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

43 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_VMEMSQ_INST_LEVEL_VMEMSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000936686936691335544322560083264640x00x7fa3b8c04180104857611096456141991125212076631726864889120766319744341061207663197475506512076631974864438
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00293668693669132768256002424124800x00x7fa3b8c3510040961077841378835612076631989518086120766319898060971207663198981249712076631989817693
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0049366869366914194304256002424129280x7fa4c491a9000x7fa3b8c3514052428810667896136549184012076631989877063120766319901009761207663199023889612076631990242964
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0069366869366914194304256003624136320x7fa4c491a8000x7fa3b8c3518052428813037531166875972012076631990314367120766319904883351207663199074241412076631990810750
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0089366869366914194304256002824140800x7fa4c491a7000x7fa3b8c351c052428813959441178679866812076631990847188120766319910300931207663199128673212076631991355774
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00109366869366914194304256002424145280x7fa4c491a6000x7fa3b8c3520052428810689784136819334812076631991381402120766319915688121207663199170721112076631991710684
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00129366869366914194304256002424149760x7fa4c491a5000x7fa3b8c3524052428810655940136397445612076631991762390120766319919251301207663199206417012076631992067828
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00149366869366914194304256002424154240x7fa4c491a4000x7fa3b8c3528052428811186260143174501212076631992148108120766319923225691207663199245936912076631992462773
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00169366869366914194304256002824161280x7fa4c491a3000x7fa3b8c352c052428813594400174007803612076631992511934120766319926912081207663199294480712076631992987780
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00189366869366914194304256002824168320x7fa4c491aa000x7fa3b8c3530052428814091881180375942812076631993018276120766319932033661207663199349792512076631993540698
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00209366869366914194304256002424175360x7fa4c491a9000x7fa3b8c3534052428812434664159161218412076631993566897120766319937633651207663199389472412076631993898233
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00229366869366914194304256002424182400x7fa4c491a8000x7fa3b8c3538052428813287858170083373612076631993952885120766319941236841207663199425200312076631994255778
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00249366869366914194304256002424189440x7fa4c491a7000x7fa3b8c353c052428812675209162233543612076631994322272120766319944867221207663199461776212076631994621148
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00269366869366914194304256002824199040x7fa4c491a6000x7fa3b8c3540052428813780254176388026812076631994671482120766319948368011207663199509184112076631995161984
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00289366869366914194304256002824206080x7fa4c491a5000x7fa3b8c3544052428814284271182834830412076631995189024120766319953740801207663199562239912076631995689605
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00309366869366914194304256002424213120x7fa4c491a4000x7fa3b8c3548052428812727172162902721612076631995716886120766319958975981207663199602687812076631996030650
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00329366869366914194304256002424220160x7fa4c491a3000x7fa3b8c354c052428811350987145299602012076631996079160120766319962497571207663199638527712076631996388806
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00349366869366914194304256002424227200x7fa4c491aa000x7fa3b8c3550052428812579972161025206812076631996452134120766319966164761207663199674735512076631996750779
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00369366869366914194304256002824236800x7fa4c491a9000x7fa3b8c3554052428812812013163986148412076631996800953120766319969646351207663199722591412076631997294401
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00389366869366914194304256002824243840x7fa4c491a8000x7fa3b8c3558052428813955090178618782412076631997317964120766319975075131207663199776111212076631997828504
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00409366869366914194304256002424250880x7fa4c491a7000x7fa3b8c355c052428812648248161895270412076631997855043120766319980380711207663199816847112076631998172133
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00429366869366914194304256002424257920x7fa4c491a6000x7fa3b8c3560052428811189762143228356412076631998221645120766319983961501207663199853215012076631998535780
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00449366869366914194304256002424264960x7fa4c491a5000x7fa3b8c3564052428813050016167029538412076631998597074120766319987585491207663199888782912076631998891311
