Files
rocm-systems/tests/workloads/Axes4/mi200/SQ_IFETCH_LEVEL.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

44 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjGRBM_COUNTGRBM_GUI_ACTIVESQ_WAVESSQ_IFETCHSQ_IFETCH_LEVELSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000217839217839335544322560043241600x00x7f57fd40428038070638070652428847185926833007643047217520169087269175194625389471752032071424417520320824664
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00221783921783932768256001224138880x00x7f57fd423f8033444334445128192606467730817520325979931175203207142441752032612353317520326128288
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0052178392178394194304256001224143360x7f58004a43800x7f57fd423fc0167781167781655369175041408901570331617520326166047175203261235331752032650433417520326506818
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0082178392178394194304256001624150400x7f58004a42000x7f57fd4240003195173195176553611141121673931874251617520326547027175203265043341752032692369417520326925937
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00112178392178394194304256001624154880x7f58004a40800x7f57fd424040322099322099655369175041389981558154417520326961796175203269236941752032733377517520327339726
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00142178392178394194304256001224159360x7f57fde0df000x7f57fd4240801703971703976553610485761576241773233617520327372316175203273337751752032764769617520327650078
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00172178392178394194304256001224163840x7f57fde0dd800x7f57fd4240c0168269168269655369830401482491660625617520327684518175203276476961752032795841617520327960480
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00202178392178394194304256001224170880x7f57fde0dc000x7f57fd4241001686031686036553611141121631851823232817520328008189175203279584161752032826753717520328269743
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00232178392178394194304256001624177920x7f57fde0da800x7f57fd4241403242303242306553613107202035032274726417520328305312175203282675371752032867713817520328679402
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00262178392178394194304256001624184960x7f57fde0d9000x7f57fd4241803186593186596553611796481777261988683217520328713471175203286771381752032909361817520329095771
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00292178392178394194304256001624192000x7f57fde0d7800x7f57fd4241c01680341680346553612451841894682119508417520329130630175203290936181752032940481917520329406863
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00322178392178394194304256001624199040x7f57fde0d6000x7f57fd4242001677201677206553612451841859172091738017520329441622175203294048191752032971489917520329717345
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00352178392178394194304256001224206080x7f58004a44800x7f57fd4242401678161678166553612451841870772099651617520329760624175203297148991752033002642017520330028417
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00382178392178394194304256001624213120x7f58004a43000x7f57fd4242803208703208706553614417922164532419934417520330064676175203300264201752033046226117520330467566
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00412178392178394194304256001624220160x7f58004a41800x7f57fd4242c03151823151826553613107201970652212268817520330500335175203304622611752033087074217520330872976
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00442178392178394194304256001624227200x7f58004a40000x7f57fd4243001680701680706553613762562051582304402817520330908765175203308707421752033118194217520331183908
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00472178392178394194304256001224234240x7f57fde0de800x7f57fd4243401670121670126553614417922173232434195617520331219097175203311819421752033147794317520331479860
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00502178392178394194304256001224241280x7f57fde0dd000x7f57fd4243801658741658746553613107201970152197026017520331521899175203314779431752033178178317520331783732
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00532178392178394194304256001624248320x7f57fde0db800x7f57fd4243c03182713182716553615728642347142627281217520331818021175203317817831752033217298417520332177622
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00562178392178394194304256001624255360x7f57fde0da000x7f57fd4244003138743138746553614417922084622334533217520332209951175203321729841752033255954517520332561402
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00592178392178394194304256001224262400x7f57fde0d8800x7f57fd4244401705011705016553615073282260972524943217520332595451175203325595451752033286610517520332867964
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00622178392178394194304256001224269440x7f57fde0d7000x7f57fd4244801693791693796553616384002443712738884417520332903204175203328661051752033316210617520333164087
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00652178392178394194304256001224276480x7f58004a45800x7f57fd4244c01685271685276553614417922171872431473217520333206676175203331621061752033346546617520333467259
