Initial commit

Cette révision appartient à :
colramos-amd
2022-11-04 14:49:36 -05:00
révision 62d130b458
9127 fichiers modifiés avec 371405 ajouts et 0 suppressions
+168
Voir le fichier
@@ -0,0 +1,168 @@
Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,BeginNs,EndNs,CompleteNs
0,"__amd_rocclr_fillBufferAligned.kd",0,0,0,236503,236503,33554432,256,0,0,4,32,4160,0x0,0x7fe83c204280,385832,385832,524288,4718592,682094,76386864,17833173257611,17832460487290,17833324063793,17833324177862
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,236503,236503,32768,256,0,0,12,24,13888,0x0,0x7fe83c223f80,34124,34124,512,8192,5540,624020,17833329373303,17833324063793,17833329503317,17833329508120
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,236503,236503,4194304,256,0,0,12,24,14336,0x7fe83f16b380,0x7fe83c223fc0,166451,166451,65536,917504,140662,15737800,17833329547519,17833329503317,17833329887317,17833329890091
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,236503,236503,4194304,256,0,0,16,24,15040,0x7fe83f16b200,0x7fe83c224000,320813,320813,65536,1114112,167869,18973284,17833329928940,17833329887317,17833330326517,17833330329380
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,236503,236503,4194304,256,0,0,16,24,15488,0x7fe83f16b080,0x7fe83c224040,323006,323006,65536,917504,146978,16539568,17833330364489,17833330326517,17833330747798,17833330753919
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,236503,236503,4194304,256,0,0,12,24,15936,0x7fe83cb0bf00,0x7fe83c224080,168550,168550,65536,1048576,159174,17856292,17833330784798,17833330747798,17833331068118,17833331070481
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,236503,236503,4194304,256,0,0,12,24,16384,0x7fe83cb0bd80,0x7fe83c2240c0,168572,168572,65536,983040,148090,16569436,17833331104930,17833331068118,17833331386678,17833331389103
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,236503,236503,4194304,256,0,0,12,24,17088,0x7fe83cb0bc00,0x7fe83c224100,167664,167664,65536,1114112,162610,18224860,17833331435702,17833331386678,17833331703318,17833331705705
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,236503,236503,4194304,256,0,0,16,24,17792,0x7fe83cb0ba80,0x7fe83c224140,320079,320079,65536,1310720,202232,22647988,17833331740015,17833331703318,17833332108599,17833332110925
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,236503,236503,4194304,256,0,0,16,24,18496,0x7fe83cb0b900,0x7fe83c224180,316809,316809,65536,1179648,176290,19855416,17833332143565,17833332108599,17833332528439,17833332530935
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,236503,236503,4194304,256,0,0,16,24,19200,0x7fe83cb0b780,0x7fe83c2241c0,168281,168281,65536,1245184,188620,21166232,17833332564054,17833332528439,17833332839959,17833332842307
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,236503,236503,4194304,256,0,0,16,24,19904,0x7fe83cb0b600,0x7fe83c224200,169494,169494,65536,1245184,202520,22612512,17833332876086,17833332839959,17833333154039,17833333156369
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,236503,236503,4194304,256,0,0,12,24,20608,0x7fe83f16b480,0x7fe83c224240,171299,171299,65536,1245184,200754,22467976,17833333198828,17833333154039,17833333471320,17833333473552
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,236503,236503,4194304,256,0,0,16,24,21312,0x7fe83f16b300,0x7fe83c224280,320776,320776,65536,1441792,216093,24168728,17833333508101,17833333471320,17833333874840,17833333881351
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,236503,236503,4194304,256,0,0,16,24,22016,0x7fe83f16b180,0x7fe83c2242c0,316393,316393,65536,1310720,197617,22204988,17833333911551,17833333874840,17833334286360,17833334289041
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,236503,236503,4194304,256,0,0,16,24,22720,0x7fe83f16b000,0x7fe83c224300,169264,169264,65536,1376256,205151,23034404,17833334324160,17833334286360,17833334608441,17833334610943
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,236503,236503,4194304,256,0,0,12,24,23424,0x7fe83cb0be80,0x7fe83c224340,168263,168263,65536,1441792,221753,24858852,17833334644352,17833334608441,17833334922841,17833334925195
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,236503,236503,4194304,256,0,0,12,24,24128,0x7fe83cb0bd00,0x7fe83c224380,167492,167492,65536,1310720,195746,21931324,17833334967074,17833334922841,17833335246361,17833335248667
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,236503,236503,4194304,256,0,0,16,24,24832,0x7fe83cb0bb80,0x7fe83c2243c0,316291,316291,65536,1572864,232311,26113788,17833335285227,17833335246361,17833335624441,17833335626348
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,236503,236503,4194304,256,0,0,16,24,25536,0x7fe83cb0ba00,0x7fe83c224400,312673,312673,65536,1441792,209241,23385064,17833335661197,17833335624441,17833335999642,17833336001459
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,236503,236503,4194304,256,0,0,12,24,26240,0x7fe83cb0b880,0x7fe83c224440,166555,166555,65536,1507328,224652,25196208,17833336035928,17833335999642,17833336288122,17833336290022
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,236503,236503,4194304,256,0,0,12,24,26944,0x7fe83cb0b700,0x7fe83c224480,168033,168033,65536,1638400,243000,27172084,17833336324411,17833336288122,17833336577882,17833336579724
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,236503,236503,4194304,256,0,0,12,24,27648,0x7fe83f16b580,0x7fe83c2244c0,169325,169325,65536,1441792,215804,24164768,17833336621253,17833336577882,17833336865242,17833336867167
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,236503,236503,4194304,256,0,0,16,24,28608,0x7fe83f16b400,0x7fe83c224500,317983,317983,65536,1703936,251876,28216384,17833336903336,17833336865242,17833337239963,17833337241868
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,236503,236503,4194304,256,0,0,16,24,29312,0x7fe83f16b280,0x7fe83c224540,316071,316071,65536,1572864,233891,26185384,17833337276507,17833337239963,17833337615003,17833337616889
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,236503,236503,4194304,256,0,0,12,24,30016,0x7fe83f16b100,0x7fe83c224580,167827,167827,65536,1638400,243052,27250156,17833337650858,17833337615003,17833337911803,17833337913661
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,236503,236503,4194304,256,0,0,8,24,30976,0x7fe83cb0bf80,0x7fe83c2245c0,167561,167561,65536,1835008,270019,30313992,17833337948630,17833337911803,17833338216123,17833338218214
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,236503,236503,4194304,256,0,0,12,24,31680,0x7fe83cb0be00,0x7fe83c224600,166155,166155,65536,1507328,223562,25065536,17833338260273,17833338216123,17833338505724,17833338507656
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,236503,236503,4194304,256,0,0,16,24,32640,0x7fe83cb0bc80,0x7fe83c224640,313708,313708,65536,1835008,272596,30454488,17833338544396,17833338505724,17833338882684,17833338884677
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,236503,236503,4194304,256,0,0,12,24,33600,0x7fe83cb0bb00,0x7fe83c224680,313561,313561,65536,1703936,248219,27816044,17833338919186,17833338882684,17833339257084,17833339259098
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,236503,236503,4194304,256,0,0,12,24,34560,0x7fe83cb0b980,0x7fe83c2246c0,168531,168531,65536,1769472,264701,29659096,17833339293197,17833339257084,17833339545244,17833339547101
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,236503,236503,4194304,256,0,0,8,24,35520,0x7fe83cb0b800,0x7fe83c224700,168533,168533,65536,2031616,303743,34041364,17833339581850,17833339545244,17833339833885,17833339835803
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,236503,236503,4194304,256,0,0,12,24,36224,0x7fe83cb0b680,0x7fe83c224740,168721,168721,65536,1638400,243880,27433232,17833339877512,17833339833885,17833340126845,17833340128726
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,236503,236503,4194304,256,0,0,12,24,37184,0x7fe83f16b500,0x7fe83c224780,311801,311801,65536,1966080,288908,32275144,17833340163205,17833340126845,17833340509405,17833340511177
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,236503,236503,4194304,256,0,0,12,24,38144,0x7fe83f16b380,0x7fe83c2247c0,314592,314592,65536,1835008,272159,30484976,17833340546636,17833340509405,17833340889245,17833340891087
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,236503,236503,4194304,256,0,0,12,24,39104,0x7fe83f16b200,0x7fe83c224800,168011,168011,65536,1900544,281499,31452584,17833340925936,17833340889245,17833341181406,17833341183040
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,236503,236503,4194304,256,0,0,8,24,40320,0x7fe83f16b080,0x7fe83c224840,168636,168636,65536,2228224,328196,36754620,17833341218079,17833341181406,17833341472606,17833341474483
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,236503,236503,4194304,256,0,0,12,24,41280,0x7fe83cb0bf00,0x7fe83c224880,169134,169134,65536,1703936,257950,28833172,17833341515762,17833341472606,17833341761886,17833341763986
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,236503,236503,4194304,256,0,0,12,24,42240,0x7fe83cb0bd80,0x7fe83c2248c0,311600,311600,65536,2097152,311380,34862612,17833341798245,17833341761886,17833342137566,17833342139966
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,236503,236503,4194304,256,0,0,12,24,43200,0x7fe83cb0bc00,0x7fe83c224900,311542,311542,65536,1966080,284002,31844304,17833342176125,17833342137566,17833342523327,17833342525247
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,236503,236503,4194304,256,0,0,8,24,44160,0x7fe83cb0ba80,0x7fe83c224940,168342,168342,65536,2031616,302765,33940188,17833342559536,17833342523327,17833342815647,17833342817649
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,236503,236503,4194304,256,0,0,12,24,45376,0x7fe83cb0b900,0x7fe83c224980,169165,169165,65536,2424832,362267,40550672,17833342852049,17833342815647,17833343114047,17833343115852
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,236503,236503,4194304,256,0,0,12,24,46336,0x7fe83cb0b780,0x7fe83c2249c0,168186,168186,65536,1835008,272130,30424784,17833343157201,17833343114047,17833343405727,17833343407425
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,236503,236503,4194304,256,0,0,12,24,47552,0x7fe83cb0b600,0x7fe83c224a00,312770,312770,65536,2228224,327050,36634776,17833343441984,17833343405727,17833343780928,17833343782835
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,236503,236503,4194304,256,0,0,12,24,48512,0x7fe83f16b480,0x7fe83c224a40,306056,306056,65536,2097152,309123,34672752,17833343818545,17833343780928,17833344158688,17833344160556
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,236503,236503,4194304,256,0,0,8,24,49472,0x7fe83f16b300,0x7fe83c224a80,167548,167548,65536,2162688,317410,35619068,17833344195655,17833344158688,17833344447968,17833344449669
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,236503,236503,4194304,256,0,0,12,24,50688,0x7fe83f16b180,0x7fe83c224ac0,169504,169504,65536,2621440,384926,43161376,17833344484848,17833344447968,17833344739968,17833344741802
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,236503,236503,4194304,256,0,0,12,24,51648,0x7fe83f16b000,0x7fe83c224b00,165512,165512,65536,1966080,291635,32744156,17833344783641,17833344739968,17833345032609,17833345034574
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,236503,236503,4194304,256,0,0,12,24,52864,0x7fe83cb0be80,0x7fe83c224b40,307635,307635,65536,2359296,355072,39814608,17833345076833,17833345032609,17833345407329,17833345409095
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,236503,236503,4194304,256,0,0,12,24,54080,0x7fe83cb0bd00,0x7fe83c224b80,306044,306044,65536,2228224,328227,36844320,17833345443604,17833345407329,17833345783969,17833345785826
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,236503,236503,4194304,256,0,0,8,24,55296,0x7fe83cb0bb80,0x7fe83c224bc0,168845,168845,65536,2293760,348654,38971364,17833345820455,17833345783969,17833346075329,17833346083318
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,236503,236503,4194304,256,0,0,12,24,56768,0x7fe83cb0ba00,0x7fe83c224c00,169498,169498,65536,2752512,404228,45354672,17833346112458,17833346075329,17833346373410,17833346375231
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,236503,236503,4194304,256,0,0,12,24,57728,0x7fe83cb0b880,0x7fe83c224c40,169071,169071,65536,2031616,303042,33913500,17833346416440,17833346373410,17833346667010,17833346668874
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,236503,236503,4194304,256,0,0,12,24,58944,0x7fe83cb0b700,0x7fe83c224c80,307122,307122,65536,2490368,369401,41428256,17833346706213,17833346667010,17833347040930,17833347042884
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,236503,236503,4194304,256,0,0,12,24,60160,0x7fe83f16b580,0x7fe83c224cc0,308959,308959,65536,2359296,365280,40887324,17833347076864,17833347040930,17833347420450,17833347422375
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,236503,236503,4194304,256,0,0,8,24,61376,0x7fe83f16b400,0x7fe83c224d00,169956,169956,65536,2424832,381780,42729400,17833347457904,17833347420450,17833347711011,17833347712878
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,236503,236503,4194304,256,0,0,12,24,62848,0x7fe83f16b280,0x7fe83c224d40,173407,173407,65536,2949120,441931,49481420,17833347747547,17833347711011,17833348005091,17833348006880
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,236503,236503,4194304,256,0,0,12,24,63808,0x7fe83f16b100,0x7fe83c224d80,166344,166344,65536,2162688,321975,36072248,17833348048719,17833348005091,17833348302691,17833348304553
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,236503,236503,4194304,256,0,0,12,24,65024,0x7fe83cb0bf80,0x7fe83c224dc0,305814,305814,65536,2621440,389080,43384336,17833348339332,17833348302691,17833348678051,17833348680044
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,236503,236503,4194304,256,0,0,12,24,66240,0x7fe83cb0be00,0x7fe83c224e00,304155,304155,65536,2490368,364521,40814816,17833348715763,17833348678051,17833349050532,17833349052354
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,236503,236503,4194304,256,0,0,8,24,67456,0x7fe83cb0bc80,0x7fe83c224e40,170016,170016,65536,2555904,381139,42794068,17833349087144,17833349050532,17833349345252,17833349346957
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,236503,236503,4194304,256,0,0,12,24,68928,0x7fe83cb0bb00,0x7fe83c224e80,177017,177017,65536,3145728,470883,52684580,17833349382036,17833349345252,17833349643652,17833349645520
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,236503,236503,4194304,256,0,0,12,24,70144,0x7fe83cb0b980,0x7fe83c224ec0,166578,166578,65536,2228224,327804,36764916,17833349687679,17833349643652,17833349935492,17833349937203
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,236503,236503,4194304,256,0,0,12,24,71616,0x7fe83cb0b800,0x7fe83c224f00,302457,302457,65536,2752512,406147,45544456,17833349973952,17833349935492,17833350316773,17833350318913
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,236503,236503,4194304,256,0,0,12,24,72832,0x7fe83cb0b680,0x7fe83c224f40,304510,304510,65536,2621440,386423,43272968,17833350354692,17833350316773,17833350692933,17833350694984
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,236503,236503,4194304,256,0,0,8,24,74048,0x7fe83f16b500,0x7fe83c224f80,167339,167339,65536,2686976,399117,44684512,17833350728583,17833350692933,17833350982053,17833350984027
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,236503,236503,4194304,256,0,0,12,24,75776,0x7fe83f16b380,0x7fe83c224fc0,183614,183614,65536,3342336,496613,55633136,17833351018986,17833350982053,17833351282533,17833351284429
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,236503,236503,4194304,256,0,0,12,24,76992,0x7fe83f16b200,0x7fe83c225000,167166,167166,65536,2359296,350153,39373624,17833351338838,17833351282533,17833351576774,17833351578622
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,236503,236503,4194304,256,0,0,12,24,78464,0x7fe83f16b080,0x7fe83c225040,303630,303630,65536,2883584,435848,48734928,17833351615461,17833351576774,17833351958214,17833351960042
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,236503,236503,4194304,256,0,0,12,24,79936,0x7fe83cb0bf00,0x7fe83c225080,303100,303100,65536,2686976,399594,44765504,17833351995661,17833351958214,17833352333094,17833352335093
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,236503,236503,4194304,256,0,0,8,24,81408,0x7fe83cb0bd80,0x7fe83c2250c0,170425,170425,65536,2818048,421112,47160840,17833352369572,17833352333094,17833352623174,17833352625026
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,236503,236503,4194304,256,0,0,12,24,83136,0x7fe83cb0bc00,0x7fe83c225100,192467,192467,65536,3538944,538081,60204324,17833352659005,17833352623174,17833352927655,17833352929528
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,236503,236503,4194304,256,0,0,12,24,84352,0x7fe83cb0ba80,0x7fe83c225140,169322,169322,65536,2424832,359577,40321568,17833352971487,17833352927655,17833353224455,17833353226431
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,236503,236503,4194304,256,0,0,12,24,85824,0x7fe83cb0b900,0x7fe83c225180,308086,308086,65536,3014656,453709,50727012,17833353260050,17833353224455,17833353611495,17833353613361
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,236503,236503,4194304,256,0,0,12,24,87296,0x7fe83cb0b780,0x7fe83c2251c0,303114,303114,65536,2818048,414457,46395432,17833353647860,17833353611495,17833353985735,17833353987472
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,236503,236503,4194304,256,0,0,12,24,88768,0x7fe83cb0b600,0x7fe83c225200,168204,168204,65536,2949120,439817,49244168,17833354022171,17833353985735,17833354291816,17833354293764
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,236503,236503,4194304,256,0,0,12,24,90752,0x7fe83f16b480,0x7fe83c225240,201871,201871,65536,3735552,560870,62806964,17833354328653,17833354291816,17833354605416,17833354607396
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,236503,236503,4194304,256,0,0,12,24,91968,0x7fe83f16b300,0x7fe83c225280,166916,166916,65536,2555904,395655,44391096,17833354649265,17833354605416,17833354895656,17833354897599
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,236503,236503,4194304,256,0,0,12,24,93440,0x7fe83f16b180,0x7fe83c2252c0,304577,304577,65536,3145728,466630,52282620,17833354933938,17833354895656,17833355272616,17833355274500
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,236503,236503,4194304,256,0,0,12,24,94912,0x7fe83f16b000,0x7fe83c225300,301618,301618,65536,2949120,438044,48999416,17833355310369,17833355272616,17833355645897,17833355647791
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,236503,236503,4194304,256,0,0,12,24,96384,0x7fe83cb0be80,0x7fe83c225340,168835,168835,65536,3080192,459338,51414080,17833355681500,17833355645897,17833355934057,17833355936003
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,236503,236503,4194304,256,0,0,12,24,98368,0x7fe83cb0bd00,0x7fe83c225380,211422,211422,65536,3932160,584962,65429388,17833355970523,17833355934057,17833356256617,17833356258445
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,236503,236503,4194304,256,0,0,12,24,99584,0x7fe83cb0bb80,0x7fe83c2253c0,167511,167511,65536,2621440,388846,43578000,17833356300124,17833356256617,17833356552617,17833356554738
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,236503,236503,4194304,256,0,0,12,24,101312,0x7fe83cb0ba00,0x7fe83c225400,304783,304783,65536,3276800,487250,54676880,17833356589057,17833356552617,17833356926858,17833356928709
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,236503,236503,4194304,256,0,0,12,24,102784,0x7fe83cb0b880,0x7fe83c225440,304031,304031,65536,3080192,465994,52152364,17833356962958,17833356926858,17833357302858,17833357304939
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,236503,236503,4194304,256,0,0,12,24,104256,0x7fe83cb0b700,0x7fe83c225480,168847,168847,65536,3211264,472919,52929148,17833357338709,17833357302858,17833357593578,17833357595522
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,236503,236503,4194304,256,0,0,12,24,106240,0x7fe83f16b580,0x7fe83c2254c0,218845,218845,65536,4128768,609203,68267656,17833357630121,17833357593578,17833357919978,17833357921834
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,236503,236503,4194304,256,0,0,12,24,107712,0x7fe83f16b400,0x7fe83c225500,167201,167201,65536,2752512,408007,45704904,17833357964573,17833357919978,17833358219659,17833358221797
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,236503,236503,4194304,256,0,0,16,24,109440,0x7fe83f16b280,0x7fe83c225540,300053,300053,65536,3407872,509053,56999112,17833358258066,17833358219659,17833358597099,17833358598907
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,236503,236503,4194304,256,0,0,16,24,111168,0x7fe83f16b100,0x7fe83c225580,300200,300200,65536,3211264,474244,53131240,17833358633596,17833358597099,17833358972619,17833358974498
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,236503,236503,4194304,256,0,0,8,24,112896,0x7fe83cb0bf80,0x7fe83c2255c0,168788,168788,65536,3276800,492858,55205864,17833359009827,17833358972619,17833359262379,17833359264261
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,236503,236503,4194304,256,0,0,12,24,115136,0x7fe83cb0be00,0x7fe83c225600,232164,232164,65536,4325376,648749,72658560,17833359298580,17833359262379,17833359594060,17833359595993
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,236503,236503,4194304,256,0,0,12,24,116608,0x7fe83cb0bc80,0x7fe83c225640,169376,169376,65536,2818048,429623,48129556,17833359638381,17833359594060,17833359888300,17833359890205
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,236503,236503,4194304,256,0,0,16,24,118336,0x7fe83cb0bb00,0x7fe83c225680,300713,300713,65536,3538944,524423,58732196,17833359923974,17833359888300,17833360260140,17833360262016
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,236503,236503,4194304,256,0,0,16,24,120064,0x7fe83cb0b980,0x7fe83c2256c0,302008,302008,65536,3407872,502770,56356060,17833360296845,17833360260140,17833360630540,17833360632417
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,236503,236503,4194304,256,0,0,12,24,121792,0x7fe83cb0b800,0x7fe83c225700,167077,167077,65536,3407872,513280,57448736,17833360666996,17833360630540,17833360919021,17833360920880
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,236503,236503,4194304,256,0,0,12,24,124032,0x7fe83cb0b680,0x7fe83c225740,240548,240548,65536,4521984,677850,76029392,17833360955349,17833360919021,17833361257421,17833361259191
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,236503,236503,4194304,256,0,0,12,24,125504,0x7fe83f16b500,0x7fe83c225780,169238,169238,65536,3014656,460312,51595968,17833361301430,17833361257421,17833361555981,17833361557714
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,236503,236503,4194304,256,0,0,12,24,127488,0x7fe83f16b380,0x7fe83c2257c0,303321,303321,65536,3801088,565090,63265024,17833361592213,17833361555981,17833361935341,17833361937344
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,236503,236503,4194304,256,0,0,12,24,129216,0x7fe83f16b200,0x7fe83c225800,304169,304169,65536,3670016,555213,62175088,17833361972664,17833361935341,17833362320622,17833362322655
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,236503,236503,4194304,256,0,0,12,24,130944,0x7fe83f16b080,0x7fe83c225840,173257,173257,65536,3670016,558045,62469356,17833362358914,17833362320622,17833362617102,17833362619097
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,236503,236503,4194304,256,0,0,12,24,133440,0x7fe83cb0bf00,0x7fe83c225880,258461,258461,65536,4915200,746817,83594780,17833362654677,17833362617102,17833362965582,17833362967549
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,236503,236503,4194304,256,0,0,12,24,134912,0x7fe83cb0bd80,0x7fe83c2258c0,170911,170911,65536,3145728,467869,52410260,17833363011138,17833362965582,17833363263343,17833363265301
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,236503,236503,4194304,256,0,0,12,24,136896,0x7fe83cb0bc00,0x7fe83c225900,301919,301919,65536,4063232,617922,69219988,17833363300421,17833363263343,17833363636943,17833363638762
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,236503,236503,4194304,256,0,0,12,24,138880,0x7fe83cb0ba80,0x7fe83c225940,301829,301829,65536,3932160,597857,66953784,17833363674591,17833363636943,17833364009263,17833364011223
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,236503,236503,4194304,256,0,0,12,24,140864,0x7fe83cb0b900,0x7fe83c225980,177968,177968,65536,3932160,596056,66734084,17833364045152,17833364009263,17833364312623,17833364314605
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,236503,236503,4194304,256,0,0,12,24,143616,0x7fe83cb0b780,0x7fe83c2259c0,278430,278430,65536,5308416,795390,89144032,17833364348674,17833364312623,17833364671344,17833364673196
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,236503,236503,4194304,256,0,0,12,24,145344,0x7fe83cb0b600,0x7fe83c225a00,168158,168158,65536,3342336,496115,55511576,17833364715915,17833364671344,17833364967984,17833364969829
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,236503,236503,4194304,256,0,0,12,24,147584,0x7fe83f16b480,0x7fe83c225a40,302112,302112,65536,4325376,679360,75998736,17833365004128,17833364967984,17833365343184,17833365345140
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,236503,236503,4194304,256,0,0,12,24,149568,0x7fe83f16b300,0x7fe83c225a80,300038,300038,65536,4194304,640040,71578624,17833365380529,17833365343184,17833365718064,17833365719900
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,236503,236503,4194304,256,0,0,12,24,151552,0x7fe83f16b180,0x7fe83c225ac0,187296,187296,65536,4194304,633708,70979648,17833365753980,17833365718064,17833366021105,17833366023093
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,236503,236503,4194304,256,0,0,12,24,154304,0x7fe83f16b000,0x7fe83c225b00,300034,300034,65536,5701632,866651,97056844,17833366058802,17833366021105,17833366401905,17833366403933
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,236503,236503,4194304,256,0,0,12,24,156288,0x7fe83cb0be80,0x7fe83c225b40,171812,171812,65536,3735552,559895,62694600,17833366446302,17833366401905,17833366700305,17833366702346
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,236503,236503,4194304,256,0,0,12,24,158784,0x7fe83cb0bd00,0x7fe83c225b80,303329,303329,65536,4849664,764136,85670204,17833366739525,17833366700305,17833367079665,17833367081477
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,236503,236503,4194304,256,0,0,12,24,161024,0x7fe83cb0bb80,0x7fe83c225bc0,304282,304282,65536,4718592,738083,82726232,17833367115496,17833367079665,17833367467186,17833367469197
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,236503,236503,4194304,256,0,0,12,24,163264,0x7fe83cb0ba00,0x7fe83c225c00,206411,206411,65536,4718592,716943,80228732,17833367503216,17833367467186,17833367783666,17833367785549
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,236503,236503,4194304,256,0,0,12,24,166528,0x7fe83cb0b880,0x7fe83c225c40,340023,340023,65536,6488064,983106,110076864,17833367819648,17833367783666,17833368182866,17833368209779
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,236503,236503,4194304,256,0,0,12,24,168512,0x7fe83cb0b700,0x7fe83c225c80,184379,184379,65536,4128768,621586,69574528,17833368228628,17833368182866,17833368500787,17833368502701
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,236503,236503,4194304,256,0,0,12,24,171264,0x7fe83f16b580,0x7fe83c225cc0,303703,303703,65536,5373952,859064,96251956,17833368539740,17833368500787,17833368880307,17833368882192
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,236503,236503,4194304,256,0,0,12,24,173760,0x7fe83f16b400,0x7fe83c225d00,306151,306151,65536,5242880,848046,94899672,17833368917151,17833368880307,17833369260947,17833369265292
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,236503,236503,4194304,256,0,0,12,24,176256,0x7fe83f16b280,0x7fe83c225d40,226653,226653,65536,5242880,782651,87709652,17833369297242,17833369260947,17833369588627,17833369590554
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,236503,236503,4194304,256,0,0,12,24,179776,0x7fe83f16b100,0x7fe83c225d80,380709,380709,65536,7274496,1096835,122880504,17833369624613,17833369588627,17833370019028,17833370038103
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,236503,236503,4194304,256,0,0,12,24,182272,0x7fe83cb0bf80,0x7fe83c225dc0,211326,211326,65536,4915200,734226,82202996,17833370063632,17833370019028,17833370349428,17833370351515
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,236503,236503,4194304,256,0,0,12,24,185536,0x7fe83cb0be00,0x7fe83c225e00,308027,308027,65536,6422528,990606,110945628,17833370385265,17833370349428,17833370734868,17833370784165
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,236503,236503,4194304,256,0,0,12,24,188544,0x7fe83cb0bc80,0x7fe83c225e40,311334,311334,65536,6291456,1015562,113688560,17833370794694,17833370734868,17833371160949,17833371207294
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,236503,236503,4194304,256,0,0,12,24,191552,0x7fe83cb0bb00,0x7fe83c225e80,266391,266391,65536,6291456,959541,107455604,17833371218164,17833371160949,17833371546549,17833371548436
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,236503,236503,4194304,256,0,0,12,24,195840,0x7fe83cb0b980,0x7fe83c225ec0,461600,461600,65536,8847360,1334366,149533012,17833371582655,17833371546549,17833372022069,17833372068323
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,236503,236503,4194304,256,0,0,12,24,198592,0x7fe83cb0b800,0x7fe83c225f00,245533,245533,65536,5701632,872385,97746628,17833372087512,17833372022069,17833372399350,17833372401214
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,236503,236503,4194304,256,0,0,12,24,202368,0x7fe83cb0b680,0x7fe83c225f40,333240,333240,65536,7471104,1190293,133416856,17833372438303,17833372399350,17833372805430,17833372827754
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,236503,236503,4194304,256,0,0,12,24,205888,0x7fe83f16b500,0x7fe83c225f80,331906,331906,65536,7340032,1156506,129439136,17833372840983,17833372805430,17833373216470,17833373237694
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,236503,236503,4194304,256,0,0,12,24,209408,0x7fe83f16b380,0x7fe83c225fc0,306784,306784,65536,7340032,1122895,125758168,17833373253713,17833373216470,17833373602070,17833373604035
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,236503,236503,4194304,256,0,0,12,24,214464,0x7fe83f16b200,0x7fe83c226000,542870,542870,65536,10420224,1572795,176191112,17833373638674,17833373602070,17833374129111,17833374151011
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,236503,236503,4194304,256,0,0,12,24,217728,0x7fe83f16b080,0x7fe83c226040,273524,273524,65536,6488064,1001580,112199020,17833374174310,17833374129111,17833374501751,17833374503742
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,236503,236503,4194304,256,0,0,12,24,222016,0x7fe83cb0bf00,0x7fe83c226080,367402,367402,65536,8519680,1353274,151506452,17833374538861,17833374501751,17833374928631,17833374946841
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,236503,236503,4194304,256,0,0,12,24,226048,0x7fe83cb0bd80,0x7fe83c2260c0,365216,365216,65536,8388608,1304526,146097372,17833374965361,17833374928631,17833375353272,17833375371071
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,236503,236503,4194304,256,0,0,12,24,230080,0x7fe83cb0bc00,0x7fe83c226100,347450,347450,65536,8388608,1301080,145747168,17833375389370,17833375353272,17833375759832,17833375776981
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,236503,236503,4194304,256,0,0,12,24,235904,0x7fe83cb0ba80,0x7fe83c226140,623883,623883,65536,11993088,1821460,204012224,17833375795600,17833375759832,17833376342393,17833376359956
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,236503,236503,4194304,256,0,0,12,24,239424,0x7fe83cb0b900,0x7fe83c226180,301927,301927,65536,7274496,1129391,126520252,17833376386155,17833376342393,17833376726873,17833376728867
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,236503,236503,4194304,256,0,0,12,24,244224,0x7fe83cb0b780,0x7fe83c2261c0,397112,397112,65536,9568256,1519909,170238480,17833376763316,17833376726873,17833377172793,17833377191405
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,236503,236503,4194304,256,0,0,12,24,248768,0x7fe83cb0b600,0x7fe83c226200,390579,390579,65536,9437184,1516148,169854668,17833377210205,17833377172793,17833377619354,17833377636884
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,236503,236503,4194304,256,0,0,12,24,253312,0x7fe83f16b480,0x7fe83c226240,388246,388246,65536,9437184,1469651,164646916,17833377656044,17833377619354,17833378054714,17833378073234
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,236503,236503,4194304,256,0,0,8,24,255552,0x7fe83f16b300,0x7fe83c226280,719031,719031,65536,16056320,2305568,258136480,17833378093213,17833378054714,17833378709754,17833378756117
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,236503,236503,4194304,256,0,0,12,24,259840,0x7fe83f16b180,0x7fe83c2262c0,364708,364708,65536,8847360,1370645,153515112,17833378775936,17833378709754,17833379159035,17833379204805
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,236503,236503,4194304,256,0,0,12,24,265664,0x7fe83f16b000,0x7fe83c226300,469173,469173,65536,11665408,1832647,205290624,17833379216425,17833379159035,17833379686075,17833379731762
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,236503,236503,4194304,256,0,0,12,24,271232,0x7fe83cb0be80,0x7fe83c226340,472147,472147,65536,11468800,1836446,205663764,17833379742592,17833379686075,17833380206876,17833380252019
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,236503,236503,4194304,256,0,0,8,24,273216,0x7fe83cb0bd00,0x7fe83c226380,483319,483319,65536,14090240,2020745,226286316,17833380262739,17833380206876,17833380730396,17833380775826
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,236503,236503,4194304,256,0,0,8,24,275712,0x7fe83cb0bb80,0x7fe83c2263c0,880693,880693,65536,19202048,2756489,308858668,17833380786746,17833380730396,17833381509117,17833381554727
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,236503,236503,4194304,256,0,0,12,24,280768,0x7fe83cb0ba00,0x7fe83c226400,426823,426823,65536,10420224,1609659,180348376,17833381573027,17833381509117,17833381995517,17833382013656
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,236503,236503,4194304,256,0,0,12,24,287616,0x7fe83cb0b880,0x7fe83c226440,550151,550151,65536,13762560,2210664,247726852,17833382032035,17833381995517,17833382551997,17833382597981
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,236503,236503,4194304,256,0,0,12,24,294208,0x7fe83cb0b700,0x7fe83c226480,551517,551517,65536,13565952,2140716,239728764,17833382609251,17833382551997,17833383127358,17833383172737
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,236503,236503,4194304,256,0,0,8,24,296960,0x7fe83f16b580,0x7fe83c2264c0,564777,564777,65536,15466496,2228456,249593016,17833383183477,17833383127358,17833383699518,17833383744933
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,236503,236503,4194304,256,0,0,8,24,299968,0x7fe83f16b400,0x7fe83c226500,1044359,1044359,65536,22347776,3211299,359707520,17833383755813,17833383699518,17833384583359,17833384626841
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,236503,236503,4194304,256,0,0,8,24,302720,0x7fe83f16b280,0x7fe83c226540,722945,722945,65536,20250624,2923813,327459048,17833384644931,17833384583359,17833385251039,17833385295565
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,236503,236503,4194304,256,0,0,12,24,305472,0x7fe83f16b100,0x7fe83c226580,725769,725769,65536,20447232,2935642,328720784,17833385306544,17833385251039,17833385941920,17833385960188
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,236503,236503,4194304,256,0,0,12,24,308224,0x7fe83cb0bf80,0x7fe83c2265c0,721755,721755,65536,19595264,2818351,315615332,17833385979718,17833385941920,17833386603840,17833386650201
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,236503,236503,4194304,256,0,0,8,24,310976,0x7fe83cb0be00,0x7fe83c226600,727949,727949,65536,20381696,2928148,327905732,17833386661111,17833386603784,17833387281864,17833387333494
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,236503,236503,4194304,256,0,0,8,24,313216,0x7fe83cb0bc80,0x7fe83c226640,1366307,1366307,65536,31522816,4509238,505473072,17833387344264,17833387281864,17833388391624,17833388436797
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,236503,236503,4194304,256,0,0,8,24,315968,0x7fe83cb0bb00,0x7fe83c226680,1373247,1373247,65536,38993920,5583960,625679232,17833388456356,17833388391624,17833389481225,17833389547849
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,236503,236503,4194304,256,0,0,12,24,318720,0x7fe83cb0b980,0x7fe83c2266c0,1373929,1373929,65536,39124992,5615805,628883484,17833389559129,17833389481225,17833390631786,17833390703550
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,236503,236503,4194304,256,0,0,12,24,321472,0x7fe83cb0b800,0x7fe83c226700,1372851,1372851,65536,38469632,5509601,617057236,17833390715150,17833390631786,17833391778986,17833391848222
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,236503,236503,4194304,256,0,0,8,24,324224,0x7fe83cb0b680,0x7fe83c226740,1375132,1375132,65536,39059456,5596845,626840900,17833391858982,17833391778986,17833392899307,17833392966684
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,236503,236503,4194304,256,0,0,8,24,326464,0x7fe83f16b500,0x7fe83c226780,2664386,2664386,65536,60489728,8652521,969163852,17833392977874,17833392899307,17833394866828,17833394944075
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,236503,236503,4194304,256,0,0,8,24,329216,0x7fe83f16b380,0x7fe83c2267c0,2669534,2669534,65536,77266944,11073873,1240553420,17833394963545,17833394866828,17833396808270,17833396876617
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,236503,236503,4194304,256,0,0,12,24,331968,0x7fe83f16b200,0x7fe83c226800,2672170,2672170,65536,77398016,11071825,1240072748,17833396887957,17833396808270,17833398795791,17833398869628
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,236503,236503,4194304,256,0,0,12,24,334720,0x7fe83f16b080,0x7fe83c226840,2668592,2668592,65536,76218368,10904144,1221576836,17833398880977,17833398795791,17833400781712,17833400848588
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,236503,236503,4194304,256,0,0,8,24,337472,0x7fe83cb0bf00,0x7fe83c226880,2672754,2672754,65536,77332480,11067421,1239281240,17833400859718,17833400781712,17833402716274,17833402787070
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,236503,236503,4194304,256,0,0,8,24,0,0x7fe83cb0bd80,0x7fe83c2268c0,5255776,5255776,65536,120258560,17187452,1925701988,17833402798580,17833402716274,17833406340436,17833406412550
1 Index KernelName gpu-id queue-id queue-index pid tid grd wgr lds scr vgpr sgpr fbar sig obj GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES DispatchNs BeginNs EndNs CompleteNs
2 0 __amd_rocclr_fillBufferAligned.kd 0 0 0 236503 236503 33554432 256 0 0 4 32 4160 0x0 0x7fe83c204280 385832 385832 524288 4718592 682094 76386864 17833173257611 17832460487290 17833324063793 17833324177862
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 236503 236503 32768 256 0 0 12 24 13888 0x0 0x7fe83c223f80 34124 34124 512 8192 5540 624020 17833329373303 17833324063793 17833329503317 17833329508120
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 5 236503 236503 4194304 256 0 0 12 24 14336 0x7fe83f16b380 0x7fe83c223fc0 166451 166451 65536 917504 140662 15737800 17833329547519 17833329503317 17833329887317 17833329890091
5 3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 8 236503 236503 4194304 256 0 0 16 24 15040 0x7fe83f16b200 0x7fe83c224000 320813 320813 65536 1114112 167869 18973284 17833329928940 17833329887317 17833330326517 17833330329380
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 11 236503 236503 4194304 256 0 0 16 24 15488 0x7fe83f16b080 0x7fe83c224040 323006 323006 65536 917504 146978 16539568 17833330364489 17833330326517 17833330747798 17833330753919
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 14 236503 236503 4194304 256 0 0 12 24 15936 0x7fe83cb0bf00 0x7fe83c224080 168550 168550 65536 1048576 159174 17856292 17833330784798 17833330747798 17833331068118 17833331070481
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 17 236503 236503 4194304 256 0 0 12 24 16384 0x7fe83cb0bd80 0x7fe83c2240c0 168572 168572 65536 983040 148090 16569436 17833331104930 17833331068118 17833331386678 17833331389103
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 20 236503 236503 4194304 256 0 0 12 24 17088 0x7fe83cb0bc00 0x7fe83c224100 167664 167664 65536 1114112 162610 18224860 17833331435702 17833331386678 17833331703318 17833331705705
10 8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 23 236503 236503 4194304 256 0 0 16 24 17792 0x7fe83cb0ba80 0x7fe83c224140 320079 320079 65536 1310720 202232 22647988 17833331740015 17833331703318 17833332108599 17833332110925
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 26 236503 236503 4194304 256 0 0 16 24 18496 0x7fe83cb0b900 0x7fe83c224180 316809 316809 65536 1179648 176290 19855416 17833332143565 17833332108599 17833332528439 17833332530935
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 29 236503 236503 4194304 256 0 0 16 24 19200 0x7fe83cb0b780 0x7fe83c2241c0 168281 168281 65536 1245184 188620 21166232 17833332564054 17833332528439 17833332839959 17833332842307
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 32 236503 236503 4194304 256 0 0 16 24 19904 0x7fe83cb0b600 0x7fe83c224200 169494 169494 65536 1245184 202520 22612512 17833332876086 17833332839959 17833333154039 17833333156369
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 35 236503 236503 4194304 256 0 0 12 24 20608 0x7fe83f16b480 0x7fe83c224240 171299 171299 65536 1245184 200754 22467976 17833333198828 17833333154039 17833333471320 17833333473552
15 13 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 38 236503 236503 4194304 256 0 0 16 24 21312 0x7fe83f16b300 0x7fe83c224280 320776 320776 65536 1441792 216093 24168728 17833333508101 17833333471320 17833333874840 17833333881351
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 41 236503 236503 4194304 256 0 0 16 24 22016 0x7fe83f16b180 0x7fe83c2242c0 316393 316393 65536 1310720 197617 22204988 17833333911551 17833333874840 17833334286360 17833334289041
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 44 236503 236503 4194304 256 0 0 16 24 22720 0x7fe83f16b000 0x7fe83c224300 169264 169264 65536 1376256 205151 23034404 17833334324160 17833334286360 17833334608441 17833334610943
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 47 236503 236503 4194304 256 0 0 12 24 23424 0x7fe83cb0be80 0x7fe83c224340 168263 168263 65536 1441792 221753 24858852 17833334644352 17833334608441 17833334922841 17833334925195
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 50 236503 236503 4194304 256 0 0 12 24 24128 0x7fe83cb0bd00 0x7fe83c224380 167492 167492 65536 1310720 195746 21931324 17833334967074 17833334922841 17833335246361 17833335248667
20 18 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 53 236503 236503 4194304 256 0 0 16 24 24832 0x7fe83cb0bb80 0x7fe83c2243c0 316291 316291 65536 1572864 232311 26113788 17833335285227 17833335246361 17833335624441 17833335626348
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 56 236503 236503 4194304 256 0 0 16 24 25536 0x7fe83cb0ba00 0x7fe83c224400 312673 312673 65536 1441792 209241 23385064 17833335661197 17833335624441 17833335999642 17833336001459
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 59 236503 236503 4194304 256 0 0 12 24 26240 0x7fe83cb0b880 0x7fe83c224440 166555 166555 65536 1507328 224652 25196208 17833336035928 17833335999642 17833336288122 17833336290022
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 62 236503 236503 4194304 256 0 0 12 24 26944 0x7fe83cb0b700 0x7fe83c224480 168033 168033 65536 1638400 243000 27172084 17833336324411 17833336288122 17833336577882 17833336579724
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 65 236503 236503 4194304 256 0 0 12 24 27648 0x7fe83f16b580 0x7fe83c2244c0 169325 169325 65536 1441792 215804 24164768 17833336621253 17833336577882 17833336865242 17833336867167
25 23 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 68 236503 236503 4194304 256 0 0 16 24 28608 0x7fe83f16b400 0x7fe83c224500 317983 317983 65536 1703936 251876 28216384 17833336903336 17833336865242 17833337239963 17833337241868
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 71 236503 236503 4194304 256 0 0 16 24 29312 0x7fe83f16b280 0x7fe83c224540 316071 316071 65536 1572864 233891 26185384 17833337276507 17833337239963 17833337615003 17833337616889
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 74 236503 236503 4194304 256 0 0 12 24 30016 0x7fe83f16b100 0x7fe83c224580 167827 167827 65536 1638400 243052 27250156 17833337650858 17833337615003 17833337911803 17833337913661
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 77 236503 236503 4194304 256 0 0 8 24 30976 0x7fe83cb0bf80 0x7fe83c2245c0 167561 167561 65536 1835008 270019 30313992 17833337948630 17833337911803 17833338216123 17833338218214
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 80 236503 236503 4194304 256 0 0 12 24 31680 0x7fe83cb0be00 0x7fe83c224600 166155 166155 65536 1507328 223562 25065536 17833338260273 17833338216123 17833338505724 17833338507656
30 28 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 83 236503 236503 4194304 256 0 0 16 24 32640 0x7fe83cb0bc80 0x7fe83c224640 313708 313708 65536 1835008 272596 30454488 17833338544396 17833338505724 17833338882684 17833338884677
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 86 236503 236503 4194304 256 0 0 12 24 33600 0x7fe83cb0bb00 0x7fe83c224680 313561 313561 65536 1703936 248219 27816044 17833338919186 17833338882684 17833339257084 17833339259098
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 89 236503 236503 4194304 256 0 0 12 24 34560 0x7fe83cb0b980 0x7fe83c2246c0 168531 168531 65536 1769472 264701 29659096 17833339293197 17833339257084 17833339545244 17833339547101
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 92 236503 236503 4194304 256 0 0 8 24 35520 0x7fe83cb0b800 0x7fe83c224700 168533 168533 65536 2031616 303743 34041364 17833339581850 17833339545244 17833339833885 17833339835803
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 95 236503 236503 4194304 256 0 0 12 24 36224 0x7fe83cb0b680 0x7fe83c224740 168721 168721 65536 1638400 243880 27433232 17833339877512 17833339833885 17833340126845 17833340128726
35 33 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 98 236503 236503 4194304 256 0 0 12 24 37184 0x7fe83f16b500 0x7fe83c224780 311801 311801 65536 1966080 288908 32275144 17833340163205 17833340126845 17833340509405 17833340511177
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 101 236503 236503 4194304 256 0 0 12 24 38144 0x7fe83f16b380 0x7fe83c2247c0 314592 314592 65536 1835008 272159 30484976 17833340546636 17833340509405 17833340889245 17833340891087
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 104 236503 236503 4194304 256 0 0 12 24 39104 0x7fe83f16b200 0x7fe83c224800 168011 168011 65536 1900544 281499 31452584 17833340925936 17833340889245 17833341181406 17833341183040
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 107 236503 236503 4194304 256 0 0 8 24 40320 0x7fe83f16b080 0x7fe83c224840 168636 168636 65536 2228224 328196 36754620 17833341218079 17833341181406 17833341472606 17833341474483
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 110 236503 236503 4194304 256 0 0 12 24 41280 0x7fe83cb0bf00 0x7fe83c224880 169134 169134 65536 1703936 257950 28833172 17833341515762 17833341472606 17833341761886 17833341763986
40 38 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 113 236503 236503 4194304 256 0 0 12 24 42240 0x7fe83cb0bd80 0x7fe83c2248c0 311600 311600 65536 2097152 311380 34862612 17833341798245 17833341761886 17833342137566 17833342139966
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 116 236503 236503 4194304 256 0 0 12 24 43200 0x7fe83cb0bc00 0x7fe83c224900 311542 311542 65536 1966080 284002 31844304 17833342176125 17833342137566 17833342523327 17833342525247
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 119 236503 236503 4194304 256 0 0 8 24 44160 0x7fe83cb0ba80 0x7fe83c224940 168342 168342 65536 2031616 302765 33940188 17833342559536 17833342523327 17833342815647 17833342817649
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 122 236503 236503 4194304 256 0 0 12 24 45376 0x7fe83cb0b900 0x7fe83c224980 169165 169165 65536 2424832 362267 40550672 17833342852049 17833342815647 17833343114047 17833343115852
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 125 236503 236503 4194304 256 0 0 12 24 46336 0x7fe83cb0b780 0x7fe83c2249c0 168186 168186 65536 1835008 272130 30424784 17833343157201 17833343114047 17833343405727 17833343407425
45 43 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 128 236503 236503 4194304 256 0 0 12 24 47552 0x7fe83cb0b600 0x7fe83c224a00 312770 312770 65536 2228224 327050 36634776 17833343441984 17833343405727 17833343780928 17833343782835
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 131 236503 236503 4194304 256 0 0 12 24 48512 0x7fe83f16b480 0x7fe83c224a40 306056 306056 65536 2097152 309123 34672752 17833343818545 17833343780928 17833344158688 17833344160556
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 134 236503 236503 4194304 256 0 0 8 24 49472 0x7fe83f16b300 0x7fe83c224a80 167548 167548 65536 2162688 317410 35619068 17833344195655 17833344158688 17833344447968 17833344449669
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 137 236503 236503 4194304 256 0 0 12 24 50688 0x7fe83f16b180 0x7fe83c224ac0 169504 169504 65536 2621440 384926 43161376 17833344484848 17833344447968 17833344739968 17833344741802
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 140 236503 236503 4194304 256 0 0 12 24 51648 0x7fe83f16b000 0x7fe83c224b00 165512 165512 65536 1966080 291635 32744156 17833344783641 17833344739968 17833345032609 17833345034574
50 48 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 143 236503 236503 4194304 256 0 0 12 24 52864 0x7fe83cb0be80 0x7fe83c224b40 307635 307635 65536 2359296 355072 39814608 17833345076833 17833345032609 17833345407329 17833345409095
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 146 236503 236503 4194304 256 0 0 12 24 54080 0x7fe83cb0bd00 0x7fe83c224b80 306044 306044 65536 2228224 328227 36844320 17833345443604 17833345407329 17833345783969 17833345785826
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 149 236503 236503 4194304 256 0 0 8 24 55296 0x7fe83cb0bb80 0x7fe83c224bc0 168845 168845 65536 2293760 348654 38971364 17833345820455 17833345783969 17833346075329 17833346083318
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 152 236503 236503 4194304 256 0 0 12 24 56768 0x7fe83cb0ba00 0x7fe83c224c00 169498 169498 65536 2752512 404228 45354672 17833346112458 17833346075329 17833346373410 17833346375231
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 155 236503 236503 4194304 256 0 0 12 24 57728 0x7fe83cb0b880 0x7fe83c224c40 169071 169071 65536 2031616 303042 33913500 17833346416440 17833346373410 17833346667010 17833346668874
55 53 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 158 236503 236503 4194304 256 0 0 12 24 58944 0x7fe83cb0b700 0x7fe83c224c80 307122 307122 65536 2490368 369401 41428256 17833346706213 17833346667010 17833347040930 17833347042884
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 161 236503 236503 4194304 256 0 0 12 24 60160 0x7fe83f16b580 0x7fe83c224cc0 308959 308959 65536 2359296 365280 40887324 17833347076864 17833347040930 17833347420450 17833347422375
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 164 236503 236503 4194304 256 0 0 8 24 61376 0x7fe83f16b400 0x7fe83c224d00 169956 169956 65536 2424832 381780 42729400 17833347457904 17833347420450 17833347711011 17833347712878
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 167 236503 236503 4194304 256 0 0 12 24 62848 0x7fe83f16b280 0x7fe83c224d40 173407 173407 65536 2949120 441931 49481420 17833347747547 17833347711011 17833348005091 17833348006880
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 170 236503 236503 4194304 256 0 0 12 24 63808 0x7fe83f16b100 0x7fe83c224d80 166344 166344 65536 2162688 321975 36072248 17833348048719 17833348005091 17833348302691 17833348304553
60 58 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 173 236503 236503 4194304 256 0 0 12 24 65024 0x7fe83cb0bf80 0x7fe83c224dc0 305814 305814 65536 2621440 389080 43384336 17833348339332 17833348302691 17833348678051 17833348680044
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 176 236503 236503 4194304 256 0 0 12 24 66240 0x7fe83cb0be00 0x7fe83c224e00 304155 304155 65536 2490368 364521 40814816 17833348715763 17833348678051 17833349050532 17833349052354
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 179 236503 236503 4194304 256 0 0 8 24 67456 0x7fe83cb0bc80 0x7fe83c224e40 170016 170016 65536 2555904 381139 42794068 17833349087144 17833349050532 17833349345252 17833349346957
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 182 236503 236503 4194304 256 0 0 12 24 68928 0x7fe83cb0bb00 0x7fe83c224e80 177017 177017 65536 3145728 470883 52684580 17833349382036 17833349345252 17833349643652 17833349645520
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 185 236503 236503 4194304 256 0 0 12 24 70144 0x7fe83cb0b980 0x7fe83c224ec0 166578 166578 65536 2228224 327804 36764916 17833349687679 17833349643652 17833349935492 17833349937203
65 63 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 188 236503 236503 4194304 256 0 0 12 24 71616 0x7fe83cb0b800 0x7fe83c224f00 302457 302457 65536 2752512 406147 45544456 17833349973952 17833349935492 17833350316773 17833350318913
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 191 236503 236503 4194304 256 0 0 12 24 72832 0x7fe83cb0b680 0x7fe83c224f40 304510 304510 65536 2621440 386423 43272968 17833350354692 17833350316773 17833350692933 17833350694984
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 194 236503 236503 4194304 256 0 0 8 24 74048 0x7fe83f16b500 0x7fe83c224f80 167339 167339 65536 2686976 399117 44684512 17833350728583 17833350692933 17833350982053 17833350984027
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 197 236503 236503 4194304 256 0 0 12 24 75776 0x7fe83f16b380 0x7fe83c224fc0 183614 183614 65536 3342336 496613 55633136 17833351018986 17833350982053 17833351282533 17833351284429
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 200 236503 236503 4194304 256 0 0 12 24 76992 0x7fe83f16b200 0x7fe83c225000 167166 167166 65536 2359296 350153 39373624 17833351338838 17833351282533 17833351576774 17833351578622
70 68 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 203 236503 236503 4194304 256 0 0 12 24 78464 0x7fe83f16b080 0x7fe83c225040 303630 303630 65536 2883584 435848 48734928 17833351615461 17833351576774 17833351958214 17833351960042
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 206 236503 236503 4194304 256 0 0 12 24 79936 0x7fe83cb0bf00 0x7fe83c225080 303100 303100 65536 2686976 399594 44765504 17833351995661 17833351958214 17833352333094 17833352335093
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 209 236503 236503 4194304 256 0 0 8 24 81408 0x7fe83cb0bd80 0x7fe83c2250c0 170425 170425 65536 2818048 421112 47160840 17833352369572 17833352333094 17833352623174 17833352625026
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 212 236503 236503 4194304 256 0 0 12 24 83136 0x7fe83cb0bc00 0x7fe83c225100 192467 192467 65536 3538944 538081 60204324 17833352659005 17833352623174 17833352927655 17833352929528
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 215 236503 236503 4194304 256 0 0 12 24 84352 0x7fe83cb0ba80 0x7fe83c225140 169322 169322 65536 2424832 359577 40321568 17833352971487 17833352927655 17833353224455 17833353226431
75 73 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 218 236503 236503 4194304 256 0 0 12 24 85824 0x7fe83cb0b900 0x7fe83c225180 308086 308086 65536 3014656 453709 50727012 17833353260050 17833353224455 17833353611495 17833353613361
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 221 236503 236503 4194304 256 0 0 12 24 87296 0x7fe83cb0b780 0x7fe83c2251c0 303114 303114 65536 2818048 414457 46395432 17833353647860 17833353611495 17833353985735 17833353987472
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 224 236503 236503 4194304 256 0 0 12 24 88768 0x7fe83cb0b600 0x7fe83c225200 168204 168204 65536 2949120 439817 49244168 17833354022171 17833353985735 17833354291816 17833354293764
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 227 236503 236503 4194304 256 0 0 12 24 90752 0x7fe83f16b480 0x7fe83c225240 201871 201871 65536 3735552 560870 62806964 17833354328653 17833354291816 17833354605416 17833354607396
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 230 236503 236503 4194304 256 0 0 12 24 91968 0x7fe83f16b300 0x7fe83c225280 166916 166916 65536 2555904 395655 44391096 17833354649265 17833354605416 17833354895656 17833354897599
80 78 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 233 236503 236503 4194304 256 0 0 12 24 93440 0x7fe83f16b180 0x7fe83c2252c0 304577 304577 65536 3145728 466630 52282620 17833354933938 17833354895656 17833355272616 17833355274500
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 236 236503 236503 4194304 256 0 0 12 24 94912 0x7fe83f16b000 0x7fe83c225300 301618 301618 65536 2949120 438044 48999416 17833355310369 17833355272616 17833355645897 17833355647791
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 239 236503 236503 4194304 256 0 0 12 24 96384 0x7fe83cb0be80 0x7fe83c225340 168835 168835 65536 3080192 459338 51414080 17833355681500 17833355645897 17833355934057 17833355936003
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 242 236503 236503 4194304 256 0 0 12 24 98368 0x7fe83cb0bd00 0x7fe83c225380 211422 211422 65536 3932160 584962 65429388 17833355970523 17833355934057 17833356256617 17833356258445
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 245 236503 236503 4194304 256 0 0 12 24 99584 0x7fe83cb0bb80 0x7fe83c2253c0 167511 167511 65536 2621440 388846 43578000 17833356300124 17833356256617 17833356552617 17833356554738
85 83 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 248 236503 236503 4194304 256 0 0 12 24 101312 0x7fe83cb0ba00 0x7fe83c225400 304783 304783 65536 3276800 487250 54676880 17833356589057 17833356552617 17833356926858 17833356928709
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 251 236503 236503 4194304 256 0 0 12 24 102784 0x7fe83cb0b880 0x7fe83c225440 304031 304031 65536 3080192 465994 52152364 17833356962958 17833356926858 17833357302858 17833357304939
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 254 236503 236503 4194304 256 0 0 12 24 104256 0x7fe83cb0b700 0x7fe83c225480 168847 168847 65536 3211264 472919 52929148 17833357338709 17833357302858 17833357593578 17833357595522
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 257 236503 236503 4194304 256 0 0 12 24 106240 0x7fe83f16b580 0x7fe83c2254c0 218845 218845 65536 4128768 609203 68267656 17833357630121 17833357593578 17833357919978 17833357921834
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 260 236503 236503 4194304 256 0 0 12 24 107712 0x7fe83f16b400 0x7fe83c225500 167201 167201 65536 2752512 408007 45704904 17833357964573 17833357919978 17833358219659 17833358221797
90 88 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 263 236503 236503 4194304 256 0 0 16 24 109440 0x7fe83f16b280 0x7fe83c225540 300053 300053 65536 3407872 509053 56999112 17833358258066 17833358219659 17833358597099 17833358598907
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 266 236503 236503 4194304 256 0 0 16 24 111168 0x7fe83f16b100 0x7fe83c225580 300200 300200 65536 3211264 474244 53131240 17833358633596 17833358597099 17833358972619 17833358974498
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 269 236503 236503 4194304 256 0 0 8 24 112896 0x7fe83cb0bf80 0x7fe83c2255c0 168788 168788 65536 3276800 492858 55205864 17833359009827 17833358972619 17833359262379 17833359264261
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 272 236503 236503 4194304 256 0 0 12 24 115136 0x7fe83cb0be00 0x7fe83c225600 232164 232164 65536 4325376 648749 72658560 17833359298580 17833359262379 17833359594060 17833359595993
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 275 236503 236503 4194304 256 0 0 12 24 116608 0x7fe83cb0bc80 0x7fe83c225640 169376 169376 65536 2818048 429623 48129556 17833359638381 17833359594060 17833359888300 17833359890205
95 93 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 278 236503 236503 4194304 256 0 0 16 24 118336 0x7fe83cb0bb00 0x7fe83c225680 300713 300713 65536 3538944 524423 58732196 17833359923974 17833359888300 17833360260140 17833360262016
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 281 236503 236503 4194304 256 0 0 16 24 120064 0x7fe83cb0b980 0x7fe83c2256c0 302008 302008 65536 3407872 502770 56356060 17833360296845 17833360260140 17833360630540 17833360632417
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 284 236503 236503 4194304 256 0 0 12 24 121792 0x7fe83cb0b800 0x7fe83c225700 167077 167077 65536 3407872 513280 57448736 17833360666996 17833360630540 17833360919021 17833360920880
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 287 236503 236503 4194304 256 0 0 12 24 124032 0x7fe83cb0b680 0x7fe83c225740 240548 240548 65536 4521984 677850 76029392 17833360955349 17833360919021 17833361257421 17833361259191
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 290 236503 236503 4194304 256 0 0 12 24 125504 0x7fe83f16b500 0x7fe83c225780 169238 169238 65536 3014656 460312 51595968 17833361301430 17833361257421 17833361555981 17833361557714
100 98 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 293 236503 236503 4194304 256 0 0 12 24 127488 0x7fe83f16b380 0x7fe83c2257c0 303321 303321 65536 3801088 565090 63265024 17833361592213 17833361555981 17833361935341 17833361937344
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 296 236503 236503 4194304 256 0 0 12 24 129216 0x7fe83f16b200 0x7fe83c225800 304169 304169 65536 3670016 555213 62175088 17833361972664 17833361935341 17833362320622 17833362322655
