Files
rocm-systems/tests/workloads/TA_CPC/mi100/pmc_perf.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

80 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_CYCLESSQ_BUSY_CYCLESSQ_WAVESSQ_BUSY_CU_CYCLESSQ_WAVE_CYCLESGRBM_COUNTGRBM_GUI_ACTIVETA_TA_BUSY_sumTA_SH_FIFO_BUSY_sumCPC_CPC_STAT_BUSYCPC_CPC_STAT_IDLETA_BUFFER_COALESCED_READ_CYCLES_sumTA_BUFFER_COALESCED_WRITE_CYCLES_sumTA_ADDR_STALLED_BY_TC_CYCLES_sumTA_TOTAL_WAVEFRONTS_sumTA_ADDR_STALLED_BY_TD_CYCLES_sumTA_DATA_STALLED_BY_TC_CYCLES_sumTA_FLAT_WAVEFRONTS_sumTA_FLAT_READ_WAVEFRONTS_sumTA_FLAT_WRITE_WAVEFRONTS_sumTA_FLAT_ATOMIC_WAVEFRONTS_sumTA_FLAT_COALESCEABLE_WAVEFRONTS_sumTA_SH_FIFO_CMD_BUSY_sumTA_SH_FIFO_ADDR_BUSY_sumCPC_CPC_TCIU_BUSYCPC_CPC_TCIU_IDLETA_SH_FIFO_DATA_BUSY_sumTA_SH_FIFO_DATA_SFIFO_BUSY_sumCPC_CPC_STAT_STALLCPC_UTCL1_STALL_ON_TRANSLATIONTA_SH_FIFO_DATA_TFIFO_BUSY_sumTA_SQ_TA_CMD_CYCLES_sumCPC_CPC_UTCL2IU_BUSYCPC_CPC_UTCL2IU_IDLETA_SP_TA_ADDR_CYCLES_sumTA_SP_TA_DATA_CYCLES_sumCPC_CPC_UTCL2IU_STALLCPC_ME1_BUSY_FOR_PACKET_DECODETA_SH_FIFO_ADDR_STARVED_WHILE_BUSY_CYCLES_sumTA_SH_FIFO_CMD_STARVED_WHILE_BUSY_CYCLES_sumCPC_ME1_DC0_SPI_BUSYTA_SH_FIFO_DATA_STARVED_WHILE_BUSY_CYCLES_sumTA_TA_SH_FIFO_STARVED_sumTA_BUFFER_WAVEFRONTS_sumTA_BUFFER_READ_WAVEFRONTS_sumTA_BUFFER_WRITE_WAVEFRONTS_sumTA_BUFFER_ATOMIC_WAVEFRONTS_sumTA_BUFFER_TOTAL_CYCLES_sumTA_BUFFER_COALESCABLE_WAVEFRONTS_sumDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000871499871504335544322560083264640x00x7f4be5a0418040591523844127524288573778933679607035073935073935449151754385312507393000175732081048576037445754104857601048576010485765265218152428399724502077543501645403922711893201554077405419430429044986424194304419430401645500477793032999900000104857612075355475932331120753725690059971207537256933047412075355721433734
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00287149987150432768256002424124800x00x7f4be5a35100225320777575121082107115377128164281648854563266281640001047754096004096409600409669572665906062691000115302023016384279824972163840019972006960319800000409612075355735989601120753725844123271207537258441888712075355736459775
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0048714998715044194304256002424129280x7f4cf17579000x7f4be5a3514017213361554366655362305156013767707321516621516621611925214355972151660001942173952428800524288524288005242882259352522582088747224718001111620600209715229152105112097152002145300194283048520000052428812075355736631033120753725844708871207537258460848612075355737130741
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0068714998715044194304256003624136320x7f4cf17578000x7f4be5a351803173192301796365536449507872240536763966483966484381975443693788396648000350024465242880052428852428800043800801437980207173948120011551198802097152275739638920971520029529003685390564400000012075355737374765120753725846558451207537258490256312075355738013652
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0088714998715044194304256002824140800x7f4cf17577000x7f4be5a351c03237136306854165536457598273448138974046414046414512928245112227404641000356279645242880052428852428800042419247423554737474056540011622243802097152317839881620971520025838003692040343000000012075355738166666120753725850443211207537258532447912075355738786748
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00108714998715044194304256002424145280x7f4cf17576000x7f4be5a3520018039121648439655362441744211825357122548822548822157488219679712254880001929062852428800524288524288005242882262873122617995717223644001131220570209715230132170922097152002187100198867052170000052428812075355738951064120753725854623971207537258558831612075355739384529
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00128714998715044194304256002424149760x7f4cf17575000x7f4be5a3524018066481638748655362432876411813557522583022583022884669227357472258300001981597052428800524288524288005242882275672422744309747225254001124820520209715228992169262097152002183700193059063930000052428812075355739616009120753725856175961207537258574271512075355740051859
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00148714998715044194304256002424154240x7f4cf17574000x7f4be5a35280172914415747946553623314876148010014216142216142223695772229142121614200019850734524288005242885242880052428821883371218695847172120040011344238702097152393521549020971520022702001865510133340000052428812075355740294300120753725858023941207537258592639312075355740712166
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00168714998715044194304256002824161280x7f4cf17573000x7f4be5a352c032015043034676655364524895028604972340018740018744106302440069974001870003576577852428800524288524288000430310514297845776340643800116652059020971523341466340209715200233070035910406760200000012075355740934158120753725859574331207537258620799012075355741549562
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00188714998715044194304256002824168320x7f4cf1757a000x7f4be5a353003165896300898565536448655063108703793957363957364418238744155239395736000360812855242880052428852428800044346465443314417174016680012126205102097152300740162720971520016352003638040353300000012075355741710291120753725863419091207537258658542712075355742332928
