Files
rocm-systems/tests/workloads/Axes2/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.kd000206513206513335544322560043241600x00x7fd82ca04280381343381343898130507525242882399194562962542097589964017336850338375173361338391481733699738676117336997497271
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00220651320651332768256001224138880x00x7fd82ca23f8034251342513079227401651218143251725340727092817337002664734173369973867611733700280788517337002812960
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0052065132065134194304256001224143360x7fd82f9673800x7fd82ca23fc016467316467313486131739265536851927021215418034250135217337002856539173370028078851733700320484517337003207389
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0082065132065134194304256001624150400x7fd82f9672000x7fd82ca24000308785308785228842470288655362175094072369781087176640817337003253058173370032048451733700363236617337003634908
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00112065132065134194304256001624154880x7fd82f9670800x7fd82ca24040311307311307251542490464655362277030542382205091254218817337003675557173370036323661733700406292617337004065557
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00142065132065134194304256001224159360x7fd82d309f000x7fd82ca2408016618916618914006132952065536754823571223205030366309617337004107216173370040629261733700439412617337004396638
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00172065132065134194304256001224163840x7fd82d309d800x7fd82ca240c016424416424414355131396065536838141641210572033698939617337004437537173370043941261733700472004717337004722629
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00202065132065134194304256001224170880x7fd82d309c000x7fd82ca24100163520163520153211308168655361089521791209222043754037217337004776258173370047200471733700504484717337005047161
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00232065132065134194304256001624177920x7fd82d309a800x7fd82ca24140309752309752243212478024655362277318092373550091265660817337005086740173370050448471733700547268717337005475289
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00262065132065134194304256001624184960x7fd82d3099000x7fd82ca24180306900306900217852455208655362122897452352134085088916017337005514718173370054726871733700589012817337005892378
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00292065132065134194304256001624192000x7fd82d3097800x7fd82ca241c0164269164269153141314160655361050184641213337042179799217337005932167173370058901281733700622852817337006230819
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00322065132065134194304256001624199040x7fd82d3096000x7fd82ca2420016410416410415077131284065536908732591211255036522134017337006271498173370062285281733700656324817337006565680
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00352065132065134194304256001224206080x7fd82f9674800x7fd82ca24240164520164520151961316168655361007966421214231040491216417337006615269173370065632481733700688980817337006892272
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00382065132065134194304256001624213120x7fd82f9673000x7fd82ca24280310572310572231772484584655362177569292379786087275697617337006936191173370068898081733700732356917337007325310
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00412065132065134194304256001624220160x7fd82f9671800x7fd82ca242c0311338311338233972490712655362256106962385262090417283617337007367859173370073235691733700771364917337007715570
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00442065132065134194304256001624227200x7fd82f9670000x7fd82ca2430016482416482414470131860065536885513111215038035593761617337007756569173370077136491733700801508917337008017032
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00472065132065134194304256001224234240x7fd82d309e800x7fd82ca2434016457616457614456131661665536958647191213023038518838017337008058321173370080150891733700831461017337008316524
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00502065132065134194304256001224241280x7fd82d309d000x7fd82ca2438016427816427814142131423265536897267751212882036063039217337008363863173370083146101733700861397017337008615696
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00532065132065134194304256001624248320x7fd82d309b800x7fd82ca243c0309116309116246562472936655362265738892368668090802686017337008661725173370086139701733700901189017337009013715
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00562065132065134194304256001624255360x7fd82d309a000x7fd82ca24400308246308246228072465976655362240428572363576089790407617337009055454173370090118901733700939893117337009400765
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00592065132065134194304256001224262400x7fd82d3098800x7fd82ca24440163240163240151571305928655361013914581207403040729546017337009441914173370093989311733700969605117337009698007
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00622065132065134194304256001224269440x7fd82d3097000x7fd82ca2448016245816245814721129967265536955232381201395038381885617337009741446173370096960511733700999765117337009999679
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00652065132065134194304256001224276480x7fd82f9675800x7fd82ca244c0163289163289149131306320655361018380041203685040908279217337010047668173370099976511733701031429117337010316311
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00682065132065134194304256001624286080x7fd82f9674000x7fd82ca24500308847308847233652470784655362236284972367976089624327217337010358800173370103142911733701070549217337010707231