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00469366869366914194304256002824277120x7fa4c491a4000x7fa3b8c3568052428813693562175275010412076631998942657120766319991142281207663199937342712076631999443258
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00489366869366914194304256002824284160x7fa4c491a3000x7fa3b8c356c052428813879294177654066412076631999467823120766319996484661207663199990526612076631999972562
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00509366869366914194304256002424291200x7fa4c491aa000x7fa3b8c3570052428812094408154798555612076631999999783120766320001806251207663200031342412076632000317183
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00529366869366914194304256002424300800x7fa4c491a9000x7fa3b8c3574052428812382294158492416412076632000369150120766320005279841207663200066078312076632000664299
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00549366869366914194304256002424307840x7fa4c491a8000x7fa3b8c3578052428812566523160850192812076632000726465120766320008895821207663200102046212076632001024289
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00569366869366914194304256002824320000x7fa4c491a7000x7fa3b8c357c052428813388619171366294012076632001073971120766320012535811207663200151518112076632001582848
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00589366869366914194304256002824329600x7fa4c491a6000x7fa3b8c3580052428813637840174563268012076632001609788120766320017889401207663200204141912076632002112032
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00609366869366914194304256002424339200x7fa4c491a5000x7fa3b8c3584052428812761042163335539612076632002136287120766320023182181207663200244941812076632002452956
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00629366869366914194304256002424348800x7fa4c491a4000x7fa3b8c3588052428811217114143587264012076632002504522120766320026678171207663200280445712076632002807966
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00649366869366914194304256002424358400x7fa4c491a3000x7fa3b8c358c052428812495035159938740412076632002871154120766320030398161207663200317117512076632003175119
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00669366869366914194304256002824373120x7fa4c491aa000x7fa3b8c3590052428813371610171152746812076632003225263120766320033969351207663200365453412076632003722938
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00689366869366914194304256002824382720x7fa4c491a9000x7fa3b8c3594052428813837964177123450812076632003750319120766320039282931207663200418429212076632004253135
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00709366869366914194304256002424392320x7fa4c491a8000x7fa3b8c3598052428811566995148055952012076632004281047120766320044598111207663200459565112076632004599128
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00729366869366914194304256002424401920x7fa4c491a7000x7fa3b8c359c052428812757724163302304812076632004649241120766320048294101207663200496125012076632004964899
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00749366869366914194304256002424411520x7fa4c491a6000x7fa3b8c35a0052428812429876159098096812076632005032524120766320051972491207663200532732912076632005331040
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00769366869366914194304256002824426240x7fa4c491a5000x7fa3b8c35a4052428813457016172247428812076632005381123120766320055455681207663200580188712076632005870243
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00789366869366914194304256002824435840x7fa4c491a4000x7fa3b8c35a8052428813657110174806205212076632005893145120766320060764461207663200633676612076632006406029
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00809366869366914194304256002424445440x7fa4c491a3000x7fa3b8c35ac052428812748746163185692412076632006432769120766320066082851207663200673932412076632006742946
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00829366869366914194304256002424457600x7fa4c491aa000x7fa3b8c35b0052428810426734133471361612076632006792678120766320069564441207663200709692312076632007100561
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00849366869366914194304256002424467200x7fa4c491a9000x7fa3b8c35b4052428812588625161126021212076632007163057120766320073247621207663200745516212076632007458918
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00869366869366914194304256002824484480x7fa4c491a8000x7fa3b8c35b8052428813875290177603130812076632007510233120766320076734011207663200793820112076632008013810
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00889366869366914194304256002824494080x7fa4c491a7000x7fa3b8c35bc052428814085119180290382012076632008038195120766320082196401207663200847499912076632008545379
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00909366869366914194304256002424503680x7fa4c491a6000x7fa3b8c35c0052428813172884168613841612076632008567961120766320087505181207663200887835812076632008881915
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00929366869366914194304256002424515840x7fa4c491a5000x7fa3b8c35c4052428810440186133624280012076632008932238120766320090991571207663200923867712076632009242375
