Files
rocm-systems/tests/workloads/Axes1/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.kd000901311901316335544322560083264640x00x7f8ba160418000012075942327036344120759425710379501207594257136018912075942571463912
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00290131190131632768256002424124800x00x7f8ba163510000012075942586056261120759425863551191207594258636183912075942586377678
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0049013119013164194304256002424129280x7f8cad17c9000x7f8ba163514000012075942586430637120759425866464781207594258677959712075942586783532
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0069013119013164194304256003624136320x7f8cad17c8000x7f8ba163518000012075942586848583120759425870138361207594258726199512075942587313227
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0089013119013164194304256002824140800x7f8cad17c7000x7f8ba16351c000012075942587346699120759425875309531207594258778727212075942587833313
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00109013119013164194304256002424145280x7f8cad17c6000x7f8ba163520000012075942587859883120759425880527111207594258818679012075942588190577
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00129013119013164194304256002424149760x7f8cad17c5000x7f8ba163524000012075942588231564120759425884248691207594258855558912075942588558702
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00149013119013164194304256002424154240x7f8cad17c4000x7f8ba163528000012075942588636646120759425888029481207594258893478712075942588938247
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00169013119013164194304256002824161280x7f8cad17c3000x7f8ba16352c000012075942588985825120759425891733461207594258943270512075942589454366
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00189013119013164194304256002824168320x7f8cad17ca000x7f8ba163530000012075942589503047120759425896658241207594258992134212075942589968021
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00209013119013164194304256002424175360x7f8cad17c9000x7f8ba163534000012075942589995662120759425901941411207594259032774112075942590331386
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00229013119013164194304256002424182400x7f8cad17c8000x7f8ba163538000012075942590377532120759425905707791207594259070709912075942590710370
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00249013119013164194304256002424189440x7f8cad17c7000x7f8ba16353c000012075942590769590120759425909334981207594259106197712075942591066142
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00269013119013164194304256002824199040x7f8cad17c6000x7f8ba163540000012075942591114481120759425912981361207594259154741512075942591593802
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00289013119013164194304256002824206080x7f8cad17c5000x7f8ba163544000012075942591620161120759425917971741207594259204917312075942592097428
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00309013119013164194304256002424213120x7f8cad17c4000x7f8ba163548000012075942592120701120759425923010111207594259243269112075942592436248
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00329013119013164194304256002424220160x7f8cad17c3000x7f8ba16354c000012075942592486060120759425926632501207594259279620912075942592799663
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00349013119013164194304256002424227200x7f8cad17ca000x7f8ba163550000012075942592862871120759425930579681207594259318804712075942593191772
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00369013119013164194304256002824236800x7f8cad17c9000x7f8ba163554000012075942593239971120759425934264461207594259367940512075942593724281
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00389013119013164194304256002824243840x7f8cad17c8000x7f8ba163558000012075942593750039120759425939301241207594259418420312075942594229420
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00409013119013164194304256002424250880x7f8cad17c7000x7f8ba16355c000012075942594267321120759425944419621207594259457380112075942594577147
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00429013119013164194304256002424257920x7f8cad17c6000x7f8ba163560000012075942594625136120759425948109201207594259493923912075942594942656
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00449013119013164194304256002424264960x7f8cad17c5000x7f8ba163564000012075942595011694120759425951830781207594259531107812075942595314357
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00469013119013164194304256002824277120x7f8cad17c4000x7f8ba163568000012075942595364370120759425955417971207594259579779512075942595842067
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00489013119013164194304256002824284160x7f8cad17c3000x7f8ba16356c000012075942595869318120759425960589141207594259631299312075942596358818
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00509013119013164194304256002424291200x7f8cad17ca000x7f8ba163570000012075942596387411120759425965542721207594259668771112075942596690865
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00529013119013164194304256002424300800x7f8cad17c9000x7f8ba163574000012075942596740076120759425969144301207594259704595012075942597049521
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00549013119013164194304256002424307840x7f8cad17c8000x7f8ba163578000012075942597110254120759425972800291207594259741554812075942597419288
