Files
rocm-systems/tests/workloads/LDS/mi100/SQ_INST_LEVEL_LDS.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

40 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_LDSSQ_INST_LEVEL_LDSSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000886028886033335544322560083264640x00x7fcf4e40418000012075646180516257120756464244109851207564642473418412075646424847586
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00288602888603332768256002424124800x00x7fcf4e43510000012075646439713714120756464400276381207564644003435812075646440043206
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0048860288860334194304256002424129280x7fd05a0919000x7fcf4e43514000012075646440101765120756464403210771207564644045467712075646440458067
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0068860288860334194304256003624136320x7fd05a0918000x7fcf4e43518000012075646440525402120756464406972361207564644094587512075646441029148
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0088860288860334194304256002824140800x7fd05a0917000x7fcf4e4351c000012075646441059254120756464412557931207564644150235212075646441570835
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00108860288860334194304256002424145280x7fd05a0916000x7fcf4e43520000012075646441599047120756464417831511207564644191611112075646441918942
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00128860288860334194304256002424149760x7fd05a0915000x7fcf4e43524000012075646441968183120756464421516301207564644228554912075646442288739
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00148860288860334194304256002424154240x7fd05a0914000x7fcf4e43528000012075646442362747120756464425369081207564644266730712075646442670128
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00168860288860334194304256002824161280x7fd05a0913000x7fcf4e4352c000012075646442719460120756464428967461207564644314730512075646443192128
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00188860288860334194304256002824168320x7fd05a091a000x7fcf4e43530000012075646443220541120756464434065041207564644365370312075646443696445
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00208860288860334194304256002424175360x7fd05a0919000x7fcf4e43534000012075646443720630120756464439121021207564644404458212075646444047788
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00228860288860334194304256002424182400x7fd05a0918000x7fcf4e43538000012075646444097811120756464442761011207564644441258012075646444415431
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00248860288860334194304256002424189440x7fd05a0917000x7fcf4e4353c000012075646444476996120756464446464991207564644477337812075646444776072
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00268860288860334194304256002824199040x7fd05a0916000x7fcf4e43540000012075646444824071120756464450010571207564644525001612075646445320073
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00288860288860334194304256002824206080x7fd05a0915000x7fcf4e43544000012075646445348866120756464455328951207564644578089412075646445849847
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00308860288860334194304256002424213120x7fd05a0914000x7fcf4e43548000012075646445877028120756464460730531207564644620041212075646446203725
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00328860288860334194304256002424220160x7fd05a0913000x7fcf4e4354c000012075646446253868120756464464239311207564644655657112075646446559346
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00348860288860334194304256002424227200x7fd05a091a000x7fcf4e43550000012075646446620520120756464467877701207564644691544912075646446918533
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00368860288860334194304256002824236800x7fd05a0919000x7fcf4e43554000012075646446967304120756464471527281207564644740408712075646447474216
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00388860288860334194304256002824243840x7fd05a0918000x7fcf4e43558000012075646447499673120756464476919261207564644794504512075646447988983
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00408860288860334194304256002424250880x7fd05a0917000x7fcf4e4355c000012075646448022014120756464482156041207564644834744312075646448350274
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00428860288860334194304256002424257920x7fd05a0916000x7fcf4e43560000012075646448403954120756464485706421207564644870072212075646448703681
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00448860288860334194304256002424264960x7fd05a0915000x7fcf4e43564000012075646448769143120756464489370411207564644906536012075646449069030
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00468860288860334194304256002824277120x7fd05a0914000x7fcf4e43568000012075646449116989120756464492893591207564644953623812075646449605307
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00488860288860334194304256002824284160x7fd05a0913000x7fcf4e4356c000012075646449634230120756464498207171207564645006983612075646450140281
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00508860288860334194304256002424291200x7fd05a091a000x7fcf4e43570000012075646450168012120756464503570351207564645048631412075646450489199
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00528860288860334194304256002424300800x7fd05a0919000x7fcf4e43574000012075646450541316120756464507088731207564645084183312075646450844690
