ruihan/qwen38-flash-next-dgx-spark
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
73a88a4e8c7f9be4af81fbeb53f07234a4c976f6
qwen38-flash-next-dgx-spark/docs/results/profile128k/eager/trace.1.summary.json
T

1360 lines
31 KiB
JSON
Raw Blame History

{
"file": "trace.1.sqlite",
"gpu_activity_span_s": 7.586749984,
"gpu_busy_union_s": 7.056227059,
"gpu_idle_within_span_s": 0.5305229249999996,
"kernel_count": 202979,
"graph_node_kernel_count": 0,
"api": {
"cudaStreamSynchronize_v3020": [
182,
2.079318495999998
],
"cudaLaunchKernel_v7000": [
54838,
0.24995051199999746
],
"cudaLaunchKernelExC_v11060": [
58978,
0.22468139200000006
],
"cuLaunchKernelEx": [
43506,
0.17475352000000302
],
"cuLaunchKernel": [
45657,
0.16430793600000082
],
"cudaMemcpyAsync_v3020": [
3045,
0.020035984000000007
],
"cudaEventRecordWithFlags_v11010": [
10742,
0.01840999999999997
],
"cudaMemsetAsync_v3020": [
1505,
0.012147199999999986
],
"cudaEventSynchronize_v3020": [
91,
0.010570208
],
"cuKernelGetFunction": [
45657,
0.010197935999999857
],
"cuTensorMapEncodeTiled": [
54236,
0.009425376000000653
],
"cudaStreamWaitEvent_v3020": [
9191,
0.0071444320000000885
],
"cudaGetDriverEntryPointByVersion_v12050": [
52416,
0.007047104000000629
],
"cuKernelGetName": [
54874,
0.005113008000000064
],
"cudaStreamIsCapturing_v10000": [
21668,
0.004255872000000042
],
"cudaEventQuery_v3020": [
2807,
0.0037000799999999962
],
"cudaEventCreateWithFlags_v3020": [
182,
0.00048713600000000005
],
"cudaEventDestroy_v3020": [
182,
0.00035211199999999997
],
"cuProfilerStart": [
1,
3.68e-06
]
},
"nvtx": {
"PLE_lookup_tokens=65": {
"count": 1,
"sum_s": 0.020658576,
"union_s": 0.020658576,
"gpu_overlap_s": 0.003048383
},
"PLE_wait_for_GPU": {
"count": 91,
"sum_s": 2.080225232,
"union_s": 2.080225232,
"gpu_overlap_s": 2.022631604
},
"PLE_CPU_dedup": {
"count": 91,
"sum_s": 0.010647504,
"union_s": 0.010647504,
"gpu_overlap_s": 0.0
},
"PLE_CPU_gather": {
"count": 91,
"sum_s": 0.205608928,
"union_s": 0.205608928,
"gpu_overlap_s": 0.0
},
"PLE_lookup_tokens=3": {
"count": 90,
"sum_s": 2.30164368,
"union_s": 2.30164368,
"gpu_overlap_s": 2.021470021
}
},
"dispatch": {
"CG_DISPATCH:actual=65:mode=NONE:padded=65": 2,
"CG_DISPATCH:actual=1:mode=NONE:padded=1": 91,
"CG_DISPATCH:actual=3:mode=NONE:padded=3": 180
},
"dispatch_timeline": [
{
"start_ns": 17438320,
"name": "CG_DISPATCH:actual=65:mode=NONE:padded=65"
},
{
"start_ns": 124235952,
"name": "CG_DISPATCH:actual=65:mode=NONE:padded=65"
},
{
"start_ns": 129678288,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 136941248,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 286806832,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 289606848,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 293471664,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 368743600,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 371514912,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 376462432,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 453781600,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 456739920,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 460413056,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 536449168,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 539166960,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 542776384,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 615999648,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 618734112,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 622156496,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 694494208,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 696318144,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 699071840,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 782685200,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 785371744,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 788993600,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 856634992,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 858405328,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 860975728,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 958298720,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 960984800,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 964327152,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1059155248,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1061931664,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 1066324192,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1127850688,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1129772800,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 1132513776,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1220754320,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1223418944,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 1226770304,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1298870480,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1301033312,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 1304118192,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1380386000,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1382259936,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 1384892576,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1460797792,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1462833040,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 1465629392,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1537765408,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1539550800,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 1541997424,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1629499648,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1631387328,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 1633883408,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1708912176,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1710699632,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 1713210736,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1790816912,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1792644048,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 1795146992,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1870817968,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1872671872,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 1875210272,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1950202000,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 1952042944,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 1954554512,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2041364064,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2044219968,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 2047637024,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2123520784,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2126140416,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 2129552672,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2205234528,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2207880240,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 2211187744,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2278602528,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2280424464,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 2283191584,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2368450112,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2371453984,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 2375914336,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2455679344,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2458628160,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 2462892016,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2530215792,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2532250208,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 2535136240,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2610570208,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2613299984,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 2616791440,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2692349904,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2695036208,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 2698467760,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2774251936,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2777030752,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 2780326960,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2858471584,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2861095872,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 2864438992,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2937209248,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 2939144080,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 2942096480,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3028829104,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3031540672,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 3035380352,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3106636416,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3109306800,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 3112664800,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3177024528,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3178847552,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 3181404144,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3256227776,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3258118368,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 3260831200,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3341560080,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3344335504,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 3347577056,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3424908288,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3428505168,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 3434771440,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3515208624,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3518361888,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 3522555104,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3604920544,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3608230752,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 3612500320,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3681906240,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3684753216,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 