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 299 236503 236503 4194304 256 0 0 12 24 130944 0x7fe83f16b080 0x7fe83c225840 173257 173257 65536 3670016 558045 62469356 17833362358914 17833362320622 17833362617102 17833362619097
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 302 236503 236503 4194304 256 0 0 12 24 133440 0x7fe83cb0bf00 0x7fe83c225880 258461 258461 65536 4915200 746817 83594780 17833362654677 17833362617102 17833362965582 17833362967549
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 305 236503 236503 4194304 256 0 0 12 24 134912 0x7fe83cb0bd80 0x7fe83c2258c0 170911 170911 65536 3145728 467869 52410260 17833363011138 17833362965582 17833363263343 17833363265301
105 103 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 308 236503 236503 4194304 256 0 0 12 24 136896 0x7fe83cb0bc00 0x7fe83c225900 301919 301919 65536 4063232 617922 69219988 17833363300421 17833363263343 17833363636943 17833363638762
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 311 236503 236503 4194304 256 0 0 12 24 138880 0x7fe83cb0ba80 0x7fe83c225940 301829 301829 65536 3932160 597857 66953784 17833363674591 17833363636943 17833364009263 17833364011223
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 314 236503 236503 4194304 256 0 0 12 24 140864 0x7fe83cb0b900 0x7fe83c225980 177968 177968 65536 3932160 596056 66734084 17833364045152 17833364009263 17833364312623 17833364314605
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 317 236503 236503 4194304 256 0 0 12 24 143616 0x7fe83cb0b780 0x7fe83c2259c0 278430 278430 65536 5308416 795390 89144032 17833364348674 17833364312623 17833364671344 17833364673196
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 320 236503 236503 4194304 256 0 0 12 24 145344 0x7fe83cb0b600 0x7fe83c225a00 168158 168158 65536 3342336 496115 55511576 17833364715915 17833364671344 17833364967984 17833364969829
110 108 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 323 236503 236503 4194304 256 0 0 12 24 147584 0x7fe83f16b480 0x7fe83c225a40 302112 302112 65536 4325376 679360 75998736 17833365004128 17833364967984 17833365343184 17833365345140
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 326 236503 236503 4194304 256 0 0 12 24 149568 0x7fe83f16b300 0x7fe83c225a80 300038 300038 65536 4194304 640040 71578624 17833365380529 17833365343184 17833365718064 17833365719900
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 329 236503 236503 4194304 256 0 0 12 24 151552 0x7fe83f16b180 0x7fe83c225ac0 187296 187296 65536 4194304 633708 70979648 17833365753980 17833365718064 17833366021105 17833366023093
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 332 236503 236503 4194304 256 0 0 12 24 154304 0x7fe83f16b000 0x7fe83c225b00 300034 300034 65536 5701632 866651 97056844 17833366058802 17833366021105 17833366401905 17833366403933
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 335 236503 236503 4194304 256 0 0 12 24 156288 0x7fe83cb0be80 0x7fe83c225b40 171812 171812 65536 3735552 559895 62694600 17833366446302 17833366401905 17833366700305 17833366702346
115 113 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 338 236503 236503 4194304 256 0 0 12 24 158784 0x7fe83cb0bd00 0x7fe83c225b80 303329 303329 65536 4849664 764136 85670204 17833366739525 17833366700305 17833367079665 17833367081477
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 341 236503 236503 4194304 256 0 0 12 24 161024 0x7fe83cb0bb80 0x7fe83c225bc0 304282 304282 65536 4718592 738083 82726232 17833367115496 17833367079665 17833367467186 17833367469197
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 344 236503 236503 4194304 256 0 0 12 24 163264 0x7fe83cb0ba00 0x7fe83c225c00 206411 206411 65536 4718592 716943 80228732 17833367503216 17833367467186 17833367783666 17833367785549
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 347 236503 236503 4194304 256 0 0 12 24 166528 0x7fe83cb0b880 0x7fe83c225c40 340023 340023 65536 6488064 983106 110076864 17833367819648 17833367783666 17833368182866 17833368209779
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 350 236503 236503 4194304 256 0 0 12 24 168512 0x7fe83cb0b700 0x7fe83c225c80 184379 184379 65536 4128768 621586 69574528 17833368228628 17833368182866 17833368500787 17833368502701
120 118 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 353 236503 236503 4194304 256 0 0 12 24 171264 0x7fe83f16b580 0x7fe83c225cc0 303703 303703 65536 5373952 859064 96251956 17833368539740 17833368500787 17833368880307 17833368882192
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 356 236503 236503 4194304 256 0 0 12 24 173760 0x7fe83f16b400 0x7fe83c225d00 306151 306151 65536 5242880 848046 94899672 17833368917151 17833368880307 17833369260947 17833369265292
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 359 236503 236503 4194304 256 0 0 12 24 176256 0x7fe83f16b280 0x7fe83c225d40 226653 226653 65536 5242880 782651 87709652 17833369297242 17833369260947 17833369588627 17833369590554
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 362 236503 236503 4194304 256 0 0 12 24 179776 0x7fe83f16b100 0x7fe83c225d80 380709 380709 65536 7274496 1096835 122880504 17833369624613 17833369588627 17833370019028 17833370038103
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 365 236503 236503 4194304 256 0 0 12 24 182272 0x7fe83cb0bf80 0x7fe83c225dc0 211326 211326 65536 4915200 734226 82202996 17833370063632 17833370019028 17833370349428 17833370351515
125 123 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 368 236503 236503 4194304 256 0 0 12 24 185536 0x7fe83cb0be00 0x7fe83c225e00 308027 308027 65536 6422528 990606 110945628 17833370385265 17833370349428 17833370734868 17833370784165
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 371 236503 236503 4194304 256 0 0 12 24 188544 0x7fe83cb0bc80 0x7fe83c225e40 311334 311334 65536 6291456 1015562 113688560 17833370794694 17833370734868 17833371160949 17833371207294
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 374 236503 236503 4194304 256 0 0 12 24 191552 0x7fe83cb0bb00 0x7fe83c225e80 266391 266391 65536 6291456 959541 107455604 17833371218164 17833371160949 17833371546549 17833371548436
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 377 236503 236503 4194304 256 0 0 12 24 195840 0x7fe83cb0b980 0x7fe83c225ec0 461600 461600 65536 8847360 1334366 149533012 17833371582655 17833371546549 17833372022069 17833372068323
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 380 236503 236503 4194304 256 0 0 12 24 198592 0x7fe83cb0b800 0x7fe83c225f00 245533 245533 65536 5701632 872385 97746628 17833372087512 17833372022069 17833372399350 17833372401214
130 128 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 383 236503 236503 4194304 256 0 0 12 24 202368 0x7fe83cb0b680 0x7fe83c225f40 333240 333240 65536 7471104 1190293 133416856 17833372438303 17833372399350 17833372805430 17833372827754
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 386 236503 236503 4194304 256 0 0 12 24 205888 0x7fe83f16b500 0x7fe83c225f80 331906 331906 65536 7340032 1156506 129439136 17833372840983 17833372805430 17833373216470 17833373237694
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 389 236503 236503 4194304 256 0 0 12 24 209408 0x7fe83f16b380 0x7fe83c225fc0 306784 306784 65536 7340032 1122895 125758168 17833373253713 17833373216470 17833373602070 17833373604035
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 392 236503 236503 4194304 256 0 0 12 24 214464 0x7fe83f16b200 0x7fe83c226000 542870 542870 65536 10420224 1572795 176191112 17833373638674 17833373602070 17833374129111 17833374151011
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 395 236503 236503 4194304 256 0 0 12 24 217728 0x7fe83f16b080 0x7fe83c226040 273524 273524 65536 6488064 1001580 112199020 17833374174310 17833374129111 17833374501751 17833374503742
135 133 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 398 236503 236503 4194304 256 0 0 12 24 222016 0x7fe83cb0bf00 0x7fe83c226080 367402 367402 65536 8519680 1353274 151506452 17833374538861 17833374501751 17833374928631 17833374946841
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 401 236503 236503 4194304 256 0 0 12 24 226048 0x7fe83cb0bd80 0x7fe83c2260c0 365216 365216 65536 8388608 1304526 146097372 17833374965361 17833374928631 17833375353272 17833375371071
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 404 236503 236503 4194304 256 0 0 12 24 230080 0x7fe83cb0bc00 0x7fe83c226100 347450 347450 65536 8388608 1301080 145747168 17833375389370 17833375353272 17833375759832 17833375776981
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 407 236503 236503 4194304 256 0 0 12 24 235904 0x7fe83cb0ba80 0x7fe83c226140 623883 623883 65536 11993088 1821460 204012224 17833375795600 17833375759832 17833376342393 17833376359956
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 410 236503 236503 4194304 256 0 0 12 24 239424 0x7fe83cb0b900 0x7fe83c226180 301927 301927 65536 7274496 1129391 126520252 17833376386155 17833376342393 17833376726873 17833376728867
140 138 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 413 236503 236503 4194304 256 0 0 12 24 244224 0x7fe83cb0b780 0x7fe83c2261c0 397112 397112 65536 9568256 1519909 170238480 17833376763316 17833376726873 17833377172793 17833377191405
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 416 236503 236503 4194304 256 0 0 12 24 248768 0x7fe83cb0b600 0x7fe83c226200 390579 390579 65536 9437184 1516148 169854668 17833377210205 17833377172793 17833377619354 17833377636884
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 419 236503 236503 4194304 256 0 0 12 24 253312 0x7fe83f16b480 0x7fe83c226240 388246 388246 65536 9437184 1469651 164646916 17833377656044 17833377619354 17833378054714 17833378073234
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 422 236503 236503 4194304 256 0 0 8 24 255552 0x7fe83f16b300 0x7fe83c226280 719031 719031 65536 16056320 2305568 258136480 17833378093213 17833378054714 17833378709754 17833378756117
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 425 236503 236503 4194304 256 0 0 12 24 259840 0x7fe83f16b180 0x7fe83c2262c0 364708 364708 65536 8847360 1370645 153515112 17833378775936 17833378709754 17833379159035 17833379204805
145 143 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 428 236503 236503 4194304 256 0 0 12 24 265664 0x7fe83f16b000 0x7fe83c226300 469173 469173 65536 11665408 1832647 205290624 17833379216425 17833379159035 17833379686075 17833379731762
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 431 236503 236503 4194304 256 0 0 12 24 271232 0x7fe83cb0be80 0x7fe83c226340 472147 472147 65536 11468800 1836446 205663764 17833379742592 17833379686075 17833380206876 17833380252019
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 434 236503 236503 4194304 256 0 0 8 24 273216 0x7fe83cb0bd00 0x7fe83c226380 483319 483319 65536 14090240 2020745 226286316 17833380262739 17833380206876 17833380730396 17833380775826
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 437 236503 236503 4194304 256 0 0 8 24 275712 0x7fe83cb0bb80 0x7fe83c2263c0 880693 880693 65536 19202048 2756489 308858668 17833380786746 17833380730396 17833381509117 17833381554727
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 440 236503 236503 4194304 256 0 0 12 24 280768 0x7fe83cb0ba00 0x7fe83c226400 426823 426823 65536 10420224 1609659 180348376 17833381573027 17833381509117 17833381995517 17833382013656
150 148 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 443 236503 236503 4194304 256 0 0 12 24 287616 0x7fe83cb0b880 0x7fe83c226440 550151 550151 65536 13762560 2210664 247726852 17833382032035 17833381995517 17833382551997 17833382597981
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 446 236503 236503 4194304 256 0 0 12 24 294208 0x7fe83cb0b700 0x7fe83c226480 551517 551517 65536 13565952 2140716 239728764 17833382609251 17833382551997 17833383127358 17833383172737
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 449 236503 236503 4194304 256 0 0 8 24 296960 0x7fe83f16b580 0x7fe83c2264c0 564777 564777 65536 15466496 2228456 249593016 17833383183477 17833383127358 17833383699518 17833383744933
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 452 236503 236503 4194304 256 0 0 8 24 299968 0x7fe83f16b400 0x7fe83c226500 1044359 1044359 65536 22347776 3211299 359707520 17833383755813 17833383699518 17833384583359 17833384626841
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 455 236503 236503 4194304 256 0 0 8 24 302720 0x7fe83f16b280 0x7fe83c226540 722945 722945 65536 20250624 2923813 327459048 17833384644931 17833384583359 17833385251039 17833385295565
155 153 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 458 236503 236503 4194304 256 0 0 12 24 305472 0x7fe83f16b100 0x7fe83c226580 725769 725769 65536 20447232 2935642 328720784 17833385306544 17833385251039 17833385941920 17833385960188
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 461 236503 236503 4194304 256 0 0 12 24 308224 0x7fe83cb0bf80 0x7fe83c2265c0 721755 721755 65536 19595264 2818351 315615332 17833385979718 17833385941920 17833386603840 17833386650201
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 464 236503 236503 4194304 256 0 0 8 24 310976 0x7fe83cb0be00 0x7fe83c226600 727949 727949 65536 20381696 2928148 327905732 17833386661111 17833386603784 17833387281864 17833387333494
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 467 236503 236503 4194304 256 0 0 8 24 313216 0x7fe83cb0bc80 0x7fe83c226640 1366307 1366307 65536 31522816 4509238 505473072 17833387344264 17833387281864 17833388391624 17833388436797
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 470 236503 236503 4194304 256 0 0 8 24 315968 0x7fe83cb0bb00 0x7fe83c226680 1373247 1373247 65536 38993920 5583960 625679232 17833388456356 17833388391624 17833389481225 17833389547849
160 158 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 473 236503 236503 4194304 256 0 0 12 24 318720 0x7fe83cb0b980 0x7fe83c2266c0 1373929 1373929 65536 39124992 5615805 628883484 17833389559129 17833389481225 17833390631786 17833390703550
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 476 236503 236503 4194304 256 0 0 12 24 321472 0x7fe83cb0b800 0x7fe83c226700 1372851 1372851 65536 38469632 5509601 617057236 17833390715150 17833390631786 17833391778986 17833391848222
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 479 236503 236503 4194304 256 0 0 8 24 324224 0x7fe83cb0b680 0x7fe83c226740 1375132 1375132 65536 39059456 5596845 626840900 17833391858982 17833391778986 17833392899307 17833392966684
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 482 236503 236503 4194304 256 0 0 8 24 326464 0x7fe83f16b500 0x7fe83c226780 2664386 2664386 65536 60489728 8652521 969163852 17833392977874 17833392899307 17833394866828 17833394944075
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 485 236503 236503 4194304 256 0 0 8 24 329216 0x7fe83f16b380 0x7fe83c2267c0 2669534 2669534 65536 77266944 11073873 1240553420 17833394963545 17833394866828 17833396808270 17833396876617
165 163 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 488 236503 236503 4194304 256 0 0 12 24 331968 0x7fe83f16b200 0x7fe83c226800 2672170 2672170 65536 77398016 11071825 1240072748 17833396887957 17833396808270 17833398795791 17833398869628
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 491 236503 236503 4194304 256 0 0 12 24 334720 0x7fe83f16b080 0x7fe83c226840 2668592 2668592 65536 76218368 10904144 1221576836 17833398880977 17833398795791 17833400781712 17833400848588
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 494 236503 236503 4194304 256 0 0 8 24 337472 0x7fe83cb0bf00 0x7fe83c226880 2672754 2672754 65536 77332480 11067421 1239281240 17833400859718 17833400781712 17833402716274 17833402787070
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 497 236503 236503 4194304 256 0 0 8 24 0 0x7fe83cb0bd80 0x7fe83c2268c0 5255776 5255776 65536 120258560 17187452 1925701988 17833402798580 17833402716274 17833406340436 17833406412550
+168
Voir le fichier
@@ -0,0 +1,168 @@
Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,BeginNs,EndNs,CompleteNs
0,"__amd_rocclr_fillBufferAligned.kd",0,0,0,238351,238351,33554432,256,0,0,4,32,4160,0x0,0x7ff888c04280,0,0,0,17852547584485,17851838027568,17852691164011,17852691281181
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,238351,238351,32768,256,0,0,12,24,13888,0x0,0x7ff888c23f80,0,0,0,17852696444493,17852691164011,17852696572335,17852696576630
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,238351,238351,4194304,256,0,0,12,24,14336,0x7ff88bbf2380,0x7ff888c23fc0,0,0,0,17852696612159,17852696572335,17852696936336,17852696938901
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,238351,238351,4194304,256,0,0,16,24,15040,0x7ff88bbf2200,0x7ff888c24000,0,0,0,17852696975310,17852696936336,17852697339696,17852697341881
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,238351,238351,4194304,256,0,0,16,24,15488,0x7ff88bbf2080,0x7ff888c24040,0,0,0,17852697374780,17852697339696,17852697731856,17852697734031
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,238351,238351,4194304,256,0,0,12,24,15936,0x7ff8895c3f00,0x7ff888c24080,0,0,0,17852697767750,17852697731856,17852698036497,17852698038724
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,238351,238351,4194304,256,0,0,12,24,16384,0x7ff8895c3d80,0x7ff888c240c0,0,0,0,17852698071613,17852698036497,17852698369937,17852698372295
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,238351,238351,4194304,256,0,0,12,24,17088,0x7ff8895c3c00,0x7ff888c24100,0,0,0,17852698416344,17852698369937,17852698676817,17852698679058
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,238351,238351,4194304,256,0,0,16,24,17792,0x7ff8895c3a80,0x7ff888c24140,0,0,0,17852698711897,17852698676817,17852699069297,17852699071448
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,238351,238351,4194304,256,0,0,16,24,18496,0x7ff8895c3900,0x7ff888c24180,0,0,0,17852699103227,17852699069297,17852699460338,17852699462438
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,238351,238351,4194304,256,0,0,16,24,19200,0x7ff8895c3780,0x7ff888c241c0,0,0,0,17852699493987,17852699460338,17852699775858,17852699778060
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,238351,238351,4194304,256,0,0,16,24,19904,0x7ff8895c3600,0x7ff888c24200,0,0,0,17852699811880,17852699775858,17852700079858,17852700082053
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,238351,238351,4194304,256,0,0,12,24,20608,0x7ff88bbf2480,0x7ff888c24240,0,0,0,17852700121632,17852700079858,17852700381299,17852700383605
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,238351,238351,4194304,256,0,0,16,24,21312,0x7ff88bbf2300,0x7ff888c24280,0,0,0,17852700416035,17852700381299,17852700771219,17852700773606
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,238351,238351,4194304,256,0,0,16,24,22016,0x7ff88bbf2180,0x7ff888c242c0,0,0,0,17852700806585,17852700771219,17852701160019,17852701162216
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,238351,238351,4194304,256,0,0,16,24,22720,0x7ff88bbf2000,0x7ff888c24300,0,0,0,17852701194595,17852701160019,17852701463540,17852701465598
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,238351,238351,4194304,256,0,0,12,24,23424,0x7ff8895c3e80,0x7ff888c24340,0,0,0,17852701497488,17852701463540,17852701764020,17852701766161
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,238351,238351,4194304,256,0,0,12,24,24128,0x7ff8895c3d00,0x7ff888c24380,0,0,0,17852701805360,17852701764020,17852702066100,17852702068263
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,238351,238351,4194304,256,0,0,16,24,24832,0x7ff8895c3b80,0x7ff888c243c0,0,0,0,17852702100643,17852702066100,17852702483061,17852702485313
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,238351,238351,4194304,256,0,0,16,24,25536,0x7ff8895c3a00,0x7ff888c24400,0,0,0,17852702517042,17852702483061,17852702873781,17852702876263
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,238351,238351,4194304,256,0,0,12,24,26240,0x7ff8895c3880,0x7ff888c24440,0,0,0,17852702907713,17852702873781,17852703202901,17852703204495
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,238351,238351,4194304,256,0,0,12,24,26944,0x7ff8895c3700,0x7ff888c24480,0,0,0,17852703236464,17852703202901,17852703480181,17852703481768
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,238351,238351,4194304,256,0,0,12,24,27648,0x7ff88bbf2580,0x7ff888c244c0,0,0,0,17852703520677,17852703480181,17852703754102,17852703755692
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,238351,238351,4194304,256,0,0,16,24,28608,0x7ff88bbf2400,0x7ff888c24500,0,0,0,17852703787681,17852703754102,17852704118422,17852704119943
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,238351,238351,4194304,256,0,0,16,24,29312,0x7ff88bbf2280,0x7ff888c24540,0,0,0,17852704151352,17852704118422,17852704479702,17852704481324
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,238351,238351,4194304,256,0,0,12,24,30016,0x7ff88bbf2100,0x7ff888c24580,0,0,0,17852704513273,17852704479702,17852704755543,17852704757237
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,238351,238351,4194304,256,0,0,8,24,30976,0x7ff8895c3f80,0x7ff888c245c0,0,0,0,17852704788706,17852704755543,17852705030423,17852705031860
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,238351,238351,4194304,256,0,0,12,24,31680,0x7ff8895c3e00,0x7ff888c24600,0,0,0,17852705070659,17852705030423,17852705307703,17852705309243
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,238351,238351,4194304,256,0,0,16,24,32640,0x7ff8895c3c80,0x7ff888c24640,0,0,0,17852705340412,17852705307703,17852705671863,17852705673524
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,238351,238351,4194304,256,0,0,12,24,33600,0x7ff8895c3b00,0x7ff888c24680,0,0,0,17852705705043,17852705671863,17852706035864,17852706037365
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,238351,238351,4194304,256,0,0,12,24,34560,0x7ff8895c3980,0x7ff888c246c0,0,0,0,17852706068534,17852706035864,17852706325464,17852706327138
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,238351,238351,4194304,256,0,0,8,24,35520,0x7ff8895c3800,0x7ff888c24700,0,0,0,17852706359087,17852706325464,17852706606264,17852706607841
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,238351,238351,4194304,256,0,0,12,24,36224,0x7ff8895c3680,0x7ff888c24740,0,0,0,17852706646370,17852706606264,17852706884824,17852706886384
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,238351,238351,4194304,256,0,0,12,24,37184,0x7ff88bbf2500,0x7ff888c24780,0,0,0,17852706918173,17852706884824,17852707251065,17852707252885
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,238351,238351,4194304,256,0,0,12,24,38144,0x7ff88bbf2380,0x7ff888c247c0,0,0,0,17852707284684,17852707251065,17852707615225,17852707616896
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,238351,238351,4194304,256,0,0,12,24,39104,0x7ff88bbf2200,0x7ff888c24800,0,0,0,17852707648045,17852707615225,17852707890105,17852707891729
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,238351,238351,4194304,256,0,0,8,24,40320,0x7ff88bbf2080,0x7ff888c24840,0,0,0,17852707923748,17852707890105,17852708166586,17852708168142
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,238351,238351,4194304,256,0,0,12,24,41280,0x7ff8895c3f00,0x7ff888c24880,0,0,0,17852708207321,17852708166586,17852708442906,17852708444485
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,238351,238351,4194304,256,0,0,12,24,42240,0x7ff8895c3d80,0x7ff888c248c0,0,0,0,17852708475035,17852708442906,17852708806266,17852708807837
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,238351,238351,4194304,256,0,0,12,24,43200,0x7ff8895c3c00,0x7ff888c24900,0,0,0,17852708841876,17852708806266,17852709173467,17852709175027
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,238351,238351,4194304,256,0,0,8,24,44160,0x7ff8895c3a80,0x7ff888c24940,0,0,0,17852709206277,17852709173467,17852709449627,17852709451181
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,238351,238351,4194304,256,0,0,12,24,45376,0x7ff8895c3900,0x7ff888c24980,0,0,0,17852709482650,17852709449627,17852709728507,17852709730184
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,238351,238351,4194304,256,0,0,12,24,46336,0x7ff8895c3780,0x7ff888c249c0,0,0,0,17852709769003,17852709728507,17852710007227,17852710008837
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,238351,238351,4194304,256,0,0,12,24,47552,0x7ff8895c3600,0x7ff888c24a00,0,0,0,17852710040166,17852710007227,17852710383548,17852710385288
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,238351,238351,4194304,256,0,0,12,24,48512,0x7ff88bbf2480,0x7ff888c24a40,0,0,0,17852710418027,17852710383548,17852710744348,17852710745959
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,238351,238351,4194304,256,0,0,8,24,49472,0x7ff88bbf2300,0x7ff888c24a80,0,0,0,17852710777528,17852710744348,17852711022108,17852711023662
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,238351,238351,4194304,256,0,0,12,24,50688,0x7ff88bbf2180,0x7ff888c24ac0,0,0,0,17852711055971,17852711022108,17852711304188,17852711305805
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,238351,238351,4194304,256,0,0,12,24,51648,0x7ff88bbf2000,0x7ff888c24b00,0,0,0,17852711344854,17852711304188,17852711596989,17852711598567
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,238351,238351,4194304,256,0,0,12,24,52864,0x7ff8895c3e80,0x7ff888c24b40,0,0,0,17852711631277,17852711596989,17852711961149,17852711962848
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,238351,238351,4194304,256,0,0,12,24,54080,0x7ff8895c3d00,0x7ff888c24b80,0,0,0,17852711994718,17852711961149,17852712327549,17852712329159
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,238351,238351,4194304,256,0,0,8,24,55296,0x7ff8895c3b80,0x7ff888c24bc0,0,0,0,17852712360458,17852712327549,17852712604990,17852712606592
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,238351,238351,4194304,256,0,0,12,24,56768,0x7ff8895c3a00,0x7ff888c24c00,0,0,0,17852712639062,17852712604990,17852712884670,17852712886435
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,238351,238351,4194304,256,0,0,12,24,57728,0x7ff8895c3880,0x7ff888c24c40,0,0,0,17852712924404,17852712884670,17852713165470,17852713167208
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,238351,238351,4194304,256,0,0,12,24,58944,0x7ff8895c3700,0x7ff888c24c80,0,0,0,17852713198898,17852713165470,17852713529470,17852713531039
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,238351,238351,4194304,256,0,0,12,24,60160,0x7ff88bbf2580,0x7ff888c24cc0,0,0,0,17852713563649,17852713529470,17852713890751,17852713892420
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,238351,238351,4194304,256,0,0,8,24,61376,0x7ff88bbf2400,0x7ff888c24d00,0,0,0,17852713925370,17852713890751,17852714168991,17852714170743
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,238351,238351,4194304,256,0,0,12,24,62848,0x7ff88bbf2280,0x7ff888c24d40,0,0,0,17852714203523,17852714168991,17852714452831,17852714454446
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,238351,238351,4194304,256,0,0,12,24,63808,0x7ff88bbf2100,0x7ff888c24d80,0,0,0,17852714493475,17852714452831,17852714730591,17852714732310
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,238351,238351,4194304,256,0,0,12,24,65024,0x7ff8895c3f80,0x7ff888c24dc0,0,0,0,17852714764259,17852714730591,17852715097952,17852715099550
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,238351,238351,4194304,256,0,0,12,24,66240,0x7ff8895c3e00,0x7ff888c24e00,0,0,0,17852715131050,17852715097952,17852715461792,17852715463411
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,238351,238351,4194304,256,0,0,8,24,67456,0x7ff8895c3c80,0x7ff888c24e40,0,0,0,17852715495341,17852715461792,17852715739392,17852715741084
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,238351,238351,4194304,256,0,0,12,24,68928,0x7ff8895c3b00,0x7ff888c24e80,0,0,0,17852715773124,17852715739392,17852716027073,17852716028717
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,238351,238351,4194304,256,0,0,12,24,70144,0x7ff8895c3980,0x7ff888c24ec0,0,0,0,17852716068486,17852716027073,17852716306273,17852716307960
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,238351,238351,4194304,256,0,0,12,24,71616,0x7ff8895c3800,0x7ff888c24f00,0,0,0,17852716339270,17852716306273,17852716670113,17852716671741
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,238351,238351,4194304,256,0,0,12,24,72832,0x7ff8895c3680,0x7ff888c24f40,0,0,0,17852716703121,17852716670113,17852717030914,17852717032592
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,238351,238351,4194304,256,0,0,8,24,74048,0x7ff88bbf2500,0x7ff888c24f80,0,0,0,17852717063472,17852717030914,17852717308194,17852717309915
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,238351,238351,4194304,256,0,0,12,24,75776,0x7ff88bbf2380,0x7ff888c24fc0,0,0,0,17852717341515,17852717308194,17852717598274,17852717599928
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,238351,238351,4194304,256,0,0,12,24,76992,0x7ff88bbf2200,0x7ff888c25000,0,0,0,17852717638877,17852717598274,17852717874434,17852717875971
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,238351,238351,4194304,256,0,0,12,24,78464,0x7ff88bbf2080,0x7ff888c25040,0,0,0,17852717908151,17852717874434,17852718242115,17852718243902
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,238351,238351,4194304,256,0,0,12,24,79936,0x7ff8895c3f00,0x7ff888c25080,0,0,0,17852718276721,17852718242115,17852718610275,17852718611863
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,238351,238351,4194304,256,0,0,8,24,81408,0x7ff8895c3d80,0x7ff888c250c0,0,0,0,17852718642982,17852718610275,17852718888355,17852718889966
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,238351,238351,4194304,256,0,0,12,24,83136,0x7ff8895c3c00,0x7ff888c25100,0,0,0,17852718921995,17852718888355,17852719182915,17852719184579
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,238351,238351,4194304,256,0,0,12,24,84352,0x7ff8895c3a80,0x7ff888c25140,0,0,0,17852719235378,17852719182915,17852719468836,17852719471082
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,238351,238351,4194304,256,0,0,12,24,85824,0x7ff8895c3900,0x7ff888c25180,0,0,0,17852719502231,17852719468836,17852719841796,17852719843403
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,238351,238351,4194304,256,0,0,12,24,87296,0x7ff8895c3780,0x7ff888c251c0,0,0,0,17852719875732,17852719841796,17852720205156,17852720206694
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,238351,238351,4194304,256,0,0,12,24,88768,0x7ff8895c3600,0x7ff888c25200,0,0,0,17852720237623,17852720205156,17852720485637,17852720487157
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,238351,238351,4194304,256,0,0,12,24,90752,0x7ff88bbf2480,0x7ff888c25240,0,0,0,17852720519426,17852720485637,17852720791237,17852720792699
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,238351,238351,4194304,256,0,0,12,24,91968,0x7ff88bbf2300,0x7ff888c25280,0,0,0,17852720831258,17852720791237,17852721075237,17852721076832
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,238351,238351,4194304,256,0,0,12,24,93440,0x7ff88bbf2180,0x7ff888c252c0,0,0,0,17852721109001,17852721075237,17852721437477,17852721439053
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,238351,238351,4194304,256,0,0,12,24,94912,0x7ff88bbf2000,0x7ff888c25300,0,0,0,17852721471482,17852721437477,17852721802598,17852721804134
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,238351,238351,4194304,256,0,0,12,24,96384,0x7ff8895c3e80,0x7ff888c25340,0,0,0,17852721835423,17852721802598,17852722083878,17852722085677
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,238351,238351,4194304,256,0,0,12,24,98368,0x7ff8895c3d00,0x7ff888c25380,0,0,0,17852722117666,17852722083878,17852722394278,17852722395829
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,238351,238351,4194304,256,0,0,12,24,99584,0x7ff8895c3b80,0x7ff888c253c0,0,0,0,17852722435088,17852722394278,17852722680359,17852722681982
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,238351,238351,4194304,256,0,0,12,24,101312,0x7ff8895c3a00,0x7ff888c25400,0,0,0,17852722713441,17852722680359,17852723043079,17852723044603
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,238351,238351,4194304,256,0,0,12,24,102784,0x7ff8895c3880,0x7ff888c25440,0,0,0,17852723076572,17852723043079,17852723405639,17852723407144
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,238351,238351,4194304,256,0,0,12,24,104256,0x7ff8895c3700,0x7ff888c25480,0,0,0,17852723438243,17852723405639,17852723683239,17852723685007
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,238351,238351,4194304,256,0,0,12,24,106240,0x7ff88bbf2580,0x7ff888c254c0,0,0,0,17852723715457,17852723683239,17852723995560,17852723997160
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,238351,238351,4194304,256,0,0,12,24,107712,0x7ff88bbf2400,0x7ff888c25500,0,0,0,17852724036629,17852723995560,17852724280840,17852724282463
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,238351,238351,4194304,256,0,0,16,24,109440,0x7ff88bbf2280,0x7ff888c25540,0,0,0,17852724316172,17852724280840,17852724642760,17852724644394
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,238351,238351,4194304,256,0,0,16,24,111168,0x7ff88bbf2100,0x7ff888c25580,0,0,0,17852724677643,17852724642760,17852725009481,17852725011105
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,238351,238351,4194304,256,0,0,8,24,112896,0x7ff8895c3f80,0x7ff888c255c0,0,0,0,17852725042374,17852725009481,17852725289481,17852725291098
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,238351,238351,4194304,256,0,0,12,24,115136,0x7ff8895c3e00,0x7ff888c25600,0,0,0,17852725322377,17852725289481,17852725611561,17852725613050
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,238351,238351,4194304,256,0,0,12,24,116608,0x7ff8895c3c80,0x7ff888c25640,0,0,0,17852725651419,17852725611561,17852725888361,17852725889983
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,238351,238351,4194304,256,0,0,16,24,118336,0x7ff8895c3b00,0x7ff888c25680,0,0,0,17852725921822,17852725888361,17852726253482,17852726255414
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,238351,238351,4194304,256,0,0,16,24,120064,0x7ff8895c3980,0x7ff888c256c0,0,0,0,17852726287623,17852726253482,17852726617482,17852726619115
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,238351,238351,4194304,256,0,0,12,24,121792,0x7ff8895c3800,0x7ff888c25700,0,0,0,17852726650804,17852726617482,17852726896522,17852726898098
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,238351,238351,4194304,256,0,0,12,24,124032,0x7ff8895c3680,0x7ff888c25740,0,0,0,17852726929667,17852726896522,17852727227403,17852727229120
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,238351,238351,4194304,256,0,0,12,24,125504,0x7ff88bbf2500,0x7ff888c25780,0,0,0,17852727267889,17852727227403,17852727511403,17852727512983
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,238351,238351,4194304,256,0,0,12,24,127488,0x7ff88bbf2380,0x7ff888c257c0,0,0,0,17852727544622,17852727511403,17852727872523,17852727874214
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,238351,238351,4194304,256,0,0,12,24,129216,0x7ff88bbf2200,0x7ff888c25800,0,0,0,17852727907013,17852727872523,17852728235724,17852728237265
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,238351,238351,4194304,256,0,0,12,24,130944,0x7ff88bbf2080,0x7ff888c25840,0,0,0,17852728269444,17852728235724,17852728517484,17852728519148
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,238351,238351,4194304,256,0,0,12,24,133440,0x7ff8895c3f00,0x7ff888c25880,0,0,0,17852728551127,17852728517484,17852728857804,17852728859459
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,238351,238351,4194304,256,0,0,12,24,134912,0x7ff8895c3d80,0x7ff888c258c0,0,0,0,17852728899498,17852728857804,17852729139564,17852729141132
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,238351,238351,4194304,256,0,0,12,24,136896,0x7ff8895c3c00,0x7ff888c25900,0,0,0,17852729172291,17852729139564,17852729503085,17852729504743
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,238351,238351,4194304,256,0,0,12,24,138880,0x7ff8895c3a80,0x7ff888c25940,0,0,0,17852729536092,17852729503085,17852729865485,17852729867124
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,238351,238351,4194304,256,0,0,12,24,140864,0x7ff8895c3900,0x7ff888c25980,0,0,0,17852729898743,17852729865485,17852730155885,17852730157467
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,238351,238351,4194304,256,0,0,12,24,143616,0x7ff8895c3780,0x7ff888c259c0,0,0,0,17852730190876,17852730155885,17852730525006,17852730526718
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,238351,238351,4194304,256,0,0,12,24,145344,0x7ff8895c3600,0x7ff888c25a00,0,0,0,17852730566577,17852730525006,17852730809646,17852730811381
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,238351,238351,4194304,256,0,0,12,24,147584,0x7ff88bbf2480,0x7ff888c25a40,0,0,0,17852730843010,17852730809646,17852731174126,17852731175882
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,238351,238351,4194304,256,0,0,12,24,149568,0x7ff88bbf2300,0x7ff888c25a80,0,0,0,17852731208061,17852731174126,17852731537327,17852731538893
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,238351,238351,4194304,256,0,0,12,24,151552,0x7ff88bbf2180,0x7ff888c25ac0,0,0,0,17852731570982,17852731537327,17852731833807,17852731835685
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,238351,238351,4194304,256,0,0,12,24,154304,0x7ff88bbf2000,0x7ff888c25b00,0,0,0,17852731867534,17852731833807,17852732204527,17852732206096
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,238351,238351,4194304,256,0,0,12,24,156288,0x7ff8895c3e80,0x7ff888c25b40,0,0,0,17852732245085,17852732204527,17852732490287,17852732491899
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,238351,238351,4194304,256,0,0,12,24,158784,0x7ff8895c3d00,0x7ff888c25b80,0,0,0,17852732523968,17852732490287,17852732856048,17852732857640
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,238351,238351,4194304,256,0,0,12,24,161024,0x7ff8895c3b80,0x7ff888c25bc0,0,0,0,17852732889679,17852732856048,17852733221648,17852733223301
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,238351,238351,4194304,256,0,0,12,24,163264,0x7ff8895c3a00,0x7ff888c25c00,0,0,0,17852733254330,17852733221648,17852733532368,17852733533913
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,238351,238351,4194304,256,0,0,12,24,166528,0x7ff8895c3880,0x7ff888c25c40,0,0,0,17852733565032,17852733532368,17852733921009,17852733941203
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,238351,238351,4194304,256,0,0,12,24,168512,0x7ff8895c3700,0x7ff888c25c80,0,0,0,17852733962372,17852733921009,17852734230929,17852734232796
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,238351,238351,4194304,256,0,0,12,24,171264,0x7ff88bbf2580,0x7ff888c25cc0,0,0,0,17852734265345,17852734230929,17852734609169,17852734610756
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,238351,238351,4194304,256,0,0,12,24,173760,0x7ff88bbf2400,0x7ff888c25d00,0,0,0,17852734643356,17852734609169,17852734977490,17852734979187
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,238351,238351,4194304,256,0,0,12,24,176256,0x7ff88bbf2280,0x7ff888c25d40,0,0,0,17852735011617,17852734977490,17852735296850,17852735298459
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,238351,238351,4194304,256,0,0,12,24,179776,0x7ff88bbf2100,0x7ff888c25d80,0,0,0,17852735330689,17852735296850,17852735711570,17852735757648
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,238351,238351,4194304,256,0,0,12,24,182272,0x7ff8895c3f80,0x7ff888c25dc0,0,0,0,17852735776978,17852735711570,17852736060851,17852736062501
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,238351,238351,4194304,256,0,0,12,24,185536,0x7ff8895c3e00,0x7ff888c25e00,0,0,0,17852736095700,17852736060851,17852736435731,17852736480820
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,238351,238351,4194304,256,0,0,12,24,188544,0x7ff8895c3c80,0x7ff888c25e40,0,0,0,17852736492510,17852736435731,17852736844051,17852736886710
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,238351,238351,4194304,256,0,0,12,24,191552,0x7ff8895c3b00,0x7ff888c25e80,0,0,0,17852736898080,17852736844051,17852737223732,17852737225292
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,238351,238351,4194304,256,0,0,12,24,195840,0x7ff8895c3980,0x7ff888c25ec0,0,0,0,17852737256371,17852737223732,17852737690612,17852737709180
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,238351,238351,4194304,256,0,0,12,24,198592,0x7ff8895c3800,0x7ff888c25f00,0,0,0,17852737731449,17852737690612,17852738033812,17852738035472
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,238351,238351,4194304,256,0,0,12,24,202368,0x7ff8895c3680,0x7ff888c25f40,0,0,0,17852738067181,17852738033812,17852738456693,17852738501100
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,238351,238351,4194304,256,0,0,12,24,205888,0x7ff88bbf2500,0x7ff888c25f80,0,0,0,17852738514830,17852738456693,17852738880533,17852738924380
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,238351,238351,4194304,256,0,0,12,24,209408,0x7ff88bbf2380,0x7ff888c25fc0,0,0,0,17852738935080,17852738880533,17852739282613,17852739284311
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,238351,238351,4194304,256,0,0,12,24,214464,0x7ff88bbf2200,0x7ff888c26000,0,0,0,17852739317490,17852739282613,17852739807414,17852739849997
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,238351,238351,4194304,256,0,0,12,24,217728,0x7ff88bbf2080,0x7ff888c26040,0,0,0,17852739870166,17852739807414,17852740189654,17852740191278
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,238351,238351,4194304,256,0,0,12,24,222016,0x7ff8895c3f00,0x7ff888c26080,0,0,0,17852740223318,17852740189654,17852740603735,17852740646387
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,238351,238351,4194304,256,0,0,12,24,226048,0x7ff8895c3d80,0x7ff888c260c0,0,0,0,17852740658167,17852740603735,17852741053975,17852741096566
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,238351,238351,4194304,256,0,0,12,24,230080,0x7ff8895c3c00,0x7ff888c26100,0,0,0,17852741108566,17852741053975,17852741477975,17852741520635
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,238351,238351,4194304,256,0,0,12,24,235904,0x7ff8895c3a80,0x7ff888c26140,0,0,0,17852741533345,17852741477975,17852742078136,17852742100261
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,238351,238351,4194304,256,0,0,12,24,239424,0x7ff8895c3900,0x7ff888c26180,0,0,0,17852742120520,17852742078136,17852742462616,17852742464122
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,238351,238351,4194304,256,0,0,12,24,244224,0x7ff8895c3780,0x7ff888c261c0,0,0,0,17852742495881,17852742462616,17852742899737,17852742943690
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,238351,238351,4194304,256,0,0,12,24,248768,0x7ff8895c3600,0x7ff888c26200,0,0,0,17852742956040,17852742899737,17852743360697,17852743403809
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,238351,238351,4194304,256,0,0,12,24,253312,0x7ff88bbf2480,0x7ff888c26240,0,0,0,17852743415308,17852743360697,17852743812697,17852743854887
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,238351,238351,4194304,256,0,0,8,24,255552,0x7ff88bbf2300,0x7ff888c26280,0,0,0,17852743866867,17852743812697,17852744476858,17852744519781
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,238351,238351,4194304,256,0,0,12,24,259840,0x7ff88bbf2180,0x7ff888c262c0,0,0,0,17852744539460,17852744476858,17852744921338,17852744964010
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,238351,238351,4194304,256,0,0,12,24,265664,0x7ff88bbf2000,0x7ff888c26300,0,0,0,17852744975050,17852744921338,17852745435899,17852745478337
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,238351,238351,4194304,256,0,0,12,24,271232,0x7ff8895c3e80,0x7ff888c26340,0,0,0,17852745489317,17852745435899,17852745954459,17852745972385
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,238351,238351,4194304,256,0,0,8,24,273216,0x7ff8895c3d00,0x7ff888c26380,0,0,0,17852745987614,17852745954459,17852746446940,17852746492852
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,238351,238351,4194304,256,0,0,8,24,275712,0x7ff8895c3b80,0x7ff888c263c0,0,0,0,17852746505581,17852746446940,17852747219101,17852747263173
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,238351,238351,4194304,256,0,0,12,24,280768,0x7ff8895c3a00,0x7ff888c26400,0,0,0,17852747283402,17852747219101,17852747705501,17852747747881
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,238351,238351,4194304,256,0,0,12,24,287616,0x7ff8895c3880,0x7ff888c26440,0,0,0,17852747758960,17852747705501,17852748268861,17852748310857
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,238351,238351,4194304,256,0,0,12,24,294208,0x7ff8895c3700,0x7ff888c26480,0,0,0,17852748322856,17852748268861,17852748832222,17852748874753
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,238351,238351,4194304,256,0,0,8,24,296960,0x7ff88bbf2580,0x7ff888c264c0,0,0,0,17852748886262,17852748832222,17852749394782,17852749436889
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,238351,238351,4194304,256,0,0,8,24,299968,0x7ff88bbf2400,0x7ff888c26500,0,0,0,17852749448568,17852749394782,17852750264863,17852750309257
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,238351,238351,4194304,256,0,0,8,24,302720,0x7ff88bbf2280,0x7ff888c26540,0,0,0,17852750329727,17852750264863,17852750929824,17852750974811
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,238351,238351,4194304,256,0,0,12,24,305472,0x7ff88bbf2100,0x7ff888c26580,0,0,0,17852750986220,17852750929824,17852751608704,17852751652374
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,238351,238351,4194304,256,0,0,12,24,308224,0x7ff8895c3f80,0x7ff888c265c0,0,0,0,17852751663494,17852751608704,17852752288225,17852752330757
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,238351,238351,4194304,256,0,0,8,24,310976,0x7ff8895c3e00,0x7ff888c26600,0,0,0,17852752342157,17852752288225,17852752950306,17852752993191
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,238351,238351,4194304,256,0,0,8,24,313216,0x7ff8895c3c80,0x7ff888c26640,0,0,0,17852753004871,17852752950014,17852754036414,17852754087294
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,238351,238351,4194304,256,0,0,8,24,315968,0x7ff8895c3b00,0x7ff888c26680,0,0,0,17852754107573,17852754036414,17852755116734,17852755164557
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,238351,238351,4194304,256,0,0,12,24,318720,0x7ff8895c3980,0x7ff888c266c0,0,0,0,17852755175877,17852755116734,17852756216414,17852756283989
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,238351,238351,4194304,256,0,0,12,24,321472,0x7ff8895c3800,0x7ff888c26700,0,0,0,17852756296649,17852756216414,17852757347295,17852757413671
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,238351,238351,4194304,256,0,0,8,24,324224,0x7ff8895c3680,0x7ff888c26740,0,0,0,17852757426311,17852757347295,17852758455615,17852758522824
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,238351,238351,4194304,256,0,0,8,24,326464,0x7ff88bbf2500,0x7ff888c26780,0,0,0,17852758535493,17852758455615,17852760413696,17852760480545
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,238351,238351,4194304,256,0,0,8,24,329216,0x7ff88bbf2380,0x7ff888c267c0,0,0,0,17852760500774,17852760413696,17852762329856,17852762401667
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,238351,238351,4194304,256,0,0,12,24,331968,0x7ff88bbf2200,0x7ff888c26800,0,0,0,17852762414887,17852762329856,17852764331937,17852764406557
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,238351,238351,4194304,256,0,0,12,24,334720,0x7ff88bbf2080,0x7ff888c26840,0,0,0,17852764419157,17852764331937,17852766312417,17852766383018
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,238351,238351,4194304,256,0,0,8,24,337472,0x7ff8895c3f00,0x7ff888c26880,0,0,0,17852766395418,17852766312417,17852768250018,17852768319691
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,238351,238351,4194304,256,0,0,8,24,0,0x7ff8895c3d80,0x7ff888c268c0,0,0,0,17852768331360,17852768250018,17852771863459,17852771934051
1 Index KernelName gpu-id queue-id queue-index pid tid grd wgr lds scr vgpr sgpr fbar sig obj SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES DispatchNs BeginNs EndNs CompleteNs
2 0 __amd_rocclr_fillBufferAligned.kd 0 0 0 238351 238351 33554432 256 0 0 4 32 4160 0x0 0x7ff888c04280 0 0 0 17852547584485 17851838027568 17852691164011 17852691281181
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 238351 238351 32768 256 0 0 12 24 13888 0x0 0x7ff888c23f80 0 0 0 17852696444493 17852691164011 17852696572335 17852696576630
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 5 238351 238351 4194304 256 0 0 12 24 14336 0x7ff88bbf2380 0x7ff888c23fc0 0 0 0 17852696612159 17852696572335 17852696936336 17852696938901
5 3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 8 238351 238351 4194304 256 0 0 16 24 15040 0x7ff88bbf2200 0x7ff888c24000 0 0 0 17852696975310 17852696936336 17852697339696 17852697341881
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 11 238351 238351 4194304 256 0 0 16 24 15488 0x7ff88bbf2080 0x7ff888c24040 0 0 0 17852697374780 17852697339696 17852697731856 17852697734031
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 14 238351 238351 4194304 256 0 0 12 24 15936 0x7ff8895c3f00 0x7ff888c24080 0 0 0 17852697767750 17852697731856 17852698036497 17852698038724
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 17 238351 238351 4194304 256 0 0 12 24 16384 0x7ff8895c3d80 0x7ff888c240c0 0 0 0 17852698071613 17852698036497 17852698369937 17852698372295
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 20 238351 238351 4194304 256 0 0 12 24 17088 0x7ff8895c3c00 0x7ff888c24100 0 0 0 17852698416344 17852698369937 17852698676817 17852698679058
10 8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 23 238351 238351 4194304 256 0 0 16 24 17792 0x7ff8895c3a80 0x7ff888c24140 0 0 0 17852698711897 17852698676817 17852699069297 17852699071448
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 26 238351 238351 4194304 256 0 0 16 24 18496 0x7ff8895c3900 0x7ff888c24180 0 0 0 17852699103227 17852699069297 17852699460338 17852699462438
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 29 238351 238351 4194304 256 0 0 16 24 19200 0x7ff8895c3780 0x7ff888c241c0 0 0 0 17852699493987 17852699460338 17852699775858 17852699778060
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 32 238351 238351 4194304 256 0 0 16 24 19904 0x7ff8895c3600 0x7ff888c24200 0 0 0 17852699811880 17852699775858 17852700079858 17852700082053
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 35 238351 238351 4194304 256 0 0 12 24 20608 0x7ff88bbf2480 0x7ff888c24240 0 0 0 17852700121632 17852700079858 17852700381299 17852700383605
15 13 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 38 238351 238351 4194304 256 0 0 16 24 21312 0x7ff88bbf2300 0x7ff888c24280 0 0 0 17852700416035 17852700381299 17852700771219 17852700773606
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 41 238351 238351 4194304 256 0 0 16 24 22016 0x7ff88bbf2180 0x7ff888c242c0 0 0 0 17852700806585 17852700771219 17852701160019 17852701162216
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 44 238351 238351 4194304 256 0 0 16 24 22720 0x7ff88bbf2000 0x7ff888c24300 0 0 0 17852701194595 17852701160019 17852701463540 17852701465598
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 47 238351 238351 4194304 256 0 0 12 24 23424 0x7ff8895c3e80 0x7ff888c24340 0 0 0 17852701497488 17852701463540 17852701764020 17852701766161
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 50 238351 238351 4194304 256 0 0 12 24 24128 0x7ff8895c3d00 0x7ff888c24380 0 0 0 17852701805360 17852701764020 17852702066100 17852702068263
20 18 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 53 238351 238351 4194304 256 0 0 16 24 24832 0x7ff8895c3b80 0x7ff888c243c0 0 0 0 17852702100643 17852702066100 17852702483061 17852702485313
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 56 238351 238351 4194304 256 0 0 16 24 25536 0x7ff8895c3a00 0x7ff888c24400 0 0 0 17852702517042 17852702483061 17852702873781 17852702876263
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 59 238351 238351 4194304 256 0 0 12 24 26240 0x7ff8895c3880 0x7ff888c24440 0 0 0 17852702907713 17852702873781 17852703202901 17852703204495
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 62 238351 238351 4194304 256 0 0 12 24 26944 0x7ff8895c3700 0x7ff888c24480 0 0 0 17852703236464 17852703202901 17852703480181 17852703481768
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 65 238351 238351 4194304 256 0 0 12 24 27648 0x7ff88bbf2580 0x7ff888c244c0 0 0 0 17852703520677 17852703480181 17852703754102 17852703755692
25 23 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 68 238351 238351 4194304 256 0 0 16 24 28608 0x7ff88bbf2400 0x7ff888c24500 0 0 0 17852703787681 17852703754102 17852704118422 17852704119943
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 71 238351 238351 4194304 256 0 0 16 24 29312 0x7ff88bbf2280 0x7ff888c24540 0 0 0 17852704151352 17852704118422 17852704479702 17852704481324
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 74 238351 238351 4194304 256 0 0 12 24 30016 0x7ff88bbf2100 0x7ff888c24580 0 0 0 17852704513273 17852704479702 17852704755543 17852704757237
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 77 238351 238351 4194304 256 0 0 8 24 30976 0x7ff8895c3f80 0x7ff888c245c0 0 0 0 17852704788706 17852704755543 17852705030423 17852705031860
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 80 238351 238351 4194304 256 0 0 12 24 31680 0x7ff8895c3e00 0x7ff888c24600 0 0 0 17852705070659 17852705030423 17852705307703 17852705309243
30 28 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 83 238351 238351 4194304 256 0 0 16 24 32640 0x7ff8895c3c80 0x7ff888c24640 0 0 0 17852705340412 17852705307703 17852705671863 17852705673524
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 86 238351 238351 4194304 256 0 0 12 24 33600 0x7ff8895c3b00 0x7ff888c24680 0 0 0 17852705705043 17852705671863 17852706035864 17852706037365
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 89 238351 238351 4194304 256 0 0 12 24 34560 0x7ff8895c3980 0x7ff888c246c0 0 0 0 17852706068534 17852706035864 17852706325464 17852706327138
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 92 238351 238351 4194304 256 0 0 8 24 35520 0x7ff8895c3800 0x7ff888c24700 0 0 0 17852706359087 17852706325464 17852706606264 17852706607841
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 95 238351 238351 4194304 256 0 0 12 24 36224 0x7ff8895c3680 0x7ff888c24740 0 0 0 17852706646370 17852706606264 17852706884824 17852706886384
35 33 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 98 238351 238351 4194304 256 0 0 12 24 37184 0x7ff88bbf2500 0x7ff888c24780 0 0 0 17852706918173 17852706884824 17852707251065 17852707252885
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 101 238351 238351 4194304 256 0 0 12 24 38144 0x7ff88bbf2380 0x7ff888c247c0 0 0 0 17852707284684 17852707251065 17852707615225 17852707616896
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 104 238351 238351 4194304 256 0 0 12 24 39104 0x7ff88bbf2200 0x7ff888c24800 0 0 0 17852707648045 17852707615225 17852707890105 17852707891729
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 107 238351 238351 4194304 256 0 0 8 24 40320 0x7ff88bbf2080 0x7ff888c24840 0 0 0 17852707923748 17852707890105 17852708166586 17852708168142
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 110 238351 238351 4194304 256 0 0 12 24 41280 0x7ff8895c3f00 0x7ff888c24880 0 0 0 17852708207321 17852708166586 17852708442906 17852708444485
40 38 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 113 238351 238351 4194304 256 0 0 12 24 42240 0x7ff8895c3d80 0x7ff888c248c0 0 0 0 17852708475035 17852708442906 17852708806266 17852708807837
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 116 238351 238351 4194304 256 0 0 12 24 43200 0x7ff8895c3c00 0x7ff888c24900 0 0 0 17852708841876 17852708806266 17852709173467 17852709175027
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 119 238351 238351 4194304 256 0 0 8 24 44160 0x7ff8895c3a80 0x7ff888c24940 0 0 0 17852709206277 17852709173467 17852709449627 17852709451181
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 122 238351 238351 4194304 256 0 0 12 24 45376 0x7ff8895c3900 0x7ff888c24980 0 0 0 17852709482650 17852709449627 17852709728507 17852709730184
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 125 238351 238351 4194304 256 0 0 12 24 46336 0x7ff8895c3780 0x7ff888c249c0 0 0 0 17852709769003 17852709728507 17852710007227 17852710008837
45 43 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 128 238351 238351 4194304 256 0 0 12 24 47552 0x7ff8895c3600 0x7ff888c24a00 0 0 0 17852710040166 17852710007227 17852710383548 17852710385288
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 131 238351 238351 4194304 256 0 0 12 24 48512 0x7ff88bbf2480 0x7ff888c24a40 0 0 0 17852710418027 17852710383548 17852710744348 17852710745959
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 134 238351 238351 4194304 256 0 0 8 24 49472 0x7ff88bbf2300 0x7ff888c24a80 0 0 0 17852710777528 17852710744348 17852711022108 17852711023662
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 137 238351 238351 4194304 256 0 0 12 24 50688 0x7ff88bbf2180 0x7ff888c24ac0 0 0 0 17852711055971 17852711022108 17852711304188 17852711305805
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 140 238351 238351 4194304 256 0 0 12 24 51648 0x7ff88bbf2000 0x7ff888c24b00 0 0 0 17852711344854 17852711304188 17852711596989 17852711598567
50 48 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 143 238351 238351 4194304 256 0 0 12 24 52864 0x7ff8895c3e80 0x7ff888c24b40 0 0 0 17852711631277 17852711596989 17852711961149 17852711962848
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 146 238351 238351 4194304 256 0 0 12 24 54080 0x7ff8895c3d00 0x7ff888c24b80 0 0 0 17852711994718 17852711961149 17852712327549 17852712329159
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 149 238351 238351 4194304 256 0 0 8 24 55296 0x7ff8895c3b80 0x7ff888c24bc0 0 0 0 17852712360458 17852712327549 17852712604990 17852712606592
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 152 238351 238351 4194304 256 0 0 12 24 56768 0x7ff8895c3a00 0x7ff888c24c00 0 0 0 17852712639062 17852712604990 17852712884670 17852712886435
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 155 238351 238351 4194304 256 0 0 12 24 57728 0x7ff8895c3880 0x7ff888c24c40 0 0 0 17852712924404 17852712884670 17852713165470 17852713167208
55 53 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 158 238351 238351 4194304 256 0 0 12 24 58944 0x7ff8895c3700 0x7ff888c24c80 0 0 0 17852713198898 17852713165470 17852713529470 17852713531039
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 161 238351 238351 4194304 256 0 0 12 24 60160 0x7ff88bbf2580 0x7ff888c24cc0 0 0 0 17852713563649 17852713529470 17852713890751 17852713892420
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 164 238351 238351 4194304 256 0 0 8 24 61376 0x7ff88bbf2400 0x7ff888c24d00 0 0 0 17852713925370 17852713890751 17852714168991 17852714170743
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 167 238351 238351 4194304 256 0 0 12 24 62848 0x7ff88bbf2280 0x7ff888c24d40 0 0 0 17852714203523 17852714168991 17852714452831 17852714454446
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 170 238351 238351 4194304 256 0 0 12 24 63808 0x7ff88bbf2100 0x7ff888c24d80 0 0 0 17852714493475 17852714452831 17852714730591 17852714732310
60 58 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 173 238351 238351 4194304 256 0 0 12 24 65024 0x7ff8895c3f80 0x7ff888c24dc0 0 0 0 17852714764259 17852714730591 17852715097952 17852715099550
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 176 238351 238351 4194304 256 0 0 12 24 66240 0x7ff8895c3e00 0x7ff888c24e00 0 0 0 17852715131050 17852715097952 17852715461792 17852715463411
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 179 238351 238351 4194304 256 0 0 8 24 67456 0x7ff8895c3c80 0x7ff888c24e40 0 0 0 17852715495341 17852715461792 17852715739392 17852715741084
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 182 238351 238351 4194304 256 0 0 12 24 68928 0x7ff8895c3b00 0x7ff888c24e80 0 0 0 17852715773124 17852715739392 17852716027073 17852716028717
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 185 238351 238351 4194304 256 0 0 12 24 70144 0x7ff8895c3980 0x7ff888c24ec0 0 0 0 17852716068486 17852716027073 17852716306273 17852716307960
65 63 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 188 238351 238351 4194304 256 0 0 12 24 71616 0x7ff8895c3800 0x7ff888c24f00 0 0 0 17852716339270 17852716306273 17852716670113 17852716671741
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 191 238351 238351 4194304 256 0 0 12 24 72832 0x7ff8895c3680 0x7ff888c24f40 0 0 0 17852716703121 17852716670113 17852717030914 17852717032592
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 194 238351 238351 4194304 256 0 0 8 24 74048 0x7ff88bbf2500 0x7ff888c24f80 0 0 0 17852717063472 17852717030914 17852717308194 17852717309915
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 197 238351 238351 4194304 256 0 0 12 24 75776 0x7ff88bbf2380 0x7ff888c24fc0 0 0 0 17852717341515 17852717308194 17852717598274 17852717599928
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 200 238351 238351 4194304 256 0 0 12 24 76992 0x7ff88bbf2200 0x7ff888c25000 0 0 0 17852717638877 17852717598274 17852717874434 17852717875971
70 68 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 203 238351 238351 4194304 256 0 0 12 24 78464 0x7ff88bbf2080 0x7ff888c25040 0 0 0 17852717908151 17852717874434 17852718242115 17852718243902
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 206 238351 238351 4194304 256 0 0 12 24 79936 0x7ff8895c3f00 0x7ff888c25080 0 0 0 17852718276721 17852718242115 17852718610275 17852718611863
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 209 238351 238351 4194304 256 0 0 8 24 81408 0x7ff8895c3d80 0x7ff888c250c0 0 0 0 17852718642982 17852718610275 17852718888355 17852718889966
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 212 238351 238351 4194304 256 0 0 12 24 83136 0x7ff8895c3c00 0x7ff888c25100 0 0 0 17852718921995 17852718888355 17852719182915 17852719184579
