Files
rocm-systems/tests/workloads/SQ/mi200/SQ_INST_LEVEL_SMEM.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

41 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_SMEMSQ_INST_LEVEL_SMEMSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000136822136822335544322560043241600x00x7ff914a042803670016291684232664782415892871944314158086760999441589302000210015893020095280
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00213682213682232768256001224138880x00x7ff914a23f80512997861118949615893025292904158930200021001589302542467515893025429601
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051368221368224194304256001224143360x7ff917ab03800x7ff914a23fc0655366273827026410415893025464240158930254246751589302579363615893025796253
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081368221368224194304256001624150400x7ff917ab02000x7ff914a24000655366571647352039215893025832352158930257936361589302620483715893026207373
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111368221368224194304256001624154880x7ff917ab00800x7ff914a24040655366548647325126415893026240573158930262048371589302662179815893026624494
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141368221368224194304256001224159360x7ff91540df000x7ff914a24080655366600387386820015893026656573158930266217981589302694211915893026944467
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171368221368224194304256001224163840x7ff91540dd800x7ff914a240c0655366164106900120815893026977876158930269421191589302725476015893027257330
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201368221368224194304256001224170880x7ff91540dc000x7ff914a241001310726714427523629615893027301949158930272547601589302757316115893027575713
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231368221368224194304256001624177920x7ff91540da800x7ff914a241401310726868587699453615893027607232158930275731611589302797220215893027974754
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261368221368224194304256001624184960x7ff91540d9000x7ff914a24180655366552407347682415893028006303158930279722021589302836452315893028366975
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291368221368224194304256001624192000x7ff91540d7800x7ff914a241c01310726866767697945615893028398065158930283645231589302868580415893028688368
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321368221368224194304256001624199040x7ff91540d6000x7ff914a242001310726862087692383215893028719737158930286858041589302899380515893028996071
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351368221368224194304256001224206080x7ff917ab04800x7ff914a242401310726934787773654415893029036770158930289938051589302930148615893029303924
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381368221368224194304256001624213120x7ff917ab03000x7ff914a242801310726905507733879215893029336104158930293014861589302969908715893029701575
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411368221368224194304256001624220160x7ff917ab01800x7ff914a242c0655366590787385350415893029732885158930296990871589303009668815893030104086
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441368221368224194304256001624227200x7ff917ab00000x7ff914a243001310726950887784668015893030132486158930300966881589303041412915893030416789
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471368221368224194304256001224234240x7ff91540de800x7ff914a243401310726841587652715215893030448949158930304141291589303072309015893030725743
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501368221368224194304256001224241280x7ff91540dd000x7ff914a243801310726837927651503215893030765362158930307230901589303101717015893031019076
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531368221368224194304256001624248320x7ff91540db800x7ff914a243c01310727080327948508015893031050945158930310171701589303138261115893031384498
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561368221368224194304256001624255360x7ff91540da000x7ff914a24400655366237666995441615893031416637158930313826111589303175861315893031760610
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591368221368224194304256001224262400x7ff91540d8800x7ff914a244401310726954847798168815893031791879158930317586131589303204021315893032042293
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621368221368224194304256001224269440x7ff91540d7000x7ff914a244801310726856987679270415893032073003158930320402131589303231989415893032321917
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651368221368224194304256001224276480x7ff917ab05800x7ff914a244c01310726589707386401615893032360786158930323198941589303260229515893032604111
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681368221368224194304256001624286080x7ff917ab04000x7ff914a245001310726843647662840015893032636780158930326022951589303297157615893032973583
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711368221368224194304256001624293120x7ff917ab02800x7ff914a24540655366527147296678415893033005122158930329715761589303333941715893033341325
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741368221368224194304256001224300160x7ff917ab01000x7ff914a245801310726564687342125615893033372664158930333394171589303361893815893033620818
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077136822136822419430425600824309760x7ff91540df800x7ff914a245c01310727170168033714415893033652408158930336189381589303390005915893033901872