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00569013119013164194304256002824320000x7f8cad17c7000x7f8ba16357c000012075942597467829120759425976470671207594259790306612075942597947660
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00589013119013164194304256002824329600x7f8cad17c6000x7f8ba163580000012075942597972797120759425981589051207594259841266312075942598458229
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00609013119013164194304256002424339200x7f8cad17c5000x7f8ba163584000012075942598484628120759425986614621207594259879362212075942598797039
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00629013119013164194304256002424348800x7f8cad17c4000x7f8ba163588000012075942598845699120759425990286601207594259916354012075942599167267
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00649013119013164194304256002424358400x7f8cad17c3000x7f8ba16358c000012075942599228821120759425993974591207594259952849812075942599531815
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00669013119013164194304256002824373120x7f8cad17ca000x7f8ba163590000012075942599583170120759425997571371207594260001377612075942600058614
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00689013119013164194304256002824382720x7f8cad17c9000x7f8ba163594000012075942600085854120759426002630551207594260051201412075942600555387
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00709013119013164194304256002424392320x7f8cad17c8000x7f8ba163598000012075942600583229120759426007518531207594260088641212075942600889888
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00729013119013164194304256002424401920x7f8cad17c7000x7f8ba16359c000012075942600937036120759426011281711207594260126609012075942601269664
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00749013119013164194304256002424411520x7f8cad17c6000x7f8ba1635a0000012075942601330177120759426014976091207594260162992912075942601633280
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00769013119013164194304256002824426240x7f8cad17c5000x7f8ba1635a4000012075942601675198120759426018630471207594260212432612075942602169687
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00789013119013164194304256002824435840x7f8cad17c4000x7f8ba1635a8000012075942602195936120759426023724851207594260262464412075942602668374
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00809013119013164194304256002424445440x7f8cad17c3000x7f8ba1635ac000012075942602694512120759426028742431207594260300576212075942603009227
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00829013119013164194304256002424457600x7f8cad17ca000x7f8ba1635b0000012075942603060793120759426032307211207594260336224112075942603365720
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00849013119013164194304256002424467200x7f8cad17c9000x7f8ba1635b4000012075942603425681120759426035910391207594260372447912075942603727963
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00869013119013164194304256002824484480x7f8cad17c8000x7f8ba1635b8000012075942603775391120759426039497581207594260421263712075942604258439
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00889013119013164194304256002824494080x7f8cad17c7000x7f8ba1635bc000012075942604284407120759426044606351207594260471647412075942604761293
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00909013119013164194304256002424503680x7f8cad17c6000x7f8ba1635c0000012075942604785869120759426049615931207594260509215312075942605095965
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00929013119013164194304256002424515840x7f8cad17c5000x7f8ba1635c4000012075942605145908120759426053252711207594260545759112075942605461094
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00949013119013164194304256002424525440x7f8cad17c4000x7f8ba1635c8000012075942605521306120759426056863901207594260581662912075942605820041
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00969013119013164194304256002824542720x7f8cad17c3000x7f8ba1635cc000012075942605869733120759426060534281207594260632286712075942606368140
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00989013119013164194304256002824554880x7f8cad17ca000x7f8ba1635d0000012075942606396122120759426065668661207594260682622512075942606869091
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001009013119013164194304256002424567040x7f8cad17c9000x7f8ba1635d4000012075942606894167120759426070756631207594260720302312075942607206538
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001029013119013164194304256002424581760x7f8cad17c8000x7f8ba1635d8000012075942607255388120759426074307021207594260757230112075942607575604
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001049013119013164194304256002424593920x7f8cad17c7000x7f8ba1635dc000012075942607636477120759426078009401207594260793373912075942607937045
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001069013119013164194304256002824613760x7f8cad17c6000x7f8ba1635e0000012075942607976970120759426081711781207594260843661712075942608481527
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001089013119013164194304256002824625920x7f8cad17c5000x7f8ba1635e4000012075942608507375120759426086878161207594260893949512075942608983480
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001109013119013164194304256002424638080x7f8cad17c4000x7f8ba1635e8000012075942609016051120759426091865341207594260931725312075942609320607
