Files
rocm-systems/tests/workloads/HBM/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.kd000875584875589335544322560083264640x00x7f5b04404180104857611071116141719312012075444941615500120754451862500061207544518657368412075445186682496
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00287558487558932768256002424124800x00x7f5b0443510040961233641578598812075445201347390120754452016509301207544520165685012075445201668637
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0048755848755894194304256002424129280x7f5c0ff999000x7f5b0443514052428812242043156690434812075445201720614120754452019355691207544520206772812075445202071947
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0068755848755894194304256003624136320x7f5c0ff998000x7f5b0443518052428813183125168742587612075445202143941120754452023182871207544520256804612075445202636566
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0088755848755894194304256002824140800x7f5c0ff997000x7f5b044351c052428814292621182945117612075445202672393120754452028603641207544520310996312075445203179696
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00108755848755894194304256002424145280x7f5c0ff996000x7f5b0443520052428812654083161968650412075445203211415120754452033899621207544520352164112075445203525238
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00128755848755894194304256002424149760x7f5c0ff995000x7f5b0443524052428812138351155368555212075445203574539120754452037466001207544520387971912075445203883243
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00148755848755894194304256002424154240x7f5c0ff994000x7f5b0443528052428812026446153937599212075445203962671120754452041336381207544520426723712075445204271114
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00168755848755894194304256002824161280x7f5c0ff993000x7f5b044352c052428813644148174644234412075445204320105120754452044950761207544520474803512075445204788996
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00188755848755894194304256002824168320x7f5c0ff99a000x7f5b0443530052428814230216182142466012075445204814634120754452049933141207544520524115312075445205281692
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00208755848755894194304256002424175360x7f5c0ff999000x7f5b0443534052428812238749156657066812075445205306138120754452054992311207544520563075112075445205634347
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00228755848755894194304256002424182400x7f5c0ff998000x7f5b0443538052428811196438143321746812075445205685092120754452058565101207544520599330912075445205996811
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00248755848755894194304256002424189440x7f5c0ff997000x7f5b044353c052428812212793156316015612075445206059277120754452062237081207544520635522712075445206358804
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00268755848755894194304256002824199040x7f5c0ff996000x7f5b0443540052428812806611163921119212075445206409598120754452065747461207544520683282512075445206898998
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00288755848755894194304256002824206080x7f5c0ff995000x7f5b0443544052428812870479164743112412075445206923924120754452071139431207544520737186212075445207440494
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00308755848755894194304256002424213120x7f5c0ff994000x7f5b0443548052428812542658160542829212075445207459650120754452076491411207544520777922012075445207782961
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00328755848755894194304256002424220160x7f5c0ff993000x7f5b044354c052428811511646147343077612075445207827193120754452079985791207544520813457912075445208138331
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00348755848755894194304256002424227200x7f5c0ff99a000x7f5b0443550052428812096847154838821212075445208198823120754452083622571207544520849377712075445208497398
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00368755848755894194304256002824236800x7f5c0ff999000x7f5b0443554052428814058725179944664812075445208550427120754452087116961207544520896209512075445209028996
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00388755848755894194304256002824243840x7f5c0ff998000x7f5b0443558052428813992064179089184812075445209052630120754452092412931207544520949041212075445209557448
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00408755848755894194304256002424250880x7f5c0ff997000x7f5b044355c052428812651846161946930012075445209581062120754452097646511207544520989425012075445209897971
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00428755848755894194304256002424257920x7f5c0ff996000x7f5b0443560052428812665739162126304012075445209948485120754452101121691207544521024240812075445210246309
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00448755848755894194304256002424264960x7f5c0ff995000x7f5b0443564052428811973210153251719612075445210307673120754452104707271207544521060288712075445210606518
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00468755848755894194304256002824277120x7f5c0ff994000x7f5b0443568052428812547634160609941212075445210655038120754452108179261207544521107648412075445211144378
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00488755848755894194304256002824284160x7f5c0ff993000x7f5b044356c052428813992156179091817212075445211168502120754452113497631207544521159968212075445211665997
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00508755848755894194304256002424291200x7f5c0ff99a000x7f5b0443570052428813332673170660550812075445211691725120754452118692801207544521199712012075445212003434
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00528755848755894194304256002424300800x7f5c0ff999000x7f5b0443574052428812764778163387881612075445212050993120754452122156791207544521234623812075445212349968
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00548755848755894194304256002424307840x7f5c0ff998000x7f5b0443578052428812607970161375884812075445212409759120754452125753571207544521270559612075445212709316
