Fichiers
rocm-systems/tests/workloads/LDS/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.kd000885840885845335544322560083264640x00x7fef7d404180104857611091777141910125212075644913284723120756451569912301207564515731938812075645157431910
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00288584088584532768256002424124800x00x7fef7d43510040961044991338695212075645172226194120756451725328281207564517253906812075645172547591
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0048858408858454194304256002424129280x7ff088fa99000x7fef7d43514052428812304897157500653212075645172600981120756451728232261207564517295538612075645172958906
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0068858408858454194304256003624136320x7ff088fa98000x7fef7d43518052428813709515175479076412075645173031190120756451732032241207564517345362312075645173524808
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0088858408858454194304256002824140800x7ff088fa97000x7fef7d4351c052428813790784176520612012075645173556747120756451737462611207564517399890012075645174068027
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00108858408858454194304256002424145280x7ff088fa96000x7fef7d43520052428812084573154671630812075645174093474120756451742832191207564517441649812075645174419931
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00128858408858454194304256002424149760x7ff088fa95000x7fef7d43524052428810885084139326649612075645174468662120756451746470571207564517478433612075645174787604
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00148858408858454194304256002424154240x7ff088fa94000x7fef7d43528052428813684854175174122412075645174866982120756451750464151207564517517185412075645175175575
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00168858408858454194304256002824161280x7ff088fa93000x7fef7d4352c052428814320446183297141212075645175224627120756451754028931207564517565825112075645175703396
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00188858408858454194304256002824168320x7ff088fa9a000x7fef7d43530052428813577912173794806812075645175730947120756451759115301207564517616608912075645176210449
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00208858408858454194304256002424175360x7ff088fa99000x7fef7d43534052428812013311153769850012075645176235014120756451764337671207564517656560712075645176568845
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00228858408858454194304256002424182400x7ff088fa98000x7fef7d43538052428812097841154841701612075645176617976120756451767926461207564517692528512075645176928663
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00248858408858454194304256002424189440x7ff088fa97000x7fef7d4353c052428812109940155008006412075645176994676120756451771736041207564517730544312075645177308810
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00268858408858454194304256002824199040x7ff088fa96000x7fef7d43540052428814351074183692003212075645177357370120756451775334421207564517778848012075645177858782
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00288858408858454194304256002824206080x7ff088fa95000x7fef7d43544052428814404220184370588012075645177888247120756451780759991207564517833007712075645178399276
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00308858408858454194304256002424213120x7ff088fa94000x7fef7d43548052428812637489161758342812075645178427449120756451786121561207564517874319512075645178746231
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00328858408858454194304256002424220160x7ff088fa93000x7fef7d4354c052428812095186154821612012075645178794511120756451789719941207564517910447312075645179108244
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00348858408858454194304256002424227200x7ff088fa9a000x7fef7d43550052428812880363164865006812075645179169558120756451793372721207564517946751212075645179470567
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00368858408858454194304256002824236800x7ff088fa99000x7fef7d43554052428814302913183070215212075645179522233120756451796854301207564517993710912075645180011893
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00388858408858454194304256002824243840x7ff088fa98000x7fef7d43558052428814063051180008140012075645180037371120756451802275081207564518048318612075645180552438
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00408858408858454194304256002424250880x7ff088fa97000x7fef7d4355c052428812857888164583131212075645180578817120756451807620651207564518089086412075645180893843
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00428858408858454194304256002424257920x7ff088fa96000x7fef7d43560052428811138856142582824812075645180941732120756451811147031207564518125134212075645181254433
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00448858408858454194304256002424264960x7ff088fa95000x7fef7d43564052428812671085162193064012075645181315155120756451814817411207564518161070012075645181613831
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00468858408858454194304256002824277120x7ff088fa94000x7fef7d43568052428814239133182259106812075645181661409120756451818329391207564518208941812075645182159174
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00488858408858454194304256002824284160x7ff088fa93000x7fef7d4356c052428813556150173514606812075645182187356120756451823730961207564518262589512075645182695361
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00508858408858454194304256002424291200x7ff088fa9a000x7fef7d43570052428812559801160761685612075645182721379120756451829017341207564518303165312075645183034791
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00528858408858454194304256002424300800x7ff088fa99000x7fef7d43574052428811959282153075426012075645183084193120756451832542121207564518338717112075645183390312
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00548858408858454194304256002424307840x7ff088fa98000x7fef7d43578052428812424861159034700412075645183448961120756451836146901207564518374588912075645183748818
