Hugging Face's logo

Buckets:
iiserkbikram
/
cute-dsl-b200

Files
xet
iiserkbikram/cute-dsl-b200 / matmul_v6_8192_bf16_trace.json
iiserkbikram's picture
iiserkbikram
download
raw
19 kB
{
"schemaVersion": 1,
"deviceProperties": [
{
"id": 0, "name": "NVIDIA B200", "totalGlobalMem": 191503138816,
"computeMajor": 10, "computeMinor": 0,
"maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048,
"regsPerBlock": 65536, "warpSize": 32,
"sharedMemPerBlock": 49152, "numSms": 148
, "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472
}],
"trace_id": "573D9F3ED046497FAA2425D4E31928F9",
"cuda_driver_version": 13000,
"cuda_runtime_version": 13000,
"cupti_version": 130001,
"host_name": "modal",
"displayTimeUnit": "ms",
"baseTimeNanoseconds": 1782967788000000000,
"traceEvents": [
{
"ph": "M",
"name": "process_name",
"ts": 3648296627557.957,
"pid": 33,
"tid": 0,
"args": {
"name": "python3"
}
},
{
"ph": "M",
"name": "process_labels",
"ts": 3648296627557.957,
"pid": 33,
"tid": 0,
"args": {
"labels": "CPU"
}
},
{
"ph": "M",
"name": "process_sort_index",
"ts": 3648296627557.957,
"pid": 33,
"tid": 0,
"args": {
"sort_index": 33
}
},
{
"ph": "M",
"name": "process_name",
"ts": 3648296627557.957,
"pid": 0,
"tid": 0,
"args": {
"name": "python3"
}
},
{
"ph": "M",
"name": "process_labels",
"ts": 3648296627557.957,
"pid": 0,
"tid": 0,
"args": {
"labels": "GPU 0"
}
},
{
"ph": "M",
"name": "process_sort_index",
"ts": 3648296627557.957,
"pid": 0,
"tid": 0,
"args": {
"sort_index": 5000000
}
},
{
"ph": "M",
"name": "process_name",
"ts": 3648296627557.957,
"pid": 1,
"tid": 0,
"args": {
"name": "python3"
}
},
{
"ph": "M",
"name": "process_labels",
"ts": 3648296627557.957,
"pid": 1,
"tid": 0,
"args": {
"labels": "GPU 1"
}
},
{
"ph": "M",
"name": "process_sort_index",
"ts": 3648296627557.957,
"pid": 1,
"tid": 0,
"args": {
"sort_index": 5000001
}
},
{
"ph": "M",
"name": "process_name",
"ts": 3648296627557.957,
"pid": 2,
"tid": 0,
"args": {
"name": "python3"
}
},
{
"ph": "M",
"name": "process_labels",
"ts": 3648296627557.957,
"pid": 2,
"tid": 0,
"args": {
"labels": "GPU 2"
}
},
{
"ph": "M",
"name": "process_sort_index",
"ts": 3648296627557.957,
"pid": 2,
"tid": 0,
"args": {
"sort_index": 5000002
}
},
{
"ph": "M",
"name": "process_name",
"ts": 3648296627557.957,
"pid": 3,
"tid": 0,
"args": {
"name": "python3"
}
},
{
"ph": "M",
"name": "process_labels",
"ts": 3648296627557.957,
"pid": 3,
"tid": 0,
"args": {
"labels": "GPU 3"
}
},
{
"ph": "M",
"name": "process_sort_index",
"ts": 3648296627557.957,
"pid": 3,
"tid": 0,
"args": {
"sort_index": 5000003
}
},
{
"ph": "M",
"name": "process_name",
"ts": 3648296627557.957,
"pid": 4,
"tid": 0,
"args": {
"name": "python3"
}
},
{
"ph": "M",
"name": "process_labels",
"ts": 3648296627557.957,
"pid": 4,
"tid": 0,
"args": {
"labels": "GPU 4"
}
},
{
"ph": "M",
"name": "process_sort_index",
"ts": 3648296627557.957,
"pid": 4,
"tid": 0,
"args": {
"sort_index": 5000004
}
},
{
"ph": "M",
"name": "process_name",
"ts": 3648296627557.957,
"pid": 5,
"tid": 0,
"args": {
"name": "python3"