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00208714998715044194304256002424175360x7f4cf17579000x7f4be5a35340173087215563486553623044299147953089216358216358217509362162734521635800019005642524288005242885242880052428822708230226876607472244220011286205602097152290221128420971520019308001893230133290000052428812075355742495440120753725867203051207537258684542412075355742912374
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00228714998715044194304256002424182400x7f4cf17578000x7f4be5a3538016928161538207655362280646015217476021160121160122008657219495972116010002017089052428800524288524288005242882232752822303709717224412001129920560209715229142136002097152002236900193875067740000052428812075355743140829120753725868742241207537258699950312075355743554467
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00248714998715044194304256002424189440x7f4cf17577000x7f4be5a353c0172447215617306553623087460150549840215558215558219171462180961821555800020084875524288005242885242880052428821191096211762317472081180011396204202097152290921238120971520024848001859390104780000052428812075355743793311120753725870427021207537258716814112075355744214744
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00268714998715044194304256002824199040x7f4cf17576000x7f4be5a3540032224563062519655364568086633068106640280640280644601226445367604028060003585432552428800524288524288000449275134492165871740413200115432057020971523443409638209715200158620037023807083500000012075355744436526120753725871963011207537258748429812075355745046860
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00288714998715044194304256002824206080x7f4cf17575000x7f4be5a3544031451442975335655364434974434659229439314239314243719296436937623931420003605810652428800524288524288000425228474246119574740538200121762491020971522902399108209715200337250036368807017200000012075355745213971120753725876198171207537258786413412075355745808676
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00308714998715044194304256002424213120x7f4cf17574000x7f4be5a35480168146415222776553622560716156199924210182210182213825082126429721018200019711967524288005242885242880052428821702696216749407172199720011143205902097152279221373720971520023593001856190160910000052428812075355745968573120753725879543731207537258807885212075355746394765
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00328714998715044194304256002424220160x7f4cf17573000x7f4be5a354c0174469615738896553623333621143236678218086218086217463772162171721808600020012792524288005242885242880052428822052002220240527642232770011387202402097152289321703720971520020638001882220110750000052428812075355746626456120753725881070121207537258823213112075355747038641
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00348714998715044194304256002424227200x7f4cf1757a000x7f4be5a35500173716015758776553623405004152045887217144217144225496922248264821714400020063213524288005242885242880052428821367469213546707172083640011564204802097152345122337420971520022128001881060127160000052428812075355747271524120753725882786901207537258840332912075355747695312
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00368714998715044194304256002824236800x7f4cf17579000x7f4be5a355403123576295979565536441933843414732333904463904464333711443313157390446000357406015242880052428852428800041956077418789427474065500011487205202097152278839974920971520030789003616600477700000012075355747914178120753725884316491207537258868012612075355748514203
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00388714998715044194304256002824243840x7f4cf17578000x7f4be5a3558031723043016229655364502803034316561339653739653744252564442225423965370003599943152428800524288524288000434727464341803871741189200120442050020971523032405377209715200328050036409007893300000012075355748676846120753725887428461207537258898876312075355749285877
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00408714998715044194304256002424250880x7f4cf17577000x7f4be5a355c0173242415688556553623222522152554102216552216552218841832175592621655200019742816524288005242885242880052428821443947214290287472091820011507205002097152329521579520971520023727001849760134770000052428812075355749447888120753725890806031207537258920572112075355749873599
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00428714998715044194304256002424257920x7f4cf17576000x7f4be5a3560017523361597240655362365798613749973421904121904122164418219978242190410001995381152428800524288524288005242882133359621320523717210852001144720480209715231692245122097152002213400196003073320000052428812075355750101943120753725892329211207537258935788012075355750519429
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00448714998715044194304256002424264960x7f4cf17575000x7f4be5a35640170047215372156553622786601160131690212558212558218207772172793921255800020197621524288005242885242880052428821363162213565447612073120011188205202097152291722074920971520022393001846040217220000052428812075355750750058120753725893993201207537258952379812075355751169046