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00548860288860334194304256002424307840x7fd05a0918000x7fcf4e43578000012075646450906835120756464510802321207564645121639112075646451219727
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00568860288860334194304256002824320000x7fd05a0917000x7fcf4e4357c000012075646451269339120756464514477501207564645169718912075646451766684
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00588860288860334194304256002824329600x7fd05a0916000x7fcf4e43580000012075646451791650120756464519794281207564645223766712075646452306867
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00608860288860334194304256002424339200x7fd05a0915000x7fcf4e43584000012075646452332305120756464525194261207564645264774512075646452650606
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00628860288860334194304256002424348800x7fd05a0914000x7fcf4e43588000012075646452698696120756464528663041207564645299942412075646453006518
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00648860288860334194304256002424358400x7fd05a0913000x7fcf4e4358c000012075646453065918120756464532355831207564645336310212075646453366016
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00668860288860334194304256002824373120x7fd05a091a000x7fcf4e43590000012075646453416700120756464535840611207564645383862012075646453882936
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00688860288860334194304256002824382720x7fd05a0919000x7fcf4e43594000012075646453908805120756464540998991207564645435173812075646454422810
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00708860288860334194304256002424392320x7fd05a0918000x7fcf4e43598000012075646454450702120756464546314171207564645476453612075646454767330
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00728860288860334194304256002424401920x7fd05a0917000x7fcf4e4359c000012075646454816221120756464549944551207564645512821512075646455131336
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00748860288860334194304256002424411520x7fd05a0916000x7fcf4e435a0000012075646455192650120756464553634141207564645549125312075646455494301
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00768860288860334194304256002824426240x7fd05a0915000x7fcf4e435a4000012075646455543242120756464557214921207564645598245112075646456052629
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00788860288860334194304256002824435840x7fd05a0914000x7fcf4e435a8000012075646456078196120756464562669301207564645651700912075646456586461
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00808860288860334194304256002424445440x7fd05a0913000x7fcf4e435ac000012075646456612309120756464567942881207564645692244712075646456925361
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00828860288860334194304256002424457600x7fd05a091a000x7fcf4e435b0000012075646456974031120756464571464461207564645728196612075646457284728
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00848860288860334194304256002424467200x7fd05a0919000x7fcf4e435b4000012075646457346373120756464575158851207564645764388412075646457646741
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00868860288860334194304256002824484480x7fd05a0918000x7fcf4e435b8000012075646457694500120756464578699631207564645813476212075646458205860
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00888860288860334194304256002824494080x7fd05a0917000x7fcf4e435bc000012075646458234073120756464584184411207564645870644012075646458776791
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00908860288860334194304256002424503680x7fd05a0916000x7fcf4e435c0000012075646458803491120756464589857991207564645911411812075646459116984
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00928860288860334194304256002424515840x7fd05a0915000x7fcf4e435c4000012075646459166786120756464593357171207564645947075612075646459473646
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00948860288860334194304256002424525440x7fd05a0914000x7fcf4e435c8000012075646459534399120756464597016361207564645983347512075646459836391
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00968860288860334194304256002824542720x7fd05a0913000x7fcf4e435cc000012075646459885642120756464600757141207564646034019312075646460410638
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00988860288860334194304256002824554880x7fd05a091a000x7fcf4e435d0000012075646460438149120756464606230721207564646087475112075646460918983
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001008860288860334194304256002424567040x7fd05a0919000x7fcf4e435d4000012075646460942206120756464611353891207564646127202912075646461275245
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001028860288860334194304256002424581760x7fd05a0918000x7fcf4e435d8000012075646461326991120756464614977881207564646163490712075646461637859
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001048860288860334194304256002424593920x7fd05a0917000x7fcf4e435dc000012075646461698010120756464618633861207564646199378612075646461996776
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001068860288860334194304256002824613760x7fd05a0916000x7fcf4e435e0000012075646462046578120756464622222651207564646248530412075646462555664
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001088860288860334194304256002824625920x7fd05a0915000x7fcf4e435e4000012075646462580010120756464627645031207564646301442212075646463084187