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00949366869366914194304256002424525440x7fa4c491a4000x7fa3b8c35c8052428812648685161901609212076632009305503120766320094666761207663200959707512076632009600642
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00969366869366914194304256002824542720x7fa4c491a3000x7fa3b8c35cc052428813896022177869730412076632009650184120766320098121151207663201008347412076632010152879
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00989366869366914194304256002824554880x7fa4c491aa000x7fa3b8c35d0052428813695447175302417612076632010178286120766320103610731207663201065707212076632010724733
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001009366869366914194304256002424567040x7fa4c491a9000x7fa3b8c35d4052428811033413141227204812076632010749959120766320109260311207663201106379112076632011067530
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001029366869366914194304256002424581760x7fa4c491a8000x7fa3b8c35d805242889420400120579071212076632011118144120766320112820301207663201142475012076632011428281
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001049366869366914194304256002424593920x7fa4c491a7000x7fa3b8c35dc052428812316996157660692812076632011489926120766320116514691207663201178474912076632011788612
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001069366869366914194304256002824613760x7fa4c491a6000x7fa3b8c35e0052428813748793175980355212076632011838214120766320120007481207663201227162712076632012314850
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001089366869366914194304256002824625920x7fa4c491a5000x7fa3b8c35e4052428813590756173968256012076632012338805120766320125239461207663201278186512076632012847862
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001109366869366914194304256002424638080x7fa4c491a4000x7fa3b8c35e8052428811638260148976479612076632012876605120766320130573851207663201319162412076632013195368
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001129366869366914194304256002424652800x7fa4c491a3000x7fa3b8c35ec05242888879909113663055212076632013244410120766320134146641207663201355386312076632013557342
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001149366869366914194304256002424664960x7fa4c491aa000x7fa3b8c35f0052428812450878159364243612076632013619327120766320137825021207663201391402212076632013917592
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001169366869366914194304256002824684800x7fa4c491a9000x7fa3b8c35f4052428813561968173590856412076632013966843120766320141383411207663201439866012076632014467595
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001189366869366914194304256002824696960x7fa4c491a8000x7fa3b8c35f8052428813479846172538739212076632014493673120766320146711401207663201492825912076632014995086
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001209366869366914194304256002424709120x7fa4c491a7000x7fa3b8c35fc052428811674039149419770412076632015027055120766320152034581207663201533897812076632015342612
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001229366869366914194304256002424723840x7fa4c491a6000x7fa3b8c36000524288707845790609367612076632015391303120766320155562571207663201569561612076632015699256
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001249366869366914194304256002424736000x7fa4c491a5000x7fa3b8c3604052428812426427159055635612076632015761031120766320159224961207663201605433512076632016058193
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001269366869366914194304256002824758400x7fa4c491a4000x7fa3b8c3608052428812975973166096842812076632016108226120766320162856951207663201655449412076632016603939
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001289366869366914194304256002824770560x7fa4c491a3000x7fa3b8c360c052428813050721167049213212076632016628494120766320168056931207663201706233212076632017113046
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001309366869366914194304256002424782720x7fa4c491aa000x7fa3b8c3610052428812464778159538024012076632017137361120766320173181711207663201745017112076632017453789
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001329366869366914194304256002424800000x7fa4c491a9000x7fa3b8c36140524288730288893467822412076632017502510120766320176652101207663201780985012076632017813499
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001349366869366914194304256002424812160x7fa4c491a8000x7fa3b8c3618052428811572968148132707612076632017875514120766320180410491207663201817560912076632018179459
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001369366869366914194304256002824834560x7fa4c491a7000x7fa3b8c361c052428812964342165950560412076632018229482120766320184002481207663201866280712076632018712851
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001389366869366914194304256002824849280x7fa4c491a6000x7fa3b8c3620052428813652339174748394412076632018736005120766320189149661207663201917160612076632019222810
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001409366869366914194304256002424864000x7fa4c491a5000x7fa3b8c3624052428811193312143268749212076632019250552120766320194274451207663201956360412076632019567371