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00468714998715044194304256002824277120x7f4cf17574000x7f4be5a356803269136309279065536460442742859551474086414086414428693444118124408641000353408065242880052428852428800044396213443900247174006280012273205002097152307440396020971520015911003708040974700000012075355751390808120753725895521181207537258980635612075355751999459
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00488714998715044194304256002824284160x7f4cf17573000x7f4be5a356c032025763025282655364510524023664723640032140032143498675432275674003210003620779252428800524288524288000450080874499326074740991000125322056020971522903395267209715200342130035805805659800000012075355752164767120753725898677951207537259011211312075355752764140
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00508714998715044194304256002424291200x7f4cf1757a000x7f4be5a3570017115441553161655362298369014863302221394221394221824894217082982139420001983201352428800524288524288005242882187818521860510717214396001140020500209715228992101502097152002237300183258092520000052428812075355752923877120753725902081121207537259033291112075355753344889
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00528714998715044194304256002424300800x7f4cf17579000x7f4be5a3574017145521550282655362288154415437434221431821431821381492212417752143180001967114252428800524288524288005242882308015323052324747230038001135320510209715230922167742097152001948000189616081690000052428812075355753572272120753725903644301207537259048906912075355753984999
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00548714998715044194304256002424307840x7f4cf17578000x7f4be5a35780168316815295876553622665932158236301210395210395214009522130225221039500019504139524288005242885242880052428821300457212697277172124040011273205702097152290421319320971520023108001909240107620000052428812075355754217681120753725905295491207537259065418712075355754622273
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00568714998715044194304256002824320000x7f4cf17577000x7f4be5a357c031556162987104655364450450533465099239445139445143660122436317673944510003528111352428800524288524288000436332424362085774739640600115362061020971523588399806209715200274050035802201992400000012075355754849064120753725906855471207537259093626512075355755452045
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00588714998715044194304256002824329600x7f4cf17576000x7f4be5a358003186952303248565536452474532580458683983683983684382734643617040398368000352300815242880052428852428800042372898423179977174009720012403205002097152349739703320971520028190003688580344000000012075355755611842120753725910324241207537259127578112075355756210063
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00608714998715044194304256002424339200x7f4cf17575000x7f4be5a35840169676015298636553622685746155447852212094212094217491772165259621209400020024604524288005242885242880052428822036363220204597472148940010942205702097152343621003820971520022802001846320132330000052428812075355756341838120753725913903401207537259151449912075355756747562
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00628714998715044194304256002424348800x7f4cf17574000x7f4be5a35880177179215991306553623706191144404598221473221473217916122152944822147300019537954524288005242885242880052428821601915215755877172165000011464205902097152289721602520971520023751001892760209100000052428812075355756949367120753725915456991207537259167113812075355757383403
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00648714998715044194304256002424358400x7f4cf17573000x7f4be5a358c0173492815765216553623348160154260653216865216865222304152213368721686500019681809524288005242885242880052428821301470212920227472069180011199206602097152327620807820971520020696001848180232770000052428812075355757614643120753725917116171207537259183673612075355758035685
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00668714998715044194304256002824373120x7f4cf1757a000x7f4be5a3590031554722996819655364460299432594993839443339443343710356436824523944330003647917452428800524288524288000447048924469979171740205200125952042020971522786388016209715200337890036774805312800000012075355758251777120753725918634561207537259210889312075355758851231
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00688714998715044194304256002824382720x7f4cf17579000x7f4be5a359403205792304242765536453354143138176234007234007234445220444400786400723000351663665242880052428852428800043609326436045997473912300012427205902097152289339977320971520033779003648200358300000012075355759013132120753725922268121207537259247065012075355759626582
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00708714998715044194304256002424392320x7f4cf17578000x7f4be5a35980180086416399246553624286703137336612225107225107227676212260979022510700019472544524288005242885242880052428821475646214502927172143240011512200302097152290821517320971520022389001893000323110000052428812075355759780688120753725925820091207537259270680812075355760204125
