Files
rocm-systems/tests/workloads/HBM/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.kd000169289169289335544322560043241600x00x7f7d6aa04280382373382373891830589925242882403911522971330097778682416686960387064166862419616671668710357845116687103695890
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00216928916928932768256001224138880x00x7f7d6aa23f8033366333662956726693651217160661603910687776416687108874628166871035784511668710901186016687109016713
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051692891692894194304256001224143360x7f7d6d9be3800x7f7d6aa23fc016455516455513735131644865536786391251206963031628922416687109061442166871090118601668710940465816687109407430
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081692891692894194304256001624150400x7f7d6d9be2000x7f7d6aa24000310357310357249822482864655362256280362373429090423972816687109453789166871094046581668710983425516687109837076
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111692891692894194304256001624154880x7f7d6d9be0800x7f7d6aa24040310115310115245322480928655362210639982367611088598233216687109877965166871098342551668711025681316687110259282
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141692891692894194304256001224159360x7f7d6b391f000x7f7d6aa2408016575716575713802132606465536782191391217120031460701616687110302231166871102568131668711059761116687110600061
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171692891692894194304256001224163840x7f7d6b391d800x7f7d6aa240c016535716535715202132286465536836621981209695033637728016687110642139166871105976111668711093120916687110933550
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201692891692894194304256001224170880x7f7d6b391c000x7f7d6aa24100163071163071160061304576655361003448781198859040310995216687110989728166871109312091668711126208716687111264649
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231692891692894194304256001624177920x7f7d6b391a800x7f7d6aa24140306421306421242492451376655362197792712348602088084600016687111305427166871112620871668711169344516687111695854
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261692891692894194304256001624184960x7f7d6b3919000x7f7d6aa24180307767307767225852462144655362140405702357572085789157216687111736223166871116934451668711211200216687112114450
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291692891692894194304256001624192000x7f7d6b3917800x7f7d6aa241c016375316375315085131003265536969686101208293038959942416687112155559166871121120021668711244272116687112445389
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321692891692894194304256001624199040x7f7d6b3916000x7f7d6aa2420016571316571315966132571265536913875811217823036728073216687112486888166871124427211668711276991916687112772389
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351692891692894194304256001224206080x7f7d6d9be4800x7f7d6aa24240165167165167155531321344655361089003501217191043732467616687112822637166871127699191668711310351716687113105918
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381692891692894194304256001624213120x7f7d6d9be3000x7f7d6aa24280312086312086252212496696655362296336792382383092026317616687113148116166871131035171668711352255516687113524994
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411692891692894194304256001624220160x7f7d6d9be1800x7f7d6aa242c0308285308285225272466288655362183103942356769087496866816687113566402166871135225551668711394063216687113943020
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441692891692894194304256001624227200x7f7d6d9be0000x7f7d6aa2430016388516388515155131108865536890611761207339035797832416687113984688166871139406321668711428479016687114287308
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471692891692894194304256001224234240x7f7d6b391e800x7f7d6aa2434016358616358614642130869665536955188851204208038380504416687114328587166871142847901668711461934816687114621227
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501692891692894194304256001224241280x7f7d6b391d000x7f7d6aa2438016349916349914743130800065536906314011205966036425143216687114670636166871146193481668711492158716687114923437
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531692891692894194304256001624248320x7f7d6b391b800x7f7d6aa243c0307067307067240992456544655362248783292353177090124265216687114970076166871149215871668711532830416687115330124
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561692891692894194304256001624255360x7f7d6b391a000x7f7d6aa24400307146307146220922457176655362122918772344976085089942816687115372782166871153283041668711571886216687115720631
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591692891692894194304256001224262400x7f7d6b3918800x7f7d6aa2444016373316373314778130987265536904113911205512036337743216687115762999166871157188621668711601982116687116021661
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621692891692894194304256001224269440x7f7d6b3917000x7f7d6aa2448016384116384114806131073665536866226271205527034821568816687116063099166871160198211668711631885916687116320591
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651692891692894194304256001224276480x7f7d6d9be5800x7f7d6aa244c016353116353116399130825665536992550241199754039875506816687116371919166871163188591668711662589716687116627831
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681692891692894194304256001624286080x7f7d6d9be4000x7f7d6aa24500308065308065233072464528655362155331002349368086386243616687116674279166871166258971668711702477516687117026657