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001108860288860334194304256002424638080x7fd05a0914000x7fcf4e435e8000012075646463114643120756464633027401207564646343522012075646463438054
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001128860288860334194304256002424652800x7fd05a0913000x7fcf4e435ec000012075646463486043120756464636574591207564646379985812075646463802702
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001148860288860334194304256002424664960x7fd05a091a000x7fcf4e435f0000012075646463866160120756464640369771207564646416545712075646464168742
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001168860288860334194304256002824684800x7fd05a0919000x7fcf4e435f4000012075646464217533120756464643921761207564646465841512075646464727671
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001188860288860334194304256002824696960x7fd05a0918000x7fcf4e435f8000012075646464754300120756464649363331207564646518689212075646465257456
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001208860288860334194304256002424709120x7fd05a0917000x7fcf4e435fc000012075646465284686120756464654659311207564646559857112075646465601685
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001228860288860334194304256002424723840x7fd05a0916000x7fcf4e43600000012075646465650265120756464658179301207564646595824912075646465960993
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001248860288860334194304256002424736000x7fd05a0915000x7fcf4e43604000012075646466029330120756464661916881207564646632768812075646466330850
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001268860288860334194304256002824758400x7fd05a0914000x7fcf4e43608000012075646466379932120756464665544071207564646681520512075646466883387
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001288860288860334194304256002824770560x7fd05a0913000x7fcf4e4360c000012075646466911950120756464671030441207564646736032312075646467431466
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001308860288860334194304256002424782720x7fd05a091a000x7fcf4e43610000012075646467459798120756464676452821207564646777424112075646467777108
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001328860288860334194304256002424800000x7fd05a0919000x7fcf4e43614000012075646467825829120756464680000011207564646814336012075646468146715
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001348860288860334194304256002424812160x7fd05a0918000x7fcf4e43618000012075646468208370120756464683753591207564646850943812075646468512335
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001368860288860334194304256002824834560x7fd05a0917000x7fcf4e4361c000012075646468559893120756464687315171207564646899391612075646469046107
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001388860288860334194304256002824849280x7fd05a0916000x7fcf4e43620000012075646469072886120756464692561551207564646950783412075646469557928
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001408860288860334194304256002424864000x7fd05a0915000x7fcf4e43624000012075646469585699120756464697625531207564646989647312075646469899703
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001428860288860334194304256002424881280x7fd05a0914000x7fcf4e43628000012075646469946810120756464701262321207564647027583112075646470278727
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001448860288860334194304256002424896000x7fd05a0913000x7fcf4e4362c000012075646470359898120756464705222301207564647065838912075646470661378
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001468860288860334194304256002824920960x7fd05a091a000x7fcf4e43630000012075646470713395120756464708828681207564647114654712075646471198917
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001488860288860334194304256002824935680x7fd05a0919000x7fcf4e43634000012075646471225727120756464714075061207564647166046512075646471711179
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001508860288860334194304256002424950400x7fd05a0918000x7fcf4e43638000012075646471736076120756464719198241207564647205518312075646472058144
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001528860288860334194304256002424967680x7fd05a0917000x7fcf4e4363c000012075646472108488120756464722846221207564647244350212075646472446496
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001548860288860334194304256002424982400x7fd05a0916000x7fcf4e43640000012075646472508281120756464726726211207564647280894012075646472812286
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015688602888603341943042560028241007360x7fd05a0915000x7fcf4e43644000012075646472860205120756464730356591207564647329821812075646473350937
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015888602888603341943042560028241022080x7fd05a0914000x7fcf4e43648000012075646473378839120756464735618971207564647381709612075646473841118
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016088602888603341943042560024241036800x7fd05a0913000x7fcf4e4364c000012075646473883006120756464740535751207564647418797412075646474191309
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016288602888603341943042560024241056640x7fd05a091a000x7fcf4e43650000012075646474238667120756464744142131207564647457885312075646474581945
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016488602888603341943042560024241071360x7fd05a0919000x7fcf4e43654000012075646474642147120756464748073321207564647493773112075646474940691