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801368221368224194304256001224316800x7ff91540de000x7ff914a246001310726827467643933615893033941081158930339000591589303419349915893034195626
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831368221368224194304256001624326400x7ff91540dc800x7ff914a246401310726662047464333615893034227385158930341934991589303457062115893034572597
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861368221368224194304256001224336000x7ff91540db000x7ff914a24680655366912467746152815893034603787158930345706211589303495014215893034952049
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891368221368224194304256001224345600x7ff91540d9800x7ff914a246c01310726857327678980815893034984168158930349501421589303523078215893035232812
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092136822136822419430425600824355200x7ff91540d8000x7ff914a247001310726954267786515215893035264162158930352307821589303551174315893035513796
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951368221368224194304256001224362240x7ff91540d6800x7ff914a247401310726902227729516815893035553435158930355117431589303579254415893035794530
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981368221368224194304256001224371840x7ff917ab05000x7ff914a247801310726563707366959215893035826029158930357925441589303615798515893036159952
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011368221368224194304256001224381440x7ff917ab03800x7ff914a247c0655366588707373650415893036192431158930361579851589303652614615893036528114
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041368221368224194304256001224391040x7ff917ab02000x7ff914a248001310726912487751089615893036559793158930365261461589303680534715893036807347
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107136822136822419430425600824403200x7ff917ab00800x7ff914a248401310726863487680066415893036839477158930368053471589303708838815893037090191
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101368221368224194304256001224412800x7ff91540df000x7ff914a248801310727365468236708815893037129390158930370883881589303737126815893037373235
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131368221368224194304256001224422400x7ff91540dd800x7ff914a248c01310726948427783857615893037405044158930373712681589303774455015893037746506
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161368221368224194304256001224432000x7ff91540dc000x7ff914a24900655366153586887393615893037778266158930377445501589303811111115893038113088
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119136822136822419430425600824441600x7ff91540da800x7ff914a249401310726871087699931215893038145527158930381111111589303839575115893038397742
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221368221368224194304256001224453760x7ff91540d9000x7ff914a249801310726873947702637615893038429151158930383957511589303868791215893038689865
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251368221368224194304256001224463360x7ff91540d7800x7ff914a249c01310726915047736528015893038728804158930386879121589303897239315893038974449
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281368221368224194304256001224475520x7ff91540d6000x7ff914a24a001310726873427695348015893039006178158930389723931589303933783415893039339881
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311368221368224194304256001224485120x7ff917ab04800x7ff914a24a40655366482827260421615893039372330158930393378341589303970599515893039707803
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134136822136822419430425600824494720x7ff917ab03000x7ff914a24a801310726974787809634415893039739612158930397059951589303998871615893039990536
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371368221368224194304256001224506880x7ff917ab01800x7ff914a24ac01310726584567373264815893040022385158930399887161589304026839715893040270170
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401368221368224194304256001224516480x7ff917ab00000x7ff914a24b001310726472547250646415893040309839158930402683971589304055239715893040554404
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431368221368224194304256001224528640x7ff91540de800x7ff914a24b401310726915467750253615893040585793158930405523971589304092135915893040923375
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461368221368224194304256001224540800x7ff91540dd000x7ff914a24b80655366539687327658415893040954025158930409213591589304128728015893041289267
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149136822136822419430425600824552960x7ff91540db800x7ff914a24bc01310726861327685255215893041321446158930412872801589304157064015893041572651
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521368221368224194304256001224567680x7ff91540da000x7ff914a24c001310726926667749911215893041604630158930415706401589304185080115893041852735
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551368221368224194304256001224577280x7ff91540d8800x7ff914a24c401310726864707704199215893041892484158930418508011589304213048215893042132678
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581368221368224194304256001224589440x7ff91540d7000x7ff914a24c801310726569627342727215893042164828158930421304821589304249704315893042498950
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611368221368224194304256001224601600x7ff917ab05800x7ff914a24cc0655366582987374723215893042531089158930424970431589304286248415893042864272
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164136822136822419430425600824613760x7ff917ab04000x7ff914a24d001310726906327734608815893042896261158930428624841589304313976515893043141646