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001429366869366914194304256002424881280x7fa4c491a4000x7fa3b8c36280524288569513772893147212076632019618155120766320197778441207663201992888312076632019932670
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001449366869366914194304256002424896000x7fa4c491a3000x7fa3b8c362c052428810959406140276804012076632020023449120766320201847221207663202032248212076632020326072
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001469366869366914194304256002824920960x7fa4c491aa000x7fa3b8c3630052428812813072164004440412076632020376556120766320205463211207663202081528012076632020865185
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001489366869366914194304256002824935680x7fa4c491a9000x7fa3b8c3634052428813523973173096754812076632020890813120766320210719201207663202132711912076632021377628
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001509366869366914194304256002424950400x7fa4c491a8000x7fa3b8c3638052428811713883149930146012076632021405300120766320215816781207663202171655812076632021720466
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001529366869366914194304256002424967680x7fa4c491a7000x7fa3b8c363c0524288494136763254018412076632021771761120766320219341571207663202209383612076632022097567
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001549366869366914194304256002424982400x7fa4c491a6000x7fa3b8c3640052428810799652138241261212076632022161166120766320223319161207663202246919512076632022472986
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015693668693669141943042560028241007360x7fa4c491a5000x7fa3b8c3644052428811637447148958685212076632022522528120766320226869551207663202295559412076632022979057
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015893668693669141943042560028241022080x7fa4c491a4000x7fa3b8c3648052428812905568165191417212076632023026165120766320231867931207663202344359212076632023494265
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016093668693669141943042560024241036800x7fa4c491a3000x7fa3b8c364c052428811704822149818366812076632023519052120766320236933521207663202382791112076632023831653
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016293668693669141943042560024241056640x7fa4c491aa000x7fa3b8c36500524288376265248157459212076632023882107120766320240571901207663202422247012076632024226297
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016493668693669141943042560024241071360x7fa4c491a9000x7fa3b8c3654052428812605205161345979212076632024292961120766320244730291207663202460406912076632024607827
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016693668693669141943042560028241098880x7fa4c491a8000x7fa3b8c3658052428810444034133677150012076632024656838120766320248263081207663202509078712076632025141429
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016893668693669141943042560028241113600x7fa4c491a7000x7fa3b8c365c052428813406164171599053612076632025164843120766320253472661207663202560598612076632025653522
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017093668693669141943042560024241128320x7fa4c491a6000x7fa3b8c3660052428811540052147713458812076632025682526120766320258549451207663202598934412076632025993064
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017293668693669141943042560024241148160x7fa4c491a5000x7fa3b8c36640524288362043046342441212076632026044579120766320262091841207663202638326312076632026387066
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017493668693669141943042560024241162880x7fa4c491a4000x7fa3b8c3668052428811668692149357198812076632026449573120766320266099821207663202674598212076632026749681
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017693668693669141943042560028241190400x7fa4c491a3000x7fa3b8c366c05242888056353103123097212076632026798572120766320269655011207663202723094112076632027282121
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017893668693669141943042560028241207680x7fa4c491aa000x7fa3b8c3670052428813749320175995657612076632027305415120766320274922201207663202775269912076632027799995
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018093668693669141943042560024241224960x7fa4c491a9000x7fa3b8c3674052428810784351138042900012076632027826113120766320280024581207663202814181812076632028145487
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018293668693669141943042560024241247360x7fa4c491a8000x7fa3b8c36780524288331118642379184412076632028195270120766320283642171207663202854709612076632028550881
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018493668693669141943042560024241264640x7fa4c491a7000x7fa3b8c367c052428811121544142367103212076632028615211120766320287747761207663202891205512076632028915730
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018693668693669141943042560020241279360x7fa4c491a6000x7fa3b8c36800524288428639754863038012076632028964851120766320291386151207663202940453412076632029428644
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018893668693669141943042560028241296640x7fa4c491a5000x7fa3b8c3684052428813462371172313835212076632029470582120766320296299731207663202989365212076632029940606