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00568755848755894194304256002824320000x7f5c0ff997000x7f5b044357c052428813333275170657546412075445212756844120754452129371151207544521319295412075445213234592
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00588755848755894194304256002824329600x7f5c0ff996000x7f5b0443580052428814024869179517070812075445213257895120754452134420731207544521369295212075445213733499
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00608755848755894194304256002424339200x7f5c0ff995000x7f5b0443584052428811231225143760937212075445213755901120754452139355101207544521407135012075445214075255
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00628755848755894194304256002424348800x7f5c0ff994000x7f5b0443588052428812122996155176053212075445214123775120754452142913491207544521442478812075445214428431
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00648755848755894194304256002424358400x7f5c0ff993000x7f5b044358c052428812724140162867074812075445214489394120754452146511871207544521478046612075445214784262
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00668755848755894194304256002824373120x7f5c0ff99a000x7f5b0443590052428814274589182705572012075445214832552120754452150004651207544521525534412075445215324426
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00688755848755894194304256002824382720x7f5c0ff999000x7f5b0443594052428813994868179132756012075445215348972120754452155319831207544521578670112075445215853018
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00708755848755894194304256002424392320x7f5c0ff998000x7f5b0443598052428811888702152166582412075445215878235120754452160619001207544521624061912075445216244456
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00728755848755894194304256002424401920x7f5c0ff997000x7f5b044359c052428812808125163938991212075445216294379120754452164676581207544521659789812075445216601399
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00748755848755894194304256002424411520x7f5c0ff996000x7f5b04435a0052428813160617168452014012075445216662363120754452168247761207544521695293612075445216956780
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00768755848755894194304256002824426240x7f5c0ff995000x7f5b04435a4052428811970878153224827212075445217011101120754452171758151207544521743325312075445217499478
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00788755848755894194304256002824435840x7f5c0ff994000x7f5b04435a8052428813277269169952458812075445217521429120754452177022121207544521798957112075445218032008
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00808755848755894194304256002424445440x7f5c0ff993000x7f5b04435ac052428812711504162709288012075445218054339120754452182366101207544521836700912075445218370717
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00828755848755894194304256002424457600x7f5c0ff99a000x7f5b04435b0052428811298077144613674812075445218422383120754452185847681207544521872188712075445218725587
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00848755848755894194304256002424467200x7f5c0ff999000x7f5b04435b4052428811770214150654812412075445218785218120754452189442861207544521907756612075445219081308
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00868755848755894194304256002824484480x7f5c0ff998000x7f5b04435b8052428811918525152555752012075445219124548120754452192991641207544521956412312075445219631781
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00888755848755894194304256002824494080x7f5c0ff997000x7f5b04435bc052428813102832167712963612075445219654573120754452198338821207544522009100112075445220157238
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00908755848755894194304256002424503680x7f5c0ff996000x7f5b04435c0052428811227652143712468812075445220178016120754452203681191207544522050395912075445220507499
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00928755848755894194304256002424515840x7f5c0ff995000x7f5b04435c4052428811497745147174191212075445220557411120754452207255581207544522086171712075445220865464
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00948755848755894194304256002424525440x7f5c0ff994000x7f5b04435c8052428812683526162346492412075445220924153120754452210908361207544522122027512075445221224231
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00968755848755894194304256002824542720x7f5c0ff993000x7f5b04435cc052428813710500175491249212075445221273252120754452214450741207544522171067312075445221752592
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00988755848755894194304256002824554880x7f5c0ff99a000x7f5b04435d0052428814223021182056335612075445221777499120754452219527521207544522220827012075445222276376
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001008755848755894194304256002424567040x7f5c0ff999000x7f5b04435d4052428811821414151309589612075445222299008120754452224842691207544522261674812075445222620505
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001028755848755894194304256002424581760x7f5c0ff998000x7f5b04435d8052428810631555136086752012075445222668294120754452228337071207544522297034712075445222974133
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001048755848755894194304256002424593920x7f5c0ff997000x7f5b04435dc052428812428129159084508412075445223039945120754452232029861207544522333370512075445223337518
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001068755848755894194304256002824613760x7f5c0ff996000x7f5b04435e0052428812046177154192826412075445223386058120754452235533841207544522381802312075445223884915
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001088755848755894194304256002824625920x7f5c0ff995000x7f5b04435e4052428814182319181537470412075445223902187120754452240972211207544522434666012075445224413969
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001108755848755894194304256002424638080x7f5c0ff994000x7f5b04435e8052428811674883149439160812075445224436961120754452246159391207544522475033812075445224754161