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671368221368224194304256001224628480x7ff917ab02800x7ff914a24d401310726838027668575215893043174345158930431397651589304343000615893043432109
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701368221368224194304256001224638080x7ff917ab01000x7ff914a24d801310727168188038381615893043471408158930434300061589304370984615893043711893
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731368221368224194304256001224650240x7ff91540df800x7ff914a24dc01310726734747543016015893043743142158930437098461589304407544715893044077425
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761368221368224194304256001224662400x7ff91540de000x7ff914a24e00655366547587337134415893044109314158930440754471589304443944815893044441307
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179136822136822419430425600824674560x7ff91540dc800x7ff914a24e401310726921627756744015893044472556158930444394481589304471912915893044721301
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821368221368224194304256001224689280x7ff91540db000x7ff914a24e801310726815387639441615893044752620158930447191291589304500953015893045011474
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851368221368224194304256001224701440x7ff91540d9800x7ff914a24ec01310726577607369812815893045050273158930450095301589304528905115893045290928
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881368221368224194304256001224716160x7ff91540d8000x7ff914a24f001310726861447674644015893045322207158930452890511589304565417215893045656080
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911368221368224194304256001224728320x7ff91540d6800x7ff914a24f40655366829367650455215893045687969158930456541721589304601961315893046021561
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194136822136822419430425600824740480x7ff917ab05000x7ff914a24f801310726820747635111215893046052091158930460196131589304631225415893046314405
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971368221368224194304256001224757760x7ff917ab03800x7ff914a24fc01310726492947273392815893046346174158930463122541589304661801515893046619888
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001368221368224194304256001224769920x7ff917ab02000x7ff914a250001310726834787656300015893046659007158930466180151589304689817515893046900102
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031368221368224194304256001224784640x7ff917ab00800x7ff914a250401310726887027701388015893046932211158930468981751589304726313615893047265144
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061368221368224194304256001224799360x7ff91540df000x7ff914a25080655366546267332612015893047297343158930472631361589304762841815893047630376
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209136822136822419430425600824814080x7ff91540dd800x7ff914a250c01310727273148158372815893047661995158930476284181589304790777815893047909589
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121368221368224194304256001224831360x7ff91540dc000x7ff914a251001310726921047754860815893047941429158930479077781589304820569915893048207683
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151368221368224194304256001224843520x7ff91540da800x7ff914a251401310726846767668723215893048259221158930482056991589304848666015893048488486
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181368221368224194304256001224858240x7ff91540d9000x7ff914a251801310726872507690788015893048520396158930484866601589304885146115893048853408
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211368221368224194304256001224872960x7ff91540d7800x7ff914a251c0655366485347266128815893048885217158930488514611589304922266215893049224500
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241368221368224194304256001224887680x7ff91540d6000x7ff914a252001310726848887677132015893049255929158930492226621589304950970315893049511663
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271368221368224194304256001224907520x7ff917ab04800x7ff914a252401310726940547775548015893049543073158930495097031589304981402415893049816027
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301368221368224194304256001224919680x7ff917ab03000x7ff914a252801310726846147668623215893049854716158930498140241589305009626515893050098190
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331368221368224194304256001224934400x7ff917ab01800x7ff914a252c01310726887427721931215893050130450158930500962651589305047098615893050472872
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361368221368224194304256001224949120x7ff917ab00000x7ff914a25300655366700967497774415893050505271158930504709861589305083882715893050840714
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391368221368224194304256001224963840x7ff91540de800x7ff914a253401310726907087734701615893050871843158930508388271589305111658715893051118538
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421368221368224194304256001224983680x7ff91540dd000x7ff914a253801310727206648079308815893051149087158930511165871589305142986815893051431731
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451368221368224194304256001224995840x7ff91540db800x7ff914a253c01310726864007686717615893051470480158930514298681589305171210915893051714045
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024813682213682241943042560012241013120x7ff91540da000x7ff914a254001310726461727227515215893051745704158930517121091589305208779015893052089776
