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

48 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjGRBM_COUNTGRBM_GUI_ACTIVECPC_ME1_BUSY_FOR_PACKET_DECODESQ_CYCLESSQ_WAVESSQ_WAVE_CYCLESSQ_BUSY_CYCLESSQ_LEVEL_WAVESSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000194332194332335544322560043241600x00x7fc390804280381340381340883430507285242882396052932963625097468061217125775589873171250687307761712592376109217125923874631
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00219433219433232768256001224138880x00x7fc390823f8033330333302986326664851217822761653750714276817125929027678171259237610921712592916796917125929172374
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051943321943324194304256001224143360x7fc3937bf3800x7fc390823fc016423516423513939131388865536804359301212523032347145617125929215982171259291679691712592956124917125929563653
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081943321943324194304256001624150400x7fc3937bf2000x7fc390824000308131308131239022465056655362274374162366838091147630017125929609812171259295612491712592999020917125929992501
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111943321943324194304256001624154880x7fc3937bf0800x7fc390824040308793308793227682470352655362167448402370791086870794417125930034760171259299902091712593043052917125930432689
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141943321943324194304256001224159360x7fc391191f000x7fc39082408016412116412112907131297665536749480471209804030152269617125930474637171259304305291712593076764917125930769699
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171943321943324194304256001224163840x7fc391191d800x7fc3908240c016365316365314159130923265536875231641210978035182142417125930809898171259307676491712593110476817125931106810
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201943321943324194304256001224170880x7fc391191c000x7fc390824100161993161993155161295952655361070507721199194042993014417125931161218171259311047681712593143292817125931435011
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231943321943324194304256001624177920x7fc391191a800x7fc390824140309379309379231102475040655362269693882375242090960514817125931475590171259314329281712593186716817125931869529
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261943321943324194304256001624184960x7fc3911919000x7fc390824180308213308213210762465712655362191582312363892087836169617125931910417171259318671681712593228780817125932289937
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291943321943324194304256001624192000x7fc3911917800x7fc3908241c016558916558915469132472065536990601011220646039796752017125932330036171259322878081712593261996817125932622018
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321943321943324194304256001624199040x7fc3911916000x7fc39082420016453016453015270131624865536935245031211989037582894817125932662227171259326199681712593295100817125932953168
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351943321943324194304256001224206080x7fc3937bf4800x7fc39082424016449916449914944131600065536988275271210804039703403617125933006067171259329510081712593328524817125933287399
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381943321943324194304256001624213120x7fc3937bf3000x7fc390824280310836310836243182486696655362290617452386426091797549217125933328958171259332852481712593370460817125933706877
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411943321943324194304256001624220160x7fc3937bf1800x7fc3908242c0307384307384216522459080655362210464442355255088591235217125933749066171259337046081712593412364817125934125886
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441943321943324194304256001624227200x7fc3937bf0000x7fc39082430016405016405014759131240865536877195751210641035261232017125934167545171259341236481712593447644717125934478806
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471943321943324194304256001224234240x7fc391191e800x7fc390824340163416163416150171307336655361078364751209452043307093617125934518745171259344764471712593479324717125934794997
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501943321943324194304256001224241280x7fc391191d000x7fc39082438016312616312614876130501665536944937311199380037969731617125934843466171259347932471712593509692717125935098389
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531943321943324194304256001624248320x7fc391191b800x7fc3908243c0308927308927242232471424655362316301672371682092824852417125935142518171259350969271712593548764717125935489378
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561943321943324194304256001624255360x7fc391191a000x7fc390824400306834306834213552454680655362193800532353205087925003617125935530957171259354876471712593587868717125935880237
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591943321943324194304256001224262400x7fc3911918800x7fc39082444016238816238814532129911265536967713301201417038881084417125935922306171259358786871712593617948717125936180989
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621943321943324194304256001224269440x7fc3911917000x7fc39082448016298616298614023130389665536879469971203291035351634417125936223208171259361794871712593648172717125936483371
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651943321943324194304256001224276480x7fc3937bf5800x7fc3908244c0162540162540144691300328655361013348291202343040707077617125936531719171259364817271712593678764717125936789212