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00682178392178394194304256001624286080x7f58004a44000x7f57fd4245003190353190356553617039362518042820844417520333502588175203334654661752033385442717520333858749
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00712178392178394194304256001624293120x7f58004a42800x7f57fd4245403140183140186553615728642328322616488817520333890878175203338544271752033424082817520334242579
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00742178392178394194304256001224300160x7f58004a41000x7f57fd4245801666971666976553616384002433812721401217520334277758175203342408281752033454818817520334550071
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077217839217839419430425600824309760x7f57fde0df800x7f57fd4245c01682081682086553618350082702513031286417520334585980175203345481881752033484594917520334847704
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00802178392178394194304256001224316800x7f57fde0de000x7f57fd4246001658251658256553615073282248802517186817520334889343175203348459491752033514674917520335148576
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00832178392178394194304256001624326400x7f57fde0dc800x7f57fd4246403146913146916553618350082724483054540017520335183535175203351467491752033553299017520335534756
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00862178392178394194304256001224336000x7f57fde0db000x7f57fd4246803137413137416553617039362492112786612817520335568575175203355329901752033591955117520335921366
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00892178392178394194304256001224345600x7f57fde0d9800x7f57fd4246c01710141710146553617694722644022957792417520335955295175203359195511752033621859117520336220348
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092217839217839419430425600824355200x7f57fde0d8000x7f57fd4247001683351683356553620316163020703393105617520336255427175203362185911752033651779217520336519561
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00952178392178394194304256001224362240x7f57fde0d6800x7f57fd4247401688441688446553616384002466702767671617520336562090175203365177921752033681491217520336816763
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00982178392178394194304256001224371840x7f58004a45000x7f57fd4247803117063117066553619660802884103231302017520336850182175203368149121752033720819317520337210043
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001012178392178394194304256001224381440x7f58004a43800x7f57fd4247c03136773136776553618350082725373052638017520337245642175203372081931752033759571417520337597643
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001042178392178394194304256001224391040x7f58004a42000x7f57fd4248001684461684466553619005442828323162854817520337633592175203375957141752033789187417520337893765
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107217839217839419430425600824403200x7f58004a40800x7f57fd4248401675901675906553622282243323253717642417520337928784175203378918741752033820211517520338203977
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001102178392178394194304256001224412800x7f57fde0df000x7f57fd4248801678521678526553617039362550742863360817520338248296175203382021151752033850915517520338511010
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001132178392178394194304256001224422400x7f57fde0dd800x7f57fd4248c03141083141086553620971523120183501519217520338545479175203385091551752033889539617520338897120
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001162178392178394194304256001224432000x7f57fde0dc000x7f57fd4249003085563085566553619660802830323176329217520338931449175203388953961752033928067717520339282640
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119217839217839419430425600824441600x7f57fde0da800x7f57fd4249401686141686146553620316163015643379332817520339316809175203392806771752033957731717520339579142
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001222178392178394194304256001224453760x7f57fde0d9000x7f57fd4249801684711684716553624248323626054065299217520339613191175203395773171752033988227817520339884094
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001252178392178394194304256001224463360x7f57fde0d7800x7f57fd4249c01684331684336553618350082719343052034017520339926043175203398822781752034018035817520340182227
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001282178392178394194304256001224475520x7f57fde0d6000x7f57fd424a003074713074716553622282243267963665545617520340217056175203401803581752034056291917520340564697
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001312178392178394194304256001224485120x7f58004a44800x7f57fd424a403051093051096553620971523098703460820417520340600296175203405629191752034094644017520340948217
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134217839217839419430425600824494720x7f58004a43000x7f57fd424a801670671670676553621626883182443561648817520340983536175203409464401752034124260017520341244349
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001372178392178394194304256001224506880x7f58004a41800x7f57fd424ac01693751693756553626214403903384370414817520341280708175203412426001752034154148117520341543182