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00728714998715044194304256002424401920x7f4cf17577000x7f4be5a359c0175276015889496553623422649156565738219094219094220959222188546321909400019167398524288005242885242880052428821253414211999377472234380011617206702097152278721870220971520024840001842460281130000052428812075355760426037120753725927340071207537259285992612075355760849053
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00748714998715044194304256002424411520x7f4cf17576000x7f4be5a35a00173484015785126553623290277143683661216854216854221459212203546921685400019378587524288005242885242880052428821372384213580497172089880011439205002097152289721366420971520018962001831700120650000052428812075355761088197120753725928992861207537259302328512075355761512285
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00768714998715044194304256002824426240x7f4cf17575000x7f4be5a35a403200096303652965536452032952503381684000114000114236812741921652400011000342947585242880052428852428800044013151439997887474004460012270197802097152306040687720971520028655003628830529400000012075355761737424120753725930544841207537259330360212075355762344201
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00788714998715044194304256002824435840x7f4cf17574000x7f4be5a35a803247712309518965536461366873181395264059634059634451639644386760405963000363083165242880052428852428800043897666438862237173959400011686205602097152293639336920971520034631003683840741900000012075355762475445120753725933501621207537259359655912075355763093233
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00808714998715044194304256002424445440x7f4cf17573000x7f4be5a35ac0170610415422236553622777842153786869213262213262214913262135900521326200019736816524288005242885242880052428821386904213595087472142300011542205702097152290021446920971520024172001840460140520000052428812075355763248411120753725936424791207537259376791812075355763658543
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00828714998715044194304256002424457600x7f4cf1757a000x7f4be5a35b00171854415570016553622931360159052476214817214817215269912132295621481700019043646524288005242885242880052428822164465221184107152275980011680238902097152291321636920971520025924001831740196910000052428812075355763885004120753725937989571207537259392519612075355764315514
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00848714998715044194304256002424467200x7f4cf17579000x7f4be5a35b40170260015357396553622767473158650228212824212824218914352181734121282400019476863524288005242885242880052428821287788212314067472190540011382204202097152301920677520971520021879001881080196780000052428812075355764551563120753725939651961207537259408983412075355764970010
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00868714998715044194304256002824484480x7f4cf17578000x7f4be5a35b8032494643081893655364589593032586701640618240618244096242438031604061820003535127552428800524288524288000449266254487294471741725200124672040020971522898411040209715200312730038428304833700000012075355765193315120753725941173541207537259436919212075355765809270
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00888714998715044194304256002824494080x7f4cf17577000x7f4be5a35bc032015443032500655364521779131901862140019240019244237132441837464001920003574143752428800524288524288000444813124447181774740035000117352408020971522894392508209715200318260036723102768300000012075355765963136120753725944149511207537259466134912075355766573710
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00908714998715044194304256002424503680x7f4cf17576000x7f4be5a35c00172632815638816553623171029151158208215790215790222517032214855921579000019355035524288005242885242880052428821680443216588957172129080011610238602097152279521574320971520021453001807380235860000052428812075355766730692120753725947066281207537259483174712075355767149851
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00928714998715044194304256002424515840x7f4cf17575000x7f4be5a35c40182783216543806553624368869152016130228478228478213242092064220422847800017600956524288005242885242880052428820633154205474777472249340012215208202097152318021716520971520025767001882640710050000052428812075355767378566120753725948605471207537259498758612075355767800981
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00948714998715044194304256002424525440x7f4cf17574000x7f4be5a35c80170812815515006553622995336157174132213515213515217304602164310921351500019772076524288005242885242880052428821235691211881507172169400011393205002097152279421167920971520021642001898520207300000052428812075355768015980120753725950333451207537259515878412075355768436381
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00968714998715044194304256002824542720x7f4cf17573000x7f4be5a35cc033055283133623655364663669330635327041319041319043882048433384174131900003724038252428800524288524288000452399344517955774742138200120892049020971523486418619209715200289370038240707388800000012075355768663573120753725951861441207537259544454112075355769286160