}
},
{
"ph": "M",
"name": "process_labels",
"ts": 3648296627557.957,
"pid": 5,
"tid": 0,
"args": {
"labels": "GPU 5"
}
},
{
"ph": "M",
"name": "process_sort_index",
"ts": 3648296627557.957,
"pid": 5,
"tid": 0,
"args": {
"sort_index": 5000005
}
},
{
"ph": "M",
"name": "process_name",
"ts": 3648296627557.957,
"pid": 6,
"tid": 0,
"args": {
"name": "python3"
}
},
{
"ph": "M",
"name": "process_labels",
"ts": 3648296627557.957,
"pid": 6,
"tid": 0,
"args": {
"labels": "GPU 6"
}
},
{
"ph": "M",
"name": "process_sort_index",
"ts": 3648296627557.957,
"pid": 6,
"tid": 0,
"args": {
"sort_index": 5000006
}
},
{
"ph": "M",
"name": "process_name",
"ts": 3648296627557.957,
"pid": 7,
"tid": 0,
"args": {
"name": "python3"
}
},
{
"ph": "M",
"name": "process_labels",
"ts": 3648296627557.957,
"pid": 7,
"tid": 0,
"args": {
"labels": "GPU 7"
}
},
{
"ph": "M",
"name": "process_sort_index",
"ts": 3648296627557.957,
"pid": 7,
"tid": 0,
"args": {
"sort_index": 5000007
}
},
{
"ph": "M",
"name": "process_name",
"ts": 3648296627557.957,
"pid": 8,
"tid": 0,
"args": {
"name": "python3"
}
},
{
"ph": "M",
"name": "process_labels",
"ts": 3648296627557.957,
"pid": 8,
"tid": 0,
"args": {
"labels": "GPU 8"
}
},
{
"ph": "M",
"name": "process_sort_index",
"ts": 3648296627557.957,
"pid": 8,
"tid": 0,
"args": {
"sort_index": 5000008
}
},
{
"ph": "M",
"name": "process_name",
"ts": 3648296627557.957,
"pid": 9,
"tid": 0,
"args": {
"name": "python3"
}
},
{
"ph": "M",
"name": "process_labels",
"ts": 3648296627557.957,
"pid": 9,
"tid": 0,
"args": {
"labels": "GPU 9"
}
},
{
"ph": "M",
"name": "process_sort_index",
"ts": 3648296627557.957,
"pid": 9,
"tid": 0,
"args": {
"sort_index": 5000009
}
},
{
"ph": "M",
"name": "process_name",
"ts": 3648296627557.957,
"pid": 10,
"tid": 0,
"args": {
"name": "python3"
}
},
{
"ph": "M",
"name": "process_labels",
"ts": 3648296627557.957,
"pid": 10,
"tid": 0,
"args": {
"labels": "GPU 10"
}
},
{
"ph": "M",
"name": "process_sort_index",
"ts": 3648296627557.957,
"pid": 10,
"tid": 0,
"args": {
"sort_index": 5000010
}
},
{
"ph": "M",
"name": "process_name",
"ts": 3648296627557.957,
"pid": 11,
"tid": 0,
"args": {
"name": "python3"
}
},
{
"ph": "M",
"name": "process_labels",
"ts": 3648296627557.957,
"pid": 11,
"tid": 0,
"args": {
"labels": "GPU 11"
}
},
{
"ph": "M",
"name": "process_sort_index",
"ts": 3648296627557.957,
"pid": 11,
"tid": 0,
"args": {
"sort_index": 5000011
}
},
{
"ph": "M",
"name": "process_name",
"ts": 3648296627557.957,
"pid": 12,
"tid": 0,
"args": {
"name": "python3"
}
},
{
"ph": "M",
"name": "process_labels",
"ts": 3648296627557.957,
"pid": 12,
"tid": 0,
"args": {
"labels": "GPU 12"
}
},
{
"ph": "M",
"name": "process_sort_index",
"ts": 3648296627557.957,
"pid": 12,
"tid": 0,
"args": {
"sort_index": 5000012
}
},
{
"ph": "M",
"name": "process_name",
"ts": 3648296627557.957,
"pid": 13,
"tid": 0,
"args": {
"name": "python3"
}
},
{
"ph": "M",
"name": "process_labels",
"ts": 3648296627557.957,
"pid": 13,
"tid": 0,
"args": {
"labels": "GPU 13"
}
},
{
"ph": "M",