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001402178392178394194304256001224516480x7f58004a40000x7f57fd424b001652371652376553619660802922163272735217520341586191175203415414811752034183556117520341837454
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001432178392178394194304256001224528640x7f57fde0de800x7f57fd424b403085573085576553623592963896294359279217520341872473175203418355611752034221812217520342220004
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001462178392178394194304256001224540800x7f57fde0dd000x7f57fd424b803064443064446553622282243284363686859217520342254653175203422181221752034261412317520342616014
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149217839217839419430425600824552960x7f57fde0db800x7f57fd424bc01669971669976553622937603401343809353217520342650113175203426141231752034291412317520342915966
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001522178392178394194304256001224567680x7f57fde0da000x7f57fd424c001718381718386553627525124053764535992417520342950456175203429141231752034321812417520343219619
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001552178392178394194304256001224577280x7f57fde0d8800x7f57fd424c401666131666136553620316163083653449428017520343261508175203432181241752034350532417520343506891
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001582178392178394194304256001224589440x7f57fde0d7000x7f57fd424c803092163092166553624903683678874122706817520343542300175203435053241752034387492517520343876392
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001612178392178394194304256001224601600x7f58004a45800x7f57fd424cc03057333057336553623592963521563957321617520343911391175203438749251752034424244517520344243902
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164217839217839419430425600824613760x7f58004a44000x7f57fd424d001687041687046553624248323668194100053617520344279511175203442424451752034452868617520344530235
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001672178392178394194304256001224628480x7f58004a42800x7f57fd424d401719611719616553629491204452024988103217520344565104175203445286861752034481476617520344816448
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001702178392178394194304256001224638080x7f58004a41000x7f57fd424d801680291680296553621626883212053598312417520344859007175203448147661752034510724717520345108860
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001732178392178394194304256001224650240x7f57fde0df800x7f57fd424dc03032793032796553626214403876234345976817520345145429175203451072471752034547236817520345474061
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001762178392178394194304256001224662400x7f57fde0de000x7f57fd424e003041313041316553624903683593694027508817520345508640175203454723681752034583892817520345840381
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179217839217839419430425600824674560x7f57fde0dc800x7f57fd424e401712231712236553625559043824054285136417520345874430175203458389281752034612436917520346125954
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001822178392178394194304256001224689280x7f57fde0db000x7f57fd424e801754751754756553631457284750765319652817520346161923175203461243691752034642212917520346423796
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001852178392178394194304256001224701440x7f57fde0d9800x7f57fd424ec01651851651856553622282243273683662028017520346465785175203464221291752034670949017520346711009
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001882178392178394194304256001224716160x7f57fde0d8000x7f57fd424f003047633047636553627525124202284709922817520346746598175203467094901752034707765117520347079250
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001912178392178394194304256001224728320x7f57fde0d6800x7f57fd424f403067693067696553626214403881784347770417520347113529175203470776511752034744693117520347448410
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194217839217839419430425600824740480x7f58004a45000x7f57fd424f801677951677956553626869763934954408018417520347481769175203474469311752034773237217520347734063
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001972178392178394194304256001224757760x7f58004a43800x7f57fd424fc01821771821776553633423365163875795162417520347769332175203477323721752034802581217520348027565
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002002178392178394194304256001224769920x7f58004a42000x7f57fd4250001669631669636553623592963602854035697617520348081994175203480258121752034831333317520348314868
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002032178392178394194304256001224784640x7f58004a40800x7f57fd4250403060883060886553628835844283744798615217520348350947175203483133331752034869781317520348699438
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002062178392178394194304256001224799360x7f57fde0df000x7f57fd4250803020653020656553626869763987574453225617520348735667175203486978131752034906533417520349066888
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209217839217839419430425600824814080x7f57fde0dd800x7f57fd4250c01705861705866553628180484258034771476417520349100858175203490653341752034935061517520349352281
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002122178392178394194304256001224831360x7f57fde0dc000x7f57fd4251001917311917316553635389445307355938799617520349387220175203493506151752034965061517520349652073