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00568858408858454194304256002824320000x7ff088fa97000x7fef7d4357c052428813535868173260301212075645183796818120756451839738881207564518426172712075645184332273
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00588858408858454194304256002824329600x7ff088fa96000x7fef7d43580052428814245448182344995212075645184356067120756451845439651207564518479836412075645184867537
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00608858408858454194304256002424339200x7ff088fa95000x7fef7d43584052428813197897168928982412075645184893436120756451850740421207564518520188212075645185204955
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00628858408858454194304256002424348800x7ff088fa94000x7fef7d43588052428811196713143324355212075645185253284120756451854289201207564518556588012075645185568871
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00648858408858454194304256002424358400x7ff088fa93000x7fef7d4358c052428812211018156299659612075645185629854120756451857943591207564518592635812075645185929341
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00668858408858454194304256002824373120x7ff088fa9a000x7fef7d43590052428813726886175705029212075645185977871120756451861564371207564518641387512075645186483350
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00688858408858454194304256002824382720x7ff088fa99000x7fef7d43594052428814272145182682468412075645186510942120756451866906741207564518697979212075645187025107
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00708858408858454194304256002424392320x7ff088fa98000x7fef7d43598052428811227562143717480012075645187051276120756451872353111207564518737099012075645187374246
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00728858408858454194304256002424401920x7ff088fa97000x7fef7d4359c052428812116672155087403612075645187422776120756451875983491207564518773114812075645187734446
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00748858408858454194304256002424411520x7ff088fa96000x7fef7d435a0052428811448392146548380012075645187795820120756451879629871207564518809610712075645188099454
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00768858408858454194304256002824426240x7ff088fa95000x7fef7d435a4052428813673652175024694812075645188148665120756451883250651207564518858650412075645188656239
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00788858408858454194304256002824435840x7ff088fa94000x7fef7d435a8052428813897464177891271212075645188683028120756451888641031207564518911690112075645189187466
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00808858408858454194304256002424445440x7ff088fa93000x7fef7d435ac052428813504623172860381612075645189214907120756451893975401207564518952409912075645189527317
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00828858408858454194304256002424457600x7ff088fa9a000x7fef7d435b0052428811348240145265575612075645189576298120756451897456981207564518988201712075645189885263
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00848858408858454194304256002424467200x7ff088fa99000x7fef7d435b4052428811878374152028931612075645189945945120756451901189761207564519025193512075645190255371
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00868858408858454194304256002824484480x7ff088fa98000x7fef7d435b8052428813248991169589170412075645190304712120756451904765741207564519074297312075645190787720
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00888858408858454194304256002824494080x7ff088fa97000x7fef7d435bc052428814213555181933848812075645190813147120756451909943311207564519124281012075645191313477
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00908858408858454194304256002424503680x7ff088fa96000x7fef7d435c0052428810678712136683466412075645191331490120756451915260091207564519166296812075645191666303
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00928858408858454194304256002424515840x7ff088fa95000x7fef7d435c4052428811346087145243412412075645191714332120756451918876071207564519202360612075645192027274
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00948858408858454194304256002424525440x7ff088fa94000x7fef7d435c8052428812700137162555453612075645192088177120756451922562451207564519238584412075645192388865
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00968858408858454194304256002824542720x7ff088fa93000x7fef7d435cc052428813076621167384106412075645192436314120756451926109631207564519288136212075645192949808
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00988858408858454194304256002824554880x7ff088fa9a000x7fef7d435d0052428813953176178600790012075645192975806120756451931642401207564519341735912075645193487878
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001008858408858454194304256002424567040x7ff088fa99000x7fef7d435d4052428811603707148524343212075645193513335120756451936946371207564519382887712075645193831857
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001028858408858454194304256002424581760x7ff088fa98000x7fef7d435d805242889732312124561714412075645193879686120756451940517551207564519419047512075645194193499
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001048858408858454194304256002424593920x7ff088fa97000x7fef7d435dc052428812751889163220002412075645194253170120756451944261541207564519455671312075645194559950
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001068858408858454194304256002824613760x7ff088fa96000x7fef7d435e0052428814242465182311928812075645194611737120756451947803921207564519504199012075645195112437
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001088858408858454194304256002824625920x7ff088fa95000x7fef7d435e4052428813520350173054417612075645195137293120756451953245491207564519557830812075645195647482
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001108858408858454194304256002424638080x7ff088fa94000x7fef7d435e8052428812459136159481520412075645195674161120756451958554261207564519598678512075645195989908