"name": "process_sort_index",
"ts": 3648296627557.957,
"pid": 13,
"tid": 0,
"args": {
"sort_index": 5000013
}
},
{
"ph": "M",
"name": "process_name",
"ts": 3648296627557.957,
"pid": 14,
"tid": 0,
"args": {
"name": "python3"
}
},
{
"ph": "M",
"name": "process_labels",
"ts": 3648296627557.957,
"pid": 14,
"tid": 0,
"args": {
"labels": "GPU 14"
}
},
{
"ph": "M",
"name": "process_sort_index",
"ts": 3648296627557.957,
"pid": 14,
"tid": 0,
"args": {
"sort_index": 5000014
}
},
{
"ph": "M",
"name": "process_name",
"ts": 3648296627557.957,
"pid": 15,
"tid": 0,
"args": {
"name": "python3"
}
},
{
"ph": "M",
"name": "process_labels",
"ts": 3648296627557.957,
"pid": 15,
"tid": 0,
"args": {
"labels": "GPU 15"
}
},
{
"ph": "M",
"name": "process_sort_index",
"ts": 3648296627557.957,
"pid": 15,
"tid": 0,
"args": {
"sort_index": 5000015
}
},
{
"ph": "M",
"name": "thread_name",
"ts": 3648296627557.957,
"pid": 0,
"tid": 7,
"args": {
"name": "stream 7 "
}
},
{
"ph": "M",
"name": "thread_sort_index",
"ts": 3648296627557.957,
"pid": 0,
"tid": 7,
"args": {
"sort_index": 7
}
},
{
"ph": "M",
"name": "thread_name",
"ts": 3648296627557.957,
"pid": 33,
"tid": 33,
"args": {
"name": "thread 33 (python3)"
}
},
{
"ph": "M",
"name": "thread_sort_index",
"ts": 3648296627557.957,
"pid": 33,
"tid": 33,
"args": {
"sort_index": 33
}
},
{
"ph": "M",
"name": "thread_name",
"ts": 3648296627557.957,
"pid": 33,
"tid": 33,
"args": {
"name": "thread 33 (python3)"
}
},
{
"ph": "M",
"name": "thread_sort_index",
"ts": 3648296627557.957,
"pid": 33,
"tid": 33,
"args": {
"sort_index": 33
}
},
{
"ph": "X",
"cat": "overhead",
"name": "Runtime Triggered Module Loading",
"pid": -1,
"tid": 0,
"ts": 3648296627681.250,
"dur": 46.030
},
{
"ph": "X",
"cat": "overhead",
"name": "Activity Buffer Request",
"pid": -1,
"tid": 0,
"ts": 3648296627727.710,
"dur": 196.581
},
{
"ph": "X",
"cat": "cuda_runtime",
"name": "cudaLibraryLoadData",
"pid": 33,
"tid": 33,
"ts": 3648296627678.366,
"dur": 254.024
,
"args": {
"cbid": 470, "correlation": 2618
}
},
{
"ph": "f",
"id": 2618,
"pid": 33,
"tid": 33,
"ts": 3648296627678.366,
"cat": "ac2g",
"name": "ac2g"
, "bp": "e"
},
{
"ph": "X",
"cat": "cuda_runtime",
"name": "cudaGetDeviceCount",
"pid": 33,
"tid": 33,
"ts": 3648296627986.077,
"dur": 0.281
,
"args": {
"cbid": 3, "correlation": 2619
}
},
{
"ph": "f",
"id": 2619,
"pid": 33,
"tid": 33,
"ts": 3648296627986.077,
"cat": "ac2g",
"name": "ac2g"
, "bp": "e"
},
{
"ph": "X",
"cat": "cuda_runtime",
"name": "cudaDeviceGetAttribute",
"pid": 33,
"tid": 33,
"ts": 3648296627991.946,
"dur": 2.334
,
"args": {
"cbid": 200, "correlation": 2620
}
},
{
"ph": "f",
"id": 2620,
"pid": 33,
"tid": 33,
"ts": 3648296627991.946,
"cat": "ac2g",
"name": "ac2g"
, "bp": "e"
},
{
"ph": "X",
"cat": "cuda_runtime",
"name": "cudaLibraryGetKernel",
"pid": 33,
"tid": 33,
"ts": 3648296627995.032,
"dur": 1.469
,
"args": {
"cbid": 473, "correlation": 2621
}
},
{
"ph": "f",
"id": 2621,
"pid": 33,
"tid": 33,
"ts": 3648296627995.032,
"cat": "ac2g",
"name": "ac2g"
, "bp": "e"
},
{
"ph": "X",