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001129013119013164194304256002424652800x7f8cad17c3000x7f8ba1635ec000012075942609372904120759426095458921207594260968733112075942609690754
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001149013119013164194304256002424664960x7f8cad17ca000x7f8ba1635f0000012075942609749434120759426099156501207594261004413012075942610047808
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001169013119013164194304256002824684800x7f8cad17c9000x7f8ba1635f4000012075942610098222120759426102726091207594261053484712075942610579206
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001189013119013164194304256002824696960x7f8cad17c8000x7f8ba1635f8000012075942610604553120759426107777261207594261102940512075942611073855
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001209013119013164194304256002424709120x7f8cad17c7000x7f8ba1635fc000012075942611101055120759426112710041207594261140348312075942611406844
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001229013119013164194304256002424723840x7f8cad17c6000x7f8ba163600000012075942611457077120759426116284421207594261176764212075942611771181
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001249013119013164194304256002424736000x7f8cad17c5000x7f8ba163604000012075942611835530120759426120038011207594261213660012075942612140317
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001269013119013164194304256002824758400x7f8cad17c4000x7f8ba163608000012075942612188106120759426123809191207594261264987812075942612694417
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001289013119013164194304256002824770560x7f8cad17c3000x7f8ba16360c000012075942612724062120759426128861971207594261313995512075942613186120
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001309013119013164194304256002424782720x7f8cad17ca000x7f8ba163610000012075942613220675120759426133913141207594261351979412075942613523548
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001329013119013164194304256002424800000x7f8cad17c9000x7f8ba163614000012075942613571396120759426137540331207594261389755212075942613900999
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001349013119013164194304256002424812160x7f8cad17c8000x7f8ba163618000012075942613962273120759426141341911207594261426379012075942614267721
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001369013119013164194304256002824834560x7f8cad17c7000x7f8ba16361c000012075942614315850120759426144905091207594261475722812075942614801933
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001389013119013164194304256002824849280x7f8cad17c6000x7f8ba163620000012075942614828934120759426149975471207594261524698612075942615293387
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001409013119013164194304256002424864000x7f8cad17c5000x7f8ba163624000012075942615317942120759426154953051207594261563050412075942615633890
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001429013119013164194304256002424881280x7f8cad17c4000x7f8ba163628000012075942615684423120759426158567431207594261600634212075942616010249
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001449013119013164194304256002424896000x7f8cad17c3000x7f8ba16362c000012075942616096099120759426162650611207594261639962012075942616403079
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001469013119013164194304256002824920960x7f8cad17ca000x7f8ba163630000012075942616445438120759426166264991207594261689513812075942616939095
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001489013119013164194304256002824935680x7f8cad17c9000x7f8ba163634000012075942616967929120759426171415371207594261739321612075942617439355
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001509013119013164194304256002424950400x7f8cad17c8000x7f8ba163638000012075942617470483120759426176455351207594261777817412075942617781641
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001529013119013164194304256002424967680x7f8cad17c7000x7f8ba16363c000012075942617829159120759426180119331207594261817017212075942618173680
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001549013119013164194304256002424982400x7f8cad17c6000x7f8ba163640000012075942618237007120759426184048911207594261853385112075942618537155
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015690131190131641943042560028241007360x7f8cad17c5000x7f8ba163644000012075942618588220120759426187560901207594261902136812075942619066609
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015890131190131641943042560028241022080x7f8cad17c4000x7f8ba163648000012075942619094461120759426192632871207594261951768612075942619561409
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016090131190131641943042560024241036800x7f8cad17c3000x7f8ba16364c000012075942619586505120759426197583251207594261989176412075942619895309
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016290131190131641943042560024241056640x7f8cad17ca000x7f8ba163650000012075942619941675120759426201368831207594262030296212075942620306584
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016490131190131641943042560024241071360x7f8cad17c9000x7f8ba163654000012075942620368639120759426205373611207594262067384112075942620677313
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016690131190131641943042560028241098880x7f8cad17c8000x7f8ba163658000012075942620725061120759426208978401207594262116279912075942621208850