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025113682213682241943042560012241027840x7ff91540d8800x7ff914a25440655366482867253744815893052121506158930520877901589305245259115893052454578
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025413682213682241943042560012241042560x7ff91540d7000x7ff914a254801310726619647406303215893052485917158930524525911589305273547215893052737252
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025713682213682241943042560012241062400x7ff917ab05800x7ff914a254c01310726579267362644815893052768531158930527354721589305305275315893053054655
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026013682213682241943042560012241077120x7ff917ab04000x7ff914a255001310726525067316008015893053094424158930530527531589305333339415893053335329
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026313682213682241943042560016241094400x7ff917ab02800x7ff914a255401310727144388010424015893053367748158930533333941589305369979515893053701720
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026613682213682241943042560016241111680x7ff917ab01000x7ff914a25580655366864047696454415893053733120158930536997951589305406731615893054069102
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691368221368224194304256008241128960x7ff91540df800x7ff914a255c01310727060187907889615893054101272158930540673161589305435259715893054354506
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027213682213682241943042560012241151360x7ff91540de000x7ff914a256001310727039967879374415893054386645158930543525971589305467531715893054677149
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027513682213682241943042560012241166080x7ff91540dc800x7ff914a256401310726896187723988015893054716198158930546753171589305495899815893054960822
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027813682213682241943042560016241183360x7ff91540db000x7ff914a256801310726976907821111215893054991612158930549589981589305533451915893055336344
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028113682213682241943042560016241200640x7ff91540d9800x7ff914a256c0655366492867257270415893055367843158930553345191589305570220015893055704226
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028413682213682241943042560012241217920x7ff91540d8000x7ff914a257001310726857567689192015893055735785158930557022001589305598556115893055987429
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028713682213682241943042560012241240320x7ff91540d6800x7ff914a257401310726844047663636015893056019019158930559855611589305631468215893056316642
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029013682213682241943042560012241255040x7ff917ab05000x7ff914a257801310726908747741114415893056356501158930563146821589305659548315893056597356
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029313682213682241943042560012241274880x7ff917ab03800x7ff914a257c01310726980887826518415893056628755158930565954831589305696108415893056962988
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029613682213682241943042560012241292160x7ff917ab02000x7ff914a25800655366510947291284015893056995347158930569610841589305733004515893057332109
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029913682213682241943042560012241309440x7ff917ab00800x7ff914a258401310726545667336851215893057363439158930573300451589305761436615893057616313
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030213682213682241943042560012241334400x7ff91540df000x7ff914a258801310726672067482355215893057648182158930576143661589305795452715893057956405
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030513682213682241943042560012241349120x7ff91540dd800x7ff914a258c0131072101634611403739215893057994775158930579545271589305824956815893058251879
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030813682213682241943042560012241368960x7ff91540dc000x7ff914a259001310726528847324508815893058283708158930582495681589305861756915893058619421
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031113682213682241943042560012241388800x7ff91540da800x7ff914a25940655366500927278923215893058651660158930586175691589305898541015893058987512
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031413682213682241943042560012241408640x7ff91540d9000x7ff914a259801310726894527717689615893059018162158930589854101589305927741115893059279316
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031713682213682241943042560012241436160x7ff91540d7800x7ff914a259c01310726911867743353615893059311275158930592774111589305963117215893059633008
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032013682213682241943042560012241453440x7ff91540d6000x7ff914a25a00131072102253811472163215893059675617158930596311721589305991741215893059919372
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032313682213682241943042560012241475840x7ff917ab04800x7ff914a25a401310726910247744872815893059950981158930599174121589306028269315893060284603
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032613682213682241943042560012241495680x7ff917ab03000x7ff914a25a80655366518707302246415893060317113158930602826931589306065053415893060652415
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032913682213682241943042560012241515520x7ff917ab01800x7ff914a25ac01310726829547649764015893060683825158930606505341589306094941515893060951329