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002152178392178394194304256001224843520x7f57fde0da800x7f57fd4251401679621679626553624248323672514113189617520349694872175203496506151752034994277617520349944326
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002182178392178394194304256001224858240x7f57fde0d9000x7f57fd4251803073143073146553630146564554985107732417520349978625175203499427761752035033397617520350335656
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002212178392178394194304256001224872960x7f57fde0d7800x7f57fd4251c03023863023866553628180484182044678697617520350371515175203503339761752035071077717520350712296
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002242178392178394194304256001224887680x7f57fde0d6000x7f57fd4252001700521700526553629491204378834897857217520350746965175203507107771752035099669817520350998159
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002272178392178394194304256001224907520x7f58004a44800x7f57fd4252402017662017666553637355525625356308170817520351032768175203509966981752035130341817520351304931
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002302178392178394194304256001224919680x7f58004a43000x7f57fd4252801690161690166553625559043894174361584417520351348100175203513034181752035159109917520351592694
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002332178392178394194304256001224934400x7f58004a41800x7f57fd4252c03053363053366553631457284629765179588017520351628883175203515910991752035196181917520351963424
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002362178392178394194304256001224949120x7f58004a40000x7f57fd4253003031483031486553629491204330534849779217520351998924175203519618191752035233190017520352333725
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002392178392178394194304256001224963840x7f57fde0de800x7f57fd4253401693951693956553630801924575085129826817520352367574175203523319001752035261750017520352619008
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002422178392178394194304256001224983680x7f57fde0dd000x7f57fd4253802115162115166553639321606051016769937217520352654707175203526175001752035293558117520352936990
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002452178392178394194304256001224995840x7f57fde0db800x7f57fd4253c01685311685316553626214403913864393007217520352978669175203529355811752035323878217520353240382
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024821783921783941943042560012241013120x7f57fde0da000x7f57fd4254003043463043466553632768004866395442594017520353274321175203532387821752035360902217520353610742
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025121783921783941943042560012241027840x7f57fde0d8800x7f57fd4254403044233044236553630801924566145111008417520353646141175203536090221752035398102317520353982483
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025421783921783941943042560012241042560x7f57fde0d7000x7f57fd4254801692101692106553632112644712325280268417520354018492175203539810231752035427542317520354277095
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025721783921783941943042560012241062400x7f58004a45800x7f57fd4254c02200222200226553641287686202586941696817520354312544175203542754231752035459766417520354599157
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026021783921783941943042560012241077120x7f58004a44000x7f57fd4255001659461659466553627525124191674685773217520354642046175203545976641752035488246517520354883980
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026321783921783941943042560016241094400x7f58004a42800x7f57fd4255403027083027086553634078725020575635632417520354918439175203548824651752035525430517520355255890
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026621783921783941943042560016241111680x7f58004a41000x7f57fd4255803029453029456553632112644763165331027617520355291089175203552543051752035562742617520355628981
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002692178392178394194304256008241128960x7f57fde0df800x7f57fd4255c01681861681866553632768004949065544207217520355664660175203556274261752035591190617520355913553
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027221783921783941943042560012241151360x7f57fde0de000x7f57fd4256002300072300076553643253766590537376838417520355947742175203559119061752035623766717520356239235
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027521783921783941943042560012241166080x7f57fde0dc800x7f57fd4256401681621681626553628180484157044655432817520356282194175203562376671752035652310717520356524678
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027821783921783941943042560016241183360x7f57fde0db000x7f57fd4256803044593044596553635389445378826018003617520356559687175203565231071752035689574817520356897218
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028121783921783941943042560016241200640x7f57fde0d9800x7f57fd4256c03052323052326553634078725096615714085217520356931497175203568957481752035726710917520357268639
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028421783921783941943042560012241217920x7f57fde0d8000x7f57fd4257001673871673876553634078725168975786181617520357302178175203572671091752035755382917520357555361