3688910144,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3761645072,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3764261664,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 3768177200,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3841820928,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3844485488,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 3848230288,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3919997248,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3922656576,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 3926549888,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 3998511568,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 4001042896,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 4004398320,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 4077757536,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 4080133952,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 4083990032,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 4165652720,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 4168213040,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 4172091264,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 4241922832,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 4244396208,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 4247963648,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 4321381280,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 4323908160,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 4327237792,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 4399516832,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 4402039760,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 4405563904,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 4484929408,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 4487867456,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 4492094080,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 4574677152,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 4578142000,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 4582414896,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 4656267728,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 4659282720,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 4662911280,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 4735184384,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 4737974800,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 4741885664,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 4816240544,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 4818970160,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 4822755440,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 4896767136,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 4899390128,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 4903103488,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 4974594928,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 4977129568,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 4980609952,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 5056260576,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 5058908384,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 5062746816,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 5137479520,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 5140079200,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 5143402416,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 5217012208,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 5219752256,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 5223068368,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 5300106944,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 5302713520,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 5306089344,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 5380831296,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 5383467072,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 5386802896,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 5462901232,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 5465557584,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 5468789360,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 5543956416,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 5546826096,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 5550711776,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 5633901968,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 5636984672,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 5641085472,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 5712274816,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 5714265376,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 5717106384,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 5793312512,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 5796036416,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 5799641536,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 5872665344,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 5875403248,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 5878970752,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 5949957968,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 5952580480,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 5955942192,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 6030408848,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 6033044640,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 6036467744,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 6113939440,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 6116655152,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 6120012720,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 6195827344,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 6198511824,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 6202004064,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 6275304352,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 6278033664,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 6281977264,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 6347953632,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 6349902128,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 6352726864,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 6435242704,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 6437831248,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 6441155632,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 6516233696,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 6518865344,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 6522046688,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 6597900848,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 6600763072,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 6604397120,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 6689062400,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 6692174064,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 6696543840,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 6771272752,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 6774147168,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 6778022304,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 6840825152,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 6842689088,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 6845361152,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 6920158384,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 6922016848,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 6924658480,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 7000425216,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 7002334896,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 7005011712,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 7079371520,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 7081222192,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 7083793248,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 7161236528,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 7163096544,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 7165640480,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 7240504976,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 7242369024,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 7244856304,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 7326033360,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 7328716416,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 7332046976,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 7407135936,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 7409776448,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 7413228224,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 7487750880,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 7490446832,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
},
{
"start_ns": 7493726800,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 7571332192,
"name": "CG_DISPATCH:actual=3:mode=NONE:padded=3"
},
{
"start_ns": 7574038768,
"name": "CG_DISPATCH:actual=1:mode=NONE:padded=1"
}
],
"top_kernels": [
[
"Kernel2",
[
45657,
3.960617126999972
]
],
[
"device_kernel",
[
8736,
1.4289199419999952
]
],
[
"kernel",
[
960,
1.3123140460000013
]
],
[
"sm120_fp8_fp4_gemm_1d1d_impl",
[
364,
0.10677743999999993
]
],
[
"gdn_decode_post_conv_mtp_kernel",
[
3240,
0.091146944
]
],
[
"computeStridesTmaWarpSpecializedKernel",
[
4368,
0.04410477599999992
]
],
[
"dot_kernel",
[
4410,
0.04041190400000002
]
],
[
"finalizeMoeRoutingKernel",
[
4368,
0.03951238399999967
]
],
[
"expandInputRowsKernel",
[
4368,
0.03720516199999999
]
],
[
"topkGating",
[
4550,
0.03414536599999995
]
],
[
"splitKreduce_kernel",
[
15080,
0.03348128000000034
]
],
[
"blockExpertPrefixSumKernel",
[
4368,
0.0319338699999999
]
],
[
"vectorized_elementwise_kernel",
[
18021,
0.02700927599999959
]
],
[
"_hc_combine_norm_kernel",
[
9191,
0.025802368000000457
]
],
[
"doActivationKernel",
[
4368,
0.021267572999999918
]
],
[
"mergeExpertPrefixSumKernel",
[
4368,
0.017134488999999968
]
],
[
"elementwise_kernel",
[
6150,
0.016718143999999893
]
],
[
"reduce_1Block_kernel",
[
4410,
0.016691328000000078
]
],
[
"cvt_fp16_to_fp4",
[
4368,
0.01633820799999996
]
],
[
"_qsa_sparse_paged_gqa_splitk_kernel",
[
1274,
0.015009248000000022
]
]
],
"notes": "GPU busy is interval union, not utilization counter. CPU/API/NVTX times overlap GPU work and each other; do not sum them as exclusive costs."
}
Reference in New Issue View Git Blame Copy Permalink