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 215 238351 238351 4194304 256 0 0 12 24 84352 0x7ff8895c3a80 0x7ff888c25140 0 0 0 17852719235378 17852719182915 17852719468836 17852719471082
75 73 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 218 238351 238351 4194304 256 0 0 12 24 85824 0x7ff8895c3900 0x7ff888c25180 0 0 0 17852719502231 17852719468836 17852719841796 17852719843403
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 221 238351 238351 4194304 256 0 0 12 24 87296 0x7ff8895c3780 0x7ff888c251c0 0 0 0 17852719875732 17852719841796 17852720205156 17852720206694
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 224 238351 238351 4194304 256 0 0 12 24 88768 0x7ff8895c3600 0x7ff888c25200 0 0 0 17852720237623 17852720205156 17852720485637 17852720487157
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 227 238351 238351 4194304 256 0 0 12 24 90752 0x7ff88bbf2480 0x7ff888c25240 0 0 0 17852720519426 17852720485637 17852720791237 17852720792699
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 230 238351 238351 4194304 256 0 0 12 24 91968 0x7ff88bbf2300 0x7ff888c25280 0 0 0 17852720831258 17852720791237 17852721075237 17852721076832
80 78 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 233 238351 238351 4194304 256 0 0 12 24 93440 0x7ff88bbf2180 0x7ff888c252c0 0 0 0 17852721109001 17852721075237 17852721437477 17852721439053
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 236 238351 238351 4194304 256 0 0 12 24 94912 0x7ff88bbf2000 0x7ff888c25300 0 0 0 17852721471482 17852721437477 17852721802598 17852721804134
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 239 238351 238351 4194304 256 0 0 12 24 96384 0x7ff8895c3e80 0x7ff888c25340 0 0 0 17852721835423 17852721802598 17852722083878 17852722085677
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 242 238351 238351 4194304 256 0 0 12 24 98368 0x7ff8895c3d00 0x7ff888c25380 0 0 0 17852722117666 17852722083878 17852722394278 17852722395829
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 245 238351 238351 4194304 256 0 0 12 24 99584 0x7ff8895c3b80 0x7ff888c253c0 0 0 0 17852722435088 17852722394278 17852722680359 17852722681982
85 83 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 248 238351 238351 4194304 256 0 0 12 24 101312 0x7ff8895c3a00 0x7ff888c25400 0 0 0 17852722713441 17852722680359 17852723043079 17852723044603
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 251 238351 238351 4194304 256 0 0 12 24 102784 0x7ff8895c3880 0x7ff888c25440 0 0 0 17852723076572 17852723043079 17852723405639 17852723407144
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 254 238351 238351 4194304 256 0 0 12 24 104256 0x7ff8895c3700 0x7ff888c25480 0 0 0 17852723438243 17852723405639 17852723683239 17852723685007
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 257 238351 238351 4194304 256 0 0 12 24 106240 0x7ff88bbf2580 0x7ff888c254c0 0 0 0 17852723715457 17852723683239 17852723995560 17852723997160
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 260 238351 238351 4194304 256 0 0 12 24 107712 0x7ff88bbf2400 0x7ff888c25500 0 0 0 17852724036629 17852723995560 17852724280840 17852724282463
90 88 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 263 238351 238351 4194304 256 0 0 16 24 109440 0x7ff88bbf2280 0x7ff888c25540 0 0 0 17852724316172 17852724280840 17852724642760 17852724644394
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 266 238351 238351 4194304 256 0 0 16 24 111168 0x7ff88bbf2100 0x7ff888c25580 0 0 0 17852724677643 17852724642760 17852725009481 17852725011105
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 269 238351 238351 4194304 256 0 0 8 24 112896 0x7ff8895c3f80 0x7ff888c255c0 0 0 0 17852725042374 17852725009481 17852725289481 17852725291098
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 272 238351 238351 4194304 256 0 0 12 24 115136 0x7ff8895c3e00 0x7ff888c25600 0 0 0 17852725322377 17852725289481 17852725611561 17852725613050
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 275 238351 238351 4194304 256 0 0 12 24 116608 0x7ff8895c3c80 0x7ff888c25640 0 0 0 17852725651419 17852725611561 17852725888361 17852725889983
95 93 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 278 238351 238351 4194304 256 0 0 16 24 118336 0x7ff8895c3b00 0x7ff888c25680 0 0 0 17852725921822 17852725888361 17852726253482 17852726255414
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 281 238351 238351 4194304 256 0 0 16 24 120064 0x7ff8895c3980 0x7ff888c256c0 0 0 0 17852726287623 17852726253482 17852726617482 17852726619115
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 284 238351 238351 4194304 256 0 0 12 24 121792 0x7ff8895c3800 0x7ff888c25700 0 0 0 17852726650804 17852726617482 17852726896522 17852726898098
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 287 238351 238351 4194304 256 0 0 12 24 124032 0x7ff8895c3680 0x7ff888c25740 0 0 0 17852726929667 17852726896522 17852727227403 17852727229120
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 290 238351 238351 4194304 256 0 0 12 24 125504 0x7ff88bbf2500 0x7ff888c25780 0 0 0 17852727267889 17852727227403 17852727511403 17852727512983
100 98 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 293 238351 238351 4194304 256 0 0 12 24 127488 0x7ff88bbf2380 0x7ff888c257c0 0 0 0 17852727544622 17852727511403 17852727872523 17852727874214
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 296 238351 238351 4194304 256 0 0 12 24 129216 0x7ff88bbf2200 0x7ff888c25800 0 0 0 17852727907013 17852727872523 17852728235724 17852728237265
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 299 238351 238351 4194304 256 0 0 12 24 130944 0x7ff88bbf2080 0x7ff888c25840 0 0 0 17852728269444 17852728235724 17852728517484 17852728519148
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 302 238351 238351 4194304 256 0 0 12 24 133440 0x7ff8895c3f00 0x7ff888c25880 0 0 0 17852728551127 17852728517484 17852728857804 17852728859459
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 305 238351 238351 4194304 256 0 0 12 24 134912 0x7ff8895c3d80 0x7ff888c258c0 0 0 0 17852728899498 17852728857804 17852729139564 17852729141132
105 103 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 308 238351 238351 4194304 256 0 0 12 24 136896 0x7ff8895c3c00 0x7ff888c25900 0 0 0 17852729172291 17852729139564 17852729503085 17852729504743
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 311 238351 238351 4194304 256 0 0 12 24 138880 0x7ff8895c3a80 0x7ff888c25940 0 0 0 17852729536092 17852729503085 17852729865485 17852729867124
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 314 238351 238351 4194304 256 0 0 12 24 140864 0x7ff8895c3900 0x7ff888c25980 0 0 0 17852729898743 17852729865485 17852730155885 17852730157467
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 317 238351 238351 4194304 256 0 0 12 24 143616 0x7ff8895c3780 0x7ff888c259c0 0 0 0 17852730190876 17852730155885 17852730525006 17852730526718
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 320 238351 238351 4194304 256 0 0 12 24 145344 0x7ff8895c3600 0x7ff888c25a00 0 0 0 17852730566577 17852730525006 17852730809646 17852730811381
110 108 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 323 238351 238351 4194304 256 0 0 12 24 147584 0x7ff88bbf2480 0x7ff888c25a40 0 0 0 17852730843010 17852730809646 17852731174126 17852731175882
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 326 238351 238351 4194304 256 0 0 12 24 149568 0x7ff88bbf2300 0x7ff888c25a80 0 0 0 17852731208061 17852731174126 17852731537327 17852731538893
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 329 238351 238351 4194304 256 0 0 12 24 151552 0x7ff88bbf2180 0x7ff888c25ac0 0 0 0 17852731570982 17852731537327 17852731833807 17852731835685
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 332 238351 238351 4194304 256 0 0 12 24 154304 0x7ff88bbf2000 0x7ff888c25b00 0 0 0 17852731867534 17852731833807 17852732204527 17852732206096
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 335 238351 238351 4194304 256 0 0 12 24 156288 0x7ff8895c3e80 0x7ff888c25b40 0 0 0 17852732245085 17852732204527 17852732490287 17852732491899
115 113 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 338 238351 238351 4194304 256 0 0 12 24 158784 0x7ff8895c3d00 0x7ff888c25b80 0 0 0 17852732523968 17852732490287 17852732856048 17852732857640
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 341 238351 238351 4194304 256 0 0 12 24 161024 0x7ff8895c3b80 0x7ff888c25bc0 0 0 0 17852732889679 17852732856048 17852733221648 17852733223301
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 344 238351 238351 4194304 256 0 0 12 24 163264 0x7ff8895c3a00 0x7ff888c25c00 0 0 0 17852733254330 17852733221648 17852733532368 17852733533913
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 347 238351 238351 4194304 256 0 0 12 24 166528 0x7ff8895c3880 0x7ff888c25c40 0 0 0 17852733565032 17852733532368 17852733921009 17852733941203
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 350 238351 238351 4194304 256 0 0 12 24 168512 0x7ff8895c3700 0x7ff888c25c80 0 0 0 17852733962372 17852733921009 17852734230929 17852734232796
120 118 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 353 238351 238351 4194304 256 0 0 12 24 171264 0x7ff88bbf2580 0x7ff888c25cc0 0 0 0 17852734265345 17852734230929 17852734609169 17852734610756
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 356 238351 238351 4194304 256 0 0 12 24 173760 0x7ff88bbf2400 0x7ff888c25d00 0 0 0 17852734643356 17852734609169 17852734977490 17852734979187
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 359 238351 238351 4194304 256 0 0 12 24 176256 0x7ff88bbf2280 0x7ff888c25d40 0 0 0 17852735011617 17852734977490 17852735296850 17852735298459
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 362 238351 238351 4194304 256 0 0 12 24 179776 0x7ff88bbf2100 0x7ff888c25d80 0 0 0 17852735330689 17852735296850 17852735711570 17852735757648
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 365 238351 238351 4194304 256 0 0 12 24 182272 0x7ff8895c3f80 0x7ff888c25dc0 0 0 0 17852735776978 17852735711570 17852736060851 17852736062501
125 123 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 368 238351 238351 4194304 256 0 0 12 24 185536 0x7ff8895c3e00 0x7ff888c25e00 0 0 0 17852736095700 17852736060851 17852736435731 17852736480820
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 371 238351 238351 4194304 256 0 0 12 24 188544 0x7ff8895c3c80 0x7ff888c25e40 0 0 0 17852736492510 17852736435731 17852736844051 17852736886710
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 374 238351 238351 4194304 256 0 0 12 24 191552 0x7ff8895c3b00 0x7ff888c25e80 0 0 0 17852736898080 17852736844051 17852737223732 17852737225292
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 377 238351 238351 4194304 256 0 0 12 24 195840 0x7ff8895c3980 0x7ff888c25ec0 0 0 0 17852737256371 17852737223732 17852737690612 17852737709180
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 380 238351 238351 4194304 256 0 0 12 24 198592 0x7ff8895c3800 0x7ff888c25f00 0 0 0 17852737731449 17852737690612 17852738033812 17852738035472
130 128 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 383 238351 238351 4194304 256 0 0 12 24 202368 0x7ff8895c3680 0x7ff888c25f40 0 0 0 17852738067181 17852738033812 17852738456693 17852738501100
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 386 238351 238351 4194304 256 0 0 12 24 205888 0x7ff88bbf2500 0x7ff888c25f80 0 0 0 17852738514830 17852738456693 17852738880533 17852738924380
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 389 238351 238351 4194304 256 0 0 12 24 209408 0x7ff88bbf2380 0x7ff888c25fc0 0 0 0 17852738935080 17852738880533 17852739282613 17852739284311
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 392 238351 238351 4194304 256 0 0 12 24 214464 0x7ff88bbf2200 0x7ff888c26000 0 0 0 17852739317490 17852739282613 17852739807414 17852739849997
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 395 238351 238351 4194304 256 0 0 12 24 217728 0x7ff88bbf2080 0x7ff888c26040 0 0 0 17852739870166 17852739807414 17852740189654 17852740191278
135 133 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 398 238351 238351 4194304 256 0 0 12 24 222016 0x7ff8895c3f00 0x7ff888c26080 0 0 0 17852740223318 17852740189654 17852740603735 17852740646387
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 401 238351 238351 4194304 256 0 0 12 24 226048 0x7ff8895c3d80 0x7ff888c260c0 0 0 0 17852740658167 17852740603735 17852741053975 17852741096566
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 404 238351 238351 4194304 256 0 0 12 24 230080 0x7ff8895c3c00 0x7ff888c26100 0 0 0 17852741108566 17852741053975 17852741477975 17852741520635
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 407 238351 238351 4194304 256 0 0 12 24 235904 0x7ff8895c3a80 0x7ff888c26140 0 0 0 17852741533345 17852741477975 17852742078136 17852742100261
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 410 238351 238351 4194304 256 0 0 12 24 239424 0x7ff8895c3900 0x7ff888c26180 0 0 0 17852742120520 17852742078136 17852742462616 17852742464122
140 138 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 413 238351 238351 4194304 256 0 0 12 24 244224 0x7ff8895c3780 0x7ff888c261c0 0 0 0 17852742495881 17852742462616 17852742899737 17852742943690
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 416 238351 238351 4194304 256 0 0 12 24 248768 0x7ff8895c3600 0x7ff888c26200 0 0 0 17852742956040 17852742899737 17852743360697 17852743403809
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 419 238351 238351 4194304 256 0 0 12 24 253312 0x7ff88bbf2480 0x7ff888c26240 0 0 0 17852743415308 17852743360697 17852743812697 17852743854887
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 422 238351 238351 4194304 256 0 0 8 24 255552 0x7ff88bbf2300 0x7ff888c26280 0 0 0 17852743866867 17852743812697 17852744476858 17852744519781
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 425 238351 238351 4194304 256 0 0 12 24 259840 0x7ff88bbf2180 0x7ff888c262c0 0 0 0 17852744539460 17852744476858 17852744921338 17852744964010
145 143 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 428 238351 238351 4194304 256 0 0 12 24 265664 0x7ff88bbf2000 0x7ff888c26300 0 0 0 17852744975050 17852744921338 17852745435899 17852745478337
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 431 238351 238351 4194304 256 0 0 12 24 271232 0x7ff8895c3e80 0x7ff888c26340 0 0 0 17852745489317 17852745435899 17852745954459 17852745972385
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 434 238351 238351 4194304 256 0 0 8 24 273216 0x7ff8895c3d00 0x7ff888c26380 0 0 0 17852745987614 17852745954459 17852746446940 17852746492852
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 437 238351 238351 4194304 256 0 0 8 24 275712 0x7ff8895c3b80 0x7ff888c263c0 0 0 0 17852746505581 17852746446940 17852747219101 17852747263173
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 440 238351 238351 4194304 256 0 0 12 24 280768 0x7ff8895c3a00 0x7ff888c26400 0 0 0 17852747283402 17852747219101 17852747705501 17852747747881
150 148 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 443 238351 238351 4194304 256 0 0 12 24 287616 0x7ff8895c3880 0x7ff888c26440 0 0 0 17852747758960 17852747705501 17852748268861 17852748310857
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 446 238351 238351 4194304 256 0 0 12 24 294208 0x7ff8895c3700 0x7ff888c26480 0 0 0 17852748322856 17852748268861 17852748832222 17852748874753
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 449 238351 238351 4194304 256 0 0 8 24 296960 0x7ff88bbf2580 0x7ff888c264c0 0 0 0 17852748886262 17852748832222 17852749394782 17852749436889
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 452 238351 238351 4194304 256 0 0 8 24 299968 0x7ff88bbf2400 0x7ff888c26500 0 0 0 17852749448568 17852749394782 17852750264863 17852750309257
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 455 238351 238351 4194304 256 0 0 8 24 302720 0x7ff88bbf2280 0x7ff888c26540 0 0 0 17852750329727 17852750264863 17852750929824 17852750974811
155 153 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 458 238351 238351 4194304 256 0 0 12 24 305472 0x7ff88bbf2100 0x7ff888c26580 0 0 0 17852750986220 17852750929824 17852751608704 17852751652374
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 461 238351 238351 4194304 256 0 0 12 24 308224 0x7ff8895c3f80 0x7ff888c265c0 0 0 0 17852751663494 17852751608704 17852752288225 17852752330757
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 464 238351 238351 4194304 256 0 0 8 24 310976 0x7ff8895c3e00 0x7ff888c26600 0 0 0 17852752342157 17852752288225 17852752950306 17852752993191
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 467 238351 238351 4194304 256 0 0 8 24 313216 0x7ff8895c3c80 0x7ff888c26640 0 0 0 17852753004871 17852752950014 17852754036414 17852754087294
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 470 238351 238351 4194304 256 0 0 8 24 315968 0x7ff8895c3b00 0x7ff888c26680 0 0 0 17852754107573 17852754036414 17852755116734 17852755164557
160 158 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 473 238351 238351 4194304 256 0 0 12 24 318720 0x7ff8895c3980 0x7ff888c266c0 0 0 0 17852755175877 17852755116734 17852756216414 17852756283989
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 476 238351 238351 4194304 256 0 0 12 24 321472 0x7ff8895c3800 0x7ff888c26700 0 0 0 17852756296649 17852756216414 17852757347295 17852757413671
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 479 238351 238351 4194304 256 0 0 8 24 324224 0x7ff8895c3680 0x7ff888c26740 0 0 0 17852757426311 17852757347295 17852758455615 17852758522824
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 482 238351 238351 4194304 256 0 0 8 24 326464 0x7ff88bbf2500 0x7ff888c26780 0 0 0 17852758535493 17852758455615 17852760413696 17852760480545
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 485 238351 238351 4194304 256 0 0 8 24 329216 0x7ff88bbf2380 0x7ff888c267c0 0 0 0 17852760500774 17852760413696 17852762329856 17852762401667
165 163 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 488 238351 238351 4194304 256 0 0 12 24 331968 0x7ff88bbf2200 0x7ff888c26800 0 0 0 17852762414887 17852762329856 17852764331937 17852764406557
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 491 238351 238351 4194304 256 0 0 12 24 334720 0x7ff88bbf2080 0x7ff888c26840 0 0 0 17852764419157 17852764331937 17852766312417 17852766383018
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 494 238351 238351 4194304 256 0 0 8 24 337472 0x7ff8895c3f00 0x7ff888c26880 0 0 0 17852766395418 17852766312417 17852768250018 17852768319691
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 497 238351 238351 4194304 256 0 0 8 24 0 0x7ff8895c3d80 0x7ff888c268c0 0 0 0 17852768331360 17852768250018 17852771863459 17852771934051
+168
Voir le fichier
@@ -0,0 +1,168 @@
Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,BeginNs,EndNs,CompleteNs
0,"__amd_rocclr_fillBufferAligned.kd",0,0,0,236281,236281,33554432,256,0,0,4,32,4160,0x0,0x7f45e2204280,3670016,2905706,325081704,17832236843728,17803198665120,17832381629870,17832381744199
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,236281,236281,32768,256,0,0,12,24,13888,0x0,0x7f45e2223f80,512,96664,10851288,17832386900391,17832381629870,17832387026519,17832387030968
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,236281,236281,4194304,256,0,0,12,24,14336,0x7f45e517a380,0x7f45e2223fc0,65536,639926,71704992,17832387064037,17832387026519,17832387402360,17832387404639
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,236281,236281,4194304,256,0,0,16,24,15040,0x7f45e517a200,0x7f45e2224000,65536,663120,74284736,17832387441058,17832387402360,17832387801401,17832387803559
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,236281,236281,4194304,256,0,0,16,24,15488,0x7f45e517a080,0x7f45e2224040,65536,655382,73467248,17832387836288,17832387801401,17832388189241,17832388191179
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,236281,236281,4194304,256,0,0,12,24,15936,0x7f45e2b1bf00,0x7f45e2224080,65536,670706,75144576,17832388224148,17832388189241,17832388486682,17832388488802
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,236281,236281,4194304,256,0,0,12,24,16384,0x7f45e2b1bd80,0x7f45e22240c0,65536,633498,70989896,17832388520711,17832388486682,17832388784443,17832388786445
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,236281,236281,4194304,256,0,0,12,24,17088,0x7f45e2b1bc00,0x7f45e2224100,131072,682790,76349744,17832388829873,17832388784443,17832389085883,17832389087897
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,236281,236281,4194304,256,0,0,16,24,17792,0x7f45e2b1ba80,0x7f45e2224140,131072,702258,78734048,17832389118956,17832389085883,17832389470044,17832389472077
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,236281,236281,4194304,256,0,0,16,24,18496,0x7f45e2b1b900,0x7f45e2224180,65536,662922,74237584,17832389504707,17832389470044,17832389854525,17832389856588
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,236281,236281,4194304,256,0,0,16,24,19200,0x7f45e2b1b780,0x7f45e22241c0,131072,702944,78662512,17832389887017,17832389854525,17832390165245,17832390167590
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,236281,236281,4194304,256,0,0,16,24,19904,0x7f45e2b1b600,0x7f45e2224200,131072,698592,78249728,17832390198889,17832390165245,17832390471646,17832390473623
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,236281,236281,4194304,256,0,0,12,24,20608,0x7f45e517a480,0x7f45e2224240,131072,699922,78366656,17832390513972,17832390471646,17832390771166,17832390773245
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,236281,236281,4194304,256,0,0,16,24,21312,0x7f45e517a300,0x7f45e2224280,131072,697276,78078456,17832390805924,17832390771166,17832391153567,17832391155576
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,236281,236281,4194304,256,0,0,16,24,22016,0x7f45e517a180,0x7f45e22242c0,65536,671700,75200016,17832391187125,17832391153567,17832391540928,17832391542376
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,236281,236281,4194304,256,0,0,16,24,22720,0x7f45e517a000,0x7f45e2224300,131072,717992,80318352,17832391573205,17832391540928,17832391812928,17832391814339
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,236281,236281,4194304,256,0,0,12,24,23424,0x7f45e2b1be80,0x7f45e2224340,131072,697818,78152560,17832391845858,17832391812928,17832392080929,17832392082433
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,236281,236281,4194304,256,0,0,12,24,24128,0x7f45e2b1bd00,0x7f45e2224380,131072,696712,78052840,17832392120672,17832392080929,17832392351169,17832392352656
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,236281,236281,4194304,256,0,0,16,24,24832,0x7f45e2b1bb80,0x7f45e22243c0,131072,703960,78811040,17832392384785,17832392351169,17832392707170,17832392708527
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,236281,236281,4194304,256,0,0,16,24,25536,0x7f45e2b1ba00,0x7f45e2224400,65536,627350,70207160,17832392739226,17832392707170,17832393068610,17832393070078
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,236281,236281,4194304,256,0,0,12,24,26240,0x7f45e2b1b880,0x7f45e2224440,131072,705208,78953168,17832393101637,17832393068610,17832393338211,17832393339751
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,236281,236281,4194304,256,0,0,12,24,26944,0x7f45e2b1b700,0x7f45e2224480,131072,700642,78443288,17832393370981,17832393338211,17832393606371,17832393607955
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,236281,236281,4194304,256,0,0,12,24,27648,0x7f45e517a580,0x7f45e22244c0,131072,680574,76153088,17832393646754,17832393606371,17832393874692,17832393876138
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,236281,236281,4194304,256,0,0,16,24,28608,0x7f45e517a400,0x7f45e2224500,131072,698066,78128680,17832393908427,17832393874692,17832394231173,17832394232719
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,236281,236281,4194304,256,0,0,16,24,29312,0x7f45e517a280,0x7f45e2224540,65536,676560,75754120,17832394265568,17832394231173,17832394590853,17832394592260
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,236281,236281,4194304,256,0,0,12,24,30016,0x7f45e517a100,0x7f45e2224580,131072,665052,74494800,17832394623679,17832394590853,17832394868134,17832394869783
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,236281,236281,4194304,256,0,0,8,24,30976,0x7f45e2b1bf80,0x7f45e22245c0,131072,662312,74088520,17832394901143,17832394868134,17832395136934,17832395138407
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,236281,236281,4194304,256,0,0,12,24,31680,0x7f45e2b1be00,0x7f45e2224600,131072,693582,77663792,17832395177386,17832395136934,17832395409415,17832395411120
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,236281,236281,4194304,256,0,0,16,24,32640,0x7f45e2b1bc80,0x7f45e2224640,131072,655674,73523104,17832395443299,17832395409415,17832395769415,17832395770881
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,236281,236281,4194304,256,0,0,12,24,33600,0x7f45e2b1bb00,0x7f45e2224680,65536,651942,73037144,17832395802430,17832395769415,17832396129576,17832396130962
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,236281,236281,4194304,256,0,0,12,24,34560,0x7f45e2b1b980,0x7f45e22246c0,131072,697390,78190624,17832396162821,17832396129576,17832396399017,17832396400575
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,236281,236281,4194304,256,0,0,8,24,35520,0x7f45e2b1b800,0x7f45e2224700,131072,705040,79031632,17832396431605,17832396399017,17832396669097,17832396670499
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,236281,236281,4194304,256,0,0,12,24,36224,0x7f45e2b1b680,0x7f45e2224740,131072,702546,78684376,17832396708378,17832396669097,17832396940938,17832396942292
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,236281,236281,4194304,256,0,0,12,24,37184,0x7f45e517a500,0x7f45e2224780,131072,700556,78359944,17832396974431,17832396940938,17832397298858,17832397300373
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,236281,236281,4194304,256,0,0,12,24,38144,0x7f45e517a380,0x7f45e22247c0,65536,670702,75074704,17832397332152,17832397298858,17832397656299,17832397657764
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,236281,236281,4194304,256,0,0,12,24,39104,0x7f45e517a200,0x7f45e2224800,131072,702376,78607656,17832397689003,17832397656299,17832397926859,17832397928307
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,236281,236281,4194304,256,0,0,8,24,40320,0x7f45e517a080,0x7f45e2224840,131072,699218,78252712,17832397960087,17832397926859,17832398207180,17832398208690
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,236281,236281,4194304,256,0,0,12,24,41280,0x7f45e2b1bf00,0x7f45e2224880,131072,702102,78566800,17832398247609,17832398207180,17832398479980,17832398481434
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,236281,236281,4194304,256,0,0,12,24,42240,0x7f45e2b1bd80,0x7f45e22248c0,131072,700322,78462936,17832398512783,17832398479980,17832398840781,17832398842455
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,236281,236281,4194304,256,0,0,12,24,43200,0x7f45e2b1bc00,0x7f45e2224900,65536,678432,76016512,17832398873754,17832398840781,17832399198542,17832399199956
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,236281,236281,4194304,256,0,0,8,24,44160,0x7f45e2b1ba80,0x7f45e2224940,131072,704048,78850440,17832399231725,17832399198542,17832399474062,17832399475529
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,236281,236281,4194304,256,0,0,12,24,45376,0x7f45e2b1b900,0x7f45e2224980,131072,704294,78762488,17832399506378,17832399474062,17832399744143,17832399745442
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,236281,236281,4194304,256,0,0,12,24,46336,0x7f45e2b1b780,0x7f45e22249c0,131072,697140,78101344,17832399784061,17832399744143,17832400014383,17832400015876
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,236281,236281,4194304,256,0,0,12,24,47552,0x7f45e2b1b600,0x7f45e2224a00,131072,691764,77411472,17832400047205,17832400014383,17832400368784,17832400370137
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,236281,236281,4194304,256,0,0,12,24,48512,0x7f45e517a480,0x7f45e2224a40,65536,658738,73825056,17832400402316,17832400368784,17832400729425,17832400730838
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,236281,236281,4194304,256,0,0,8,24,49472,0x7f45e517a300,0x7f45e2224a80,131072,656782,73609296,17832400762547,17832400729425,17832401000945,17832401002361
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,236281,236281,4194304,256,0,0,12,24,50688,0x7f45e517a180,0x7f45e2224ac0,131072,661124,73973224,17832401033580,17832401000945,17832401268146,17832401269644
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,236281,236281,4194304,256,0,0,12,24,51648,0x7f45e517a000,0x7f45e2224b00,131072,684772,76598464,17832401308053,17832401268146,17832401548306,17832401549867
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,236281,236281,4194304,256,0,0,12,24,52864,0x7f45e2b1be80,0x7f45e2224b40,131072,697314,78128704,17832401581147,17832401548306,17832401907827,17832401909338
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,236281,236281,4194304,256,0,0,12,24,54080,0x7f45e2b1bd00,0x7f45e2224b80,65536,669406,75005032,17832401940558,17832401907827,17832402263187,17832402264740
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,236281,236281,4194304,256,0,0,8,24,55296,0x7f45e2b1bb80,0x7f45e2224bc0,131072,700766,78516768,17832402296189,17832402263187,17832402535028,17832402536433
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,236281,236281,4194304,256,0,0,12,24,56768,0x7f45e2b1ba00,0x7f45e2224c00,131072,697972,78177560,17832402567832,17832402535028,17832402805428,17832402806846
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,236281,236281,4194304,256,0,0,12,24,57728,0x7f45e2b1b880,0x7f45e2224c40,131072,700048,78487152,17832402845555,17832402805428,17832403074549,17832403076009
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,236281,236281,4194304,256,0,0,12,24,58944,0x7f45e2b1b700,0x7f45e2224c80,131072,688204,77079128,17832403107349,17832403074549,17832403429910,17832403431351
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,236281,236281,4194304,256,0,0,12,24,60160,0x7f45e517a580,0x7f45e2224cc0,65536,671532,75179760,17832403463430,17832403429910,17832403788470,17832403789782
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,236281,236281,4194304,256,0,0,8,24,61376,0x7f45e517a400,0x7f45e2224d00,131072,698470,78218528,17832403821291,17832403788470,17832404062391,17832404063835
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,236281,236281,4194304,256,0,0,12,24,62848,0x7f45e517a280,0x7f45e2224d40,131072,719656,80602296,17832404096124,17832404062391,17832404342871,17832404344338
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,236281,236281,4194304,256,0,0,12,24,63808,0x7f45e517a100,0x7f45e2224d80,131072,699666,78335584,17832404383487,17832404342871,17832404613432,17832404614811
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,236281,236281,4194304,256,0,0,12,24,65024,0x7f45e2b1bf80,0x7f45e2224dc0,131072,670210,75060888,17832404646430,17832404613432,17832404968153,17832404969772
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,236281,236281,4194304,256,0,0,12,24,66240,0x7f45e2b1be00,0x7f45e2224e00,65536,633208,71027776,17832405001072,17832404968153,17832405322393,17832405323704
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,236281,236281,4194304,256,0,0,8,24,67456,0x7f45e2b1bc80,0x7f45e2224e40,131072,707008,79154256,17832405354693,17832405322393,17832405595354,17832405596747
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,236281,236281,4194304,256,0,0,12,24,68928,0x7f45e2b1bb00,0x7f45e2224e80,131072,697218,78137600,17832405628186,17832405595354,17832405873754,17832405875160
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,236281,236281,4194304,256,0,0,12,24,70144,0x7f45e2b1b980,0x7f45e2224ec0,131072,658308,73724672,17832405914139,17832405873754,17832406146555,17832406148433
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,236281,236281,4194304,256,0,0,12,24,71616,0x7f45e2b1b800,0x7f45e2224f00,131072,701386,78527344,17832406179992,17832406146555,17832406507515,17832406508934
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,236281,236281,4194304,256,0,0,12,24,72832,0x7f45e2b1b680,0x7f45e2224f40,65536,699622,78401520,17832406541013,17832406507515,17832406867356,17832406868765
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,236281,236281,4194304,256,0,0,8,24,74048,0x7f45e517a500,0x7f45e2224f80,131072,671958,75210128,17832406900764,17832406867356,17832407143517,17832407144948
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,236281,236281,4194304,256,0,0,12,24,75776,0x7f45e517a380,0x7f45e2224fc0,131072,672706,75381112,17832407176878,17832407143517,17832407432797,17832407434251
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,236281,236281,4194304,256,0,0,12,24,76992,0x7f45e517a200,0x7f45e2225000,131072,696606,78217128,17832407473750,17832407432797,17832407701278,17832407702625
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,236281,236281,4194304,256,0,0,12,24,78464,0x7f45e517a080,0x7f45e2225040,131072,708204,79429472,17832407734074,17832407701278,17832408057758,17832408059176
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,236281,236281,4194304,256,0,0,12,24,79936,0x7f45e2b1bf00,0x7f45e2225080,65536,661894,74152040,17832408090825,17832408057758,17832408412799,17832408414247
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,236281,236281,4194304,256,0,0,8,24,81408,0x7f45e2b1bd80,0x7f45e22250c0,131072,702324,78672392,17832408445166,17832408412799,17832408681919,17832408683310
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,236281,236281,4194304,256,0,0,12,24,83136,0x7f45e2b1bc00,0x7f45e2225100,131072,703198,78825248,17832408714829,17832408681919,17832408971200,17832408972643
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,236281,236281,4194304,256,0,0,12,24,84352,0x7f45e2b1ba80,0x7f45e2225140,131072,699814,78254928,17832409022692,17832408971200,17832409251040,17832409253036
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,236281,236281,4194304,256,0,0,12,24,85824,0x7f45e2b1b900,0x7f45e2225180,131072,698260,78216224,17832409284085,17832409251040,17832409610241,17832409611667
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,236281,236281,4194304,256,0,0,12,24,87296,0x7f45e2b1b780,0x7f45e22251c0,65536,663758,74336688,17832409642866,17832409610241,17832409971362,17832409972698
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,236281,236281,4194304,256,0,0,12,24,88768,0x7f45e2b1b600,0x7f45e2225200,131072,694200,77848640,17832410003777,17832409971362,17832410252802,17832410254361
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,236281,236281,4194304,256,0,0,12,24,90752,0x7f45e517a480,0x7f45e2225240,131072,704834,78911016,17832410286130,17832410252802,17832410551683,17832410553104
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,236281,236281,4194304,256,0,0,12,24,91968,0x7f45e517a300,0x7f45e2225280,131072,696928,78035104,17832410592273,17832410551683,17832410821763,17832410823297
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,236281,236281,4194304,256,0,0,12,24,93440,0x7f45e517a180,0x7f45e22252c0,131072,696032,78057056,17832410854646,17832410821763,17832411183844,17832411185188
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,236281,236281,4194304,256,0,0,12,24,94912,0x7f45e517a000,0x7f45e2225300,65536,660730,74005000,17832411216967,17832411183844,17832411540005,17832411541479
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,236281,236281,4194304,256,0,0,12,24,96384,0x7f45e2b1be80,0x7f45e2225340,131072,701146,78404240,17832411573128,17832411540005,17832411810245,17832411811662
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,236281,236281,4194304,256,0,0,12,24,98368,0x7f45e2b1bd00,0x7f45e2225380,131072,703188,78765024,17832411843102,17832411810245,17832412111046,17832412112465
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,236281,236281,4194304,256,0,0,12,24,99584,0x7f45e2b1bb80,0x7f45e22253c0,131072,709754,79435024,17832412151434,17832412111046,17832412380646,17832412382098
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,236281,236281,4194304,256,0,0,12,24,101312,0x7f45e2b1ba00,0x7f45e2225400,131072,658220,73796752,17832412413128,17832412380646,17832412737927,17832412739229
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,236281,236281,4194304,256,0,0,12,24,102784,0x7f45e2b1b880,0x7f45e2225440,65536,668226,74799216,17832412770779,17832412737927,17832413094088,17832413095561
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,236281,236281,4194304,256,0,0,12,24,104256,0x7f45e2b1b700,0x7f45e2225480,131072,699192,78287464,17832413126350,17832413094088,17832413365928,17832413367344
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,236281,236281,4194304,256,0,0,12,24,106240,0x7f45e517a580,0x7f45e22254c0,131072,664510,74391096,17832413398753,17832413365928,17832413681769,17832413683106
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,236281,236281,4194304,256,0,0,12,24,107712,0x7f45e517a400,0x7f45e2225500,131072,661860,74059304,17832413722855,17832413681769,17832413960329,17832413961969
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,236281,236281,4194304,256,0,0,16,24,109440,0x7f45e517a280,0x7f45e2225540,131072,737226,82573104,17832413994028,17832413960329,17832414330890,17832414332460
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,236281,236281,4194304,256,0,0,16,24,111168,0x7f45e517a100,0x7f45e2225580,65536,649046,72669000,17832414364689,17832414330890,17832414688490,17832414689831
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,236281,236281,4194304,256,0,0,8,24,112896,0x7f45e2b1bf80,0x7f45e22255c0,131072,700704,78428320,17832414720670,17832414688490,17832414958891,17832414960154
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,236281,236281,4194304,256,0,0,12,24,115136,0x7f45e2b1be00,0x7f45e2225600,131072,698686,78251168,17832414991923,17832414958891,17832415269932,17832415271487
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,236281,236281,4194304,256,0,0,12,24,116608,0x7f45e2b1bc80,0x7f45e2225640,131072,710916,79668896,17832415310446,17832415269932,17832415545452,17832415546950
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,236281,236281,4194304,256,0,0,16,24,118336,0x7f45e2b1bb00,0x7f45e2225680,131072,697310,78148408,17832415578609,17832415545452,17832415904493,17832415905951
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,236281,236281,4194304,256,0,0,16,24,120064,0x7f45e2b1b980,0x7f45e22256c0,65536,661938,74012344,17832415937590,17832415904493,17832416259213,17832416260682
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,236281,236281,4194304,256,0,0,12,24,121792,0x7f45e2b1b800,0x7f45e2225700,131072,692126,77552648,17832416291961,17832416259213,17832416530734,17832416532145
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,236281,236281,4194304,256,0,0,12,24,124032,0x7f45e2b1b680,0x7f45e2225740,131072,698988,78259728,17832416563474,17832416530734,17832416860815,17832416862117
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,236281,236281,4194304,256,0,0,12,24,125504,0x7f45e517a500,0x7f45e2225780,131072,702876,78705712,17832416901386,17832416860815,17832417138575,17832417139930
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,236281,236281,4194304,256,0,0,12,24,127488,0x7f45e517a380,0x7f45e22257c0,131072,693560,77710752,17832417171159,17832417138575,17832417493776,17832417495141
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,236281,236281,4194304,256,0,0,12,24,129216,0x7f45e517a200,0x7f45e2225800,65536,662746,74090080,17832417526740,17832417493776,17832417851056,17832417852392
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,236281,236281,4194304,256,0,0,12,24,130944,0x7f45e517a080,0x7f45e2225840,131072,661518,74056760,17832417884092,17832417851056,17832418128657,17832418130245
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,236281,236281,4194304,256,0,0,12,24,133440,0x7f45e2b1bf00,0x7f45e2225880,131072,653794,73269240,17832418161545,17832418128657,17832418465617,17832418467077
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,236281,236281,4194304,256,0,0,12,24,134912,0x7f45e2b1bd80,0x7f45e22258c0,131072,1023684,114753968,17832418506686,17832418465617,17832418740658,17832418742170
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,236281,236281,4194304,256,0,0,12,24,136896,0x7f45e2b1bc00,0x7f45e2225900,131072,671298,75085032,17832418772820,17832418740658,17832419097139,17832419098551
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,236281,236281,4194304,256,0,0,12,24,138880,0x7f45e2b1ba80,0x7f45e2225940,65536,666606,74689200,17832419130061,17832419097139,17832419452179,17832419453583
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,236281,236281,4194304,256,0,0,12,24,140864,0x7f45e2b1b900,0x7f45e2225980,131072,710322,79534256,17832419484652,17832419452179,17832419735860,17832419737316
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,236281,236281,4194304,256,0,0,12,24,143616,0x7f45e2b1b780,0x7f45e22259c0,131072,736312,82503920,17832419768565,17832419735860,17832420079220,17832420080667
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,236281,236281,4194304,256,0,0,12,24,145344,0x7f45e2b1b600,0x7f45e2225a00,131072,1046700,117191448,17832420119236,17832420079220,17832420355061,17832420356480
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,236281,236281,4194304,256,0,0,12,24,147584,0x7f45e517a480,0x7f45e2225a40,131072,700300,78439888,17832420388939,17832420355061,17832420711382,17832420712981
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,236281,236281,4194304,256,0,0,12,24,149568,0x7f45e517a300,0x7f45e2225a80,65536,656180,73492696,17832420744921,17832420711382,17832421067382,17832421068772
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,236281,236281,4194304,256,0,0,12,24,151552,0x7f45e517a180,0x7f45e2225ac0,131072,661490,74168088,17832421100522,17832421067382,17832421352503,17832421354025
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,236281,236281,4194304,256,0,0,12,24,154304,0x7f45e517a000,0x7f45e2225b00,131072,661534,74112968,17832421385605,17832421352503,17832421716504,17832421717916
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,236281,236281,4194304,256,0,0,12,24,156288,0x7f45e2b1be80,0x7f45e2225b40,131072,1011892,113488728,17832421756865,17832421716504,17832421995064,17832421996489
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,236281,236281,4194304,256,0,0,12,24,158784,0x7f45e2b1bd00,0x7f45e2225b80,131072,696698,78101400,17832422028569,17832421995064,17832422368025,17832422369470
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,236281,236281,4194304,256,0,0,12,24,161024,0x7f45e2b1bb80,0x7f45e2225bc0,65536,656468,73595576,17832422401369,17832422368025,17832422728505,17832422729841
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,236281,236281,4194304,256,0,0,12,24,163264,0x7f45e2b1ba00,0x7f45e2225c00,131072,669734,74996912,17832422761010,17832422728505,17832423026106,17832423027444
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,236281,236281,4194304,256,0,0,12,24,166528,0x7f45e2b1b880,0x7f45e2225c40,131072,690138,77349608,17832423059093,17832423026106,17832423408987,17832423453883
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,236281,236281,4194304,256,0,0,12,24,168512,0x7f45e2b1b700,0x7f45e2225c80,131072,1046912,117125320,17832423472813,17832423408987,17832423731227,17832423732736
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,236281,236281,4194304,256,0,0,12,24,171264,0x7f45e517a580,0x7f45e2225cc0,131072,690800,77384592,17832423764206,17832423731227,17832424090748,17832424092097
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,236281,236281,4194304,256,0,0,12,24,173760,0x7f45e517a400,0x7f45e2225d00,65536,668714,74860336,17832424123747,17832424090748,17832424452029,17832424453478
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,236281,236281,4194304,256,0,0,12,24,176256,0x7f45e517a280,0x7f45e2225d40,131072,706034,79144240,17832424484928,17832424452029,17832424772349,17832424773870
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,236281,236281,4194304,256,0,0,12,24,179776,0x7f45e517a100,0x7f45e2225d80,131072,714758,80019096,17832424805450,17832424772349,17832425182430,17832425201200
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,236281,236281,4194304,256,0,0,12,24,182272,0x7f45e2b1bf80,0x7f45e2225dc0,131072,970250,108608768,17832425223149,17832425182430,17832425496191,17832425497572
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,236281,236281,4194304,256,0,0,12,24,185536,0x7f45e2b1be00,0x7f45e2225e00,131072,692588,77495152,17832425529002,17832425496191,17832425861951,17832425879323
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,236281,236281,4194304,256,0,0,12,24,188544,0x7f45e2b1bc80,0x7f45e2225e40,65536,661972,74144176,17832425894783,17832425861951,17832426234112,17832426255404
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,236281,236281,4194304,256,0,0,12,24,191552,0x7f45e2b1bb00,0x7f45e2225e80,131072,651518,72914568,17832426267983,17832426234112,17832426585633,17832426587085
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,236281,236281,4194304,256,0,0,12,24,195840,0x7f45e2b1b980,0x7f45e2225ec0,131072,671736,75207744,17832426618065,17832426585633,17832427044993,17832427089873
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,236281,236281,4194304,256,0,0,12,24,198592,0x7f45e2b1b800,0x7f45e2225f00,131072,1062116,119035424,17832427108662,17832427044993,17832427406114,17832427407555
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,236281,236281,4194304,256,0,0,12,24,202368,0x7f45e2b1b680,0x7f45e2225f40,131072,1014410,113677256,17832427438934,17832427406114,17832427792675,17832427838994
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,236281,236281,4194304,256,0,0,12,24,205888,0x7f45e517a500,0x7f45e2225f80,65536,657096,73695568,17832427849524,17832427792675,17832428213636,17832428255404
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,236281,236281,4194304,256,0,0,12,24,209408,0x7f45e517a380,0x7f45e2225fc0,131072,717844,80385384,17832428266174,17832428213636,17832428607556,17832428608975
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,236281,236281,4194304,256,0,0,12,24,214464,0x7f45e517a200,0x7f45e2226000,131072,673558,75636112,17832428640334,17832428607556,17832429119877,17832429137962
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,236281,236281,4194304,256,0,0,12,24,217728,0x7f45e517a080,0x7f45e2226040,131072,1041120,116628760,17832429161011,17832429119877,17832429472198,17832429473604
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,236281,236281,4194304,256,0,0,12,24,222016,0x7f45e2b1bf00,0x7f45e2226080,131072,1067732,119659152,17832429504273,17832429472198,17832429880679,17832429898823
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,236281,236281,4194304,256,0,0,12,24,226048,0x7f45e2b1bd80,0x7f45e22260c0,65536,658714,73729664,17832429916513,17832429880679,17832430292359,17832430311503
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,236281,236281,4194304,256,0,0,12,24,230080,0x7f45e2b1bc00,0x7f45e2226100,131072,687526,77019512,17832430325033,17832430292359,17832430692680,17832430710793
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,236281,236281,4194304,256,0,0,12,24,235904,0x7f45e2b1ba80,0x7f45e2226140,131072,666764,74771272,17832430725573,17832430692680,17832431260201,17832431301548
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,236281,236281,4194304,256,0,0,12,24,239424,0x7f45e2b1b900,0x7f45e2226180,131072,1033082,115803352,17832431320018,17832431260201,17832431648682,17832431650150
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,236281,236281,4194304,256,0,0,12,24,244224,0x7f45e2b1b780,0x7f45e22261c0,131072,1018378,114085552,17832431681109,17832431648682,17832432079403,17832432098638
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,236281,236281,4194304,256,0,0,12,24,248768,0x7f45e2b1b600,0x7f45e2226200,65536,707324,79208912,17832432112608,17832432079403,17832432509483,17832432526118
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,236281,236281,4194304,256,0,0,12,24,253312,0x7f45e517a480,0x7f45e2226240,131072,686242,76860856,17832432542687,17832432509483,17832432925964,17832432942478
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,236281,236281,4194304,256,0,0,8,24,255552,0x7f45e517a300,0x7f45e2226280,131072,1038276,116262688,17832432959327,17832432925964,17832433558125,17832433575932
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,236281,236281,4194304,256,0,0,12,24,259840,0x7f45e517a180,0x7f45e22262c0,131072,1036858,116181864,17832433599221,17832433558125,17832433967406,17832433983822
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,236281,236281,4194304,256,0,0,12,24,265664,0x7f45e517a000,0x7f45e2226300,131072,987292,110725048,17832433999841,17832433967406,17832434454927,17832434474699
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,236281,236281,4194304,256,0,0,12,24,271232,0x7f45e2b1be80,0x7f45e2226340,65536,659696,73899072,17832434488319,17832434454927,17832434939088,17832434981337
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,236281,236281,4194304,256,0,0,8,24,273216,0x7f45e2b1bd00,0x7f45e2226380,131072,1018800,114147848,17832434992227,17832434939088,17832435444529,17832435485844
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,236281,236281,4194304,256,0,0,8,24,275712,0x7f45e2b1bb80,0x7f45e22263c0,131072,1031960,115523272,17832435497234,17832435444529,17832436205010,17832436246585
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,236281,236281,4194304,256,0,0,12,24,280768,0x7f45e2b1ba00,0x7f45e2226400,131072,1016270,113811808,17832436266265,17832436205010,17832436678611,17832436698824
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,236281,236281,4194304,256,0,0,12,24,287616,0x7f45e2b1b880,0x7f45e2226440,131072,1032280,115828136,17832436711484,17832436678611,17832437211732,17832437228671
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,236281,236281,4194304,256,0,0,12,24,294208,0x7f45e2b1b700,0x7f45e2226480,65536,659624,74051544,17832437245851,17832437211732,17832437740053,17832437759248
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,236281,236281,4194304,256,0,0,8,24,296960,0x7f45e517a580,0x7f45e22264c0,131072,1005662,112551368,17832437773327,17832437740053,17832438273334,17832438291035
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,236281,236281,4194304,256,0,0,8,24,299968,0x7f45e517a400,0x7f45e2226500,131072,1031584,115645744,17832438307094,17832438273334,17832439116216,17832439157763
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,236281,236281,4194304,256,0,0,8,24,302720,0x7f45e517a280,0x7f45e2226540,131072,1061368,118941344,17832439177303,17832439116216,17832439767897,17832439809577
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,236281,236281,4194304,256,0,0,12,24,305472,0x7f45e517a100,0x7f45e2226580,131072,1036776,116154712,17832439821457,17832439767897,17832440436698,17832440477671
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,236281,236281,4194304,256,0,0,12,24,308224,0x7f45e2b1bf80,0x7f45e22265c0,65536,660196,73909144,17832440489810,17832440436698,17832441100379,17832441118625
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,236281,236281,4194304,256,0,0,8,24,310976,0x7f45e2b1be00,0x7f45e2226600,131072,1039478,116410952,17832441132995,17832441100379,17832441730941,17832441747759
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,236281,236281,4194304,256,0,0,8,24,313216,0x7f45e2b1bc80,0x7f45e2226640,131072,1041146,116504080,17832441763269,17832441730941,17832442784223,17832442804243
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,236281,236281,4194304,256,0,0,8,24,315968,0x7f45e2b1bb00,0x7f45e2226680,131072,1038534,116343664,17832442825283,17832442784223,17832443822464,17832443864977
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,236281,236281,4194304,256,0,0,12,24,318720,0x7f45e2b1b980,0x7f45e22266c0,131072,1034026,115706080,17832443875707,17832443822308,17832444914309,17832444984019
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,236281,236281,4194304,256,0,0,12,24,321472,0x7f45e2b1b800,0x7f45e2226700,65536,654370,73416832,17832444995709,17832444914309,17832446040870,17832446107291
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,236281,236281,4194304,256,0,0,8,24,324224,0x7f45e2b1b680,0x7f45e2226740,131072,1062574,118922864,17832446119451,17832446040870,17832447150632,17832447217504
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,236281,236281,4194304,256,0,0,8,24,326464,0x7f45e517a500,0x7f45e2226780,131072,1035830,116234136,17832447229853,17832447150632,17832449094475,17832449159095
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,236281,236281,4194304,256,0,0,8,24,329216,0x7f45e517a380,0x7f45e22267c0,131072,1037504,116109664,17832449179225,17832449094475,17832451003758,17832451072248
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,236281,236281,4194304,256,0,0,12,24,331968,0x7f45e517a200,0x7f45e2226800,131072,1028376,115273240,17832451084307,17832451003758,17832452981041,17832453045679
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,236281,236281,4194304,256,0,0,12,24,334720,0x7f45e517a080,0x7f45e2226840,65536,662726,74252864,17832453056848,17832452981041,17832454942484,17832455013900
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,236281,236281,4194304,256,0,0,8,24,337472,0x7f45e2b1bf00,0x7f45e2226880,131072,1040770,116756344,17832455025780,17832454942484,17832456880247,17832456947382
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,236281,236281,4194304,256,0,0,8,24,0,0x7f45e2b1bd80,0x7f45e22268c0,131072,1035694,116127016,17832456958722,17832456880247,17832460486492,17832460564112
1 Index KernelName gpu-id queue-id queue-index pid tid grd wgr lds scr vgpr sgpr fbar sig obj SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES DispatchNs BeginNs EndNs CompleteNs
2 0 __amd_rocclr_fillBufferAligned.kd 0 0 0 236281 236281 33554432 256 0 0 4 32 4160 0x0 0x7f45e2204280 3670016 2905706 325081704 17832236843728 17803198665120 17832381629870 17832381744199
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 236281 236281 32768 256 0 0 12 24 13888 0x0 0x7f45e2223f80 512 96664 10851288 17832386900391 17832381629870 17832387026519 17832387030968
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 5 236281 236281 4194304 256 0 0 12 24 14336 0x7f45e517a380 0x7f45e2223fc0 65536 639926 71704992 17832387064037 17832387026519 17832387402360 17832387404639
5 3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 8 236281 236281 4194304 256 0 0 16 24 15040 0x7f45e517a200 0x7f45e2224000 65536 663120 74284736 17832387441058 17832387402360 17832387801401 17832387803559
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 11 236281 236281 4194304 256 0 0 16 24 15488 0x7f45e517a080 0x7f45e2224040 65536 655382 73467248 17832387836288 17832387801401 17832388189241 17832388191179
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 14 236281 236281 4194304 256 0 0 12 24 15936 0x7f45e2b1bf00 0x7f45e2224080 65536 670706 75144576 17832388224148 17832388189241 17832388486682 17832388488802
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 17 236281 236281 4194304 256 0 0 12 24 16384 0x7f45e2b1bd80 0x7f45e22240c0 65536 633498 70989896 17832388520711 17832388486682 17832388784443 17832388786445
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 20 236281 236281 4194304 256 0 0 12 24 17088 0x7f45e2b1bc00 0x7f45e2224100 131072 682790 76349744 17832388829873 17832388784443 17832389085883 17832389087897
10 8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 23 236281 236281 4194304 256 0 0 16 24 17792 0x7f45e2b1ba80 0x7f45e2224140 131072 702258 78734048 17832389118956 17832389085883 17832389470044 17832389472077
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 26 236281 236281 4194304 256 0 0 16 24 18496 0x7f45e2b1b900 0x7f45e2224180 65536 662922 74237584 17832389504707 17832389470044 17832389854525 17832389856588
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 29 236281 236281 4194304 256 0 0 16 24 19200 0x7f45e2b1b780 0x7f45e22241c0 131072 702944 78662512 17832389887017 17832389854525 17832390165245 17832390167590
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 32 236281 236281 4194304 256 0 0 16 24 19904 0x7f45e2b1b600 0x7f45e2224200 131072 698592 78249728 17832390198889 17832390165245 17832390471646 17832390473623
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 35 236281 236281 4194304 256 0 0 12 24 20608 0x7f45e517a480 0x7f45e2224240 131072 699922 78366656 17832390513972 17832390471646 17832390771166 17832390773245
15 13 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 38 236281 236281 4194304 256 0 0 16 24 21312 0x7f45e517a300 0x7f45e2224280 131072 697276 78078456 17832390805924 17832390771166 17832391153567 17832391155576
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 41 236281 236281 4194304 256 0 0 16 24 22016 0x7f45e517a180 0x7f45e22242c0 65536 671700 75200016 17832391187125 17832391153567 17832391540928 17832391542376
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 44 236281 236281 4194304 256 0 0 16 24 22720 0x7f45e517a000 0x7f45e2224300 131072 717992 80318352 17832391573205 17832391540928 17832391812928 17832391814339
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 47 236281 236281 4194304 256 0 0 12 24 23424 0x7f45e2b1be80 0x7f45e2224340 131072 697818 78152560 17832391845858 17832391812928 17832392080929 17832392082433
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 50 236281 236281 4194304 256 0 0 12 24 24128 0x7f45e2b1bd00 0x7f45e2224380 131072 696712 78052840 17832392120672 17832392080929 17832392351169 17832392352656
20 18 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 53 236281 236281 4194304 256 0 0 16 24 24832 0x7f45e2b1bb80 0x7f45e22243c0 131072 703960 78811040 17832392384785 17832392351169 17832392707170 17832392708527
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 56 236281 236281 4194304 256 0 0 16 24 25536 0x7f45e2b1ba00 0x7f45e2224400 65536 627350 70207160 17832392739226 17832392707170 17832393068610 17832393070078
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 59 236281 236281 4194304 256 0 0 12 24 26240 0x7f45e2b1b880 0x7f45e2224440 131072 705208 78953168 17832393101637 17832393068610 17832393338211 17832393339751
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 62 236281 236281 4194304 256 0 0 12 24 26944 0x7f45e2b1b700 0x7f45e2224480 131072 700642 78443288 17832393370981 17832393338211 17832393606371 17832393607955
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 65 236281 236281 4194304 256 0 0 12 24 27648 0x7f45e517a580 0x7f45e22244c0 131072 680574 76153088 17832393646754 17832393606371 17832393874692 17832393876138
25 23 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 68 236281 236281 4194304 256 0 0 16 24 28608 0x7f45e517a400 0x7f45e2224500 131072 698066 78128680 17832393908427 17832393874692 17832394231173 17832394232719
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 71 236281 236281 4194304 256 0 0 16 24 29312 0x7f45e517a280 0x7f45e2224540 65536 676560 75754120 17832394265568 17832394231173 17832394590853 17832394592260
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 74 236281 236281 4194304 256 0 0 12 24 30016 0x7f45e517a100 0x7f45e2224580 131072 665052 74494800 17832394623679 17832394590853 17832394868134 17832394869783
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 77 236281 236281 4194304 256 0 0 8 24 30976 0x7f45e2b1bf80 0x7f45e22245c0 131072 662312 74088520 17832394901143 17832394868134 17832395136934 17832395138407
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 80 236281 236281 4194304 256 0 0 12 24 31680 0x7f45e2b1be00 0x7f45e2224600 131072 693582 77663792 17832395177386 17832395136934 17832395409415 17832395411120
30 28 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 83 236281 236281 4194304 256 0 0 16 24 32640 0x7f45e2b1bc80 0x7f45e2224640 131072 655674 73523104 17832395443299 17832395409415 17832395769415 17832395770881
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 86 236281 236281 4194304 256 0 0 12 24 33600 0x7f45e2b1bb00 0x7f45e2224680 65536 651942 73037144 17832395802430 17832395769415 17832396129576 17832396130962
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 89 236281 236281 4194304 256 0 0 12 24 34560 0x7f45e2b1b980 0x7f45e22246c0 131072 697390 78190624 17832396162821 17832396129576 17832396399017 17832396400575
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 92 236281 236281 4194304 256 0 0 8 24 35520 0x7f45e2b1b800 0x7f45e2224700 131072 705040 79031632 17832396431605 17832396399017 17832396669097 17832396670499
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 95 236281 236281 4194304 256 0 0 12 24 36224 0x7f45e2b1b680 0x7f45e2224740 131072 702546 78684376 17832396708378 17832396669097 17832396940938 17832396942292
35 33 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 98 236281 236281 4194304 256 0 0 12 24 37184 0x7f45e517a500 0x7f45e2224780 131072 700556 78359944 17832396974431 17832396940938 17832397298858 17832397300373
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 101 236281 236281 4194304 256 0 0 12 24 38144 0x7f45e517a380 0x7f45e22247c0 65536 670702 75074704 17832397332152 17832397298858 17832397656299 17832397657764
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 104 236281 236281 4194304 256 0 0 12 24 39104 0x7f45e517a200 0x7f45e2224800 131072 702376 78607656 17832397689003 17832397656299 17832397926859 17832397928307
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 107 236281 236281 4194304 256 0 0 8 24 40320 0x7f45e517a080 0x7f45e2224840 131072 699218 78252712 17832397960087 17832397926859 17832398207180 17832398208690
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 110 236281 236281 4194304 256 0 0 12 24 41280 0x7f45e2b1bf00 0x7f45e2224880 131072 702102 78566800 17832398247609 17832398207180 17832398479980 17832398481434
40 38 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 113 236281 236281 4194304 256 0 0 12 24 42240 0x7f45e2b1bd80 0x7f45e22248c0 131072 700322 78462936 17832398512783 17832398479980 17832398840781 17832398842455
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 116 236281 236281 4194304 256 0 0 12 24 43200 0x7f45e2b1bc00 0x7f45e2224900 65536 678432 76016512 17832398873754 17832398840781 17832399198542 17832399199956