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028721783921783941943042560012241240320x7f57fde0d6800x7f57fd4257402389772389776553645219846809427614271217520357589520175203575538291752035788311017520357884483
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029021783921783941943042560012241255040x7f58004a45000x7f57fd4257801688251688256553630146564524495071294817520357926532175203578831101752035816983017520358171355
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029321783921783941943042560012241274880x7f58004a43800x7f57fd4257c03038893038896553638010885662466338383217520358206944175203581698301752035855463117520358556255
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029621783921783941943042560012241292160x7f58004a42000x7f57fd4258003048833048836553636700165437416089742417520358591645175203585546311752035892711217520358928646
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029921783921783941943042560012241309440x7f58004a40800x7f57fd4258401719431719436553636700165737406426718417520358963495175203589271121752035921751217520359219008
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030221783921783941943042560012241334400x7f57fde0df000x7f57fd4258802590632590636553649152007400958280706817520359254778175203592175121752035956071317520359562260
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030521783921783941943042560012241349120x7f57fde0dd800x7f57fd4258c01683401683406553631457284698745266546817520359604879175203595607131752035984935317520359850902
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030821783921783941943042560012241368960x7f57fde0dc000x7f57fd4259002997492997496553640632326111156844071617520359885241175203598493531752036021847417520360220203
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031121783921783941943042560012241388800x7f57fde0da800x7f57fd4259403046763046766553639321605927986640601617520360254822175203602184741752036059543517520360597053
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031421783921783941943042560012241408640x7f57fde0d9000x7f57fd4259801782721782726553639321605943166673795217520360630972175203605954351752036089159517520360893245
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031721783921783941943042560012241436160x7f57fde0d7800x7f57fd4259c02811062811066553653084167966438919912417520360927465175203608915951752036124775617520361249286
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032021783921783941943042560012241453440x7f57fde0d6000x7f57fd425a001672901672906553633423365070915675441217520361291335175203612477561752036153271617520361534309
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032321783921783941943042560012241475840x7f58004a44800x7f57fd425a403025353025356553643253766712657512793217520361569098175203615327161752036190327717520361904799
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032621783921783941943042560012241495680x7f58004a43000x7f57fd425a803021783021786553641943046491467273303217520361939579175203619032771752036228071817520362282400
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032921783921783941943042560012241515520x7f58004a41800x7f57fd425ac01857321857326553641943046266257021426417520362318169175203622807181752036258231817520362583912
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033221783921783941943042560012241543040x7f58004a40000x7f57fd425b002991632991636553657016328563229600668017520362619301175203625823181752036294983917520362951523
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033521783921783941943042560012241562880x7f57fde0de800x7f57fd425b401724871724876553637355525507246174687617520362994072175203629498391752036323959917520363241185
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033821783921783941943042560012241587840x7f57fde0dd000x7f57fd425b803050873050876553648496647275038153958017520363275044175203632395991752036361320017520363614836
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034121783921783941943042560012241610240x7f57fde0db800x7f57fd425bc03013953013956553647185927148138006660017520363648685175203636132001752036398856117520363990146
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034421783921783941943042560012241632640x7f57fde0da000x7f57fd425c002067092067096553647185927098417949510817520364024685175203639885611752036429720117520364298718
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034721783921783941943042560012241665280x7f57fde0d8800x7f57fd425c4034151134151165536648806497661210939231217520364333237175203642972011752036469112217520364739447
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035021783921783941943042560012241685120x7f57fde0d7000x7f57fd425c801836411836416553641287686232526969609217520364758026175203646911221752036502392317520365025379
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035321783921783941943042560012241712640x7f58004a45800x7f57fd425cc03012913012916553653739528288169280840417520365061038175203650239231752036539656317520365398180
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035621783921783941943042560012241737600x7f58004a44000x7f57fd425d003024603024606553652428808368729369141217520365433149175203653965631752036577016417520365771730