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681943321943324194304256001624286080x7fc3937bf4000x7fc390824500305040305040237272440328655362120128632335008084978102817125936833541171259367876471712593717820717125937179881
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711943321943324194304256001624293120x7fc3937bf2800x7fc390824540306762306762209402454104655362135316132349729085585546417125937222860171259371782071712593757212717125937573840
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741943321943324194304256001224300160x7fc3937bf1000x7fc390824580161204161204144931289640655361022136921192834041058558017125937616529171259375721271712593787324617125937874992
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077194332194332419430425600824309760x7fc391191f800x7fc3908245c016222016222014832129776865536975048931195937039174570017125937916841171259378732461712593817596617125938177844
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801943321943324194304256001224316800x7fc391191e000x7fc39082460016240516240514302129924865536947992361198245038092265217125938227472171259381759661712593849468617125938496215
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831943321943324194304256001624326400x7fc391191c800x7fc390824640304323304323227452434592655362229674992331339089360494017125938538624171259384946861712593888924617125938890794
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861943321943324194304256001224336000x7fc391191b000x7fc390824680306200306200226852449608655362204145192347657088338561617125938932973171259388892461712593928076617125939282393
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891943321943324194304256001224345600x7fc3911919800x7fc3908246c0162903162903151601303232655361030074331203470041375566817125939323452171259392807661712593960028617125939601934
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092194332194332419430425600824355200x7fc3911918000x7fc39082470016322816322814832130583265536999744251207029040162038417125939643953171259396002861712593990364617125939905345
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951943321943324194304256001224362240x7fc3911916800x7fc39082474016181216181215003129450465536979625931191034039357448817125939952934171259399036461712594021116617125940212717
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981943321943324194304256001224371840x7fc3937bf5000x7fc390824780301681301681227992413456655362232749862312497089483127217125940259326171259402111661712594061468617125940616466
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011943321943324194304256001224381440x7fc3937bf3800x7fc3908247c0304538304538225972436312655362160731262337039086602203217125940656805171259406146861712594100364617125941005375
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041943321943324194304256001224391040x7fc3937bf2000x7fc39082480016178616178614113129429665536925865091195169037207891217125941046174171259410036461712594130860617125941310296
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107194332194332419430425600824403200x7fc3937bf0800x7fc39082484016321216321215036130570465536928239181201226037302396017125941352135171259413086061712594161468517125941616178
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101943321943324194304256001224412800x7fc391191f000x7fc390824880162423162423147661299392655361034264781199927041542558417125941664966171259416146851712594192316517125941924729
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131943321943324194304256001224422400x7fc391191d800x7fc3908248c0306696306696239192453576655362300679692352565092200063617125941966148171259419231651712594232428517125942325908
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161943321943324194304256001224432000x7fc391191c000x7fc390824900306657306657238882453264655362230557582346706089395727617125942366157171259423242851712594271772517125942719407
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119194332194332419430425600824441600x7fc391191a800x7fc39082494016198216198214717129586465536991548391196939039834185217125942759796171259427177251712594301996517125943021609
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221943321943324194304256001224453760x7fc3911919000x7fc39082498016159016159015041129272865536907678131188799036479814017125943062998171259430199651712594332492517125943326470
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251943321943324194304256001224463360x7fc3911917800x7fc3908249c016143416143413907129148065536973409521194568039108767217125943374659171259433249251712594363260517125943634112
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281943321943324194304256001224475520x7fc3911916000x7fc390824a00303827303827224962430624655362126194032325201085220808017125943675690171259436326051712594402092517125944022421
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311943321943324194304256001224485120x7fc3937bf4800x7fc390824a40302160302160213312417288655362104699712312130084360747217125944064130171259440209251712594440956517125944411080
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134194332194332419430425600824494720x7fc3937bf3000x7fc390824a8016113816113814536128911265536950122361189673038177750017125944452269171259444095651712594471164517125944713342
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371943321943324194304256001224506880x7fc3937bf1800x7fc390824ac016146316146315753129171265536963572141188044038716162417125944754970171259447116451712594501468417125945016153
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401943321943324194304256001224516480x7fc3937bf0000x7fc390824b0016080916080914396128648065536899340621185460036147242017125945065262171259450146841712594532140417125945322955