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 119 236281 236281 4194304 256 0 0 8 24 44160 0x7f45e2b1ba80 0x7f45e2224940 131072 704048 78850440 17832399231725 17832399198542 17832399474062 17832399475529
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 122 236281 236281 4194304 256 0 0 12 24 45376 0x7f45e2b1b900 0x7f45e2224980 131072 704294 78762488 17832399506378 17832399474062 17832399744143 17832399745442
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 125 236281 236281 4194304 256 0 0 12 24 46336 0x7f45e2b1b780 0x7f45e22249c0 131072 697140 78101344 17832399784061 17832399744143 17832400014383 17832400015876
45 43 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 128 236281 236281 4194304 256 0 0 12 24 47552 0x7f45e2b1b600 0x7f45e2224a00 131072 691764 77411472 17832400047205 17832400014383 17832400368784 17832400370137
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 131 236281 236281 4194304 256 0 0 12 24 48512 0x7f45e517a480 0x7f45e2224a40 65536 658738 73825056 17832400402316 17832400368784 17832400729425 17832400730838
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 134 236281 236281 4194304 256 0 0 8 24 49472 0x7f45e517a300 0x7f45e2224a80 131072 656782 73609296 17832400762547 17832400729425 17832401000945 17832401002361
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 137 236281 236281 4194304 256 0 0 12 24 50688 0x7f45e517a180 0x7f45e2224ac0 131072 661124 73973224 17832401033580 17832401000945 17832401268146 17832401269644
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 140 236281 236281 4194304 256 0 0 12 24 51648 0x7f45e517a000 0x7f45e2224b00 131072 684772 76598464 17832401308053 17832401268146 17832401548306 17832401549867
50 48 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 143 236281 236281 4194304 256 0 0 12 24 52864 0x7f45e2b1be80 0x7f45e2224b40 131072 697314 78128704 17832401581147 17832401548306 17832401907827 17832401909338
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 146 236281 236281 4194304 256 0 0 12 24 54080 0x7f45e2b1bd00 0x7f45e2224b80 65536 669406 75005032 17832401940558 17832401907827 17832402263187 17832402264740
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 149 236281 236281 4194304 256 0 0 8 24 55296 0x7f45e2b1bb80 0x7f45e2224bc0 131072 700766 78516768 17832402296189 17832402263187 17832402535028 17832402536433
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 152 236281 236281 4194304 256 0 0 12 24 56768 0x7f45e2b1ba00 0x7f45e2224c00 131072 697972 78177560 17832402567832 17832402535028 17832402805428 17832402806846
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 155 236281 236281 4194304 256 0 0 12 24 57728 0x7f45e2b1b880 0x7f45e2224c40 131072 700048 78487152 17832402845555 17832402805428 17832403074549 17832403076009
55 53 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 158 236281 236281 4194304 256 0 0 12 24 58944 0x7f45e2b1b700 0x7f45e2224c80 131072 688204 77079128 17832403107349 17832403074549 17832403429910 17832403431351
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 161 236281 236281 4194304 256 0 0 12 24 60160 0x7f45e517a580 0x7f45e2224cc0 65536 671532 75179760 17832403463430 17832403429910 17832403788470 17832403789782
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 164 236281 236281 4194304 256 0 0 8 24 61376 0x7f45e517a400 0x7f45e2224d00 131072 698470 78218528 17832403821291 17832403788470 17832404062391 17832404063835
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 167 236281 236281 4194304 256 0 0 12 24 62848 0x7f45e517a280 0x7f45e2224d40 131072 719656 80602296 17832404096124 17832404062391 17832404342871 17832404344338
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 170 236281 236281 4194304 256 0 0 12 24 63808 0x7f45e517a100 0x7f45e2224d80 131072 699666 78335584 17832404383487 17832404342871 17832404613432 17832404614811
60 58 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 173 236281 236281 4194304 256 0 0 12 24 65024 0x7f45e2b1bf80 0x7f45e2224dc0 131072 670210 75060888 17832404646430 17832404613432 17832404968153 17832404969772
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 176 236281 236281 4194304 256 0 0 12 24 66240 0x7f45e2b1be00 0x7f45e2224e00 65536 633208 71027776 17832405001072 17832404968153 17832405322393 17832405323704
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 179 236281 236281 4194304 256 0 0 8 24 67456 0x7f45e2b1bc80 0x7f45e2224e40 131072 707008 79154256 17832405354693 17832405322393 17832405595354 17832405596747
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 182 236281 236281 4194304 256 0 0 12 24 68928 0x7f45e2b1bb00 0x7f45e2224e80 131072 697218 78137600 17832405628186 17832405595354 17832405873754 17832405875160
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 185 236281 236281 4194304 256 0 0 12 24 70144 0x7f45e2b1b980 0x7f45e2224ec0 131072 658308 73724672 17832405914139 17832405873754 17832406146555 17832406148433
65 63 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 188 236281 236281 4194304 256 0 0 12 24 71616 0x7f45e2b1b800 0x7f45e2224f00 131072 701386 78527344 17832406179992 17832406146555 17832406507515 17832406508934
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 191 236281 236281 4194304 256 0 0 12 24 72832 0x7f45e2b1b680 0x7f45e2224f40 65536 699622 78401520 17832406541013 17832406507515 17832406867356 17832406868765
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 194 236281 236281 4194304 256 0 0 8 24 74048 0x7f45e517a500 0x7f45e2224f80 131072 671958 75210128 17832406900764 17832406867356 17832407143517 17832407144948
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 197 236281 236281 4194304 256 0 0 12 24 75776 0x7f45e517a380 0x7f45e2224fc0 131072 672706 75381112 17832407176878 17832407143517 17832407432797 17832407434251
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 200 236281 236281 4194304 256 0 0 12 24 76992 0x7f45e517a200 0x7f45e2225000 131072 696606 78217128 17832407473750 17832407432797 17832407701278 17832407702625
70 68 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 203 236281 236281 4194304 256 0 0 12 24 78464 0x7f45e517a080 0x7f45e2225040 131072 708204 79429472 17832407734074 17832407701278 17832408057758 17832408059176
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 206 236281 236281 4194304 256 0 0 12 24 79936 0x7f45e2b1bf00 0x7f45e2225080 65536 661894 74152040 17832408090825 17832408057758 17832408412799 17832408414247
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 209 236281 236281 4194304 256 0 0 8 24 81408 0x7f45e2b1bd80 0x7f45e22250c0 131072 702324 78672392 17832408445166 17832408412799 17832408681919 17832408683310
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 212 236281 236281 4194304 256 0 0 12 24 83136 0x7f45e2b1bc00 0x7f45e2225100 131072 703198 78825248 17832408714829 17832408681919 17832408971200 17832408972643
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 215 236281 236281 4194304 256 0 0 12 24 84352 0x7f45e2b1ba80 0x7f45e2225140 131072 699814 78254928 17832409022692 17832408971200 17832409251040 17832409253036
75 73 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 218 236281 236281 4194304 256 0 0 12 24 85824 0x7f45e2b1b900 0x7f45e2225180 131072 698260 78216224 17832409284085 17832409251040 17832409610241 17832409611667
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 221 236281 236281 4194304 256 0 0 12 24 87296 0x7f45e2b1b780 0x7f45e22251c0 65536 663758 74336688 17832409642866 17832409610241 17832409971362 17832409972698
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 224 236281 236281 4194304 256 0 0 12 24 88768 0x7f45e2b1b600 0x7f45e2225200 131072 694200 77848640 17832410003777 17832409971362 17832410252802 17832410254361
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 227 236281 236281 4194304 256 0 0 12 24 90752 0x7f45e517a480 0x7f45e2225240 131072 704834 78911016 17832410286130 17832410252802 17832410551683 17832410553104
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 230 236281 236281 4194304 256 0 0 12 24 91968 0x7f45e517a300 0x7f45e2225280 131072 696928 78035104 17832410592273 17832410551683 17832410821763 17832410823297
80 78 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 233 236281 236281 4194304 256 0 0 12 24 93440 0x7f45e517a180 0x7f45e22252c0 131072 696032 78057056 17832410854646 17832410821763 17832411183844 17832411185188
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 236 236281 236281 4194304 256 0 0 12 24 94912 0x7f45e517a000 0x7f45e2225300 65536 660730 74005000 17832411216967 17832411183844 17832411540005 17832411541479
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 239 236281 236281 4194304 256 0 0 12 24 96384 0x7f45e2b1be80 0x7f45e2225340 131072 701146 78404240 17832411573128 17832411540005 17832411810245 17832411811662
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 242 236281 236281 4194304 256 0 0 12 24 98368 0x7f45e2b1bd00 0x7f45e2225380 131072 703188 78765024 17832411843102 17832411810245 17832412111046 17832412112465
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 245 236281 236281 4194304 256 0 0 12 24 99584 0x7f45e2b1bb80 0x7f45e22253c0 131072 709754 79435024 17832412151434 17832412111046 17832412380646 17832412382098
85 83 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 248 236281 236281 4194304 256 0 0 12 24 101312 0x7f45e2b1ba00 0x7f45e2225400 131072 658220 73796752 17832412413128 17832412380646 17832412737927 17832412739229
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 251 236281 236281 4194304 256 0 0 12 24 102784 0x7f45e2b1b880 0x7f45e2225440 65536 668226 74799216 17832412770779 17832412737927 17832413094088 17832413095561
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 254 236281 236281 4194304 256 0 0 12 24 104256 0x7f45e2b1b700 0x7f45e2225480 131072 699192 78287464 17832413126350 17832413094088 17832413365928 17832413367344
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 257 236281 236281 4194304 256 0 0 12 24 106240 0x7f45e517a580 0x7f45e22254c0 131072 664510 74391096 17832413398753 17832413365928 17832413681769 17832413683106
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 260 236281 236281 4194304 256 0 0 12 24 107712 0x7f45e517a400 0x7f45e2225500 131072 661860 74059304 17832413722855 17832413681769 17832413960329 17832413961969
90 88 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 263 236281 236281 4194304 256 0 0 16 24 109440 0x7f45e517a280 0x7f45e2225540 131072 737226 82573104 17832413994028 17832413960329 17832414330890 17832414332460
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 266 236281 236281 4194304 256 0 0 16 24 111168 0x7f45e517a100 0x7f45e2225580 65536 649046 72669000 17832414364689 17832414330890 17832414688490 17832414689831
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 269 236281 236281 4194304 256 0 0 8 24 112896 0x7f45e2b1bf80 0x7f45e22255c0 131072 700704 78428320 17832414720670 17832414688490 17832414958891 17832414960154
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 272 236281 236281 4194304 256 0 0 12 24 115136 0x7f45e2b1be00 0x7f45e2225600 131072 698686 78251168 17832414991923 17832414958891 17832415269932 17832415271487
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 275 236281 236281 4194304 256 0 0 12 24 116608 0x7f45e2b1bc80 0x7f45e2225640 131072 710916 79668896 17832415310446 17832415269932 17832415545452 17832415546950
95 93 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 278 236281 236281 4194304 256 0 0 16 24 118336 0x7f45e2b1bb00 0x7f45e2225680 131072 697310 78148408 17832415578609 17832415545452 17832415904493 17832415905951
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 281 236281 236281 4194304 256 0 0 16 24 120064 0x7f45e2b1b980 0x7f45e22256c0 65536 661938 74012344 17832415937590 17832415904493 17832416259213 17832416260682
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 284 236281 236281 4194304 256 0 0 12 24 121792 0x7f45e2b1b800 0x7f45e2225700 131072 692126 77552648 17832416291961 17832416259213 17832416530734 17832416532145
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 287 236281 236281 4194304 256 0 0 12 24 124032 0x7f45e2b1b680 0x7f45e2225740 131072 698988 78259728 17832416563474 17832416530734 17832416860815 17832416862117
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 290 236281 236281 4194304 256 0 0 12 24 125504 0x7f45e517a500 0x7f45e2225780 131072 702876 78705712 17832416901386 17832416860815 17832417138575 17832417139930
100 98 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 293 236281 236281 4194304 256 0 0 12 24 127488 0x7f45e517a380 0x7f45e22257c0 131072 693560 77710752 17832417171159 17832417138575 17832417493776 17832417495141
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 296 236281 236281 4194304 256 0 0 12 24 129216 0x7f45e517a200 0x7f45e2225800 65536 662746 74090080 17832417526740 17832417493776 17832417851056 17832417852392
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 299 236281 236281 4194304 256 0 0 12 24 130944 0x7f45e517a080 0x7f45e2225840 131072 661518 74056760 17832417884092 17832417851056 17832418128657 17832418130245
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 302 236281 236281 4194304 256 0 0 12 24 133440 0x7f45e2b1bf00 0x7f45e2225880 131072 653794 73269240 17832418161545 17832418128657 17832418465617 17832418467077
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 305 236281 236281 4194304 256 0 0 12 24 134912 0x7f45e2b1bd80 0x7f45e22258c0 131072 1023684 114753968 17832418506686 17832418465617 17832418740658 17832418742170
105 103 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 308 236281 236281 4194304 256 0 0 12 24 136896 0x7f45e2b1bc00 0x7f45e2225900 131072 671298 75085032 17832418772820 17832418740658 17832419097139 17832419098551
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 311 236281 236281 4194304 256 0 0 12 24 138880 0x7f45e2b1ba80 0x7f45e2225940 65536 666606 74689200 17832419130061 17832419097139 17832419452179 17832419453583
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 314 236281 236281 4194304 256 0 0 12 24 140864 0x7f45e2b1b900 0x7f45e2225980 131072 710322 79534256 17832419484652 17832419452179 17832419735860 17832419737316
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 317 236281 236281 4194304 256 0 0 12 24 143616 0x7f45e2b1b780 0x7f45e22259c0 131072 736312 82503920 17832419768565 17832419735860 17832420079220 17832420080667
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 320 236281 236281 4194304 256 0 0 12 24 145344 0x7f45e2b1b600 0x7f45e2225a00 131072 1046700 117191448 17832420119236 17832420079220 17832420355061 17832420356480
110 108 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 323 236281 236281 4194304 256 0 0 12 24 147584 0x7f45e517a480 0x7f45e2225a40 131072 700300 78439888 17832420388939 17832420355061 17832420711382 17832420712981
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 326 236281 236281 4194304 256 0 0 12 24 149568 0x7f45e517a300 0x7f45e2225a80 65536 656180 73492696 17832420744921 17832420711382 17832421067382 17832421068772
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 329 236281 236281 4194304 256 0 0 12 24 151552 0x7f45e517a180 0x7f45e2225ac0 131072 661490 74168088 17832421100522 17832421067382 17832421352503 17832421354025
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 332 236281 236281 4194304 256 0 0 12 24 154304 0x7f45e517a000 0x7f45e2225b00 131072 661534 74112968 17832421385605 17832421352503 17832421716504 17832421717916
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 335 236281 236281 4194304 256 0 0 12 24 156288 0x7f45e2b1be80 0x7f45e2225b40 131072 1011892 113488728 17832421756865 17832421716504 17832421995064 17832421996489
115 113 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 338 236281 236281 4194304 256 0 0 12 24 158784 0x7f45e2b1bd00 0x7f45e2225b80 131072 696698 78101400 17832422028569 17832421995064 17832422368025 17832422369470
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 341 236281 236281 4194304 256 0 0 12 24 161024 0x7f45e2b1bb80 0x7f45e2225bc0 65536 656468 73595576 17832422401369 17832422368025 17832422728505 17832422729841
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 344 236281 236281 4194304 256 0 0 12 24 163264 0x7f45e2b1ba00 0x7f45e2225c00 131072 669734 74996912 17832422761010 17832422728505 17832423026106 17832423027444
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 347 236281 236281 4194304 256 0 0 12 24 166528 0x7f45e2b1b880 0x7f45e2225c40 131072 690138 77349608 17832423059093 17832423026106 17832423408987 17832423453883
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 350 236281 236281 4194304 256 0 0 12 24 168512 0x7f45e2b1b700 0x7f45e2225c80 131072 1046912 117125320 17832423472813 17832423408987 17832423731227 17832423732736
120 118 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 353 236281 236281 4194304 256 0 0 12 24 171264 0x7f45e517a580 0x7f45e2225cc0 131072 690800 77384592 17832423764206 17832423731227 17832424090748 17832424092097
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 356 236281 236281 4194304 256 0 0 12 24 173760 0x7f45e517a400 0x7f45e2225d00 65536 668714 74860336 17832424123747 17832424090748 17832424452029 17832424453478
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 359 236281 236281 4194304 256 0 0 12 24 176256 0x7f45e517a280 0x7f45e2225d40 131072 706034 79144240 17832424484928 17832424452029 17832424772349 17832424773870
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 362 236281 236281 4194304 256 0 0 12 24 179776 0x7f45e517a100 0x7f45e2225d80 131072 714758 80019096 17832424805450 17832424772349 17832425182430 17832425201200
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 365 236281 236281 4194304 256 0 0 12 24 182272 0x7f45e2b1bf80 0x7f45e2225dc0 131072 970250 108608768 17832425223149 17832425182430 17832425496191 17832425497572
125 123 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 368 236281 236281 4194304 256 0 0 12 24 185536 0x7f45e2b1be00 0x7f45e2225e00 131072 692588 77495152 17832425529002 17832425496191 17832425861951 17832425879323
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 371 236281 236281 4194304 256 0 0 12 24 188544 0x7f45e2b1bc80 0x7f45e2225e40 65536 661972 74144176 17832425894783 17832425861951 17832426234112 17832426255404
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 374 236281 236281 4194304 256 0 0 12 24 191552 0x7f45e2b1bb00 0x7f45e2225e80 131072 651518 72914568 17832426267983 17832426234112 17832426585633 17832426587085
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 377 236281 236281 4194304 256 0 0 12 24 195840 0x7f45e2b1b980 0x7f45e2225ec0 131072 671736 75207744 17832426618065 17832426585633 17832427044993 17832427089873
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 380 236281 236281 4194304 256 0 0 12 24 198592 0x7f45e2b1b800 0x7f45e2225f00 131072 1062116 119035424 17832427108662 17832427044993 17832427406114 17832427407555
130 128 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 383 236281 236281 4194304 256 0 0 12 24 202368 0x7f45e2b1b680 0x7f45e2225f40 131072 1014410 113677256 17832427438934 17832427406114 17832427792675 17832427838994
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 386 236281 236281 4194304 256 0 0 12 24 205888 0x7f45e517a500 0x7f45e2225f80 65536 657096 73695568 17832427849524 17832427792675 17832428213636 17832428255404
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 389 236281 236281 4194304 256 0 0 12 24 209408 0x7f45e517a380 0x7f45e2225fc0 131072 717844 80385384 17832428266174 17832428213636 17832428607556 17832428608975
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 392 236281 236281 4194304 256 0 0 12 24 214464 0x7f45e517a200 0x7f45e2226000 131072 673558 75636112 17832428640334 17832428607556 17832429119877 17832429137962
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 395 236281 236281 4194304 256 0 0 12 24 217728 0x7f45e517a080 0x7f45e2226040 131072 1041120 116628760 17832429161011 17832429119877 17832429472198 17832429473604
135 133 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 398 236281 236281 4194304 256 0 0 12 24 222016 0x7f45e2b1bf00 0x7f45e2226080 131072 1067732 119659152 17832429504273 17832429472198 17832429880679 17832429898823
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 401 236281 236281 4194304 256 0 0 12 24 226048 0x7f45e2b1bd80 0x7f45e22260c0 65536 658714 73729664 17832429916513 17832429880679 17832430292359 17832430311503
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 404 236281 236281 4194304 256 0 0 12 24 230080 0x7f45e2b1bc00 0x7f45e2226100 131072 687526 77019512 17832430325033 17832430292359 17832430692680 17832430710793
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 407 236281 236281 4194304 256 0 0 12 24 235904 0x7f45e2b1ba80 0x7f45e2226140 131072 666764 74771272 17832430725573 17832430692680 17832431260201 17832431301548
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 410 236281 236281 4194304 256 0 0 12 24 239424 0x7f45e2b1b900 0x7f45e2226180 131072 1033082 115803352 17832431320018 17832431260201 17832431648682 17832431650150
140 138 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 413 236281 236281 4194304 256 0 0 12 24 244224 0x7f45e2b1b780 0x7f45e22261c0 131072 1018378 114085552 17832431681109 17832431648682 17832432079403 17832432098638
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 416 236281 236281 4194304 256 0 0 12 24 248768 0x7f45e2b1b600 0x7f45e2226200 65536 707324 79208912 17832432112608 17832432079403 17832432509483 17832432526118
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 419 236281 236281 4194304 256 0 0 12 24 253312 0x7f45e517a480 0x7f45e2226240 131072 686242 76860856 17832432542687 17832432509483 17832432925964 17832432942478
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 422 236281 236281 4194304 256 0 0 8 24 255552 0x7f45e517a300 0x7f45e2226280 131072 1038276 116262688 17832432959327 17832432925964 17832433558125 17832433575932
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 425 236281 236281 4194304 256 0 0 12 24 259840 0x7f45e517a180 0x7f45e22262c0 131072 1036858 116181864 17832433599221 17832433558125 17832433967406 17832433983822
145 143 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 428 236281 236281 4194304 256 0 0 12 24 265664 0x7f45e517a000 0x7f45e2226300 131072 987292 110725048 17832433999841 17832433967406 17832434454927 17832434474699
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 431 236281 236281 4194304 256 0 0 12 24 271232 0x7f45e2b1be80 0x7f45e2226340 65536 659696 73899072 17832434488319 17832434454927 17832434939088 17832434981337
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 434 236281 236281 4194304 256 0 0 8 24 273216 0x7f45e2b1bd00 0x7f45e2226380 131072 1018800 114147848 17832434992227 17832434939088 17832435444529 17832435485844
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 437 236281 236281 4194304 256 0 0 8 24 275712 0x7f45e2b1bb80 0x7f45e22263c0 131072 1031960 115523272 17832435497234 17832435444529 17832436205010 17832436246585
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 440 236281 236281 4194304 256 0 0 12 24 280768 0x7f45e2b1ba00 0x7f45e2226400 131072 1016270 113811808 17832436266265 17832436205010 17832436678611 17832436698824
150 148 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 443 236281 236281 4194304 256 0 0 12 24 287616 0x7f45e2b1b880 0x7f45e2226440 131072 1032280 115828136 17832436711484 17832436678611 17832437211732 17832437228671
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 446 236281 236281 4194304 256 0 0 12 24 294208 0x7f45e2b1b700 0x7f45e2226480 65536 659624 74051544 17832437245851 17832437211732 17832437740053 17832437759248
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 449 236281 236281 4194304 256 0 0 8 24 296960 0x7f45e517a580 0x7f45e22264c0 131072 1005662 112551368 17832437773327 17832437740053 17832438273334 17832438291035
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 452 236281 236281 4194304 256 0 0 8 24 299968 0x7f45e517a400 0x7f45e2226500 131072 1031584 115645744 17832438307094 17832438273334 17832439116216 17832439157763
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 455 236281 236281 4194304 256 0 0 8 24 302720 0x7f45e517a280 0x7f45e2226540 131072 1061368 118941344 17832439177303 17832439116216 17832439767897 17832439809577
155 153 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 458 236281 236281 4194304 256 0 0 12 24 305472 0x7f45e517a100 0x7f45e2226580 131072 1036776 116154712 17832439821457 17832439767897 17832440436698 17832440477671
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 461 236281 236281 4194304 256 0 0 12 24 308224 0x7f45e2b1bf80 0x7f45e22265c0 65536 660196 73909144 17832440489810 17832440436698 17832441100379 17832441118625
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 464 236281 236281 4194304 256 0 0 8 24 310976 0x7f45e2b1be00 0x7f45e2226600 131072 1039478 116410952 17832441132995 17832441100379 17832441730941 17832441747759
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 467 236281 236281 4194304 256 0 0 8 24 313216 0x7f45e2b1bc80 0x7f45e2226640 131072 1041146 116504080 17832441763269 17832441730941 17832442784223 17832442804243
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 470 236281 236281 4194304 256 0 0 8 24 315968 0x7f45e2b1bb00 0x7f45e2226680 131072 1038534 116343664 17832442825283 17832442784223 17832443822464 17832443864977
160 158 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 473 236281 236281 4194304 256 0 0 12 24 318720 0x7f45e2b1b980 0x7f45e22266c0 131072 1034026 115706080 17832443875707 17832443822308 17832444914309 17832444984019
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 476 236281 236281 4194304 256 0 0 12 24 321472 0x7f45e2b1b800 0x7f45e2226700 65536 654370 73416832 17832444995709 17832444914309 17832446040870 17832446107291
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 479 236281 236281 4194304 256 0 0 8 24 324224 0x7f45e2b1b680 0x7f45e2226740 131072 1062574 118922864 17832446119451 17832446040870 17832447150632 17832447217504
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 482 236281 236281 4194304 256 0 0 8 24 326464 0x7f45e517a500 0x7f45e2226780 131072 1035830 116234136 17832447229853 17832447150632 17832449094475 17832449159095
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 485 236281 236281 4194304 256 0 0 8 24 329216 0x7f45e517a380 0x7f45e22267c0 131072 1037504 116109664 17832449179225 17832449094475 17832451003758 17832451072248
165 163 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 488 236281 236281 4194304 256 0 0 12 24 331968 0x7f45e517a200 0x7f45e2226800 131072 1028376 115273240 17832451084307 17832451003758 17832452981041 17832453045679
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 491 236281 236281 4194304 256 0 0 12 24 334720 0x7f45e517a080 0x7f45e2226840 65536 662726 74252864 17832453056848 17832452981041 17832454942484 17832455013900
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 494 236281 236281 4194304 256 0 0 8 24 337472 0x7f45e2b1bf00 0x7f45e2226880 131072 1040770 116756344 17832455025780 17832454942484 17832456880247 17832456947382
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 497 236281 236281 4194304 256 0 0 8 24 0 0x7f45e2b1bd80 0x7f45e22268c0 131072 1035694 116127016 17832456958722 17832456880247 17832460486492 17832460564112
+168
Voir le fichier
@@ -0,0 +1,168 @@
Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,BeginNs,EndNs,CompleteNs
0,"__amd_rocclr_fillBufferAligned.kd",0,0,0,238129,238129,33554432,256,0,0,4,32,4160,0x0,0x7fe2c7e04280,524288,5497472,615656480,17851610507915,17849318958956,17851757718801,17851757807931
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,238129,238129,32768,256,0,0,12,24,13888,0x0,0x7fe2c7e23f80,4096,55920,6257708,17851762985423,17851757718801,17851763112570,17851763117229
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,238129,238129,4194304,256,0,0,12,24,14336,0x7fe2d67ec380,0x7fe2c7e23fc0,524288,10960198,1227561992,17851763151509,17851763112570,17851763483290,17851763485710
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,238129,238129,4194304,256,0,0,16,24,15040,0x7fe2d67ec200,0x7fe2c7e24000,524288,11381323,1274672356,17851763522879,17851763483290,17851763890331,17851763892860
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,238129,238129,4194304,256,0,0,16,24,15488,0x7fe2d67ec080,0x7fe2c7e24040,524288,11627241,1302212244,17851763925789,17851763890331,17851764290172,17851764292530
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,238129,238129,4194304,256,0,0,12,24,15936,0x7fe2d414df00,0x7fe2c7e24080,524288,10699863,1198379556,17851764323980,17851764290172,17851764605852,17851764608203
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,238129,238129,4194304,256,0,0,12,24,16384,0x7fe2d414dd80,0x7fe2c7e240c0,524288,11118838,1245185864,17851764640972,17851764605852,17851764908573,17851764910935
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,238129,238129,4194304,256,0,0,12,24,17088,0x7fe2d414dc00,0x7fe2c7e24100,524288,11178497,1251943004,17851764953374,17851764908573,17851765209053,17851765211248
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,238129,238129,4194304,256,0,0,16,24,17792,0x7fe2d414da80,0x7fe2c7e24140,524288,11592460,1298324336,17851765242887,17851765209053,17851765599934,17851765602108
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,238129,238129,4194304,256,0,0,16,24,18496,0x7fe2d414d900,0x7fe2c7e24180,524288,11494634,1287368864,17851765632697,17851765599934,17851765988574,17851765990788
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,238129,238129,4194304,256,0,0,16,24,19200,0x7fe2d414d780,0x7fe2c7e241c0,524288,11287982,1264243188,17851766020358,17851765988574,17851766334655,17851766337010
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,238129,238129,4194304,256,0,0,16,24,19904,0x7fe2d414d600,0x7fe2c7e24200,524288,11023054,1234642988,17851766367699,17851766334655,17851766641056,17851766643422
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,238129,238129,4194304,256,0,0,12,24,20608,0x7fe2d67ec480,0x7fe2c7e24240,524288,11244797,1259455848,17851766682701,17851766641056,17851766954976,17851766957234
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,238129,238129,4194304,256,0,0,16,24,21312,0x7fe2d67ec300,0x7fe2c7e24280,524288,11510571,1289156640,17851766990564,17851766954976,17851767331937,17851767333595
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,238129,238129,4194304,256,0,0,16,24,22016,0x7fe2d67ec180,0x7fe2c7e242c0,524288,11447156,1282083652,17851767364564,17851767331937,17851767690497,17851767692186
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,238129,238129,4194304,256,0,0,16,24,22720,0x7fe2d67ec000,0x7fe2c7e24300,524288,11276589,1263015848,17851767723665,17851767690497,17851767963778,17851767965349
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,238129,238129,4194304,256,0,0,12,24,23424,0x7fe2d414de80,0x7fe2c7e24340,524288,10903637,1221189884,17851767996329,17851767963778,17851768237058,17851768238773
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,238129,238129,4194304,256,0,0,12,24,24128,0x7fe2d414dd00,0x7fe2c7e24380,524288,11051283,1237706736,17851768276892,17851768237058,17851768510659,17851768512396
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,238129,238129,4194304,256,0,0,16,24,24832,0x7fe2d414db80,0x7fe2c7e243c0,524288,11567105,1295514892,17851768543615,17851768510659,17851768871299,17851768873267
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,238129,238129,4194304,256,0,0,16,24,25536,0x7fe2d414da00,0x7fe2c7e24400,524288,11440192,1281276188,17851768903966,17851768871299,17851769237540,17851769239258
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,238129,238129,4194304,256,0,0,12,24,26240,0x7fe2d414d880,0x7fe2c7e24440,524288,11218351,1256413152,17851769269957,17851769237540,17851769511780,17851769513491
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,238129,238129,4194304,256,0,0,12,24,26944,0x7fe2d414d700,0x7fe2c7e24480,524288,10893140,1220038764,17851769544010,17851769511780,17851769786981,17851769788744
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,238129,238129,4194304,256,0,0,12,24,27648,0x7fe2d67ec580,0x7fe2c7e244c0,524288,11184468,1252652572,17851769827593,17851769786981,17851770067781,17851770069447
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,238129,238129,4194304,256,0,0,16,24,28608,0x7fe2d67ec400,0x7fe2c7e24500,524288,11405712,1277359184,17851770101856,17851770067781,17851770434982,17851770436678
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,238129,238129,4194304,256,0,0,16,24,29312,0x7fe2d67ec280,0x7fe2c7e24540,524288,11384947,1275100984,17851770467807,17851770434982,17851770798343,17851770800169
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,238129,238129,4194304,256,0,0,12,24,30016,0x7fe2d67ec100,0x7fe2c7e24580,524288,11239872,1258881312,17851770831338,17851770798343,17851771073223,17851771074972
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,238129,238129,4194304,256,0,0,8,24,30976,0x7fe2d414df80,0x7fe2c7e245c0,524288,10799987,1209563668,17851771105501,17851771073223,17851771344744,17851771346485
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,238129,238129,4194304,256,0,0,12,24,31680,0x7fe2d414de00,0x7fe2c7e24600,524288,11131170,1246673252,17851771384385,17851771344744,17851771619144,17851771620859
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,238129,238129,4194304,256,0,0,16,24,32640,0x7fe2d414dc80,0x7fe2c7e24640,524288,11467964,1284374572,17851771652478,17851771619144,17851771986025,17851771987720
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,238129,238129,4194304,256,0,0,12,24,33600,0x7fe2d414db00,0x7fe2c7e24680,524288,11240089,1258865168,17851772018959,17851771986025,17851772349385,17851772351110
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,238129,238129,4194304,256,0,0,12,24,34560,0x7fe2d414d980,0x7fe2c7e246c0,524288,11111679,1244473400,17851772381930,17851772349385,17851772624266,17851772626054
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,238129,238129,4194304,256,0,0,8,24,35520,0x7fe2d414d800,0x7fe2c7e24700,524288,10752960,1204236396,17851772656993,17851772624266,17851772900906,17851772902707
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,238129,238129,4194304,256,0,0,12,24,36224,0x7fe2d414d680,0x7fe2c7e24740,524288,11148981,1248709068,17851772941226,17851772900906,17851773176907,17851773178670
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,238129,238129,4194304,256,0,0,12,24,37184,0x7fe2d67ec500,0x7fe2c7e24780,524288,11424600,1279548008,17851773209649,17851773176907,17851773539627,17851773541161
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,238129,238129,4194304,256,0,0,12,24,38144,0x7fe2d67ec380,0x7fe2c7e247c0,524288,11391928,1275859604,17851773572850,17851773539627,17851773903308,17851773905072
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,238129,238129,4194304,256,0,0,12,24,39104,0x7fe2d67ec200,0x7fe2c7e24800,524288,10688825,1197121120,17851773936171,17851773903308,17851774175948,17851774177675
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,238129,238129,4194304,256,0,0,8,24,40320,0x7fe2d67ec080,0x7fe2c7e24840,524288,10142263,1135919060,17851774209724,17851774175948,17851774455789,17851774457488
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,238129,238129,4194304,256,0,0,12,24,41280,0x7fe2d414df00,0x7fe2c7e24880,524288,10949440,1226295444,17851774496357,17851774455789,17851774742829,17851774744601
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,238129,238129,4194304,256,0,0,12,24,42240,0x7fe2d414dd80,0x7fe2c7e248c0,524288,11379921,1274545880,17851774774940,17851774742829,17851775110510,17851775112212
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,238129,238129,4194304,256,0,0,12,24,43200,0x7fe2d414dc00,0x7fe2c7e24900,524288,11416790,1278677352,17851775143441,17851775110510,17851775471951,17851775473633
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,238129,238129,4194304,256,0,0,8,24,44160,0x7fe2d414da80,0x7fe2c7e24940,524288,10352192,1159389384,17851775504362,17851775471951,17851775746831,17851775748466
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,238129,238129,4194304,256,0,0,12,24,45376,0x7fe2d414d900,0x7fe2c7e24980,524288,9913960,1110386536,17851775779665,17851775746831,17851776020432,17851776022119
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,238129,238129,4194304,256,0,0,12,24,46336,0x7fe2d414d780,0x7fe2c7e249c0,524288,10513747,1177552012,17851776060108,17851776020432,17851776296912,17851776298582
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,238129,238129,4194304,256,0,0,12,24,47552,0x7fe2d414d600,0x7fe2c7e24a00,524288,11381922,1274753504,17851776329492,17851776296912,17851776657713,17851776659383
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,238129,238129,4194304,256,0,0,12,24,48512,0x7fe2d67ec480,0x7fe2c7e24a40,524288,11333933,1269382580,17851776690293,17851776657713,17851777015633,17851777017335
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,238129,238129,4194304,256,0,0,8,24,49472,0x7fe2d67ec300,0x7fe2c7e24a80,524288,10580465,1185002716,17851777048404,17851777015633,17851777289234,17851777290928
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,238129,238129,4194304,256,0,0,12,24,50688,0x7fe2d67ec180,0x7fe2c7e24ac0,524288,9199320,1030329784,17851777322447,17851777289234,17851777571314,17851777572971
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,238129,238129,4194304,256,0,0,12,24,51648,0x7fe2d67ec000,0x7fe2c7e24b00,524288,10586783,1185637180,17851777611420,17851777571314,17851777859635,17851777861264
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,238129,238129,4194304,256,0,0,12,24,52864,0x7fe2d414de80,0x7fe2c7e24b40,524288,11290441,1264513584,17851777892063,17851777859635,17851778228755,17851778230584
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,238129,238129,4194304,256,0,0,12,24,54080,0x7fe2d414dd00,0x7fe2c7e24b80,524288,11333004,1269285372,17851778262294,17851778228755,17851778596116,17851778597795
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,238129,238129,4194304,256,0,0,8,24,55296,0x7fe2d414db80,0x7fe2c7e24bc0,524288,10333600,1157349612,17851778628455,17851778596116,17851778872916,17851778874719
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,238129,238129,4194304,256,0,0,12,24,56768,0x7fe2d414da00,0x7fe2c7e24c00,524288,7758862,868986468,17851778905648,17851778872916,17851779148117,17851779149842
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,238129,238129,4194304,256,0,0,12,24,57728,0x7fe2d414d880,0x7fe2c7e24c40,524288,10751011,1204055656,17851779187561,17851779148117,17851779424917,17851779426605
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,238129,238129,4194304,256,0,0,12,24,58944,0x7fe2d414d700,0x7fe2c7e24c80,524288,11359499,1272250716,17851779457324,17851779424917,17851779788118,17851779789916
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,238129,238129,4194304,256,0,0,12,24,60160,0x7fe2d67ec580,0x7fe2c7e24cc0,524288,11359245,1272205808,17851779820985,17851779788118,17851780151639,17851780153257
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,238129,238129,4194304,256,0,0,8,24,61376,0x7fe2d67ec400,0x7fe2c7e24d00,524288,10233865,1146208680,17851780183876,17851780151639,17851780432279,17851780434060
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,238129,238129,4194304,256,0,0,12,24,62848,0x7fe2d67ec280,0x7fe2c7e24d40,524288,6790915,760638956,17851780466599,17851780432279,17851780715160,17851780716753
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,238129,238129,4194304,256,0,0,12,24,63808,0x7fe2d67ec100,0x7fe2c7e24d80,524288,10722907,1200890196,17851780755482,17851780715160,17851780993400,17851780994976
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,238129,238129,4194304,256,0,0,12,24,65024,0x7fe2d414df80,0x7fe2c7e24dc0,524288,11235953,1258389508,17851781026845,17851780993400,17851781354361,17851781356027
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,238129,238129,4194304,256,0,0,12,24,66240,0x7fe2d414de00,0x7fe2c7e24e00,524288,11251763,1260196968,17851781387597,17851781354361,17851781716601,17851781718348
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,238129,238129,4194304,256,0,0,8,24,67456,0x7fe2d414dc80,0x7fe2c7e24e40,524288,10603428,1187614532,17851781749108,17851781716601,17851781993562,17851781995242
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,238129,238129,4194304,256,0,0,12,24,68928,0x7fe2d414db00,0x7fe2c7e24e80,524288,5736171,642479920,17851782026071,17851781993562,17851782284602,17851782286414
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,238129,238129,4194304,256,0,0,12,24,70144,0x7fe2d414d980,0x7fe2c7e24ec0,524288,10761174,1205159824,17851782324253,17851782284602,17851782562523,17851782564147
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,238129,238129,4194304,256,0,0,12,24,71616,0x7fe2d414d800,0x7fe2c7e24f00,524288,11277622,1263104348,17851782596237,17851782562523,17851782924923,17851782926658
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,238129,238129,4194304,256,0,0,12,24,72832,0x7fe2d414d680,0x7fe2c7e24f40,524288,11403554,1277177012,17851782958358,17851782924923,17851783294044,17851783295759
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,238129,238129,4194304,256,0,0,8,24,74048,0x7fe2d67ec500,0x7fe2c7e24f80,524288,9971998,1116839528,17851783326518,17851783294044,17851783572605,17851783574332
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,238129,238129,4194304,256,0,0,12,24,75776,0x7fe2d67ec380,0x7fe2c7e24fc0,524288,4788676,536323888,17851783605412,17851783572605,17851783862525,17851783864245
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,238129,238129,4194304,256,0,0,12,24,76992,0x7fe2d67ec200,0x7fe2c7e25000,524288,10496241,1175548992,17851783902714,17851783862525,17851784138365,17851784140138
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,238129,238129,4194304,256,0,0,12,24,78464,0x7fe2d67ec080,0x7fe2c7e25040,524288,11254474,1260459736,17851784171147,17851784138365,17851784500446,17851784502099
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,238129,238129,4194304,256,0,0,12,24,79936,0x7fe2d414df00,0x7fe2c7e25080,524288,11308943,1266564232,17851784534368,17851784500446,17851784865247,17851784866980
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,238129,238129,4194304,256,0,0,8,24,81408,0x7fe2d414dd80,0x7fe2c7e250c0,524288,9969059,1116531716,17851784897639,17851784865247,17851785139647,17851785141433
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,238129,238129,4194304,256,0,0,12,24,83136,0x7fe2d414dc00,0x7fe2c7e25100,524288,4101249,459292572,17851785172763,17851785139647,17851785435168,17851785436936
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,238129,238129,4194304,256,0,0,12,24,84352,0x7fe2d414da80,0x7fe2c7e25140,524288,10552160,1181829580,17851785487385,17851785435168,17851785716928,17851785718719
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,238129,238129,4194304,256,0,0,12,24,85824,0x7fe2d414d900,0x7fe2c7e25180,524288,11311011,1266806536,17851785749208,17851785716928,17851786084129,17851786085730
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,238129,238129,4194304,256,0,0,12,24,87296,0x7fe2d414d780,0x7fe2c7e251c0,524288,11219564,1256568920,17851786117729,17851786084129,17851786457889,17851786459631
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,238129,238129,4194304,256,0,0,12,24,88768,0x7fe2d414d600,0x7fe2c7e25200,524288,9820308,1099748564,17851786490400,17851786457889,17851786735490,17851786737154
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,238129,238129,4194304,256,0,0,12,24,90752,0x7fe2d67ec480,0x7fe2c7e25240,524288,3671648,411187864,17851786768093,17851786735490,17851787037890,17851787039626
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,238129,238129,4194304,256,0,0,12,24,91968,0x7fe2d67ec300,0x7fe2c7e25280,524288,10077664,1128706364,17851787077675,17851787037890,17851787315331,17851787316989
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,238129,238129,4194304,256,0,0,12,24,93440,0x7fe2d67ec180,0x7fe2c7e252c0,524288,11126647,1246159484,17851787348009,17851787315331,17851787674692,17851787676360
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,238129,238129,4194304,256,0,0,12,24,94912,0x7fe2d67ec000,0x7fe2c7e25300,524288,11153488,1249170388,17851787708170,17851787674692,17851788032292,17851788034032
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,238129,238129,4194304,256,0,0,12,24,96384,0x7fe2d414de80,0x7fe2c7e25340,524288,8941596,1001449384,17851788064441,17851788032292,17851788306853,17851788308635
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,238129,238129,4194304,256,0,0,12,24,98368,0x7fe2d414dd00,0x7fe2c7e25380,524288,3497243,391708692,17851788339414,17851788306853,17851788613413,17851788614977
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,238129,238129,4194304,256,0,0,12,24,99584,0x7fe2d414db80,0x7fe2c7e253c0,524288,9670492,1083108004,17851788652536,17851788613413,17851788896934,17851788898650
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,238129,238129,4194304,256,0,0,12,24,101312,0x7fe2d414da00,0x7fe2c7e25400,524288,11021697,1234414332,17851788930049,17851788896934,17851789261734,17851789263381
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,238129,238129,4194304,256,0,0,12,24,102784,0x7fe2d414d880,0x7fe2c7e25440,524288,11132126,1246798012,17851789294310,17851789261734,17851789621895,17851789623662
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,238129,238129,4194304,256,0,0,12,24,104256,0x7fe2d414d700,0x7fe2c7e25480,524288,8689261,973198924,17851789653931,17851789621895,17851789898375,17851789900145
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,238129,238129,4194304,256,0,0,12,24,106240,0x7fe2d67ec580,0x7fe2c7e254c0,524288,3296359,369169100,17851789930734,17851789898375,17851790211816,17851790213657
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,238129,238129,4194304,256,0,0,12,24,107712,0x7fe2d67ec400,0x7fe2c7e25500,524288,10037455,1124195284,17851790252606,17851790211816,17851790489256,17851790491010
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,238129,238129,4194304,256,0,0,16,24,109440,0x7fe2d67ec280,0x7fe2c7e25540,524288,11174234,1251471072,17851790521940,17851790489256,17851790848457,17851790850182
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,238129,238129,4194304,256,0,0,16,24,111168,0x7fe2d67ec100,0x7fe2c7e25580,524288,11156391,1249494572,17851790881871,17851790848457,17851791213898,17851791215562
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,238129,238129,4194304,256,0,0,8,24,112896,0x7fe2d414df80,0x7fe2c7e255c0,524288,8453395,946749724,17851791246402,17851791213898,17851791491658,17851791493396
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,238129,238129,4194304,256,0,0,12,24,115136,0x7fe2d414de00,0x7fe2c7e25600,524288,3024996,338796148,17851791524785,17851791491658,17851791816619,17851791818288
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,238129,238129,4194304,256,0,0,12,24,116608,0x7fe2d414dc80,0x7fe2c7e25640,524288,9898403,1108578380,17851791856967,17851791816619,17851792098539,17851792100221
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,238129,238129,4194304,256,0,0,16,24,118336,0x7fe2d414db00,0x7fe2c7e25680,524288,11104075,1243642512,17851792131210,17851792098539,17851792457420,17851792459142
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,238129,238129,4194304,256,0,0,16,24,120064,0x7fe2d414d980,0x7fe2c7e256c0,524288,11097123,1242879504,17851792489141,17851792457420,17851792817900,17851792819553
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,238129,238129,4194304,256,0,0,12,24,121792,0x7fe2d414d800,0x7fe2c7e25700,524288,7310378,818624588,17851792849692,17851792817900,17851793096141,17851793097826
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,238129,238129,4194304,256,0,0,12,24,124032,0x7fe2d414d680,0x7fe2c7e25740,524288,2941237,329425624,17851793128535,17851793096141,17851793421421,17851793423188
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,238129,238129,4194304,256,0,0,12,24,125504,0x7fe2d67ec500,0x7fe2c7e25780,524288,9559653,1070725500,17851793461137,17851793421421,17851793695662,17851793697541
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,238129,238129,4194304,256,0,0,12,24,127488,0x7fe2d67ec380,0x7fe2c7e257c0,524288,11023374,1234615968,17851793727930,17851793695662,17851794053262,17851794055012
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,238129,238129,4194304,256,0,0,12,24,129216,0x7fe2d67ec200,0x7fe2c7e25800,524288,11082656,1241258564,17851794092211,17851794053262,17851794431823,17851794433593
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,238129,238129,4194304,256,0,0,12,24,130944,0x7fe2d67ec080,0x7fe2c7e25840,524288,6353255,711593988,17851794464132,17851794431823,17851794712304,17851794713966
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,238129,238129,4194304,256,0,0,12,24,133440,0x7fe2d414df00,0x7fe2c7e25880,524288,2939088,329191932,17851794744745,17851794712304,17851795055664,17851795057367
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,238129,238129,4194304,256,0,0,12,24,134912,0x7fe2d414dd80,0x7fe2c7e258c0,524288,8674328,971491172,17851795096216,17851795055664,17851795333105,17851795334710
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,238129,238129,4194304,256,0,0,12,24,136896,0x7fe2d414dc00,0x7fe2c7e25900,524288,10772675,1206512204,17851795365530,17851795333105,17851795695185,17851795696821
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,238129,238129,4194304,256,0,0,12,24,138880,0x7fe2d414da80,0x7fe2c7e25940,524288,10815365,1211244236,17851795728621,17851795695185,17851796056626,17851796058483
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,238129,238129,4194304,256,0,0,12,24,140864,0x7fe2d414d900,0x7fe2c7e25980,524288,5008411,560934772,17851796088352,17851796056626,17851796340466,17851796342176
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,238129,238129,4194304,256,0,0,12,24,143616,0x7fe2d414d780,0x7fe2c7e259c0,524288,2860023,320346980,17851796373065,17851796340466,17851796691027,17851796692677
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,238129,238129,4194304,256,0,0,12,24,145344,0x7fe2d414d600,0x7fe2c7e25a00,524288,6975002,781170540,17851796731096,17851796691027,17851796968787,17851796970440
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,238129,238129,4194304,256,0,0,12,24,147584,0x7fe2d67ec480,0x7fe2c7e25a40,524288,10836988,1213716384,17851797001379,17851796968787,17851797330868,17851797332751
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,238129,238129,4194304,256,0,0,12,24,149568,0x7fe2d67ec300,0x7fe2c7e25a80,524288,10812264,1210981884,17851797363950,17851797330868,17851797699349,17851797701022
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,238129,238129,4194304,256,0,0,12,24,151552,0x7fe2d67ec180,0x7fe2c7e25ac0,524288,3932869,440446248,17851797731601,17851797699349,17851797996469,17851797998205
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,238129,238129,4194304,256,0,0,12,24,154304,0x7fe2d67ec000,0x7fe2c7e25b00,524288,2846565,318818040,17851798029344,17851797996469,17851798366710,17851798368385
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,238129,238129,4194304,256,0,0,12,24,156288,0x7fe2d414de80,0x7fe2c7e25b40,524288,5834515,653448932,17851798406914,17851798366710,17851798658070,17851798659808
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,238129,238129,4194304,256,0,0,12,24,158784,0x7fe2d414dd00,0x7fe2c7e25b80,524288,10823083,1212141256,17851798690347,17851798658070,17851799020311,17851799022009
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,238129,238129,4194304,256,0,0,12,24,161024,0x7fe2d414db80,0x7fe2c7e25bc0,524288,10796310,1209189816,17851799053408,17851799020311,17851799383512,17851799385260
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,238129,238129,4194304,256,0,0,12,24,163264,0x7fe2d414da00,0x7fe2c7e25c00,524288,3807149,426378124,17851799416469,17851799383512,17851799687192,17851799688903
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,238129,238129,4194304,256,0,0,12,24,166528,0x7fe2d414d880,0x7fe2c7e25c40,524288,2876568,322203864,17851799719172,17851799687192,17851800076153,17851800121672
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,238129,238129,4194304,256,0,0,12,24,168512,0x7fe2d414d700,0x7fe2c7e25c80,524288,4400559,492855256,17851800141391,17851800076153,17851800403993,17851800405705
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,238129,238129,4194304,256,0,0,12,24,171264,0x7fe2d67ec580,0x7fe2c7e25cc0,524288,10574190,1184279480,17851800437434,17851800403993,17851800769434,17851800771206
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,238129,238129,4194304,256,0,0,12,24,173760,0x7fe2d67ec400,0x7fe2c7e25d00,524288,9756056,1092609072,17851800803335,17851800769434,17851801141275,17851801142977
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,238129,238129,4194304,256,0,0,12,24,176256,0x7fe2d67ec280,0x7fe2c7e25d40,524288,2937151,328969808,17851801174356,17851801141275,17851801460635,17851801462349
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,238129,238129,4194304,256,0,0,12,24,179776,0x7fe2d67ec100,0x7fe2c7e25d80,524288,2885783,323165516,17851801493368,17851801460635,17851801877596,17851801898488
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,238129,238129,4194304,256,0,0,12,24,182272,0x7fe2d414df80,0x7fe2c7e25dc0,524288,3062370,343015688,17851801918537,17851801877596,17851802207196,17851802209040
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,238129,238129,4194304,256,0,0,12,24,185536,0x7fe2d414de00,0x7fe2c7e25e00,524288,7965851,892150972,17851802241089,17851802207196,17851802586877,17851802634739
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,238129,238129,4194304,256,0,0,12,24,188544,0x7fe2d414dc80,0x7fe2c7e25e40,524288,7295385,817165120,17851802647099,17851802586877,17851803000478,17851803045659
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,238129,238129,4194304,256,0,0,12,24,191552,0x7fe2d414db00,0x7fe2c7e25e80,524288,2808501,314562680,17851803057569,17851803000478,17851803378718,17851803380351
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,238129,238129,4194304,256,0,0,12,24,195840,0x7fe2d414d980,0x7fe2c7e25ec0,524288,2834429,317413852,17851803410380,17851803378718,17851803844639,17851803889878
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,238129,238129,4194304,256,0,0,12,24,198592,0x7fe2d414d800,0x7fe2c7e25f00,524288,2829364,316816148,17851803909458,17851803844639,17851804211040,17851804212750
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,238129,238129,4194304,256,0,0,12,24,202368,0x7fe2d414d680,0x7fe2c7e25f40,524288,7156252,801412676,17851804244429,17851804211040,17851804606400,17851804648529
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,238129,238129,4194304,256,0,0,12,24,205888,0x7fe2d67ec500,0x7fe2c7e25f80,524288,6546543,733169316,17851804661659,17851804606400,17851805024321,17851805066159
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,238129,238129,4194304,256,0,0,12,24,209408,0x7fe2d67ec380,0x7fe2c7e25fc0,524288,2782400,311622300,17851805077389,17851805024321,17851805419362,17851805421170
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,238129,238129,4194304,256,0,0,12,24,214464,0x7fe2d67ec200,0x7fe2c7e26000,524288,2897542,324507732,17851805452989,17851805419362,17851805937923,17851805958267
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,238129,238129,4194304,256,0,0,12,24,217728,0x7fe2d67ec080,0x7fe2c7e26040,524288,2758709,309008928,17851805978236,17851805937923,17851806302243,17851806304268
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,238129,238129,4194304,256,0,0,12,24,222016,0x7fe2d414df00,0x7fe2c7e26080,524288,5361502,600451100,17851806335168,17851806302243,17851806715684,17851806759087
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,238129,238129,4194304,256,0,0,12,24,226048,0x7fe2d414dd80,0x7fe2c7e260c0,524288,5241560,587040032,17851806772477,17851806715684,17851807162405,17851807206206
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,238129,238129,4194304,256,0,0,12,24,230080,0x7fe2d414dc00,0x7fe2c7e26100,524288,2719578,304632596,17851807218236,17851807162405,17851807586246,17851807627715
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,238129,238129,4194304,256,0,0,12,24,235904,0x7fe2d414da80,0x7fe2c7e26140,524288,2929353,328060908,17851807640425,17851807586246,17851808183207,17851808224711
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,238129,238129,4194304,256,0,0,12,24,239424,0x7fe2d414d900,0x7fe2c7e26180,524288,2798443,313443644,17851808244280,17851808183207,17851808586727,17851808588512
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,238129,238129,4194304,256,0,0,12,24,244224,0x7fe2d414d780,0x7fe2c7e261c0,524288,5198688,582256312,17851808619471,17851808586727,17851809020488,17851809062250
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,238129,238129,4194304,256,0,0,12,24,248768,0x7fe2d414d600,0x7fe2c7e26200,524288,3227946,361493392,17851809075529,17851809020488,17851809479849,17851809522538
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,238129,238129,4194304,256,0,0,12,24,253312,0x7fe2d67ec480,0x7fe2c7e26240,524288,2765869,309719692,17851809534718,17851809479849,17851809928650,17851809947908
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,238129,238129,4194304,256,0,0,8,24,255552,0x7fe2d67ec300,0x7fe2c7e26280,524288,2372030,265583500,17851809961547,17851809928650,17851810579051,17851810623291
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,238129,238129,4194304,256,0,0,12,24,259840,0x7fe2d67ec180,0x7fe2c7e262c0,524288,2780688,311398384,17851810643791,17851810579051,17851811023211,17851811067380
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,238129,238129,4194304,256,0,0,12,24,265664,0x7fe2d67ec000,0x7fe2c7e26300,524288,3273190,366588524,17851811079870,17851811023211,17851811539532,17851811581427
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,238129,238129,4194304,256,0,0,12,24,271232,0x7fe2d414de80,0x7fe2c7e26340,524288,3706436,415100620,17851811593917,17851811539532,17851812051693,17851812094375
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,238129,238129,4194304,256,0,0,8,24,273216,0x7fe2d414dd00,0x7fe2c7e26380,524288,2392570,267988172,17851812106724,17851812051693,17851812564014,17851812605892
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,238129,238129,4194304,256,0,0,8,24,275712,0x7fe2d414db80,0x7fe2c7e263c0,524288,2380155,266528932,17851812617972,17851812564014,17851813336815,17851813378153
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,238129,238129,4194304,256,0,0,12,24,280768,0x7fe2d414da00,0x7fe2c7e26400,524288,2651241,296869496,17851813398483,17851813336815,17851813813936,17851813832062
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,238129,238129,4194304,256,0,0,12,24,287616,0x7fe2d414d880,0x7fe2c7e26440,524288,3358527,376130448,17851813847012,17851813813936,17851814349137,17851814394698
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,238129,238129,4194304,256,0,0,12,24,294208,0x7fe2d414d700,0x7fe2c7e26480,524288,3595083,402577832,17851814407058,17851814349137,17851814926578,17851814972024
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,238129,238129,4194304,256,0,0,8,24,296960,0x7fe2d67ec580,0x7fe2c7e264c0,524288,2398306,268633068,17851814983683,17851814926578,17851815496819,17851815538310
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,238129,238129,4194304,256,0,0,8,24,299968,0x7fe2d67ec400,0x7fe2c7e26500,524288,2389962,267666172,17851815550579,17851815496819,17851816367541,17851816409418
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,238129,238129,4194304,256,0,0,8,24,302720,0x7fe2d67ec280,0x7fe2c7e26540,524288,2388205,267475364,17851816429357,17851816367541,17851817028342,17851817069932
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,238129,238129,4194304,256,0,0,12,24,305472,0x7fe2d67ec100,0x7fe2c7e26580,524288,2579021,288843416,17851817081861,17851817028342,17851817710423,17851817752365
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,238129,238129,4194304,256,0,0,12,24,308224,0x7fe2d414df80,0x7fe2c7e265c0,524288,2592302,290292660,17851817764284,17851817710423,17851818386584,17851818432168
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,238129,238129,4194304,256,0,0,8,24,310976,0x7fe2d414de00,0x7fe2c7e26600,524288,2392252,267948208,17851818443947,17851818386584,17851819065625,17851819114581
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,238129,238129,4194304,256,0,0,8,24,313216,0x7fe2d414dc80,0x7fe2c7e26640,524288,2411106,269994500,17851819127690,17851819065625,17851820154427,17851820200824
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,238129,238129,4194304,256,0,0,8,24,315968,0x7fe2d414db00,0x7fe2c7e26680,524288,2438201,273086344,17851820221473,17851820154085,17851821239526,17851821308076
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,238129,238129,4194304,256,0,0,12,24,318720,0x7fe2d414d980,0x7fe2c7e266c0,524288,2595984,290719540,17851821320076,17851821239526,17851822378407,17851822445038
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,238129,238129,4194304,256,0,0,12,24,321472,0x7fe2d414d800,0x7fe2c7e26700,524288,2597137,290863004,17851822458078,17851822378407,17851823516328,17851823583740
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,238129,238129,4194304,256,0,0,8,24,324224,0x7fe2d414d680,0x7fe2c7e26740,524288,2428844,272065092,17851823596109,17851823516328,17851824627689,17851824694792
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,238129,238129,4194304,256,0,0,8,24,326464,0x7fe2d67ec500,0x7fe2c7e26780,524288,2466156,276132408,17851824706782,17851824627689,17851826578251,17851826648574
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,238129,238129,4194304,256,0,0,8,24,329216,0x7fe2d67ec380,0x7fe2c7e267c0,524288,2464191,275993492,17851826670493,17851826578251,17851828504333,17851828576246
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,238129,238129,4194304,256,0,0,12,24,331968,0x7fe2d67ec200,0x7fe2c7e26800,524288,2621651,293624628,17851828588236,17851828504333,17851830489935,17851830560797
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,238129,238129,4194304,256,0,0,12,24,334720,0x7fe2d67ec080,0x7fe2c7e26840,524288,2626645,294164516,17851830573217,17851830489935,17851832474737,17851832543988
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,238129,238129,4194304,256,0,0,8,24,337472,0x7fe2d414df00,0x7fe2c7e26880,524288,2455750,275010384,17851832555917,17851832474737,17851834403859,17851834473550