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00712065132065134194304256001624293120x7fd82f9672800x7fd82ca24540309134309134223152473080655362239919982372474089769638817337010751860173370107054921733701110229217337011104310
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00742065132065134194304256001224300160x7fd82f9671000x7fd82ca24580162481162481149231299856655361014338491201007040747373217337011145349173370111022921733701139989217337011401662
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077206513206513419430425600824309760x7fd82d309f800x7fd82ca245c016236416236414787129892065536943017831197865037893856817337011444921173370113998921733701169941317337011701184
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00802065132065134194304256001224316800x7fd82d309e000x7fd82ca2460016290316290315161130323265536955835881201745038405758417337011749123173370116994131733701200069317337012002647
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00832065132065134194304256001624326400x7fd82d309c800x7fd82ca24640304758304758229752438072655362184702122330304087561338417337012043175173370120006931733701238869317337012390606
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00862065132065134194304256001224336000x7fd82d309b000x7fd82ca24680307214307214228112457720655362229428542352816089350014017337012432615173370123886931733701277653317337012778546
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00892065132065134194304256001224345600x7fd82d3099800x7fd82ca246c016359916359914540130880065536936504971204070037632848417337012819785173370127765331733701307653417337013078458
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092206513206513419430425600824355200x7fd82d3098000x7fd82ca2470016540016540015150132320865536990566611218468039795327217337013119127173370130765341733701337813417337013379960
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00952065132065134194304256001224362240x7fd82d3096800x7fd82ca24740162429162429148291299440655361050852461200527042206515217337013427909173370133781341733701368389417337013685742
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00982065132065134194304256001224371840x7fd82f9675000x7fd82ca24780305822305822230512446584655362274409632346688091149576817337013730861173370136838941733701407397517337014080352
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001012065132065134194304256001224381440x7fd82f9673800x7fd82ca247c0304925304925220362439408655362111043522336457084614686017337014117191173370140739751733701446485517337014466702
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001042065132065134194304256001224391040x7fd82f9672000x7fd82ca2480016349816349814976130799265536940312571205277037785623617337014508080173370144648551733701476901517337014770874
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107206513206513419430425600824403200x7fd82f9670800x7fd82ca2484016357016357014363130856865536826568951198605033235609217337014812582173370147690151733701507221517337015073985
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001102065132065134194304256001224412800x7fd82d309f000x7fd82ca2488016219616219614205129757665536915540961193631036794335617337015122274173370150722151733701537861617337015380447
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001132065132065134194304256001224422400x7fd82d309d800x7fd82ca248c0306818306818244992454552655362263237972352739090702498017337015425716173370153786161733701578357617337015785437
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001162065132065134194304256001224432000x7fd82d309c000x7fd82ca24900303894303894216072431160655362178170452329512087300108017337015827216173370157835761733701617557617337016177336
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119206513206513419430425600824441600x7fd82d309a800x7fd82ca2494016364416364414535130916065536910933571196528036609724417337016217685173370161755761733701647637717337016478218
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001222065132065134194304256001224453760x7fd82d3099000x7fd82ca2498016248316248314937129987265536907369561199952036467722817337016519377173370164763771733701677685717337016778660
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001252065132065134194304256001224463360x7fd82d3097800x7fd82ca249c016202916202914648129624065536887729931192710035682040017337016828149173370167768571733701708533717337017087172
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001282065132065134194304256001224475520x7fd82d3096000x7fd82ca24a00302848302848230762422792655362225512572320331089193418817337017132541173370170853371733701747701717337017478842
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001312065132065134194304256001224485120x7fd82f9674800x7fd82ca24a40301478301478205542411832655362075958012308082083211461617337017520511173370174770171733701786357817337017865441
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134206513206513419430425600824494720x7fd82f9673000x7fd82ca24a8016190616190614840129525665536864389111193758034748854817337017907000173370178635781733701816389817337018165734
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001372065132065134194304256001224506880x7fd82f9671800x7fd82ca24ac016377016377015848131016865536982220951204581039462288817337018207692173370181638981733701847285817337018474645
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001402065132065134194304256001224516480x7fd82f9670000x7fd82ca24b0016229016229015343129832865536975040701193016039175174017337018523874173370184728581733701878053917337018782367