"cat": "overhead",
"name": "Lazy Function Loading",
"pid": -1,
"tid": 0,
"ts": 3648296628063.401,
"dur": 42.863
},
{
"ph": "X",
"cat": "cuda_runtime",
"name": "cudaKernelSetAttributeForDevice",
"pid": 33,
"tid": 33,
"ts": 3648296628001.611,
"dur": 105.501
,
"args": {
"cbid": 479, "correlation": 2624
}
},
{
"ph": "f",
"id": 2624,
"pid": 33,
"tid": 33,
"ts": 3648296628001.611,
"cat": "ac2g",
"name": "ac2g"
, "bp": "e"
},
{
"ph": "X",
"cat": "cuda_runtime",
"name": "cudaKernelSetAttributeForDevice",
"pid": 33,
"tid": 33,
"ts": 3648296628107.367,
"dur": 0.916
,
"args": {
"cbid": 479, "correlation": 2625
}
},
{
"ph": "f",
"id": 2625,
"pid": 33,
"tid": 33,
"ts": 3648296628107.367,
"cat": "ac2g",
"name": "ac2g"
, "bp": "e"
},
{
"ph": "X",
"cat": "kernel",
"name": "kernel_cutlass_kernel_TiledMMA_ThrLayoutVMNK21111000_PermutationMNK____MMAAtom_ThrID21_ShapeMNK25625616_TVLayoutA2128161281256_TVLayoutB2128161281256_TVLayoutC21282561281256_CopyAtom_ThrI_0",
"pid": 0,
"tid": 7,
"ts": 3648296629293.928,
"dur": 616.801
,
"args": {
"queued": 0, "device": 0, "context": 1, "stream": 7, "correlation": 2627, "registers per thread": 39, "shared memory": 213120, "blocks per SM": 13.837838, "warps per SM": 83.027031, "grid": [64, 32, 1], "block": [192, 1, 1], "est. achieved occupancy %": 0, "occupancy": { "activeBlocksPerMultiprocessor": 0, "limitingFactors": "SMEM", "blockLimitRegs": 8, "blockLimitSharedMem": 0, "blockLimitWarps": 10, "blockLimitBlocks": 32, "blockLimitBarriers": 2147483647, "allocatedRegistersPerBlock": 7680, "allocatedSharedMemPerBlock": 214144 }, "graph id": 0, "graph node id": 0, "channel": 0, "channel_type": 1
}
},
{
"ph": "f",
"id": 2627,
"pid": 0,
"tid": 7,
"ts": 3648296629293.928,
"cat": "ac2g",
"name": "ac2g"
, "bp": "e"
},
{
"ph": "X",
"cat": "cuda_runtime",
"name": "cudaLaunchKernelExC",
"pid": 33,
"tid": 33,
"ts": 3648296628138.968,
"dur": 1159.124
,
"args": {
"cbid": 430, "correlation": 2627
}
},
{
"ph": "s",
"id": 2627,
"pid": 33,
"tid": 33,
"ts": 3648296628138.968,
"cat": "ac2g",
"name": "ac2g"
},
{
"ph": "X",
"cat": "kernel",
"name": "kernel_cutlass_kernel_TiledMMA_ThrLayoutVMNK21111000_PermutationMNK____MMAAtom_ThrID21_ShapeMNK25625616_TVLayoutA2128161281256_TVLayoutB2128161281256_TVLayoutC21282561281256_CopyAtom_ThrI_0",
"pid": 0,
"tid": 7,
"ts": 3648296629912.361,
"dur": 606.946
,
"args": {
"queued": 0, "device": 0, "context": 1, "stream": 7, "correlation": 2629, "registers per thread": 39, "shared memory": 213120, "blocks per SM": 13.837838, "warps per SM": 83.027031, "grid": [64, 32, 1], "block": [192, 1, 1], "est. achieved occupancy %": 0, "occupancy": { "activeBlocksPerMultiprocessor": 0, "limitingFactors": "SMEM", "blockLimitRegs": 8, "blockLimitSharedMem": 0, "blockLimitWarps": 10, "blockLimitBlocks": 32, "blockLimitBarriers": 2147483647, "allocatedRegistersPerBlock": 7680, "allocatedSharedMemPerBlock": 214144 }, "graph id": 0, "graph node id": 0, "channel": 0, "channel_type": 1
}
},
{
"ph": "f",
"id": 2629,
"pid": 0,
"tid": 7,
"ts": 3648296629912.361,