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,238129,238129,4194304,256,0,0,8,24,0,0x7fe2d414dd80,0x7fe2c7e268c0,524288,2496448,279555072,17851834487209,17851834403859,17851838027063,17851838150278
1 Index KernelName gpu-id queue-id queue-index pid tid grd wgr lds scr vgpr sgpr fbar sig obj SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES DispatchNs BeginNs EndNs CompleteNs
2 0 __amd_rocclr_fillBufferAligned.kd 0 0 0 238129 238129 33554432 256 0 0 4 32 4160 0x0 0x7fe2c7e04280 524288 5497472 615656480 17851610507915 17849318958956 17851757718801 17851757807931
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 238129 238129 32768 256 0 0 12 24 13888 0x0 0x7fe2c7e23f80 4096 55920 6257708 17851762985423 17851757718801 17851763112570 17851763117229
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 5 238129 238129 4194304 256 0 0 12 24 14336 0x7fe2d67ec380 0x7fe2c7e23fc0 524288 10960198 1227561992 17851763151509 17851763112570 17851763483290 17851763485710
5 3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 8 238129 238129 4194304 256 0 0 16 24 15040 0x7fe2d67ec200 0x7fe2c7e24000 524288 11381323 1274672356 17851763522879 17851763483290 17851763890331 17851763892860
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 11 238129 238129 4194304 256 0 0 16 24 15488 0x7fe2d67ec080 0x7fe2c7e24040 524288 11627241 1302212244 17851763925789 17851763890331 17851764290172 17851764292530
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 14 238129 238129 4194304 256 0 0 12 24 15936 0x7fe2d414df00 0x7fe2c7e24080 524288 10699863 1198379556 17851764323980 17851764290172 17851764605852 17851764608203
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 17 238129 238129 4194304 256 0 0 12 24 16384 0x7fe2d414dd80 0x7fe2c7e240c0 524288 11118838 1245185864 17851764640972 17851764605852 17851764908573 17851764910935
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 20 238129 238129 4194304 256 0 0 12 24 17088 0x7fe2d414dc00 0x7fe2c7e24100 524288 11178497 1251943004 17851764953374 17851764908573 17851765209053 17851765211248
10 8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 23 238129 238129 4194304 256 0 0 16 24 17792 0x7fe2d414da80 0x7fe2c7e24140 524288 11592460 1298324336 17851765242887 17851765209053 17851765599934 17851765602108
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 26 238129 238129 4194304 256 0 0 16 24 18496 0x7fe2d414d900 0x7fe2c7e24180 524288 11494634 1287368864 17851765632697 17851765599934 17851765988574 17851765990788
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 29 238129 238129 4194304 256 0 0 16 24 19200 0x7fe2d414d780 0x7fe2c7e241c0 524288 11287982 1264243188 17851766020358 17851765988574 17851766334655 17851766337010
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 32 238129 238129 4194304 256 0 0 16 24 19904 0x7fe2d414d600 0x7fe2c7e24200 524288 11023054 1234642988 17851766367699 17851766334655 17851766641056 17851766643422
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 35 238129 238129 4194304 256 0 0 12 24 20608 0x7fe2d67ec480 0x7fe2c7e24240 524288 11244797 1259455848 17851766682701 17851766641056 17851766954976 17851766957234
15 13 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 38 238129 238129 4194304 256 0 0 16 24 21312 0x7fe2d67ec300 0x7fe2c7e24280 524288 11510571 1289156640 17851766990564 17851766954976 17851767331937 17851767333595
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 41 238129 238129 4194304 256 0 0 16 24 22016 0x7fe2d67ec180 0x7fe2c7e242c0 524288 11447156 1282083652 17851767364564 17851767331937 17851767690497 17851767692186
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 44 238129 238129 4194304 256 0 0 16 24 22720 0x7fe2d67ec000 0x7fe2c7e24300 524288 11276589 1263015848 17851767723665 17851767690497 17851767963778 17851767965349
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 47 238129 238129 4194304 256 0 0 12 24 23424 0x7fe2d414de80 0x7fe2c7e24340 524288 10903637 1221189884 17851767996329 17851767963778 17851768237058 17851768238773
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 50 238129 238129 4194304 256 0 0 12 24 24128 0x7fe2d414dd00 0x7fe2c7e24380 524288 11051283 1237706736 17851768276892 17851768237058 17851768510659 17851768512396
20 18 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 53 238129 238129 4194304 256 0 0 16 24 24832 0x7fe2d414db80 0x7fe2c7e243c0 524288 11567105 1295514892 17851768543615 17851768510659 17851768871299 17851768873267
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 56 238129 238129 4194304 256 0 0 16 24 25536 0x7fe2d414da00 0x7fe2c7e24400 524288 11440192 1281276188 17851768903966 17851768871299 17851769237540 17851769239258
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 59 238129 238129 4194304 256 0 0 12 24 26240 0x7fe2d414d880 0x7fe2c7e24440 524288 11218351 1256413152 17851769269957 17851769237540 17851769511780 17851769513491
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 62 238129 238129 4194304 256 0 0 12 24 26944 0x7fe2d414d700 0x7fe2c7e24480 524288 10893140 1220038764 17851769544010 17851769511780 17851769786981 17851769788744
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 65 238129 238129 4194304 256 0 0 12 24 27648 0x7fe2d67ec580 0x7fe2c7e244c0 524288 11184468 1252652572 17851769827593 17851769786981 17851770067781 17851770069447
25 23 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 68 238129 238129 4194304 256 0 0 16 24 28608 0x7fe2d67ec400 0x7fe2c7e24500 524288 11405712 1277359184 17851770101856 17851770067781 17851770434982 17851770436678
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 71 238129 238129 4194304 256 0 0 16 24 29312 0x7fe2d67ec280 0x7fe2c7e24540 524288 11384947 1275100984 17851770467807 17851770434982 17851770798343 17851770800169
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 74 238129 238129 4194304 256 0 0 12 24 30016 0x7fe2d67ec100 0x7fe2c7e24580 524288 11239872 1258881312 17851770831338 17851770798343 17851771073223 17851771074972
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 77 238129 238129 4194304 256 0 0 8 24 30976 0x7fe2d414df80 0x7fe2c7e245c0 524288 10799987 1209563668 17851771105501 17851771073223 17851771344744 17851771346485
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 80 238129 238129 4194304 256 0 0 12 24 31680 0x7fe2d414de00 0x7fe2c7e24600 524288 11131170 1246673252 17851771384385 17851771344744 17851771619144 17851771620859
30 28 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 83 238129 238129 4194304 256 0 0 16 24 32640 0x7fe2d414dc80 0x7fe2c7e24640 524288 11467964 1284374572 17851771652478 17851771619144 17851771986025 17851771987720
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 86 238129 238129 4194304 256 0 0 12 24 33600 0x7fe2d414db00 0x7fe2c7e24680 524288 11240089 1258865168 17851772018959 17851771986025 17851772349385 17851772351110
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 89 238129 238129 4194304 256 0 0 12 24 34560 0x7fe2d414d980 0x7fe2c7e246c0 524288 11111679 1244473400 17851772381930 17851772349385 17851772624266 17851772626054
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 92 238129 238129 4194304 256 0 0 8 24 35520 0x7fe2d414d800 0x7fe2c7e24700 524288 10752960 1204236396 17851772656993 17851772624266 17851772900906 17851772902707
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 95 238129 238129 4194304 256 0 0 12 24 36224 0x7fe2d414d680 0x7fe2c7e24740 524288 11148981 1248709068 17851772941226 17851772900906 17851773176907 17851773178670
35 33 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 98 238129 238129 4194304 256 0 0 12 24 37184 0x7fe2d67ec500 0x7fe2c7e24780 524288 11424600 1279548008 17851773209649 17851773176907 17851773539627 17851773541161
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 101 238129 238129 4194304 256 0 0 12 24 38144 0x7fe2d67ec380 0x7fe2c7e247c0 524288 11391928 1275859604 17851773572850 17851773539627 17851773903308 17851773905072
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 104 238129 238129 4194304 256 0 0 12 24 39104 0x7fe2d67ec200 0x7fe2c7e24800 524288 10688825 1197121120 17851773936171 17851773903308 17851774175948 17851774177675
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 107 238129 238129 4194304 256 0 0 8 24 40320 0x7fe2d67ec080 0x7fe2c7e24840 524288 10142263 1135919060 17851774209724 17851774175948 17851774455789 17851774457488
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 110 238129 238129 4194304 256 0 0 12 24 41280 0x7fe2d414df00 0x7fe2c7e24880 524288 10949440 1226295444 17851774496357 17851774455789 17851774742829 17851774744601
40 38 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 113 238129 238129 4194304 256 0 0 12 24 42240 0x7fe2d414dd80 0x7fe2c7e248c0 524288 11379921 1274545880 17851774774940 17851774742829 17851775110510 17851775112212
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 116 238129 238129 4194304 256 0 0 12 24 43200 0x7fe2d414dc00 0x7fe2c7e24900 524288 11416790 1278677352 17851775143441 17851775110510 17851775471951 17851775473633
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 119 238129 238129 4194304 256 0 0 8 24 44160 0x7fe2d414da80 0x7fe2c7e24940 524288 10352192 1159389384 17851775504362 17851775471951 17851775746831 17851775748466
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 122 238129 238129 4194304 256 0 0 12 24 45376 0x7fe2d414d900 0x7fe2c7e24980 524288 9913960 1110386536 17851775779665 17851775746831 17851776020432 17851776022119
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 125 238129 238129 4194304 256 0 0 12 24 46336 0x7fe2d414d780 0x7fe2c7e249c0 524288 10513747 1177552012 17851776060108 17851776020432 17851776296912 17851776298582
45 43 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 128 238129 238129 4194304 256 0 0 12 24 47552 0x7fe2d414d600 0x7fe2c7e24a00 524288 11381922 1274753504 17851776329492 17851776296912 17851776657713 17851776659383
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 131 238129 238129 4194304 256 0 0 12 24 48512 0x7fe2d67ec480 0x7fe2c7e24a40 524288 11333933 1269382580 17851776690293 17851776657713 17851777015633 17851777017335
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 134 238129 238129 4194304 256 0 0 8 24 49472 0x7fe2d67ec300 0x7fe2c7e24a80 524288 10580465 1185002716 17851777048404 17851777015633 17851777289234 17851777290928
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 137 238129 238129 4194304 256 0 0 12 24 50688 0x7fe2d67ec180 0x7fe2c7e24ac0 524288 9199320 1030329784 17851777322447 17851777289234 17851777571314 17851777572971
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 140 238129 238129 4194304 256 0 0 12 24 51648 0x7fe2d67ec000 0x7fe2c7e24b00 524288 10586783 1185637180 17851777611420 17851777571314 17851777859635 17851777861264
50 48 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 143 238129 238129 4194304 256 0 0 12 24 52864 0x7fe2d414de80 0x7fe2c7e24b40 524288 11290441 1264513584 17851777892063 17851777859635 17851778228755 17851778230584
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 146 238129 238129 4194304 256 0 0 12 24 54080 0x7fe2d414dd00 0x7fe2c7e24b80 524288 11333004 1269285372 17851778262294 17851778228755 17851778596116 17851778597795
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 149 238129 238129 4194304 256 0 0 8 24 55296 0x7fe2d414db80 0x7fe2c7e24bc0 524288 10333600 1157349612 17851778628455 17851778596116 17851778872916 17851778874719
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 152 238129 238129 4194304 256 0 0 12 24 56768 0x7fe2d414da00 0x7fe2c7e24c00 524288 7758862 868986468 17851778905648 17851778872916 17851779148117 17851779149842
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 155 238129 238129 4194304 256 0 0 12 24 57728 0x7fe2d414d880 0x7fe2c7e24c40 524288 10751011 1204055656 17851779187561 17851779148117 17851779424917 17851779426605
55 53 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 158 238129 238129 4194304 256 0 0 12 24 58944 0x7fe2d414d700 0x7fe2c7e24c80 524288 11359499 1272250716 17851779457324 17851779424917 17851779788118 17851779789916
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 161 238129 238129 4194304 256 0 0 12 24 60160 0x7fe2d67ec580 0x7fe2c7e24cc0 524288 11359245 1272205808 17851779820985 17851779788118 17851780151639 17851780153257
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 164 238129 238129 4194304 256 0 0 8 24 61376 0x7fe2d67ec400 0x7fe2c7e24d00 524288 10233865 1146208680 17851780183876 17851780151639 17851780432279 17851780434060
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 167 238129 238129 4194304 256 0 0 12 24 62848 0x7fe2d67ec280 0x7fe2c7e24d40 524288 6790915 760638956 17851780466599 17851780432279 17851780715160 17851780716753
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 170 238129 238129 4194304 256 0 0 12 24 63808 0x7fe2d67ec100 0x7fe2c7e24d80 524288 10722907 1200890196 17851780755482 17851780715160 17851780993400 17851780994976
60 58 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 173 238129 238129 4194304 256 0 0 12 24 65024 0x7fe2d414df80 0x7fe2c7e24dc0 524288 11235953 1258389508 17851781026845 17851780993400 17851781354361 17851781356027
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 176 238129 238129 4194304 256 0 0 12 24 66240 0x7fe2d414de00 0x7fe2c7e24e00 524288 11251763 1260196968 17851781387597 17851781354361 17851781716601 17851781718348
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 179 238129 238129 4194304 256 0 0 8 24 67456 0x7fe2d414dc80 0x7fe2c7e24e40 524288 10603428 1187614532 17851781749108 17851781716601 17851781993562 17851781995242
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 182 238129 238129 4194304 256 0 0 12 24 68928 0x7fe2d414db00 0x7fe2c7e24e80 524288 5736171 642479920 17851782026071 17851781993562 17851782284602 17851782286414
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 185 238129 238129 4194304 256 0 0 12 24 70144 0x7fe2d414d980 0x7fe2c7e24ec0 524288 10761174 1205159824 17851782324253 17851782284602 17851782562523 17851782564147
65 63 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 188 238129 238129 4194304 256 0 0 12 24 71616 0x7fe2d414d800 0x7fe2c7e24f00 524288 11277622 1263104348 17851782596237 17851782562523 17851782924923 17851782926658
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 191 238129 238129 4194304 256 0 0 12 24 72832 0x7fe2d414d680 0x7fe2c7e24f40 524288 11403554 1277177012 17851782958358 17851782924923 17851783294044 17851783295759
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 194 238129 238129 4194304 256 0 0 8 24 74048 0x7fe2d67ec500 0x7fe2c7e24f80 524288 9971998 1116839528 17851783326518 17851783294044 17851783572605 17851783574332
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 197 238129 238129 4194304 256 0 0 12 24 75776 0x7fe2d67ec380 0x7fe2c7e24fc0 524288 4788676 536323888 17851783605412 17851783572605 17851783862525 17851783864245
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 200 238129 238129 4194304 256 0 0 12 24 76992 0x7fe2d67ec200 0x7fe2c7e25000 524288 10496241 1175548992 17851783902714 17851783862525 17851784138365 17851784140138
70 68 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 203 238129 238129 4194304 256 0 0 12 24 78464 0x7fe2d67ec080 0x7fe2c7e25040 524288 11254474 1260459736 17851784171147 17851784138365 17851784500446 17851784502099
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 206 238129 238129 4194304 256 0 0 12 24 79936 0x7fe2d414df00 0x7fe2c7e25080 524288 11308943 1266564232 17851784534368 17851784500446 17851784865247 17851784866980
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 209 238129 238129 4194304 256 0 0 8 24 81408 0x7fe2d414dd80 0x7fe2c7e250c0 524288 9969059 1116531716 17851784897639 17851784865247 17851785139647 17851785141433
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 212 238129 238129 4194304 256 0 0 12 24 83136 0x7fe2d414dc00 0x7fe2c7e25100 524288 4101249 459292572 17851785172763 17851785139647 17851785435168 17851785436936
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 215 238129 238129 4194304 256 0 0 12 24 84352 0x7fe2d414da80 0x7fe2c7e25140 524288 10552160 1181829580 17851785487385 17851785435168 17851785716928 17851785718719
75 73 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 218 238129 238129 4194304 256 0 0 12 24 85824 0x7fe2d414d900 0x7fe2c7e25180 524288 11311011 1266806536 17851785749208 17851785716928 17851786084129 17851786085730
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 221 238129 238129 4194304 256 0 0 12 24 87296 0x7fe2d414d780 0x7fe2c7e251c0 524288 11219564 1256568920 17851786117729 17851786084129 17851786457889 17851786459631
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 224 238129 238129 4194304 256 0 0 12 24 88768 0x7fe2d414d600 0x7fe2c7e25200 524288 9820308 1099748564 17851786490400 17851786457889 17851786735490 17851786737154
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 227 238129 238129 4194304 256 0 0 12 24 90752 0x7fe2d67ec480 0x7fe2c7e25240 524288 3671648 411187864 17851786768093 17851786735490 17851787037890 17851787039626
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 230 238129 238129 4194304 256 0 0 12 24 91968 0x7fe2d67ec300 0x7fe2c7e25280 524288 10077664 1128706364 17851787077675 17851787037890 17851787315331 17851787316989
80 78 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 233 238129 238129 4194304 256 0 0 12 24 93440 0x7fe2d67ec180 0x7fe2c7e252c0 524288 11126647 1246159484 17851787348009 17851787315331 17851787674692 17851787676360
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 236 238129 238129 4194304 256 0 0 12 24 94912 0x7fe2d67ec000 0x7fe2c7e25300 524288 11153488 1249170388 17851787708170 17851787674692 17851788032292 17851788034032
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 239 238129 238129 4194304 256 0 0 12 24 96384 0x7fe2d414de80 0x7fe2c7e25340 524288 8941596 1001449384 17851788064441 17851788032292 17851788306853 17851788308635
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 242 238129 238129 4194304 256 0 0 12 24 98368 0x7fe2d414dd00 0x7fe2c7e25380 524288 3497243 391708692 17851788339414 17851788306853 17851788613413 17851788614977
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 245 238129 238129 4194304 256 0 0 12 24 99584 0x7fe2d414db80 0x7fe2c7e253c0 524288 9670492 1083108004 17851788652536 17851788613413 17851788896934 17851788898650
85 83 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 248 238129 238129 4194304 256 0 0 12 24 101312 0x7fe2d414da00 0x7fe2c7e25400 524288 11021697 1234414332 17851788930049 17851788896934 17851789261734 17851789263381
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 251 238129 238129 4194304 256 0 0 12 24 102784 0x7fe2d414d880 0x7fe2c7e25440 524288 11132126 1246798012 17851789294310 17851789261734 17851789621895 17851789623662
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 254 238129 238129 4194304 256 0 0 12 24 104256 0x7fe2d414d700 0x7fe2c7e25480 524288 8689261 973198924 17851789653931 17851789621895 17851789898375 17851789900145
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 257 238129 238129 4194304 256 0 0 12 24 106240 0x7fe2d67ec580 0x7fe2c7e254c0 524288 3296359 369169100 17851789930734 17851789898375 17851790211816 17851790213657
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 260 238129 238129 4194304 256 0 0 12 24 107712 0x7fe2d67ec400 0x7fe2c7e25500 524288 10037455 1124195284 17851790252606 17851790211816 17851790489256 17851790491010
90 88 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 263 238129 238129 4194304 256 0 0 16 24 109440 0x7fe2d67ec280 0x7fe2c7e25540 524288 11174234 1251471072 17851790521940 17851790489256 17851790848457 17851790850182
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 266 238129 238129 4194304 256 0 0 16 24 111168 0x7fe2d67ec100 0x7fe2c7e25580 524288 11156391 1249494572 17851790881871 17851790848457 17851791213898 17851791215562
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 269 238129 238129 4194304 256 0 0 8 24 112896 0x7fe2d414df80 0x7fe2c7e255c0 524288 8453395 946749724 17851791246402 17851791213898 17851791491658 17851791493396
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 272 238129 238129 4194304 256 0 0 12 24 115136 0x7fe2d414de00 0x7fe2c7e25600 524288 3024996 338796148 17851791524785 17851791491658 17851791816619 17851791818288
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 275 238129 238129 4194304 256 0 0 12 24 116608 0x7fe2d414dc80 0x7fe2c7e25640 524288 9898403 1108578380 17851791856967 17851791816619 17851792098539 17851792100221
95 93 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 278 238129 238129 4194304 256 0 0 16 24 118336 0x7fe2d414db00 0x7fe2c7e25680 524288 11104075 1243642512 17851792131210 17851792098539 17851792457420 17851792459142
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 281 238129 238129 4194304 256 0 0 16 24 120064 0x7fe2d414d980 0x7fe2c7e256c0 524288 11097123 1242879504 17851792489141 17851792457420 17851792817900 17851792819553
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 284 238129 238129 4194304 256 0 0 12 24 121792 0x7fe2d414d800 0x7fe2c7e25700 524288 7310378 818624588 17851792849692 17851792817900 17851793096141 17851793097826
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 287 238129 238129 4194304 256 0 0 12 24 124032 0x7fe2d414d680 0x7fe2c7e25740 524288 2941237 329425624 17851793128535 17851793096141 17851793421421 17851793423188
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 290 238129 238129 4194304 256 0 0 12 24 125504 0x7fe2d67ec500 0x7fe2c7e25780 524288 9559653 1070725500 17851793461137 17851793421421 17851793695662 17851793697541
100 98 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 293 238129 238129 4194304 256 0 0 12 24 127488 0x7fe2d67ec380 0x7fe2c7e257c0 524288 11023374 1234615968 17851793727930 17851793695662 17851794053262 17851794055012
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 296 238129 238129 4194304 256 0 0 12 24 129216 0x7fe2d67ec200 0x7fe2c7e25800 524288 11082656 1241258564 17851794092211 17851794053262 17851794431823 17851794433593
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 299 238129 238129 4194304 256 0 0 12 24 130944 0x7fe2d67ec080 0x7fe2c7e25840 524288 6353255 711593988 17851794464132 17851794431823 17851794712304 17851794713966
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 302 238129 238129 4194304 256 0 0 12 24 133440 0x7fe2d414df00 0x7fe2c7e25880 524288 2939088 329191932 17851794744745 17851794712304 17851795055664 17851795057367
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 305 238129 238129 4194304 256 0 0 12 24 134912 0x7fe2d414dd80 0x7fe2c7e258c0 524288 8674328 971491172 17851795096216 17851795055664 17851795333105 17851795334710
105 103 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 308 238129 238129 4194304 256 0 0 12 24 136896 0x7fe2d414dc00 0x7fe2c7e25900 524288 10772675 1206512204 17851795365530 17851795333105 17851795695185 17851795696821
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 311 238129 238129 4194304 256 0 0 12 24 138880 0x7fe2d414da80 0x7fe2c7e25940 524288 10815365 1211244236 17851795728621 17851795695185 17851796056626 17851796058483
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 314 238129 238129 4194304 256 0 0 12 24 140864 0x7fe2d414d900 0x7fe2c7e25980 524288 5008411 560934772 17851796088352 17851796056626 17851796340466 17851796342176
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 317 238129 238129 4194304 256 0 0 12 24 143616 0x7fe2d414d780 0x7fe2c7e259c0 524288 2860023 320346980 17851796373065 17851796340466 17851796691027 17851796692677
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 320 238129 238129 4194304 256 0 0 12 24 145344 0x7fe2d414d600 0x7fe2c7e25a00 524288 6975002 781170540 17851796731096 17851796691027 17851796968787 17851796970440
110 108 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 323 238129 238129 4194304 256 0 0 12 24 147584 0x7fe2d67ec480 0x7fe2c7e25a40 524288 10836988 1213716384 17851797001379 17851796968787 17851797330868 17851797332751
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 326 238129 238129 4194304 256 0 0 12 24 149568 0x7fe2d67ec300 0x7fe2c7e25a80 524288 10812264 1210981884 17851797363950 17851797330868 17851797699349 17851797701022
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 329 238129 238129 4194304 256 0 0 12 24 151552 0x7fe2d67ec180 0x7fe2c7e25ac0 524288 3932869 440446248 17851797731601 17851797699349 17851797996469 17851797998205
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 332 238129 238129 4194304 256 0 0 12 24 154304 0x7fe2d67ec000 0x7fe2c7e25b00 524288 2846565 318818040 17851798029344 17851797996469 17851798366710 17851798368385
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 335 238129 238129 4194304 256 0 0 12 24 156288 0x7fe2d414de80 0x7fe2c7e25b40 524288 5834515 653448932 17851798406914 17851798366710 17851798658070 17851798659808
115 113 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 338 238129 238129 4194304 256 0 0 12 24 158784 0x7fe2d414dd00 0x7fe2c7e25b80 524288 10823083 1212141256 17851798690347 17851798658070 17851799020311 17851799022009
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 341 238129 238129 4194304 256 0 0 12 24 161024 0x7fe2d414db80 0x7fe2c7e25bc0 524288 10796310 1209189816 17851799053408 17851799020311 17851799383512 17851799385260
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 344 238129 238129 4194304 256 0 0 12 24 163264 0x7fe2d414da00 0x7fe2c7e25c00 524288 3807149 426378124 17851799416469 17851799383512 17851799687192 17851799688903
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 347 238129 238129 4194304 256 0 0 12 24 166528 0x7fe2d414d880 0x7fe2c7e25c40 524288 2876568 322203864 17851799719172 17851799687192 17851800076153 17851800121672
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 350 238129 238129 4194304 256 0 0 12 24 168512 0x7fe2d414d700 0x7fe2c7e25c80 524288 4400559 492855256 17851800141391 17851800076153 17851800403993 17851800405705
120 118 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 353 238129 238129 4194304 256 0 0 12 24 171264 0x7fe2d67ec580 0x7fe2c7e25cc0 524288 10574190 1184279480 17851800437434 17851800403993 17851800769434 17851800771206
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 356 238129 238129 4194304 256 0 0 12 24 173760 0x7fe2d67ec400 0x7fe2c7e25d00 524288 9756056 1092609072 17851800803335 17851800769434 17851801141275 17851801142977
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 359 238129 238129 4194304 256 0 0 12 24 176256 0x7fe2d67ec280 0x7fe2c7e25d40 524288 2937151 328969808 17851801174356 17851801141275 17851801460635 17851801462349
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 362 238129 238129 4194304 256 0 0 12 24 179776 0x7fe2d67ec100 0x7fe2c7e25d80 524288 2885783 323165516 17851801493368 17851801460635 17851801877596 17851801898488
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 365 238129 238129 4194304 256 0 0 12 24 182272 0x7fe2d414df80 0x7fe2c7e25dc0 524288 3062370 343015688 17851801918537 17851801877596 17851802207196 17851802209040
125 123 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 368 238129 238129 4194304 256 0 0 12 24 185536 0x7fe2d414de00 0x7fe2c7e25e00 524288 7965851 892150972 17851802241089 17851802207196 17851802586877 17851802634739
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 371 238129 238129 4194304 256 0 0 12 24 188544 0x7fe2d414dc80 0x7fe2c7e25e40 524288 7295385 817165120 17851802647099 17851802586877 17851803000478 17851803045659
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 374 238129 238129 4194304 256 0 0 12 24 191552 0x7fe2d414db00 0x7fe2c7e25e80 524288 2808501 314562680 17851803057569 17851803000478 17851803378718 17851803380351
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 377 238129 238129 4194304 256 0 0 12 24 195840 0x7fe2d414d980 0x7fe2c7e25ec0 524288 2834429 317413852 17851803410380 17851803378718 17851803844639 17851803889878
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 380 238129 238129 4194304 256 0 0 12 24 198592 0x7fe2d414d800 0x7fe2c7e25f00 524288 2829364 316816148 17851803909458 17851803844639 17851804211040 17851804212750
130 128 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 383 238129 238129 4194304 256 0 0 12 24 202368 0x7fe2d414d680 0x7fe2c7e25f40 524288 7156252 801412676 17851804244429 17851804211040 17851804606400 17851804648529
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 386 238129 238129 4194304 256 0 0 12 24 205888 0x7fe2d67ec500 0x7fe2c7e25f80 524288 6546543 733169316 17851804661659 17851804606400 17851805024321 17851805066159
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 389 238129 238129 4194304 256 0 0 12 24 209408 0x7fe2d67ec380 0x7fe2c7e25fc0 524288 2782400 311622300 17851805077389 17851805024321 17851805419362 17851805421170
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 392 238129 238129 4194304 256 0 0 12 24 214464 0x7fe2d67ec200 0x7fe2c7e26000 524288 2897542 324507732 17851805452989 17851805419362 17851805937923 17851805958267
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 395 238129 238129 4194304 256 0 0 12 24 217728 0x7fe2d67ec080 0x7fe2c7e26040 524288 2758709 309008928 17851805978236 17851805937923 17851806302243 17851806304268
135 133 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 398 238129 238129 4194304 256 0 0 12 24 222016 0x7fe2d414df00 0x7fe2c7e26080 524288 5361502 600451100 17851806335168 17851806302243 17851806715684 17851806759087
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 401 238129 238129 4194304 256 0 0 12 24 226048 0x7fe2d414dd80 0x7fe2c7e260c0 524288 5241560 587040032 17851806772477 17851806715684 17851807162405 17851807206206
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 404 238129 238129 4194304 256 0 0 12 24 230080 0x7fe2d414dc00 0x7fe2c7e26100 524288 2719578 304632596 17851807218236 17851807162405 17851807586246 17851807627715
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 407 238129 238129 4194304 256 0 0 12 24 235904 0x7fe2d414da80 0x7fe2c7e26140 524288 2929353 328060908 17851807640425 17851807586246 17851808183207 17851808224711
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 410 238129 238129 4194304 256 0 0 12 24 239424 0x7fe2d414d900 0x7fe2c7e26180 524288 2798443 313443644 17851808244280 17851808183207 17851808586727 17851808588512
140 138 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 413 238129 238129 4194304 256 0 0 12 24 244224 0x7fe2d414d780 0x7fe2c7e261c0 524288 5198688 582256312 17851808619471 17851808586727 17851809020488 17851809062250
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 416 238129 238129 4194304 256 0 0 12 24 248768 0x7fe2d414d600 0x7fe2c7e26200 524288 3227946 361493392 17851809075529 17851809020488 17851809479849 17851809522538
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 419 238129 238129 4194304 256 0 0 12 24 253312 0x7fe2d67ec480 0x7fe2c7e26240 524288 2765869 309719692 17851809534718 17851809479849 17851809928650 17851809947908
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 422 238129 238129 4194304 256 0 0 8 24 255552 0x7fe2d67ec300 0x7fe2c7e26280 524288 2372030 265583500 17851809961547 17851809928650 17851810579051 17851810623291
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 425 238129 238129 4194304 256 0 0 12 24 259840 0x7fe2d67ec180 0x7fe2c7e262c0 524288 2780688 311398384 17851810643791 17851810579051 17851811023211 17851811067380
145 143 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 428 238129 238129 4194304 256 0 0 12 24 265664 0x7fe2d67ec000 0x7fe2c7e26300 524288 3273190 366588524 17851811079870 17851811023211 17851811539532 17851811581427
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 431 238129 238129 4194304 256 0 0 12 24 271232 0x7fe2d414de80 0x7fe2c7e26340 524288 3706436 415100620 17851811593917 17851811539532 17851812051693 17851812094375
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 434 238129 238129 4194304 256 0 0 8 24 273216 0x7fe2d414dd00 0x7fe2c7e26380 524288 2392570 267988172 17851812106724 17851812051693 17851812564014 17851812605892
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 437 238129 238129 4194304 256 0 0 8 24 275712 0x7fe2d414db80 0x7fe2c7e263c0 524288 2380155 266528932 17851812617972 17851812564014 17851813336815 17851813378153
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 440 238129 238129 4194304 256 0 0 12 24 280768 0x7fe2d414da00 0x7fe2c7e26400 524288 2651241 296869496 17851813398483 17851813336815 17851813813936 17851813832062
150 148 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 443 238129 238129 4194304 256 0 0 12 24 287616 0x7fe2d414d880 0x7fe2c7e26440 524288 3358527 376130448 17851813847012 17851813813936 17851814349137 17851814394698
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 446 238129 238129 4194304 256 0 0 12 24 294208 0x7fe2d414d700 0x7fe2c7e26480 524288 3595083 402577832 17851814407058 17851814349137 17851814926578 17851814972024
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 449 238129 238129 4194304 256 0 0 8 24 296960 0x7fe2d67ec580 0x7fe2c7e264c0 524288 2398306 268633068 17851814983683 17851814926578 17851815496819 17851815538310
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 452 238129 238129 4194304 256 0 0 8 24 299968 0x7fe2d67ec400 0x7fe2c7e26500 524288 2389962 267666172 17851815550579 17851815496819 17851816367541 17851816409418
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 455 238129 238129 4194304 256 0 0 8 24 302720 0x7fe2d67ec280 0x7fe2c7e26540 524288 2388205 267475364 17851816429357 17851816367541 17851817028342 17851817069932
155 153 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 458 238129 238129 4194304 256 0 0 12 24 305472 0x7fe2d67ec100 0x7fe2c7e26580 524288 2579021 288843416 17851817081861 17851817028342 17851817710423 17851817752365
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 461 238129 238129 4194304 256 0 0 12 24 308224 0x7fe2d414df80 0x7fe2c7e265c0 524288 2592302 290292660 17851817764284 17851817710423 17851818386584 17851818432168
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 464 238129 238129 4194304 256 0 0 8 24 310976 0x7fe2d414de00 0x7fe2c7e26600 524288 2392252 267948208 17851818443947 17851818386584 17851819065625 17851819114581
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 467 238129 238129 4194304 256 0 0 8 24 313216 0x7fe2d414dc80 0x7fe2c7e26640 524288 2411106 269994500 17851819127690 17851819065625 17851820154427 17851820200824
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 470 238129 238129 4194304 256 0 0 8 24 315968 0x7fe2d414db00 0x7fe2c7e26680 524288 2438201 273086344 17851820221473 17851820154085 17851821239526 17851821308076
160 158 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 473 238129 238129 4194304 256 0 0 12 24 318720 0x7fe2d414d980 0x7fe2c7e266c0 524288 2595984 290719540 17851821320076 17851821239526 17851822378407 17851822445038
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 476 238129 238129 4194304 256 0 0 12 24 321472 0x7fe2d414d800 0x7fe2c7e26700 524288 2597137 290863004 17851822458078 17851822378407 17851823516328 17851823583740
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 479 238129 238129 4194304 256 0 0 8 24 324224 0x7fe2d414d680 0x7fe2c7e26740 524288 2428844 272065092 17851823596109 17851823516328 17851824627689 17851824694792
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 482 238129 238129 4194304 256 0 0 8 24 326464 0x7fe2d67ec500 0x7fe2c7e26780 524288 2466156 276132408 17851824706782 17851824627689 17851826578251 17851826648574
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 485 238129 238129 4194304 256 0 0 8 24 329216 0x7fe2d67ec380 0x7fe2c7e267c0 524288 2464191 275993492 17851826670493 17851826578251 17851828504333 17851828576246
165 163 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 488 238129 238129 4194304 256 0 0 12 24 331968 0x7fe2d67ec200 0x7fe2c7e26800 524288 2621651 293624628 17851828588236 17851828504333 17851830489935 17851830560797
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 491 238129 238129 4194304 256 0 0 12 24 334720 0x7fe2d67ec080 0x7fe2c7e26840 524288 2626645 294164516 17851830573217 17851830489935 17851832474737 17851832543988
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 494 238129 238129 4194304 256 0 0 8 24 337472 0x7fe2d414df00 0x7fe2c7e26880 524288 2455750 275010384 17851832555917 17851832474737 17851834403859 17851834473550
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 497 238129 238129 4194304 256 0 0 8 24 0 0x7fe2d414dd80 0x7fe2c7e268c0 524288 2496448 279555072 17851834487209 17851834403859 17851838027063 17851838150278
+168
Voir le fichier
@@ -0,0 +1,168 @@
Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,BeginNs,EndNs,CompleteNs
0,"__amd_rocclr_fillBufferAligned.kd",0,0,0,236725,236725,33554432,256,0,0,4,32,4160,0x0,0x7fc8d4204280,388118,388118,8813,3104952,524288,245379700,3015215,0,997822932,17834114824366,17833406340767,17834261594719,17834261709089
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,236725,236725,32768,256,0,0,12,24,13888,0x0,0x7fc8d4223f80,34226,34226,30380,273816,512,1732870,162674,0,6944808,17834266862991,17834261594719,17834267004326,17834267009117
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,236725,236725,4194304,256,0,0,12,24,14336,0x7fc8d71bf380,0x7fc8d4223fc0,166068,166068,13553,1328552,65536,78338107,1221027,0,315083700,17834267052826,17834267004326,17834267413606,17834267416207
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,236725,236725,4194304,256,0,0,16,24,15040,0x7fc8d71bf200,0x7fc8d4224000,309075,309075,24040,2472608,65536,207974461,2361927,0,833627480,17834267463736,17834267413606,17834267844007,17834267846456
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,236725,236725,4194304,256,0,0,16,24,15488,0x7fc8d71bf080,0x7fc8d4224040,312717,312717,25835,2501744,65536,225690218,2387810,0,904488700,17834267887865,17834267844007,17834268268807,17834268271026
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,236725,236725,4194304,256,0,0,12,24,15936,0x7fc8d4b91f00,0x7fc8d4224080,165971,165971,14858,1327776,65536,88194064,1222047,0,354501948,17834268313195,17834268268807,17834268603048,17834268605407
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,236725,236725,4194304,256,0,0,12,24,16384,0x7fc8d4b91d80,0x7fc8d42240c0,165219,165219,14018,1321760,65536,79047699,1212215,0,317927864,17834268645846,17834268603048,17834268930728,17834268933069
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,236725,236725,4194304,256,0,0,12,24,17088,0x7fc8d4b91c00,0x7fc8d4224100,164375,164375,14488,1315008,65536,91462162,1207066,0,367580624,17834268987318,17834268930728,17834269259369,17834269261561
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,236725,236725,4194304,256,0,0,16,24,17792,0x7fc8d4b91a80,0x7fc8d4224140,309703,309703,24852,2477632,65536,219777215,2368747,0,880840144,17834269301450,17834269259369,17834269686569,17834269688940
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,236725,236725,4194304,256,0,0,16,24,18496,0x7fc8d4b91900,0x7fc8d4224180,310809,310809,22257,2486480,65536,225212276,2380921,0,902579640,17834269729219,17834269686569,17834270108970,17834270111340
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,236725,236725,4194304,256,0,0,16,24,19200,0x7fc8d4b91780,0x7fc8d42241c0,165404,165404,14552,1323240,65536,80450116,1211697,0,323537692,17834270152509,17834270108970,17834270450890,17834270453171
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,236725,236725,4194304,256,0,0,16,24,19904,0x7fc8d4b91600,0x7fc8d4224200,165585,165585,14733,1324688,65536,89465853,1214515,0,359591852,17834270494250,17834270450890,17834270782411,17834270784683
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,236725,236725,4194304,256,0,0,12,24,20608,0x7fc8d71bf480,0x7fc8d4224240,166366,166366,14862,1330936,65536,91499648,1220000,0,367728464,17834270836062,17834270782411,17834271116011,17834271118425
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,236725,236725,4194304,256,0,0,16,24,21312,0x7fc8d71bf300,0x7fc8d4224280,312319,312319,24507,2498560,65536,233250131,2390649,0,934730296,17834271160384,17834271116011,17834271555532,17834271557414
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,236725,236725,4194304,256,0,0,16,24,22016,0x7fc8d71bf180,0x7fc8d42242c0,308649,308649,21619,2469200,65536,224851158,2359776,0,901134076,17834271600213,17834271555532,17834271944652,17834271946314
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,236725,236725,4194304,256,0,0,16,24,22720,0x7fc8d71bf000,0x7fc8d4224300,163725,163725,14889,1309808,65536,91154035,1208364,0,366346432,17834271989503,17834271944652,17834272252333,17834272254047
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,236725,236725,4194304,256,0,0,12,24,23424,0x7fc8d4b91e80,0x7fc8d4224340,163463,163463,14910,1307712,65536,95401874,1206350,0,383341996,17834272296706,17834272252333,17834272551373,17834272553179
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,236725,236725,4194304,256,0,0,12,24,24128,0x7fc8d4b91d00,0x7fc8d4224380,165174,165174,15006,1321400,65536,93783281,1212963,0,376860444,17834272601598,17834272551373,17834272857294,17834272859102
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,236725,236725,4194304,256,0,0,16,24,24832,0x7fc8d4b91b80,0x7fc8d42243c0,308899,308899,24067,2471200,65536,231007192,2364827,0,925758852,17834272905440,17834272857294,17834273249934,17834273251682
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,236725,236725,4194304,256,0,0,16,24,25536,0x7fc8d4b91a00,0x7fc8d4224400,309717,309717,24064,2477744,65536,223804023,2368967,0,896947924,17834273293911,17834273249934,17834273638895,17834273640612
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,236725,236725,4194304,256,0,0,12,24,26240,0x7fc8d4b91880,0x7fc8d4224440,164390,164390,15085,1315128,65536,93431898,1207629,0,375461760,17834273682421,17834273638895,17834273938095,17834273939705
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,236725,236725,4194304,256,0,0,12,24,26944,0x7fc8d4b91700,0x7fc8d4224480,164938,164938,14955,1319512,65536,107825297,1214954,0,433026808,17834273982454,17834273938095,17834274250575,17834274252317
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,236725,236725,4194304,256,0,0,12,24,27648,0x7fc8d71bf580,0x7fc8d42244c0,163684,163684,15364,1309480,65536,98572989,1202351,0,396025084,17834274303036,17834274250575,17834274560336,17834274561989
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,236725,236725,4194304,256,0,0,16,24,28608,0x7fc8d71bf400,0x7fc8d4224500,309216,309216,24259,2473736,65536,229456145,2366399,0,919555808,17834274608288,17834274560336,17834274967056,17834274968889
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,236725,236725,4194304,256,0,0,16,24,29312,0x7fc8d71bf280,0x7fc8d4224540,306859,306859,22328,2454880,65536,211370468,2340855,0,847210304,17834275011958,17834274967056,17834275359377,17834275361219
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,236725,236725,4194304,256,0,0,12,24,30016,0x7fc8d71bf100,0x7fc8d4224580,162796,162796,14816,1302376,65536,90130881,1195582,0,362264460,17834275404238,17834275359377,17834275659857,17834275661632
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,236725,236725,4194304,256,0,0,8,24,30976,0x7fc8d4b91f80,0x7fc8d42245c0,164176,164176,15291,1313416,65536,94637530,1203733,0,380286336,17834275703781,17834275659857,17834275964978,17834275966724
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,236725,236725,4194304,256,0,0,12,24,31680,0x7fc8d4b91e00,0x7fc8d4224600,164486,164486,15106,1315896,65536,98263113,1206137,0,394774388,17834276016083,17834275964978,17834276271378,17834276273017
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,236725,236725,4194304,256,0,0,16,24,32640,0x7fc8d4b91c80,0x7fc8d4224640,308147,308147,24483,2465184,65536,225461106,2358920,0,903576612,17834276314886,17834276271378,17834276663219,17834276665107
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,236725,236725,4194304,256,0,0,12,24,33600,0x7fc8d4b91b00,0x7fc8d4224680,306784,306784,21822,2454280,65536,212758018,2344118,0,852761708,17834276707936,17834276663219,17834277052179,17834277053737
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,236725,236725,4194304,256,0,0,12,24,34560,0x7fc8d4b91980,0x7fc8d42246c0,164291,164291,15379,1314336,65536,89768986,1209049,0,360811080,17834277096186,17834277052179,17834277355220,17834277357100
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,236725,236725,4194304,256,0,0,8,24,35520,0x7fc8d4b91800,0x7fc8d4224700,166338,166338,16385,1330712,65536,95949531,1221575,0,385529096,17834277398619,17834277355220,17834277660660,17834277662272
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,236725,236725,4194304,256,0,0,12,24,36224,0x7fc8d4b91680,0x7fc8d4224740,162847,162847,15060,1302784,65536,97505447,1200686,0,391750292,17834277710811,17834277660660,17834277967700,17834277969325
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,236725,236725,4194304,256,0,0,12,24,37184,0x7fc8d71bf500,0x7fc8d4224780,306864,306864,24043,2454920,65536,228596035,2350247,0,916117520,17834278011794,17834277967700,17834278362581,17834278364495
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,236725,236725,4194304,256,0,0,12,24,38144,0x7fc8d71bf380,0x7fc8d42247c0,307280,307280,22874,2458248,65536,219189165,2355632,0,878486864,17834278407854,17834278362581,17834278758901,17834278760595
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,236725,236725,4194304,256,0,0,12,24,39104,0x7fc8d71bf200,0x7fc8d4224800,163646,163646,15305,1309176,65536,92738259,1205867,0,372683892,17834278802324,17834278758901,17834279065622,17834279067307
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,236725,236725,4194304,256,0,0,8,24,40320,0x7fc8d71bf080,0x7fc8d4224840,162812,162812,15305,1302504,65536,91513072,1197944,0,367781628,17834279109276,17834279065622,17834279368342,17834279369940
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,236725,236725,4194304,256,0,0,12,24,41280,0x7fc8d4b91f00,0x7fc8d4224880,163697,163697,14743,1309584,65536,97528475,1204580,0,391844768,17834279418069,17834279368342,17834279676023,17834279677612
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,236725,236725,4194304,256,0,0,12,24,42240,0x7fc8d4b91d80,0x7fc8d42248c0,306817,306817,23855,2454544,65536,224074796,2348571,0,898027912,17834279723881,17834279676023,17834280077463,17834280079182
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,236725,236725,4194304,256,0,0,12,24,43200,0x7fc8d4b91c00,0x7fc8d4224900,303088,303088,21848,2424712,65536,215098226,2320002,0,862124472,17834280121761,17834280077463,17834280466424,17834280468003
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,236725,236725,4194304,256,0,0,8,24,44160,0x7fc8d4b91a80,0x7fc8d4224940,162715,162715,14617,1301728,65536,100141673,1199730,0,402297404,17834280509402,17834280466424,17834280770264,17834280771805
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,236725,236725,4194304,256,0,0,12,24,45376,0x7fc8d4b91900,0x7fc8d4224980,163608,163608,15486,1308872,65536,91950043,1202769,0,369547032,17834280813514,17834280770264,17834281073305,17834281075087
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,236725,236725,4194304,256,0,0,12,24,46336,0x7fc8d4b91780,0x7fc8d42249c0,162297,162297,14425,1298384,65536,94382812,1195314,0,379256192,17834281124096,17834281073305,17834281384345,17834281386110
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,236725,236725,4194304,256,0,0,12,24,47552,0x7fc8d4b91600,0x7fc8d4224a00,306664,306664,24786,2453320,65536,225485821,2347896,0,903674356,17834281432619,17834281384345,17834281788666,17834281790470
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,236725,236725,4194304,256,0,0,12,24,48512,0x7fc8d71bf480,0x7fc8d4224a40,304669,304669,22899,2437360,65536,214318449,2330625,0,859002420,17834281832979,17834281788666,17834282182906,17834282184770
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,236725,236725,4194304,256,0,0,8,24,49472,0x7fc8d71bf300,0x7fc8d4224a80,164032,164032,14631,1312264,65536,88858198,1205412,0,357162416,17834282227459,17834282182906,17834282489146,17834282490792
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,236725,236725,4194304,256,0,0,12,24,50688,0x7fc8d71bf180,0x7fc8d4224ac0,163201,163201,15807,1305616,65536,96721866,1200217,0,388622312,17834282533281,17834282489146,17834282793627,17834282795345
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,236725,236725,4194304,256,0,0,12,24,51648,0x7fc8d71bf000,0x7fc8d4224b00,161463,161463,14952,1291712,65536,88740842,1187214,0,356698560,17834282844754,17834282793627,17834283100827,17834283102377
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,236725,236725,4194304,256,0,0,12,24,52864,0x7fc8d4b91e80,0x7fc8d4224b40,303745,303745,22710,2429968,65536,201836625,2316360,0,809078756,17834283144876,17834283100827,17834283496508,17834283498217
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,236725,236725,4194304,256,0,0,12,24,54080,0x7fc8d4b91d00,0x7fc8d4224b80,301047,301047,21601,2408384,65536,210437020,2303682,0,843478572,17834283539956,17834283496508,17834283892508,17834283894117
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,236725,236725,4194304,256,0,0,8,24,55296,0x7fc8d4b91b80,0x7fc8d4224bc0,162428,162428,14903,1299432,65536,88474318,1194758,0,355627208,17834283936316,17834283892508,17834284193629,17834284195250
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,236725,236725,4194304,256,0,0,12,24,56768,0x7fc8d4b91a00,0x7fc8d4224c00,163629,163629,16950,1309040,65536,101217691,1198725,0,406601800,17834284237269,17834284193629,17834284495869,17834284497512
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,236725,236725,4194304,256,0,0,12,24,57728,0x7fc8d4b91880,0x7fc8d4224c40,163391,163391,14597,1307136,65536,91714320,1200360,0,368585112,17834284546191,17834284495869,17834284805790,17834284807455
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,236725,236725,4194304,256,0,0,12,24,58944,0x7fc8d4b91700,0x7fc8d4224c80,300221,300221,21845,2401776,65536,212739892,2297136,0,852693288,17834284848824,17834284805790,17834285192510,17834285194135
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,236725,236725,4194304,256,0,0,12,24,60160,0x7fc8d71bf580,0x7fc8d4224cc0,301545,301545,20283,2412368,65536,205629479,2301410,0,824246612,17834285238724,17834285192510,17834285579871,17834285581566
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,236725,236725,4194304,256,0,0,8,24,61376,0x7fc8d71bf400,0x7fc8d4224d00,163132,163132,15667,1305064,65536,95210655,1200481,0,382572852,17834285623274,17834285579871,17834285881151,17834285882808
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,236725,236725,4194304,256,0,0,12,24,62848,0x7fc8d71bf280,0x7fc8d4224d40,169065,169065,16375,1352528,65536,97879669,1245323,0,393262852,17834285924347,17834285881151,17834286199391,17834286201270
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,236725,236725,4194304,256,0,0,12,24,63808,0x7fc8d71bf100,0x7fc8d4224d80,162702,162702,15058,1301624,65536,92605328,1194089,0,372151888,17834286252129,17834286199391,17834286509952,17834286511732
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,236725,236725,4194304,256,0,0,12,24,65024,0x7fc8d4b91f80,0x7fc8d4224dc0,302903,302903,22609,2423232,65536,215042701,2319421,0,861904624,17834286559221,17834286509952,17834286905152,17834286906793
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,236725,236725,4194304,256,0,0,12,24,66240,0x7fc8d4b91e00,0x7fc8d4224e00,299934,299934,20991,2399480,65536,211568934,2288440,0,848010412,17834286949312,17834286905152,17834287299553,17834287301333
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,236725,236725,4194304,256,0,0,8,24,67456,0x7fc8d4b91c80,0x7fc8d4224e40,164917,164917,15176,1319344,65536,92895653,1215543,0,373328368,17834287342372,17834287299553,17834287601473,17834287603155
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,236725,236725,4194304,256,0,0,12,24,68928,0x7fc8d4b91b00,0x7fc8d4224e80,177796,177796,16578,1422376,65536,104994509,1313234,0,421714412,17834287645334,17834287601473,17834287915234,17834287916868
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,236725,236725,4194304,256,0,0,12,24,70144,0x7fc8d4b91980,0x7fc8d4224ec0,160811,160811,14705,1286496,65536,89629786,1181277,0,360258064,17834287965816,17834287915234,17834288223074,17834288224820
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,236725,236725,4194304,256,0,0,12,24,71616,0x7fc8d4b91800,0x7fc8d4224f00,302087,302087,23294,2416704,65536,219851616,2309099,0,881138856,17834288266549,17834288223074,17834288616835,17834288618460
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,236725,236725,4194304,256,0,0,12,24,72832,0x7fc8d4b91680,0x7fc8d4224f40,303611,303611,23005,2428896,65536,222137973,2319977,0,890282592,17834288661129,17834288616835,17834289007715,17834289009390
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,236725,236725,4194304,256,0,0,8,24,74048,0x7fc8d71bf500,0x7fc8d4224f80,163161,163161,15630,1305296,65536,91235959,1194973,0,366677940,17834289050369,17834289007715,17834289310436,17834289312333
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,236725,236725,4194304,256,0,0,12,24,75776,0x7fc8d71bf380,0x7fc8d4224fc0,183219,183219,17101,1465760,65536,109826885,1356619,0,441057852,17834289355122,17834289310436,17834289625796,17834289627395
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,236725,236725,4194304,256,0,0,12,24,76992,0x7fc8d71bf200,0x7fc8d4225000,162997,162997,15184,1303984,65536,88666144,1192526,0,356405896,17834289690813,17834289625796,17834289938917,17834289940647
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,236725,236725,4194304,256,0,0,12,24,78464,0x7fc8d71bf080,0x7fc8d4225040,301969,301969,22124,2415760,65536,214738349,2310781,0,860686468,17834289987216,17834289938917,17834290365157,17834290367057
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,236725,236725,4194304,256,0,0,12,24,79936,0x7fc8d4b91f00,0x7fc8d4225080,302753,302753,23164,2422032,65536,210241017,2311664,0,842698468,17834290408876,17834290365157,17834290767398,17834290769027
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,236725,236725,4194304,256,0,0,8,24,81408,0x7fc8d4b91d80,0x7fc8d42250c0,162581,162581,15730,1300656,65536,93338046,1195432,0,375088052,17834290811296,17834290767398,17834291075238,17834291077019
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,236725,236725,4194304,256,0,0,12,24,83136,0x7fc8d4b91c00,0x7fc8d4225100,192516,192516,18259,1540136,65536,115988784,1429576,0,465701400,17834291118798,17834291075238,17834291400198,17834291402111
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,236725,236725,4194304,256,0,0,12,24,84352,0x7fc8d4b91a80,0x7fc8d4225140,162889,162889,15404,1303120,65536,96009514,1198118,0,385765176,17834291450040,17834291400198,17834291712679,17834291714363
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,236725,236725,4194304,256,0,0,12,24,85824,0x7fc8d4b91900,0x7fc8d4225180,303894,303894,22975,2431160,65536,220298015,2321393,0,882931436,17834291756322,17834291712679,17834292106279,17834292108014
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,236725,236725,4194304,256,0,0,12,24,87296,0x7fc8d4b91780,0x7fc8d42251c0,299823,299823,22016,2398592,65536,213726362,2293812,0,856641476,17834292152253,17834292106279,17834292497480,17834292499214
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,236725,236725,4194304,256,0,0,12,24,88768,0x7fc8d4b91600,0x7fc8d4225200,162456,162456,15936,1299656,65536,96275564,1197182,0,386834488,17834292541063,17834292497480,17834292804840,17834292806386
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,236725,236725,4194304,256,0,0,12,24,90752,0x7fc8d71bf480,0x7fc8d4225240,203471,203471,18200,1627776,65536,117796929,1513037,0,472938496,17834292847715,17834292804840,17834293142121,17834293143698
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,236725,236725,4194304,256,0,0,12,24,91968,0x7fc8d71bf300,0x7fc8d4225280,162292,162292,15476,1298344,65536,93981779,1192840,0,377663004,17834293192997,17834293142121,17834293452041,17834293453861
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,236725,236725,4194304,256,0,0,12,24,93440,0x7fc8d71bf180,0x7fc8d42252c0,301740,301740,23035,2413928,65536,223216311,2308970,0,894601568,17834293501559,17834293452041,17834293849802,17834293851431
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,236725,236725,4194304,256,0,0,12,24,94912,0x7fc8d71bf000,0x7fc8d4225300,299586,299586,21971,2396696,65536,212866702,2295181,0,853196760,17834293895900,17834293849802,17834294243242,17834294245081
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,236725,236725,4194304,256,0,0,12,24,96384,0x7fc8d4b91e80,0x7fc8d4225340,162618,162618,15249,1300952,65536,98466108,1197652,0,395598028,17834294286870,17834294243242,17834294553963,17834294555623
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,236725,236725,4194304,256,0,0,12,24,98368,0x7fc8d4b91d00,0x7fc8d4225380,211130,211130,19059,1689048,65536,139997082,1578277,0,561732788,17834294597952,17834294553963,17834294888843,17834294890575
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,236725,236725,4194304,256,0,0,12,24,99584,0x7fc8d4b91b80,0x7fc8d42253c0,162454,162454,15664,1299640,65536,95675469,1195184,0,384430776,17834294938784,17834294888843,17834295197484,17834295199077
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,236725,236725,4194304,256,0,0,12,24,101312,0x7fc8d4b91a00,0x7fc8d4225400,298352,298352,22850,2386824,65536,218183439,2281773,0,874465752,17834295239986,17834295197484,17834295591724,17834295593397
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,236725,236725,4194304,256,0,0,12,24,102784,0x7fc8d4b91880,0x7fc8d4225440,299448,299448,22428,2395592,65536,208003050,2290833,0,833743560,17834295635696,17834295591724,17834295985005,17834295986638
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,236725,236725,4194304,256,0,0,12,24,104256,0x7fc8d4b91700,0x7fc8d4225480,161836,161836,15933,1294696,65536,98449694,1189411,0,395538516,17834296029047,17834295985005,17834296289485,17834296291350
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,236725,236725,4194304,256,0,0,12,24,106240,0x7fc8d71bf580,0x7fc8d42254c0,220777,220777,19935,1766224,65536,126795673,1647432,0,508938936,17834296332469,17834296289485,17834296633806,17834296635512
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,236725,236725,4194304,256,0,0,12,24,107712,0x7fc8d71bf400,0x7fc8d4225500,161888,161888,15580,1295112,65536,89962750,1188814,0,361583932,17834296685250,17834296633806,17834296943246,17834296945044
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,236725,236725,4194304,256,0,0,16,24,109440,0x7fc8d71bf280,0x7fc8d4225540,297291,297291,21409,2378336,65536,206695233,2272110,0,828513140,17834296991243,17834296943246,17834297338286,17834297340024
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,236725,236725,4194304,256,0,0,16,24,111168,0x7fc8d71bf100,0x7fc8d4225580,301879,301879,23718,2415040,65536,215905745,2301239,0,865353032,17834297383633,17834297338286,17834297732367,17834297734054
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,236725,236725,4194304,256,0,0,8,24,112896,0x7fc8d4b91f80,0x7fc8d42255c0,164601,164601,16231,1316816,65536,99833361,1209593,0,401091668,17834297775473,17834297732367,17834298041807,17834298043577
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,236725,236725,4194304,256,0,0,12,24,115136,0x7fc8d4b91e00,0x7fc8d4225600,229723,229723,19773,1837792,65536,149136492,1730381,0,598297608,17834298092205,17834298041807,17834298404048,17834298405698
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,236725,236725,4194304,256,0,0,12,24,116608,0x7fc8d4b91c80,0x7fc8d4225640,161402,161402,15123,1291224,65536,90921050,1187708,0,365422976,17834298454706,17834298404048,17834298712048,17834298713750
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,236725,236725,4194304,256,0,0,16,24,118336,0x7fc8d4b91b00,0x7fc8d4225680,298204,298204,20792,2385640,65536,197986138,2276652,0,793685384,17834298760439,17834298712048,17834299105809,17834299107450
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,236725,236725,4194304,256,0,0,16,24,120064,0x7fc8d4b91980,0x7fc8d42256c0,300595,300595,22494,2404768,65536,215379737,2301175,0,863254268,17834299150079,17834299105809,17834299496689,17834299498340
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,236725,236725,4194304,256,0,0,12,24,121792,0x7fc8d4b91800,0x7fc8d4225700,164958,164958,16370,1319672,65536,101616331,1214016,0,408212144,17834299539319,17834299496689,17834299801810,17834299803813
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,236725,236725,4194304,256,0,0,12,24,124032,0x7fc8d4b91680,0x7fc8d4225740,240645,240645,20516,1925168,65536,157732556,1813466,0,632674640,17834299844102,17834299801810,17834300163570,17834300165174
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,236725,236725,4194304,256,0,0,12,24,125504,0x7fc8d71bf500,0x7fc8d4225780,162126,162126,15768,1297016,65536,98187098,1194453,0,394504012,17834300214413,17834300163570,17834300475571,17834300477146
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,236725,236725,4194304,256,0,0,12,24,127488,0x7fc8d71bf380,0x7fc8d42257c0,302955,302955,20938,2423648,65536,205734897,2308541,0,824672836,17834300523855,17834300475571,17834300872531,17834300874236
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,236725,236725,4194304,256,0,0,12,24,129216,0x7fc8d71bf200,0x7fc8d4225800,298432,298432,20729,2387464,65536,202637622,2282225,0,812285600,17834300916045,17834300872531,17834301262772,17834301264587
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,236725,236725,4194304,256,0,0,12,24,130944,0x7fc8d71bf080,0x7fc8d4225840,171091,171091,16030,1368736,65536,100852134,1263541,0,405154688,17834301305746,17834301262772,17834301573972,17834301575609
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,236725,236725,4194304,256,0,0,12,24,133440,0x7fc8d4b91f00,0x7fc8d4225880,259655,259655,21249,2077248,65536,166745550,1964412,0,668732852,17834301617628,17834301573972,17834301938933,17834301940650
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,236725,236725,4194304,256,0,0,12,24,134912,0x7fc8d4b91d80,0x7fc8d42258c0,161815,161815,15866,1294528,65536,95893855,1188755,0,385320516,17834301990029,17834301938933,17834302259413,17834302260992