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001432065132065134194304256001224528640x7fd82d309e800x7fd82ca24b40303572303572229782428584655362228017932327173089293621617337018824896173370187805391733701916693917337019168997
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001462065132065134194304256001224540800x7fd82d309d000x7fd82ca24b80302048302048207142416392655362119058922309905084935262017337019211426173370191669391733701956357917337019565546
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149206513206513419430425600824552960x7fd82d309b800x7fd82ca24bc016269416269414864130156065536931105561201660037416544017337019605945173370195635791733701986373917337019865518
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001522065132065134194304256001224567680x7fd82d309a000x7fd82ca24c00162734162734156561301880655361006381721201013040429010017337019906657173370198637391733702016678017337020168620
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001552065132065134194304256001224577280x7fd82d3098800x7fd82ca24c4016119216119213912128954465536907690781189399036480388417337020216729173370201667801733702047430017337020476162
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001582065132065134194304256001224589440x7fd82d3097000x7fd82ca24c80304772304772237252438184655362246059062335262090015596817337020521971173370204743001733702087014017337020871872
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001612065132065134194304256001224601600x7fd82f9675800x7fd82ca24cc0302277302277213772418224655362153694312317854086320598817337020913421173370208701401733702126150117337021263391
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164206513206513419430425600824613760x7fd82f9674000x7fd82ca24d0016304416304415300130436065536916205121201898036821907217337021305530173370212615011733702156150117337021563353
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001672065132065134194304256001224628480x7fd82f9672800x7fd82ca24d40168501168501166291348016655361049153701248118042139744817337021603672173370215615011733702187350117337021875295
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001702065132065134194304256001224638080x7fd82f9671000x7fd82ca24d8016191016191014501129528865536950851291196353038206747617337021924554173370218735011733702217878117337022180897
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001732065132065134194304256001224650240x7fd82d309f800x7fd82ca24dc0300615300615225352404928655362194230342302767087942427217337022223296173370221787811733702256822217337022570037
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001762065132065134194304256001224662400x7fd82d309e000x7fd82ca24e00299591299591210812396736655362153356962294718086307925617337022611916173370225682221733702295574217337022957567
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179206513206513419430425600824674560x7fd82d309c800x7fd82ca24e4016243516243514847129948865536881120521196839035417467217337022998706173370229557421733702325398217337023255879
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001822065132065134194304256001224689280x7fd82d309b000x7fd82ca24e80177389177389166751419120655361038556941312200041716434417337023298788173370232539821733702356470317337023566601
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001852065132065134194304256001224701440x7fd82d3099800x7fd82ca24ec016096016096014526128768865536899562411184798036155756817337023615049173370235647031733702387750317337023879282
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001882065132065134194304256001224716160x7fd82d3098000x7fd82ca24f00303489303489229432427920655362243232102327885089902520017337023921091173370238775031733702427094317337024272732
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001912065132065134194304256001224728320x7fd82d3096800x7fd82ca24f40304010304010228212432088655362169451992325342086951012817337024316211173370242709431733702466022417337024662232
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194206513206513419430425600824740480x7fd82f9675000x7fd82ca24f8016108116108115457128865665536910842031185479036607383217337024703381173370246602241733702495750417337024959484
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001972065132065134194304256001224757760x7fd82f9673800x7fd82ca24fc0182132182132171071457064655361129642961351736045360546417337024999973173370249575041733702527222417337025273976
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002002065132065134194304256001224769920x7fd82f9672000x7fd82ca2500016134616134615091129077665536900420451188506036189882017337025333834173370252722241733702557238417337025574108
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002032065132065134194304256001224784640x7fd82f9670800x7fd82ca25040302364302364229612418920655362223404192317721089109912817337025616927173370255723841733702596278517337025964507
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002062065132065134194304256001224799360x7fd82d309f000x7fd82ca25080303882303882239622431064655362236746522328281089642482817337026007156173370259627851733702637286517337026374887
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209206513206513419430425600824814080x7fd82d309d800x7fd82ca250c016332916332916054130664065536917070591199606036855958417337026415735173370263728651733702667494517337026676909
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002122065132065134194304256001224831360x7fd82d309c000x7fd82ca25100192550192550190491540408655361202860821430340048289005617337026718337173370266749451733702699638617337026998140