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001128755848755894194304256002424652800x7f5c0ff993000x7f5b04435ec05242889221224118023580412075445224803943120754452249719371207544522511417612075445225118097
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001148755848755894194304256002424664960x7f5c0ff99a000x7f5b04435f0052428812504674160063105212075445225180353120754452253432951207544522547369512075445225477625
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001168755848755894194304256002824684800x7f5c0ff999000x7f5b04435f4052428811703016149797217612075445225525334120754452256949731207544522595577212075445226022668
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001188755848755894194304256002824696960x7f5c0ff998000x7f5b04435f8052428812256949156884213212075445226045811120754452262280911207544522648297012075445226549988
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001208755848755894194304256002424709120x7f5c0ff997000x7f5b04435fc052428810848266138854276012075445226575546120754452267487281207544522688584812075445226889639
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001228755848755894194304256002424723840x7f5c0ff996000x7f5b044360005242888358145106980587212075445226938080120754452271128871207544522725144612075445227255259
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001248755848755894194304256002424736000x7f5c0ff995000x7f5b0443604052428812555089160710648012075445227316543120754452274775251207544522760792412075445227611772
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001268755848755894194304256002824758400x7f5c0ff994000x7f5b0443608052428813283158170023966412075445227660422120754452278330431207544522809608212075445228144872
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001288755848755894194304256002824770560x7f5c0ff993000x7f5b044360c052428813975311178882310012075445228168927120754452283495211207544522860503912075445228653498
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001308755848755894194304256002424782720x7f5c0ff99a000x7f5b0443610052428812521954160291171612075445228674987120754452288533581207544522898375812075445228987478
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001328755848755894194304256002424800000x7f5c0ff999000x7f5b04436140524288733843093937836412075445229035578120754452292050361207544522934871612075445229352386
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001348755848755894194304256002424812160x7f5c0ff998000x7f5b0443618052428813103930167728096012075445229412468120754452295725551207544522970103412075445229704761
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001368755848755894194304256002824834560x7f5c0ff997000x7f5b044361c052428813078984167407612012075445229751568120754452299191131207544523017911212075445230228164
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001388755848755894194304256002824849280x7f5c0ff996000x7f5b0443620052428812224011156461782012075445230251077120754452304330311207544523068934912075445230710681
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001408755848755894194304256002424864000x7f5c0ff995000x7f5b0443624052428812215939156362370412075445230753330120754452309151081207544523104726812075445231051244
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001428755848755894194304256002424881280x7f5c0ff994000x7f5b04436280524288592262175807658412075445231104402120754452312669461207544523141782612075445231421622
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001448755848755894194304256002424896000x7f5c0ff993000x7f5b044362c052428811164844142917910012075445231502222120754452316602251207544523179622412075445231800105
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001468755848755894194304256002824920960x7f5c0ff99a000x7f5b0443630052428811072665141725934412075445231848085120754452320226231207544523228518212075445232333847
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001488755848755894194304256002824935680x7f5c0ff999000x7f5b0443634052428812738660163048665612075445232357511120754452325355801207544523279269912075445232840970
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001508755848755894194304256002424950400x7f5c0ff998000x7f5b0443638052428811560016147970368812075445232862931120754452330474181207544523318117712075445233184959
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001528755848755894194304256002424967680x7f5c0ff997000x7f5b044363c0524288440388056373088412075445233233499120754452334016561207544523355909512075445233563032
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001548755848755894194304256002424982400x7f5c0ff996000x7f5b0443640052428811403545145952686812075445233623755120754452337829341207544523391717412075445233920927
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015687558487558941943042560028241007360x7f5c0ff995000x7f5b0443644052428810889606139385545212075445233967964120754452341418131207544523440853112075445234431035
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015887558487558941943042560028241022080x7f5c0ff994000x7f5b0443648052428814102128180500595612075445234473213120754452346381301207544523488804912075445234934741
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016087558487558941943042560024241036800x7f5c0ff993000x7f5b044364c052428811285718144460116412075445234956411120754452351421281207544523527812712075445235282217
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016287558487558941943042560024241056640x7f5c0ff99a000x7f5b04436500524288434218755576462812075445235332240120754452355032461207544523566996512075445235673684
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016487558487558941943042560024241071360x7f5c0ff999000x7f5b0443654052428811433598146347052412075445235733866120754452358955641207544523603060312075445236034635