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,236725,236725,4194304,256,0,0,12,24,136896,0x7fc8d4b91c00,0x7fc8d4225900,296539,296539,20914,2372320,65536,202649671,2263614,0,812338056,17834302302771,17834302259413,17834302655254,17834302657002
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,236725,236725,4194304,256,0,0,12,24,138880,0x7fc8d4b91a80,0x7fc8d4225940,297031,297031,21172,2376256,65536,205901482,2265136,0,825344388,17834302698781,17834302655254,17834303044374,17834303046012
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,236725,236725,4194304,256,0,0,12,24,140864,0x7fc8d4b91900,0x7fc8d4225980,178771,178771,16738,1430176,65536,106947525,1324370,0,429537856,17834303087531,17834303044374,17834303357495,17834303359055
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,236725,236725,4194304,256,0,0,12,24,143616,0x7fc8d4b91780,0x7fc8d42259c0,280909,280909,23093,2247280,65536,190802329,2129530,0,764957064,17834303400584,17834303357495,17834303734775,17834303736465
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,236725,236725,4194304,256,0,0,12,24,145344,0x7fc8d4b91600,0x7fc8d4225a00,163019,163019,16590,1304160,65536,102331826,1195152,0,411073356,17834303785814,17834303734775,17834304045176,17834304046747
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,236725,236725,4194304,256,0,0,12,24,147584,0x7fc8d71bf480,0x7fc8d4225a40,296769,296769,21322,2374160,65536,203778534,2261266,0,816877520,17834304088806,17834304045176,17834304437496,17834304439028
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,236725,236725,4194304,256,0,0,12,24,149568,0x7fc8d71bf300,0x7fc8d4225a80,296072,296072,20953,2368584,65536,206833922,2259877,0,829074876,17834304479807,17834304437496,17834304828857,17834304830788
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,236725,236725,4194304,256,0,0,12,24,151552,0x7fc8d71bf180,0x7fc8d4225ac0,186912,186912,17450,1495304,65536,103138691,1380354,0,414306260,17834304870297,17834304828857,17834305160377,17834305162140
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,236725,236725,4194304,256,0,0,12,24,154304,0x7fc8d71bf000,0x7fc8d4225b00,300476,300476,23558,2403816,65536,195767935,2289652,0,784828060,17834305202979,17834305160377,17834305553338,17834305555040
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,236725,236725,4194304,256,0,0,12,24,156288,0x7fc8d4b91e80,0x7fc8d4225b40,171069,171069,16766,1368560,65536,101300694,1266522,0,406947060,17834305604099,17834305553338,17834305872538,17834305874242
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,236725,236725,4194304,256,0,0,12,24,158784,0x7fc8d4b91d00,0x7fc8d4225b80,299366,299366,19246,2394936,65536,164222368,2269854,0,658639616,17834305915891,17834305872538,17834306266619,17834306268682
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,236725,236725,4194304,256,0,0,12,24,161024,0x7fc8d4b91b80,0x7fc8d4225bc0,297382,297382,20708,2379064,65536,191601847,2264334,0,768152064,17834306309591,17834306266619,17834306661499,17834306663382
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,236725,236725,4194304,256,0,0,12,24,163264,0x7fc8d4b91a00,0x7fc8d4225c00,207412,207412,19074,1659304,65536,123377617,1541710,0,495275328,17834306703341,17834306661499,17834306993019,17834306994584
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,236725,236725,4194304,256,0,0,12,24,166528,0x7fc8d4b91880,0x7fc8d4225c40,341044,341044,25539,2728360,65536,230738852,2613176,0,924716048,17834307035523,17834306993019,17834307411260,17834307459113
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,236725,236725,4194304,256,0,0,12,24,168512,0x7fc8d4b91700,0x7fc8d4225c80,184919,184919,18033,1479360,65536,115675289,1368223,0,464448212,17834307478252,17834307411260,17834307767581,17834307769255
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,236725,236725,4194304,256,0,0,12,24,171264,0x7fc8d71bf580,0x7fc8d4225cc0,298024,298024,21863,2384200,65536,158606979,2238111,0,636177212,17834307811134,17834307767581,17834308161181,17834308162815
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,236725,236725,4194304,256,0,0,12,24,173760,0x7fc8d71bf400,0x7fc8d4225d00,297180,297180,20530,2377448,65536,184505727,2259504,0,739772484,17834308205604,17834308161181,17834308556062,17834308557885
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,236725,236725,4194304,256,0,0,12,24,176256,0x7fc8d71bf280,0x7fc8d4225d40,224815,224815,19630,1798528,65536,145776401,1689205,0,584851028,17834308598954,17834308556062,17834308900702,17834308902377
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,236725,236725,4194304,256,0,0,12,24,179776,0x7fc8d71bf100,0x7fc8d4225d80,381869,381869,27926,3054960,65536,257070858,2936653,0,1030042636,17834308943066,17834308900702,17834309347263,17834309366235
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,236725,236725,4194304,256,0,0,12,24,182272,0x7fc8d4b91f80,0x7fc8d4225dc0,212815,212815,19513,1702528,65536,122464861,1583033,0,491617708,17834309397585,17834309347263,17834309686303,17834309687957
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,236725,236725,4194304,256,0,0,12,24,185536,0x7fc8d4b91e00,0x7fc8d4225e00,310102,310102,24097,2480824,65536,185464783,2345934,0,743628116,17834309728316,17834309686303,17834310090304,17834310096947
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,236725,236725,4194304,256,0,0,12,24,188544,0x7fc8d4b91c80,0x7fc8d4225e40,311821,311821,20978,2494576,65536,179673646,2366407,0,720457404,17834310132456,17834310090304,17834310509824,17834310531006
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,236725,236725,4194304,256,0,0,12,24,191552,0x7fc8d4b91b00,0x7fc8d4225e80,266016,266016,21765,2128136,65536,177645979,2018546,0,712343952,17834310551946,17834310509824,17834310879745,17834310881678
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,236725,236725,4194304,256,0,0,12,24,195840,0x7fc8d4b91980,0x7fc8d4225ec0,462230,462230,31445,3697848,65536,327814997,3582185,0,1313021200,17834310921557,17834310879745,17834311373345,17834311392615
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,236725,236725,4194304,256,0,0,12,24,198592,0x7fc8d4b91800,0x7fc8d4225f00,243299,243299,20537,1946400,65536,168632596,1836482,0,676289424,17834311423864,17834311373345,17834311732706,17834311734556
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,236725,236725,4194304,256,0,0,12,24,202368,0x7fc8d4b91680,0x7fc8d4225f40,334675,334675,23818,2677408,65536,199877609,2554723,0,801277260,17834311774095,17834311732706,17834312160866,17834312179645
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,236725,236725,4194304,256,0,0,12,24,205888,0x7fc8d71bf500,0x7fc8d4225f80,333944,333944,23247,2671560,65536,207389401,2543268,0,831339332,17834312203145,17834312160866,17834312584067,17834312601845
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,236725,236725,4194304,256,0,0,12,24,209408,0x7fc8d71bf380,0x7fc8d4225fc0,307785,307785,23645,2462288,65536,204659723,2351204,0,820405932,17834312625324,17834312584067,17834312985508,17834312987395
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,236725,236725,4194304,256,0,0,12,24,214464,0x7fc8d71bf200,0x7fc8d4226000,543831,543831,36446,4350656,65536,400108703,4228041,0,1602203616,17834313028704,17834312985508,17834313528868,17834313545371
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,236725,236725,4194304,256,0,0,12,24,217728,0x7fc8d71bf080,0x7fc8d4226040,272076,272076,22079,2176616,65536,195969289,2069235,0,785630088,17834313580611,17834313528868,17834313907589,17834313909332
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,236725,236725,4194304,256,0,0,12,24,222016,0x7fc8d4b91f00,0x7fc8d4226080,366676,366676,27448,2933416,65536,245183051,2817157,0,982512760,17834313950611,17834313907589,17834314357029,17834314375181
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,236725,236725,4194304,256,0,0,12,24,226048,0x7fc8d4b91d80,0x7fc8d42260c0,364698,364698,28121,2917592,65536,255642502,2806900,0,1024333444,17834314399810,17834314357029,17834314802630,17834314845409
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,236725,236725,4194304,256,0,0,12,24,230080,0x7fc8d4b91c00,0x7fc8d4226100,347899,347899,25794,2783200,65536,242487603,2672104,0,971720320,17834314855839,17834314802630,17834315245191,17834315287608
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,236725,236725,4194304,256,0,0,12,24,235904,0x7fc8d4b91a80,0x7fc8d4226140,625481,625481,40686,5003856,65536,460031137,4879068,0,1841894612,17834315298628,17834315245191,17834315876071,17834315918383
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,236725,236725,4194304,256,0,0,12,24,239424,0x7fc8d4b91900,0x7fc8d4226180,302927,302927,23596,2423424,65536,213261601,2312174,0,854813768,17834315937612,17834315876071,17834316297832,17834316299403
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,236725,236725,4194304,256,0,0,12,24,244224,0x7fc8d4b91780,0x7fc8d42261c0,399075,399075,27608,3192608,65536,264195773,3080075,0,1058569392,17834316340782,17834316297832,17834316759753,17834316801851
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,236725,236725,4194304,256,0,0,12,24,248768,0x7fc8d4b91600,0x7fc8d4226200,392130,392130,27681,3137048,65536,289347031,3022706,0,1159165792,17834316812020,17834316759753,17834317239753,17834317281259
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,236725,236725,4194304,256,0,0,12,24,253312,0x7fc8d71bf480,0x7fc8d4226240,387952,387952,27807,3103624,65536,280753329,2989110,0,1124778064,17834317291418,17834317239753,17834317709354,17834317727518
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,236725,236725,4194304,256,0,0,8,24,255552,0x7fc8d71bf300,0x7fc8d4226280,719930,719930,44876,5759448,65536,543357386,5636111,0,2175169880,17834317752167,17834317709354,17834318374795,17834318418700
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,236725,236725,4194304,256,0,0,12,24,259840,0x7fc8d71bf180,0x7fc8d42262c0,364824,364824,27411,2918600,65536,263017562,2801039,0,1053835448,17834318438150,17834318374795,17834318836235,17834318879929
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,236725,236725,4194304,256,0,0,12,24,265664,0x7fc8d71bf000,0x7fc8d4226300,471292,471292,32403,3770344,65536,351197243,3653322,0,1406578836,17834318891029,17834318836235,17834319369036,17834319411026
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,236725,236725,4194304,256,0,0,12,24,271232,0x7fc8d4b91e80,0x7fc8d4226340,474138,474138,32968,3793112,65536,349572599,3680200,0,1400078536,17834319421405,17834319369036,17834319910157,17834319951892
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,236725,236725,4194304,256,0,0,8,24,273216,0x7fc8d4b91d00,0x7fc8d4226380,483314,483314,33001,3866520,65536,352783080,3753336,0,1412873680,17834319962552,17834319910157,17834320437198,17834320479809
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,236725,236725,4194304,256,0,0,8,24,275712,0x7fc8d4b91b80,0x7fc8d42263c0,880138,880138,52986,7041112,65536,675410808,6929733,0,2703384488,17834320490389,17834320437198,17834321229839,17834321272819
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,236725,236725,4194304,256,0,0,12,24,280768,0x7fc8d4b91a00,0x7fc8d4226400,425881,425881,29669,3407056,65536,318126163,3299396,0,1274275000,17834321292269,17834321229839,17834321724559,17834321742908
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,236725,236725,4194304,256,0,0,12,24,287616,0x7fc8d4b91880,0x7fc8d4226440,552000,552000,35408,4416008,65536,405168085,4305890,0,1622465864,17834321767237,17834321724559,17834322289360,17834322335643
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,236725,236725,4194304,256,0,0,12,24,294208,0x7fc8d4b91700,0x7fc8d4226480,551581,551581,36057,4412656,65536,409721582,4298465,0,1640670012,17834322347203,17834322289360,17834322879601,17834322924048
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,236725,236725,4194304,256,0,0,8,24,296960,0x7fc8d71bf580,0x7fc8d42264c0,563270,563270,36733,4506168,65536,422198219,4392694,0,1690538260,17834322935358,17834322879601,17834323460242,17834323501854
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,236725,236725,4194304,256,0,0,8,24,299968,0x7fc8d71bf400,0x7fc8d4226500,1041630,1041630,61508,8333048,65536,797586758,8218915,0,3192089132,17834323512054,17834323460072,17834324354792,17834324401882
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,236725,236725,4194304,256,0,0,8,24,302720,0x7fc8d71bf280,0x7fc8d4226540,721638,721638,44565,5773112,65536,538243078,5659185,0,2154714336,17834324420811,17834324354792,17834325038312,17834325080545
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,236725,236725,4194304,256,0,0,12,24,305472,0x7fc8d71bf100,0x7fc8d4226580,723659,723659,45227,5789280,65536,541683722,5671557,0,2168477180,17834325091305,17834325038312,17834325732233,17834325775538
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,236725,236725,4194304,256,0,0,12,24,308224,0x7fc8d4b91f80,0x7fc8d42265c0,724066,724066,45236,5792536,65536,554432325,5665808,0,2219470204,17834325786137,17834325732233,17834326425354,17834326470040
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,236725,236725,4194304,256,0,0,8,24,310976,0x7fc8d4b91e00,0x7fc8d4226600,727528,727528,45271,5820232,65536,542132432,5700957,0,2170273016,17834326481840,17834326425354,17834327121354,17834327165433
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,236725,236725,4194304,256,0,0,8,24,313216,0x7fc8d4b91c80,0x7fc8d4226640,1368716,1368716,77974,10949736,65536,1066748922,10813154,0,4268737600,17834327175473,17834327121354,17834328226315,17834328269906
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,236725,236725,4194304,256,0,0,8,24,315968,0x7fc8d4b91b00,0x7fc8d4226680,1369824,1369824,77831,10958600,65536,1076782474,10843115,0,4308871668,17834328288855,17834328226315,17834329311116,17834329374338
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,236725,236725,4194304,256,0,0,12,24,318720,0x7fc8d4b91980,0x7fc8d42266c0,1375124,1375124,78065,11001000,65536,1071881202,10865494,0,4289266868,17834329385588,17834329311116,17834330454158,17834330521830
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,236725,236725,4194304,256,0,0,12,24,321472,0x7fc8d4b91800,0x7fc8d4226700,1371238,1371238,77436,10969912,65536,1077779295,10853697,0,4312857984,17834330533269,17834330454158,17834331595599,17834331662981
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,236725,236725,4194304,256,0,0,8,24,324224,0x7fc8d4b91680,0x7fc8d4226740,1376130,1376130,77713,11009048,65536,1084688254,10886966,0,4340495408,17834331673821,17834331595599,17834332731920,17834332799413
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,236725,236725,4194304,256,0,0,8,24,326464,0x7fc8d71bf500,0x7fc8d4226780,2662336,2662336,142424,21298696,65536,2131580032,21184514,0,8528061380,17834332810773,17834332731920,17834334704242,17834334776354
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,236725,236725,4194304,256,0,0,8,24,329216,0x7fc8d71bf380,0x7fc8d42267c0,2670852,2670852,143342,21366824,65536,2131999864,21233521,0,8529740752,17834334795274,17834334704242,17834336653524,17834336720826
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,236725,236725,4194304,256,0,0,12,24,331968,0x7fc8d71bf200,0x7fc8d4226800,2670556,2670556,142721,21364456,65536,2122324716,21238623,0,8491039852,17834336731875,17834336653524,17834338654006,17834338725046
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,236725,236725,4194304,256,0,0,12,24,334720,0x7fc8d71bf080,0x7fc8d4226840,2669612,2669612,143666,21356904,65536,2113520736,21229473,0,8455823144,17834338736746,17834338654006,17834340663928,17834340732916
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,236725,236725,4194304,256,0,0,8,24,337472,0x7fc8d4b91f00,0x7fc8d4226880,2674293,2674293,143290,21394352,65536,2122181246,21263814,0,8490468052,17834340744566,17834340663928,17834342616730,17834342688017
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,236725,236725,4194304,256,0,0,8,24,0,0x7fc8d4b91d80,0x7fc8d42268c0,5256862,5256862,273842,42054904,65536,4229210368,41928959,0,16918583340,17834342699137,17834342616730,17834346261054,17834346333537
1 Index KernelName gpu-id queue-id queue-index pid tid grd wgr lds scr vgpr sgpr fbar sig obj GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES DispatchNs BeginNs EndNs CompleteNs
2 0 __amd_rocclr_fillBufferAligned.kd 0 0 0 236725 236725 33554432 256 0 0 4 32 4160 0x0 0x7fc8d4204280 388118 388118 8813 3104952 524288 245379700 3015215 0 997822932 17834114824366 17833406340767 17834261594719 17834261709089
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 236725 236725 32768 256 0 0 12 24 13888 0x0 0x7fc8d4223f80 34226 34226 30380 273816 512 1732870 162674 0 6944808 17834266862991 17834261594719 17834267004326 17834267009117
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 5 236725 236725 4194304 256 0 0 12 24 14336 0x7fc8d71bf380 0x7fc8d4223fc0 166068 166068 13553 1328552 65536 78338107 1221027 0 315083700 17834267052826 17834267004326 17834267413606 17834267416207
5 3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 8 236725 236725 4194304 256 0 0 16 24 15040 0x7fc8d71bf200 0x7fc8d4224000 309075 309075 24040 2472608 65536 207974461 2361927 0 833627480 17834267463736 17834267413606 17834267844007 17834267846456
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 11 236725 236725 4194304 256 0 0 16 24 15488 0x7fc8d71bf080 0x7fc8d4224040 312717 312717 25835 2501744 65536 225690218 2387810 0 904488700 17834267887865 17834267844007 17834268268807 17834268271026
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 14 236725 236725 4194304 256 0 0 12 24 15936 0x7fc8d4b91f00 0x7fc8d4224080 165971 165971 14858 1327776 65536 88194064 1222047 0 354501948 17834268313195 17834268268807 17834268603048 17834268605407
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 17 236725 236725 4194304 256 0 0 12 24 16384 0x7fc8d4b91d80 0x7fc8d42240c0 165219 165219 14018 1321760 65536 79047699 1212215 0 317927864 17834268645846 17834268603048 17834268930728 17834268933069
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 20 236725 236725 4194304 256 0 0 12 24 17088 0x7fc8d4b91c00 0x7fc8d4224100 164375 164375 14488 1315008 65536 91462162 1207066 0 367580624 17834268987318 17834268930728 17834269259369 17834269261561
10 8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 23 236725 236725 4194304 256 0 0 16 24 17792 0x7fc8d4b91a80 0x7fc8d4224140 309703 309703 24852 2477632 65536 219777215 2368747 0 880840144 17834269301450 17834269259369 17834269686569 17834269688940
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 26 236725 236725 4194304 256 0 0 16 24 18496 0x7fc8d4b91900 0x7fc8d4224180 310809 310809 22257 2486480 65536 225212276 2380921 0 902579640 17834269729219 17834269686569 17834270108970 17834270111340
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 29 236725 236725 4194304 256 0 0 16 24 19200 0x7fc8d4b91780 0x7fc8d42241c0 165404 165404 14552 1323240 65536 80450116 1211697 0 323537692 17834270152509 17834270108970 17834270450890 17834270453171
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 32 236725 236725 4194304 256 0 0 16 24 19904 0x7fc8d4b91600 0x7fc8d4224200 165585 165585 14733 1324688 65536 89465853 1214515 0 359591852 17834270494250 17834270450890 17834270782411 17834270784683
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 35 236725 236725 4194304 256 0 0 12 24 20608 0x7fc8d71bf480 0x7fc8d4224240 166366 166366 14862 1330936 65536 91499648 1220000 0 367728464 17834270836062 17834270782411 17834271116011 17834271118425
15 13 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 38 236725 236725 4194304 256 0 0 16 24 21312 0x7fc8d71bf300 0x7fc8d4224280 312319 312319 24507 2498560 65536 233250131 2390649 0 934730296 17834271160384 17834271116011 17834271555532 17834271557414
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 41 236725 236725 4194304 256 0 0 16 24 22016 0x7fc8d71bf180 0x7fc8d42242c0 308649 308649 21619 2469200 65536 224851158 2359776 0 901134076 17834271600213 17834271555532 17834271944652 17834271946314
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 44 236725 236725 4194304 256 0 0 16 24 22720 0x7fc8d71bf000 0x7fc8d4224300 163725 163725 14889 1309808 65536 91154035 1208364 0 366346432 17834271989503 17834271944652 17834272252333 17834272254047
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 47 236725 236725 4194304 256 0 0 12 24 23424 0x7fc8d4b91e80 0x7fc8d4224340 163463 163463 14910 1307712 65536 95401874 1206350 0 383341996 17834272296706 17834272252333 17834272551373 17834272553179
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 50 236725 236725 4194304 256 0 0 12 24 24128 0x7fc8d4b91d00 0x7fc8d4224380 165174 165174 15006 1321400 65536 93783281 1212963 0 376860444 17834272601598 17834272551373 17834272857294 17834272859102
20 18 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 53 236725 236725 4194304 256 0 0 16 24 24832 0x7fc8d4b91b80 0x7fc8d42243c0 308899 308899 24067 2471200 65536 231007192 2364827 0 925758852 17834272905440 17834272857294 17834273249934 17834273251682
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 56 236725 236725 4194304 256 0 0 16 24 25536 0x7fc8d4b91a00 0x7fc8d4224400 309717 309717 24064 2477744 65536 223804023 2368967 0 896947924 17834273293911 17834273249934 17834273638895 17834273640612
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 59 236725 236725 4194304 256 0 0 12 24 26240 0x7fc8d4b91880 0x7fc8d4224440 164390 164390 15085 1315128 65536 93431898 1207629 0 375461760 17834273682421 17834273638895 17834273938095 17834273939705
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 62 236725 236725 4194304 256 0 0 12 24 26944 0x7fc8d4b91700 0x7fc8d4224480 164938 164938 14955 1319512 65536 107825297 1214954 0 433026808 17834273982454 17834273938095 17834274250575 17834274252317
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 65 236725 236725 4194304 256 0 0 12 24 27648 0x7fc8d71bf580 0x7fc8d42244c0 163684 163684 15364 1309480 65536 98572989 1202351 0 396025084 17834274303036 17834274250575 17834274560336 17834274561989
25 23 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 68 236725 236725 4194304 256 0 0 16 24 28608 0x7fc8d71bf400 0x7fc8d4224500 309216 309216 24259 2473736 65536 229456145 2366399 0 919555808 17834274608288 17834274560336 17834274967056 17834274968889
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 71 236725 236725 4194304 256 0 0 16 24 29312 0x7fc8d71bf280 0x7fc8d4224540 306859 306859 22328 2454880 65536 211370468 2340855 0 847210304 17834275011958 17834274967056 17834275359377 17834275361219
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 74 236725 236725 4194304 256 0 0 12 24 30016 0x7fc8d71bf100 0x7fc8d4224580 162796 162796 14816 1302376 65536 90130881 1195582 0 362264460 17834275404238 17834275359377 17834275659857 17834275661632
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 77 236725 236725 4194304 256 0 0 8 24 30976 0x7fc8d4b91f80 0x7fc8d42245c0 164176 164176 15291 1313416 65536 94637530 1203733 0 380286336 17834275703781 17834275659857 17834275964978 17834275966724
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 80 236725 236725 4194304 256 0 0 12 24 31680 0x7fc8d4b91e00 0x7fc8d4224600 164486 164486 15106 1315896 65536 98263113 1206137 0 394774388 17834276016083 17834275964978 17834276271378 17834276273017
30 28 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 83 236725 236725 4194304 256 0 0 16 24 32640 0x7fc8d4b91c80 0x7fc8d4224640 308147 308147 24483 2465184 65536 225461106 2358920 0 903576612 17834276314886 17834276271378 17834276663219 17834276665107
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 86 236725 236725 4194304 256 0 0 12 24 33600 0x7fc8d4b91b00 0x7fc8d4224680 306784 306784 21822 2454280 65536 212758018 2344118 0 852761708 17834276707936 17834276663219 17834277052179 17834277053737
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 89 236725 236725 4194304 256 0 0 12 24 34560 0x7fc8d4b91980 0x7fc8d42246c0 164291 164291 15379 1314336 65536 89768986 1209049 0 360811080 17834277096186 17834277052179 17834277355220 17834277357100
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 92 236725 236725 4194304 256 0 0 8 24 35520 0x7fc8d4b91800 0x7fc8d4224700 166338 166338 16385 1330712 65536 95949531 1221575 0 385529096 17834277398619 17834277355220 17834277660660 17834277662272
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 95 236725 236725 4194304 256 0 0 12 24 36224 0x7fc8d4b91680 0x7fc8d4224740 162847 162847 15060 1302784 65536 97505447 1200686 0 391750292 17834277710811 17834277660660 17834277967700 17834277969325
35 33 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 98 236725 236725 4194304 256 0 0 12 24 37184 0x7fc8d71bf500 0x7fc8d4224780 306864 306864 24043 2454920 65536 228596035 2350247 0 916117520 17834278011794 17834277967700 17834278362581 17834278364495
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 101 236725 236725 4194304 256 0 0 12 24 38144 0x7fc8d71bf380 0x7fc8d42247c0 307280 307280 22874 2458248 65536 219189165 2355632 0 878486864 17834278407854 17834278362581 17834278758901 17834278760595
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 104 236725 236725 4194304 256 0 0 12 24 39104 0x7fc8d71bf200 0x7fc8d4224800 163646 163646 15305 1309176 65536 92738259 1205867 0 372683892 17834278802324 17834278758901 17834279065622 17834279067307
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 107 236725 236725 4194304 256 0 0 8 24 40320 0x7fc8d71bf080 0x7fc8d4224840 162812 162812 15305 1302504 65536 91513072 1197944 0 367781628 17834279109276 17834279065622 17834279368342 17834279369940
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 110 236725 236725 4194304 256 0 0 12 24 41280 0x7fc8d4b91f00 0x7fc8d4224880 163697 163697 14743 1309584 65536 97528475 1204580 0 391844768 17834279418069 17834279368342 17834279676023 17834279677612
40 38 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 113 236725 236725 4194304 256 0 0 12 24 42240 0x7fc8d4b91d80 0x7fc8d42248c0 306817 306817 23855 2454544 65536 224074796 2348571 0 898027912 17834279723881 17834279676023 17834280077463 17834280079182
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 116 236725 236725 4194304 256 0 0 12 24 43200 0x7fc8d4b91c00 0x7fc8d4224900 303088 303088 21848 2424712 65536 215098226 2320002 0 862124472 17834280121761 17834280077463 17834280466424 17834280468003
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 119 236725 236725 4194304 256 0 0 8 24 44160 0x7fc8d4b91a80 0x7fc8d4224940 162715 162715 14617 1301728 65536 100141673 1199730 0 402297404 17834280509402 17834280466424 17834280770264 17834280771805
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 122 236725 236725 4194304 256 0 0 12 24 45376 0x7fc8d4b91900 0x7fc8d4224980 163608 163608 15486 1308872 65536 91950043 1202769 0 369547032 17834280813514 17834280770264 17834281073305 17834281075087
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 125 236725 236725 4194304 256 0 0 12 24 46336 0x7fc8d4b91780 0x7fc8d42249c0 162297 162297 14425 1298384 65536 94382812 1195314 0 379256192 17834281124096 17834281073305 17834281384345 17834281386110
45 43 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 128 236725 236725 4194304 256 0 0 12 24 47552 0x7fc8d4b91600 0x7fc8d4224a00 306664 306664 24786 2453320 65536 225485821 2347896 0 903674356 17834281432619 17834281384345 17834281788666 17834281790470
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 131 236725 236725 4194304 256 0 0 12 24 48512 0x7fc8d71bf480 0x7fc8d4224a40 304669 304669 22899 2437360 65536 214318449 2330625 0 859002420 17834281832979 17834281788666 17834282182906 17834282184770
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 134 236725 236725 4194304 256 0 0 8 24 49472 0x7fc8d71bf300 0x7fc8d4224a80 164032 164032 14631 1312264 65536 88858198 1205412 0 357162416 17834282227459 17834282182906 17834282489146 17834282490792
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 137 236725 236725 4194304 256 0 0 12 24 50688 0x7fc8d71bf180 0x7fc8d4224ac0 163201 163201 15807 1305616 65536 96721866 1200217 0 388622312 17834282533281 17834282489146 17834282793627 17834282795345
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 140 236725 236725 4194304 256 0 0 12 24 51648 0x7fc8d71bf000 0x7fc8d4224b00 161463 161463 14952 1291712 65536 88740842 1187214 0 356698560 17834282844754 17834282793627 17834283100827 17834283102377
50 48 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 143 236725 236725 4194304 256 0 0 12 24 52864 0x7fc8d4b91e80 0x7fc8d4224b40 303745 303745 22710 2429968 65536 201836625 2316360 0 809078756 17834283144876 17834283100827 17834283496508 17834283498217
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 146 236725 236725 4194304 256 0 0 12 24 54080 0x7fc8d4b91d00 0x7fc8d4224b80 301047 301047 21601 2408384 65536 210437020 2303682 0 843478572 17834283539956 17834283496508 17834283892508 17834283894117
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 149 236725 236725 4194304 256 0 0 8 24 55296 0x7fc8d4b91b80 0x7fc8d4224bc0 162428 162428 14903 1299432 65536 88474318 1194758 0 355627208 17834283936316 17834283892508 17834284193629 17834284195250
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 152 236725 236725 4194304 256 0 0 12 24 56768 0x7fc8d4b91a00 0x7fc8d4224c00 163629 163629 16950 1309040 65536 101217691 1198725 0 406601800 17834284237269 17834284193629 17834284495869 17834284497512
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 155 236725 236725 4194304 256 0 0 12 24 57728 0x7fc8d4b91880 0x7fc8d4224c40 163391 163391 14597 1307136 65536 91714320 1200360 0 368585112 17834284546191 17834284495869 17834284805790 17834284807455
55 53 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 158 236725 236725 4194304 256 0 0 12 24 58944 0x7fc8d4b91700 0x7fc8d4224c80 300221 300221 21845 2401776 65536 212739892 2297136 0 852693288 17834284848824 17834284805790 17834285192510 17834285194135
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 161 236725 236725 4194304 256 0 0 12 24 60160 0x7fc8d71bf580 0x7fc8d4224cc0 301545 301545 20283 2412368 65536 205629479 2301410 0 824246612 17834285238724 17834285192510 17834285579871 17834285581566
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 164 236725 236725 4194304 256 0 0 8 24 61376 0x7fc8d71bf400 0x7fc8d4224d00 163132 163132 15667 1305064 65536 95210655 1200481 0 382572852 17834285623274 17834285579871 17834285881151 17834285882808
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 167 236725 236725 4194304 256 0 0 12 24 62848 0x7fc8d71bf280 0x7fc8d4224d40 169065 169065 16375 1352528 65536 97879669 1245323 0 393262852 17834285924347 17834285881151 17834286199391 17834286201270
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 170 236725 236725 4194304 256 0 0 12 24 63808 0x7fc8d71bf100 0x7fc8d4224d80 162702 162702 15058 1301624 65536 92605328 1194089 0 372151888 17834286252129 17834286199391 17834286509952 17834286511732
60 58 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 173 236725 236725 4194304 256 0 0 12 24 65024 0x7fc8d4b91f80 0x7fc8d4224dc0 302903 302903 22609 2423232 65536 215042701 2319421 0 861904624 17834286559221 17834286509952 17834286905152 17834286906793
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 176 236725 236725 4194304 256 0 0 12 24 66240 0x7fc8d4b91e00 0x7fc8d4224e00 299934 299934 20991 2399480 65536 211568934 2288440 0 848010412 17834286949312 17834286905152 17834287299553 17834287301333
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 179 236725 236725 4194304 256 0 0 8 24 67456 0x7fc8d4b91c80 0x7fc8d4224e40 164917 164917 15176 1319344 65536 92895653 1215543 0 373328368 17834287342372 17834287299553 17834287601473 17834287603155
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 182 236725 236725 4194304 256 0 0 12 24 68928 0x7fc8d4b91b00 0x7fc8d4224e80 177796 177796 16578 1422376 65536 104994509 1313234 0 421714412 17834287645334 17834287601473 17834287915234 17834287916868
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 185 236725 236725 4194304 256 0 0 12 24 70144 0x7fc8d4b91980 0x7fc8d4224ec0 160811 160811 14705 1286496 65536 89629786 1181277 0 360258064 17834287965816 17834287915234 17834288223074 17834288224820
65 63 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 188 236725 236725 4194304 256 0 0 12 24 71616 0x7fc8d4b91800 0x7fc8d4224f00 302087 302087 23294 2416704 65536 219851616 2309099 0 881138856 17834288266549 17834288223074 17834288616835 17834288618460
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 191 236725 236725 4194304 256 0 0 12 24 72832 0x7fc8d4b91680 0x7fc8d4224f40 303611 303611 23005 2428896 65536 222137973 2319977 0 890282592 17834288661129 17834288616835 17834289007715 17834289009390
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 194 236725 236725 4194304 256 0 0 8 24 74048 0x7fc8d71bf500 0x7fc8d4224f80 163161 163161 15630 1305296 65536 91235959 1194973 0 366677940 17834289050369 17834289007715 17834289310436 17834289312333
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 197 236725 236725 4194304 256 0 0 12 24 75776 0x7fc8d71bf380 0x7fc8d4224fc0 183219 183219 17101 1465760 65536 109826885 1356619 0 441057852 17834289355122 17834289310436 17834289625796 17834289627395
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 200 236725 236725 4194304 256 0 0 12 24 76992 0x7fc8d71bf200 0x7fc8d4225000 162997 162997 15184 1303984 65536 88666144 1192526 0 356405896 17834289690813 17834289625796 17834289938917 17834289940647
70 68 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 203 236725 236725 4194304 256 0 0 12 24 78464 0x7fc8d71bf080 0x7fc8d4225040 301969 301969 22124 2415760 65536 214738349 2310781 0 860686468 17834289987216 17834289938917 17834290365157 17834290367057
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 206 236725 236725 4194304 256 0 0 12 24 79936 0x7fc8d4b91f00 0x7fc8d4225080 302753 302753 23164 2422032 65536 210241017 2311664 0 842698468 17834290408876 17834290365157 17834290767398 17834290769027
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 209 236725 236725 4194304 256 0 0 8 24 81408 0x7fc8d4b91d80 0x7fc8d42250c0 162581 162581 15730 1300656 65536 93338046 1195432 0 375088052 17834290811296 17834290767398 17834291075238 17834291077019
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 212 236725 236725 4194304 256 0 0 12 24 83136 0x7fc8d4b91c00 0x7fc8d4225100 192516 192516 18259 1540136 65536 115988784 1429576 0 465701400 17834291118798 17834291075238 17834291400198 17834291402111
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 215 236725 236725 4194304 256 0 0 12 24 84352 0x7fc8d4b91a80 0x7fc8d4225140 162889 162889 15404 1303120 65536 96009514 1198118 0 385765176 17834291450040 17834291400198 17834291712679 17834291714363
75 73 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 218 236725 236725 4194304 256 0 0 12 24 85824 0x7fc8d4b91900 0x7fc8d4225180 303894 303894 22975 2431160 65536 220298015 2321393 0 882931436 17834291756322 17834291712679 17834292106279 17834292108014
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 221 236725 236725 4194304 256 0 0 12 24 87296 0x7fc8d4b91780 0x7fc8d42251c0 299823 299823 22016 2398592 65536 213726362 2293812 0 856641476 17834292152253 17834292106279 17834292497480 17834292499214
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 224 236725 236725 4194304 256 0 0 12 24 88768 0x7fc8d4b91600 0x7fc8d4225200 162456 162456 15936 1299656 65536 96275564 1197182 0 386834488 17834292541063 17834292497480 17834292804840 17834292806386
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 227 236725 236725 4194304 256 0 0 12 24 90752 0x7fc8d71bf480 0x7fc8d4225240 203471 203471 18200 1627776 65536 117796929 1513037 0 472938496 17834292847715 17834292804840 17834293142121 17834293143698
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 230 236725 236725 4194304 256 0 0 12 24 91968 0x7fc8d71bf300 0x7fc8d4225280 162292 162292 15476 1298344 65536 93981779 1192840 0 377663004 17834293192997 17834293142121 17834293452041 17834293453861
80 78 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 233 236725 236725 4194304 256 0 0 12 24 93440 0x7fc8d71bf180 0x7fc8d42252c0 301740 301740 23035 2413928 65536 223216311 2308970 0 894601568 17834293501559 17834293452041 17834293849802 17834293851431
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 236 236725 236725 4194304 256 0 0 12 24 94912 0x7fc8d71bf000 0x7fc8d4225300 299586 299586 21971 2396696 65536 212866702 2295181 0 853196760 17834293895900 17834293849802 17834294243242 17834294245081
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 239 236725 236725 4194304 256 0 0 12 24 96384 0x7fc8d4b91e80 0x7fc8d4225340 162618 162618 15249 1300952 65536 98466108 1197652 0 395598028 17834294286870 17834294243242 17834294553963 17834294555623
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 242 236725 236725 4194304 256 0 0 12 24 98368 0x7fc8d4b91d00 0x7fc8d4225380 211130 211130 19059 1689048 65536 139997082 1578277 0 561732788 17834294597952 17834294553963 17834294888843 17834294890575
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 245 236725 236725 4194304 256 0 0 12 24 99584 0x7fc8d4b91b80 0x7fc8d42253c0 162454 162454 15664 1299640 65536 95675469 1195184 0 384430776 17834294938784 17834294888843 17834295197484 17834295199077
85 83 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 248 236725 236725 4194304 256 0 0 12 24 101312 0x7fc8d4b91a00 0x7fc8d4225400 298352 298352 22850 2386824 65536 218183439 2281773 0 874465752 17834295239986 17834295197484 17834295591724 17834295593397
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 251 236725 236725 4194304 256 0 0 12 24 102784 0x7fc8d4b91880 0x7fc8d4225440 299448 299448 22428 2395592 65536 208003050 2290833 0 833743560 17834295635696 17834295591724 17834295985005 17834295986638
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 254 236725 236725 4194304 256 0 0 12 24 104256 0x7fc8d4b91700 0x7fc8d4225480 161836 161836 15933 1294696 65536 98449694 1189411 0 395538516 17834296029047 17834295985005 17834296289485 17834296291350
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 257 236725 236725 4194304 256 0 0 12 24 106240 0x7fc8d71bf580 0x7fc8d42254c0 220777 220777 19935 1766224 65536 126795673 1647432 0 508938936 17834296332469 17834296289485 17834296633806 17834296635512
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 260 236725 236725 4194304 256 0 0 12 24 107712 0x7fc8d71bf400 0x7fc8d4225500 161888 161888 15580 1295112 65536 89962750 1188814 0 361583932 17834296685250 17834296633806 17834296943246 17834296945044
90 88 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 263 236725 236725 4194304 256 0 0 16 24 109440 0x7fc8d71bf280 0x7fc8d4225540 297291 297291 21409 2378336 65536 206695233 2272110 0 828513140 17834296991243 17834296943246 17834297338286 17834297340024
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 266 236725 236725 4194304 256 0 0 16 24 111168 0x7fc8d71bf100 0x7fc8d4225580 301879 301879 23718 2415040 65536 215905745 2301239 0 865353032 17834297383633 17834297338286 17834297732367 17834297734054
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 269 236725 236725 4194304 256 0 0 8 24 112896 0x7fc8d4b91f80 0x7fc8d42255c0 164601 164601 16231 1316816 65536 99833361 1209593 0 401091668 17834297775473 17834297732367 17834298041807 17834298043577
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 272 236725 236725 4194304 256 0 0 12 24 115136 0x7fc8d4b91e00 0x7fc8d4225600 229723 229723 19773 1837792 65536 149136492 1730381 0 598297608 17834298092205 17834298041807 17834298404048 17834298405698
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 275 236725 236725 4194304 256 0 0 12 24 116608 0x7fc8d4b91c80 0x7fc8d4225640 161402 161402 15123 1291224 65536 90921050 1187708 0 365422976 17834298454706 17834298404048 17834298712048 17834298713750
95 93 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 278 236725 236725 4194304 256 0 0 16 24 118336 0x7fc8d4b91b00 0x7fc8d4225680 298204 298204 20792 2385640 65536 197986138 2276652 0 793685384 17834298760439 17834298712048 17834299105809 17834299107450
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 281 236725 236725 4194304 256 0 0 16 24 120064 0x7fc8d4b91980 0x7fc8d42256c0 300595 300595 22494 2404768 65536 215379737 2301175 0 863254268 17834299150079 17834299105809 17834299496689 17834299498340
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 284 236725 236725 4194304 256 0 0 12 24 121792 0x7fc8d4b91800 0x7fc8d4225700 164958 164958 16370 1319672 65536 101616331 1214016 0 408212144 17834299539319 17834299496689 17834299801810 17834299803813
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 287 236725 236725 4194304 256 0 0 12 24 124032 0x7fc8d4b91680 0x7fc8d4225740 240645 240645 20516 1925168 65536 157732556 1813466 0 632674640 17834299844102 17834299801810 17834300163570 17834300165174
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 290 236725 236725 4194304 256 0 0 12 24 125504 0x7fc8d71bf500 0x7fc8d4225780 162126 162126 15768 1297016 65536 98187098 1194453 0 394504012 17834300214413 17834300163570 17834300475571 17834300477146
100 98 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 293 236725 236725 4194304 256 0 0 12 24 127488 0x7fc8d71bf380 0x7fc8d42257c0 302955 302955 20938 2423648 65536 205734897 2308541 0 824672836 17834300523855 17834300475571 17834300872531 17834300874236
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 296 236725 236725 4194304 256 0 0 12 24 129216 0x7fc8d71bf200 0x7fc8d4225800 298432 298432 20729 2387464 65536 202637622 2282225 0 812285600 17834300916045 17834300872531 17834301262772 17834301264587
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 299 236725 236725 4194304 256 0 0 12 24 130944 0x7fc8d71bf080 0x7fc8d4225840 171091 171091 16030 1368736 65536 100852134 1263541 0 405154688 17834301305746 17834301262772 17834301573972 17834301575609
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 302 236725 236725 4194304 256 0 0 12 24 133440 0x7fc8d4b91f00 0x7fc8d4225880 259655 259655 21249 2077248 65536 166745550 1964412 0 668732852 17834301617628 17834301573972 17834301938933 17834301940650
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 305 236725 236725 4194304 256 0 0 12 24 134912 0x7fc8d4b91d80 0x7fc8d42258c0 161815 161815 15866 1294528 65536 95893855 1188755 0 385320516 17834301990029 17834301938933 17834302259413 17834302260992
105 103 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 308 236725 236725 4194304 256 0 0 12 24 136896 0x7fc8d4b91c00 0x7fc8d4225900 296539 296539 20914 2372320 65536 202649671 2263614 0 812338056 17834302302771 17834302259413 17834302655254 17834302657002
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 311 236725 236725 4194304 256 0 0 12 24 138880 0x7fc8d4b91a80 0x7fc8d4225940 297031 297031 21172 2376256 65536 205901482 2265136 0 825344388 17834302698781 17834302655254 17834303044374 17834303046012
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 314 236725 236725 4194304 256 0 0 12 24 140864 0x7fc8d4b91900 0x7fc8d4225980 178771 178771 16738 1430176 65536 106947525 1324370 0 429537856 17834303087531 17834303044374 17834303357495 17834303359055
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 317 236725 236725 4194304 256 0 0 12 24 143616 0x7fc8d4b91780 0x7fc8d42259c0 280909 280909 23093 2247280 65536 190802329 2129530 0 764957064 17834303400584 17834303357495 17834303734775 17834303736465
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 320 236725 236725 4194304 256 0 0 12 24 145344 0x7fc8d4b91600 0x7fc8d4225a00 163019 163019 16590 1304160 65536 102331826 1195152 0 411073356 17834303785814 17834303734775 17834304045176 17834304046747
110 108 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 323 236725 236725 4194304 256 0 0 12 24 147584 0x7fc8d71bf480 0x7fc8d4225a40 296769 296769 21322 2374160 65536 203778534 2261266 0 816877520 17834304088806 17834304045176 17834304437496 17834304439028
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 326 236725 236725 4194304 256 0 0 12 24 149568 0x7fc8d71bf300 0x7fc8d4225a80 296072 296072 20953 2368584 65536 206833922 2259877 0 829074876 17834304479807 17834304437496 17834304828857 17834304830788
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 329 236725 236725 4194304 256 0 0 12 24 151552 0x7fc8d71bf180 0x7fc8d4225ac0 186912 186912 17450 1495304 65536 103138691 1380354 0 414306260 17834304870297 17834304828857 17834305160377 17834305162140
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 332 236725 236725 4194304 256 0 0 12 24 154304 0x7fc8d71bf000 0x7fc8d4225b00 300476 300476 23558 2403816 65536 195767935 2289652 0 784828060 17834305202979 17834305160377 17834305553338 17834305555040
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 335 236725 236725 4194304 256 0 0 12 24 156288 0x7fc8d4b91e80 0x7fc8d4225b40 171069 171069 16766 1368560 65536 101300694 1266522 0 406947060 17834305604099 17834305553338 17834305872538 17834305874242
115 113 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 338 236725 236725 4194304 256 0 0 12 24 158784 0x7fc8d4b91d00 0x7fc8d4225b80 299366 299366 19246 2394936 65536 164222368 2269854 0 658639616 17834305915891 17834305872538 17834306266619 17834306268682
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 341 236725 236725 4194304 256 0 0 12 24 161024 0x7fc8d4b91b80 0x7fc8d4225bc0 297382 297382 20708 2379064 65536 191601847 2264334 0 768152064 17834306309591 17834306266619 17834306661499 17834306663382
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 344 236725 236725 4194304 256 0 0 12 24 163264 0x7fc8d4b91a00 0x7fc8d4225c00 207412 207412 19074 1659304 65536 123377617 1541710 0 495275328 17834306703341 17834306661499 17834306993019 17834306994584
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 347 236725 236725 4194304 256 0 0 12 24 166528 0x7fc8d4b91880 0x7fc8d4225c40 341044 341044 25539 2728360 65536 230738852 2613176 0 924716048 17834307035523 17834306993019 17834307411260 17834307459113
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 350 236725 236725 4194304 256 0 0 12 24 168512 0x7fc8d4b91700 0x7fc8d4225c80 184919 184919 18033 1479360 65536 115675289 1368223 0 464448212 17834307478252 17834307411260 17834307767581 17834307769255
120 118 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 353 236725 236725 4194304 256 0 0 12 24 171264 0x7fc8d71bf580 0x7fc8d4225cc0 298024 298024 21863 2384200 65536 158606979 2238111 0 636177212 17834307811134 17834307767581 17834308161181 17834308162815
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 356 236725 236725 4194304 256 0 0 12 24 173760 0x7fc8d71bf400 0x7fc8d4225d00 297180 297180 20530 2377448 65536 184505727 2259504 0 739772484 17834308205604 17834308161181 17834308556062 17834308557885
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 359 236725 236725 4194304 256 0 0 12 24 176256 0x7fc8d71bf280 0x7fc8d4225d40 224815 224815 19630 1798528 65536 145776401 1689205 0 584851028 17834308598954 17834308556062 17834308900702 17834308902377
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 362 236725 236725 4194304 256 0 0 12 24 179776 0x7fc8d71bf100 0x7fc8d4225d80 381869 381869 27926 3054960 65536 257070858 2936653 0 1030042636 17834308943066 17834308900702 17834309347263 17834309366235
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 365 236725 236725 4194304 256 0 0 12 24 182272 0x7fc8d4b91f80 0x7fc8d4225dc0 212815 212815 19513 1702528 65536 122464861 1583033 0 491617708 17834309397585 17834309347263 17834309686303 17834309687957
125 123 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 368 236725 236725 4194304 256 0 0 12 24 185536 0x7fc8d4b91e00 0x7fc8d4225e00 310102 310102 24097 2480824 65536 185464783 2345934 0 743628116 17834309728316 17834309686303 17834310090304 17834310096947
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 371 236725 236725 4194304 256 0 0 12 24 188544 0x7fc8d4b91c80 0x7fc8d4225e40 311821 311821 20978 2494576 65536 179673646 2366407 0 720457404 17834310132456 17834310090304 17834310509824 17834310531006
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 374 236725 236725 4194304 256 0 0 12 24 191552 0x7fc8d4b91b00 0x7fc8d4225e80 266016 266016 21765 2128136 65536 177645979 2018546 0 712343952 17834310551946 17834310509824 17834310879745 17834310881678
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 377 236725 236725 4194304 256 0 0 12 24 195840 0x7fc8d4b91980 0x7fc8d4225ec0 462230 462230 31445 3697848 65536 327814997 3582185 0 1313021200 17834310921557 17834310879745 17834311373345 17834311392615
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 380 236725 236725 4194304 256 0 0 12 24 198592 0x7fc8d4b91800 0x7fc8d4225f00 243299 243299 20537 1946400 65536 168632596 1836482 0 676289424 17834311423864 17834311373345 17834311732706 17834311734556
130 128 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 383 236725 236725 4194304 256 0 0 12 24 202368 0x7fc8d4b91680 0x7fc8d4225f40 334675 334675 23818 2677408 65536 199877609 2554723 0 801277260 17834311774095 17834311732706 17834312160866 17834312179645
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 386 236725 236725 4194304 256 0 0 12 24 205888 0x7fc8d71bf500 0x7fc8d4225f80 333944 333944 23247 2671560 65536 207389401 2543268 0 831339332 17834312203145 17834312160866 17834312584067 17834312601845
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 389 236725 236725 4194304 256 0 0 12 24 209408 0x7fc8d71bf380 0x7fc8d4225fc0 307785 307785 23645 2462288 65536 204659723 2351204 0 820405932 17834312625324 17834312584067 17834312985508 17834312987395
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 392 236725 236725 4194304 256 0 0 12 24 214464 0x7fc8d71bf200 0x7fc8d4226000 543831 543831 36446 4350656 65536 400108703 4228041 0 1602203616 17834313028704 17834312985508 17834313528868 17834313545371
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 395 236725 236725 4194304 256 0 0 12 24 217728 0x7fc8d71bf080 0x7fc8d4226040 272076 272076 22079 2176616 65536 195969289 2069235 0 785630088 17834313580611 17834313528868 17834313907589 17834313909332
135 133 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 398 236725 236725 4194304 256 0 0 12 24 222016 0x7fc8d4b91f00 0x7fc8d4226080 366676 366676 27448 2933416 65536 245183051 2817157 0 982512760 17834313950611 17834313907589 17834314357029 17834314375181
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 401 236725 236725 4194304 256 0 0 12 24 226048 0x7fc8d4b91d80 0x7fc8d42260c0 364698 364698 28121 2917592 65536 255642502 2806900 0 1024333444 17834314399810 17834314357029 17834314802630 17834314845409
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 404 236725 236725 4194304 256 0 0 12 24 230080 0x7fc8d4b91c00 0x7fc8d4226100 347899 347899 25794 2783200 65536 242487603 2672104 0 971720320 17834314855839 17834314802630 17834315245191 17834315287608
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 407 236725 236725 4194304 256 0 0 12 24 235904 0x7fc8d4b91a80 0x7fc8d4226140 625481 625481 40686 5003856 65536 460031137 4879068 0 1841894612 17834315298628 17834315245191 17834315876071 17834315918383
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 410 236725 236725 4194304 256 0 0 12 24 239424 0x7fc8d4b91900 0x7fc8d4226180 302927 302927 23596 2423424 65536 213261601 2312174 0 854813768 17834315937612 17834315876071 17834316297832 17834316299403
140 138 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 413 236725 236725 4194304 256 0 0 12 24 244224 0x7fc8d4b91780 0x7fc8d42261c0 399075 399075 27608 3192608 65536 264195773 3080075 0 1058569392 17834316340782 17834316297832 17834316759753 17834316801851
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 416 236725 236725 4194304 256 0 0 12 24 248768 0x7fc8d4b91600 0x7fc8d4226200 392130 392130 27681 3137048 65536 289347031 3022706 0 1159165792 17834316812020 17834316759753 17834317239753 17834317281259
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 419 236725 236725 4194304 256 0 0 12 24 253312 0x7fc8d71bf480 0x7fc8d4226240 387952 387952 27807 3103624 65536 280753329 2989110 0 1124778064 17834317291418 17834317239753 17834317709354 17834317727518
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 422 236725 236725 4194304 256 0 0 8 24 255552 0x7fc8d71bf300 0x7fc8d4226280 719930 719930 44876 5759448 65536 543357386 5636111 0 2175169880 17834317752167 17834317709354 17834318374795 17834318418700
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 425 236725 236725 4194304 256 0 0 12 24 259840 0x7fc8d71bf180 0x7fc8d42262c0 364824 364824 27411 2918600 65536 263017562 2801039 0 1053835448 17834318438150 17834318374795 17834318836235 17834318879929
145 143 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 428 236725 236725 4194304 256 0 0 12 24 265664 0x7fc8d71bf000 0x7fc8d4226300 471292 471292 32403 3770344 65536 351197243 3653322 0 1406578836 17834318891029 17834318836235 17834319369036 17834319411026
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 431 236725 236725 4194304 256 0 0 12 24 271232 0x7fc8d4b91e80 0x7fc8d4226340 474138 474138 32968 3793112 65536 349572599 3680200 0 1400078536 17834319421405 17834319369036 17834319910157 17834319951892
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 434 236725 236725 4194304 256 0 0 8 24 273216 0x7fc8d4b91d00 0x7fc8d4226380 483314 483314 33001 3866520 65536 352783080 3753336 0 1412873680 17834319962552 17834319910157 17834320437198 17834320479809
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 437 236725 236725 4194304 256 0 0 8 24 275712 0x7fc8d4b91b80 0x7fc8d42263c0 880138 880138 52986 7041112 65536 675410808 6929733 0 2703384488 17834320490389 17834320437198 17834321229839 17834321272819
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 440 236725 236725 4194304 256 0 0 12 24 280768 0x7fc8d4b91a00 0x7fc8d4226400 425881 425881 29669 3407056 65536 318126163 3299396 0 1274275000 17834321292269 17834321229839 17834321724559 17834321742908
150 148 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 443 236725 236725 4194304 256 0 0 12 24 287616 0x7fc8d4b91880 0x7fc8d4226440 552000 552000 35408 4416008 65536 405168085 4305890 0 1622465864 17834321767237 17834321724559 17834322289360 17834322335643
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 446 236725 236725 4194304 256 0 0 12 24 294208 0x7fc8d4b91700 0x7fc8d4226480 551581 551581 36057 4412656 65536 409721582 4298465 0 1640670012 17834322347203 17834322289360 17834322879601 17834322924048
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 449 236725 236725 4194304 256 0 0 8 24 296960 0x7fc8d71bf580 0x7fc8d42264c0 563270 563270 36733 4506168 65536 422198219 4392694 0 1690538260 17834322935358 17834322879601 17834323460242 17834323501854
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 452 236725 236725 4194304 256 0 0 8 24 299968 0x7fc8d71bf400 0x7fc8d4226500 1041630 1041630 61508 8333048 65536 797586758 8218915 0 3192089132 17834323512054 17834323460072 17834324354792 17834324401882
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 455 236725 236725 4194304 256 0 0 8 24 302720 0x7fc8d71bf280 0x7fc8d4226540 721638 721638 44565 5773112 65536 538243078 5659185 0 2154714336 17834324420811 17834324354792 17834325038312 17834325080545
155 153 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 458 236725 236725 4194304 256 0 0 12 24 305472 0x7fc8d71bf100 0x7fc8d4226580 723659 723659 45227 5789280 65536 541683722 5671557 0 2168477180 17834325091305 17834325038312 17834325732233 17834325775538
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 461 236725 236725 4194304 256 0 0 12 24 308224 0x7fc8d4b91f80 0x7fc8d42265c0 724066 724066 45236 5792536 65536 554432325 5665808 0 2219470204 17834325786137 17834325732233 17834326425354 17834326470040
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 464 236725 236725 4194304 256 0 0 8 24 310976 0x7fc8d4b91e00 0x7fc8d4226600 727528 727528 45271 5820232 65536 542132432 5700957 0 2170273016 17834326481840 17834326425354 17834327121354 17834327165433
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 467 236725 236725 4194304 256 0 0 8 24 313216 0x7fc8d4b91c80 0x7fc8d4226640 1368716 1368716 77974 10949736 65536 1066748922 10813154 0 4268737600 17834327175473 17834327121354 17834328226315 17834328269906
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 470 236725 236725 4194304 256 0 0 8 24 315968 0x7fc8d4b91b00 0x7fc8d4226680 1369824 1369824 77831 10958600 65536 1076782474 10843115 0 4308871668 17834328288855 17834328226315 17834329311116 17834329374338
160 158 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 473 236725 236725 4194304 256 0 0 12 24 318720 0x7fc8d4b91980 0x7fc8d42266c0 1375124 1375124 78065 11001000 65536 1071881202 10865494 0 4289266868 17834329385588 17834329311116 17834330454158 17834330521830
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 476 236725 236725 4194304 256 0 0 12 24 321472 0x7fc8d4b91800 0x7fc8d4226700 1371238 1371238 77436 10969912 65536 1077779295 10853697 0 4312857984 17834330533269 17834330454158 17834331595599 17834331662981
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 479 236725 236725 4194304 256 0 0 8 24 324224 0x7fc8d4b91680 0x7fc8d4226740 1376130 1376130 77713 11009048 65536 1084688254 10886966 0 4340495408 17834331673821 17834331595599 17834332731920 17834332799413
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 482 236725 236725 4194304 256 0 0 8 24 326464 0x7fc8d71bf500 0x7fc8d4226780 2662336 2662336 142424 21298696 65536 2131580032 21184514 0 8528061380 17834332810773 17834332731920 17834334704242 17834334776354
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 485 236725 236725 4194304 256 0 0 8 24 329216 0x7fc8d71bf380 0x7fc8d42267c0 2670852 2670852 143342 21366824 65536 2131999864 21233521 0 8529740752 17834334795274 17834334704242 17834336653524 17834336720826
165 163 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 488 236725 236725 4194304 256 0 0 12 24 331968 0x7fc8d71bf200 0x7fc8d4226800 2670556 2670556 142721 21364456 65536 2122324716 21238623 0 8491039852 17834336731875 17834336653524 17834338654006 17834338725046
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 491 236725 236725 4194304 256 0 0 12 24 334720 0x7fc8d71bf080 0x7fc8d4226840 2669612 2669612 143666 21356904 65536 2113520736 21229473 0 8455823144 17834338736746 17834338654006 17834340663928 17834340732916
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 494 236725 236725 4194304 256 0 0 8 24 337472 0x7fc8d4b91f00 0x7fc8d4226880 2674293 2674293 143290 21394352 65536 2122181246 21263814 0 8490468052 17834340744566 17834340663928 17834342616730 17834342688017
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 497 236725 236725 4194304 256 0 0 8 24 0 0x7fc8d4b91d80 0x7fc8d42268c0 5256862 5256862 273842 42054904 65536 4229210368 41928959 0 16918583340 17834342699137 17834342616730 17834346261054 17834346333537
+5
Voir le fichier
@@ -0,0 +1,5 @@
pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
+5
Voir le fichier
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
+5
Voir le fichier
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
+5
Voir le fichier
@@ -0,0 +1,5 @@
pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
+5
Voir le fichier
@@ -0,0 +1,5 @@
pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES
gpu:
range:
kernel:
+21
Voir le fichier
@@ -0,0 +1,21 @@
pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_BUSY_CU_CYCLES SQ_WAVE_CYCLES SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ SQC_TC_DATA_WRITE_REQ GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_SH_FIFO_BUSY_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum
pmc: SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES SQC_ICACHE_MISSES_DUPLICATE GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_SH_FIFO_CMD_BUSY_sum TA_SH_FIFO_ADDR_BUSY_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum
pmc: SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE SQC_DCACHE_REQ_READ_1 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_SH_FIFO_DATA_BUSY_sum TA_SH_FIFO_DATA_SFIFO_BUSY_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum
pmc: SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_SH_FIFO_DATA_TFIFO_BUSY_sum TA_SQ_TA_CMD_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum
pmc: SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 SQ_INSTS_VALU_MUL_F32 TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_SP_TA_ADDR_CYCLES_sum TA_SP_TA_DATA_CYCLES_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_STALL_sum
pmc: SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 SQ_INSTS_VALU_INT64 TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_SH_FIFO_ADDR_STARVED_WHILE_BUSY_CYCLES_sum TA_SH_FIFO_CMD_STARVED_WHILE_BUSY_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_IO_CREDIT_STALL_sum TCC_EA_WRREQ_GMI_CREDIT_STALL_sum TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum
pmc: SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_WAIT_ANY TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_SH_FIFO_DATA_STARVED_WHILE_BUSY_CYCLES_sum TA_TA_SH_FIFO_STARVED_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_ATOMIC_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum
pmc: SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_BUFFER_WAVEFRONTS_sum TA_BUFFER_READ_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_EA_RDREQ_IO_CREDIT_STALL_sum TCC_EA_RDREQ_GMI_CREDIT_STALL_sum TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum TCC_TAG_STALL_sum
pmc: SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum
pmc: SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum TA_BUFFER_TOTAL_CYCLES_sum TA_BUFFER_COALESCABLE_WAVEFRONTS_sum TCC_EA_RDREQ_DRAM_sum TCC_EA_WRREQ_DRAM_sum TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum
pmc: SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TCC_EA_ATOMIC_LEVEL_sum
pmc: SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31]
pmc: SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31]
pmc: TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31]
pmc: TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31]
pmc: TA_FLAT_COALESCEABLE_WAVEFRONTS_sum TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31]
pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31]
gpu:
range:
kernel:
+168
Voir le fichier
@@ -0,0 +1,168 @@
Index,KernelName,gpu-id