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002152065132065134194304256001224843520x7fd82d309a800x7fd82ca2514016198516198514850129588865536912242941195907036663764017337027047229173370269963861733702730550617337027307282
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002182065132065134194304256001224858240x7fd82d3099000x7fd82ca25180303646303646236932429176655362221425212325982089030428817337027353161173370273055061733702769766617337027699651
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002212065132065134194304256001224872960x7fd82d3097800x7fd82ca251c0299061299061218652392496655362129494402292344085352748817337027741570173370276976661733702808246617337028084231
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002242065132065134194304256001224887680x7fd82d3096000x7fd82ca2520016209816209815440129679265536957544011193585038474644017337028125630173370280824661733702838294717337028384713
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002272065132065134194304256001224907520x7fd82f9674800x7fd82ca25240199963199963179411599712655361363813141498163054726788017337028424482173370283829471733702871462717337028716504
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002302065132065134194304256001224919680x7fd82f9673000x7fd82ca2528016171216171215684129370465536931725811188627037442048817337028764493173370287146271733702902230717337029024056
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002332065132065134194304256001224934400x7fd82f9671800x7fd82ca252c0302068302068224482416552655362182474132313291087472131617337029069825173370290223071733702941430817337029416046
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002362065132065134194304256001224949120x7fd82f9670000x7fd82ca25300298620298620209272388968655362069334022283268082946963217337029457735173370294143081733702980006817337029801806
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002392065132065134194304256001224963840x7fd82d309e800x7fd82ca2534016220216220215799129762465536992096841195000039856931217337029842395173370298000681733703010198817337030103778
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002422065132065134194304256001224983680x7fd82d309d000x7fd82ca25380210720210720185621685768655361254549081573296050356602417337030146047173370301019881733703043830817337030440199
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002452065132065134194304256001224995840x7fd82d309b800x7fd82ca253c016133216133214735129066465536924116981190133037137661217337030488837173370304383081733703074550917337030747391
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024820651320651341943042560012241013120x7fd82d309a000x7fd82ca25400299832299832226852398664655362167912702293449086890324017337030788230173370307455091733703114374917337031145500
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025120651320651341943042560012241027840x7fd82d3098800x7fd82ca25440299482299482201352395864655361985705112289874079601609617337031187119173370311437491733703153094917337031532750
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025420651320651341943042560012241042560x7fd82d3097000x7fd82ca2548016279516279515949130236865536998723831199561040122941617337031573989173370315309491733703183271017337031834472
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025720651320651341943042560012241062400x7fd82f9675800x7fd82ca254c0218292218292191271746344655361465703411638670058802660417337031875861173370318327101733703216951017337032171363
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026020651320651341943042560012241077120x7fd82f9674000x7fd82ca2550016042616042614979128341665536935303451183952037585704817337032219602173370321695101733703247847017337032480305
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026320651320651341943042560016241094400x7fd82f9672800x7fd82ca25540297329297329215792378640655362162060852276612086655943217337032526413173370324784701733703288519117337032887014
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026620651320651341943042560016241111680x7fd82f9671000x7fd82ca25580300111300111221582400896655362132780962297541085484593217337032929153173370328851911733703328055117337033282333
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002692065132065134194304256008241128960x7fd82d309f800x7fd82ca255c0162161162161153281297296655361001166061195615040220094417337033323722173370332805511733703359079117337033592435
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027220651320651341943042560012241151360x7fd82d309e000x7fd82ca25600229728229728196051837832655361543693991727662061921930817337033634024173370335907911733703393815117337033940056
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027520651320651341943042560012241166080x7fd82d309c800x7fd82ca2564016068916068915185128552065536958265791185088038503742417337033988585173370339381511733703425287217337034254758
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027820651320651341943042560016241183360x7fd82d309b000x7fd82ca25680296520296520215342372168655362123295942272483085105712417337034297357173370342528721733703464103217337034642937
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028120651320651341943042560016241200640x7fd82d3099800x7fd82ca256c0297461297461201492379696655362053509832272226082314126817337034684526173370346410321733703502695217337035028717
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028420651320651341943042560012241217920x7fd82d3098000x7fd82ca25700163779163779158371310240655361029935141210209041370859217337035070656173370350269521733703532887317337035330769