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431943321943324194304256001224528640x7fc391191e800x7fc390824b40305128305128242802441032655362243866572336721089927442817125945368753171259453214041712594572332417125945724983
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461943321943324194304256001224540800x7fc391191d000x7fc390824b80300035300035198692400288655362058148892294941082498863617125945768172171259457233241712594612060417125946122272
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149194332194332419430425600824552960x7fc391191b800x7fc390824bc0162731162731149021301856655361012755911199291040682359617125946163161171259461206041712594642780417125946429384
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521943321943324194304256001224567680x7fc391191a000x7fc390824c00162961162961154391303696655361028420471205134041310228817125946470083171259464278041712594673708417125946738755
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551943321943324194304256001224577280x7fc3911918800x7fc390824c4016206716206714843129654465536952794051195877038284405617125946786664171259467370841712594704284417125947044367
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581943321943324194304256001224589440x7fc3911917000x7fc390824c80303593303593229742428752655362239882102325002089768607217125947091505171259470428441712594744012417125947441686
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611943321943324194304256001224601600x7fc3937bf5800x7fc390824cc0300307300307208642402464655362151700182299894086240804417125947485814171259474401241712594783420417125947835665
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164194332194332419430425600824613760x7fc3937bf4000x7fc390824d0016232716232714427129862465536939833821201659037766793217125947878863171259478342041712594814028417125948141916
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671943321943324194304256001224628480x7fc3937bf2800x7fc390824d40168017168017161921344144655361070282361242516042984747217125948184265171259481402841712594845388317125948455277
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701943321943324194304256001224638080x7fc3937bf1000x7fc390824d8016063216063214497128506465536953527261187612038313299217125948505186171259484538831712594875356317125948755269
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731943321943324194304256001224650240x7fc391191f800x7fc390824dc0301754301754234282414040655362220436482310314088990953217125948800848171259487535631712594914828317125949149788
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761943321943324194304256001224662400x7fc391191e000x7fc390824e00300309300309216422402480655362140770532298861085803938817125949192447171259491482831712594953564317125949537277
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179194332194332419430425600824674560x7fc391191c800x7fc390824e4016261016261014505130088865536934819981199654037565315217125949577756171259495356431712594983804317125949839789
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821943321943324194304256001224689280x7fc391191b000x7fc390824e80175643175643163601405152655361062676141304364042681016017125949882718171259498380431712595015308317125950154680
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851943321943324194304256001224701440x7fc3911919800x7fc390824ec016060616060615049128485665536937614571184291037678054817125950203859171259501530831712595046380317125950465371
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881943321943324194304256001224716160x7fc3911918000x7fc390824f00302425302425229492419408655362220105112321865088976994017125950506350171259504638031712595085436317125950856031
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911943321943324194304256001224728320x7fc3911916800x7fc390824f40301255301255228342410048655362232637242313901089478266017125950897290171259508543631712595124284317125951244370
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194194332194332419430425600824740480x7fc3937bf5000x7fc390824f8016024316024314783128195265536912128781183471036658720417125951284919171259512428431712595154588317125951547452
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971943321943324194304256001224757760x7fc3937bf3800x7fc390824fc0181828181828171131454632655361100095811350382044178362017125951588810171259515458831712595186396217125951865453
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001943321943324194304256001224769920x7fc3937bf2000x7fc39082500016094316094314923128755265536928833921188959037326333617125951925371171259518639621712595216972217125952171474
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031943321943324194304256001224784640x7fc3937bf0800x7fc390825040301048301048231872408392655362142632652307682085878437617125952213353171259521697221712595256012217125952561673
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061943321943324194304256001224799360x7fc391191f000x7fc390825080299641299641222622397136655362192421482298804087869836417125952603162171259525601221712595295276217125952954283
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209194332194332419430425600824814080x7fc391191d800x7fc3908250c016257016257015174130056865536958594851198280038515966417125952994671171259529527621712595325452217125953256254
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121943321943324194304256001224831360x7fc391191c000x7fc390825100191402191402178561531224655361187900471425666047689975617125953296813171259532545221712595357676217125953578345
