| "ts": 1851334766831.743, | |
| "pid": 6, | |
| "tid": 0, | |
| "args": { | |
| "labels": "GPU 6" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_sort_index", | |
| "ts": 1851334766831.743, | |
| "pid": 6, | |
| "tid": 0, | |
| "args": { | |
| "sort_index": 5000006 | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_name", | |
| "ts": 1851334766831.743, | |
| "pid": 7, | |
| "tid": 0, | |
| "args": { | |
| "name": "python3" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_labels", | |
| "ts": 1851334766831.743, | |
| "pid": 7, | |
| "tid": 0, | |
| "args": { | |
| "labels": "GPU 7" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_sort_index", | |
| "ts": 1851334766831.743, | |
| "pid": 7, | |
| "tid": 0, | |
| "args": { | |
| "sort_index": 5000007 | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_name", | |
| "ts": 1851334766831.743, | |
| "pid": 8, | |
| "tid": 0, | |
| "args": { | |
| "name": "python3" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_labels", | |
| "ts": 1851334766831.743, | |
| "pid": 8, | |
| "tid": 0, | |
| "args": { | |
| "labels": "GPU 8" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_sort_index", | |
| "ts": 1851334766831.743, | |
| "pid": 8, | |
| "tid": 0, | |
| "args": { | |
| "sort_index": 5000008 | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_name", | |
| "ts": 1851334766831.743, | |
| "pid": 9, | |
| "tid": 0, | |
| "args": { | |
| "name": "python3" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_labels", | |
| "ts": 1851334766831.743, | |
| "pid": 9, | |
| "tid": 0, | |
| "args": { | |
| "labels": "GPU 9" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_sort_index", | |
| "ts": 1851334766831.743, | |
| "pid": 9, | |
| "tid": 0, | |
| "args": { | |
| "sort_index": 5000009 | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_name", | |
| "ts": 1851334766831.743, | |
| "pid": 10, | |
| "tid": 0, | |
| "args": { | |
| "name": "python3" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_labels", | |
| "ts": 1851334766831.743, | |
| "pid": 10, | |
| "tid": 0, | |
| "args": { | |
| "labels": "GPU 10" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_sort_index", | |
| "ts": 1851334766831.743, | |
| "pid": 10, | |
| "tid": 0, | |
| "args": { | |
| "sort_index": 5000010 | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_name", | |
| "ts": 1851334766831.743, | |
| "pid": 11, | |
| "tid": 0, | |
| "args": { | |
| "name": "python3" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_labels", | |
| "ts": 1851334766831.743, | |
| "pid": 11, | |
| "tid": 0, | |
| "args": { | |
| "labels": "GPU 11" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_sort_index", | |
| "ts": 1851334766831.743, | |
| "pid": 11, | |
| "tid": 0, | |
| "args": { | |
| "sort_index": 5000011 | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_name", | |
| "ts": 1851334766831.743, | |
| "pid": 12, | |
| "tid": 0, | |
| "args": { | |
| "name": "python3" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_labels", | |
| "ts": 1851334766831.743, | |
| "pid": 12, | |
| "tid": 0, | |
| "args": { | |
| "labels": "GPU 12" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_sort_index", | |
| "ts": 1851334766831.743, | |
| "pid": 12, | |
| "tid": 0, | |
| "args": { | |
| "sort_index": 5000012 | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_name", | |
| "ts": 1851334766831.743, | |
| "pid": 13, | |
| "tid": 0, | |
| "args": { | |
| "name": "python3" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_labels", | |
| "ts": 1851334766831.743, | |
| "pid": 13, | |
| "tid": 0, | |
| "args": { | |
| "labels": "GPU 13" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_sort_index", | |
| "ts": 1851334766831.743, | |
| "pid": 13, | |
| "tid": 0, | |
| "args": { | |
| "sort_index": 5000013 | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_name", | |
| "ts": 1851334766831.743, | |
| "pid": 14, | |
| "tid": 0, | |
| "args": { | |
| "name": "python3" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_labels", | |
| "ts": 1851334766831.743, | |
| "pid": 14, | |
| "tid": 0, | |
| "args": { | |
| "labels": "GPU 14" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_sort_index", | |
| "ts": 1851334766831.743, | |
| "pid": 14, | |
| "tid": 0, | |
| "args": { | |
| "sort_index": 5000014 | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_name", | |
| "ts": 1851334766831.743, | |
| "pid": 15, | |
| "tid": 0, | |
| "args": { | |
| "name": "python3" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_labels", | |