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001128858408858454194304256002424652800x7ff088fa93000x7fef7d435ec05242889131356116886823612075645196037556120756451962162241207564519635606312075645196359385
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001148858408858454194304256002424664960x7ff088fa9a000x7fef7d435f0052428811490821147072017212075645196419336120756451965858221207564519672022212075645196723301
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001168858408858454194304256002824684800x7ff088fa99000x7fef7d435f4052428812972199166044460812075645196770449120756451969432601207564519721301912075645197283211
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001188858408858454194304256002824696960x7ff088fa98000x7fef7d435f8052428813705339175426191612075645197308288120756451974926981207564519775157612075645197820931
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001208858408858454194304256002424709120x7ff088fa97000x7fef7d435fc052428812947452165725988012075645197846568120756451980346151207564519816421412075645198167675
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001228858408858454194304256002424723840x7ff088fa96000x7fef7d436000524288667388885429823612075645198214172120756451983922131207564519853125212075645198534317
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001248858408858454194304256002424736000x7ff088fa95000x7fef7d43604052428811959314153069741212075645198594949120756451987595711207564519889317012075645198896179
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001268858408858454194304256002824758400x7ff088fa94000x7fef7d43608052428813331839170647497612075645198943768120756451991259691207564519939492812075645199464585
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001288858408858454194304256002824770560x7ff088fa93000x7fef7d4360c052428813792765176542412012075645199489241120756451996746061207564519993316512075645199977579
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001308858408858454194304256002424782720x7ff088fa9a000x7fef7d43610052428811139404142586971212075645199999339120756452001941231207564520033060312075645200334021
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001328858408858454194304256002424800000x7ff088fa99000x7fef7d436140524288703026089985926412075645200380978120756452005520421207564520069572112075645200698879
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001348858408858454194304256002424812160x7ff088fa98000x7fef7d43618052428812182484155930584812075645200758390120756452009250001207564520105635912075645201060031
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001368858408858454194304256002824834560x7ff088fa97000x7fef7d4361c052428813440123172027754012075645201107138120756452012832381207564520155315612075645201603811
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001388858408858454194304256002824849280x7ff088fa96000x7fef7d43620052428813726690175706266812075645201629729120756452018101151207564520206835412075645202119920
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001408858408858454194304256002424864000x7ff088fa95000x7fef7d43624052428811089866141949861612075645202148083120756452023286721207564520246515212075645202468338
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001428858408858454194304256002424881280x7ff088fa94000x7fef7d436280524288643612782375714412075645202517549120756452026824301207564520283267012075645202836131
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001448858408858454194304256002424896000x7ff088fa93000x7fef7d4362c052428811122944142366534012075645202915359120756452030851481207564520321986812075645203223090
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001468858408858454194304256002824920960x7ff088fa9a000x7fef7d43630052428812773487163500860412075645203270298120756452034454671207564520371170512075645203762313
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001488858408858454194304256002824935680x7ff088fa99000x7fef7d43634052428813489940172664671212075645203784814120756452039675441207564520422370212075645204275927
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001508858408858454194304256002424950400x7ff088fa98000x7fef7d43638052428811719072149995762012075645204299601120756452044848211207564520461938012075645204622531
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001528858408858454194304256002424967680x7ff088fa97000x7fef7d4363c0524288481010561573368412075645204669028120756452048393791207564520499697812075645205004982
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001548858408858454194304256002424982400x7ff088fa96000x7fef7d43640052428810875951139209588012075645205061647120756452052313771207564520536929612075645205372635
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015688584088584541943042560028241007360x7ff088fa95000x7fef7d43644052428812485136159804438812075645205418881120756452055942551207564520586273412075645205913430
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015888584088584541943042560028241022080x7ff088fa94000x7fef7d43648052428814211733181913433612075645205940521120756452061273731207564520638113112075645206432785
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016088584088584541943042560024241036800x7ff088fa93000x7fef7d4364c052428811727014150098553212075645206458724120756452066416101207564520677632912075645206779550
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016288584088584541943042560024241056640x7ff088fa9a000x7fef7d436500524288427015554659026812075645206827489120756452070048081207564520717008712075645207173692
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016488584088584541943042560024241071360x7ff088fa99000x7fef7d43654052428811610096148612280012075645207234255120756452074019261207564520753600512075645207539472