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016890131190131641943042560028241113600x7f8cad17c7000x7f8ba16365c000012075942621238055120759426214040771207594262169607612075942621715061
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017090131190131641943042560024241128320x7f8cad17c6000x7f8ba163660000012075942621770905120759426219371951207594262207303412075942622077004
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017290131190131641943042560024241148160x7f8cad17c5000x7f8ba163664000012075942622127538120759426223123931207594262248647212075942622489821
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017490131190131641943042560024241162880x7f8cad17c4000x7f8ba163668000012075942622553249120759426227202311207594262285527112075942622858646
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017690131190131641943042560028241190400x7f8cad17c3000x7f8ba16366c000012075942622906395120759426230965501207594262335670812075942623402237
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017890131190131641943042560028241207680x7f8cad17ca000x7f8ba163670000012075942623428826120759426235971871207594262384966612075942623893690
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018090131190131641943042560024241224960x7f8cad17c9000x7f8ba163674000012075942623918797120759426240981451207594262423190412075942624235595
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018290131190131641943042560024241247360x7f8cad17c8000x7f8ba163678000012075942624285268120759426244583031207594262464086212075942624644375
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018490131190131641943042560024241264640x7f8cad17c7000x7f8ba16367c000012075942624704677120759426248696611207594262500566112075942625009504
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018690131190131641943042560020241279360x7f8cad17c6000x7f8ba163680000012075942625056140120759426252351001207594262550245912075942625540070
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018890131190131641943042560028241296640x7f8cad17c5000x7f8ba163684000012075942625572360120759426257333371207594262598149612075942626017106
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019090131190131641943042560024241313920x7f8cad17c4000x7f8ba163688000012075942626050198120759426262181351207594262635189512075942626355515
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019290131190131641943042560024241336320x7f8cad17c3000x7f8ba16368c000012075942626400799120759426265778141207594262676981312075942626787839
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019490131190131641943042560024241353600x7f8cad17ca000x7f8ba163690000012075942626851036120759426270218121207594262716085112075942627164449
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019690131190131641943042560020241368320x7f8cad17c9000x7f8ba163694000012075942627209392120759426273906101207594262767348912075942627696187
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019890131190131641943042560028241385600x7f8cad17c8000x7f8ba163698000012075942627734047120759426278954071207594262815028612075942628186198
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020090131190131641943042560024241402880x7f8cad17c7000x7f8ba16369c000012075942628218668120759426283883651207594262851940512075942628523174
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020290131190131641943042560024241427840x7f8cad17c6000x7f8ba1636a0000012075942628571944120759426287480441207594262895780312075942628979913
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020490131190131641943042560024241447680x7f8cad17c5000x7f8ba1636a4000012075942629043992120759426292107611207594262935300112075942629356793
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020690131190131641943042560020241457280x7f8cad17c4000x7f8ba1636a8000012075942629403530120759426295843601207594262989139812075942629914509
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020890131190131641943042560028241477120x7f8cad17c3000x7f8ba1636ac000012075942629959453120759426301341171207594263039395612075942630418186
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021090131190131641943042560024241496960x7f8cad17ca000x7f8ba1636b0000012075942630466756120759426306333151207594263076867412075942630772414
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021290131190131641943042560024241521920x7f8cad17c9000x7f8ba1636b4000012075942630818900120759426310051531207594263123363212075942631258728
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021490131190131641943042560024241541760x7f8cad17c8000x7f8ba1636b8000012075942631314101120759426314816311207594263161971012075942631623375
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021690131190131641943042560020241556480x7f8cad17c7000x7f8ba1636bc000012075942631671465120759426318517091207594263218146812075942632218351
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021890131190131641943042560028241576320x7f8cad17c6000x7f8ba1636c0000012075942632252875120759426324217871207594263267794512075942632699756
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022090131190131641943042560024241596160x7f8cad17c5000x7f8ba1636c4000012075942632744429120759426329086641207594263305042412075942633054365