| "ts": 1851334766831.743, | |
| "pid": 15, | |
| "tid": 0, | |
| "args": { | |
| "labels": "GPU 15" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_sort_index", | |
| "ts": 1851334766831.743, | |
| "pid": 15, | |
| "tid": 0, | |
| "args": { | |
| "sort_index": 5000015 | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "thread_name", | |
| "ts": 1851334766831.743, | |
| "pid": 0, | |
| "tid": 7, | |
| "args": { | |
| "name": "stream 7 " | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "thread_sort_index", | |
| "ts": 1851334766831.743, | |
| "pid": 0, | |
| "tid": 7, | |
| "args": { | |
| "sort_index": 7 | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "thread_name", | |
| "ts": 1851334766831.743, | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "args": { | |
| "name": "thread 2487845 (python3)" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "thread_sort_index", | |
| "ts": 1851334766831.743, | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "args": { | |
| "sort_index": 2487845 | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "thread_name", | |
| "ts": 1851334766831.743, | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "args": { | |
| "name": "thread 2487845 (python3)" | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "thread_sort_index", | |
| "ts": 1851334766831.743, | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "args": { | |
| "sort_index": 2487845 | |
| } | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "user_annotation", | |
| "name": "ProfilerStep#2", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334766926.714, | |
| "dur": 244.438 | |
| , | |
| "args": { | |
| "External id": 1,"Record function id": 0, "Ev Idx": 0 | |
| } | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "user_annotation", | |
| "name": "linear_fwd", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334766940.690, | |
| "dur": 221.495 | |
| , | |
| "args": { | |
| "External id": 2,"Record function id": 0, "Ev Idx": 1 | |
| } | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "cpu_op", | |
| "name": "TorchDynamo Cache Lookup", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334766978.310, | |
| "dur": 12.985 | |
| , | |
| "args": { | |
| "External id": 3,"Record function id": 0, "Ev Idx": 2 | |
| } | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "cpu_op", | |
| "name": "Torch-Compiled Region: 0/0", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334766994.320, | |
| "dur": 147.768 | |
| , | |
| "args": { | |
| "External id": 4,"Record function id": 0, "Ev Idx": 3 | |
| } | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "cpu_op", | |
| "name": "Pregraph bytecode", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767021.551, | |
| "dur": 4.329 | |
| , | |
| "args": { | |
| "External id": 5,"Record function id": 0, "Ev Idx": 4 | |
| } | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "cpu_op", | |
| "name": "AOTDispatcher Runtime Wrapper Prologue", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767050.296, | |
| "dur": 2.915 | |
| , | |
| "args": { | |
| "External id": 6,"Record function id": 0, "Ev Idx": 5 | |
| } | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "cpu_op", | |
| "name": "## Call CompiledFxGraph f4qcshesfrszubntdbg3ojazjd4eydwlr6wafrwpsmabese4aqxu ##", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767063.240, | |
| "dur": 71.554 | |
| , | |
| "args": { | |
| "External id": 7,"Record function id": 0, "Ev Idx": 6 | |
| } | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "cpu_op", | |
| "name": "aten::addmm", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767092.945, | |
| "dur": 37.070 | |
| , | |
| "args": { | |
| "External id": 8,"Record function id": 0, "Ev Idx": 7 | |
| } | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "user_annotation", | |
| "name": "ProfilerStep#3", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767187.373, | |
| "dur": 177.773 | |
| , | |
| "args": { | |
| "External id": 9,"Record function id": 0, "Ev Idx": 8 | |
| } | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "user_annotation", | |
| "name": "linear_fwd", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767197.982, | |
| "dur": 159.379 | |
| , | |
| "args": { | |
| "External id": 10,"Record function id": 0, "Ev Idx": 9 | |
| } | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "cpu_op", | |
| "name": "TorchDynamo Cache Lookup", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767223.189, | |