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711692891692894194304256001624293120x7f7d6d9be2800x7f7d6aa24540306258306258221072450072655362143022442341451085893670816687117068586166871170247751668711742109316687117422834
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741692891692894194304256001224300160x7f7d6d9be1000x7f7d6aa2458016187816187815151129503265536988019071192083039693857616687117465493166871174210931668711772045116687117722214
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077169289169289419430425600824309760x7f7d6b391f800x7f7d6aa245c016175616175614830129405665536950039321191475038174449216687117765433166871177204511668711802092916687118022844
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801692891692894194304256001224316800x7f7d6b391e000x7f7d6aa2460016396616396616221131173665536961118301203976038617091216687118071343166871180209291668711833052816687118332464
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831692891692894194304256001624326400x7f7d6b391c800x7f7d6aa24640307406307406241772459256655362262618632350613090678197216687118374113166871183305281668711872924516687118731371
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861692891692894194304256001224336000x7f7d6b391b000x7f7d6aa24680305264305264220132442120655362191403302338018087828902016687118772729166871187292451668711911708316687119118818
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891692891692894194304256001224345600x7f7d6b3919800x7f7d6aa246c016259816259814820130079265536907437061194374036469928816687119160997166871191170831668711941788216687119419748
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092169289169289419430425600824355200x7f7d6b3918000x7f7d6aa2470016331616331615107130653665536866884161197544034847800416687119461347166871194178821668711971996016687119721758
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951692891692894194304256001224362240x7f7d6b3916800x7f7d6aa2474016244716244714893129958465536939046831194435037734386416687119770266166871197199601668712002891816687120030708
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981692891692894194304256001224371840x7f7d6d9be5000x7f7d6aa24780303637303637239492429104655362183076672322726087496509216687120077806166871200289181668712043019616687120432114
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011692891692894194304256001224381440x7f7d6d9be3800x7f7d6aa247c0305600305600228502444808655362093241912334104083902695216687120474223166871204301961668712081899416687120820701
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041692891692894194304256001224391040x7f7d6d9be2000x7f7d6aa24800164161164161157431313296655361000976341203931040212082416687120862530166871208189941668712112443216687121126251
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107169289169289419430425600824403200x7f7d6d9be0800x7f7d6aa2484016384816384815802131079265536899840671199888036166704816687121170230166871211244321668712142715016687121428961
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101692891692894194304256001224412800x7f7d6b391f000x7f7d6aa2488016298116298115676130385665536994158421195963039938859616687121478180166871214271501668712173226916687121734001
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131692891692894194304256001224422400x7f7d6b391d800x7f7d6aa248c0307619307619243612460960655362254810432354680090365407616687121780150166871217322691668712212618616687122128118
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161692891692894194304256001224432000x7f7d6b391c000x7f7d6aa24900303095303095225712424768655362114938812313066084770626416687122171107166871221261861668712253434416687122536195
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119169289169289419430425600824441600x7f7d6b391a800x7f7d6aa2494016282816282815427130263265536938701501196890037720414016687122578413166871225343441668712283962216687122841304
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221692891692894194304256001224453760x7f7d6b3919000x7f7d6aa2498016243216243215413129946465536869088871193318034936492816687122882733166871228396221668712314266116687123144474
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251692891692894194304256001224463360x7f7d6b3917800x7f7d6aa249c016266616266614422130133665536907056661199377036455106016687123193203166871231426611668712345193916687123453694
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281692891692894194304256001224475520x7f7d6b3916000x7f7d6aa24a00306071306071230532448576655362156247222337167086422715616687123496183166871234519391668712384457716687123846341
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311692891692894194304256001224485120x7f7d6d9be4800x7f7d6aa24a40301535301535215182412288655362121847522305352085046788016687123888500166871238445771668712423417516687124235988
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134169289169289419430425600824494720x7f7d6d9be3000x7f7d6aa24a8016310316310315347130483265536828557681196276033315695616687124277487166871242341751668712453417316687124535938
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371692891692894194304256001224506880x7f7d6d9be1800x7f7d6aa24ac016197016197016348129576865536963860901187234038727974016687124578497166871245341731668712483721116687124839088
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401692891692894194304256001224516480x7f7d6d9be0000x7f7d6aa24b0016109316109314635128875265536887339181183163035667228016687124888736166871248372111668712514313016687125144748