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028720651320651341943042560012241240320x7fd82d3096800x7fd82ca25740240493240493200441923952655361451999721811956058255339217337035372168173370353288731733703568391317337035685910
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029020651320651341943042560012241255040x7fd82f9675000x7fd82ca2578016077816077815502128623265536940070871184855037776331617337035734339173370356839131733703598743317337035989192
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029320651320651341943042560012241274880x7fd82f9673800x7fd82ca257c0298738298738212192389912655362121709702280238085041571617337036034181173370359874331733703638151417337036383392
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029620651320651341943042560012241292160x7fd82f9672000x7fd82ca25800298224298224208262385800655362048688642277808082121268417337036424940173370363815141733703677351417337036775361
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029920651320651341943042560012241309440x7fd82f9670800x7fd82ca2584017224417224416884137796065536987610401273275039679722417337036815910173370367735141733703708247417337037084473
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030220651320651341943042560012241334400x7fd82d309f000x7fd82ca25880259098259098216412072792655361758384231959099070510536817337037126152173370370824741733703744615417337037447924
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030520651320651341943042560012241349120x7fd82d309d800x7fd82ca258c016187616187615984129501665536980321991192694039386184417337037496742173370374461541733703775415517337037755945
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030820651320651341943042560012241368960x7fd82d309c000x7fd82ca25900296556296556193782372456655361955770892263607078405367217337037796794173370377541551733703814807517337038150015
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031120651320651341943042560012241388800x7fd82d309a800x7fd82ca25940296880296880211992375048655362129949592274603085372224817337038193834173370381480751733703854199517337038543785
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031420651320651341943042560012241408640x7fd82d3099000x7fd82ca25980177442177442164341419544655361136285791316889045625606817337038583963173370385419951733703885479617337038856656
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031720651320651341943042560012241436160x7fd82d3097800x7fd82ca259c0279168279168219002233352655361942720202128629077883716817337038898125173370388547961733703923271617337039234646
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032020651320651341943042560012241453440x7fd82d3096000x7fd82ca25a0016150416150415904129204065536989215591189540039742833217337039284065173370392327161733703954183617337039543658
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032320651320651341943042560012241475840x7fd82f9674800x7fd82ca25a40296217296217211122369744655362089253832266798083744510817337039585727173370395418361733703993175717337039933558
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032620651320651341943042560012241495680x7fd82f9673000x7fd82ca25a80296482296482207912371864655362021180372263273081021381617337039975607173370399317571733704032103717337040322777
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032920651320651341943042560012241515520x7fd82f9671800x7fd82ca25ac0186729186729176901493840655361146334481387157046029427217337040363716173370403210371733704064535717337040647149
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033220651320651341943042560012241543040x7fd82f9670000x7fd82ca25b00298546298546235052388376655362132819562282208085487554817337040688328173370406453571733704103735717337041039128
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033520651320651341943042560012241562880x7fd82d309e800x7fd82ca25b40171087171087160571368704655361063852841267172042728953617337041087747173370410373571733704134567817337041347570
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033820651320651341943042560012241587840x7fd82d309d000x7fd82ca25b80297534297534196262380280655361795654472257136072001235217337041388669173370413456781733704173687817337041738720
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034120651320651341943042560012241610240x7fd82d309b800x7fd82ca25bc0296467296467196992371744655361909736412254681076564574017337041780859173370417368781733704212599817337042128080
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034420651320651341943042560012241632640x7fd82d309a000x7fd82ca25c00206082206082182761648664655361283641251541605051521268417337042169238173370421259981733704245959917337042461351
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034720651320651341943042560012241665280x7fd82d3098800x7fd82ca25c40339502339502255812716024655362493243432609588099905264417337042502230173370424595991733704287303917337042895879
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035020651320651341943042560012241685120x7fd82d3097000x7fd82ca25c80184338184338172471474712655361099736361365308044164317217337042924208173370428730391733704319943917337043201231
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035320651320651341943042560012241712640x7fd82f9675800x7fd82ca25cc0295804295804197902366440655361934749382252639077565917617337043241130173370431994391733704359016017337043592011
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035620651320651341943042560012241737600x7fd82f9674000x7fd82ca25d00300036300036212532400296655361608481472260601064514100017337043633880173370435901601733704398296017337043984760