0,__amd_rocclr_fillBufferAligned.kd,0
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0
1 Index KernelName gpu-id
2 0 __amd_rocclr_fillBufferAligned.kd 0
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0
5 3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0
10 8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0
15 13 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0
20 18 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0
25 23 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0
30 28 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0
35 33 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0
40 38 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0
45 43 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0
50 48 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0
55 53 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0
60 58 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0
65 63 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0
70 68 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0
75 73 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0
80 78 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0
85 83 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0
90 88 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0
95 93 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0
100 98 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0
105 103 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0
110 108 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0
115 113 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0
120 118 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0
125 123 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0
130 128 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0
135 133 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0
140 138 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0
145 143 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0
150 148 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0
155 153 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0
160 158 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0
165 163 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0
Diff de fichier supprimé car une ou plusieurs lignes sont trop longues
+11
Voir le fichier
@@ -0,0 +1,11 @@
KernelName,Count,Sum(ns),Mean(ns),Median(ns),Pct
"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",1,3357122.0,3357122.0,3357122.0,7.840630919671416
"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,1724001.0,1724001.0,1724001.0,4.026441560999106
"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",1,1714881.0,1714881.0,1714881.0,4.005141604075466
"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",1,1696801.0,1696801.0,1696801.0,3.9629153736829874
"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",1,1672801.0,1672801.0,1672801.0,3.906862855462883
"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",1,1664801.0,1664801.0,1664801.0,3.888178682722848
"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",1,885601.0,885601.0,885601.0,2.0683402578434524
"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",1,879680.0,879680.0,879680.0,2.0545116344942342
"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",1,868961.0,868961.0,868961.0,2.02947717854418
"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",1,859681.0,859681.0,859681.0,2.0078035381657395
1 KernelName Count Sum(ns) Mean(ns) Median(ns) Pct
2 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 1 3357122.0 3357122.0 3357122.0 7.840630919671416
3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 1 1724001.0 1724001.0 1724001.0 4.026441560999106
4 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 1 1714881.0 1714881.0 1714881.0 4.005141604075466
5 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 1 1696801.0 1696801.0 1696801.0 3.9629153736829874
6 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 1 1672801.0 1672801.0 1672801.0 3.906862855462883
7 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 1 1664801.0 1664801.0 1664801.0 3.888178682722848
8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 1 885601.0 885601.0 885601.0 2.0683402578434524
9 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 1 879680.0 879680.0 879680.0 2.0545116344942342
10 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 1 868961.0 868961.0 868961.0 2.02947717854418
11 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 1 859681.0 859681.0 859681.0 2.0078035381657395
+9
Voir le fichier
@@ -0,0 +1,9 @@
Metric,Count,Unit
VALU - Vector,494.8622754491018,Instr per wave
VMEM,7.958083832335329,Instr per wave
LDS,0.0,Instr per wave
VALU - MFMA,0.0,Instr per wave
SALU,24.520958083832337,Instr per wave
SMEM,1.8023952095808384,Instr per wave
Branch,10.179640718562874,Instr per wave
GDS,0.0,Instr per wave
1 Metric Count Unit
2 VALU - Vector 494.8622754491018 Instr per wave
3 VMEM 7.958083832335329 Instr per wave
4 LDS 0.0 Instr per wave
5 VALU - MFMA 0.0 Instr per wave
6 SALU 24.520958083832337 Instr per wave
7 SMEM 1.8023952095808384 Instr per wave
8 Branch 10.179640718562874 Instr per wave
9 GDS 0.0 Instr per wave
+16
Voir le fichier
@@ -0,0 +1,16 @@
Metric,Count,Unit
INT32,176.1556886227545,Instr per wave
INT64,6.970059880239521,Instr per wave
F16-ADD,0.0,Instr per wave
F16-MUL,0.0,Instr per wave
F16-FMA,76.33532934131736,Instr per wave
F16-Trans,0.0,Instr per wave
F32-ADD,0.0,Instr per wave
F32-MUL,0.0,Instr per wave
F32-FMA,144.51497005988023,Instr per wave
F32-Trans,0.0,Instr per wave
F64-ADD,0.0,Instr per wave
F64-MUL,0.0,Instr per wave
F64-FMA,76.33532934131736,Instr per wave
F64-Trans,0.0,Instr per wave
Conversion,0.0,Instr per wave
1 Metric Count Unit
2 INT32 176.1556886227545 Instr per wave
3 INT64 6.970059880239521 Instr per wave
4 F16-ADD 0.0 Instr per wave
5 F16-MUL 0.0 Instr per wave
6 F16-FMA 76.33532934131736 Instr per wave
7 F16-Trans 0.0 Instr per wave
8 F32-ADD 0.0 Instr per wave
9 F32-MUL 0.0 Instr per wave
10 F32-FMA 144.51497005988023 Instr per wave
11 F32-Trans 0.0 Instr per wave
12 F64-ADD 0.0 Instr per wave
13 F64-MUL 0.0 Instr per wave
14 F64-FMA 76.33532934131736 Instr per wave
15 F64-Trans 0.0 Instr per wave
16 Conversion 0.0 Instr per wave
+9
Voir le fichier
@@ -0,0 +1,9 @@
type,Count
Buffer Instr,0.0
Buffer Read,0.0
Buffer Write,0.0
Buffer Atomic,0.0
Flat Instr,7.958083832335329
Flat Read,7.952095808383233
Flat Write,0.005988023952095809
Flat Atomic,0.0
1 type Count
2 Buffer Instr 0.0
3 Buffer Read 0.0
4 Buffer Write 0.0
5 Buffer Atomic 0.0
6 Flat Instr 7.958083832335329
7 Flat Read 7.952095808383233
8 Flat Write 0.005988023952095809
9 Flat Atomic 0.0
+6
Voir le fichier
@@ -0,0 +1,6 @@
type,Count
MFMA-I8,0.0
MFMA-F16,0.0
MFMA-BF16,0.0
MFMA-F32,0.0
MFMA-F64,0.0
1 type Count
2 MFMA-I8 0.0
3 MFMA-F16 0.0
4 MFMA-BF16 0.0
5 MFMA-F32 0.0
6 MFMA-F64 0.0
+26
Voir le fichier
@@ -0,0 +1,26 @@
Info
invdev
06fa5f860366
AMD EPYC 7282 16-Core Processor
Ubuntu 20.04.5 LTS
5.11.0-27-generic
5.1.3-66
Wed Sep 28 20:50:32 2022 ()
gfx90a
8
104
4
64
32
1024
16
8192
1700
1600
800
1600
32
mi200
56
1638.4
roofline|SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF
1 Info
2 invdev
3 06fa5f860366
4 AMD EPYC 7282 16-Core Processor
5 Ubuntu 20.04.5 LTS
6 5.11.0-27-generic
7 5.1.3-66
8 Wed Sep 28 20:50:32 2022 ()
9 gfx90a
10 8
11 104
12 4
13 64
14 32
15 1024
16 16
17 8192
18 1700
19 1600
20 800
21 1600
22 32
23 mi200
24 56
25 1638.4
26 roofline|SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF
+7
Voir le fichier
@@ -0,0 +1,7 @@
Metric,Value
valu_flops_pop,32.86522814467785
mfma_flops_bf16_pop,0.0
mfma_flops_f16_pop,0.0
mfma_flops_f32_pop,0.0
mfma_flops_f64_pop,0.0
mfma_flops_i8_pop,0.0
1 Metric Value
2 valu_flops_pop 32.86522814467785
3 mfma_flops_bf16_pop 0.0
4 mfma_flops_f16_pop 0.0
5 mfma_flops_f32_pop 0.0
6 mfma_flops_f64_pop 0.0
7 mfma_flops_i8_pop 0.0
+8
Voir le fichier
@@ -0,0 +1,8 @@
Metric,Avg,Min,Max,Unit
IPC (Avg),0.7041533174396638,0.02534724389619167,1.15944860531231,Instr/cycle
IPC (Issue),1.0,1.0,1.0,Instr/cycle
SALU Util,2.625564540636618,0.029705405919730424,27.217319335633324,Pct
VALU Util,58.3677767471036,0.7574878509531259,98.94796544288582,Pct
VALU Active Threads,64.0,64.0,64.0,Threads
MFMA Util,0.0,0.0,0.0,Pct
MFMA Instr Cycles,,,,Cycles/instr
1 Metric Avg Min Max Unit
2 IPC (Avg) 0.7041533174396638 0.02534724389619167 1.15944860531231 Instr/cycle
3 IPC (Issue) 1.0 1.0 1.0 Instr/cycle
4 SALU Util 2.625564540636618 0.029705405919730424 27.217319335633324 Pct
5 VALU Util 58.3677767471036 0.7574878509531259 98.94796544288582 Pct
6 VALU Active Threads 64.0 64.0 64.0 Threads
7 MFMA Util 0.0 0.0 0.0 Pct
8 MFMA Instr Cycles Cycles/instr
+7
Voir le fichier
@@ -0,0 +1,7 @@
Metric,Avg,Min,Max,Unit
FLOPs (Total),38039.760479041914,0.0,524800.0,Ops per wave
INT8 OPs,0.0,0.0,0.0,Ops per wave
F16 OPs,9770.922155688622,0.0,524800.0,Ops per wave
BF16 OPs,0.0,0.0,0.0,Ops per wave
F32 OPs,18497.91616766467,0.0,524800.0,Ops per wave
F64 OPs,9770.922155688622,0.0,524800.0,Ops per wave
1 Metric Avg Min Max Unit
2 FLOPs (Total) 38039.760479041914 0.0 524800.0 Ops per wave
3 INT8 OPs 0.0 0.0 0.0 Ops per wave
4 F16 OPs 9770.922155688622 0.0 524800.0 Ops per wave
5 BF16 OPs 0.0 0.0 0.0 Ops per wave
6 F32 OPs 18497.91616766467 0.0 524800.0 Ops per wave
7 F64 OPs 9770.922155688622 0.0 524800.0 Ops per wave
+5
Voir le fichier
@@ -0,0 +1,5 @@
Metric,Value
Utilization,0.0
Access Rate,0.0
Bandwith (Pct-of-Peak),0.0
Bank Conflict Rate,
1 Metric Value
2 Utilization 0.0
3 Access Rate 0.0
4 Bandwith (Pct-of-Peak) 0.0
5 Bank Conflict Rate
+12
Voir le fichier
@@ -0,0 +1,12 @@
Metric,Avg,Min,Max,Unit
Wave Cycles,18296.269474052384,1894.2776184082031,258229.23516845703,Cycles/wave
LDS Instrs,0.0,0.0,0.0,Instr per wave
Bandwidth,0.0,0.0,0.0,Bytes per wave
Bank Conficts/Access,,,,Conflicts/access
Index Accesses,0.0,0.0,0.0,Cycles per wave
Atomic Cycles,0.0,0.0,0.0,Cycles per wave
Bank Conflict,0.0,0.0,0.0,Cycles per wave
Addr Conflict,0.0,0.0,0.0,Cycles per wave
Unaligned Stall,0.0,0.0,0.0,Cycles per wave
Mem Violations,0.0,0.0,0.0, per wave
LDS Latency,,,,Cycles
1 Metric Avg Min Max Unit
2 Wave Cycles 18296.269474052384 1894.2776184082031 258229.23516845703 Cycles/wave
3 LDS Instrs 0.0 0.0 0.0 Instr per wave
4 Bandwidth 0.0 0.0 0.0 Bytes per wave
5 Bank Conficts/Access Conflicts/access
6 Index Accesses 0.0 0.0 0.0 Cycles per wave
7 Atomic Cycles 0.0 0.0 0.0 Cycles per wave
8 Bank Conflict 0.0 0.0 0.0 Cycles per wave
9 Addr Conflict 0.0 0.0 0.0 Cycles per wave
10 Unaligned Stall 0.0 0.0 0.0 Cycles per wave
11 Mem Violations 0.0 0.0 0.0 per wave
12 LDS Latency Cycles
+3
Voir le fichier
@@ -0,0 +1,3 @@
Metric,Value
Bandwidth,27.441870036596768
Cache Hit,99.56538959749767
1 Metric Value
2 Bandwidth 27.441870036596768
3 Cache Hit 99.56538959749767
+6
Voir le fichier
@@ -0,0 +1,6 @@
Metric,Mean,Min,Max,Unit
Req,127.76646706586827,9.0,1835.0,Req per wave
Hits,127.5332046782899,8.993011474609375,1834.9175720214844,Hits per wave
Misses - Non Duplicated,0.0017574104720247006,0.0,0.109375,Misses per wave
Misses - Duplicated,0.23150497710633422,0.00677490234375,3.79296875,Misses per wave
Cache Hit,99.56538959749767,75.6103515625,99.99550801206999,Pct
1 Metric Mean Min Max Unit
2 Req 127.76646706586827 9.0 1835.0 Req per wave
3 Hits 127.5332046782899 8.993011474609375 1834.9175720214844 Hits per wave
4 Misses - Non Duplicated 0.0017574104720247006 0.0 0.109375 Misses per wave
5 Misses - Duplicated 0.23150497710633422 0.00677490234375 3.79296875 Misses per wave
6 Cache Hit 99.56538959749767 75.6103515625 99.99550801206999 Pct
+3
Voir le fichier
@@ -0,0 +1,3 @@
Metric,Value
Bandwidth,0.9345053588728524
Cache Hit,97.79806879466166
1 Metric Value
2 Bandwidth 0.9345053588728524
3 Cache Hit 97.79806879466166
+13
Voir le fichier
@@ -0,0 +1,13 @@
Metric,Mean,Min,Max,Unit
Req,1.8023952095808384,1.0,7.0,Req per wave
Hits,1.770159293077663,0.0,6.987329483032227,Req per wave
Misses - Non Duplicated,0.001501757227732036,0.00042724609375,0.109375,Req per wave
Misses- Duplicated,0.030734159275443255,0.012243270874023438,0.890625,Req per wave
Cache Hit,97.79806879466166,0.0,99.8189926147461,Pct
Read Req (Total),1.8023952095808384,1.0,7.0,Req per wave
Atomic Req,0.0,0.0,0.0,Req per wave
Read Req (1 DWord),0.5868263473053892,0.0,2.0,Req per wave
Read Req (2 DWord),1.0059880239520957,0.0,2.0,Req per wave
Read Req (4 DWord),0.20359281437125748,0.0,2.0,Req per wave
Read Req (8 DWord),0.005988023952095809,0.0,1.0,Req per wave
Read Req (16 DWord),0.0,0.0,0.0,Req per wave
1 Metric Mean Min Max Unit
2 Req 1.8023952095808384 1.0 7.0 Req per wave
3 Hits 1.770159293077663 0.0 6.987329483032227 Req per wave
4 Misses - Non Duplicated 0.001501757227732036 0.00042724609375 0.109375 Req per wave
5 Misses- Duplicated 0.030734159275443255 0.012243270874023438 0.890625 Req per wave
6 Cache Hit 97.79806879466166 0.0 99.8189926147461 Pct
7 Read Req (Total) 1.8023952095808384 1.0 7.0 Req per wave
8 Atomic Req 0.0 0.0 0.0 Req per wave
9 Read Req (1 DWord) 0.5868263473053892 0.0 2.0 Req per wave
10 Read Req (2 DWord) 1.0059880239520957 0.0 2.0 Req per wave
11 Read Req (4 DWord) 0.20359281437125748 0.0 2.0 Req per wave
12 Read Req (8 DWord) 0.005988023952095809 0.0 1.0 Req per wave
13 Read Req (16 DWord) 0.0 0.0 0.0 Req per wave
+5
Voir le fichier
@@ -0,0 +1,5 @@
Metric,Mean,Min,Max,Unit
Read Req,0.001501757227732036,0.00042724609375,0.109375,Req per wave
Write Req,0.0,0.0,0.0,Req per wave
Atomic Req,0.0,0.0,0.0,Req per wave
Stall,0.0,0.0,0.0,Cycles per wave
1 Metric Mean Min Max Unit
2 Read Req 0.001501757227732036 0.00042724609375 0.109375 Req per wave
3 Write Req 0.0 0.0 0.0 Req per wave
4 Atomic Req 0.0 0.0 0.0 Req per wave
5 Stall 0.0 0.0 0.0 Cycles per wave
+17
Voir le fichier
@@ -0,0 +1,17 @@
Metric,Avg,Min,Max,Unit
TA Busy,60.05179215393539,0.9559106795575751,91.38774974744675,Pct
TC2TA Addr Stall,39.00120735349709,0.018892582078970366,71.91598141411671,Pct
TC2TA Data Stall,0.3245565066341392,0.0,54.20093660790125,Pct
TD2TA Addr Stall,0.0,0.0,0.0,Pct
Total Instructions,7.958083832335329,1.0,8.0,Instr per wave
Flat Instr,7.958083832335329,1.0,8.0,Instr per wave
Flat Read Instr,7.952095808383233,0.0,8.0,Instr per wave
Flat Write Instr,0.005988023952095809,0.0,1.0,Instr per wave
Flat Atomic Instr,0.0,0.0,0.0,Instr per wave
Buffer Instr,0.0,0.0,0.0,Instr per wave
Buffer Read Instr,0.0,0.0,0.0,Instr per wave
Buffer Write Instr,0.0,0.0,0.0,Instr per wave
Buffer Atomic Instr,0.0,0.0,0.0,Instr per wave
Buffer Total Cylces,0.0,0.0,0.0,Cycles per wave
Buffer Coalesced Read,0.0,0.0,0.0,Cycles per wave
Buffer Coalesced Write,0.0,0.0,0.0,Cycles per wave
1 Metric Avg Min Max Unit
2 TA Busy 60.05179215393539 0.9559106795575751 91.38774974744675 Pct
3 TC2TA Addr Stall 39.00120735349709 0.018892582078970366 71.91598141411671 Pct
4 TC2TA Data Stall 0.3245565066341392 0.0 54.20093660790125 Pct
5 TD2TA Addr Stall 0.0 0.0 0.0 Pct
6 Total Instructions 7.958083832335329 1.0 8.0 Instr per wave
7 Flat Instr 7.958083832335329 1.0 8.0 Instr per wave
8 Flat Read Instr 7.952095808383233 0.0 8.0 Instr per wave
9 Flat Write Instr 0.005988023952095809 0.0 1.0 Instr per wave
10 Flat Atomic Instr 0.0 0.0 0.0 Instr per wave
11 Buffer Instr 0.0 0.0 0.0 Instr per wave
12 Buffer Read Instr 0.0 0.0 0.0 Instr per wave
13 Buffer Write Instr 0.0 0.0 0.0 Instr per wave
14 Buffer Atomic Instr 0.0 0.0 0.0 Instr per wave
15 Buffer Total Cylces 0.0 0.0 0.0 Cycles per wave
16 Buffer Coalesced Read 0.0 0.0 0.0 Cycles per wave
17 Buffer Coalesced Write 0.0 0.0 0.0 Cycles per wave
+8
Voir le fichier
@@ -0,0 +1,8 @@
Metric,Avg,Min,Max,Unit
TD Busy,79.08056398970129,4.481455007913706,95.2557378605352,Pct
TC2TD Stall,63.61922366802417,3.9358792568078758,93.87501248382047,Pct
SPI2TD Stall,0.007817740810349489,0.0,0.01905204047427641,Pct
Coalescable Instr,4.790419161676646,0.0,8.0,Instr per wave
Load Instr,7.952095808383233,0.0,8.0,Instr per wave
Store Instr,0.005988023952095809,0.0,1.0,Instr per wave
Atomic Instr,0.0,0.0,0.0,Instr per wave
1 Metric Avg Min Max Unit
2 TD Busy 79.08056398970129 4.481455007913706 95.2557378605352 Pct
3 TC2TD Stall 63.61922366802417 3.9358792568078758 93.87501248382047 Pct
4 SPI2TD Stall 0.007817740810349489 0.0 0.01905204047427641 Pct
5 Coalescable Instr 4.790419161676646 0.0 8.0 Instr per wave
6 Load Instr 7.952095808383233 0.0 8.0 Instr per wave
7 Store Instr 0.005988023952095809 0.0 1.0 Instr per wave
8 Atomic Instr 0.0 0.0 0.0 Instr per wave
+5
Voir le fichier
@@ -0,0 +1,5 @@
Metric,Value
Buffer Coalescing,69.91017964071857
Cache Util,83.77291675765915
Cache BW,3.789330348599962
Cache Hit,20.35928143712575
1 Metric Value
2 Buffer Coalescing 69.91017964071857
3 Cache Util 83.77291675765915
4 Cache BW 3.789330348599962
5 Cache Hit 20.35928143712575
+6
Voir le fichier
@@ -0,0 +1,6 @@
Metric,Mean,Min,Max,unit
Stalled on L2 Data,65.78450692680276,4.608646068082825,90.71647990838945,Pct
Stalled on L2 Req,2.003597890399542,0.0,10.79597118002572,Pct
Tag RAM Stall (Read),0.0,0.0,0.0,Pct
Tag RAM Stall (Write),0.0,0.0,0.0,Pct
Tag RAM Stall (Atomic),0.0,0.0,0.0,Pct
1 Metric Mean Min Max unit
2 Stalled on L2 Data 65.78450692680276 4.608646068082825 90.71647990838945 Pct
3 Stalled on L2 Req 2.003597890399542 0.0 10.79597118002572 Pct
4 Tag RAM Stall (Read) 0.0 0.0 0.0 Pct
5 Tag RAM Stall (Write) 0.0 0.0 0.0 Pct
6 Tag RAM Stall (Atomic) 0.0 0.0 0.0 Pct
+15
Voir le fichier
@@ -0,0 +1,15 @@
Metric,Avg,Min,Max,Unit
Total Req,279.377245508982,64.0,512.0,Req per wave
Read Req,278.9940119760479,0.0,512.0,Req per wave
Write Req,0.38323353293413176,0.0,64.0,Req per wave
Atomic Req,0.0,0.0,0.0,Req per wave
Cache Accesses,69.8443113772455,16.0,128.0,Req per wave
Cache Hits,25.437125748502993,0.0,64.0,Req per wave
Cache Hit Rate,20.35928143712575,0.0,50.0,Pct
Invalidate,0.0027854142788641466,0.0001983642578125,0.203125,Req per wave
L1-TCR Read,44.35928143712575,0.0,64.0,Req per wave
L1-L2 Write,0.04790419161676647,0.0,8.0,Req per wave
L1-L2 Atomic,0.0,0.0,0.0,Req per wave
L1 Access Latency,1267.9031301258567,437.29411125183105,1929.5430164337158,Cycles
L1-L2 Read Latency,780.3639466432204,375.36071968078613,1135.0321774482727,Cycles
L1-L2 Write Latency,354.663063287735,354.663063287735,354.663063287735,Cycles
1 Metric Avg Min Max Unit
2 Total Req 279.377245508982 64.0 512.0 Req per wave
3 Read Req 278.9940119760479 0.0 512.0 Req per wave
4 Write Req 0.38323353293413176 0.0 64.0 Req per wave
5 Atomic Req 0.0 0.0 0.0 Req per wave
6 Cache Accesses 69.8443113772455 16.0 128.0 Req per wave
7 Cache Hits 25.437125748502993 0.0 64.0 Req per wave
8 Cache Hit Rate 20.35928143712575 0.0 50.0 Pct
9 Invalidate 0.0027854142788641466 0.0001983642578125 0.203125 Req per wave
10 L1-TCR Read 44.35928143712575 0.0 64.0 Req per wave
11 L1-L2 Write 0.04790419161676647 0.0 8.0 Req per wave
12 L1-L2 Atomic 0.0 0.0 0.0 Req per wave
13 L1 Access Latency 1267.9031301258567 437.29411125183105 1929.5430164337158 Cycles
14 L1-L2 Read Latency 780.3639466432204 375.36071968078613 1135.0321774482727 Cycles
15 L1-L2 Write Latency 354.663063287735 354.663063287735 354.663063287735 Cycles
+13
Voir le fichier
@@ -0,0 +1,13 @@
Xfer,Mean,Min,Max,Unit
NC - Read,0.0,0.0,0.0,Req per wave
UC - Read,0.0,0.0,0.0,Req per wave
CC - Read,0.0,0.0,0.0,Req per wave
RW - Read,44.35928143712575,0.0,64.0,Req per wave
RW - Write,0.04790419161676647,0.0,8.0,Req per wave
NC - Write,0.0,0.0,0.0,Req per wave
UC - Write,0.0,0.0,0.0,Req per wave
CC - Write,0.0,0.0,0.0,Req per wave
NC - Atomic,0.0,0.0,0.0,Req per wave
UC - Atomic,0.0,0.0,0.0,Req per wave
CC - Atomic,0.0,0.0,0.0,Req per wave
RW - Atomic,0.0,0.0,0.0,Req per wave
1 Xfer Mean Min Max Unit
2 NC - Read 0.0 0.0 0.0 Req per wave
3 UC - Read 0.0 0.0 0.0 Req per wave
4 CC - Read 0.0 0.0 0.0 Req per wave
5 RW - Read 44.35928143712575 0.0 64.0 Req per wave
6 RW - Write 0.04790419161676647 0.0 8.0 Req per wave
7 NC - Write 0.0 0.0 0.0 Req per wave
8 UC - Write 0.0 0.0 0.0 Req per wave
9 CC - Write 0.0 0.0 0.0 Req per wave
10 NC - Atomic 0.0 0.0 0.0 Req per wave
11 UC - Atomic 0.0 0.0 0.0 Req per wave
12 CC - Atomic 0.0 0.0 0.0 Req per wave
13 RW - Atomic 0.0 0.0 0.0 Req per wave
+6
Voir le fichier
@@ -0,0 +1,6 @@
Metric,Mean,Min,Max,Units
Req,69.8443113772455,16.0,128.0, per wave
Hit Ratio,97.72526118569745,93.017578125,98.4992504119873,Pct
Hits,68.48541632098352,15.721416473388672,125.9581298828125, per wave
Misses (Translation),0.1391296158293764,0.025325775146484375,0.203125, per wave
Misses (Permission),0.0,0.0,0.0, per wave
1 Metric Mean Min Max Units
2 Req 69.8443113772455 16.0 128.0 per wave
3 Hit Ratio 97.72526118569745 93.017578125 98.4992504119873 Pct
4 Hits 68.48541632098352 15.721416473388672 125.9581298828125 per wave
5 Misses (Translation) 0.1391296158293764 0.025325775146484375 0.203125 per wave
6 Misses (Permission) 0.0 0.0 0.0 per wave
+5
Voir le fichier
@@ -0,0 +1,5 @@
Metric,Value,Unit
L2 Util,91.00959571640085,Pct
Cache Hit,3.855530631367665,Pct
L2-EA Rd BW,1157.2645255860773,Gb/s
L2-EA Wr BW,6.60164530751581,Gb/s
1 Metric Value Unit
2 L2 Util 91.00959571640085 Pct
3 Cache Hit 3.855530631367665 Pct
4 L2-EA Rd BW 1157.2645255860773 Gb/s
5 L2-EA Wr BW 6.60164530751581 Gb/s
+16
Voir le fichier
@@ -0,0 +1,16 @@
Metric,Avg,Min,Max,Unit
Read BW,2839.266489725627,0.0379638671875,4096.3310546875,Bytes per wave
Write BW,3.0179640718562872,0.0,504.0,Bytes per wave
Read (32B),0.0,0.0,0.0,Req per wave
Read (Uncached 32B),0.007365129664986434,0.001155853271484375,0.23046875,Req per wave
Read (64B),44.36353890196292,0.0005931854248046875,64.00517272949219,Req per wave
HBM Read,44.362073224461724,0.000270843505859375,64.00436401367188,Req per wave
Write (32B),0.0,0.0,0.0,Req per wave
Write (Uncached 32B),0.0,0.0,0.0,Req per wave
Write (64B),0.04715568862275449,0.0,7.875,Req per wave
HBM Write,0.04715568862275449,0.0,7.875,Req per wave
Read Latency,529.4951240521125,254.47494514318083,2069.379421221865,Cycles
Write Latency,411.7537543887184,411.7537543887184,411.7537543887184,Cycles
Atomic Latency,,,,Cycles
Read Stall,5.662330760293383,0.0,13.131874935902374,Pct
Write Stall,0.09703262601202511,0.0,16.204448544008194,Pct
1 Metric Avg Min Max Unit
2 Read BW 2839.266489725627 0.0379638671875 4096.3310546875 Bytes per wave
3 Write BW 3.0179640718562872 0.0 504.0 Bytes per wave
4 Read (32B) 0.0 0.0 0.0 Req per wave
5 Read (Uncached 32B) 0.007365129664986434 0.001155853271484375 0.23046875 Req per wave
6 Read (64B) 44.36353890196292 0.0005931854248046875 64.00517272949219 Req per wave
7 HBM Read 44.362073224461724 0.000270843505859375 64.00436401367188 Req per wave
8 Write (32B) 0.0 0.0 0.0 Req per wave
9 Write (Uncached 32B) 0.0 0.0 0.0 Req per wave
10 Write (64B) 0.04715568862275449 0.0 7.875 Req per wave
11 HBM Write 0.04715568862275449 0.0 7.875 Req per wave
12 Read Latency 529.4951240521125 254.47494514318083 2069.379421221865 Cycles
13 Write Latency 411.7537543887184 411.7537543887184 411.7537543887184 Cycles
14 Atomic Latency Cycles
15 Read Stall 5.662330760293383 0.0 13.131874935902374 Pct
16 Write Stall 0.09703262601202511 0.0 16.204448544008194 Pct
+19
Voir le fichier
@@ -0,0 +1,19 @@
Metric,Avg,Min,Max,Unit
Req,23.467293173967008,8.00143051147461,36.25372314453125,Req per wave
Streaming Req,0.0,0.0,0.0,Req per wave
Read Req,23.444925399597533,0.0014400482177734375,36.297088623046875,Req per wave
Write Req,0.04790419161676647,0.0,8.0,Req per wave
Atomic Req,0.0,0.0,0.0,Req per wave
Probe Req,0.0,0.0,0.0,Req per wave
Hits,1.2596518008294935,0.00592041015625,4.2498321533203125,Hits per wave
Misses,22.207641373137513,4.000587463378906,32.0050048828125,Misses per wave
Cache Hit,3.855530631367665,0.03698228377040102,50.00159711889287,Pct
Writeback,0.024407792234135244,0.0004730224609375,3.9375057220458984, per wave
NC Req,6.395899607035928e-07,0.0,0.0001068115234375,Req per wave
UC Req,0.0036939632392928986,0.0005741119384765625,0.1171875,Req per wave
CC Req,0.0,0.0,0.0,Req per wave
RW Req,23.475410233000794,8.000747680664062,36.41102600097656,Req per wave
Writeback (Normal),0.023577844311377244,0.0,3.9375, per wave
Writeback (TC Req),0.0,0.0,0.0, per wave
Evict (Normal),21.16718569772686,0.0,31.000839233398438, per wave
Evict (TC Req),0.0,0.0,0.0, per wave
1 Metric Avg Min Max Unit
2 Req 23.467293173967008 8.00143051147461 36.25372314453125 Req per wave
3 Streaming Req 0.0 0.0 0.0 Req per wave
4 Read Req 23.444925399597533 0.0014400482177734375 36.297088623046875 Req per wave
5 Write Req 0.04790419161676647 0.0 8.0 Req per wave
6 Atomic Req 0.0 0.0 0.0 Req per wave
7 Probe Req 0.0 0.0 0.0 Req per wave
8 Hits 1.2596518008294935 0.00592041015625 4.2498321533203125 Hits per wave
9 Misses 22.207641373137513 4.000587463378906 32.0050048828125 Misses per wave
10 Cache Hit 3.855530631367665 0.03698228377040102 50.00159711889287 Pct
11 Writeback 0.024407792234135244 0.0004730224609375 3.9375057220458984 per wave
12 NC Req 6.395899607035928e-07 0.0 0.0001068115234375 Req per wave
13 UC Req 0.0036939632392928986 0.0005741119384765625 0.1171875 Req per wave
14 CC Req 0.0 0.0 0.0 Req per wave
15 RW Req 23.475410233000794 8.000747680664062 36.41102600097656 Req per wave
16 Writeback (Normal) 0.023577844311377244 0.0 3.9375 per wave
17 Writeback (TC Req) 0.0 0.0 0.0 per wave
18 Evict (Normal) 21.16718569772686 0.0 31.000839233398438 per wave
19 Evict (TC Req) 0.0 0.0 0.0 per wave
+8
Voir le fichier
@@ -0,0 +1,8 @@
Metric,Avg,Min,Max,Unit
Read - Remote Socket Stall,0.0,0.0,0.0,Req per wave
Read - Peer GCD Stall,0.0,0.0,0.0,Req per wave
Read - HBM Stall,5.598615634941055,0.0,14.219879150390625,Req per wave
Write - Remote Socket Stall,0.0,0.0,0.0,Req per wave
Write - Peer GCD Stall,0.0,0.0,0.0,Req per wave
Write - HBM Stall,0.01764870832066336,0.0,2.9473342895507812,Req per wave
Write - Credit Starvation,0.0,0.0,0.0,Req per wave
1 Metric Avg Min Max Unit
2 Read - Remote Socket Stall 0.0 0.0 0.0 Req per wave
3 Read - Peer GCD Stall 0.0 0.0 0.0 Req per wave
4 Read - HBM Stall 5.598615634941055 0.0 14.219879150390625 Req per wave
5 Write - Remote Socket Stall 0.0 0.0 0.0 Req per wave
6 Write - Peer GCD Stall 0.0 0.0 0.0 Req per wave
7 Write - HBM Stall 0.01764870832066336 0.0 2.9473342895507812 Req per wave
8 Write - Credit Starvation 0.0 0.0 0.0 Req per wave
+17
Voir le fichier
@@ -0,0 +1,17 @@
Channel,Hit Rate,Req,Read Req,Write Req,AtomicReq,EA Read Req,EA Write Req,EA AtomicReq,EA Read Lat - cycles,EA Write Lat - cycles,EA Atomic Lat - cycles,EA Read Stall - IO,EA Read Stall - GMI,EA Read Stall - DRAM,EA Write Stall - IO,EA Write Stall - GMI,EA Write Stall - DRAM,EA Write Stall - Starve
0,3.7895718616332856,0.7330604598907653,0.7315634539027414,0.0014970059880239522,0.0,1.3862423468492702,0.0014736152694610778,0.0,512.4759314846668,402.3611111111111,,0.0,0.0,0.15983362254982222,0.0,0.0,0.0005222480454130801,0.0
1,3.81309749410961,0.7335050662834487,0.7320080602954248,0.0014970059880239522,0.0,1.3862426209592533,0.0014736152694610778,0.0,505.7891423239866,401.80970207093253,,0.0,0.0,0.15946805120228294,0.0,0.0,0.0005297746487006456,0.0
2,3.8014206311458385,0.7331581458360136,0.7316611398479895,0.0014970059880239522,0.0,1.3862421641092815,0.0014736152694610778,0.0,524.8110042761184,402.74786861359127,,0.0,0.0,0.14608993073423465,0.0,0.0,0.0005343659909185536,0.0
3,3.813668343492799,0.7336020212687419,0.7321050152807178,0.0014970059880239522,0.0,1.3865635466432857,0.0014736152694610778,0.0,531.9793122279001,414.2158668154762,,0.0,0.0,0.1706504593352358,0.0,0.0,0.0005589787831563436,0.0
4,3.80242128057692,0.7330687745602545,0.7315717685722305,0.0014970059880239522,0.0,1.3862425524317576,0.0014736152694610778,0.0,523.8541553060674,406.70176866319446,,0.0,0.0,0.1592140426178892,0.0,0.0,0.0005319332648180202,0.0
5,4.174952053188192,0.7357135704177582,0.7342165644297343,0.0014970059880239522,0.0,1.386288854176413,0.0014736152694610778,0.0,539.4153477299254,409.1932353670635,,0.0,0.0,0.2536792869339446,0.0,0.0,0.0005435029903571762,0.0
6,3.8050667150346706,0.7332251999906437,0.7317281940026198,0.0014970059880239522,0.0,1.3862421641092815,0.0014736152694610778,0.0,540.790908896914,403.5860150049603,,0.0,0.0,0.238656689306933,0.0,0.0,0.0005261426914237931,0.0
7,3.799478881192864,0.7332007128321482,0.7317037068441242,0.0014970059880239522,0.0,1.386242072739287,0.0014736152694610778,0.0,564.8097274030364,421.11803230406747,,0.0,0.0,0.28763977781741207,0.0,0.0,0.0005697490212446201,0.0
8,3.8189147898613123,0.7333427931734188,0.7318457871853948,0.0014970059880239522,0.0,1.386242255479276,0.0014736152694610778,0.0,511.34685887259985,406.9412047371032,,0.0,0.0,0.171766178336686,0.0,0.0,0.0005339205621959207,0.0
9,3.788496118174839,0.7330019830943582,0.7315049771063342,0.0014970059880239522,0.0,1.3862418899992983,0.0014736152694610778,0.0,492.4154965185424,406.613040984623,,0.0,0.0,0.1216218685675524,0.0,0.0,0.0005479344350849083,0.0
10,3.8071823933979556,0.7334333408378555,0.7319363348498316,0.0014970059880239522,0.0,1.3862573315283495,0.0014736152694610778,0.0,487.53574152873574,400.2972392733135,,0.0,0.0,0.12753506049424587,0.0,0.0,0.0005264739076534431,0.0
11,3.795518808413885,0.7346767950914577,0.7331797891034337,0.0014970059880239522,0.0,1.3862417986293039,0.0014736152694610778,0.0,506.9065761802826,416.8939732142857,,0.0,0.0,0.15344229144250562,0.0,0.0,0.0005722616960902413,0.0
12,3.8146943763722967,0.733625503357299,0.7321284973692751,0.0014970059880239522,0.0,1.3865326293214353,0.0014736152694610778,0.0,512.3877719039374,412.91038876488096,,0.0,0.0,0.14086557719521894,0.0,0.0,0.0005470664201382391,0.0
13,3.8015251432193624,0.7331317284863866,0.7316347224983627,0.0014970059880239522,0.0,1.3862694037888579,0.0014736152694610778,0.0,3737.876065351138,410.3890128968254,,0.0,0.0,0.128666129654753,0.0,0.0,0.0005516806048547437,0.0
14,4.1865798778999785,0.7358360975802302,0.7343390915922062,0.0014970059880239522,0.0,1.386288854176413,0.0014736152694610778,0.0,492.74812678677654,407.633052765377,,0.0,0.0,0.1674625602311003,0.0,0.0,0.0005461527201943768,0.0
15,3.8143081588416488,0.7332943670763941,0.7317973610883701,0.0014970059880239522,0.0,1.3862430778092254,0.0014736152694610778,0.0,534.0008449829592,422.1587146577381,,0.0,0.0,0.21530324970176834,0.0,0.0,0.0005728441798044536,0.0
1 Channel Hit Rate Req Read Req Write Req AtomicReq EA Read Req EA Write Req EA AtomicReq EA Read Lat - cycles EA Write Lat - cycles EA Atomic Lat - cycles EA Read Stall - IO EA Read Stall - GMI EA Read Stall - DRAM EA Write Stall - IO EA Write Stall - GMI EA Write Stall - DRAM EA Write Stall - Starve
2 0 3.7895718616332856 0.7330604598907653 0.7315634539027414 0.0014970059880239522 0.0 1.3862423468492702 0.0014736152694610778 0.0 512.4759314846668 402.3611111111111 0.0 0.0 0.15983362254982222 0.0 0.0 0.0005222480454130801 0.0
3 1 3.81309749410961 0.7335050662834487 0.7320080602954248 0.0014970059880239522 0.0 1.3862426209592533 0.0014736152694610778 0.0 505.7891423239866 401.80970207093253 0.0 0.0 0.15946805120228294 0.0 0.0 0.0005297746487006456 0.0
4 2 3.8014206311458385 0.7331581458360136 0.7316611398479895 0.0014970059880239522 0.0 1.3862421641092815 0.0014736152694610778 0.0 524.8110042761184 402.74786861359127 0.0 0.0 0.14608993073423465 0.0 0.0 0.0005343659909185536 0.0
5 3 3.813668343492799 0.7336020212687419 0.7321050152807178 0.0014970059880239522 0.0 1.3865635466432857 0.0014736152694610778 0.0 531.9793122279001 414.2158668154762 0.0 0.0 0.1706504593352358 0.0 0.0 0.0005589787831563436 0.0
6 4 3.80242128057692 0.7330687745602545 0.7315717685722305 0.0014970059880239522 0.0 1.3862425524317576 0.0014736152694610778 0.0 523.8541553060674 406.70176866319446 0.0 0.0 0.1592140426178892 0.0 0.0 0.0005319332648180202 0.0
7 5 4.174952053188192 0.7357135704177582 0.7342165644297343 0.0014970059880239522 0.0 1.386288854176413 0.0014736152694610778 0.0 539.4153477299254 409.1932353670635 0.0 0.0 0.2536792869339446 0.0 0.0 0.0005435029903571762 0.0
8 6 3.8050667150346706 0.7332251999906437 0.7317281940026198 0.0014970059880239522 0.0 1.3862421641092815 0.0014736152694610778 0.0 540.790908896914 403.5860150049603 0.0 0.0 0.238656689306933 0.0 0.0 0.0005261426914237931 0.0
9 7 3.799478881192864 0.7332007128321482 0.7317037068441242 0.0014970059880239522 0.0 1.386242072739287 0.0014736152694610778 0.0 564.8097274030364 421.11803230406747 0.0 0.0 0.28763977781741207 0.0 0.0 0.0005697490212446201 0.0
10 8 3.8189147898613123 0.7333427931734188 0.7318457871853948 0.0014970059880239522 0.0 1.386242255479276 0.0014736152694610778 0.0 511.34685887259985 406.9412047371032 0.0 0.0 0.171766178336686 0.0 0.0 0.0005339205621959207 0.0
11 9 3.788496118174839 0.7330019830943582 0.7315049771063342 0.0014970059880239522 0.0 1.3862418899992983 0.0014736152694610778 0.0 492.4154965185424 406.613040984623 0.0 0.0 0.1216218685675524 0.0 0.0 0.0005479344350849083 0.0
12 10 3.8071823933979556 0.7334333408378555 0.7319363348498316 0.0014970059880239522 0.0 1.3862573315283495 0.0014736152694610778 0.0 487.53574152873574 400.2972392733135 0.0 0.0 0.12753506049424587 0.0 0.0 0.0005264739076534431 0.0
13 11 3.795518808413885 0.7346767950914577 0.7331797891034337 0.0014970059880239522 0.0 1.3862417986293039 0.0014736152694610778 0.0 506.9065761802826 416.8939732142857 0.0 0.0 0.15344229144250562 0.0 0.0 0.0005722616960902413 0.0
14 12 3.8146943763722967 0.733625503357299 0.7321284973692751 0.0014970059880239522 0.0 1.3865326293214353 0.0014736152694610778 0.0 512.3877719039374 412.91038876488096 0.0 0.0 0.14086557719521894 0.0 0.0 0.0005470664201382391 0.0
15 13 3.8015251432193624 0.7331317284863866 0.7316347224983627 0.0014970059880239522 0.0 1.3862694037888579 0.0014736152694610778 0.0 3737.876065351138 410.3890128968254 0.0 0.0 0.128666129654753 0.0 0.0 0.0005516806048547437 0.0
16 14 4.1865798778999785 0.7358360975802302 0.7343390915922062 0.0014970059880239522 0.0 1.386288854176413 0.0014736152694610778 0.0 492.74812678677654 407.633052765377 0.0 0.0 0.1674625602311003 0.0 0.0 0.0005461527201943768 0.0
17 15 3.8143081588416488 0.7332943670763941 0.7317973610883701 0.0014970059880239522 0.0 1.3862430778092254 0.0014736152694610778 0.0 534.0008449829592 422.1587146577381 0.0 0.0 0.21530324970176834 0.0 0.0 0.0005728441798044536 0.0
+17
Voir le fichier
@@ -0,0 +1,17 @@
Channel,Hit Rate,Req,Read Req,Write Req,AtomicReq,EA Read Req,EA Write Req,EA AtomicReq,EA Read Lat - cycles,EA Write Lat - cycles,EA Atomic Lat - cycles,EA Read Stall - IO,EA Read Stall - GMI,EA Read Stall - DRAM,EA Write Stall - IO,EA Write Stall - GMI,EA Write Stall - DRAM,EA Write Stall - Starve
16,3.779048839080373,0.7329206637993544,0.7314236578113305,0.0014970059880239522,0.0,1.3877529669664577,0.0014736152694610778,0.0,530.4836472166746,402.0967571924603,,0.0,0.0,0.17332613825084206,0.0,0.0,0.00051707421948096,0.0
17,3.81250192565867,0.7333050687869865,0.7318080627989626,0.0014970059880239522,0.0,1.386269221048869,0.0014736152694610778,0.0,526.6401697563895,402.4264400421627,,0.0,0.0,0.18236866111526945,0.0,0.0,0.0005284040987848522,0.0
18,3.791114411268259,0.7330928962387725,0.7315958902507484,0.0014970059880239522,0.0,1.386242072739287,0.0014736152694610778,0.0,520.4840500997606,398.65807136656747,,0.0,0.0,0.18284817084580837,0.0,0.0,0.0005149498671114802,0.0
19,3.773896974831362,0.732896907600814,0.73139990161279,0.0014970059880239522,0.0,1.3862421641092815,0.0014736152694610778,0.0,532.5629319239533,412.99733382936506,,0.0,0.0,0.19374203253648953,0.0,0.0,0.0005571628045179173,0.0
20,3.793954865480005,0.7329970491146613,0.7315000431266373,0.0014970059880239522,0.0,1.386242529589259,0.0014736152694610778,0.0,538.0362658018178,406.76612878224205,,0.0,0.0,0.20529978860638098,0.0,0.0,0.0005269536001239708,0.0
21,3.805516637979221,0.7339424772890742,0.7324454713010502,0.0014970059880239522,0.0,1.387014274825593,0.0014736152694610778,0.0,519.1033097582226,406.85870070684524,,0.0,0.0,0.1407541971720621,0.0,0.0,0.0005328469647618825,0.0
22,3.8106426601128236,0.7331944083025356,0.7316974023145116,0.0014970059880239522,0.0,1.3862422097942786,0.0014736152694610778,0.0,528.2219582086902,402.28794642857144,,0.0,0.0,0.16057938444400263,0.0,0.0,0.0005204434880239521,0.0
23,3.982729248808964,0.7338425870427114,0.7323455810546875,0.0014970059880239522,0.0,1.3862543163185348,0.0014736152694610778,0.0,551.2163861917193,417.9811197916667,,0.0,0.0,0.2803750409337575,0.0,0.0,0.0005604635455651198,0.0
24,3.819108733002833,0.7333260724644461,0.7318290664764222,0.0014970059880239522,0.0,1.3862428036992422,0.0014736152694610778,0.0,510.88124138464656,403.9800502232143,,0.0,0.0,0.19807808699008234,0.0,0.0,0.0005232873790992235,0.0
25,3.7834396266167216,0.7329739325060816,0.7314769265180576,0.0014970059880239522,0.0,1.386242255479276,0.0014736152694610778,0.0,511.42809354420575,406.13596695188494,,0.0,0.0,0.1400604248046875,0.0,0.0,0.0005433202503684038,0.0
26,3.8144076235217534,0.7333539403127339,0.73185693432471,0.0014970059880239522,0.0,1.3862419813692928,0.0014736152694610778,0.0,503.38833792023655,399.1180013020833,,0.0,0.0,0.18065245851071296,0.0,0.0,0.0005220995691722025,0.0
27,3.784694874508206,0.7330117596837575,0.7315147536957335,0.0014970059880239522,0.0,1.386242072739287,0.0014736152694610778,0.0,515.3725696800907,419.3984840029762,,0.0,0.0,0.1545203660062687,0.0,0.0,0.0005763505033390251,0.0
28,3.7725108245216425,0.7328964507508421,0.7313994447628182,0.0014970059880239522,0.0,1.386242072739287,0.0014736152694610778,0.0,516.0649215192589,409.70965091765873,,0.0,0.0,0.166656494140625,0.0,0.0,0.0005382035306827751,0.0
29,3.7965732109831842,0.7330519624812875,0.7315549564932635,0.0014970059880239522,0.0,1.3862424382192646,0.0014736152694610778,0.0,518.5381618368095,412.92992001488096,,0.0,0.0,0.16276669073961453,0.0,0.0,0.0005627592166740738,0.0
30,3.795675756580328,0.7338621402215101,0.7323651342334861,0.0014970059880239522,0.0,1.387037094481691,0.0014736152694610778,0.0,523.190477661644,406.03724888392856,,0.0,0.0,0.1582224040688155,0.0,0.0,0.0005382720581785647,0.0
31,3.8213811798589417,0.7333387728936658,0.7318417669056418,0.0014970059880239522,0.0,1.3862425410105084,0.0014736152694610778,0.0,537.6031362360802,420.5706845238095,,0.0,0.0,0.2330806526595247,0.0,0.0,0.0005717705823704154,0.0
1 Channel Hit Rate Req Read Req Write Req AtomicReq EA Read Req EA Write Req EA AtomicReq EA Read Lat - cycles EA Write Lat - cycles EA Atomic Lat - cycles EA Read Stall - IO EA Read Stall - GMI EA Read Stall - DRAM EA Write Stall - IO EA Write Stall - GMI EA Write Stall - DRAM EA Write Stall - Starve
2 16 3.779048839080373 0.7329206637993544 0.7314236578113305 0.0014970059880239522 0.0 1.3877529669664577 0.0014736152694610778 0.0 530.4836472166746 402.0967571924603 0.0 0.0 0.17332613825084206 0.0 0.0 0.00051707421948096 0.0
3 17 3.81250192565867 0.7333050687869865 0.7318080627989626 0.0014970059880239522 0.0 1.386269221048869 0.0014736152694610778 0.0 526.6401697563895 402.4264400421627 0.0 0.0 0.18236866111526945 0.0 0.0 0.0005284040987848522 0.0
4 18 3.791114411268259 0.7330928962387725 0.7315958902507484 0.0014970059880239522 0.0 1.386242072739287 0.0014736152694610778 0.0 520.4840500997606 398.65807136656747 0.0 0.0 0.18284817084580837 0.0 0.0 0.0005149498671114802 0.0
5 19 3.773896974831362 0.732896907600814 0.73139990161279 0.0014970059880239522 0.0 1.3862421641092815 0.0014736152694610778 0.0 532.5629319239533 412.99733382936506 0.0 0.0 0.19374203253648953 0.0 0.0 0.0005571628045179173 0.0
6 20 3.793954865480005 0.7329970491146613 0.7315000431266373 0.0014970059880239522 0.0 1.386242529589259 0.0014736152694610778 0.0 538.0362658018178 406.76612878224205 0.0 0.0 0.20529978860638098 0.0 0.0 0.0005269536001239708 0.0
7 21 3.805516637979221 0.7339424772890742 0.7324454713010502 0.0014970059880239522 0.0 1.387014274825593 0.0014736152694610778 0.0 519.1033097582226 406.85870070684524 0.0 0.0 0.1407541971720621 0.0 0.0 0.0005328469647618825 0.0
8 22 3.8106426601128236 0.7331944083025356 0.7316974023145116 0.0014970059880239522 0.0 1.3862422097942786 0.0014736152694610778 0.0 528.2219582086902 402.28794642857144 0.0 0.0 0.16057938444400263 0.0 0.0 0.0005204434880239521 0.0
9 23 3.982729248808964 0.7338425870427114 0.7323455810546875 0.0014970059880239522 0.0 1.3862543163185348 0.0014736152694610778 0.0 551.2163861917193 417.9811197916667 0.0 0.0 0.2803750409337575 0.0 0.0 0.0005604635455651198 0.0
10 24 3.819108733002833 0.7333260724644461 0.7318290664764222 0.0014970059880239522 0.0 1.3862428036992422 0.0014736152694610778 0.0 510.88124138464656 403.9800502232143 0.0 0.0 0.19807808699008234 0.0 0.0 0.0005232873790992235 0.0
11 25 3.7834396266167216 0.7329739325060816 0.7314769265180576 0.0014970059880239522 0.0 1.386242255479276 0.0014736152694610778 0.0 511.42809354420575 406.13596695188494 0.0 0.0 0.1400604248046875 0.0 0.0 0.0005433202503684038 0.0
12 26 3.8144076235217534 0.7333539403127339 0.73185693432471 0.0014970059880239522 0.0 1.3862419813692928 0.0014736152694610778 0.0 503.38833792023655 399.1180013020833 0.0 0.0 0.18065245851071296 0.0 0.0 0.0005220995691722025 0.0
13 27 3.784694874508206 0.7330117596837575 0.7315147536957335 0.0014970059880239522 0.0 1.386242072739287 0.0014736152694610778 0.0 515.3725696800907 419.3984840029762 0.0 0.0 0.1545203660062687 0.0 0.0 0.0005763505033390251 0.0
14 28 3.7725108245216425 0.7328964507508421 0.7313994447628182 0.0014970059880239522 0.0 1.386242072739287 0.0014736152694610778 0.0 516.0649215192589 409.70965091765873 0.0 0.0 0.166656494140625 0.0 0.0 0.0005382035306827751 0.0
15 29 3.7965732109831842 0.7330519624812875 0.7315549564932635 0.0014970059880239522 0.0 1.3862424382192646 0.0014736152694610778 0.0 518.5381618368095 412.92992001488096 0.0 0.0 0.16276669073961453 0.0 0.0 0.0005627592166740738 0.0
16 30 3.795675756580328 0.7338621402215101 0.7323651342334861 0.0014970059880239522 0.0 1.387037094481691 0.0014736152694610778 0.0 523.190477661644 406.03724888392856 0.0 0.0 0.1582224040688155 0.0 0.0 0.0005382720581785647 0.0
17 31 3.8213811798589417 0.7333387728936658 0.7318417669056418 0.0014970059880239522 0.0 1.3862425410105084 0.0014736152694610778 0.0 537.6031362360802 420.5706845238095 0.0 0.0 0.2330806526595247 0.0 0.0 0.0005717705823704154 0.0
+55
Voir le fichier
@@ -0,0 +1,55 @@
Metric,Value,Alias
Wave Life,18296.0,wave_life_
Active CUs,103/104,active_cu_
SALU,25.0,salu_
SMEM,2.0,smem_
VALU,495.0,valu_
MFMA,0.0,mfma_
VMEM,8.0,vmem_
LDS,0.0,lds_
GWS,0.0,gws_
BR,10.0,br_
VGPR,12.0,vgpr_
SGPR,24.0,sgpr_
LDS Allocation,0.0,lds_alloc_
Scratch Allocation,0.0,scratch_alloc_
Wavefronts,67894.0,wavefronts_
Workgroups,16973.0,workgroups_
LDS Req,0.0,lds_req_
IL1 Fetch,128.0,il1_fetch_
IL1 Hit,100.0,il1_hit_
IL1_L2 Rd,0.0,il1_l2_req_
vL1D Rd,2.0,sl1_rd_
vL1D Hit,98.0,sl1_hit_
vL1D_L2 Rd,0.0,sl1_l2_rd_
vL1D_L2 Wr,0.0,sl1_l2_wr_
vL1D_L2 Atomic,0.0,sl1_l2_atom_
VL1 Rd,279.0,vl1_rd_
VL1 Wr,0.0,vl1_wr_
VL1 Atomic,0.0,vl1_atom_
VL1 Hit,20.0,vl1_hit_
VL1 Lat,1268.0,vl1_lat_
VL1_L2 Rd,44.0,vl1_l2_rd_
VL1_L2 Wr,0.0,vl1_l2_wr_
vL1_L2 Atomic,0.0,vl1_l2_atom_
L2 Rd,23.0,l2_rd_
L2 Wr,0.0,l2_wr_
L2 Atomic,0.0,l2_atom_
L2 Hit,4.0,l2_hit_
L2 Rd Lat,780.0,l2_rd_lat_
L2 Wr Lat,355.0,l2_wr_lat_
Fabric Rd Lat,529.0,fabric_rd_lat_
Fabric Wr Lat,412.0,fabric_wr_lat_
Fabric Atomic Lat,,fabric_atom_lat_
Fabric_L2 Rd,44.0,l2_fabric_rd_
Fabric_L2 Wr,0.0,l2_fabric_wr_
Fabric_l2 Atomic,0.0,l2_fabric_atom_
HBM Rd,44.0,hbm_rd_
HBM Wr,0.0,hbm_wr_
LDS Util,0.0,lds_util_
VL1 Coalesce,70.0,vl1_coales_
VL1 Stall,2.0,vl1_stall_
LDS Lat,,lds_lat_
vL1D Lat,,sl1_lat_
IL1 Lat,,il1_lat_
Wave Occupancy,25.0,wave_occ_
1 Metric Value Alias
2 Wave Life 18296.0 wave_life_
3 Active CUs 103/104 active_cu_
4 SALU 25.0 salu_
5 SMEM 2.0 smem_
6 VALU 495.0 valu_
7 MFMA 0.0 mfma_
8 VMEM 8.0 vmem_
9 LDS 0.0 lds_
10 GWS 0.0 gws_
11 BR 10.0 br_
12 VGPR 12.0 vgpr_
13 SGPR 24.0 sgpr_
14 LDS Allocation 0.0 lds_alloc_
15 Scratch Allocation 0.0 scratch_alloc_
16 Wavefronts 67894.0 wavefronts_
17 Workgroups 16973.0 workgroups_
18 LDS Req 0.0 lds_req_
19 IL1 Fetch 128.0 il1_fetch_
20 IL1 Hit 100.0 il1_hit_
21 IL1_L2 Rd 0.0 il1_l2_req_
22 vL1D Rd 2.0 sl1_rd_
23 vL1D Hit 98.0 sl1_hit_
24 vL1D_L2 Rd 0.0 sl1_l2_rd_
25 vL1D_L2 Wr 0.0 sl1_l2_wr_
26 vL1D_L2 Atomic 0.0 sl1_l2_atom_
27 VL1 Rd 279.0 vl1_rd_
28 VL1 Wr 0.0 vl1_wr_
29 VL1 Atomic 0.0 vl1_atom_
30 VL1 Hit 20.0 vl1_hit_
31 VL1 Lat 1268.0 vl1_lat_
32 VL1_L2 Rd 44.0 vl1_l2_rd_
33 VL1_L2 Wr 0.0 vl1_l2_wr_
34 vL1_L2 Atomic 0.0 vl1_l2_atom_
35 L2 Rd 23.0 l2_rd_
36 L2 Wr 0.0 l2_wr_
37 L2 Atomic 0.0 l2_atom_
38 L2 Hit 4.0 l2_hit_
39 L2 Rd Lat 780.0 l2_rd_lat_
40 L2 Wr Lat 355.0 l2_wr_lat_
41 Fabric Rd Lat 529.0 fabric_rd_lat_
42 Fabric Wr Lat 412.0 fabric_wr_lat_
43 Fabric Atomic Lat fabric_atom_lat_
44 Fabric_L2 Rd 44.0 l2_fabric_rd_
45 Fabric_L2 Wr 0.0 l2_fabric_wr_
46 Fabric_l2 Atomic 0.0 l2_fabric_atom_
47 HBM Rd 44.0 hbm_rd_
48 HBM Wr 0.0 hbm_wr_
49 LDS Util 0.0 lds_util_
50 VL1 Coalesce 70.0 vl1_coales_
51 VL1 Stall 2.0 vl1_stall_
52 LDS Lat lds_lat_
53 vL1D Lat sl1_lat_
54 IL1 Lat il1_lat_
55 Wave Occupancy 25.0 wave_occ_
+168
Voir le fichier
@@ -0,0 +1,168 @@
Index,KernelName,gpu-id
0,__amd_rocclr_fillBufferAligned.kd,0
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0
1 Index KernelName gpu-id
2 0 __amd_rocclr_fillBufferAligned.kd 0
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0
5 3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0
10 8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0
15 13 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0
20 18 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0
25 23 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0
30 28 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0
35 33 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0
40 38 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0
45 43 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0
50 48 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0
55 53 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0
60 58 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0
65 63 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0
70 68 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0
75 73 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0
80 78 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0
85 83 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0
90 88 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0
95 93 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0
100 98 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0
105 103 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0
110 108 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0
115 113 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0
120 118 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0
125 123 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0
130 128 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0
135 133 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0
140 138 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0
145 143 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0
150 148 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0
155 153 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0
160 158 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0
165 163 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0
+30
Voir le fichier
@@ -0,0 +1,30 @@
Metric,Value,Unit,Peak,PoP
VALU FLOPs,7437.532590053177,Gflop,22630.4,32.86522814467785
VALU IOPs,2297.2282209316063,Giop,22630.4,10.15107210182589
MFMA FLOPs (BF16),0.0,Gflop,90521.6,0.0
MFMA FLOPs (F16),0.0,Gflop,181043.2,0.0
MFMA FLOPs (F32),0.0,Gflop,45260.8,0.0
MFMA FLOPs (F64),0.0,Gflop,45260.8,0.0
MFMA IOPs (Int8),0.0,Giop,181043.2,0.0
Active CUs,103,Cus,104,99.03846153846153
SALU Util,2.6255645406366175,Pct,100,2.6255645406366175
VALU Util,58.3677767471036,Pct,100,58.3677767471036
MFMA Util,0.0,Pct,100,0.0
VALU Active Threads/Wave,64.0,Threads,64,100.0
IPC - Issue,1.0,Instr/cycle,5,20.0
LDS BW,0.0,Gb/sec,22630.4,0.0
LDS Bank Conflict,,Conflicts/access,32,
Instr Cache Hit Rate,99.99259859947313,Pct,100,99.99259859947313
Instr Cache BW,1671.978257589768,Gb/s,6092.8,27.441870036596768
Scalar L1D Cache Hit Rate,99.3485588612334,Pct,100,99.3485588612334
Scalar L1D Cache BW,56.93754250540514,Gb/s,6092.8,0.9345053588728522
Vector L1D Cache Hit Rate,20.35928143712575,Pct,100,20.35928143712575
Vector L1D Cache BW,1690.5441090458708,Gb/s,11315.199999999999,14.940470420724962
L2 Cache Hit Rate,3.855530631367665,Pct,100,3.855530631367665
L2-Fabric Read BW,1157.2645255860773,Gb/s,1638.4,70.63382114172835
L2-Fabric Write BW,6.60164530751581,Gb/s,1638.4,0.40293245285130674
L2-Fabric Read Latency,529.4951240521125,Cycles,,
L2-Fabric Write Latency,411.7537543887184,Cycles,,
Wave Occupancy,2621.069420561901,Wavefronts,3328,78.75809556976866
Instr Fetch BW,404.9210622988756,Gb/s,3046.4,13.291789072310781
Instr Fetch Latency,17.174407318683716,Cycles,,
1 Metric Value Unit Peak PoP
2 VALU FLOPs 7437.532590053177 Gflop 22630.4 32.86522814467785
3 VALU IOPs 2297.2282209316063 Giop 22630.4 10.15107210182589
4 MFMA FLOPs (BF16) 0.0 Gflop 90521.6 0.0
5 MFMA FLOPs (F16) 0.0 Gflop 181043.2 0.0
6 MFMA FLOPs (F32) 0.0 Gflop 45260.8 0.0
7 MFMA FLOPs (F64) 0.0 Gflop 45260.8 0.0
8 MFMA IOPs (Int8) 0.0 Giop 181043.2 0.0
9 Active CUs 103 Cus 104 99.03846153846153
10 SALU Util 2.6255645406366175 Pct 100 2.6255645406366175
11 VALU Util 58.3677767471036 Pct 100 58.3677767471036
12 MFMA Util 0.0 Pct 100 0.0
13 VALU Active Threads/Wave 64.0 Threads 64 100.0
14 IPC - Issue 1.0 Instr/cycle 5 20.0
15 LDS BW 0.0 Gb/sec 22630.4 0.0
16 LDS Bank Conflict Conflicts/access 32
17 Instr Cache Hit Rate 99.99259859947313 Pct 100 99.99259859947313
18 Instr Cache BW 1671.978257589768 Gb/s 6092.8 27.441870036596768
19 Scalar L1D Cache Hit Rate 99.3485588612334 Pct 100 99.3485588612334
20 Scalar L1D Cache BW 56.93754250540514 Gb/s 6092.8 0.9345053588728522
21 Vector L1D Cache Hit Rate 20.35928143712575 Pct 100 20.35928143712575
22 Vector L1D Cache BW 1690.5441090458708 Gb/s 11315.199999999999 14.940470420724962
23 L2 Cache Hit Rate 3.855530631367665 Pct 100 3.855530631367665
24 L2-Fabric Read BW 1157.2645255860773 Gb/s 1638.4 70.63382114172835
25 L2-Fabric Write BW 6.60164530751581 Gb/s 1638.4 0.40293245285130674
26 L2-Fabric Read Latency 529.4951240521125 Cycles
27 L2-Fabric Write Latency 411.7537543887184 Cycles
28 Wave Occupancy 2621.069420561901 Wavefronts 3328 78.75809556976866
29 Instr Fetch BW 404.9210622988756 Gb/s 3046.4 13.291789072310781
30 Instr Fetch Latency 17.174407318683716 Cycles
+9
Voir le fichier
@@ -0,0 +1,9 @@
Metric,Avg,Min,Max,Unit
GPU Busy Cycles,416564.371257485,33146,5256591,Cycles/kernel
CPF Busy,416564.371257485,33146,5256591,Cycles/kernel
CPF Util,100.0,100.0,100.0,Pct
CPF Stall,0.0,0.0,0.0,Cycles/kernel
L2Cache Intf Busy,2289.5209580838323,2215,2620,Cycles/kernel
L2Cache Intf Util,0.9447317604196492,0.049094377952175,6.7370153728579405,Pct
L2Cache Intf Stall,0.0,0.0,0.0,Pct
UTCL1 Stall,0.0,0,0,Cycles/kernel
1 Metric Avg Min Max Unit
2 GPU Busy Cycles 416564.371257485 33146 5256591 Cycles/kernel
3 CPF Busy 416564.371257485 33146 5256591 Cycles/kernel
4 CPF Util 100.0 100.0 100.0 Pct
5 CPF Stall 0.0 0.0 0.0 Cycles/kernel
6 L2Cache Intf Busy 2289.5209580838323 2215 2620 Cycles/kernel
7 L2Cache Intf Util 0.9447317604196492 0.049094377952175 6.7370153728579405 Pct
8 L2Cache Intf Stall 0.0 0.0 0.0 Pct
9 UTCL1 Stall 0.0 0 0 Cycles/kernel
+13
Voir le fichier
@@ -0,0 +1,13 @@
Metric,Avg,Min,Max,Unit
GPU Busy Cycles,416564.371257485,33146,5256591,Cycles
CPC Busy Cycles,416564.371257485,33146,5256591,Cycles
CPC Util,100.0,100.0,100.0,Pct
CPC Stall Cycles,12034.862275449103,8608,45046,Cycles
CPC Stall Rate,4.529452267109492,0.85694321662081,34.854884450612445,Pct
CPC Packet Decoding,28739.94610778443,8834,273884,Cycles
SPI Intf Busy Cycles,385525.7964071856,499,4979307,Cycles
SPI Intf Util,90.56276836329359,1.505460689072588,97.00898538428908,Pct
L2Cache Intf Util,0.12531703421706647,0.005744097416848959,0.8967810903907828,Pct
UTCL1 Stall Cycles,2611.8323353293413,920,3303,Cycles
UTCL2 Intf Busy Cycles,2866.2694610778444,1179,3630,Cycles
UTCL2 Intf Util,1.1625714386293555,0.05326591012200729,3.980326077056198,Pct
1 Metric Avg Min Max Unit
2 GPU Busy Cycles 416564.371257485 33146 5256591 Cycles
3 CPC Busy Cycles 416564.371257485 33146 5256591 Cycles
4 CPC Util 100.0 100.0 100.0 Pct
5 CPC Stall Cycles 12034.862275449103 8608 45046 Cycles
6 CPC Stall Rate 4.529452267109492 0.85694321662081 34.854884450612445 Pct
7 CPC Packet Decoding 28739.94610778443 8834 273884 Cycles
8 SPI Intf Busy Cycles 385525.7964071856 499 4979307 Cycles
9 SPI Intf Util 90.56276836329359 1.505460689072588 97.00898538428908 Pct
10 L2Cache Intf Util 0.12531703421706647 0.005744097416848959 0.8967810903907828 Pct
11 UTCL1 Stall Cycles 2611.8323353293413 920 3303 Cycles
12 UTCL2 Intf Busy Cycles 2866.2694610778444 1179 3630 Cycles
13 UTCL2 Intf Util 1.1625714386293555 0.05326591012200729 3.980326077056198 Pct
+9
Voir le fichier
@@ -0,0 +1,9 @@
Metric,Avg,Min,Max,Unit
GPU Busy,416564.371257485,33146,5256591,Cycles
CS Busy,3229501.5329341316,172482,41937937,Cycles
SPI Busy,405409.10778443114,24013,5246123,Cycles
SQ Busy,3222538.3293413175,165559,41929704,Cycles
Dispatched Workgroups,16973.413173652694,128,131072,Workgroups
Dispatched Wavefronts,67893.65269461078,512,524288,Wavefronts
Wave Alloc Failed,613874.7365269461,6,9875883,Cycles
Wave Alloc Failed - CS,397291.2574850299,518,2474189,Cycles
1 Metric Avg Min Max Unit
2 GPU Busy 416564.371257485 33146 5256591 Cycles
3 CS Busy 3229501.5329341316 172482 41937937 Cycles
4 SPI Busy 405409.10778443114 24013 5246123 Cycles
5 SQ Busy 3222538.3293413175 165559 41929704 Cycles
6 Dispatched Workgroups 16973.413173652694 128 131072 Workgroups
7 Dispatched Wavefronts 67893.65269461078 512 524288 Wavefronts
8 Wave Alloc Failed 613874.7365269461 6 9875883 Cycles
9 Wave Alloc Failed - CS 397291.2574850299 518 2474189 Cycles
+15
Voir le fichier
@@ -0,0 +1,15 @@
Metric,Avg,Min,Max,Unit
Wave request Failed (CS),397291.2574850299,518,2474189,Cycles
CS Stall,299942.67065868265,0,7870319,Cycles
CS Stall Rate,50.16637143772269,0.0,150.02162549372176,Pct
Scratch Stall,0.0,0,0,Cycles
Insufficient SIMD Waveslots,12526180.185628742,0,370304750,Simd
Insufficient SIMD VGPRs,0.0,0,0,Simd
Insufficient SIMD SGPRs,0.0,0,0,Simd
Insufficient CU LDS,0.0,0,0,Cu
Insufficient CU Barries,0.0,0,0,Cu
Insufficient Bulky Resource,0.0,0,0,Cu
Reach CU Threadgroups Limit,0.0,0,0,Cycles
Reach CU Wave Limit,0.0,0,0,Cycles
VGPR Writes,4.0,4.0,4.0,Cycles/wave
SGPR Writes,2.0059880239520957,2.0,3.0,Cycles/wave
1 Metric Avg Min Max Unit
2 Wave request Failed (CS) 397291.2574850299 518 2474189 Cycles
3 CS Stall 299942.67065868265 0 7870319 Cycles
4 CS Stall Rate 50.16637143772269 0.0 150.02162549372176 Pct
5 Scratch Stall 0.0 0 0 Cycles
6 Insufficient SIMD Waveslots 12526180.185628742 0 370304750 Simd
7 Insufficient SIMD VGPRs 0.0 0 0 Simd
8 Insufficient SIMD SGPRs 0.0 0 0 Simd
9 Insufficient CU LDS 0.0 0 0 Cu
10 Insufficient CU Barries 0.0 0 0 Cu
11 Insufficient Bulky Resource 0.0 0 0 Cu
12 Reach CU Threadgroups Limit 0.0 0 0 Cycles
13 Reach CU Wave Limit 0.0 0 0 Cycles
14 VGPR Writes 4.0 4.0 4.0 Cycles/wave
15 SGPR Writes 2.0059880239520957 2.0 3.0 Cycles/wave
+10
Voir le fichier
@@ -0,0 +1,10 @@
Metric,Avg,Min,Max,Unit
Grid Size,4345193.77245509,32768,33554432,Work items
Workgroup Size,256.0,256,256,Work items
Total Wavefronts,67893.65269461078,512,524288,Wavefronts
Saved Wavefronts,0.0,0,0,Wavefronts
Restored Wavefronts,0.0,0,0,Wavefronts
VGPRs,11.784431137724551,4,16,Registers
SGPRs,24.047904191616766,24,32,Registers
LDS Allocation,0.0,0,0,Bytes
Scratch Allocation,0.0,0,0,Bytes
1 Metric Avg Min Max Unit
2 Grid Size 4345193.77245509 32768 33554432 Work items
3 Workgroup Size 256.0 256 256 Work items
4 Total Wavefronts 67893.65269461078 512 524288 Wavefronts
5 Saved Wavefronts 0.0 0 0 Wavefronts
6 Restored Wavefronts 0.0 0 0 Wavefronts
7 VGPRs 11.784431137724551 4 16 Registers
8 SGPRs 24.047904191616766 24 32 Registers
9 LDS Allocation 0.0 0 0 Bytes
10 Scratch Allocation 0.0 0 0 Bytes
+9
Voir le fichier
@@ -0,0 +1,9 @@
Metric,Avg,Min,Max,Unit
Kernel Time (Nanosec),256389.1497005988,13440,3357122,Ns
Kernel Time (Cycles),416564.371257485,33146,5256591,Cycle
Instr/wavefront,557.1197604790419,49.0,9300.0,Instr/wavefront
Wave Cycles,18296.269474052384,1894.2776184082031,258229.23516845703,Cycles/wave
Dependency Wait Cycles,3013.7689203959026,871.6751708984375,12761.421875,Cycles/wave
Issue Wait Cycles,13166.985218527789,96.1484375,211888.8803100586,Cycles/wave
Active Cycles,2161.293413173653,184.0,36172.0,Cycles/wave
Wavefront Occupancy,2621.069420561901,202.9103021095074,3218.3807259920463,Wavefronts
1 Metric Avg Min Max Unit
2 Kernel Time (Nanosec) 256389.1497005988 13440 3357122 Ns
3 Kernel Time (Cycles) 416564.371257485 33146 5256591 Cycle
4 Instr/wavefront 557.1197604790419 49.0 9300.0 Instr/wavefront
5 Wave Cycles 18296.269474052384 1894.2776184082031 258229.23516845703 Cycles/wave
6 Dependency Wait Cycles 3013.7689203959026 871.6751708984375 12761.421875 Cycles/wave
7 Issue Wait Cycles 13166.985218527789 96.1484375 211888.8803100586 Cycles/wave
8 Active Cycles 2161.293413173653 184.0 36172.0 Cycles/wave
9 Wavefront Occupancy 2621.069420561901 202.9103021095074 3218.3807259920463 Wavefronts
+2
Voir le fichier
@@ -0,0 +1,2 @@
device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh
0,1405.4927,1404.3667,1406.6187,4978.1846,4950.6733,5005.6958,9217.7363,9216.8818,9218.5908,20842.088,20838.24,20845.936,21051.77,21051.189,21052.35,20428.023,20427.414,20428.633,169535.09,167598.56,171471.62,164787.06,164781.25,164792.88,41409.887,41408.715,41411.059,41362.176,41360.668,41363.684,165640.86,163773.39,167508.33
1 device HBMBw HBMBwLow hbmBwHigh L2Bw L2BwLow L2BwHigh L1Bw L1BwLow L1BwHigh LDSBw LDSBwLow LDSBwHigh FP32Flops FP32FlopsLow FP32FlopsHigh FP64Flops FP64FlopsLow FP64FlopsHigh MFMABF16Flops MFMABF16FlopsLow MFMABF16FlopsHigh MFMAF16Flops MFMAF16FlopsLow MFMAF16FlopsHigh MFMAF32Flops MFMAF32FlopsLow MFMAF32FlopsHigh MFMAF64Flops MFMAF64FlopsLow MFMAF64FlopsHigh MFMAI8Ops MFMAFI8OpsLow MFMAI8OpsHigh
2 0 1405.4927 1404.3667 1406.6187 4978.1846 4950.6733 5005.6958 9217.7363 9216.8818 9218.5908 20842.088 20838.24 20845.936 21051.77 21051.189 21052.35 20428.023 20427.414 20428.633 169535.09 167598.56 171471.62 164787.06 164781.25 164792.88 41409.887 41408.715 41411.059 41362.176 41360.668 41363.684 165640.86 163773.39 167508.33
+2
Voir le fichier
@@ -0,0 +1,2 @@
workload_name,host_name,host_cpu,host_distro,host_kernel,host_rocmver,date,gpu_soc,numSE,numCU,numSIMD,waveSize,maxWavesPerCU,maxWorkgroupSize,L1,L2,sclk,mclk,cur_sclk,cur_mclk,L2Banks,name,numSQC,hbmBW,ip_blocks
invdev,06fa5f860366,AMD EPYC 7282 16-Core Processor,Ubuntu 20.04.5 LTS,5.11.0-27-generic,5.1.3-66,Wed Sep 28 20:50:32 2022 (),gfx90a,8,104,4,64,32,1024,16,8192,1700,1600,800,1600,32,mi200,56,1638.4,roofline|SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF
1 workload_name host_name host_cpu host_distro host_kernel host_rocmver date gpu_soc numSE numCU numSIMD waveSize maxWavesPerCU maxWorkgroupSize L1 L2 sclk mclk cur_sclk cur_mclk L2Banks name numSQC hbmBW ip_blocks
2 invdev 06fa5f860366 AMD EPYC 7282 16-Core Processor Ubuntu 20.04.5 LTS 5.11.0-27-generic 5.1.3-66 Wed Sep 28 20:50:32 2022 () gfx90a 8 104 4 64 32 1024 16 8192 1700 1600 800 1600 32 mi200 56 1638.4 roofline|SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF
+168
Voir le fichier
@@ -0,0 +1,168 @@
Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,sig,obj,DispatchNs,BeginNs,EndNs,CompleteNs
0,"__amd_rocclr_fillBufferAligned.kd",0,0,0,238434,238434,33554432,256,0,0,4,32,4160,0x0,0x7fd647c04280,17853365225848,17853365250419,17853365490099,17853365576439
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,238434,238434,32768,256,0,0,12,24,13888,0x0,0x7fd647c23f80,17853370260633,17853370276021,17853370289461,17853370306822
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,238434,238434,4194304,256,0,0,12,24,14336,0x7fd66e582380,0x7fd647c23fc0,17853370311482,17853370360501,17853370452981,17853370455238
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,238434,238434,4194304,256,0,0,16,24,15040,0x7fd66e582200,0x7fd647c24000,17853370476128,17853370485781,17853370665621,17853370667633
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,238434,238434,4194304,256,0,0,16,24,15488,0x7fd66e582080,0x7fd647c24040,17853370682173,17853370690581,17853370869302,17853370871458
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,238434,238434,4194304,256,0,0,12,24,15936,0x7fd66c109f00,0x7fd647c24080,17853370885518,17853370893622,17853370987062,17853370989065
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,238434,238434,4194304,256,0,0,12,24,16384,0x7fd66c109d80,0x7fd647c240c0,17853371004375,17853371012662,17853371104502,17853371106392
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,238434,238434,4194304,256,0,0,12,24,17088,0x7fd66c109c00,0x7fd647c24100,17853371133792,17853371144022,17853371236022,17853371238009
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,238434,238434,4194304,256,0,0,16,24,17792,0x7fd66c109a80,0x7fd647c24140,17853371255939,17853371265302,17853371443702,17853371445714
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,238434,238434,4194304,256,0,0,16,24,18496,0x7fd66c109900,0x7fd647c24180,17853371463453,17853371472022,17853371651702,17853371653619
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,238434,238434,4194304,256,0,0,16,24,19200,0x7fd66c109780,0x7fd647c241c0,17853371670068,17853371752342,17853371846102,17853371848234
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,238434,238434,4194304,256,0,0,16,24,19904,0x7fd66c109600,0x7fd647c24200,17853371887383,17853371900822,17853371993462,17853371995550
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,238434,238434,4194304,256,0,0,12,24,20608,0x7fd66e582480,0x7fd647c24240,17853372038389,17853372048342,17853372141302,17853372143427
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,238434,238434,4194304,256,0,0,16,24,21312,0x7fd66e582300,0x7fd647c24280,17853372165016,17853372175222,17853372354902,17853372356961
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,238434,238434,4194304,256,0,0,16,24,22016,0x7fd66e582180,0x7fd647c242c0,17853372378331,17853372387862,17853372568183,17853372570076
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,238434,238434,4194304,256,0,0,16,24,22720,0x7fd66e582000,0x7fd647c24300,17853372588936,17853372598743,17853372692663,17853372694633