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151943321943324194304256001224843520x7fc391191a800x7fc39082514016049416049414549128396065536942323461186075037866114817125953626704171259535767621712595389148217125953893137
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181943321943324194304256001224858240x7fc3911919000x7fc390825180300925300925229182407408655362230694822310429089401408417125953934685171259538914821712595429420217125954295915
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211943321943324194304256001224872960x7fc3911917800x7fc3908251c0299793299793226632398352655362176603202299933087237008817125954336574171259542942021712595468764217125954689374
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241943321943324194304256001224887680x7fc3911916000x7fc39082520016182416182415743129460065536981470381187529039431493217125954728963171259546876421712595498876217125954990226
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271943321943324194304256001224907520x7fc3937bf4800x7fc390825240201973201973184901615792655361212168941501665048661529617125955030625171259549887621712595532124117125955323097
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301943321943324194304256001224919680x7fc3937bf3000x7fc39082528016119816119814588128959265536930673141189405037399579217125955372125171259553212411712595562444117125955625958
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331943321943324194304256001224934400x7fc3937bf1800x7fc3908252c0302414302414241882419320655362203338722314085088306852017125955667477171259556244411712595601452117125956016077
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361943321943324194304256001224949120x7fc3937bf0000x7fc390825300299438299438210132395512655362080371402292007083388153617125956059466171259560145211712595640412117125956405567
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391943321943324194304256001224963840x7fc391191e800x7fc39082534016138316138315156129107265536977924911191414039289998017125956446855171259564041211712595670796117125956709468
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421943321943324194304256001224983680x7fc391191d000x7fc390825380210364210364191041682920655361342803561572768053886179217125956750817171259567079611712595704188117125957043659
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451943321943324194304256001224995840x7fc391191b800x7fc3908253c016108416108415170128868065536924854441186314037167102017125957091508171259570418811712595735100117125957352470
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024819433219433241943042560012241013120x7fc391191a000x7fc390825400297326297326224022378616655362172580702277071087077056817125957393529171259573510011712595774412117125957745739
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025119433219433241943042560012241027840x7fc3911918800x7fc390825440298532298532221222388264655362121316842280139085025741617125957788308171259577441211712595813356117125958134998
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025419433219433241943042560012241042560x7fc3911917000x7fc39082548016002216002214919128018465536989961381182306039772688017125958176547171259581335611712595843996117125958441360
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025719433219433241943042560012241062400x7fc3937bf5800x7fc3908254c0219118219118189311752952655361425870451649553057209675617125958482599171259584399611712595878252017125958784130
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026019433219433241943042560012241077120x7fc3937bf4000x7fc39082550016002416002414741128020065536961998051180542038653684017125958833209171259587825201712595909404017125959095542
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026319433219433241943042560016241094400x7fc3937bf2800x7fc390825540297104297104211072376840655362101074782274308084216274017125959139321171259590940401712595948396017125959485431
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026619433219433241943042560016241111680x7fc3937bf1000x7fc390825580298133298133208392385072655362026457842279286081231500417125959526800171259594839601712595987500017125959876570
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691943321943324194304256008241128960x7fc391191f800x7fc3908255c0163249163249149991306000655361036063091205097041616345217125959917049171259598750001712596018796017125960189521
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027219433219433241943042560012241151360x7fc391191e000x7fc390825600228489228489194931827920655361540091801720796061778018017125960230690171259601879601712596053852017125960540092
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027519433219433241943042560012241166080x7fc391191c800x7fc39082564015986515986515059127892865536969118841179856038937154017125960587660171259605385201712596085516017125960856753
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027819433219433241943042560016241183360x7fc391191b000x7fc390825680296591296591211182372736655362132932602272586085490700417125960898152171259608551601712596124508017125961246612
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028119433219433241943042560016241200640x7fc3911919800x7fc3908256c0300603300603224582404832655362136463372301096085631614017125961289191171259612450801712596163772017125961639441
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028419433219433241943042560012241217920x7fc3911918000x7fc390825700162585162585153411300688655361018565141202977040915796817125961680040171259616377201712596194364017125961945182