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431692891692894194304256001224528640x7f7d6b391e800x7f7d6aa24b40304889304889239212439120655362192120492333609087857876816687125191206166871251431301668712553880716687125540575
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461692891692894194304256001224540800x7f7d6b391d000x7f7d6aa24b80302266302266228902418136655362126119852309861085217524816687125581643166871255388071668712593368516687125935372
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149169289169289419430425600824552960x7f7d6b391b800x7f7d6aa24bc016315416315415378130524065536903751341193962036322602016687125976260166871259336851668712624424316687126245901
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521692891692894194304256001224567680x7f7d6b391a000x7f7d6aa24c0016371616371616865130973665536984245791199516039543919616687126287760166871262442431668712654824216687126550101
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551692891692894194304256001224577280x7f7d6b3918800x7f7d6aa24c4016448916448915778131592065536908301681201064036504829616687126599570166871265482421668712685528016687126857071
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581692891692894194304256001224589440x7f7d6b3917000x7f7d6aa24c80301841301841234052414736655362182674112306229087480165216687126904630166871268552801668712725063816687127252438
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611692891692894194304256001224601600x7f7d6d9be5800x7f7d6aa24cc0299805299805205272398448655362079126642294420083337948816687127296037166871272506381668712764007616687127641935
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164169289169289419430425600824613760x7f7d6d9be4000x7f7d6aa24d0016219916219914949129760065536892287291192244035864146416687127684404166871276400761668712794135416687127943165
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671692891692894194304256001224628480x7f7d6d9be2800x7f7d6aa24d40168845168845170121350768655361020640731239854040998914416687127984894166871279413541668712825511216687128257035
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701692891692894194304256001224638080x7f7d6d9be1000x7f7d6aa24d8016167616167615015129341665536924479891189900037151896016687128306723166871282551121668712855623116687128558035
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731692891692894194304256001224650240x7f7d6b391f800x7f7d6aa24dc0301041301041231642408336655362190332782304234087786457216687128605283166871285562311668712894998816687128951712
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761692891692894194304256001224662400x7f7d6b391e000x7f7d6aa24e00299639299639219332397120655362124177052288532085140275216687128994220166871289499881668712933526616687129337059
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179169289169289419430425600824674560x7f7d6b391c800x7f7d6aa24e4016306316306314904130451265536845875071195469034008292416687129378197166871293352661668712963766416687129639619
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821692891692894194304256001224689280x7f7d6b391b000x7f7d6aa24e80176269176269167601410160655361047467801302421042072479616687129681247166871296376641668712994870316687129950548
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851692891692894194304256001224701440x7f7d6b3919800x7f7d6aa24ec016084316084314897128675265536822787481178147033085223216687130000147166871299487031668713025814116687130259968
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881692891692894194304256001224716160x7f7d6b3918000x7f7d6aa24f00301884301884240522415080655362162963012304224086691612416687130300947166871302581411668713065781916687130659685
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911692891692894194304256001224728320x7f7d6b3916800x7f7d6aa24f40301894301894247862415160655362187562882301730087675404016687130702524166871306578191668713104629716687131048052
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194169289169289419430425600824740480x7f7d6d9be5000x7f7d6aa24f8016176416176415371129412065536869290991185249034944940816687131089081166871310462971668713134917516687131350942
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971692891692894194304256001224757760x7f7d6d9be3800x7f7d6aa24fc0180773180773172721446192655361140101361337473045777995616687131393361166871313491751668713166421316687131666022
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001692891692894194304256001224769920x7f7d6d9be2000x7f7d6aa2500016111516111515235128892865536911884211184846036648281216687131726890166871316642131668713196629116687131968192
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031692891692894194304256001224784640x7f7d6d9be0800x7f7d6aa25040299544299544224282396360655362115138292289156084778194816687132009710166871319662911668713236036916687132362258
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061692891692894194304256001224799360x7f7d6b391f000x7f7d6aa25080298842298842223272390744655362157836302285626086486635616687132406627166871323603691668713275764716687132759435
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209169289169289419430425600824814080x7f7d6b391d800x7f7d6aa250c016243216243215542129946465536884172681191273035539693216687132800864166871327576471668713305892516687133060785
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121692891692894194304256001224831360x7f7d6b391c000x7f7d6aa25100191942191942189371535544655361257890761426475050489562016687133105594166871330589251668713338212416687133383915