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016688584088584541943042560028241098880x7ff088fa98000x7fef7d4365805242889904120126768339212075645207586620120756452077584041207564520802576312075645208077502
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016888584088584541943042560028241113600x7ff088fa97000x7fef7d4365c052428813254795169654507612075645208101166120756452082888011207564520854400012075645208594563
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017088584088584541943042560024241128320x7ff088fa96000x7fef7d43660052428811626378148826826812075645208620471120756452088107191207564520894527812075645208948591
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017288584088584541943042560024241148160x7ff088fa95000x7fef7d436640524288376516648187755212075645208996079120756452091694371207564520934351612075645209347072
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017488584088584541943042560024241162880x7ff088fa94000x7fef7d43668052428811073357141731421212075645209407113120756452095729551207564520970959412075645209713052
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017688584088584541943042560028241190400x7ff088fa93000x7fef7d4366c0524288781299499995943612075645209762644120756452099300731207564521019343112075645210221306
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017888584088584541943042560028241207680x7ff088fa9a000x7fef7d43670052428813623122174378605612075645210264106120756452104292701207564521068542912075645210710515
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018088584088584541943042560024241224960x7ff088fa99000x7fef7d43674052428811646896149076786412075645210751011120756452109143881207564521104830712075645211052000
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018288584088584541943042560024241247360x7ff088fa98000x7fef7d436780524288346830344401780812075645211102354120756452112759861207564521145966512075645211465819
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018488584088584541943042560024241264640x7ff088fa97000x7fef7d4367c052428810875248139206738812075645211522444120756452116839841207564521182286312075645211826099
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018688584088584541943042560020241279360x7ff088fa96000x7fef7d436800524288424620854354232012075645211872435120756452120575821207564521232318012075645212350954
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018888584088584541943042560028241296640x7ff088fa95000x7fef7d43684052428814204410181814985612075645212391910120756452125583791207564521281517812075645212840865
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019088584088584541943042560024241313920x7ff088fa94000x7fef7d43688052428812648936161900866412075645212882121120756452130529361207564521318429612075645213187829
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019288584088584541943042560024241336320x7ff088fa93000x7fef7d4368c0524288354079045325272812075645213235648120756452134098951207564521363741312075645213663453
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019488584088584541943042560024241353600x7ff088fa9a000x7fef7d43690052428811348122145252534812075645213718125120756452138834921207564521401917112075645214022921
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019688584088584541943042560020241368320x7ff088fa99000x7fef7d436940524288287328136774830412075645214072303120756452142497301207564521453308912075645214559098
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019888584088584541943042560028241385600x7ff088fa98000x7fef7d43698052428814053918179889175612075645214597179120756452147612471207564521501340612075645215041134
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020088584088584541943042560024241402880x7ff088fa97000x7fef7d4369c052428810556977135139857612075645215082701120756452152487651207564521538796412075645215391244
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020288584088584541943042560024241427840x7ff088fa96000x7fef7d436a00524288354389145355647212075645215439003120756452156116431207564521582236212075645215847943
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020488584088584541943042560024241447680x7ff088fa95000x7fef7d436a4052428810915457139712403212075645215901302120756452160727611207564521621052012075645216214304
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020688584088584541943042560020241457280x7ff088fa94000x7fef7d436a80524288258633033099364412075645216263736120756452164383591207564521674539712075645216771419
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020888584088584541943042560028241477120x7ff088fa93000x7fef7d436ac052428814208642181867803612075645216812957120756452169778761207564521723131512075645217261360
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021088584088584541943042560024241496960x7ff088fa9a000x7fef7d436b0052428810198050130535487212075645217300783120756452174636331207564521760315312075645217606391
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021288584088584541943042560024241521920x7ff088fa99000x7fef7d436b40524288342769343869210012075645217652998120756452178244321207564521805131012075645218078609
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021488584088584541943042560024241541760x7ff088fa98000x7fef7d436b8052428810389941132987627212075645218138730120756452183082691207564521844714812075645218450380
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021688584088584541943042560020241556480x7ff088fa97000x7fef7d436bc0524288245779231460921212075645218496555120756452186714671207564521900218512075645219029175
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021888584088584541943042560028241576320x7ff088fa96000x7fef7d436c0052428812337300157917555612075645219072746120756452192397841207564521950394312075645219529485
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022088584088584541943042560024241596160x7ff088fa95000x7fef7d436c4052428810749350137595364012075645219568668120756452197308221207564521986922112075645219872573