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00988714998715044194304256002824554880x7f4cf1757a000x7f4be5a35d0032247603067327655364580351235028563540309440309445088694450691044030940003559322552428800524288524288000448923764488798771740262000122932050020971522899404623209715200328290034613602703500000012075355769436890120753725954858211207537259573605912075355770045591
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001008714998715044194304256002424567040x7f4cf17579000x7f4be5a35d40174094415763056553623351145149343497217617217617218397952163420221761700019502749524288005242885242880052428822075851220575217472157180011540239602097152290920865320971520022037001847700147500000052428812075355770205859120753725957779781207537259590293712075355770621501
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001028714998715044194304256002424581760x7f4cf17578000x7f4be5a35d801835664167686165536246341421538477962294572294572084796819837463229457000173898475242880052428852428800524288188054901862669271722953200119952051020971523290223639209715200267330019405901208410000052428812075355770849144120753725959314171207537259606021512075355771284133
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001048714998715044194304256002424593920x7f4cf17577000x7f4be5a35dc0174305615808816553623363765150222244217881217881218206742164378521788100019948749524288005242885242880052428821847716218347477472127660011445206702097152289521477920971520023952001887140329860000052428812075355771520221120753725961016551207537259622645412075355771933720
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001068714998715044194304256002824613760x7f4cf17576000x7f4be5a35e00328082431187396553646396559344212549410102410102447510504453210341010200035201886524288005242885242880004189106841760919717409892001204122340209715229084086942097152003325400365519013978500000012075355772151324120753725962546141207537259651333112075355772771627
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001088714998715044194304256002824625920x7f4cf17575000x7f4be5a35e403173216299954465536447337303089679973966513966514393987443898424396651000367493715242880052428852428800043819512437955657474039660012499205702097152336845836120971520031566003635280389500000012075355772926855120753725965525311207537259679860812075355773540586
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001108714998715044194304256002424638080x7f4cf17574000x7f4be5a35e80173511215749476553623335459154339855216888216888218671582170278321688800020203825524288005242885242880052428821720057216841627202187050011482209202097152290721671820971520025095001881660230460000052428812075355773672911120753725968434081207537259696804712075355774090898
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001128714998715044194304256002424652800x7f4cf17573000x7f4be5a35ec01827656163126965536239255801764251352284562284561810693216703223228456000157497925242880052428852428800524288159760841566880874722775800120991987020971522782219972209715200281340019037903023950000052428812075355774317740120753725969957261207537259712292512075355774745314
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001148714998715044194304256002424664960x7f4cf1757a000x7f4be5a35f00173852815849046553623483784151558197217315217315221312072192831321731500019263030524288005242885242880052428821590613215647487172142520011543204202097152279221425020971520021875001885830215900000052428812075355774983627120753725971632451207537259728804412075355775405391
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001168714998715044194304256002824684800x7f4cf17579000x7f4be5a35f4032810163108103655364615773630983108741012641012643508614429359834101260003235528852428800524288524288000379020403767188874740137400125802057020971522789404156209715200326220036433101596100000012075355775626131120753725973168431207537259757988112075355776243197
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001188714998715044194304256002824696960x7f4cf17578000x7f4be5a35f8031774403020655655364497976633480086039717939717944255381442240913971790003556550452428800524288524288000445156204450570510844602450012399205702097152333140579920971520034434003503270373300000012075355776390882120753725976234001207537259786851812075355776998711
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001208714998715044194304256002424709120x7f4cf17577000x7f4be5a35fc0166004815027666553622264330161329825207505207505209249232080020920750500019435691524288005242885242880052428822379974223394727912289860011690204902097152289221346220971520024952001978440172570000052428812075355777161544120753725979104381207537259803523612075355777570654
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001228714998715044194304256002424723840x7f4cf17576000x7f4be5a36000177422416166176553623907888188549173221777221777129559571130857822177700011121887524288005242885242880052428810544809998453575422660700120192442020971522908221973209715200277780019116003786590000052428812075355777797265120753725980664361207537259820403512075355778230570