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035920651320651341943042560012241762560x7fd82f9672800x7fd82ca25d40224412224412192801795304655361519452191689248060953526017337044025729173370439829601733704432632017337044328101
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036220651320651341943042560012241797760x7fd82f9671000x7fd82ca25d803802213802212737330417766553627573863129331950110471271617337044369710173370443263201733704476552117337044788499
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036520651320651341943042560012241822720x7fd82d309f800x7fd82ca25dc0210188210188185651681512655361388927181577681055732371617337044817348173370447655211733704510776117337045109520
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036820651320651341943042560012241855360x7fd82d309e000x7fd82ca25e00306416306416218062451336655361943608702333074077921344417337045150639173370451077611733704550968117337045527369
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037120651320651341943042560012241885440x7fd82d309c800x7fd82ca25e40308703308703237282469632655361768567722327592070918491217337045551979173370455096811733704592376217337045940788
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037420651320651341943042560012241915520x7fd82d309b000x7fd82ca25e80265751265751214852126016655361814678582017703072762641217337045966388173370459237621733704630536217337046307449
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037720651320651341943042560012241958400x7fd82d3099800x7fd82ca25ec04606614606613137836852966553634544418035755830138353732817337046348568173370463053621733704680264217337046849304
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038020651320651341943042560012241985920x7fd82d3098000x7fd82ca25f00244443244443206721955552655361507679041845393060482589217337046869244173370468026421733704718696317337047188815
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038320651320651341943042560012242023680x7fd82d3096800x7fd82ca25f40333855333855231872670848655362092319402559686083870607217337047230284173370471869631733704760376317337047646553
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038620651320651341943042560012242058880x7fd82f9675000x7fd82ca25f80332359332359234732658880655362128724802533945085326444017337047658103173370476037631733704803976317337048081922
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038920651320651341943042560012242094080x7fd82f9673800x7fd82ca25fc0307001307001234422456016655362185592552347929087600273617337048093311173370480397631733704846296417337048464812
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039220651320651341943042560012242144640x7fd82f9672000x7fd82ca260005425215425213576343401766553640595130842273710162557202017337048506430173370484629641733704900824417337049050876
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039520651320651341943042560012242177280x7fd82f9670800x7fd82ca26040272707272707216072181664655361850238922072875074186313217337049070755173370490082441733704940216517337049403987
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039820651320651341943042560012242220160x7fd82d309f000x7fd82ca26080368177368177262992945424655362371322282811416095031843617337049445596173370494021651733704984024517337049859205
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040120651320651341943042560012242260480x7fd82d309d800x7fd82ca260c03664283664282839229314326553625230049528216010101097436417337049883374173370498402451733705028264517337050327402
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040420651320651341943042560012242300800x7fd82d309c000x7fd82ca261003465493465492547927724006553625125285126641070100677445217337050339012173370502826451733705072968617337050777020
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040720651320651341943042560012242359040x7fd82d309a800x7fd82ca261406228696228693975749829606553648132365948752320192706399617337050788350173370507296861733705135064617337051392774
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041020651320651341943042560012242394240x7fd82d3099000x7fd82ca26180302052302052230862416424655362155651452311375086402874017337051412494173370513506461733705177192717337051773864
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041320651320651341943042560012242442240x7fd82d3097800x7fd82ca261c03977393977392710831819206553627067526330670150108448776417337051814903173370517719271733705223304717337052275251
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041620651320651341943042560012242487680x7fd82d3096000x7fd82ca262003902333902332753431218726553629291683730216310117343936017337052287511173370522330471733705270904717337052751328
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041920651320651341943042560012242533120x7fd82f9674800x7fd82ca262403874003874002766730992086553628707393529892060115006301217337052761948173370527090471733705317400817337053216056
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004222065132065134194304256008242555520x7fd82f9673000x7fd82ca262807178997178994504757432006553653589213656314780214530852817337053228136173370531740081733705385624817337053898438
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042520651320651341943042560012242598400x7fd82f9671800x7fd82ca262c03648083648082667329184726553625324338828019010101474184417337053918798173370538562481733705431960917337054367006