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151692891692894194304256001224843520x7f7d6b391a800x7f7d6aa2514016099016099014921128792865536945941531182193038010140816687133432523166871333821241668713368964216687133691334
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181692891692894194304256001224858240x7f7d6b3919000x7f7d6aa25180300924300924236002407400655362138968172303519085732562016687133738863166871336896421668713408612016687134088041
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211692891692894194304256001224872960x7f7d6b3917800x7f7d6aa251c0302163302163227352417312655362070699462308665083001495216687134131470166871340861201668713448627716687134488168
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241692891692894194304256001224887680x7f7d6b3916000x7f7d6aa2520016264416264416090130116065536960361991193039038587116416687134530736166871344862771668713478995616687134791848
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271692891692894194304256001224907520x7f7d6d9be4800x7f7d6aa25240201754201754177991614040655361255502151506409050395214016687134833596166871347899561668713512387416687135125617
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301692891692894194304256001224919680x7f7d6d9be3000x7f7d6aa2528016199116199115546129593665536844967271186319033972204016687135175275166871351238741668713542547216687135427227
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331692891692894194304256001224934400x7f7d6d9be1800x7f7d6aa252c0302333302333235412418672655362172448232308245087071306416687135470705166871354254721668713581875016687135820554
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361692891692894194304256001224949120x7f7d6d9be0000x7f7d6aa25300299309299309214932394480655362069283012291313082944525216687135863172166871358187501668713620706816687136208871
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391692891692894194304256001224963840x7f7d6b391e800x7f7d6aa2534016330616330616706130645665536970412771195450038989596416687136250139166871362070681668713651026616687136512101
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421692891692894194304256001224983680x7f7d6b391d000x7f7d6aa25380210814210814188631686520655361216006391572358048815302016687136555079166871365102661668713685010416687136851809
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451692891692894194304256001224995840x7f7d6b391b800x7f7d6aa253c016230316230314879129843265536838446281191573033711372816687136900318166871368501041668713716162216687137163439
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024816928916928941943042560012241013120x7f7d6b391a000x7f7d6aa25400296350296350218182370808655362105958162264117084411903216687137204598166871371616221668713755554016687137557436
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025116928916928941943042560012241027840x7f7d6b3918800x7f7d6aa25440299785299785224252398288655362091587352291664083836794816687137599515166871375555401668713794657816687137948533
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025416928916928941943042560012241042560x7f7d6b3917000x7f7d6aa2548016169816169816097129359265536984639671188413039558902416687137989352166871379465781668713825729616687138259133
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025716928916928941943042560012241062400x7f7d6d9be5800x7f7d6aa254c0218966218966196971751736655361335852071635224053608630816687138300951166871382572961668713860017416687138602031
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026016928916928941943042560012241077120x7f7d6d9be4000x7f7d6aa2550016025616025614844128205665536905415471175997036389597216687138651150166871386001741668713890193316687138903731
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026316928916928941943042560016241094400x7f7d6d9be2800x7f7d6aa25540296173296173214792369392655362057046932260359082455222416687138945680166871389019331668713929153116687139293548
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026616928916928941943042560016241111680x7f7d6d9be1000x7f7d6aa25580301356301356230072410856655362103960682297257084331445616687139335717166871392915311668713968304816687139684935
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691692891692894194304256008241128960x7f7d6b391f800x7f7d6aa255c0161730161730156571293848655361035751201189824041603410016687139726394166871396830481668713999008716687139991855
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027216928916928941943042560012241151360x7f7d6b391e000x7f7d6aa25600230631230631199481845056655361315004891725602052774697216687140033394166871399900871668714033552516687140337344
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027516928916928941943042560012241166080x7f7d6b391c800x7f7d6aa2564016106016106015804128848865536896947881181959036050899216687140388112166871403355251668714065232316687140654233
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027816928916928941943042560016241183360x7f7d6b391b000x7f7d6aa25680296154296154214132369240655362112203842264743084661727616687140695922166871406523231668714104144116687141043270
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028116928916928941943042560016241200640x7f7d6b3919800x7f7d6aa256c0297508297508208272380072655362048789162270407082124636016687141085079166871410414411668714143727916687141439097
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028416928916928941943042560012241217920x7f7d6b3918000x7f7d6aa25700164454164454160791315640655361041979961213264041852985616687141481196166871414372791668714174191716687141743747