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035921783921783941943042560012241762560x7f58004a42800x7f57fd425d402256042256046553652428807900438835829617520365806439175203657701641752036609240517520366094022
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036221783921783941943042560012241797760x7f58004a41000x7f57fd425d80381362381362655367274496110372112373294417520366129691175203660924051752036652168517520366544870
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036521783921783941943042560012241822720x7f57fde0df800x7f57fd425dc02114922114926553649152007304728179302417520366566140175203665216851752036684472617520366846263
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036821783921783941943042560012241855360x7f57fde0de000x7f57fd425e00305890305890655366422528101898511412500017520366880682175203668447261752036722440717520367244712
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037121783921783941943042560012241885440x7f57fde0dc800x7f57fd425e40312508312508655366291456102215111458700417520367260342175203672244071752036760872717520367629333
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037421783921783941943042560012241915520x7f57fde0db000x7f57fd425e8026704426704465536629145697045610867278017520367643542175203676087271752036796216817520367963724
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037721783921783941943042560012241958400x7f57fde0d9800x7f57fd425ec0462526462526655368847360134718415082176017520367998083175203679621681752036843704917520368458681
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038021783921783941943042560012241985920x7f57fde0d8000x7f57fd425f002436422436426553657016328592199621952017520368480861175203684370491752036878520917520368786673
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038321783921783941943042560012242023680x7f57fde0d6800x7f57fd425f40332968332968655367471104115307512915394417520368821232175203687852091752036918057017520369198132
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038621783921783941943042560012242058880x7f58004a45000x7f57fd425f80330644330644655367340032116138813010703217520369216302175203691805701752036957929117520369599112
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038921783921783941943042560012242094080x7f58004a43800x7f57fd425fc0306710306710655367340032112065012545020817520369616321175203695792911752036995705217520369958623
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039221783921783941943042560012242144640x7f58004a42000x7f57fd4260005426045426046553610420224161301018060641617520369993812175203699570521752037049097217520370536458
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039521783921783941943042560012242177280x7f58004a40800x7f57fd42604027290827290865536648806497732210946519217520370556387175203704909721752037088153317520370883069
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039821783921783941943042560012242220160x7f57fde0df000x7f57fd426080368444368444655368519680135527115182988017520370919538175203708815331752037129865417520371341257
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040121783921783941943042560012242260480x7f57fde0dd800x7f57fd4260c0368446368446655368388608130743814635952017520371351937175203712986541752037174633517520371788526
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040421783921783941943042560012242300800x7f57fde0dc000x7f57fd426100347031347031655368388608128834114432390817520371799425175203717463351752037217177517520372214175
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040721783921783941943042560012242359040x7f57fde0da800x7f57fd4261406244716244716553611993088181265920299414817520372225514175203721717751752037277385717520372816659
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041021783921783941943042560012242394240x7f57fde0d9000x7f57fd426180304639304639655367274496111054412439888817520372836359175203727738571752037318041717520373182090
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041321783921783941943042560012242442240x7f57fde0d7800x7f57fd4261c0398461398461655369568256152217317044610817520373217339175203731804171752037361817817520373660688
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041621783921783941943042560012242487680x7f57fde0d6000x7f57fd426200391987391987655369437184150208716819853617520373670837175203736181781752037407977917520374105056
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041921783921783941943042560012242533120x7f58004a44800x7f57fd426240388647388647655369437184147888516559448417520374116516175203740797791752037451882017520374563114
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004222178392178394194304256008242555520x7f58004a43000x7f57fd4262807188497188496553616056320230294525800769217520374574014175203745188201752037518618117520375229817
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042521783921783941943042560012242598400x7f58004a41800x7f57fd4262c0363013363013655368847360137277015381896417520375249347175203751861811752037562506217520375667406