"cat": "ac2g",
"name": "ac2g"
, "bp": "e"
},
{
"ph": "X",
"cat": "cuda_runtime",
"name": "cudaLaunchKernelExC",
"pid": 33,
"tid": 33,
"ts": 3648296629318.990,
"dur": 8.623
,
"args": {
"cbid": 430, "correlation": 2629
}
},
{
"ph": "s",
"id": 2629,
"pid": 33,
"tid": 33,
"ts": 3648296629318.990,
"cat": "ac2g",
"name": "ac2g"
},
{
"ph": "X",
"cat": "kernel",
"name": "kernel_cutlass_kernel_TiledMMA_ThrLayoutVMNK21111000_PermutationMNK____MMAAtom_ThrID21_ShapeMNK25625616_TVLayoutA2128161281256_TVLayoutB2128161281256_TVLayoutC21282561281256_CopyAtom_ThrI_0",
"pid": 0,
"tid": 7,
"ts": 3648296630520.523,
"dur": 615.522
,
"args": {
"queued": 0, "device": 0, "context": 1, "stream": 7, "correlation": 2631, "registers per thread": 39, "shared memory": 213120, "blocks per SM": 13.837838, "warps per SM": 83.027031, "grid": [64, 32, 1], "block": [192, 1, 1], "est. achieved occupancy %": 0, "occupancy": { "activeBlocksPerMultiprocessor": 0, "limitingFactors": "SMEM", "blockLimitRegs": 8, "blockLimitSharedMem": 0, "blockLimitWarps": 10, "blockLimitBlocks": 32, "blockLimitBarriers": 2147483647, "allocatedRegistersPerBlock": 7680, "allocatedSharedMemPerBlock": 214144 }, "graph id": 0, "graph node id": 0, "channel": 0, "channel_type": 1
}
},
{
"ph": "f",
"id": 2631,
"pid": 0,
"tid": 7,
"ts": 3648296630520.523,
"cat": "ac2g",
"name": "ac2g"
, "bp": "e"
},
{
"ph": "X",
"cat": "cuda_runtime",
"name": "cudaLaunchKernelExC",
"pid": 33,
"tid": 33,
"ts": 3648296629332.253,
"dur": 5.430
,
"args": {
"cbid": 430, "correlation": 2631
}
},
{
"ph": "s",
"id": 2631,
"pid": 33,
"tid": 33,
"ts": 3648296629332.253,
"cat": "ac2g",
"name": "ac2g"
},
{
"ph": "X",
"cat": "cuda_runtime",
"name": "cudaDeviceSynchronize",
"pid": 33,
"tid": 33,
"ts": 3648296629387.241,
"dur": 1753.758
,
"args": {
"cbid": 165, "correlation": 2634
}
},
{
"ph": "s",
"id": 2634,
"pid": 33,
"tid": 33,
"ts": 3648296629387.241,
"cat": "ac2g",
"name": "ac2g"
},
{
"ph": "X",
"cat": "cuda_runtime",
"name": "cudaDeviceSynchronize",
"pid": 33,
"tid": 33,
"ts": 3648296631160.482,
"dur": 3.666
,
"args": {
"cbid": 165, "correlation": 2638
}
},
{
"ph": "s",
"id": 2638,
"pid": 33,
"tid": 33,
"ts": 3648296631160.482,
"cat": "ac2g",
"name": "ac2g"
},
{
"ph": "X",
"cat": "Trace",
"name": "PyTorch Profiler (0)",
"pid": "Spans",
"tid": "PyTorch Profiler",
"ts": 3648296627482.265,
"dur": 3696.629
,
"args": {
"Op count": 0
}
},
{
"ph": "M",
"name": "process_sort_index",
"ts": 3648296627482.265,
"pid": "Spans",
"tid": 0,
"args": {
"sort_index": 536870912
}
},
{
"ph": "i",
"s": "g",
"name": "Iteration Start: PyTorch Profiler",
"pid": "Traces",
"tid": "Trace PyTorch Profiler",
"ts": 3648296627482.265
},
{
"ph": "i",
"s": "g",
"name": "Record Window End",
"pid": "",
"tid": "",
"ts": 3648296631311.163
}
],"traceName": "/root/gpulab/kernels/cute_dsl/B200/traces/matmul_v6_8192_bf16_trace.json" }

Xet Storage Details

Size:
19 kB
·
Xet hash:
eb101d8f8fe6dbd41b357877ebf900a74c30225a741502e5199acfe3c980dc57

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.