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016688602888603341943042560028241098880x7fd05a0918000x7fcf4e43658000012075646474989913120756464751702101207564647543468912075646475488169
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016888602888603341943042560028241113600x7fd05a0917000x7fcf4e4365c000012075646475513336120756464756958081207564647594764712075646475997926
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017088602888603341943042560024241128320x7fd05a0916000x7fcf4e43660000012075646476030367120756464762193261207564647635532512075646476359117
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017288602888603341943042560024241148160x7fd05a0915000x7fcf4e43664000012075646476406696120756464765780441207564647675148412075646476754733
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017488602888603341943042560024241162880x7fd05a0914000x7fcf4e43668000012075646476815235120756464769809231207564647711260212075646477116064
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017688602888603341943042560028241190400x7fd05a0913000x7fcf4e4366c000012075646477163783120756464773393211207564647759708012075646477647832
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017888602888603341943042560028241207680x7fd05a091a000x7fcf4e43670000012075646477674171120756464778537191207564647810587812075646478157369
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018088602888603341943042560024241224960x7fd05a0919000x7fcf4e43674000012075646478184440120756464783645971207564647849739612075646478500417
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018288602888603341943042560024241247360x7fd05a0918000x7fcf4e43678000012075646478548396120756464787217151207564647890427512075646478907333
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018488602888603341943042560024241264640x7fd05a0917000x7fcf4e4367c000012075646478967755120756464791375541207564647927707312075646479280246
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018688602888603341943042560020241279360x7fd05a0916000x7fcf4e43680000012075646479328265120756464795033121207564647976971112075646479792588
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018888602888603341943042560028241296640x7fd05a0915000x7fcf4e43684000012075646479837842120756464800033101207564648026282912075646480313567
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019088602888603341943042560024241313920x7fd05a0914000x7fcf4e43688000012075646480340396120756464805228281207564648065962712075646480662956
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019288602888603341943042560024241336320x7fd05a0913000x7fcf4e4368c000012075646480710023120756464808799461207564648107194512075646481121939
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019488602888603341943042560024241353600x7fd05a091a000x7fcf4e43690000012075646481162795120756464813287441207564648146330412075646481466349
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019688602888603341943042560020241368320x7fd05a0919000x7fcf4e43694000012075646481514779120756464816861831207564648197018212075646482023965
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019888602888603341943042560028241385600x7fd05a0918000x7fcf4e43698000012075646482052328120756464822365801207564648249129912075646482542429
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020088602888603341943042560024241402880x7fd05a0917000x7fcf4e4369c000012075646482569699120756464827501781207564648288761812075646482890746
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020288602888603341943042560024241427840x7fd05a0916000x7fcf4e436a0000012075646482939907120756464831191371207564648332873612075646483380015
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020488602888603341943042560024241447680x7fd05a0915000x7fcf4e436a4000012075646483419629120756464835871351207564648372665412075646483729785
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020688602888603341943042560020241457280x7fd05a0914000x7fcf4e436a8000012075646483779037120756464839572131207564648426441212075646484316285
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020888602888603341943042560028241477120x7fd05a0913000x7fcf4e436ac000012075646484341162120756464845260111207564648478553012075646484836101
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021088602888603341943042560024241496960x7fd05a091a000x7fcf4e436b0000012075646484861929120756464850501691207564648519016812075646485193245
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021288602888603341943042560024241521920x7fd05a0919000x7fcf4e436b4000012075646485241154120756464854152871207564648564280612075646485693194
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021488602888603341943042560024241541760x7fd05a0918000x7fcf4e436b8000012075646485734050120756464859031251207564648603960412075646486043105
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021688602888603341943042560020241556480x7fd05a0917000x7fcf4e436bc000012075646486095432120756464862666431207564648659672212075646486647849
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021888602888603341943042560028241576320x7fd05a0916000x7fcf4e436c0000012075646486673326120756464868554411207564648710696012075646487134914
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022088602888603341943042560024241596160x7fd05a0915000x7fcf4e436c4000012075646487177884120756464873415001207564648747590012075646487483041