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016687558487558941943042560028241098880x7f5c0ff998000x7f5b0443658052428810220070130817001212075445236087433120754452362488421207544523650980112075445236557687
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016887558487558941943042560028241113600x7f5c0ff997000x7f5b044365c052428813620211174339675612075445236583064120754452367603601207544523701491912075445237062746
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017087558487558941943042560024241128320x7f5c0ff996000x7f5b0443660052428811426388146254526812075445237086360120754452372681971207544523740339712075445237407236
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017287558487558941943042560024241148160x7f5c0ff995000x7f5b04436640524288361813346311592812075445237456137120754452376240361207544523779811512075445237801819
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017487558487558941943042560024241162880x7f5c0ff994000x7f5b0443668052428812479411159729118012075445237860929120754452380275541207544523815971312075445238164173
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017687558487558941943042560028241190400x7f5c0ff993000x7f5b044366c05242888847721113253545212075445238212312120754452383824321207544523864227112075445238666166
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017887558487558941943042560028241207680x7f5c0ff99a000x7f5b0443670052428813526668173137661612075445238710418120754452388734701207544523912818812075445239155455
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018087558487558941943042560024241224960x7f5c0ff999000x7f5b0443674052428811802974151074392412075445239195469120754452393541071207544523948818712075445239492040
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018287558487558941943042560024241247360x7f5c0ff998000x7f5b04436780524288355147245458124412075445239539639120754452397070661207544523989010512075445239894008
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018487558487558941943042560024241264640x7f5c0ff997000x7f5b044367c052428810943653140079898012075445239954049120754452401219441207544524026066312075445240264676
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018687558487558941943042560020241279360x7f5c0ff996000x7f5b04436800524288418111653516024012075445240314950120754452404835421207544524074930112075445240773552
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018887558487558941943042560028241296640x7f5c0ff995000x7f5b0443684052428813714222175535008012075445240816492120754452409731391207544524123169812075445241257431
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019087558487558941943042560024241313920x7f5c0ff994000x7f5b0443688052428811106078142158916412075445241300161120754452414595371207544524159473612075445241598746
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019287558487558941943042560024241336320x7f5c0ff993000x7f5b044368c0524288349385644725580012075445241646845120754452418148951207544524200625412075445242010180
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019487558487558941943042560024241353600x7f5c0ff99a000x7f5b0443690052428810991023140683480012075445242090009120754452422540931207544524239089312075445242394755
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019687558487558941943042560020241368320x7f5c0ff999000x7f5b04436940524288293142737516869212075445242442183120754452426166511207544524289985012075445242924640
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019887558487558941943042560028241385600x7f5c0ff998000x7f5b0443698052428813844168177202246012075445242966728120754452431318491207544524338512812075445243412757
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020087558487558941943042560024241402880x7f5c0ff997000x7f5b044369c052428811153081142753986812075445243451749120754452436100871207544524374592612075445243749833
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020287558487558941943042560024241427840x7f5c0ff996000x7f5b04436a00524288350696544874774412075445243801509120754452439624051207544524417296412075445244198637
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020487558487558941943042560024241447680x7f5c0ff995000x7f5b04436a4052428810612791135845608812075445244252958120754452444155231207544524455472212075445244558707
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020687558487558941943042560020241457280x7f5c0ff994000x7f5b04436a80524288254516632577634812075445244607006120754452447744011207544524508336012075445245109120
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020887558487558941943042560028241477120x7f5c0ff993000x7f5b04436ac052428812821199164106852012075445245149585120754452453108781207544524556767712075445245591506
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021087558487558941943042560024241496960x7f5c0ff99a000x7f5b04436b0052428812123124155166266412075445245632913120754452457918361207544524592495512075445245928993
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021287558487558941943042560024241521920x7f5c0ff999000x7f5b04436b40524288341300143683325612075445245975480120754452461612741207544524638879312075445246415327
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021487558487558941943042560024241541760x7f5c0ff998000x7f5b04436b8052428810326131132184002012075445246473976120754452466364721207544524677663112075445246780666
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021687558487558941943042560020241556480x7f5c0ff997000x7f5b04436bc0524288244686131305940012075445246828866120754452469982301207544524732798912075445247355775
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021887558487558941943042560028241576320x7f5c0ff996000x7f5b04436c0052428812895496165058676412075445247398294120754452475588681207544524782062612075445247843952
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022087558487558941943042560024241596160x7f5c0ff995000x7f5b04436c4052428811156533142810963612075445247886872120754452480537451207544524818990412075445248193953