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028716928916928941943042560012241240320x7f7d6b3916800x7f7d6aa25740241254241254207431930040655361437572941810722057677379616687141784656166871417419171668714209727516687142099165
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029016928916928941943042560012241255040x7f7d6d9be5000x7f7d6aa2578016051516051515957128412865536989327961180468039746281216687142147794166871420972751668714240943316687142411345
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029316928916928941943042560012241274880x7f7d6d9be3800x7f7d6aa257c0298062298062213242384504655362078024492276888083294538816687142458783166871424094331668714280607116687142807952
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029616928916928941943042560012241292160x7f7d6d9be2000x7f7d6aa25800298750298750207542390008655361957223012279027078462508816687142851060166871428060711668714319406916687143195849
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029916928916928941943042560012241309440x7f7d6d9be0800x7f7d6aa25840169679169679160761357440655361057367301254779042468698416687143237877166871431940691668714350366716687143505429
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030216928916928941943042560012241334400x7f7d6b391f000x7f7d6aa25880259144259144214692073160655361722004251962414069056379616687143549497166871435036671668714386878516687143870656
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030516928916928941943042560012241349120x7f7d6b391d800x7f7d6aa258c016204916204915856129640065536979077021189088039336730816687143919035166871438687851668714417966316687144181476
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030816928916928941943042560012241368960x7f7d6b391c000x7f7d6aa25900297100297100211492376808655362047791602269186082085372016687144223315166871441796631668714457294116687144574713
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031116928916928941943042560012241388800x7f7d6b391a800x7f7d6aa25940295581295581212492364656655362136409012261103085629831616687144617112166871445729411668714496333916687144965210
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031416928916928941943042560012241408640x7f7d6b3919000x7f7d6aa25980179301179301180251434416655361045480811316066041993274416687145005759166871449633391668714527837716687145280130
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031716928916928941943042560012241436160x7f7d6b3917800x7f7d6aa259c0279739279739226272237920655361939273652125077077745196016687145321168166871452783771668714565837516687145660397
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032016928916928941943042560012241453440x7f7d6b3916000x7f7d6aa25a0016120716120716083128966465536979350111184472039348308016687145709675166871456583751668714596349316687145965287
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032316928916928941943042560012241475840x7f7d6d9be4800x7f7d6aa25a40294715294715217832357728655362058461162250794082513012016687146011285166871459634931668714636541116687146367314
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032616928916928941943042560012241495680x7f7d6d9be3000x7f7d6aa25a80296644296644215442373160655362055822072258208082406622016687146409982166871463654111668714675692916687146758961
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032916928916928941943042560012241515520x7f7d6d9be1800x7f7d6aa25ac0186267186267181691490144655361102544631378052044276786416687146801019166871467569291668714708284716687147084640
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033216928916928941943042560012241543040x7f7d6d9be0000x7f7d6aa25b00299668299668234502397352655362040337322287858081788628816687147126438166871470828471668714747244516687147474227
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033516928916928941943042560012241562880x7f7d6b391e800x7f7d6aa25b40171645171645172861373168655361031316211268450041426991616687147524095166871474724451668714778236316687147784297
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033816928916928941943042560012241587840x7f7d6b391d000x7f7d6aa25b80297216297216193652377736655361709015012251125068536407616687147825815166871477823631668714817260116687148174524
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034116928916928941943042560012241610240x7f7d6b391b800x7f7d6aa25bc0297438297438192852379512655361666749822254679066844114016687148216102166871481726011668714856427916687148566101
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034416928916928941943042560012241632640x7f7d6b391a000x7f7d6aa25c00205700205700184031645608655361242078751532882049857796416687148607139166871485642791668714889483716687148896660
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034716928916928941943042560012241665280x7f7d6b3918800x7f7d6aa25c40339761339761260182718096655362396879362609469096050176416687148938418166871488948371668714931291516687149333105
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035016928916928941943042560012241685120x7f7d6b3917000x7f7d6aa25c80185470185470185441483768655361064228801363410042744302816687149364644166871493129151668714963995316687149641785
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035316928916928941943042560012241712640x7f7d6d9be5800x7f7d6aa25cc0297856297856197322382856655361819146222263388072941806816687149682854166871496399531668715003339016687150035192
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035616928916928941943042560012241737600x7f7d6d9be4000x7f7d6aa25d00296046296046205072368376655361866693022258654074843253216687150085680166871500333901668715043210816687150433959