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019093668693669141943042560024241313920x7fa4c491a4000x7fa3b8c3688052428812055338154317164012076632029965813120766320301486911207663203028197112076632030285869
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019293668693669141943042560024241336320x7fa4c491a3000x7fa3b8c368c0524288358074545834770812076632030335832120766320305006901207663203069301012076632030740785
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019493668693669141943042560024241353600x7fa4c491aa000x7fa3b8c3690052428810762855137763207612076632030778806120766320309360491207663203107492912076632031078844
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019693668693669141943042560020241368320x7fa4c491a9000x7fa3b8c36940524288296566837954478412076632031129438120766320313019681207663203158756712076632031637383
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019893668693669141943042560028241385600x7fa4c491a8000x7fa3b8c3698052428813724870175682996412076632031664984120766320318410061207663203210100512076632032149555
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020093668693669141943042560024241402880x7fa4c491a7000x7fa3b8c369c052428812556783160722617212076632032177487120766320323536451207663203248692412076632032490890
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020293668693669141943042560024241427840x7fa4c491a6000x7fa3b8c36a00524288350953744916853212076632032541094120766320327030831207663203291316312076632032960313
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020493668693669141943042560024241447680x7fa4c491a5000x7fa3b8c36a405242889577535122594785612076632032998785120766320331670821207663203331044212076632033314402
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020693668693669141943042560020241457280x7fa4c491a4000x7fa3b8c36a80524288254934132637360812076632033365447120766320335280411207663203383556012076632033882228
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020893668693669141943042560028241477120x7fa4c491a3000x7fa3b8c36ac052428813938329178404876412076632033904650120766320340894791207663203435203812076632034402696
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021093668693669141943042560024241496960x7fa4c491aa000x7fa3b8c36b005242889647066123492646412076632034426060120766320346048381207663203474435712076632034748249
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021293668693669141943042560024241521920x7fa4c491a9000x7fa3b8c36b40524288349759744775693612076632034796669120766320349590761207663203518723612076632035237569
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021493668693669141943042560024241541760x7fa4c491a8000x7fa3b8c36b8052428810935167139959234412076632035275720120766320354413151207663203557715512076632035581098
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021693668693669141943042560020241556480x7fa4c491a7000x7fa3b8c36bc0524288248782131841548012076632035630039120766320357963541207663203612691312076632036176236
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021893668693669141943042560028241576320x7fa4c491a6000x7fa3b8c36c0052428813487975172638834812076632036200771120766320363816321207663203663891112076632036686435
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022093668693669141943042560024241596160x7fa4c491a5000x7fa3b8c36c4052428810837100138711993212076632036712363120766320368873901207663203702851012076632037032228
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022293668693669141943042560024241623680x7fa4c491a4000x7fa3b8c36c80524288341803243739374012076632037082782120766320372475761207663203749381612076632037520967
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022493668693669141943042560024241646080x7fa4c491a3000x7fa3b8c36cc05242889739267124666440812076632037571831120766320377349341207663203787557412076632037878542
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022693668693669141943042560020241663360x7fa4c491aa000x7fa3b8c36d00524288239295430616650812076632037926591120766320381021331207663203847989312076632038529072
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022893668693669141943042560028241685760x7fa4c491a9000x7fa3b8c36d4052428811973629153252916812076632038558877120766320387334921207663203899989112076632039047356
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023093668693669141943042560024241708160x7fa4c491a8000x7fa3b8c36d805242889364067119851655212076632039084305120766320392486911207663203938853112076632039391546
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023293668693669141943042560024241740800x7fa4c491a7000x7fa3b8c36dc0524288343012243910289212076632039440808120766320396150901207663203989509012076632039917334
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023493668693669141943042560024241765760x7fa4c491a6000x7fa3b8c36e005242888700235111356630812076632039971595120766320401434091207663204028324912076632040286551
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023693668693669141943042560020241777920x7fa4c491a5000x7fa3b8c36e40524288236152930211288012076632040336604120766320404994081207663204094772712076632040994448