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001248714998715044194304256002424736000x7f4cf17575000x7f4be5a36040176008015996576553623641937146873468220009220009219189702162556722000900019584333524288005242885242880052428821356005213372697472105500011487205902097152290321093020971520024916001838560207530000052428812075355778463172120753725982449941207537259837011312075355778882271
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001268714998715044194304256002824758400x7f4cf17574000x7f4be5a36080334316031708956553647181323339552724417894417894447175674436181341789400032482651524288005242885242880004229335642167426717415852001247219870209715227864197602097152003783000380363018489500000012075355779089907120753725983969931207537259866115012075355779705260
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001288714998715044194304256002824770560x7f4cf17573000x7f4be5a360c031846723007710655364483178533113593339808339808344096904440732053980830003459097052428800524288524288000433326644332378374739251800119942114020971522900390461209715200281930036449808424300000012075355779866650120753725987032301207537259894866812075355780484488
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001308714998715044194304256002424782720x7f4cf1757a000x7f4be5a36100169036015229806553622582907140616712211294211294209472682069618621129400019473562524288005242885242880052428821173014211406567172145800011562205602097152276222620020971520020738001965540174460000052428812075355780644265120753725989950671207537259912018612075355781061691
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001328714998715044194304256002424800000x7f4cf17579000x7f4be5a36140184549616734836553624782238199050889230686230686105657718751953230686000661495652428800524288524288005242889478211887330974723037400119612065020971522901228349209715200271270019829106036170000052428812075355781289404120753725991481861207537259929106412075355781722168
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001348714998715044194304256002424812160x7f4cf17578000x7f4be5a36180170944815509716553622922246151991692213680213680217288542152987121368000018914005524288005242885242880052428821432064213741217172218760011452204302097152290621686420971520024036001818800188180000052428812075355781958938120753725993313841207537259945698312075355782377967
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001368714998715044194304256002824834560x7f4cf17577000x7f4be5a361c0326633630676026553645601068342087030408291408291434952374318026340829100033201840524288005242885242880004420530844126935747419654001274220270209715229104186352097152003093400373135019641400000012075355782599899120753725994848231207537259973890012075355783208329
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001388714998715044194304256002824849280x7f4cf17576000x7f4be5a3620032098483034096655364511063223230578940123040123042381424419055584012300003545828852428800524288524288000445306214452485271740059600124372041020971522912400185209715200330980035814206538100000012075355783366563120753725997829001207537260002753712075355783977569
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001408714998715044194304256002424864000x7f4cf17575000x7f4be5a36240176959216008096553623702286143169447221198221198218593582156820922119800019368195524288005242885242880052428822363369223220417472236940011303204002097152291822051620971520024822001860840159960000052428812075355784140111120753726000812971207537260020689612075355784558118
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001428714998715044194304256002424881280x7f4cf17574000x7f4be5a3628019135521762495655362611906420817339523919323919390356857262305239193000467363052428800524288524288005242886510933575763971723821200119992002020971522913236904209715200285250020664807143410000052428812075355784756947120753726002345751207537260038545412075355785191314
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001448714998715044194304256002424896000x7f4cf17573000x7f4be5a362c0172519215624046553623068394150847992215648215648215508212128053021564800020138183524288005242885242880052428822313348222966417472191740011545205002097152290021537320971520021137001823060191710000052428812075355785444224120753726004435331207537260056865212075355785864355
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001468714998715044194304256002824920960x7f4cf1757a000x7f4be5a36300333083231586856553646958497327517565416353416353418543064099426241635300034557420524288005242885242880004213413841996377717416932001234219770209715229004155252097152003617700370971016028700000012075355786089162120753726005961721207537260084800912075355786711268
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001488714998715044194304256002824935680x7f4cf17579000x7f4be5a3634031507122989582655364460799934229348439383839383843613015435688363938380003562564952428800524288524288000444185044439937676340445400123722058020971522903397538209715200331100036124401421400000012075355786870925120753726008904091207537260113584712075355787485918