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,238434,238434,4194304,256,0,0,12,24,23424,0x7fd66c109e80,0x7fd647c24340,17853372716233,17853372727383,17853372821303,17853372823280
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,238434,238434,4194304,256,0,0,12,24,24128,0x7fd66c109d00,0x7fd647c24380,17853372856349,17853372866263,17853372959543,17853372961476
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,238434,238434,4194304,256,0,0,16,24,24832,0x7fd66c109b80,0x7fd647c243c0,17853372983426,17853372992823,17853373172183,17853373174171
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,238434,238434,4194304,256,0,0,16,24,25536,0x7fd66c109a00,0x7fd647c24400,17853373193601,17853373204663,17853373384023,17853373386026
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,238434,238434,4194304,256,0,0,12,24,26240,0x7fd66c109880,0x7fd647c24440,17853373404926,17853373416343,17853373509623,17853373511723
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,238434,238434,4194304,256,0,0,12,24,26944,0x7fd66c109700,0x7fd647c24480,17853373532722,17853373543543,17853373636983,17853373639060
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,238434,238434,4194304,256,0,0,12,24,27648,0x7fd66e582580,0x7fd647c244c0,17853373670989,17853373682423,17853373775383,17853373777356
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,238434,238434,4194304,256,0,0,16,24,28608,0x7fd66e582400,0x7fd647c24500,17853373797266,17853373807383,17853373986583,17853373988551
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,238434,238434,4194304,256,0,0,16,24,29312,0x7fd66e582280,0x7fd647c24540,17853374006851,17853374017463,17853374197944,17853374200306
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,238434,238434,4194304,256,0,0,12,24,30016,0x7fd66e582100,0x7fd647c24580,17853374221155,17853374232664,17853374325304,17853374327363
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,238434,238434,4194304,256,0,0,8,24,30976,0x7fd66c109f80,0x7fd647c245c0,17853374350282,17853374359704,17853374452184,17853374454200
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,238434,238434,4194304,256,0,0,12,24,31680,0x7fd66c109e00,0x7fd647c24600,17853374488439,17853374498104,17853374591224,17853374593276
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,238434,238434,4194304,256,0,0,16,24,32640,0x7fd66c109c80,0x7fd647c24640,17853374612836,17853374623864,17853374803224,17853374805211
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,238434,238434,4194304,256,0,0,12,24,33600,0x7fd66c109b00,0x7fd647c24680,17853374824170,17853374833944,17853375015064,17853375016616
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,238434,238434,4194304,256,0,0,12,24,34560,0x7fd66c109980,0x7fd647c246c0,17853375035915,17853375044344,17853375138584,17853375140343
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,238434,238434,4194304,256,0,0,8,24,35520,0x7fd66c109800,0x7fd647c24700,17853375161562,17853375171544,17853375265784,17853375267459
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,238434,238434,4194304,256,0,0,12,24,36224,0x7fd66c109680,0x7fd647c24740,17853375300689,17853375310264,17853375404504,17853375406006
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,238434,238434,4194304,256,0,0,12,24,37184,0x7fd66e582500,0x7fd647c24780,17853375427215,17853375436984,17853375616824,17853375618571
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,238434,238434,4194304,256,0,0,12,24,38144,0x7fd66e582380,0x7fd647c247c0,17853375637680,17853375647704,17853375826745,17853375828305
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,238434,238434,4194304,256,0,0,12,24,39104,0x7fd66e582200,0x7fd647c24800,17853375848345,17853375857465,17853375951225,17853375952902
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,238434,238434,4194304,256,0,0,8,24,40320,0x7fd66e582080,0x7fd647c24840,17853375972742,17853375983705,17853376077945,17853376079429
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,238434,238434,4194304,256,0,0,12,24,41280,0x7fd66c109f00,0x7fd647c24880,17853376111698,17853376121785,17853376216185,17853376217666
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,238434,238434,4194304,256,0,0,12,24,42240,0x7fd66c109d80,0x7fd647c248c0,17853376237695,17853376248185,17853376427545,17853376428970
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,238434,238434,4194304,256,0,0,12,24,43200,0x7fd66c109c00,0x7fd647c24900,17853376448540,17853376458425,17853376639225,17853376640755
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,238434,238434,4194304,256,0,0,8,24,44160,0x7fd66c109a80,0x7fd647c24940,17853376661135,17853376671865,17853376766265,17853376767712
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,238434,238434,4194304,256,0,0,12,24,45376,0x7fd66c109900,0x7fd647c24980,17853376787452,17853376796505,17853376891545,17853376893089
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,238434,238434,4194304,256,0,0,12,24,46336,0x7fd66c109780,0x7fd647c249c0,17853376925198,17853376934905,17853377029465,17853377030986
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,238434,238434,4194304,256,0,0,12,24,47552,0x7fd66c109600,0x7fd647c24a00,17853377051455,17853377061785,17853377240665,17853377242080
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,238434,238434,4194304,256,0,0,12,24,48512,0x7fd66e582480,0x7fd647c24a40,17853377261540,17853377271225,17853377451225,17853377452725
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,238434,238434,4194304,256,0,0,8,24,49472,0x7fd66e582300,0x7fd647c24a80,17853377471865,17853377481785,17853377574746,17853377576232
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,238434,238434,4194304,256,0,0,12,24,50688,0x7fd66e582180,0x7fd647c24ac0,17853377595852,17853377605626,17853377699386,17853377700889
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,238434,238434,4194304,256,0,0,12,24,51648,0x7fd66e582000,0x7fd647c24b00,17853377733238,17853377742906,17853377834906,17853377836396
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,238434,238434,4194304,256,0,0,12,24,52864,0x7fd66c109e80,0x7fd647c24b40,17853377857845,17853377867546,17853378046426,17853378047970
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,238434,238434,4194304,256,0,0,12,24,54080,0x7fd66c109d00,0x7fd647c24b80,17853378067680,17853378076986,17853378255546,17853378257345
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,238434,238434,4194304,256,0,0,8,24,55296,0x7fd66c109b80,0x7fd647c24bc0,17853378277035,17853378285466,17853378380346,17853378381882
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,238434,238434,4194304,256,0,0,12,24,56768,0x7fd66c109a00,0x7fd647c24c00,17853378401721,17853378410586,17853378506266,17853378507719
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,238434,238434,4194304,256,0,0,12,24,57728,0x7fd66c109880,0x7fd647c24c40,17853378540478,17853378550426,17853378644026,17853378645675
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,238434,238434,4194304,256,0,0,12,24,58944,0x7fd66c109700,0x7fd647c24c80,17853378665435,17853378676026,17853378857466,17853378858970
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,238434,238434,4194304,256,0,0,12,24,60160,0x7fd66e582580,0x7fd647c24cc0,17853378878800,17853378890106,17853379070906,17853379072325
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,238434,238434,4194304,256,0,0,8,24,61376,0x7fd66e582400,0x7fd647c24d00,17853379092714,17853379102906,17853379197946,17853379199752
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,238434,238434,4194304,256,0,0,12,24,62848,0x7fd66e582280,0x7fd647c24d40,17853379220781,17853379230266,17853379330747,17853379332398
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,238434,238434,4194304,256,0,0,12,24,63808,0x7fd66e582100,0x7fd647c24d80,17853379365488,17853379375867,17853379470907,17853379472345
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,238434,238434,4194304,256,0,0,12,24,65024,0x7fd66c109f80,0x7fd647c24dc0,17853379492904,17853379502747,17853379681627,17853379683210
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,238434,238434,4194304,256,0,0,12,24,66240,0x7fd66c109e00,0x7fd647c24e00,17853379702729,17853379712507,17853379890267,17853379891804
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,238434,238434,4194304,256,0,0,8,24,67456,0x7fd66c109c80,0x7fd647c24e40,17853379911654,17853379922907,17853380017467,17853380019001
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,238434,238434,4194304,256,0,0,12,24,68928,0x7fd66c109b00,0x7fd647c24e80,17853380038641,17853380049307,17853380153947,17853380155388
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,238434,238434,4194304,256,0,0,12,24,70144,0x7fd66c109980,0x7fd647c24ec0,17853380187807,17853380197467,17853380290107,17853380291675
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,238434,238434,4194304,256,0,0,12,24,71616,0x7fd66c109800,0x7fd647c24f00,17853380311304,17853380320667,17853380501627,17853380503139
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,238434,238434,4194304,256,0,0,12,24,72832,0x7fd66c109680,0x7fd647c24f40,17853380524119,17853380533947,17853380712827,17853380714314
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,238434,238434,4194304,256,0,0,8,24,74048,0x7fd66e582500,0x7fd647c24f80,17853380734164,17853380743387,17853380836667,17853380838191
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,238434,238434,4194304,256,0,0,12,24,75776,0x7fd66e582380,0x7fd647c24fc0,17853380857990,17853380866907,17853380974108,17853380975668
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,238434,238434,4194304,256,0,0,12,24,76992,0x7fd66e582200,0x7fd647c25000,17853381008227,17853381018268,17853381112188,17853381113684
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,238434,238434,4194304,256,0,0,12,24,78464,0x7fd66e582080,0x7fd647c25040,17853381134304,17853381144668,17853381324348,17853381325819
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,238434,238434,4194304,256,0,0,12,24,79936,0x7fd66c109f00,0x7fd647c25080,17853381345468,17853381354908,17853381535068,17853381536564
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,238434,238434,4194304,256,0,0,8,24,81408,0x7fd66c109d80,0x7fd647c250c0,17853381556203,17853381566268,17853381661628,17853381663040
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,238434,238434,4194304,256,0,0,12,24,83136,0x7fd66c109c00,0x7fd647c25100,17853381683210,17853381692668,17853381808348,17853381809847
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,238434,238434,4194304,256,0,0,12,24,84352,0x7fd66c109a80,0x7fd647c25140,17853381864385,17853381874108,17853381968668,17853381970133
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,238434,238434,4194304,256,0,0,12,24,85824,0x7fd66c109900,0x7fd647c25180,17853381990282,17853382001308,17853382180828,17853382182618
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,238434,238434,4194304,256,0,0,12,24,87296,0x7fd66c109780,0x7fd647c251c0,17853382205157,17853382215228,17853382393788,17853382395292
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,238434,238434,4194304,256,0,0,12,24,88768,0x7fd66c109600,0x7fd647c25200,17853382415522,17853382425948,17853382521308,17853382522839
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,238434,238434,4194304,256,0,0,12,24,90752,0x7fd66e582480,0x7fd647c25240,17853382542919,17853382553468,17853382674909,17853382676325
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,238434,238434,4194304,256,0,0,12,24,91968,0x7fd66e582300,0x7fd647c25280,17853382708895,17853382718589,17853382813629,17853382815162
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,238434,238434,4194304,256,0,0,12,24,93440,0x7fd66e582180,0x7fd647c252c0,17853382835241,17853382845949,17853383025949,17853383027487
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,238434,238434,4194304,256,0,0,12,24,94912,0x7fd66e582000,0x7fd647c25300,17853383043876,17853383051709,17853383230909,17853383232362
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,238434,238434,4194304,256,0,0,12,24,96384,0x7fd66c109e80,0x7fd647c25340,17853383248671,17853383256029,17853383351869,17853383353359
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,238434,238434,4194304,256,0,0,12,24,98368,0x7fd66c109d00,0x7fd647c25380,17853383369318,17853383378909,17853383504989,17853383506405
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,238434,238434,4194304,256,0,0,12,24,99584,0x7fd66c109b80,0x7fd647c253c0,17853383526794,17853383537309,17853383631069,17853383632452
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,238434,238434,4194304,256,0,0,12,24,101312,0x7fd66c109a00,0x7fd647c25400,17853383648041,17853383656349,17853383836989,17853383838427
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,238434,238434,4194304,256,0,0,12,24,102784,0x7fd66c109880,0x7fd647c25440,17853383852226,17853383860189,17853384041629,17853384043042
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,238434,238434,4194304,256,0,0,12,24,104256,0x7fd66c109700,0x7fd647c25480,17853384057181,17853384066589,17853384160989,17853384162419
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,238434,238434,4194304,256,0,0,12,24,106240,0x7fd66e582580,0x7fd647c254c0,17853384176678,17853384185469,17853384316029,17853384317535
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,238434,238434,4194304,256,0,0,12,24,107712,0x7fd66e582400,0x7fd647c25500,17853384338694,17853384349949,17853384443230,17853384444592
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,238434,238434,4194304,256,0,0,16,24,109440,0x7fd66e582280,0x7fd647c25540,17853384461571,17853384469470,17853384648030,17853384649437
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,238434,238434,4194304,256,0,0,16,24,111168,0x7fd66e582100,0x7fd647c25580,17853384664166,17853384672510,17853384851390,17853384852782
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,238434,238434,4194304,256,0,0,8,24,112896,0x7fd66c109f80,0x7fd647c255c0,17853384867081,17853384876510,17853384972350,17853384973879
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,238434,238434,4194304,256,0,0,12,24,115136,0x7fd66c109e00,0x7fd647c25600,17853384989388,17853384998910,17853385137310,17853385138755
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,238434,238434,4194304,256,0,0,12,24,116608,0x7fd66c109c80,0x7fd647c25640,17853385160014,17853385170910,17853385266110,17853385267521
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,238434,238434,4194304,256,0,0,16,24,118336,0x7fd66c109b00,0x7fd647c25680,17853385282121,17853385291070,17853385470110,17853385471546
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,238434,238434,4194304,256,0,0,16,24,120064,0x7fd66c109980,0x7fd647c256c0,17853385485536,17853385494910,17853385674430,17853385675901
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,238434,238434,4194304,256,0,0,12,24,121792,0x7fd66c109800,0x7fd647c25700,17853385690091,17853385698430,17853385796030,17853385797378
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,238434,238434,4194304,256,0,0,12,24,124032,0x7fd66c109680,0x7fd647c25740,17853385813418,17853385823230,17853385967710,17853385969114
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,238434,238434,4194304,256,0,0,12,24,125504,0x7fd66e582500,0x7fd647c25780,17853385989584,17853386000990,17853386098111,17853386099511
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,238434,238434,4194304,256,0,0,12,24,127488,0x7fd66e582380,0x7fd647c257c0,17853386113341,17853386121631,17853386305951,17853386307376
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,238434,238434,4194304,256,0,0,12,24,129216,0x7fd66e582200,0x7fd647c25800,17853386322405,17853386330111,17853386513311,17853386514861
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,238434,238434,4194304,256,0,0,12,24,130944,0x7fd66e582080,0x7fd647c25840,17853386529440,17853386537471,17853386638431,17853386639847
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,238434,238434,4194304,256,0,0,12,24,133440,0x7fd66c109f00,0x7fd647c25880,17853386654497,17853386662591,17853386817631,17853386819163
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,238434,238434,4194304,256,0,0,12,24,134912,0x7fd66c109d80,0x7fd647c258c0,17853386839453,17853386849951,17853386945791,17853386947310
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,238434,238434,4194304,256,0,0,12,24,136896,0x7fd66c109c00,0x7fd647c25900,17853386962329,17853386970111,17853387148511,17853387150065
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,238434,238434,4194304,256,0,0,12,24,138880,0x7fd66c109a80,0x7fd647c25940,17853387165734,17853387173471,17853387353951,17853387355540
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,238434,238434,4194304,256,0,0,12,24,140864,0x7fd66c109900,0x7fd647c25980,17853387369959,17853387377951,17853387485151,17853387486846
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,238434,238434,4194304,256,0,0,12,24,143616,0x7fd66c109780,0x7fd647c259c0,17853387501446,17853387509311,17853387680671,17853387682132
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,238434,238434,4194304,256,0,0,12,24,145344,0x7fd66c109600,0x7fd647c25a00,17853387703421,17853387713951,17853387809632,17853387811158
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,238434,238434,4194304,256,0,0,12,24,147584,0x7fd66e582480,0x7fd647c25a40,17853387827178,17853387835392,17853388016192,17853388017593
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,238434,238434,4194304,256,0,0,12,24,149568,0x7fd66e582300,0x7fd647c25a80,17853388032093,17853388040192,17853388219872,17853388221448
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,238434,238434,4194304,256,0,0,12,24,151552,0x7fd66e582180,0x7fd647c25ac0,17853388236758,17853388246912,17853388356832,17853388358395
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,238434,238434,4194304,256,0,0,12,24,154304,0x7fd66e582000,0x7fd647c25b00,17853388373444,17853388382752,17853388564512,17853388566070
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,238434,238434,4194304,256,0,0,12,24,156288,0x7fd66c109e80,0x7fd647c25b40,17853388587589,17853388597472,17853388700032,17853388701426
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,238434,238434,4194304,256,0,0,12,24,158784,0x7fd66c109d00,0x7fd647c25b80,17853388717986,17853388725952,17853388911872,17853388913381
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,238434,238434,4194304,256,0,0,12,24,161024,0x7fd66c109b80,0x7fd647c25bc0,17853388927261,17853388935392,17853389119872,17853389121236
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,238434,238434,4194304,256,0,0,12,24,163264,0x7fd66c109a00,0x7fd647c25c00,17853389134835,17853389143872,17853389265792,17853389267312
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,238434,238434,4194304,256,0,0,12,24,166528,0x7fd66c109880,0x7fd647c25c40,17853389282602,17853389292032,17853389498273,17853389519406
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,238434,238434,4194304,256,0,0,12,24,168512,0x7fd66c109700,0x7fd647c25c80,17853389535666,17853389546593,17853389656833,17853389658282
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,238434,238434,4194304,256,0,0,12,24,171264,0x7fd66e582580,0x7fd647c25cc0,17853389674412,17853389682913,17853389865633,17853389867207
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,238434,238434,4194304,256,0,0,12,24,173760,0x7fd66e582400,0x7fd647c25d00,17853389882317,17853389892193,17853390078433,17853390079932
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,238434,238434,4194304,256,0,0,12,24,176256,0x7fd66e582280,0x7fd647c25d40,17853390096002,17853390105473,17853390240033,17853390241438
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,238434,238434,4194304,256,0,0,12,24,179776,0x7fd66e582100,0x7fd647c25d80,17853390254848,17853390262753,17853390494753,17853390510641
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,238434,238434,4194304,256,0,0,12,24,182272,0x7fd66c109f80,0x7fd647c25dc0,17853390525931,17853390537633,17853390664673,17853390666187
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,238434,238434,4194304,256,0,0,12,24,185536,0x7fd66c109e00,0x7fd647c25e00,17853390680587,17853390688673,17853390878433,17853390880072
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,238434,238434,4194304,256,0,0,12,24,188544,0x7fd66c109c80,0x7fd647c25e40,17853390894582,17853390902753,17853391095233,17853391096667
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,238434,238434,4194304,256,0,0,12,24,191552,0x7fd66c109b00,0x7fd647c25e80,17853391111176,17853391119233,17853391279074,17853391280522
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,238434,238434,4194304,256,0,0,12,24,195840,0x7fd66c109980,0x7fd647c25ec0,17853391295262,17853391303394,17853391586594,17853391627604
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,238434,238434,4194304,256,0,0,12,24,198592,0x7fd66c109800,0x7fd647c25f00,17853391644153,17853391654914,17853391803234,17853391804749
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,238434,238434,4194304,256,0,0,12,24,202368,0x7fd66c109680,0x7fd647c25f40,17853391821579,17853391828994,17853392036514,17853392077102
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,238434,238434,4194304,256,0,0,12,24,205888,0x7fd66e582500,0x7fd647c25f80,17853392084762,17853392095234,17853392302434,17853392319066
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,238434,238434,4194304,256,0,0,12,24,209408,0x7fd66e582380,0x7fd647c25fc0,17853392326686,17853392336674,17853392522594,17853392524041
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,238434,238434,4194304,256,0,0,12,24,214464,0x7fd66e582200,0x7fd647c26000,17853392538891,17853392548834,17853392882914,17853392899062
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,238434,238434,4194304,256,0,0,12,24,217728,0x7fd66e582080,0x7fd647c26040,17853392915042,17853392925635,17853393093315,17853393094777
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,238434,238434,4194304,256,0,0,12,24,222016,0x7fd66c109f00,0x7fd647c26080,17853393109927,17853393118595,17853393347715,17853393365050
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,238434,238434,4194304,256,0,0,12,24,226048,0x7fd66c109d80,0x7fd647c260c0,17853393373070,17853393383235,17853393612995,17853393628784
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,238434,238434,4194304,256,0,0,12,24,230080,0x7fd66c109c00,0x7fd647c26100,17853393636584,17853393646595,17853393858435,17853393874138
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,238434,238434,4194304,256,0,0,12,24,235904,0x7fd66c109a80,0x7fd647c26140,17853393882958,17853393892995,17853394278435,17853394322967
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,238434,238434,4194304,256,0,0,12,24,239424,0x7fd66c109900,0x7fd647c26180,17853394339686,17853394349795,17853394536995,17853394538511
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,238434,238434,4194304,256,0,0,12,24,244224,0x7fd66c109780,0x7fd647c261c0,17853394553111,17853394560995,17853394811396,17853394854953
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,238434,238434,4194304,256,0,0,12,24,248768,0x7fd66c109600,0x7fd647c26200,17853394862603,17853394872996,17853395122276,17853395162696
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,238434,238434,4194304,256,0,0,12,24,253312,0x7fd66e582480,0x7fd647c26240,17853395169996,17853395180356,17853395416996,17853395460938
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,238434,238434,4194304,256,0,0,8,24,255552,0x7fd66e582300,0x7fd647c26280,17853395468628,17853395479076,17853395932996,17853395973596
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,238434,238434,4194304,256,0,0,12,24,259840,0x7fd66e582180,0x7fd647c262c0,17853395988605,17853395999396,17853396224676,17853396264908
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,238434,238434,4194304,256,0,0,12,24,265664,0x7fd66e582000,0x7fd647c26300,17853396272678,17853396282756,17853396580997,17853396621420
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,238434,238434,4194304,256,0,0,12,24,271232,0x7fd66c109e80,0x7fd647c26340,17853396630769,17853396640357,17853396938597,17853396981901
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,238434,238434,4194304,256,0,0,8,24,273216,0x7fd66c109d00,0x7fd647c26380,17853396990180,17853397000357,17853397296677,17853397316172
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,238434,238434,4194304,256,0,0,8,24,275712,0x7fd66c109b80,0x7fd647c263c0,17853397323962,17853397334437,17853397891557,17853397907428
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,238434,238434,4194304,256,0,0,12,24,280768,0x7fd66c109a00,0x7fd647c26400,17853397922097,17853397932997,17853398196838,17853398244909
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,238434,238434,4194304,256,0,0,12,24,287616,0x7fd66c109880,0x7fd647c26440,17853398253159,17853398263558,17853398614758,17853398660249
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,238434,238434,4194304,256,0,0,12,24,294208,0x7fd66c109700,0x7fd647c26480,17853398667379,17853398682118,17853399033478,17853399076959
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,238434,238434,4194304,256,0,0,8,24,296960,0x7fd66e582580,0x7fd647c264c0,17853399085538,17853399095718,17853399443238,17853399483669
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,238434,238434,4194304,256,0,0,8,24,299968,0x7fd66e582400,0x7fd647c26500,17853399491198,17853399501478,17853400162439,17853400210121
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,238434,238434,4194304,256,0,0,8,24,302720,0x7fd66e582280,0x7fd647c26540,17853400226560,17853400236199,17853400684039,17853400727478
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,238434,238434,4194304,256,0,0,12,24,305472,0x7fd66e582100,0x7fd647c26580,17853400734908,17853400745479,17853401209159,17853401254555
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,238434,238434,4194304,256,0,0,12,24,308224,0x7fd66c109f80,0x7fd647c265c0,17853401262935,17853401273639,17853401735560,17853401753193
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,238434,238434,4194304,256,0,0,8,24,310976,0x7fd66c109e00,0x7fd647c26600,17853401764152,17853401789160,17853402241160,17853402289999
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,238434,238434,4194304,256,0,0,8,24,313216,0x7fd66c109c80,0x7fd647c26640,17853402298769,17853402309000,17853403177961,17853403226186
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,238434,238434,4194304,256,0,0,8,24,315968,0x7fd66c109b00,0x7fd647c26680,17853403242506,17853403253481,17853404107561,17853404153433
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,238434,238434,4194304,256,0,0,12,24,318720,0x7fd66c109980,0x7fd647c266c0,17853404161333,17853404171881,17853405057482,17853405102819
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,238434,238434,4194304,256,0,0,12,24,321472,0x7fd66c109800,0x7fd647c26700,17853405113659,17853405145162,17853406024842,17853406071935
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,238434,238434,4194304,256,0,0,8,24,324224,0x7fd66c109680,0x7fd647c26740,17853406085685,17853406101482,17853406961163,17853407010752
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,238434,238434,4194304,256,0,0,8,24,326464,0x7fd66e582500,0x7fd647c26780,17853407019172,17853407029483,17853408726284,17853408800448
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,238434,238434,4194304,256,0,0,8,24,329216,0x7fd66e582380,0x7fd647c267c0,17853408816517,17853408827084,17853410491885,17853410563814
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,238434,238434,4194304,256,0,0,12,24,331968,0x7fd66e582200,0x7fd647c26800,17853410572544,17853410582925,17853412306926,17853412372679
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,238434,238434,4194304,256,0,0,12,24,334720,0x7fd66e582080,0x7fd647c26840,17853412383399,17853412402126,17853414117007,17853414187994
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,238434,238434,4194304,256,0,0,8,24,337472,0x7fd66c109f00,0x7fd647c26880,17853414196694,17853414207087,17853415879888,17853415948540
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,238434,238434,4194304,256,0,0,8,24,0,0x7fd66c109d80,0x7fd647c268c0,17853415957550,17853415981168,17853419338290,17853419414415
1 Index KernelName gpu-id queue-id queue-index pid tid grd wgr lds scr vgpr sgpr fbar sig obj DispatchNs BeginNs EndNs CompleteNs
2 0 __amd_rocclr_fillBufferAligned.kd 0 0 0 238434 238434 33554432 256 0 0 4 32 4160 0x0 0x7fd647c04280 17853365225848 17853365250419 17853365490099 17853365576439
3 1 void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd] 0 0 2 238434 238434 32768 256 0 0 12 24 13888 0x0 0x7fd647c23f80 17853370260633 17853370276021 17853370289461 17853370306822
4 2 void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd] 0 0 5 238434 238434 4194304 256 0 0 12 24 14336 0x7fd66e582380 0x7fd647c23fc0 17853370311482 17853370360501 17853370452981 17853370455238
5 3 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 8 238434 238434 4194304 256 0 0 16 24 15040 0x7fd66e582200 0x7fd647c24000 17853370476128 17853370485781 17853370665621 17853370667633
6 4 void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd] 0 0 11 238434 238434 4194304 256 0 0 16 24 15488 0x7fd66e582080 0x7fd647c24040 17853370682173 17853370690581 17853370869302 17853370871458
7 5 void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd] 0 0 14 238434 238434 4194304 256 0 0 12 24 15936 0x7fd66c109f00 0x7fd647c24080 17853370885518 17853370893622 17853370987062 17853370989065
8 6 void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd] 0 0 17 238434 238434 4194304 256 0 0 12 24 16384 0x7fd66c109d80 0x7fd647c240c0 17853371004375 17853371012662 17853371104502 17853371106392
9 7 void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd] 0 0 20 238434 238434 4194304 256 0 0 12 24 17088 0x7fd66c109c00 0x7fd647c24100 17853371133792 17853371144022 17853371236022 17853371238009
10 8 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 23 238434 238434 4194304 256 0 0 16 24 17792 0x7fd66c109a80 0x7fd647c24140 17853371255939 17853371265302 17853371443702 17853371445714
11 9 void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd] 0 0 26 238434 238434 4194304 256 0 0 16 24 18496 0x7fd66c109900 0x7fd647c24180 17853371463453 17853371472022 17853371651702 17853371653619
12 10 void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd] 0 0 29 238434 238434 4194304 256 0 0 16 24 19200 0x7fd66c109780 0x7fd647c241c0 17853371670068 17853371752342 17853371846102 17853371848234
13 11 void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd] 0 0 32 238434 238434 4194304 256 0 0 16 24 19904 0x7fd66c109600 0x7fd647c24200 17853371887383 17853371900822 17853371993462 17853371995550
14 12 void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd] 0 0 35 238434 238434 4194304 256 0 0 12 24 20608 0x7fd66e582480 0x7fd647c24240 17853372038389 17853372048342 17853372141302 17853372143427
15 13 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 38 238434 238434 4194304 256 0 0 16 24 21312 0x7fd66e582300 0x7fd647c24280 17853372165016 17853372175222 17853372354902 17853372356961
16 14 void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd] 0 0 41 238434 238434 4194304 256 0 0 16 24 22016 0x7fd66e582180 0x7fd647c242c0 17853372378331 17853372387862 17853372568183 17853372570076
17 15 void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd] 0 0 44 238434 238434 4194304 256 0 0 16 24 22720 0x7fd66e582000 0x7fd647c24300 17853372588936 17853372598743 17853372692663 17853372694633
18 16 void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd] 0 0 47 238434 238434 4194304 256 0 0 12 24 23424 0x7fd66c109e80 0x7fd647c24340 17853372716233 17853372727383 17853372821303 17853372823280
19 17 void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd] 0 0 50 238434 238434 4194304 256 0 0 12 24 24128 0x7fd66c109d00 0x7fd647c24380 17853372856349 17853372866263 17853372959543 17853372961476
20 18 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 53 238434 238434 4194304 256 0 0 16 24 24832 0x7fd66c109b80 0x7fd647c243c0 17853372983426 17853372992823 17853373172183 17853373174171
21 19 void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd] 0 0 56 238434 238434 4194304 256 0 0 16 24 25536 0x7fd66c109a00 0x7fd647c24400 17853373193601 17853373204663 17853373384023 17853373386026
22 20 void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd] 0 0 59 238434 238434 4194304 256 0 0 12 24 26240 0x7fd66c109880 0x7fd647c24440 17853373404926 17853373416343 17853373509623 17853373511723
23 21 void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd] 0 0 62 238434 238434 4194304 256 0 0 12 24 26944 0x7fd66c109700 0x7fd647c24480 17853373532722 17853373543543 17853373636983 17853373639060
24 22 void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd] 0 0 65 238434 238434 4194304 256 0 0 12 24 27648 0x7fd66e582580 0x7fd647c244c0 17853373670989 17853373682423 17853373775383 17853373777356
25 23 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 68 238434 238434 4194304 256 0 0 16 24 28608 0x7fd66e582400 0x7fd647c24500 17853373797266 17853373807383 17853373986583 17853373988551
26 24 void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd] 0 0 71 238434 238434 4194304 256 0 0 16 24 29312 0x7fd66e582280 0x7fd647c24540 17853374006851 17853374017463 17853374197944 17853374200306
27 25 void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd] 0 0 74 238434 238434 4194304 256 0 0 12 24 30016 0x7fd66e582100 0x7fd647c24580 17853374221155 17853374232664 17853374325304 17853374327363
28 26 void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd] 0 0 77 238434 238434 4194304 256 0 0 8 24 30976 0x7fd66c109f80 0x7fd647c245c0 17853374350282 17853374359704 17853374452184 17853374454200
29 27 void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd] 0 0 80 238434 238434 4194304 256 0 0 12 24 31680 0x7fd66c109e00 0x7fd647c24600 17853374488439 17853374498104 17853374591224 17853374593276
30 28 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 83 238434 238434 4194304 256 0 0 16 24 32640 0x7fd66c109c80 0x7fd647c24640 17853374612836 17853374623864 17853374803224 17853374805211
31 29 void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd] 0 0 86 238434 238434 4194304 256 0 0 12 24 33600 0x7fd66c109b00 0x7fd647c24680 17853374824170 17853374833944 17853375015064 17853375016616
32 30 void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd] 0 0 89 238434 238434 4194304 256 0 0 12 24 34560 0x7fd66c109980 0x7fd647c246c0 17853375035915 17853375044344 17853375138584 17853375140343
33 31 void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd] 0 0 92 238434 238434 4194304 256 0 0 8 24 35520 0x7fd66c109800 0x7fd647c24700 17853375161562 17853375171544 17853375265784 17853375267459
34 32 void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd] 0 0 95 238434 238434 4194304 256 0 0 12 24 36224 0x7fd66c109680 0x7fd647c24740 17853375300689 17853375310264 17853375404504 17853375406006
35 33 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 98 238434 238434 4194304 256 0 0 12 24 37184 0x7fd66e582500 0x7fd647c24780 17853375427215 17853375436984 17853375616824 17853375618571
36 34 void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd] 0 0 101 238434 238434 4194304 256 0 0 12 24 38144 0x7fd66e582380 0x7fd647c247c0 17853375637680 17853375647704 17853375826745 17853375828305
37 35 void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd] 0 0 104 238434 238434 4194304 256 0 0 12 24 39104 0x7fd66e582200 0x7fd647c24800 17853375848345 17853375857465 17853375951225 17853375952902
38 36 void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd] 0 0 107 238434 238434 4194304 256 0 0 8 24 40320 0x7fd66e582080 0x7fd647c24840 17853375972742 17853375983705 17853376077945 17853376079429
39 37 void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd] 0 0 110 238434 238434 4194304 256 0 0 12 24 41280 0x7fd66c109f00 0x7fd647c24880 17853376111698 17853376121785 17853376216185 17853376217666
40 38 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 113 238434 238434 4194304 256 0 0 12 24 42240 0x7fd66c109d80 0x7fd647c248c0 17853376237695 17853376248185 17853376427545 17853376428970
41 39 void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd] 0 0 116 238434 238434 4194304 256 0 0 12 24 43200 0x7fd66c109c00 0x7fd647c24900 17853376448540 17853376458425 17853376639225 17853376640755
42 40 void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd] 0 0 119 238434 238434 4194304 256 0 0 8 24 44160 0x7fd66c109a80 0x7fd647c24940 17853376661135 17853376671865 17853376766265 17853376767712
43 41 void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd] 0 0 122 238434 238434 4194304 256 0 0 12 24 45376 0x7fd66c109900 0x7fd647c24980 17853376787452 17853376796505 17853376891545 17853376893089
44 42 void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd] 0 0 125 238434 238434 4194304 256 0 0 12 24 46336 0x7fd66c109780 0x7fd647c249c0 17853376925198 17853376934905 17853377029465 17853377030986
45 43 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 128 238434 238434 4194304 256 0 0 12 24 47552 0x7fd66c109600 0x7fd647c24a00 17853377051455 17853377061785 17853377240665 17853377242080
46 44 void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd] 0 0 131 238434 238434 4194304 256 0 0 12 24 48512 0x7fd66e582480 0x7fd647c24a40 17853377261540 17853377271225 17853377451225 17853377452725
47 45 void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd] 0 0 134 238434 238434 4194304 256 0 0 8 24 49472 0x7fd66e582300 0x7fd647c24a80 17853377471865 17853377481785 17853377574746 17853377576232
48 46 void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd] 0 0 137 238434 238434 4194304 256 0 0 12 24 50688 0x7fd66e582180 0x7fd647c24ac0 17853377595852 17853377605626 17853377699386 17853377700889
49 47 void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd] 0 0 140 238434 238434 4194304 256 0 0 12 24 51648 0x7fd66e582000 0x7fd647c24b00 17853377733238 17853377742906 17853377834906 17853377836396
50 48 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 143 238434 238434 4194304 256 0 0 12 24 52864 0x7fd66c109e80 0x7fd647c24b40 17853377857845 17853377867546 17853378046426 17853378047970
51 49 void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd] 0 0 146 238434 238434 4194304 256 0 0 12 24 54080 0x7fd66c109d00 0x7fd647c24b80 17853378067680 17853378076986 17853378255546 17853378257345
52 50 void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd] 0 0 149 238434 238434 4194304 256 0 0 8 24 55296 0x7fd66c109b80 0x7fd647c24bc0 17853378277035 17853378285466 17853378380346 17853378381882
53 51 void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd] 0 0 152 238434 238434 4194304 256 0 0 12 24 56768 0x7fd66c109a00 0x7fd647c24c00 17853378401721 17853378410586 17853378506266 17853378507719
54 52 void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd] 0 0 155 238434 238434 4194304 256 0 0 12 24 57728 0x7fd66c109880 0x7fd647c24c40 17853378540478 17853378550426 17853378644026 17853378645675
55 53 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 158 238434 238434 4194304 256 0 0 12 24 58944 0x7fd66c109700 0x7fd647c24c80 17853378665435 17853378676026 17853378857466 17853378858970
56 54 void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd] 0 0 161 238434 238434 4194304 256 0 0 12 24 60160 0x7fd66e582580 0x7fd647c24cc0 17853378878800 17853378890106 17853379070906 17853379072325
57 55 void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd] 0 0 164 238434 238434 4194304 256 0 0 8 24 61376 0x7fd66e582400 0x7fd647c24d00 17853379092714 17853379102906 17853379197946 17853379199752
58 56 void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd] 0 0 167 238434 238434 4194304 256 0 0 12 24 62848 0x7fd66e582280 0x7fd647c24d40 17853379220781 17853379230266 17853379330747 17853379332398
59 57 void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd] 0 0 170 238434 238434 4194304 256 0 0 12 24 63808 0x7fd66e582100 0x7fd647c24d80 17853379365488 17853379375867 17853379470907 17853379472345
60 58 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 173 238434 238434 4194304 256 0 0 12 24 65024 0x7fd66c109f80 0x7fd647c24dc0 17853379492904 17853379502747 17853379681627 17853379683210
61 59 void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd] 0 0 176 238434 238434 4194304 256 0 0 12 24 66240 0x7fd66c109e00 0x7fd647c24e00 17853379702729 17853379712507 17853379890267 17853379891804
62 60 void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd] 0 0 179 238434 238434 4194304 256 0 0 8 24 67456 0x7fd66c109c80 0x7fd647c24e40 17853379911654 17853379922907 17853380017467 17853380019001
63 61 void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd] 0 0 182 238434 238434 4194304 256 0 0 12 24 68928 0x7fd66c109b00 0x7fd647c24e80 17853380038641 17853380049307 17853380153947 17853380155388
64 62 void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd] 0 0 185 238434 238434 4194304 256 0 0 12 24 70144 0x7fd66c109980 0x7fd647c24ec0 17853380187807 17853380197467 17853380290107 17853380291675
65 63 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 188 238434 238434 4194304 256 0 0 12 24 71616 0x7fd66c109800 0x7fd647c24f00 17853380311304 17853380320667 17853380501627 17853380503139
66 64 void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd] 0 0 191 238434 238434 4194304 256 0 0 12 24 72832 0x7fd66c109680 0x7fd647c24f40 17853380524119 17853380533947 17853380712827 17853380714314
67 65 void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd] 0 0 194 238434 238434 4194304 256 0 0 8 24 74048 0x7fd66e582500 0x7fd647c24f80 17853380734164 17853380743387 17853380836667 17853380838191
68 66 void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd] 0 0 197 238434 238434 4194304 256 0 0 12 24 75776 0x7fd66e582380 0x7fd647c24fc0 17853380857990 17853380866907 17853380974108 17853380975668
69 67 void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd] 0 0 200 238434 238434 4194304 256 0 0 12 24 76992 0x7fd66e582200 0x7fd647c25000 17853381008227 17853381018268 17853381112188 17853381113684
70 68 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 203 238434 238434 4194304 256 0 0 12 24 78464 0x7fd66e582080 0x7fd647c25040 17853381134304 17853381144668 17853381324348 17853381325819
71 69 void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd] 0 0 206 238434 238434 4194304 256 0 0 12 24 79936 0x7fd66c109f00 0x7fd647c25080 17853381345468 17853381354908 17853381535068 17853381536564
72 70 void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd] 0 0 209 238434 238434 4194304 256 0 0 8 24 81408 0x7fd66c109d80 0x7fd647c250c0 17853381556203 17853381566268 17853381661628 17853381663040
73 71 void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd] 0 0 212 238434 238434 4194304 256 0 0 12 24 83136 0x7fd66c109c00 0x7fd647c25100 17853381683210 17853381692668 17853381808348 17853381809847
74 72 void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd] 0 0 215 238434 238434 4194304 256 0 0 12 24 84352 0x7fd66c109a80 0x7fd647c25140 17853381864385 17853381874108 17853381968668 17853381970133
75 73 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 218 238434 238434 4194304 256 0 0 12 24 85824 0x7fd66c109900 0x7fd647c25180 17853381990282 17853382001308 17853382180828 17853382182618
76 74 void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd] 0 0 221 238434 238434 4194304 256 0 0 12 24 87296 0x7fd66c109780 0x7fd647c251c0 17853382205157 17853382215228 17853382393788 17853382395292
77 75 void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd] 0 0 224 238434 238434 4194304 256 0 0 12 24 88768 0x7fd66c109600 0x7fd647c25200 17853382415522 17853382425948 17853382521308 17853382522839
78 76 void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd] 0 0 227 238434 238434 4194304 256 0 0 12 24 90752 0x7fd66e582480 0x7fd647c25240 17853382542919 17853382553468 17853382674909 17853382676325
79 77 void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd] 0 0 230 238434 238434 4194304 256 0 0 12 24 91968 0x7fd66e582300 0x7fd647c25280 17853382708895 17853382718589 17853382813629 17853382815162
80 78 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 233 238434 238434 4194304 256 0 0 12 24 93440 0x7fd66e582180 0x7fd647c252c0 17853382835241 17853382845949 17853383025949 17853383027487
81 79 void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd] 0 0 236 238434 238434 4194304 256 0 0 12 24 94912 0x7fd66e582000 0x7fd647c25300 17853383043876 17853383051709 17853383230909 17853383232362
82 80 void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd] 0 0 239 238434 238434 4194304 256 0 0 12 24 96384 0x7fd66c109e80 0x7fd647c25340 17853383248671 17853383256029 17853383351869 17853383353359
83 81 void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd] 0 0 242 238434 238434 4194304 256 0 0 12 24 98368 0x7fd66c109d00 0x7fd647c25380 17853383369318 17853383378909 17853383504989 17853383506405
84 82 void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd] 0 0 245 238434 238434 4194304 256 0 0 12 24 99584 0x7fd66c109b80 0x7fd647c253c0 17853383526794 17853383537309 17853383631069 17853383632452
85 83 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 248 238434 238434 4194304 256 0 0 12 24 101312 0x7fd66c109a00 0x7fd647c25400 17853383648041 17853383656349 17853383836989 17853383838427
86 84 void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd] 0 0 251 238434 238434 4194304 256 0 0 12 24 102784 0x7fd66c109880 0x7fd647c25440 17853383852226 17853383860189 17853384041629 17853384043042
87 85 void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd] 0 0 254 238434 238434 4194304 256 0 0 12 24 104256 0x7fd66c109700 0x7fd647c25480 17853384057181 17853384066589 17853384160989 17853384162419
88 86 void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd] 0 0 257 238434 238434 4194304 256 0 0 12 24 106240 0x7fd66e582580 0x7fd647c254c0 17853384176678 17853384185469 17853384316029 17853384317535
89 87 void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd] 0 0 260 238434 238434 4194304 256 0 0 12 24 107712 0x7fd66e582400 0x7fd647c25500 17853384338694 17853384349949 17853384443230 17853384444592
90 88 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 263 238434 238434 4194304 256 0 0 16 24 109440 0x7fd66e582280 0x7fd647c25540 17853384461571 17853384469470 17853384648030 17853384649437
91 89 void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd] 0 0 266 238434 238434 4194304 256 0 0 16 24 111168 0x7fd66e582100 0x7fd647c25580 17853384664166 17853384672510 17853384851390 17853384852782
92 90 void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd] 0 0 269 238434 238434 4194304 256 0 0 8 24 112896 0x7fd66c109f80 0x7fd647c255c0 17853384867081 17853384876510 17853384972350 17853384973879
93 91 void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd] 0 0 272 238434 238434 4194304 256 0 0 12 24 115136 0x7fd66c109e00 0x7fd647c25600 17853384989388 17853384998910 17853385137310 17853385138755
94 92 void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd] 0 0 275 238434 238434 4194304 256 0 0 12 24 116608 0x7fd66c109c80 0x7fd647c25640 17853385160014 17853385170910 17853385266110 17853385267521
95 93 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 278 238434 238434 4194304 256 0 0 16 24 118336 0x7fd66c109b00 0x7fd647c25680 17853385282121 17853385291070 17853385470110 17853385471546
96 94 void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd] 0 0 281 238434 238434 4194304 256 0 0 16 24 120064 0x7fd66c109980 0x7fd647c256c0 17853385485536 17853385494910 17853385674430 17853385675901
97 95 void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd] 0 0 284 238434 238434 4194304 256 0 0 12 24 121792 0x7fd66c109800 0x7fd647c25700 17853385690091 17853385698430 17853385796030 17853385797378
98 96 void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd] 0 0 287 238434 238434 4194304 256 0 0 12 24 124032 0x7fd66c109680 0x7fd647c25740 17853385813418 17853385823230 17853385967710 17853385969114
99 97 void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd] 0 0 290 238434 238434 4194304 256 0 0 12 24 125504 0x7fd66e582500 0x7fd647c25780 17853385989584 17853386000990 17853386098111 17853386099511
100 98 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 293 238434 238434 4194304 256 0 0 12 24 127488 0x7fd66e582380 0x7fd647c257c0 17853386113341 17853386121631 17853386305951 17853386307376
101 99 void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd] 0 0 296 238434 238434 4194304 256 0 0 12 24 129216 0x7fd66e582200 0x7fd647c25800 17853386322405 17853386330111 17853386513311 17853386514861
102 100 void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd] 0 0 299 238434 238434 4194304 256 0 0 12 24 130944 0x7fd66e582080 0x7fd647c25840 17853386529440 17853386537471 17853386638431 17853386639847
103 101 void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd] 0 0 302 238434 238434 4194304 256 0 0 12 24 133440 0x7fd66c109f00 0x7fd647c25880 17853386654497 17853386662591 17853386817631 17853386819163
104 102 void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd] 0 0 305 238434 238434 4194304 256 0 0 12 24 134912 0x7fd66c109d80 0x7fd647c258c0 17853386839453 17853386849951 17853386945791 17853386947310
105 103 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 308 238434 238434 4194304 256 0 0 12 24 136896 0x7fd66c109c00 0x7fd647c25900 17853386962329 17853386970111 17853387148511 17853387150065
106 104 void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd] 0 0 311 238434 238434 4194304 256 0 0 12 24 138880 0x7fd66c109a80 0x7fd647c25940 17853387165734 17853387173471 17853387353951 17853387355540
107 105 void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd] 0 0 314 238434 238434 4194304 256 0 0 12 24 140864 0x7fd66c109900 0x7fd647c25980 17853387369959 17853387377951 17853387485151 17853387486846
108 106 void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd] 0 0 317 238434 238434 4194304 256 0 0 12 24 143616 0x7fd66c109780 0x7fd647c259c0 17853387501446 17853387509311 17853387680671 17853387682132
109 107 void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd] 0 0 320 238434 238434 4194304 256 0 0 12 24 145344 0x7fd66c109600 0x7fd647c25a00 17853387703421 17853387713951 17853387809632 17853387811158
110 108 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 323 238434 238434 4194304 256 0 0 12 24 147584 0x7fd66e582480 0x7fd647c25a40 17853387827178 17853387835392 17853388016192 17853388017593
111 109 void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd] 0 0 326 238434 238434 4194304 256 0 0 12 24 149568 0x7fd66e582300 0x7fd647c25a80 17853388032093 17853388040192 17853388219872 17853388221448
112 110 void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd] 0 0 329 238434 238434 4194304 256 0 0 12 24 151552 0x7fd66e582180 0x7fd647c25ac0 17853388236758 17853388246912 17853388356832 17853388358395
113 111 void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd] 0 0 332 238434 238434 4194304 256 0 0 12 24 154304 0x7fd66e582000 0x7fd647c25b00 17853388373444 17853388382752 17853388564512 17853388566070
114 112 void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd] 0 0 335 238434 238434 4194304 256 0 0 12 24 156288 0x7fd66c109e80 0x7fd647c25b40 17853388587589 17853388597472 17853388700032 17853388701426
115 113 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 338 238434 238434 4194304 256 0 0 12 24 158784 0x7fd66c109d00 0x7fd647c25b80 17853388717986 17853388725952 17853388911872 17853388913381
116 114 void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd] 0 0 341 238434 238434 4194304 256 0 0 12 24 161024 0x7fd66c109b80 0x7fd647c25bc0 17853388927261 17853388935392 17853389119872 17853389121236
117 115 void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd] 0 0 344 238434 238434 4194304 256 0 0 12 24 163264 0x7fd66c109a00 0x7fd647c25c00 17853389134835 17853389143872 17853389265792 17853389267312
118 116 void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd] 0 0 347 238434 238434 4194304 256 0 0 12 24 166528 0x7fd66c109880 0x7fd647c25c40 17853389282602 17853389292032 17853389498273 17853389519406
119 117 void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd] 0 0 350 238434 238434 4194304 256 0 0 12 24 168512 0x7fd66c109700 0x7fd647c25c80 17853389535666 17853389546593 17853389656833 17853389658282
120 118 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 353 238434 238434 4194304 256 0 0 12 24 171264 0x7fd66e582580 0x7fd647c25cc0 17853389674412 17853389682913 17853389865633 17853389867207
121 119 void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd] 0 0 356 238434 238434 4194304 256 0 0 12 24 173760 0x7fd66e582400 0x7fd647c25d00 17853389882317 17853389892193 17853390078433 17853390079932
122 120 void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd] 0 0 359 238434 238434 4194304 256 0 0 12 24 176256 0x7fd66e582280 0x7fd647c25d40 17853390096002 17853390105473 17853390240033 17853390241438
123 121 void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd] 0 0 362 238434 238434 4194304 256 0 0 12 24 179776 0x7fd66e582100 0x7fd647c25d80 17853390254848 17853390262753 17853390494753 17853390510641
124 122 void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd] 0 0 365 238434 238434 4194304 256 0 0 12 24 182272 0x7fd66c109f80 0x7fd647c25dc0 17853390525931 17853390537633 17853390664673 17853390666187
125 123 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 368 238434 238434 4194304 256 0 0 12 24 185536 0x7fd66c109e00 0x7fd647c25e00 17853390680587 17853390688673 17853390878433 17853390880072
126 124 void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd] 0 0 371 238434 238434 4194304 256 0 0 12 24 188544 0x7fd66c109c80 0x7fd647c25e40 17853390894582 17853390902753 17853391095233 17853391096667
127 125 void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd] 0 0 374 238434 238434 4194304 256 0 0 12 24 191552 0x7fd66c109b00 0x7fd647c25e80 17853391111176 17853391119233 17853391279074 17853391280522
128 126 void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd] 0 0 377 238434 238434 4194304 256 0 0 12 24 195840 0x7fd66c109980 0x7fd647c25ec0 17853391295262 17853391303394 17853391586594 17853391627604
129 127 void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd] 0 0 380 238434 238434 4194304 256 0 0 12 24 198592 0x7fd66c109800 0x7fd647c25f00 17853391644153 17853391654914 17853391803234 17853391804749
130 128 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 383 238434 238434 4194304 256 0 0 12 24 202368 0x7fd66c109680 0x7fd647c25f40 17853391821579 17853391828994 17853392036514 17853392077102
131 129 void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd] 0 0 386 238434 238434 4194304 256 0 0 12 24 205888 0x7fd66e582500 0x7fd647c25f80 17853392084762 17853392095234 17853392302434 17853392319066
132 130 void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd] 0 0 389 238434 238434 4194304 256 0 0 12 24 209408 0x7fd66e582380 0x7fd647c25fc0 17853392326686 17853392336674 17853392522594 17853392524041
133 131 void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd] 0 0 392 238434 238434 4194304 256 0 0 12 24 214464 0x7fd66e582200 0x7fd647c26000 17853392538891 17853392548834 17853392882914 17853392899062
134 132 void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd] 0 0 395 238434 238434 4194304 256 0 0 12 24 217728 0x7fd66e582080 0x7fd647c26040 17853392915042 17853392925635 17853393093315 17853393094777
135 133 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 398 238434 238434 4194304 256 0 0 12 24 222016 0x7fd66c109f00 0x7fd647c26080 17853393109927 17853393118595 17853393347715 17853393365050
136 134 void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd] 0 0 401 238434 238434 4194304 256 0 0 12 24 226048 0x7fd66c109d80 0x7fd647c260c0 17853393373070 17853393383235 17853393612995 17853393628784
137 135 void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd] 0 0 404 238434 238434 4194304 256 0 0 12 24 230080 0x7fd66c109c00 0x7fd647c26100 17853393636584 17853393646595 17853393858435 17853393874138
138 136 void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd] 0 0 407 238434 238434 4194304 256 0 0 12 24 235904 0x7fd66c109a80 0x7fd647c26140 17853393882958 17853393892995 17853394278435 17853394322967
139 137 void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd] 0 0 410 238434 238434 4194304 256 0 0 12 24 239424 0x7fd66c109900 0x7fd647c26180 17853394339686 17853394349795 17853394536995 17853394538511
140 138 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 413 238434 238434 4194304 256 0 0 12 24 244224 0x7fd66c109780 0x7fd647c261c0 17853394553111 17853394560995 17853394811396 17853394854953
141 139 void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd] 0 0 416 238434 238434 4194304 256 0 0 12 24 248768 0x7fd66c109600 0x7fd647c26200 17853394862603 17853394872996 17853395122276 17853395162696
142 140 void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd] 0 0 419 238434 238434 4194304 256 0 0 12 24 253312 0x7fd66e582480 0x7fd647c26240 17853395169996 17853395180356 17853395416996 17853395460938
143 141 void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd] 0 0 422 238434 238434 4194304 256 0 0 8 24 255552 0x7fd66e582300 0x7fd647c26280 17853395468628 17853395479076 17853395932996 17853395973596
144 142 void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd] 0 0 425 238434 238434 4194304 256 0 0 12 24 259840 0x7fd66e582180 0x7fd647c262c0 17853395988605 17853395999396 17853396224676 17853396264908
145 143 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 428 238434 238434 4194304 256 0 0 12 24 265664 0x7fd66e582000 0x7fd647c26300 17853396272678 17853396282756 17853396580997 17853396621420
146 144 void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd] 0 0 431 238434 238434 4194304 256 0 0 12 24 271232 0x7fd66c109e80 0x7fd647c26340 17853396630769 17853396640357 17853396938597 17853396981901
147 145 void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd] 0 0 434 238434 238434 4194304 256 0 0 8 24 273216 0x7fd66c109d00 0x7fd647c26380 17853396990180 17853397000357 17853397296677 17853397316172
148 146 void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd] 0 0 437 238434 238434 4194304 256 0 0 8 24 275712 0x7fd66c109b80 0x7fd647c263c0 17853397323962 17853397334437 17853397891557 17853397907428
149 147 void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd] 0 0 440 238434 238434 4194304 256 0 0 12 24 280768 0x7fd66c109a00 0x7fd647c26400 17853397922097 17853397932997 17853398196838 17853398244909
150 148 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 443 238434 238434 4194304 256 0 0 12 24 287616 0x7fd66c109880 0x7fd647c26440 17853398253159 17853398263558 17853398614758 17853398660249
151 149 void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd] 0 0 446 238434 238434 4194304 256 0 0 12 24 294208 0x7fd66c109700 0x7fd647c26480 17853398667379 17853398682118 17853399033478 17853399076959
152 150 void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd] 0 0 449 238434 238434 4194304 256 0 0 8 24 296960 0x7fd66e582580 0x7fd647c264c0 17853399085538 17853399095718 17853399443238 17853399483669
153 151 void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd] 0 0 452 238434 238434 4194304 256 0 0 8 24 299968 0x7fd66e582400 0x7fd647c26500 17853399491198 17853399501478 17853400162439 17853400210121
154 152 void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd] 0 0 455 238434 238434 4194304 256 0 0 8 24 302720 0x7fd66e582280 0x7fd647c26540 17853400226560 17853400236199 17853400684039 17853400727478
155 153 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 458 238434 238434 4194304 256 0 0 12 24 305472 0x7fd66e582100 0x7fd647c26580 17853400734908 17853400745479 17853401209159 17853401254555
156 154 void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd] 0 0 461 238434 238434 4194304 256 0 0 12 24 308224 0x7fd66c109f80 0x7fd647c265c0 17853401262935 17853401273639 17853401735560 17853401753193
157 155 void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd] 0 0 464 238434 238434 4194304 256 0 0 8 24 310976 0x7fd66c109e00 0x7fd647c26600 17853401764152 17853401789160 17853402241160 17853402289999
158 156 void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd] 0 0 467 238434 238434 4194304 256 0 0 8 24 313216 0x7fd66c109c80 0x7fd647c26640 17853402298769 17853402309000 17853403177961 17853403226186
159 157 void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd] 0 0 470 238434 238434 4194304 256 0 0 8 24 315968 0x7fd66c109b00 0x7fd647c26680 17853403242506 17853403253481 17853404107561 17853404153433
160 158 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 473 238434 238434 4194304 256 0 0 12 24 318720 0x7fd66c109980 0x7fd647c266c0 17853404161333 17853404171881 17853405057482 17853405102819
161 159 void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd] 0 0 476 238434 238434 4194304 256 0 0 12 24 321472 0x7fd66c109800 0x7fd647c26700 17853405113659 17853405145162 17853406024842 17853406071935
162 160 void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd] 0 0 479 238434 238434 4194304 256 0 0 8 24 324224 0x7fd66c109680 0x7fd647c26740 17853406085685 17853406101482 17853406961163 17853407010752
163 161 void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd] 0 0 482 238434 238434 4194304 256 0 0 8 24 326464 0x7fd66e582500 0x7fd647c26780 17853407019172 17853407029483 17853408726284 17853408800448
164 162 void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd] 0 0 485 238434 238434 4194304 256 0 0 8 24 329216 0x7fd66e582380 0x7fd647c267c0 17853408816517 17853408827084 17853410491885 17853410563814
165 163 void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd] 0 0 488 238434 238434 4194304 256 0 0 12 24 331968 0x7fd66e582200 0x7fd647c26800 17853410572544 17853410582925 17853412306926 17853412372679
166 164 void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd] 0 0 491 238434 238434 4194304 256 0 0 12 24 334720 0x7fd66e582080 0x7fd647c26840 17853412383399 17853412402126 17853414117007 17853414187994
167 165 void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd] 0 0 494 238434 238434 4194304 256 0 0 8 24 337472 0x7fd66c109f00 0x7fd647c26880 17853414196694 17853414207087 17853415879888 17853415948540
168 166 void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd] 0 0 497 238434 238434 4194304 256 0 0 8 24 0 0x7fd66c109d80 0x7fd647c268c0 17853415957550 17853415981168 17853419338290 17853419414415