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022288602888603341943042560024241623680x7fd05a0914000x7fcf4e436c8000012075646487526552120756464876982981207564648794421712075646487993760
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022488602888603341943042560024241646080x7fd05a0913000x7fcf4e436cc000012075646488035698120756464882128561207564648835429512075646488357265
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022688602888603341943042560020241663360x7fd05a091a000x7fcf4e436d0000012075646488405225120756464885776551207564648895589312075646489011451
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022888602888603341943042560028241685760x7fd05a0919000x7fcf4e436d4000012075646489040475120756464892230931207564648947909212075646489530526
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023088602888603341943042560024241708160x7fd05a0918000x7fcf4e436d8000012075646489559189120756464897386111207564648987749012075646489879955
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023288602888603341943042560024241740800x7fd05a0917000x7fcf4e436dc000012075646489929688120756464901176491207564649039828812075646490451337
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023488602888603341943042560024241765760x7fd05a0916000x7fcf4e436e0000012075646490489678120756464906549281207564649079764712075646490800105
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023688602888603341943042560020241777920x7fd05a0915000x7fcf4e436e4000012075646490846852120756464910266061207564649145348512075646491505045
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023888602888603341943042560028241802880x7fd05a0914000x7fcf4e436e8000012075646491530012120756464917189241207564649197812312075646492028929
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024088602888603341943042560024241827840x7fd05a0913000x7fcf4e436ec000012075646492062622120756464922344421207564649237412212075646492376675
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024288602888603341943042560024241863040x7fd05a091a000x7fcf4e436f0000012075646492425125120756464925994011207564649291396012075646492963656
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024488602888603341943042560024241893120x7fd05a0919000x7fcf4e436f4000012075646493008860120756464931773191207564649333043812075646493333333
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024688602888603341943042560020241907840x7fd05a0918000x7fcf4e436f8000012075646493383817120756464935601981207564649409523612075646494146304
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024888602888603341943042560028241937920x7fd05a0917000x7fcf4e436fc000012075646494173645120756464943629151207564649466259412075646494712647
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025088602888603341943042560024241968000x7fd05a0916000x7fcf4e43700000012075646494739236120756464949230731207564649507811212075646495081061
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025288602888603341943042560024242010880x7fd05a0915000x7fcf4e43704000012075646495135182120756464953227511207564649570867012075646495758340
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025488602888603341943042560024242046080x7fd05a0914000x7fcf4e43708000012075646495797843120756464959656291207564649614082912075646496143826
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025688602888603341943042560020242060800x7fd05a0913000x7fcf4e4370c000012075646496191946120756464963697881207564649699202612075646497042807
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025888602888603341943042560028242096000x7fd05a091a000x7fcf4e43710000012075646497071030120756464972513851207564649757714412075646497626532
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026088602888603341943042560024242131200x7fd05a0919000x7fcf4e43714000012075646497655987120756464978347431207564649801314212075646498015735
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026288602888603341943042560024242181760x7fd05a0918000x7fcf4e43718000012075646498067732120756464982461011207564649870338012075646498755290
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026488602888603341943042560024242222080x7fd05a0917000x7fcf4e4371c000012075646498794783120756464989609791207564649916049812075646499211828
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026688602888603341943042560020242239360x7fd05a0916000x7fcf4e43720000012075646499244739120756464994256171207564650013041512075646500181250
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026888602888603341943042560028242279680x7fd05a0915000x7fcf4e43724000012075646500213550120756465003888141207564650076177312075646500810730
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027088602888603341943042560024242320000x7fd05a0914000x7fcf4e43728000012075646500837640120756465010222521207564650122625112075646501276275
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027288602888603341943042560024242378240x7fd05a0913000x7fcf4e4372c000012075646501304006120756465014856101207564650202864812075646502079528
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027488602888603341943042560024242423680x7fd05a091a000x7fcf4e43730000012075646502120454120756465022900871207564650251280712075646502560902
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027688602888603341943042560020242435840x7fd05a0919000x7fcf4e43734000012075646502587381120756465027678461207564650356848312075646503620692