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001508714998715044194304256002424950400x7f4cf17578000x7f4be5a36380183048016553596553624522977152165843228809228809227001802236240022880900019233550524288005242885242880052428821051049210215807172102520011620218602097152310421838620971520025363001859860259300000052428812075355787644973120753726011883261207537260131392512075355788063491
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001528714998715044194304256002424967680x7f4cf17577000x7f4be5a363c020095041846660655362743371321948549625118725118775630165931965251187000328809352428800524288524288005242886100968534965074725410200120792049020971522900249861209715200291330021888207772650000052428812075355788292316120753726013430451207537260150032312075355788730280
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001548714998715044194304256002424982400x7f4cf17576000x7f4be5a36400173928015756736553623246000150179745217409217409214604902117425321740900019109712524288005242885242880052428821733106217112147172153640011800205902097152348322195120971520024213001914800286110000052428812075355788964856120753726015414431207537260166720212075355789394795
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015687149987150441943042560028241007360x7f4cf17575000x7f4be5a36440323916030493456553645159863314402900404894404894374388113603365040489400026169354524288005242885242880003621132235889900747410206001309620520209715232913996392097152003395400371083044220600000012075355789611046120753726016964811207537260195503912075355790226811
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015887149987150441943042560028241022080x7f4cf17574000x7f4be5a3648031806643016183655364490947327412189339758239758243555105433781753975820003575208852428800524288524288000445496274454012971740296400124162372020971522721393152209715200279190036336007708500000012075355790358846120753726019980781207537260224303612075355790932292
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016087149987150441943042560024241036800x7f4cf17573000x7f4be5a364c0180594416343436553624167809146659164225742225742224368812206526322574200019657028524288005242885242880052428822297388222493727472267740011331204302097152358221683520971520023731001933600436040000052428812075355791118387120753726022934361207537260241903412075355791544038
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016287149987150441943042560024241056640x7f4cf1757a000x7f4be5a3650020985681940825655362882984623475346526232026232070104655434376262320000328660452428800524288524288005242885895721512543371726231600121272051020971522904262098209715200290220022858207722320000052428812075355791768986120753726024467141207537260261231212075355792229322
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016487149987150441943042560024241071360x7f4cf17579000x7f4be5a36540173760815703486553623194479154752977217200217200218151132158617821720000019841180524288005242885242880052428821541951215032237472188700011574206502097152306921074020971520024814001877520217880000052428812075355792462365120753726026531121207537260277887112075355792874621
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016687149987150441943042560028241098880x7f4cf17578000x7f4be5a36580329710431214996553646362766321126713412137412137344959533247227641213700025404255524288005242885242880002798881827365810717412548001293619470209715233154051342097152003546000374363036487700000012075355793100781120753726028067111207537260306814812075355793722616
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016887149987150441943042560028241113600x7f4cf17577000x7f4be5a365c032024643021197655364501847232287868940030740030744158536441271484003070003559907952428800524288524288000443226034431665974739951800124152067020971523844396934209715200288820036627001879500000012075355793883485120753726031139081207537260336014512075355794493569
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017087149987150441943042560024241128320x7f4cf17576000x7f4be5a36600178038416065716553623756490148242588222547222547217849692140623522254700019363383524288005242885242880052428821564397214972457172231720011978207202097152289821512020971520024240001926620368840000052428812075355794654869120753726034020651207537260352766412075355795077674
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017287149987150441943042560024241148160x7f4cf17575000x7f4be5a3664022125122050662655363045486024491857127656327656369926685461998276563000245669152428800524288524288005242884985349425832774727559800122271984020971523487273858209715200301740024005407856510000052428812075355795304025120753726035555031207537260372782212075355795761936
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017487149987150441943042560024241162880x7f4cf17574000x7f4be5a36680178463216235956553623948937155740595223078223078221209272180466922307800018786011524288005242885242880052428822505861224717237172247000011650205802097152293021635220971520024177001945400162780000052428812075355795992324120753726037700611207537260389598012075355796413827