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028719433219433241943042560012241240320x7fc3911916800x7fc390825740239943239943200121919552655361474162141808980059141442417125961985341171259619436401712596231147917125962313262
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029019433219433241943042560012241255040x7fc3937bf5000x7fc39082578016184016184016339129472865536977319611188624039265466017125962362501171259623114791712596261883917125962620484
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029319433219433241943042560012241274880x7fc3937bf3800x7fc3908257c0297462297462193282379704655361931985442280617077452932417125962666292171259626188391712596301259917125963014153
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029619433219433241943042560012241292160x7fc3937bf2000x7fc390825800296150296150203722369208655362046844312265713082047158817125963056132171259630125991712596340123917125963402762
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029919433219433241943042560012241309440x7fc3937bf0800x7fc390825840170340170340164261362728655361002554851261215040276501217125963443791171259634012391712596371147917125963713043
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030219433219433241943042560012241334400x7fc391191f000x7fc390825880258402258402207452067224655361681180601957558067421958417125963754262171259637114791712596407499917125964076583
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030519433219433241943042560012241349120x7fc391191d800x7fc3908258c016060016060015502128480865536977622681182505039277802817125964125922171259640749991712596437787917125964379345
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030819433219433241943042560012241368960x7fc391191c000x7fc390825900296344296344207312370760655362102343932269243084269550017125964421384171259643778791712596477387917125964775394
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031119433219433241943042560012241388800x7fc391191a800x7fc390825940294600294600210102356808655362044910452252118081970780817125964817253171259647738791712596516363917125965165183
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031419433219433241943042560012241408640x7fc3911919000x7fc390825980178542178542164401428344655361009076871321976040538144017125965205652171259651636391712596548011917125965481634
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031719433219433241943042560012241436160x7fc3911917800x7fc3908259c0280086280086226452240696655361918797612129699076926701617125965522483171259654801191712596585835817125965859914
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032019433219433241943042560012241453440x7fc3911916000x7fc390825a00160202160202154881281624655361009399181181745040549366017125965908123171259658583581712596616827817125966169895
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032319433219433241943042560012241475840x7fc3937bf4800x7fc390825a40295760295760213172366088655362115722632264263084802158017125966212864171259661682781712596656891817125966570384
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032619433219433241943042560012241495680x7fc3937bf3000x7fc390825a80293482293482209892347864655362104820972244928084366574017125966615463171259665689181712596696587817125966967353
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032919433219433241943042560012241515520x7fc3937bf1800x7fc390825ac0185492185492172671483944655361178586551380288047317620017125967007372171259669658781712596729067817125967292154
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033219433219433241943042560012241543040x7fc3937bf0000x7fc390825b00298558298558231972388472655362093669902282139083921636017125967333953171259672906781712596768059817125967682163
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033519433219433241943042560012241562880x7fc391191e800x7fc390825b40170260170260166041362088655361063327981262552042707242417125967731402171259676805981712596799243817125967994055
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033819433219433241943042560012241587840x7fc391191d000x7fc390825b80297942297942181492383544655361674884642258643067170009617125968036043171259679924381712596839019817125968391804
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034119433219433241943042560012241610240x7fc391191b800x7fc390825bc0296398296398192032371192655361901340472258794076228858417125968433612171259683901981712596878347817125968785163
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034419433219433241943042560012241632640x7fc391191a000x7fc390825c00205786205786184581646296655361295167481535560051982158817125968825861171259687834781712596911595817125969117423
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034719433219433241943042560012241665280x7fc3911918800x7fc390825c40339418339418253672715352655362402435352605951096272250817125969158032171259691159581712596953307717125969552721
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035019433219433241943042560012241685120x7fc3911917000x7fc390825c80184069184069171141472560655361056383201362405042429667617125969585390171259695330771712596987227717125969873792
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035319433219433241943042560012241712640x7fc3937bf5800x7fc390825cc0294168294168197822353352655361962443152247462078674199217125969914331171259698722771712597026523717125970266861
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035619433219433241943042560012241737600x7fc3937bf4000x7fc390825d00295818295818199042366552655361828681512260153073322197617125970309420171259702652371712597066187717125970663460