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027888602888603341943042560028242481280x7fd05a0918000x7fcf4e43738000012075646503648143120756465038310421207564650427584112075646504328277
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028088602888603341943042560024242526720x7fd05a0917000x7fcf4e4373c000012075646504355387120756465045499201207564650477663912075646504826062
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028288602888603341943042560024242592640x7fd05a0916000x7fcf4e43740000012075646504851900120756465050447981207564650564223612075646505694446
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028488602888603341943042560024242648320x7fd05a0915000x7fcf4e43744000012075646505735312120756465059015951207564650617215412075646506222517
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028688602888603341943042560020242663040x7fd05a0914000x7fcf4e43748000012075646506249517120756465064305531207564650741663012075646507487378
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028888602888603341943042560028242718720x7fd05a0913000x7fcf4e4374c000012075646507520309120756465077033491207564650821870712075646508289479
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029088602888603341943042560024242774400x7fd05a091a000x7fcf4e43750000012075646508325616120756465084918261207564650879486512075646508863355
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029288602888603341943042560012242799360x7fd05a0919000x7fcf4e43754000012075646508894543120756465090876641207564650982670212075646509896074
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029488602888603341943042560024242865280x7fd05a0918000x7fcf4e43758000012075646509941298120756465101174211207564651043517912075646510505808
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029688602888603341943042560020242880000x7fd05a0917000x7fcf4e4375c000012075646510537016120756465107220581207564651189293412075646511962264
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029888602888603341943042560032242945920x7fd05a0916000x7fcf4e43760000012075646511997239120756465121886131207564651279821112075646512869500
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030088602888603341943042560024243011840x7fd05a0915000x7fcf4e43764000012075646512897583120756465130849301207564651340412912075646513474375
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030288602888603341943042560012243049600x7fd05a0914000x7fcf4e43768000012075646513501886120756465136826881207564651456172512075646514631866
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030488602888603341943042560024243136000x7fd05a0913000x7fcf4e4376c000012075646514673212120756465148410841207564651525388312075646515323852
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030688602888603341943042560020243148160x7fd05a091a000x7fcf4e43770000012075646515357394120756465155297221207564651707707712075646517148393
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030888602888603341943042560020243175680x7fd05a0919000x7fcf4e43774000012075646517182055120756465173617161207564651815723312075646518227298
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031088602888603341943042560012243203200x7fd05a0918000x7fcf4e43778000012075646518259948120756465184388321207564651885387012075646518923872
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031288602888603341943042560012243240960x7fd05a0917000x7fcf4e4377c000012075646518954770120756465191449091207564652030378512075646520375199
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031488602888603341943042560012243288960x7fd05a0916000x7fcf4e43780000012075646520423219120756465205905041207564652137642212075646521446871
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031688602888603341943042560020243301120x7fd05a0915000x7fcf4e43784000012075646521478680120756465216626611207564652471161012075646524782370
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031888602888603341943042560020243328640x7fd05a0914000x7fcf4e43788000012075646524814900120756465249970491207564652654232412075646526614525
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032088602888603341943042560012243356160x7fd05a0913000x7fcf4e4378c000012075646526643479120756465268340031207564652762360012075646527694592
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032288602888603341943042560012243393920x7fd05a091a000x7fcf4e43790000012075646527722464120756465279071191207564653018935112075646530259769
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032488602888603341943042560012243441920x7fd05a0919000x7fcf4e43794000012075646530305965120756465304784701207564653201366512075646532083729
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032688602888603341943042560020243454080x7fd05a0918000x7fcf4e43798000012075646532117011120756465322992641207564653835652312075646538426527
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032888602888603341943042560020243481600x7fd05a0917000x7fcf4e4379c000012075646538457595120756465386366821207564654168083212075646541751446
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033088602888603341943042560012243509120x7fd05a0916000x7fcf4e437a0000012075646541783025120756465419694711207564654350930512075646543581718
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332886028886033419430425600122400x7fd05a0915000x7fcf4e437a4000012075646543613837120756465437990641207564654832784912075646548401255