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023893668693669141943042560028241802880x7fa4c491a4000x7fa3b8c36e8052428810828654138600537212076632041026187120766320412067671207663204147540612076632041522701
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024093668693669141943042560024241827840x7fa4c491a3000x7fa3b8c36ec0524288748653395833407612076632041549200120766320417290061207663204186900612076632041871770
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024293668693669141943042560024241863040x7fa4c491aa000x7fa3b8c36f00524288344978644152641612076632041920781120766320420899651207663204240564412076632042455185
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024493668693669141943042560024241893120x7fa4c491a9000x7fa3b8c36f40524288415304953148965612076632042496352120766320426605241207663204281412412076632042817058
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024693668693669141943042560020241907840x7fa4c491a8000x7fa3b8c36f80524288238627930535902012076632042866139120766320430435631207663204356340212076632043613570
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024893668693669141943042560028241937920x7fa4c491a7000x7fa3b8c36fc05242887969875102013946812076632043638085120766320438184421207663204411812112076632044167029
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025093668693669141943042560024241968000x7fa4c491a6000x7fa3b8c37000524288340701543599550812076632044190914120766320443768401207663204453204012076632044535024
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025293668693669141943042560024242010880x7fa4c491a5000x7fa3b8c37040524288347391944476371612076632044584306120766320447523601207663204516387912076632045187578
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025493668693669141943042560024242046080x7fa4c491a4000x7fa3b8c37080524288327231541874037212076632045246337120766320454134781207663204559059812076632045594014
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025693668693669141943042560020242060800x7fa4c491a3000x7fa3b8c370c0524288229498329373269612076632045643756120766320458075571207663204641891612076632046469482
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025893668693669141943042560028242096000x7fa4c491aa000x7fa3b8c37100524288439633656264382012076632046492745120766320466800361207663204700787512076632047056684
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026093668693669141943042560024242131200x7fa4c491a9000x7fa3b8c37140524288335667242965072812076632047089546120766320472609941207663204744019412076632047443404
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026293668693669141943042560024242181760x7fa4c491a8000x7fa3b8c37180524288369808847335341612076632047493357120766320476557141207663204811123312076632048160708
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026493668693669141943042560024242222080x7fa4c491a7000x7fa3b8c371c0524288311536339866352412076632048197096120766320483605121207663204856035212076632048608731
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026693668693669141943042560020242239360x7fa4c491a6000x7fa3b8c37200524288235339930132621212076632048638747120766320488193911207663204952403012076632049574578
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026893668693669141943042560028242279680x7fa4c491a5000x7fa3b8c37240524288375929748124098412076632049597982120766320497809891207663205015490812076632050204870
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027093668693669141943042560024242320000x7fa4c491a4000x7fa3b8c37280524288333756242713043612076632050230498120766320504097881207663205061410712076632050661219
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027293668693669141943042560024242378240x7fa4c491a3000x7fa3b8c372c0524288448318357387630812076632050687679120766320508630671207663205138962612076632051440479
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027493668693669141943042560024242423680x7fa4c491aa000x7fa3b8c37300524288319147440844150012076632051481154120766320516453051207663205187026512076632051916845
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027693668693669141943042560020242435840x7fa4c491a9000x7fa3b8c37340524288231430329606436812076632051943294120766320521238641207663205292514312076632052974532
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027893668693669141943042560028242481280x7fa4c491a8000x7fa3b8c37380524288333063742635688012076632052998307120766320531832221207663205360546112076632053655018
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028093668693669141943042560024242526720x7fa4c491a7000x7fa3b8c373c0524288317809840676007612076632053678402120766320538581011207663205408402012076632054134019
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028293668693669141943042560024242592640x7fa4c491a6000x7fa3b8c37400524288468160159923133212076632054161791120766320543429001207663205494065912076632054989581
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028493668693669141943042560024242648320x7fa4c491a5000x7fa3b8c37440524288330077142265116812076632055030657120766320551987381207663205546817712076632055518154