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022288584088584541943042560024241623680x7ff088fa94000x7fef7d436c80524288340173843537543612075645219923467120756452201016741207564522034615312075645220378984
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022488584088584541943042560024241646080x7ff088fa93000x7fef7d436cc05242889626985123219196812075645220423166120756452205896711207564522073223012075645220734535
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022688584088584541943042560020241663360x7ff088fa9a000x7fef7d436d00524288241072030863519212075645220783416120756452209579891207564522135910812075645221387999
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022888584088584541943042560028241685760x7ff088fa99000x7fef7d436d4052428813787159176474056012075645221428174120756452215963871207564522185910612075645221883159
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023088584088584541943042560024241708160x7ff088fa98000x7fef7d436d805242889924538127023068812075645221924246120756452220943051207564522223126412075645222233871
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023288584088584541943042560024241740800x7ff088fa97000x7fef7d436dc0524288339092243410523212075645222282081120756452224578231207564522273670212075645222757605
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023488584088584541943042560024241765760x7ff088fa96000x7fef7d436e005242888054434103095147612075645222810262120756452229760611207564522311686112075645223119567
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023688584088584541943042560020241777920x7ff088fa95000x7fef7d436e40524288236571930275301612075645223160093120756452233443801207564522376949812075645223795002
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023888584088584541943042560028241802880x7ff088fa94000x7fef7d436e8052428811177676143074491612075645223828455120756452239962181207564522426549712075645224294140
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024088584088584541943042560024241827840x7ff088fa93000x7fef7d436ec05242888088183103536130012075645224326370120756452245147761207564522465365512075645224656023
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024288584088584541943042560024241863040x7ff088fa9a000x7fef7d436f00524288338344143321760012075645224701968120756452248730141207564522518757312075645225217135
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024488584088584541943042560024241893120x7ff088fa99000x7fef7d436f40524288388285049709605612075645225267148120756452254371721207564522558965112075645225592132
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024688584088584541943042560020241907840x7ff088fa98000x7fef7d436f80524288230833529522310812075645225638388120756452258221311207564522633940912075645226365209
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024888584088584541943042560028241937920x7ff088fa97000x7fef7d436fc0524288722204592445199612075645226408560120756452265800481207564522687796612075645226901466
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025088584088584541943042560024241968000x7ff088fa96000x7fef7d437000524288339378743432850412075645226942662120756452271045261207564522725940512075645227261885
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025288584088584541943042560024242010880x7ff088fa95000x7fef7d437040524288346244444320044812075645227309223120756452274966841207564522788244312075645227907936
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025488584088584541943042560024242046080x7ff088fa94000x7fef7d437080524288332153342503142412075645227960724120756452281366821207564522831348112075645228315904
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025688584088584541943042560020242060800x7ff088fa93000x7fef7d4370c0524288234904730056050812075645228363593120756452285520401207564522916195812075645229189117
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025888584088584541943042560028242096000x7ff088fa9a000x7fef7d437100524288394644350522490412075645229228330120756452293953971207564522975075512075645229775176
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026088584088584541943042560024242131200x7ff088fa99000x7fef7d437140524288326537141793112012075645229825640120756452299934741207564523017187412075645230174138
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026288584088584541943042560024242181760x7ff088fa98000x7fef7d437180524288399289251096908412075645230215965120756452304046731207564523086067112075645230887704
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026488584088584541943042560024242222080x7ff088fa97000x7fef7d4371c0524288321816241179919612075645230944910120756452311184301207564523131842912075645231346607
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026688584088584541943042560020242239360x7ff088fa96000x7fef7d437200524288230416829486250412075645231378286120756452315569881207564523226034612075645232286093
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026888584088584541943042560028242279680x7ff088fa95000x7fef7d437240524288370022047364601612075645232329574120756452324966651207564523289458312075645232918939
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027088584088584541943042560024242320000x7ff088fa94000x7fef7d437280524288327990141995700012075645232960346120756452331337821207564523333634212075645233364757
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027288584088584541943042560024242378240x7ff088fa93000x7fef7d4372c0524288430904955159049612075645233408919120756452335753811207564523410161912075645234128236
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027488584088584541943042560024242423680x7ff088fa9a000x7fef7d437300524288305732339136825612075645234187026120756452343564981207564523457953712075645234603740
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027688584088584541943042560020242435840x7ff088fa99000x7fef7d437340524288233785029918501212075645234645247120756452348108961207564523561105312075645235661816