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022290131190131641943042560024241623680x7f8cad17c4000x7f8ba1636c8000012075942633100911120759426332813031207594263352594212075942633547882
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022490131190131641943042560024241646080x7f8cad17c3000x7f8ba1636cc000012075942633602213120759426337689801207594263390930012075942633912930
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022690131190131641943042560020241663360x7f8cad17ca000x7f8ba1636d0000012075942633960158120759426341537921207594263453027112075942634569991
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022890131190131641943042560028241685760x7f8cad17c9000x7f8ba1636d4000012075942634597913120759426347638691207594263502882712075942635051647
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023090131190131641943042560024241708160x7f8cad17c8000x7f8ba1636d8000012075942635102681120759426352686661207594263540786612075942635411505
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023290131190131641943042560024241740800x7f8cad17c7000x7f8ba1636dc000012075942635460416120759426356344251207594263594498312075942635966767
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023490131190131641943042560024241765760x7f8cad17c6000x7f8ba1636e0000012075942636032640120759426362041821207594263634194212075942636345621
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023690131190131641943042560020241777920x7f8cad17c5000x7f8ba1636e4000012075942636391436120759426365771411207594263702449912075942637047305
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023890131190131641943042560028241802880x7f8cad17c4000x7f8ba1636e8000012075942637096286120759426372638581207594263752913712075942637550561
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024090131190131641943042560024241827840x7f8cad17c3000x7f8ba1636ec000012075942637598470120759426377622551207594263790049512075942637904348
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024290131190131641943042560024241863040x7f8cad17ca000x7f8ba1636f0000012075942637950484120759426381428941207594263845713212075942638493824
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024490131190131641943042560024241893120x7f8cad17c9000x7f8ba1636f4000012075942638537826120759426387038511207594263885633112075942638859944
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024690131190131641943042560020241907840x7f8cad17c8000x7f8ba1636f8000012075942638906952120759426390918501207594263960976712075942639644893
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024890131190131641943042560028241937920x7f8cad17c7000x7f8ba1636fc000012075942639680359120759426398468861207594264014384512075942640166282
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025090131190131641943042560024241968000x7f8cad17c6000x7f8ba163700000012075942640215043120759426403840041207594264053968312075942640543172
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025290131190131641943042560024242010880x7f8cad17c5000x7f8ba163704000012075942640591162120759426407657621207594264115312112075942641175748
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025490131190131641943042560024242046080x7f8cad17c4000x7f8ba163708000012075942641238164120759426414070391207594264158335912075942641586922
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025690131190131641943042560020242060800x7f8cad17c3000x7f8ba16370c000012075942641634050120759426418183981207594264244095512075942642476886
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025890131190131641943042560028242096000x7f8cad17ca000x7f8ba163710000012075942642510799120759426426782341207594264300767212075942643029964
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026090131190131641943042560024242131200x7f8cad17c9000x7f8ba163714000012075942643079486120759426432422311207594264342159112075942643425098
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026290131190131641943042560024242181760x7f8cad17c8000x7f8ba163718000012075942643473719120759426436561501207594264413358812075942644156778
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026490131190131641943042560024242222080x7f8cad17c7000x7f8ba16371c000012075942644218383120759426443881461207594264458942612075942644611022
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026690131190131641943042560020242239360x7f8cad17c6000x7f8ba163720000012075942644662959120759426448297441207594264553950112075942645580304
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026890131190131641943042560028242279680x7f8cad17c5000x7f8ba163724000012075942645604989120759426457819001207594264615469912075942646202690
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027090131190131641943042560024242320000x7f8cad17c4000x7f8ba163728000012075942646230452120759426463974181207594264660045712075942646645203
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027290131190131641943042560024242378240x7f8cad17c3000x7f8ba16372c000012075942646679246120759426468457361207594264737181312075942647417688
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027490131190131641943042560024242423680x7f8cad17ca000x7f8ba163730000012075942647455809120759426476281321207594264785165112075942647896388
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027690131190131641943042560020242435840x7f8cad17c9000x7f8ba163734000012075942647930111120759426481004501207594264890060712075942648945428