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033213682213682241943042560012241543040x7ff917ab00000x7ff914a25b001310726615147400667215893060983238158930609494151589306132157615893061323540
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033513682213682241943042560012241562880x7ff91540de800x7ff914a25b4013107295628010710264815893061362889158930613215761589306161277715893061614654
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033813682213682241943042560012241587840x7ff91540dd000x7ff914a25b801310726937187769755215893061646993158930616127771589306197981815893061981786
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034113682213682241943042560012241610240x7ff91540db800x7ff914a25bc0655366524367315625615893062012805158930619798181589306235981915893062361907
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034413682213682241943042560012241632640x7ff91540da000x7ff914a25c001310726616207413479215893062393896158930623598191589306267198015893062674130
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034713682213682241943042560012241665280x7ff91540d8800x7ff914a25c401310726557307353729615893062706099158930626719801589306306814115893063113990
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035013682213682241943042560012241685120x7ff91540d7000x7ff914a25c80131072101934811399583215893063135110158930630681411589306339966215893063401604
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035313682213682241943042560012241712640x7ff917ab05800x7ff914a25cc01310726533907324768815893063434173158930633996621589306376958315893063771456
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035613682213682241943042560012241737600x7ff917ab04000x7ff914a25d00655366479387259886415893063803595158930637695831589306413982415893064141817
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035913682213682241943042560012241762560x7ff917ab02800x7ff914a25d401310726529387318270415893064174107158930641398241589306446478515893064466700
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036213682213682241943042560012241797760x7ff917ab01000x7ff914a25d801310726531047315976015893064498019158930644647851589306488142615893064926940
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036513682213682241943042560012241822720x7ff91540df800x7ff914a25dc0131072103616211615325615893064947009158930648814261589306522862715893065230683
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036813682213682241943042560012241855360x7ff91540de000x7ff914a25e001310726840327663353615893065261432158930652286271589306560446815893065607995
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037113682213682241943042560012241885440x7ff91540dc800x7ff914a25e40655366464327249770415893065638134158930656044681589306598687015893065988966
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037413682213682241943042560012241915520x7ff91540db000x7ff914a25e801310726447387214043215893066020015158930659868701589306635407115893066356098
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037713682213682241943042560012241958400x7ff91540d9800x7ff914a25ec01310726486447264596815893066388167158930663540711589306682879215893066874476
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038013682213682241943042560012241985920x7ff91540d8000x7ff914a25f00131072102321411453043215893066894006158930668287921589306720335315893067205289
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038313682213682241943042560012242023680x7ff91540d6800x7ff914a25f4013107295988410757718415893067238288158930672033531589306759695415893067642089
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038613682213682241943042560012242058880x7ff917ab05000x7ff914a25f80655366458567235384815893067653819158930675969541589306802671515893068072490
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038913682213682241943042560012242094080x7ff917ab03800x7ff914a25fc01310726524307312896815893068083670158930680267151589306843327615893068435112
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039213682213682241943042560012242144640x7ff917ab02000x7ff914a260001310726519447303305615893068467041158930684332761589306895439815893068996689
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039513682213682241943042560012242177280x7ff917ab00800x7ff914a26040131072103058211549162415893069015969158930689543981589306933711915893069339062
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039813682213682241943042560012242220160x7ff91540df000x7ff914a26080131072105492211820528015893069370601158930693371191589306975504015893069774072
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040113682213682241943042560012242260480x7ff91540dd800x7ff914a260c0655366537547324262415893069787982158930697550401589307017792115893070223992
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040413682213682241943042560012242300800x7ff91540dc000x7ff914a261001310726528987309130415893070235792158930701779211589307061328315893070656922
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040713682213682241943042560012242359040x7ff91540da800x7ff914a261401310726855327671452815893070669422158930706132831589307122224415893071242049
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041013682213682241943042560012242394240x7ff91540d9000x7ff914a26180131072102417411493174415893071262979158930712222441589307160192515893071603791
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041313682213682241943042560012242442240x7ff91540d7800x7ff914a261c013107296091610771763215893071634481158930716019251589307204304715893072085041