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027888584088584541943042560028242481280x7ff088fa98000x7fef7d437380524288360529346139892012075645235685701120756452358737721207564523629425012075645236348603
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028088584088584541943042560024242526720x7ff088fa97000x7fef7d4373c0524288311764539899532012075645236372958120756452365585691207564523678688812075645236835848
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028288584088584541943042560024242592640x7ff088fa96000x7fef7d437400524288478324261222285212075645236860945120756452370547271207564523765120512075645237701798
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028488584088584541943042560024242648320x7ff088fa95000x7fef7d437440524288329255042128652412075645237737474120756452379152041207564523818480312075645238234548
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028688584088584541943042560020242663040x7ff088fa94000x7fef7d437480524288232022329698128412075645238261638120756452384480021207564523943391812075645239502374
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028888584088584541943042560028242718720x7ff088fa93000x7fef7d4374c0524288329429542157100812075645239529414120756452397183971207564524024831512075645240317920
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029088584088584541943042560024242774400x7ff088fa9a000x7fef7d437500524288332451542535857612075645240349498120756452405385541207564524081135312075645240855088
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029288584088584541943042560012242799360x7ff088fa99000x7fef7d437540524288222001428417812012075645240877429120756452411420711207564524188046912075645241988825
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029488584088584541943042560024242865280x7ff088fa98000x7fef7d437580524288330600242326290012075645242039259120756452425810261207564524289734512075645242969597
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029688584088584541943042560020242880000x7ff088fa97000x7fef7d4375c0524288227518529114839212075645243031482120756452433005431207564524447269912075645244543372
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029888584088584541943042560032242945920x7ff088fa96000x7fef7d437600524288320552741030583212075645244598435120756452448418171207564524545029512075645245520148
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030088584088584541943042560024243011840x7ff088fa95000x7fef7d437640524288334001442755083612075645245574519120756452458254931207564524614645212075645246216261
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030288584088584541943042560012243049600x7ff088fa94000x7fef7d437680524288222248428450306812075645246277936120756452465309311207564524740964712075645247479569
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030488584088584541943042560024243136000x7ff088fa93000x7fef7d4376c0524288329978642249052412075645247557925120756452478002061207564524823332412075645248304152
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030688584088584541943042560020243148160x7ff088fa9a000x7fef7d437700524288230382929501593212075645248357891120756452486014831207564525015027712075645250220914
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030888584088584541943042560020243175680x7ff088fa99000x7fef7d437740524288228746829291369612075645250273101120756452505259551207564525132115212075645251391690
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031088584088584541943042560012243203200x7ff088fa98000x7fef7d437780524288215913627645379612075645251443225120756452516944311207564525210882912075645252178883
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031288584088584541943042560012243240960x7ff088fa97000x7fef7d4377c0524288224234628687724012075645252232051120756452524838681207564525364322312075645253713515
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031488584088584541943042560012243288960x7ff088fa96000x7fef7d437800524288228232729196055612075645253790267120756452540400221207564525482577912075645254897204
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031688584088584541943042560020243301120x7ff088fa95000x7fef7d437840524288269739234533602012075645254951686120756452551998571207564525825056612075645258321609
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031888584088584541943042560020243328640x7ff088fa94000x7fef7d437880524288232535629742953212075645258375709120756452586180841207564526015871812075645260229595
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032088584088584541943042560012243356160x7ff088fa93000x7fef7d4378c0524288217726827870126812075645260285649120756452605355171207564526132367412075645261394229
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032288584088584541943042560012243393920x7ff088fa9a000x7fef7d437900524288249370231912183212075645261446436120756452616963121207564526397790312075645264048382
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032488584088584541943042560012243441920x7ff088fa99000x7fef7d437940524288237265730371703612075645264124152120756452643671821207564526590253612075645265971956
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032688584088584541943042560020243454080x7ff088fa98000x7fef7d437980524288291696437337191212075645266036466120756452662764551207564527233211112075645272401866
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032888584088584541943042560020243481600x7ff088fa97000x7fef7d4379c0524288318813040817450012075645272455376120756452727109901207564527575433812075645275824988
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033088584088584541943042560012243509120x7ff088fa96000x7fef7d437a00524288248819731852500012075645275877606120756452761460171207564527768505112075645277755425
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332885840885845419430425600122400x7ff088fa95000x7fef7d437a40524288257119932901868012075645277807943120756452780589691207564528258583212075645282656103