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035916928916928941943042560012241762560x7f7d6d9be2800x7f7d6aa25d40225492225492199791803944655361432815571691989057487518816687150475417166871504321081668715077738616687150779227
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036216928916928941943042560012241797760x7f7d6d9be1000x7f7d6aa25d803808033808032779330464326553627202420629326130108984891216687150821616166871507773861668715121818416687151264671
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036516928916928941943042560012241822720x7f7d6b391f800x7f7d6aa25dc0210820210820190651686568655361323270901576982053105474016687151284901166871512181841668715158138216687151583191
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036816928916928941943042560012241855360x7f7d6b391e000x7f7d6aa25e00304505304505225922436048655361863749442315370074725514816687151624599166871515813821668715198362016687152029006
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037116928916928941943042560012241885440x7f7d6b391c800x7f7d6aa25e40309302309302240852474424655361674542432332976067158767616687152040376166871519836201668715241513716687152458452
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037416928916928941943042560012241915520x7f7d6b391b000x7f7d6aa25e80265908265908218982127272655361822799612015715073088142816687152469741166871524151371668715280617516687152808210
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037716928916928941943042560012241958400x7f7d6b3919800x7f7d6aa25ec04617134617133260036937126553634229102735784980137092138016687152850339166871528061751668715329897216687153318703
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038016928916928941943042560012241985920x7f7d6b3918000x7f7d6aa25f00243755243755206071950048655361541192291837817061823376416687153350352166871532989721668715366393016687153665872
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038316928916928941943042560012242023680x7f7d6b3916800x7f7d6aa25f40334893334893232302679152655362042683072566542081884439616687153707571166871536639301668715408344816687154105277
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038616928916928941943042560012242058880x7f7d6d9be5000x7f7d6aa25f80330505330505234562644048655362134547062517320085558556416687154128387166871540834481668715450456516687154529073
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038916928916928941943042560012242094080x7f7d6d9be3800x7f7d6aa25fc0307345307345241492458768655362122000692342398085056637216687154547563166871545045651668715491032316687154912341
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039216928916928941943042560012242144640x7f7d6d9be2000x7f7d6aa260005415975415973574743327846553640223401842212870161070798416687154953789166871549103231668715545240016687155470282
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039516928916928941943042560012242177280x7f7d6d9be0800x7f7d6aa26040272681272681221112181456655361827633792069511073280932016687155504331166871554524001668715583719816687155839010
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039816928916928941943042560012242220160x7f7d6b391f000x7f7d6aa26080363986363986271342911896655362395954962802986096015475616687155886078166871558371981668715628279616687156300005
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040116928916928941943042560012242260480x7f7d6b391d800x7f7d6aa260c03673133673132897129385126553625614300128199870102634722416687156327374166871562827961668715672535316687156744220
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040416928916928941943042560012242300800x7f7d6b391c000x7f7d6aa26100346610346610258712772888655362481140342662418099421462016687156768489166871567253531668715714615116687157163446
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040716928916928941943042560012242359040x7f7d6b391a800x7f7d6aa261406240286240284007249922326553647147945148704830188768956416687157189245166871571461511668715774486716687157763866
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041016928916928941943042560012242394240x7f7d6b3919000x7f7d6aa26180303972303972234502431784655362116599692319982084840216416687157796145166871577448671668715814806516687158150013
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041316928916928941943042560012242442240x7f7d6b3917800x7f7d6aa261c03990593990592745131924806553626789085830762170107334118416687158191612166871581480651668715861766216687158635427
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041616928916928941943042560012242487680x7f7d6b3916000x7f7d6aa262003923543923542794731388406553628266110130274890113242392816687158662686166871586176621668715907878016687159095952
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041916928916928941943042560012242533120x7f7d6d9be4800x7f7d6aa262403882433882432837431059526553627904793329881070111796450816687159122221166871590787801668715952917716687159546727
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221692891692894194304256008242555520x7f7d6d9be3000x7f7d6aa262807199627199624564757597046553653720547656369190215056224416687159571866166871595291771668716019381416687160211305
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042516928916928941943042560012242598400x7f7d6d9be1800x7f7d6aa262c0366403366403269532931232655362457962722806184098495032016687160244704166871601938141668716063701116687160653360