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035919433219433241943042560012241762560x7fc3937bf2800x7fc390825d40224364224364193321794920655361508507211690013060515102417125970704579171259706618771712597100859717125971010291
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036219433219433241943042560012241797760x7fc3937bf1000x7fc390825d803809123809122747730473046553626678472329295630106889890017125971051029171259710085971712597145371717125971475768
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036519433219433241943042560012241822720x7fc391191f800x7fc390825dc0211269211269185541690160655361319959431583293052973894417125971503527171259714537171712597179947717125971801419
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036819433219433241943042560012241855360x7fc391191e000x7fc390825e00305368305368228292442952655361888653692320780075721522817125971842717171259717994771712597220363717125972223407
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037119433219433241943042560012241885440x7fc391191c800x7fc390825e40304878304878228762439032655361652076372308200066258464017125972245726171259722036371712597261179717125972613426
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037419433219433241943042560012241915520x7fc391191b000x7fc390825e80264638264638212402117112655361884031362013214075536580017125972653475171259726117971712597298171617125972983276
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037719433219433241943042560012241958400x7fc3911919800x7fc390825ec04615654615653196236925286553634544389435779310138353661617125973024475171259729817161712597347787617125973495181
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038019433219433241943042560012241985920x7fc3911918000x7fc390825f00244408244408206471955272655361567813621845676062888652417125973528540171259734778761712597384283617125973844452
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038319433219433241943042560012242023680x7fc3911916800x7fc390825f40333021333021229572664176655362047723682548690082086227617125973890860171259738428361712597426971617125974292579
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038619433219433241943042560012242058880x7fc3937bf5000x7fc390825f80330782330782230992646264655362039901272519797081772678817125974312969171259742697161712597469339617125974737397
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038919433219433241943042560012242094080x7fc3937bf3800x7fc390825fc0305049305049232322440400655362171039592337920087016930817125974747627171259746933961712597511867617125975120256
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039219433219433241943042560012242144640x7fc3937bf2000x7fc3908260005412855412853541743302886553640514573642247820162234499217125975162225171259751186761712597566315617125975680181
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039519433219433241943042560012242177280x7fc3937bf0800x7fc390826040272535272535214952180288655361748483822073731070115477217125975714770171259756631561712597605083617125976052350
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039819433219433241943042560012242220160x7fc391191f000x7fc390826080364471364471248652915776655362359368502795363094552987617125976098529171259760508361712597649803517125976515067
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040119433219433241943042560012242260480x7fc391191d800x7fc3908260c03665013665012895329320166553625924115928234040103873396817125976541257171259764980351712597694123517125976959985
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040419433219433241943042560012242300800x7fc391191c000x7fc390826100346645346645252902773168655362491403702665386099832875217125976983494171259769412351712597736619517125977383213
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040719433219433241943042560012242359040x7fc391191a800x7fc3908261406228676228673968049829446553647166470048711580188842283217125977408832171259773661951712597796747517125977988206
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041019433219433241943042560012242394240x7fc3911919000x7fc390826180302629302629229142421040655362124995952315414085175624017125978018675171259779674751712597838267517125978384105
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041319433219433241943042560012242442240x7fc3911917800x7fc3908261c03972473972472659431779846553627302564130730800109387901617125978425774171259783826751712597884507517125978886911
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041619433219433241943042560012242487680x7fc3911916000x7fc3908262003896633896632773031173126553628725545130123860115079214017125978898391171259788450751712597932219517125979339789
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041919433219433241943042560012242533120x7fc3937bf4800x7fc3908262403870753870752746030966086553628035362029870710112318103617125979364728171259793221951712597977099417125979788066
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221943321943324194304256008242555520x7fc3937bf3000x7fc3908262807189157189154407257513286553653500957556384000214177846417125979813616171259797709941712598043291417125980449448
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042519433219433241943042560012242598400x7fc3937bf1800x7fc3908262c03637473637472621129099846553626173318428028080104870039217125980483677171259804329141712598087339417125980889516