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042821783921783941943042560012242656640x7f58004a40000x7f57fd4263004676584676586553611665408178859420033865217520375678916175203756250621752037613594317520376178313
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043121783921783941943042560012242712320x7f57fde0de800x7f57fd4263404709904709906553611468800180046820165440417520376189503175203761359431752037664746417520376689650
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004342178392178394194304256008242732160x7f57fde0dd000x7f57fd4263804845884845886553614090240201825022622552817520376700150175203766474641752037716842417520377211046
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004372178392178394194304256008242757120x7f57fde0db800x7f57fd4263c08806528806526553619202048275740730868540417520377223196175203771684241752037793914617520377981847
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044021783921783941943042560012242807680x7f57fde0da000x7f57fd4264004281764281766553610420224159431217848668417520378001176175203779391461752037842762717520378471924
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044321783921783941943042560012242876160x7f57fde0d8800x7f57fd4264405500125500126553613762560220475124696083617520378483484175203784276271752037899706817520379045459
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044621783921783941943042560012242942080x7f57fde0d7000x7f57fd4264805507705507706553613565952217665424379471617520379056909175203789970681752037956666917520379608835
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004492178392178394194304256008242969600x7f58004a45800x7f57fd4264c05643935643936553615466496223020324978202017520379620625175203795666691752038012955017520380171510
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004522178392178394194304256008242999680x7f58004a44000x7f57fd426500104141510414156553622347776320626035932182417520380182490175203801295501752038100187117520381044538
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004552178392178394194304256008243027200x7f58004a42800x7f57fd4265407220097220096553620250624291249532626860417520381063818175203810018711752038166251217520381704881
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045821783921783941943042560012243054720x7f58004a41000x7f57fd4265807231257231256553620447232296825933247096417520381715791175203816625121752038234363417520382389003
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046121783921783941943042560012243082240x7f57fde0df800x7f57fd4265c07211857211856553619595264281636931538595217520382400743175203823436341752038302587517520383070116
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004642178392178394194304256008243109760x7f57fde0de000x7f57fd4266007258737258736553620381696293357032855937617520383080966175203830257081752038369242917520383738569
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004672178392178394194304256008243132160x7f57fde0dc800x7f57fd426640136993113699316553631522816452227350647458417520383750019175203836924291752038478411017520384826991
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004702178392178394194304256008243159680x7f57fde0db000x7f57fd426680137112813711286553638993920558819762586186417520384847620175203847841101752038585227217520385915883
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047321783921783941943042560012243187200x7f57fde0d9800x7f57fd4266c0137392713739276553639124992561203162845408417520385926193175203858522721752038698139317520387046634
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047621783921783941943042560012243214720x7f57fde0d8000x7f57fd426700137189013718906553638469632552184661853504417520387057974175203869813931752038809995517520388166465
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004792178392178394194304256008243242240x7f57fde0d6800x7f57fd426740137660113766016553639059456559644362677628417520388177485175203880999551752038921259717520389278847
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004822178392178394194304256008243264640x7f58004a45000x7f57fd426780266326826632686553660489728865156396896241217520389289916175203892125971752039117243917520391243806
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004852178392178394194304256008243292160x7f58004a43800x7f57fd4267c026712342671234655367726694411054530123826746417520391264086175203911724391752039310492217520393171477
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048821783921783941943042560012243319680x7f58004a42000x7f57fd42680026710982671098655367739801611072124124019984817520393183276175203931049221752039508380517520395154766
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049121783921783941943042560012243347200x7f58004a40800x7f57fd42684026717582671758655367621836810917710122251628817520395166895175203950838051752039707148817520397142415
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004942178392178394194304256008243374720x7f57fde0df000x7f57fd42688026726082672608655367733248011064213123908943217520397154434175203970714881752039900941117520399079685
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049721783921783941943042560082400x7f57fde0dd800x7f57fd4268c0525771852577186553612025856017191459192579838417520399092345175203990094111752040263165617520402704062