| "dur": 9.158 | |
| , | |
| "args": { | |
| "External id": 11,"Record function id": 0, "Ev Idx": 10 | |
| } | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "cpu_op", | |
| "name": "Torch-Compiled Region: 0/0", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767233.619, | |
| "dur": 105.247 | |
| , | |
| "args": { | |
| "External id": 12,"Record function id": 0, "Ev Idx": 11 | |
| } | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "cpu_op", | |
| "name": "Pregraph bytecode", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767252.034, | |
| "dur": 2.905 | |
| , | |
| "args": { | |
| "External id": 13,"Record function id": 0, "Ev Idx": 12 | |
| } | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "cpu_op", | |
| "name": "AOTDispatcher Runtime Wrapper Prologue", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767264.177, | |
| "dur": 2.514 | |
| , | |
| "args": { | |
| "External id": 14,"Record function id": 0, "Ev Idx": 13 | |
| } | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "cpu_op", | |
| "name": "## Call CompiledFxGraph f4qcshesfrszubntdbg3ojazjd4eydwlr6wafrwpsmabese4aqxu ##", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767272.221, | |
| "dur": 60.193 | |
| , | |
| "args": { | |
| "External id": 15,"Record function id": 0, "Ev Idx": 14 | |
| } | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "cpu_op", | |
| "name": "aten::addmm", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767295.054, | |
| "dur": 32.742 | |
| , | |
| "args": { | |
| "External id": 16,"Record function id": 0, "Ev Idx": 15 | |
| } | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "user_annotation", | |
| "name": "ProfilerStep#4", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767381.096, | |
| "dur": 170.499 | |
| , | |
| "args": { | |
| "External id": 17,"Record function id": 0, "Ev Idx": 16 | |
| } | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "user_annotation", | |
| "name": "linear_fwd", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767390.223, | |
| "dur": 153.548 | |
| , | |
| "args": { | |
| "External id": 18,"Record function id": 0, "Ev Idx": 17 | |
| } | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "cpu_op", | |
| "name": "TorchDynamo Cache Lookup", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767415.300, | |
| "dur": 8.656 | |
| , | |
| "args": { | |
| "External id": 19,"Record function id": 0, "Ev Idx": 18 | |
| } | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "cpu_op", | |
| "name": "Torch-Compiled Region: 0/0", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767425.168, | |
| "dur": 99.928 | |
| , | |
| "args": { | |
| "External id": 20,"Record function id": 0, "Ev Idx": 19 | |
| } | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "cpu_op", | |
| "name": "Pregraph bytecode", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767441.940, | |
| "dur": 2.625 | |
| , | |
| "args": { | |
| "External id": 21,"Record function id": 0, "Ev Idx": 20 | |
| } | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "cpu_op", | |
| "name": "AOTDispatcher Runtime Wrapper Prologue", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767453.071, | |
| "dur": 2.374 | |
| , | |
| "args": { | |
| "External id": 22,"Record function id": 0, "Ev Idx": 21 | |
| } | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "cpu_op", | |
| "name": "## Call CompiledFxGraph f4qcshesfrszubntdbg3ojazjd4eydwlr6wafrwpsmabese4aqxu ##", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767460.595, | |
| "dur": 58.670 | |
| , | |
| "args": { | |
| "External id": 23,"Record function id": 0, "Ev Idx": 22 | |
| } | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "cpu_op", | |
| "name": "aten::addmm", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767482.496, | |
| "dur": 32.230 | |
| , | |
| "args": { | |
| "External id": 24,"Record function id": 0, "Ev Idx": 23 | |
| } | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "cuda_runtime", | |
| "name": "cudaDeviceGetAttribute", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767112.041, | |
| "dur": 0.551 | |
| , | |
| "args": { | |
| "External id": 8, "cbid": 200, "correlation": 40 | |
| } | |
| }, | |
| { | |
| "ph": "f", | |
| "id": 40, | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767112.041, | |
| "cat": "ac2g", | |
| "name": "ac2g" | |
| , "bp": "e" | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "cuda_runtime", | |
| "name": "cudaMemsetAsync", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767114.085, | |