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028693668693669141943042560020242663040x7fa4c491a4000x7fa3b8c37480524288231873429675694012076632055546176120766320557256171207663205671313512076632056783137
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028893668693669141943042560028242718720x7fa4c491a3000x7fa3b8c374c0524288353747345280278812076632056818092120766320569859341207663205750273312076632057571854
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029093668693669141943042560024242774400x7fa4c491aa000x7fa3b8c37500524288330618542315843612076632057603863120766320577804931207663205805377212076632058122468
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029293668693669141943042560012242799360x7fa4c491a9000x7fa3b8c37540524288221118228306568412076632058155329120766320583243321207663205906353012076632059131936
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029493668693669141943042560024242865280x7fa4c491a8000x7fa3b8c37580524288334352742794624412076632059175547120766320593387291207663205965552912076632059722444
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029693668693669141943042560020242880000x7fa4c491a7000x7fa3b8c375c0524288227297229099993212076632059747401120766320599289681207663206110224612076632061171640
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029893668693669141943042560032242945920x7fa4c491a6000x7fa3b8c37600524288345507144224071612076632061201365120766320613875251207663206199616412076632062064481
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030093668693669141943042560024243011840x7fa4c491a5000x7fa3b8c37640524288334416042803712012076632062093996120766320622764831207663206259664312076632062663014
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030293668693669141943042560012243049600x7fa4c491a4000x7fa3b8c37680524288221532528355695212076632062686568120766320628716821207663206375168012076632063820357
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030493668693669141943042560024243136000x7fa4c491a3000x7fa3b8c376c0524288333236442646086812076632063861203120766320640321601207663206444495912076632064513807
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030693668693669141943042560020243148160x7fa4c491aa000x7fa3b8c37700524288229650729395670812076632064536629120766320647190381207663206626959512076632066338411
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030893668693669141943042560020243175680x7fa4c491a9000x7fa3b8c37740524288226784229021500012076632066369378120766320665529551207663206734831312076632067416947
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031093668693669141943042560012243203200x7fa4c491a8000x7fa3b8c37780524288215609027589846012076632067446322120766320676286321207663206806703112076632068135273
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031293668693669141943042560012243240960x7fa4c491a7000x7fa3b8c377c0524288223288328581313212076632068165610120766320683463911207663206950558812076632069574180
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031493668693669141943042560012243288960x7fa4c491a6000x7fa3b8c37800524288222595928500746812076632069618492120766320697863881207663207057326612076632070643479
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031693668693669141943042560020243301120x7fa4c491a5000x7fa3b8c37840524288266262234067213612076632070676410120766320708518261207663207390605912076632073976108
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031893668693669141943042560020243328640x7fa4c491a4000x7fa3b8c37880524288231516529621548812076632074010582120766320741945391207663207573901612076632075809107
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032093668693669141943042560012243356160x7fa4c491a3000x7fa3b8c378c0524288218024927895192012076632075842059120766320760322951207663207682205312076632076890990
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032293668693669141943042560012243393920x7fa4c491aa000x7fa3b8c37900524288256631332851403612076632076915155120766320771206131207663207940316812076632079473193
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032493668693669141943042560012243441920x7fa4c491a9000x7fa3b8c37940524288234099129961343212076632079518137120766320796868471207663208122252412076632081291946
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032693668693669141943042560020243454080x7fa4c491a8000x7fa3b8c37980524288283764936308881612076632081322042120766320815031641207663208756091112076632087632931
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032893668693669141943042560020243481600x7fa4c491a7000x7fa3b8c379c0524288330850942341696412076632087658479120766320878389911207663209088538412076632090958577
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033093668693669141943042560012243509120x7fa4c491a6000x7fa3b8c37a00524288230319129480574812076632090985548120766320911772241207663209271658112076632092788411
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332936686936691419430425600122400x7fa4c491a5000x7fa3b8c37a40524288253511732443176812076632092814990120766320930047401207663209753353112076632097603959