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041613682213682241943042560012242487680x7ff91540d6000x7ff914a26200655366889007727125615893072097470158930720430471589307250592815893072547450
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041913682213682241943042560012242533120x7ff917ab04800x7ff914a262401310726460527229662415893072559160158930725059281589307296528915893073007550
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221368221368224194304256008242555520x7ff917ab03000x7ff914a26280131072103483011591647215893073018910158930729652891589307363489115893073678015
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042513682213682241943042560012242598400x7ff917ab01800x7ff914a262c0131072101850411417066415893073697495158930736348911589307407905215893074149054
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042813682213682241943042560012242656640x7ff917ab00000x7ff914a26300131072102158811454805615893074161444158930740790521589307471665415893074795960
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043113682213682241943042560012242712320x7ff91540de800x7ff914a26340655366515747289941615893074807710158930747166541589307534833615893075425606
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341368221368224194304256008242732160x7ff91540dd000x7ff914a2638013107297457610913384015893075437146158930753483361589307597569815893076051232
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371368221368224194304256008242757120x7ff91540db800x7ff914a263c0131072102427411480160815893076063522158930759756981589307686178015893076937912
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044013682213682241943042560012242807680x7ff91540da000x7ff914a2640013107295850610727961615893076957632158930768617801589307746706215893077544029
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044313682213682241943042560012242876160x7ff91540d8800x7ff914a26440131072102288011448718415893077556398158930774670621589307814994415893078228023
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044613682213682241943042560012242942080x7ff91540d7000x7ff914a26480655366490827264601615893078240273158930781499441589307883618615893078915448
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491368221368224194304256008242969600x7ff917ab05800x7ff914a264c013107297022810863371215893078927428158930788361861589307951730815893079564913
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521368221368224194304256008242999680x7ff917ab04000x7ff914a26500131072102789211477379215893079576453158930795173081589308043027015893080476223
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551368221368224194304256008243027200x7ff917ab02800x7ff914a26540131072102885211527044015893080495873158930804302701589308112675215893081200037
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045813682213682241943042560012243054720x7ff917ab01000x7ff914a26580131072103078011545497615893081212447158930811267521589308191955515893081968020
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046113682213682241943042560012243082240x7ff91540df800x7ff914a265c0655366505367285241615893081979919158930819196891589308267457115893082795051
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641368221368224194304256008243109760x7ff91540de000x7ff914a26600131072102370211465142415893082808061158930826745711589308351057315893083608813
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671368221368224194304256008243132160x7ff91540dc800x7ff914a26640131072101958411415716015893083621963158930835105731589308474129715893084830936
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701368221368224194304256008243159680x7ff91540db000x7ff914a26680131072102611011482474415893084851915158930847412971589308591778015893086007489
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047313682213682241943042560012243187200x7ff91540d9800x7ff914a266c0131072101528611381504815893086019759158930859177801589308713698415893087228822
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047613682213682241943042560012243214720x7ff91540d8000x7ff914a26700655366519607287963215893087241232158930871369841589308834402815893088434556
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791368221368224194304256008243242240x7ff91540d6800x7ff914a26740131072105127211754339215893088447005158930883440281589308952899115893089620219
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821368221368224194304256008243264640x7ff917ab05000x7ff914a26780131072102517811468980015893089632879158930895289911589309154659815893091647164
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851368221368224194304256008243292160x7ff917ab03800x7ff914a267c0131072102435411506069615893091667244158930915465981589309355140415893093644050
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048813682213682241943042560012243319680x7ff917ab02000x7ff914a26800131072100680211278493615893093656229158930935514041589309560949015893095706753
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049113682213682241943042560012243347200x7ff917ab00800x7ff914a26840655366532167329775215893095718833158930956094901589309766933715893097762908
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941368221368224194304256008243374720x7ff91540df000x7ff914a26880131072102325011451736815893097775727158930976693371589309968758315893099791182
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049713682213682241943042560082400x7ff91540dd800x7ff914a268c0131072101841011431541615893099803802158930996875831589310339607415893103487300