| "dur": 0.331 | |
| , | |
| "args": { | |
| "External id": 8, "cbid": 51, "correlation": 42 | |
| } | |
| }, | |
| { | |
| "ph": "s", | |
| "id": 42, | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767114.085, | |
| "cat": "ac2g", | |
| "name": "ac2g" | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "kernel", | |
| "name": "void cutlass::Kernel2<cutlass_80_wmma_tensorop_bf16_s161616gemm_bf16_32x32_32x1_tn_align8>(cutlass_80_wmma_tensorop_bf16_s161616gemm_bf16_32x32_32x1_tn_align8::Params)", | |
| "pid": 0, | |
| "tid": 7, | |
| "ts": 1851334767127.822, | |
| "dur": 3.264 | |
| , | |
| "args": { | |
| "External id": 8, "queued": 0, "device": 0, "context": 1, "stream": 7, "correlation": 43, "registers per thread": 48, "shared memory": 5120, "blocks per SM": 0.592593, "warps per SM": 2.370370, "grid": [64, 1, 1], "block": [128, 1, 1], "est. achieved occupancy %": 4, "occupancy": { "activeBlocksPerMultiprocessor": 10, "limitingFactors": "REGS", "blockLimitRegs": 10, "blockLimitSharedMem": 27, "blockLimitWarps": 16, "blockLimitBlocks": 32, "blockLimitBarriers": 2147483647, "allocatedRegistersPerBlock": 6144, "allocatedSharedMemPerBlock": 6144 }, "graph id": 0, "graph node id": 0, "channel": 0, "channel_type": 1 | |
| } | |
| }, | |
| { | |
| "ph": "f", | |
| "id": 43, | |
| "pid": 0, | |
| "tid": 7, | |
| "ts": 1851334767127.822, | |
| "cat": "ac2g", | |
| "name": "ac2g" | |
| , "bp": "e" | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "cuda_driver", | |
| "name": "cuLaunchKernel", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767114.726, | |
| "dur": 12.213 | |
| , | |
| "args": { | |
| "External id": 8, "cbid": 307, "correlation": 43 | |
| } | |
| }, | |
| { | |
| "ph": "s", | |
| "id": 43, | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767114.726, | |
| "cat": "ac2g", | |
| "name": "ac2g" | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "cuda_runtime", | |
| "name": "cudaDeviceGetAttribute", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767311.906, | |
| "dur": 0.461 | |
| , | |
| "args": { | |
| "External id": 16, "cbid": 200, "correlation": 63 | |
| } | |
| }, | |
| { | |
| "ph": "f", | |
| "id": 63, | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767311.906, | |
| "cat": "ac2g", | |
| "name": "ac2g" | |
| , "bp": "e" | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "cuda_runtime", | |
| "name": "cudaMemsetAsync", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767313.669, | |
| "dur": 0.311 | |
| , | |
| "args": { | |
| "External id": 16, "cbid": 51, "correlation": 65 | |
| } | |
| }, | |
| { | |
| "ph": "s", | |
| "id": 65, | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767313.669, | |
| "cat": "ac2g", | |
| "name": "ac2g" | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "kernel", | |
| "name": "void cutlass::Kernel2<cutlass_80_wmma_tensorop_bf16_s161616gemm_bf16_32x32_32x1_tn_align8>(cutlass_80_wmma_tensorop_bf16_s161616gemm_bf16_32x32_32x1_tn_align8::Params)", | |
| "pid": 0, | |
| "tid": 7, | |
| "ts": 1851334767326.095, | |
| "dur": 3.072 | |
| , | |
| "args": { | |
| "External id": 16, "queued": 0, "device": 0, "context": 1, "stream": 7, "correlation": 66, "registers per thread": 48, "shared memory": 5120, "blocks per SM": 0.592593, "warps per SM": 2.370370, "grid": [64, 1, 1], "block": [128, 1, 1], "est. achieved occupancy %": 4, "occupancy": { "activeBlocksPerMultiprocessor": 10, "limitingFactors": "REGS", "blockLimitRegs": 10, "blockLimitSharedMem": 27, "blockLimitWarps": 16, "blockLimitBlocks": 32, "blockLimitBarriers": 2147483647, "allocatedRegistersPerBlock": 6144, "allocatedSharedMemPerBlock": 6144 }, "graph id": 0, "graph node id": 0, "channel": 0, "channel_type": 1 | |
| } | |
| }, | |
| { | |
| "ph": "f", | |
| "id": 66, | |
| "pid": 0, | |
| "tid": 7, | |
| "ts": 1851334767326.095, | |
| "cat": "ac2g", | |
| "name": "ac2g" | |
| , "bp": "e" | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "cuda_driver", | |
| "name": "cuLaunchKernel", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767314.280, | |
| "dur": 10.811 | |
| , | |
| "args": { | |
| "External id": 16, "cbid": 307, "correlation": 66 | |
| } | |
| }, | |
| { | |
| "ph": "s", | |
| "id": 66, | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767314.280, | |
| "cat": "ac2g", | |
| "name": "ac2g" | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "cuda_runtime", | |
| "name": "cudaDeviceGetAttribute", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767499.508, | |