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022287558487558941943042560024241623680x7f5c0ff994000x7f5b04436c80524288342787043878310012075445248241461120754452484158231207544524866142212075445248685436
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022487558487558941943042560024241646080x7f5c0ff993000x7f5b04436cc05242889612210123033692412075445248741480120754452489052611207544524904846012075445249052618
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022687558487558941943042560020241663360x7f5c0ff99a000x7f5b04436d00524288239548430655701212075445249100738120754452492738531207544524965209212075445249679263
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022887558487558941943042560028241685760x7f5c0ff999000x7f5b04436d4052428813167816168540782812075445249717654120754452498792901207544525013928912075445250165266
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023087558487558941943042560024241708160x7f5c0ff998000x7f5b04436d805242889293134118947127612075445250204659120754452503661681207544525051064812075445250513223
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023287558487558941943042560024241740800x7f5c0ff997000x7f5b04436dc0524288334007542751850412075445250564889120754452507381671207544525104856612075445251072352
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023487558487558941943042560024241765760x7f5c0ff996000x7f5b04436e005242889186430117575978812075445251131973120754452512976851207544525143352512075445251436108
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023687558487558941943042560020241777920x7f5c0ff995000x7f5b04436e40524288235550930154362012075445251484949120754452516484041207544525207496312075445252098649
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023887558487558941943042560028241802880x7f5c0ff994000x7f5b04436e8052428810248423131177694812075445252140828120754452523007221207544525256488212075445252587107
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024087558487558941943042560024241827840x7f5c0ff993000x7f5b04436ec05242888143353104235918012075445252630217120754452527912811207544525293176012075445252934423
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024287558487558941943042560024241863040x7f5c0ff99a000x7f5b04436f00524288339649943471368012075445252981300120754452531576801207544525347303912075445253498952
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024487558487558941943042560024241893120x7f5c0ff999000x7f5b04436f40524288366765746938387212075445253553553120754452537175181207544525387079812075445253873297
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024687558487558941943042560020241907840x7f5c0ff998000x7f5b04436f80524288234489030017152412075445253921507120754452540960771207544525461559512075445254642818
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024887558487558941943042560028241937920x7f5c0ff997000x7f5b04436fc05242888172764104611561212075445254687871120754452548511151207544525514855412075445255175137
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025087558487558941943042560024241968000x7f5c0ff996000x7f5b04437000524288329438242163330012075445255211935120754452553850331207544525553991212075445255542600
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025287558487558941943042560024242010880x7f5c0ff995000x7f5b04437040524288339876243498039212075445255590739120754452557624721207544525614759112075445256172701
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025487558487558941943042560024242046080x7f5c0ff994000x7f5b04437080524288323956041450922012075445256230769120754452563943101207544525657142912075445256574187
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025687558487558941943042560020242060800x7f5c0ff993000x7f5b044370c0524288232654829767741612075445256621705120754452567915891207544525741334712075445257440467
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025887558487558941943042560028242096000x7f5c0ff99a000x7f5b04437100524288403951351700868812075445257485300120754452576475861207544525797590512075445257997572
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026087558487558941943042560024242131200x7f5c0ff999000x7f5b04437140524288344003444021385612075445258049479120754452582139841207544525839286412075445258395331
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026287558487558941943042560024242181760x7f5c0ff998000x7f5b04437180524288387787649631412812075445258444803120754452586101431207544525906630112075445259090012
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026487558487558941943042560024242222080x7f5c0ff997000x7f5b044371c0524288321113941113360412075445259149693120754452593130211207544525951350012075445259535591
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026687558487558941943042560020242239360x7f5c0ff996000x7f5b04437200524288230013929433814012075445259582117120754452597426191207544526044533712075445260468584
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026887558487558941943042560028242279680x7f5c0ff995000x7f5b04437240524288340797243617073612075445260511264120754452606742971207544526104741512075445261071635
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027087558487558941943042560024242320000x7f5c0ff994000x7f5b04437280524288324101841477334812075445261116338120754452612776551207544526148069412075445261503017
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027287558487558941943042560024242378240x7f5c0ff993000x7f5b044372c0524288397725250903775612075445261552449120754452617179731207544526224469212075445262268259
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027487558487558941943042560024242423680x7f5c0ff99a000x7f5b04437300524288321349441143284812075445262328842120754452624925311207544526275173012075445262775462
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027687558487558941943042560020242435840x7f5c0ff999000x7f5b04437340524288229544629381242412075445262818211120754452629784491207544526377812712075445263805857