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042820651320651341943042560012242656640x7fd82f9670000x7fd82ca263004705814705813151437646566553636203301636626000144992841617337054379255173370543196091733705485752917337054900672
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043120651320651341943042560012242712320x7fd82d309e800x7fd82ca263404713804713803168537710486553634979618936634940140096762017337054912751173370548575291733705539257017337055435027
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004342065132065134194304256008242732160x7fd82d309d000x7fd82ca263804829134829133290638633126553635389902737528680141733845617337055446107173370553925701733705591833017337055960303
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004372065132065134194304256008242757120x7fd82d309b800x7fd82ca263c08807208807205222170457686553668219400469297050273051822417337055971233173370559183301733705670473117337056746793
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044020651320651341943042560012242807680x7fd82d309a000x7fd82ca264004264824264822957134118646553631816188533060760127441949617337056767122173370567047311733705719897117337057241030
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044320651320651341943042560012242876160x7fd82d3098800x7fd82ca264405492925492923560643943446553640984585242902060164116985617337057252279173370571989711733705778057217337057822754
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044620651320651341943042560012242942080x7fd82d3097000x7fd82ca264805509805509803566244078486553641656957343072360166806173217337057834154173370577805721733705836121217337058407179
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004492065132065134194304256008242969600x7fd82f9675800x7fd82ca264c05627415627413618545019366553642023754243901100168269398817337058418688173370583612121733705894553317337058989683
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004522065132065134194304256008242999680x7fd82f9674000x7fd82ca26500104099010409906059383279286553680357560782216280321604422417337059000523173370589455331733705984265317337059885359
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004552065132065134194304256008243027200x7fd82f9672800x7fd82ca265407217457217454442157739686553654977103056570790220082646417337059905009173370598424311733706052227117337060568501
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045820651320651341943042560012243054720x7fd82f9671000x7fd82ca265807238367238364451557906966553655110497256748280220616139617337060580371173370605222711733706121843117337061260333
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046120651320651341943042560012243082240x7fd82d309f800x7fd82ca265c07215407215404452957723286553655357625856635010221604435217337061272203173370612184311733706190451117337061924115
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004642065132065134194304256008243109760x7fd82d309e000x7fd82ca266007274057274054486158192486553655987764157022130224125358817337061947785173370619045111733706256947117337062614547
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004672065132065134194304256008243132160x7fd82d309c800x7fd82ca26640136623513662357756110929888655361074480432108144540429966344017337062625887173370625694711733706367011217337063713838
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004702065132065134194304256008243159680x7fd82d309b000x7fd82ca26680137073513707357715310965888655361082890376108487890433330357217337063734168173370636701121733706475699217337064820179
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047320651320651341943042560012243187200x7fd82d3099800x7fd82ca266c0137285713728577759910982864655361073340523108594510429510346817337064832379173370647569921733706589059317337065959469
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047620651320651341943042560012243214720x7fd82d3098000x7fd82ca26700137171513717157680710973728655361073266930108531710429480850017337065971569173370658905931733706703411317337067102299
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004792065132065134194304256008243242240x7fd82d3096800x7fd82ca26740137497713749777755010999824655361086088670108839760434609728017337067113978173370670341131733706816819417337068234969
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004822065132065134194304256008243264640x7fd82f9675000x7fd82ca267802665471266547114312721323776655362129827555211848770852105291217337068246338173370681681941733707013523417337070207106
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004852065132065134194304256008243292160x7fd82f9673800x7fd82ca267c02667157266715714232921337264655362131358619212244030852717548017337070227226173370701352341733707207859517337072147155
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048820651320651341943042560012243319680x7fd82f9672000x7fd82ca268002671372267137214321221370984655362133705692212452210853656376417337072159255173370720785951733707407507617337074125643
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049120651320651341943042560012243347200x7fd82f9670800x7fd82ca268402667694266769414229821341560655362121038226212307720848589344417337074138472173370740750761733707605715717337076127140
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004942065132065134194304256008243374720x7fd82d309f000x7fd82ca268802674254267425414313221394040655362127418593212633590851141616417337076138619173370760571571733707800611817337078073789
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049720651320651341943042560082400x7fd82d309d800x7fd82ca268c052556945255694273670420455606553642328472124192887801693313028817337078099068173370780061181733708165091917337081719282