| "dur": 0.440 | |
| , | |
| "args": { | |
| "External id": 24, "cbid": 200, "correlation": 86 | |
| } | |
| }, | |
| { | |
| "ph": "f", | |
| "id": 86, | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767499.508, | |
| "cat": "ac2g", | |
| "name": "ac2g" | |
| , "bp": "e" | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "cuda_runtime", | |
| "name": "cudaMemsetAsync", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767501.221, | |
| "dur": 0.281 | |
| , | |
| "args": { | |
| "External id": 24, "cbid": 51, "correlation": 88 | |
| } | |
| }, | |
| { | |
| "ph": "s", | |
| "id": 88, | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767501.221, | |
| "cat": "ac2g", | |
| "name": "ac2g" | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "kernel", | |
| "name": "void cutlass::Kernel2<cutlass_80_wmma_tensorop_bf16_s161616gemm_bf16_32x32_32x1_tn_align8>(cutlass_80_wmma_tensorop_bf16_s161616gemm_bf16_32x32_32x1_tn_align8::Params)", | |
| "pid": 0, | |
| "tid": 7, | |
| "ts": 1851334767513.169, | |
| "dur": 3.136 | |
| , | |
| "args": { | |
| "External id": 24, "queued": 0, "device": 0, "context": 1, "stream": 7, "correlation": 89, "registers per thread": 48, "shared memory": 5120, "blocks per SM": 0.592593, "warps per SM": 2.370370, "grid": [64, 1, 1], "block": [128, 1, 1], "est. achieved occupancy %": 4, "occupancy": { "activeBlocksPerMultiprocessor": 10, "limitingFactors": "REGS", "blockLimitRegs": 10, "blockLimitSharedMem": 27, "blockLimitWarps": 16, "blockLimitBlocks": 32, "blockLimitBarriers": 2147483647, "allocatedRegistersPerBlock": 6144, "allocatedSharedMemPerBlock": 6144 }, "graph id": 0, "graph node id": 0, "channel": 0, "channel_type": 1 | |
| } | |
| }, | |
| { | |
| "ph": "f", | |
| "id": 89, | |
| "pid": 0, | |
| "tid": 7, | |
| "ts": 1851334767513.169, | |
| "cat": "ac2g", | |
| "name": "ac2g" | |
| , "bp": "e" | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "cuda_driver", | |
| "name": "cuLaunchKernel", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767501.752, | |
| "dur": 10.289 | |
| , | |
| "args": { | |
| "External id": 24, "cbid": 307, "correlation": 89 | |
| } | |
| }, | |
| { | |
| "ph": "s", | |
| "id": 89, | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767501.752, | |
| "cat": "ac2g", | |
| "name": "ac2g" | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "cuda_runtime", | |
| "name": "cudaDeviceSynchronize", | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767587.092, | |
| "dur": 10.450 | |
| , | |
| "args": { | |
| "cbid": 165, "correlation": 95 | |
| } | |
| }, | |
| { | |
| "ph": "s", | |
| "id": 95, | |
| "pid": 2487845, | |
| "tid": 2487845, | |
| "ts": 1851334767587.092, | |
| "cat": "ac2g", | |
| "name": "ac2g" | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "gpu_user_annotation", | |
| "name": "linear_fwd", | |
| "pid": 0, | |
| "tid": 7, | |
| "ts": 1851334767513.168, | |
| "dur": 3.138 | |
| , | |
| "args": { | |
| "External id": 18 | |
| } | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "gpu_user_annotation", | |
| "name": "linear_fwd", | |
| "pid": 0, | |
| "tid": 7, | |
| "ts": 1851334767326.094, | |
| "dur": 3.074 | |
| , | |
| "args": { | |
| "External id": 10 | |
| } | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "gpu_user_annotation", | |
| "name": "linear_fwd", | |
| "pid": 0, | |
| "tid": 7, | |
| "ts": 1851334767127.821, | |
| "dur": 3.266 | |
| , | |
| "args": { | |
| "External id": 2 | |
| } | |
| }, | |
| { | |
| "ph": "X", | |
| "cat": "Trace", | |
| "name": "PyTorch Profiler (0)", | |
| "pid": "Spans", | |
| "tid": "PyTorch Profiler", | |
| "ts": 1851334766741.765, | |
| "dur": 862.306 | |
| , | |
| "args": { | |
| "Op count": 0 | |
| } | |
| }, | |
| { | |
| "ph": "M", | |
| "name": "process_sort_index", | |
| "ts": 1851334766741.765, | |
| "pid": "Spans", | |
| "tid": 0, | |
| "args": { | |
| "sort_index": 536870912 | |
| } | |
| }, | |
| { | |
| "ph": "i", | |
| "s": "g", | |
| "name": "Iteration Start: PyTorch Profiler", | |
| "pid": "Traces", | |
| "tid": "Trace PyTorch Profiler", | |
| "ts": 1851334766741.765 | |
| }, | |
| { | |
| "ph": "i", | |
| "s": "g", | |
| "name": "Record Window End", | |
| "pid": "", | |
| "tid": "", | |
| "ts": 1851334767865.351 | |
| } | |
| ],"traceName": "./traces/02_linear/1024_32_64_compile.json" } |
Xet Storage Details
- Size:
- 25.4 kB
- Xet hash:
- e07bf028637773129db9f2a78e9c747708041a4c9afc373066cf3fac8e7c44ce
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.