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042816928916928941943042560012242656640x7f7d6d9be0000x7f7d6aa263004704114704113185737632966553635321247136585600141464194416687160680809166871606370111668716114964816687161168813
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043116928916928941943042560012242712320x7f7d6b391e800x7f7d6aa263404728434728433251537827526553635156673536683490140805278416687161192802166871611496481668716166548516687161682736
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341692891692894194304256008242732160x7f7d6b391d000x7f7d6aa263804831774831773329838654246553635264984837495260141233925216687161707505166871616654851668716217188316687162191029
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371692891692894194304256008242757120x7f7d6b391b800x7f7d6aa263c08818218818215383670545766553667449370669247550269971594416687162214608166871621718831668716294499816687162991343
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044016928916928941943042560012242807680x7f7d6b391a000x7f7d6aa264004259654259652999834077286553631682960932983810126908538816687163011572166871629449981668716344099616687163483786
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044316928916928941943042560012242876160x7f7d6b3918800x7f7d6aa264405476875476873580643815046553641098041442751700164570508816687163495336166871634409961668716401939216687164062237
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044616928916928941943042560012242942080x7f7d6b3917000x7f7d6aa264805515315515313608544122566553641587876443063400166530139216687164073727166871640193921668716460226916687164644488
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491692891692894194304256008242969600x7f7d6d9be5800x7f7d6aa264c05635035635033659845080326553641344911243965860165554387216687164655677166871646022691668716517938616687165221909
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521692891692894194304256008242999680x7f7d6d9be4000x7f7d6aa26500104288210428826096483430646553680626190982127190322679023216687165233688166871651793861668716608002116687166114659
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551692891692894194304256008243027200x7f7d6d9be2800x7f7d6aa265407230497230494562957844006553654188762656613830216929218816687166134588166871660799211668716675863716687166806876
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045816928916928941943042560012243054720x7f7d6d9be1000x7f7d6aa265807244827244824459357958646553654308957456742730217410077216687166819016166871667586371668716745991216687167502263
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046116928916928941943042560012243082240x7f7d6b391f800x7f7d6aa265c07213417213414502957707366553654644916056623720218753691216687167514242166871674599121668716815190816687168194430
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641692891692894194304256008243109760x7f7d6b391e000x7f7d6aa266007275087275084516258200726553654871842256988060219661442416687168206399166871681519081668716883270416687168874557
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671692891692894194304256008243132160x7f7d6b391c800x7f7d6aa26640136684913668497794310934800655361063904462108137980425735930816687168886167166871688327041668716993349716687169976161
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701692891692894194304256008243159680x7f7d6b391b000x7f7d6aa26680137371613737167807710989736655361072761096108489480429278669216687169996430166871699334971668717102341116687171089954
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047316928916928941943042560012243187200x7f7d6b3919800x7f7d6aa266c0137369113736917812610989536655361056249450108578010422673892416687171101703166871710234111668717216948416687172236066
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047616928916928941943042560012243214720x7f7d6b3918000x7f7d6aa26700137290213729027814610983224655361068363079108485570427519299616687172247325166871721694841668717330675816687173373778
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791692891692894194304256008243242240x7f7d6b3916800x7f7d6aa26740137625113762517764211010016655361080899329108872340432533934016687173385598166871733067581668717443859116687174506620
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821692891692894194304256008243264640x7f7d6d9be5000x7f7d6aa267802664990266499014335121319928655362115704797211875900846456156816687174519110166871744385911668717641538016687176482445
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851692891692894194304256008243292160x7f7d6d9be3800x7f7d6aa267c02668679266867914367721349440655362129037245212242000851788978416687176502544166871764153801668717835200916687178422690
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048816928916928941943042560012243319680x7f7d6d9be2000x7f7d6aa268002671552267155214246021372424655362125288435212365500850289454816687178435450166871783520091668718035455716687180428314
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049116928916928941943042560012243347200x7f7d6d9be0800x7f7d6aa268402667831266783114301821342656655362121011374212231790848578572816687180440273166871803545571668718236654516687182489045
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941692891692894194304256008243374720x7f7d6b391f000x7f7d6aa268802673562267356214344721388504655362127061107212591660850998604016687182502485166871823665451668718445293316687184558937
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049716928916928941943042560082400x7f7d6b391d800x7f7d6aa268c052566685256668273748420533526553642184664634192512201687560755216687184571076166871844529331668718819995216687188305662