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042819433219433241943042560012242656640x7fc3937bf0000x7fc3908263004689194689193136037513606553635560272836513960142419925217125980916625171259808733941712598138299417125981399562
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043119433219433241943042560012242712320x7fc391191e800x7fc3908263404704764704763121037638166553635063094636636240140430574417125981425131171259813829941712598189803417125981914868
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341943321943324194304256008242732160x7fc391191d000x7fc3908263804829174829173315438633446553635517070637482730142242295217125981939667171259818980341712598241195417125982430433
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371943321943324194304256008242757120x7fc391191b800x7fc3908263c08805128805125263970441046553667989171569291600272130732017125982454563171259824119541712598318379417125983204022
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044019433219433241943042560012242807680x7fc391191a000x7fc3908264004255904255902934034047286553631792293132986850127346223617125983234651171259831837941712598366379317125983680108
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044319433219433241943042560012242876160x7fc3911918800x7fc3908264405481725481723519043853846553641261784742792550165225234817125983707318171259836637931712598422699317125984244043
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044619433219433241943042560012242942080x7fc3911917000x7fc3908264805496025496023583043968246553641224791642919490165077549617125984270902171259842269931712598478747317125984804197
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491943321943324194304256008242969600x7fc3937bf5800x7fc3908264c05629585629583634145036726553642317198643927280169443352817125984829746171259847874731712598534635317125985364322
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521943321943324194304256008242999680x7fc3937bf4000x7fc390826500104129810412986063883303926553680951634782171010323980689617125985389461171259853463531712598622395317125986243617
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551943321943324194304256008243027200x7fc3937bf2800x7fc3908265407204757204754396057638086553655016298656559870220239421617125986274966171259862240891712598689288917125986914128
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045819433219433241943042560012243054720x7fc3937bf1000x7fc3908265807229277229274381357834246553654953992856702620219990300817125986935098171259868928891712598757144717125987588980
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046119433219433241943042560012243082240x7fc391191f800x7fc3908265c07214897214894470357719206553655569887656620580222453561217125987614259171259875714471712598825160717125988267601
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641943321943324194304256008243109760x7fc391191e000x7fc3908266007265757265754506358126086553655444972156950540221953995617125988294030171259882516071712598892136717125988937962
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671943321943324194304256008243132160x7fc391191c800x7fc390826640136652113665217697810932176655361065157712108149850426237218417125988963591171259889213671712599000504717125990022302
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701943321943324194304256008243159680x7fc391191b000x7fc390826680137215313721537773210977232655361081382508108449060432727244817125990055691171259900050471712599108568717125991149851
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047319433219433241943042560012243187200x7fc3911919800x7fc3908266c0137118713711877741410969504655361078414736108609130431539941217125991161770171259910856871712599222568717125992287979
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047619433219433241943042560012243214720x7fc3911918000x7fc390826700136966713696677604210957344655361073820046108457150429702094817125992300199171259922256871712599335416717125993416398
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791943321943324194304256008243242240x7fc3911916800x7fc390826740137552813755287774011004232655361086217699108849160434661336817125993427468171259933541671712599446360717125994526877
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821943321943324194304256008243264640x7fc3937bf5000x7fc3908267802664839266483914238121318720655362128333752211944750851507691217125994539037171259944636071712599643320717125996497602
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851943321943324194304256008243292160x7fc3937bf3800x7fc3908267c02667280266728014268921338248655362130273802212223050852283598017125996517052171259964332071712599837400717125998418859
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048819433219433241943042560012243319680x7fc3937bf2000x7fc3908268002670375267037514236721363008655362126282473212430600850687048417125998431398171259983740071712600035336717126000420323
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049119433219433241943042560012243347200x7fc3937bf0800x7fc3908268402667206266720614225921337656655362129658288212266840852037334417126000431313171260003533671712600234904717126002419107
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941943321943324194304256008243374720x7fc391191f000x7fc3908268802673279267327914244021386240655362132300589212615960853094442417126002432077171260023490471712600430728717126004378233
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049719433219433241943042560082400x7fc391191d800x7fc3908268c052556835255683273645420454726553642315493714192851801692793905217126004389442171260043072871712600793928717126008009862