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027887558487558941943042560028242481280x7f5c0ff998000x7f5b04437380524288339564143460432012075445263846242120754452640067661207544526442772512075445264452699
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028087558487558941943042560024242526720x7f5c0ff997000x7f5b044373c0524288308545139505820812075445264500598120754452646658041207544526489268312075445264912363
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028287558487558941943042560024242592640x7f5c0ff996000x7f5b04437400524288450914157717980412075445264961504120754452651315631207544526572804112075445265754769
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028487558487558941943042560024242648320x7f5c0ff995000x7f5b04437440524288349251344691535612075445265805803120754452659702801207544526624035912075445266265478
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028687558487558941943042560020242663040x7f5c0ff994000x7f5b04437480524288229765229405644812075445266307776120754452664686791207544526745251612075445267519318
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028887558487558941943042560028242718720x7f5c0ff993000x7f5b044374c0524288337511743207494012075445267548612120754452677336351207544526824915312075445268316550
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029087558487558941943042560024242774400x7f5c0ff99a000x7f5b04437500524288336625343081331212075445268345914120754452685289921207544526880179112075445268867704
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029287558487558941943042560012242799360x7f5c0ff999000x7f5b04437540524288219560128098380812075445268893622120754452690750711207544526981362812075445269882169
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029487558487558941943042560024242865280x7f5c0ff998000x7f5b04437580524288332596542574846012075445269919118120754452700870671207544527040482612075445270470713
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029687558487558941943042560020242880000x7f5c0ff997000x7f5b044375c0524288228785829274526812075445270493846120754452706821061207544527185202212075445271918474
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029887558487558941943042560032242945920x7f5c0ff996000x7f5b04437600524288335739442964950012075445271948980120754452721360211207544527274641912075445272814399
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030087558487558941943042560024243011840x7f5c0ff995000x7f5b04437640524288332026742487148012075445272837051120754452730297781207544527334833712075445273415896
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030287558487558941943042560012243049600x7f5c0ff994000x7f5b04437680524288226684829010547212075445273439200120754452736260971207544527450417412075445274572286
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030487558487558941943042560024243136000x7f5c0ff993000x7f5b044376c0524288325221841622789612075445274608693120754452747699331207544527517985212075445275249164
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030687558487558941943042560020243148160x7f5c0ff99a000x7f5b04437700524288229762829412887212075445275281133120754452754688111207544527701504612075445277082761
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030887558487558941943042560020243175680x7f5c0ff999000x7f5b04437740524288228602729258705212075445277114240120754452772958451207544527808976312075445278157509
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031087558487558941943042560012243203200x7f5c0ff998000x7f5b04437780524288218020327907496412075445278186272120754452783683221207544527878288112075445278849054
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031287558487558941943042560012243240960x7f5c0ff997000x7f5b044377c0524288221095428303288012075445278875844120754452790728001207544528023167612075445280300291
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031487558487558941943042560012243288960x7f5c0ff996000x7f5b04437800524288218730127999298012075445280336839120754452805015951207544528128831312075445281355692
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031687558487558941943042560020243301120x7f5c0ff995000x7f5b04437840524288269876534544905612075445281386660120754452815691121207544528461886312075445284687103
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031887558487558941943042560020243328640x7f5c0ff994000x7f5b04437880524288233321129863930812075445284717310120754452848983821207544528644093712075445286510212
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032087558487558941943042560012243356160x7f5c0ff993000x7f5b044378c0524288220817728265390412075445286534347120754452867327761207544528752173412075445287588736
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032287558487558941943042560012243393920x7f5c0ff99a000x7f5b04437900524288252499332317670012075445287619623120754452878007731207544529008188612075445290150878
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032487558487558941943042560012243441920x7f5c0ff999000x7f5b04437940524288236400030244678012075445290195551120754452903583651207544529189388012075445291961262
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032687558487558941943042560020243454080x7f5c0ff998000x7f5b04437980524288292421237431401212075445291989956120754452921786791207544529823402012075445298302768
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032887558487558941943042560020243481600x7f5c0ff997000x7f5b044379c0524288324662641545547612075445298332062120754452985154601207544530155705012075445301627707
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033087558487558941943042560012243509120x7f5c0ff996000x7f5b04437a00524288247878231719087612075445301650890120754453018405691207544530337976512075445303449443
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332875584875589419430425600122400x7f5c0ff995000x7f5b04437a40524288257066232897828012075445303480610120754453036636041207544530819095012075445308261676