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027890131190131641943042560028242481280x7f8cad17c8000x7f8ba163738000012075942648973880120759426491423661207594264956444412075942649610193
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028090131190131641943042560024242526720x7f8cad17c7000x7f8ba16373c000012075942649637033120759426498150031207594265004188212075942650087961
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028290131190131641943042560024242592640x7f8cad17c6000x7f8ba163740000012075942650114811120759426502855611207594265088347812075942650927822
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028490131190131641943042560024242648320x7f8cad17c5000x7f8ba163744000012075942650965622120759426511409171207594265141051612075942651456434
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028690131190131641943042560020242663040x7f8cad17c4000x7f8ba163748000012075942651483795120759426516505151207594265263707012075942652682503
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028890131190131641943042560028242718720x7f8cad17c3000x7f8ba16374c000012075942652716917120759426528884291207594265340250712075942653447484
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029090131190131641943042560024242774400x7f8cad17ca000x7f8ba163750000012075942653480205120759426536487461207594265392154512075942653940391
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029290131190131641943042560012242799360x7f8cad17c9000x7f8ba163754000012075942653997196120759426541719431207594265491018012075942654956098
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029490131190131641943042560024242865280x7f8cad17c8000x7f8ba163758000012075942655006211120759426551732191207594265549097812075942655537188
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029690131190131641943042560020242880000x7f8cad17c7000x7f8ba16375c000012075942655563377120759426557375371207594265690841112075942656954803
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029890131190131641943042560032242945920x7f8cad17c6000x7f8ba163760000012075942656985460120759426571722501207594265778328812075942657828116
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030090131190131641943042560024243011840x7f8cad17c5000x7f8ba163764000012075942657860576120759426580362471207594265835688512075942658403515
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030290131190131641943042560012243049600x7f8cad17c4000x7f8ba163768000012075942658436627120759426586056841207594265948456012075942659530540
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030490131190131641943042560024243136000x7f8cad17c3000x7f8ba16376c000012075942659575934120759426597418391207594266015399712075942660200495
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030690131190131641943042560020243148160x7f8cad17ca000x7f8ba163770000012075942660230140120759426603941561207594266194358912075942661989640
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030890131190131641943042560020243175680x7f8cad17c9000x7f8ba163774000012075942662020527120759426621891881207594266298518512075942663031947
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031090131190131641943042560012243203200x7f8cad17c8000x7f8ba163778000012075942663064217120759426632319041207594266364726212075942663692524
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031290131190131641943042560012243240960x7f8cad17c7000x7f8ba16377c000012075942663725806120759426638919011207594266505109612075942665097435
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031490131190131641943042560012243288960x7f8cad17c6000x7f8ba163780000012075942665142760120759426653133351207594266609893112075942666144461
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031690131190131641943042560020243301120x7f8cad17c5000x7f8ba163784000012075942666178565120759426663454901207594266939731712075942669443643
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031890131190131641943042560020243328640x7f8cad17c4000x7f8ba163788000012075942669475031120759426696453161207594267118898912075942671235262
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032090131190131641943042560012243356160x7f8cad17c3000x7f8ba16378c000012075942671269526120759426714384281207594267222834412075942672274363
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032290131190131641943042560012243393920x7f8cad17ca000x7f8ba163790000012075942672308807120759426724768231207594267475905312075942674804786
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032490131190131641943042560012243441920x7f8cad17c9000x7f8ba163794000012075942674847535120759426750134521207594267654912512075942676595995
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032690131190131641943042560020243454080x7f8cad17c8000x7f8ba163798000012075942676629688120759426768001641207594268285469812075942682901904
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032890131190131641943042560020243481600x7f8cad17c7000x7f8ba16379c000012075942682936198120759426831156561207594268615676312075942686204051
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033090131190131641943042560012243509120x7f8cad17c6000x7f8ba1637a0000012075942686233836120759426863967621207594268793547512075942687982366
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332901311901316419430425600122400x7f8cad17c5000x7f8ba1637a4000012075942688024494120759426881906741207594269271753412075942692765686