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017687149987150441943042560028241190400x7f4cf17573000x7f4be5a366c0323408030507706553645367288327231894404259404259273081972461762340425900020826413524288005242885242880002349226122719116747412230001268620650209715229014017812097152003753000363055072389700000012075355796634788120753726039246201207537260417981712075355797252455
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017887149987150441943042560028241207680x7f4cf1757a000x7f4be5a36700326294430950796553646123006307792593407867407867446179714451859840786700033763778524288005242885242880004403980644032959717399108001260720670209715228043940452097152003033000357806015951500000012075355797409948120753726042239771207537260447309512075355798022516
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018087149987150441943042560024241224960x7f4cf17579000x7f4be5a36740179470416256446553624002617146765806224337224337218947612141651022433700019785183524288005242885242880052428822244769221992607472260540011654203702097152290222134720971520023308001951860278840000052428812075355798177564120753726045146941207537260464125312075355798600440
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018287149987150441943042560024241247360x7f4cf17578000x7f4be5a3678023116882158634655363210974326113318328896028896068502745395499288960000245501452428800524288524288005242885065450433702071728879600125132066020971522899287174209715200318440025290007967500000052428812075355798822453120753726046687731207537260485101112075355799365461
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018487149987150441943042560024241264640x7f4cf17577000x7f4be5a367c0185236016732596553624745545147376391231544231544219125932139815423154400020059384524288005242885242880052428820876245208062667472234460011631243302097152284422348520971520024568001905240434000000052428812075355799530067120753726048918111207537260501820912075355799953434
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018687149987150441943042560020241279360x7f4cf17576000x7f4be5a368003287712312324965536464641233773551144109634109632257581915253253410963000278974152428800524288524288000973210962996617174096520013027205802097152290440660120971520035607003647060358714200000012075355800172601120753726050474891207537260531068612075355800782555
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018887149987150441943042560028241296640x7f4cf17575000x7f4be5a3684031844162998148655364451070928406214139805139805143015001428472653980510003571682352428800524288524288000440932714408521174739933400125312056020971522909398293209715200331950035670806623300000012075355800937362120753726053543661207537260560156412075355801842133
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019087149987150441943042560024241313920x7f4cf17574000x7f4be5a36880174720815902796553623475296145205791218400218400217927112133585821840000019396654524288005242885242880052428821350544213262857172122520011739204902097152290722583020971520021517001989760494830000052428812075355802058626120753726056441231207537260576956212075355802640066
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019287149987150441943042560024241336320x7f4cf17573000x7f4be5a368c024160082251541655363347975827280458430200030200066820245220295302000000222326852428800524288524288005242884896124417995676330499000123571985020971522900301310209715200316090026397807705900000052428812075355802902163120753726057985221207537260598988012075355803566457
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019487149987150441943042560024241353600x7f4cf1757a000x7f4be5a36900178143216247036553623911572147795427222678222678215028182093070222267800019200505524288005242885242880052428821325402212629037172216440011951204802097152279620911820971520026954001864550349300000052428812075355803772410120753726060359601207537260616267812075355804324666
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019687149987150441943042560020241368320x7f4cf17579000x7f4be5a369403483792331973565536494375884037891744354734354732260241214686917435473000161860752428800524288524288000892032053165187474341820013365205002097152280043173720971520039579003922600371640900000012075355804578959120753726061906781207537260647275512075355805328672
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019887149987150441943042560028241385600x7f4cf17578000x7f4be5a3698031567282995188655364453857531868491239459039459043494333434472143945900003507042552428800524288524288000408274464072630671740704400124522067020971522794404207209715200325460036663106943100000012075355805520819120753726065167551207537260676651212075355806247549
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020087149987150441943042560024241402880x7f4cf17577000x7f4be5a369c0180077616125896553623833829149840530225096225096215841692103766922509600018479217524288005242885242880052428820864576207843917472233180011734204102097152319622595020971520027886001982150528360000052428812075355806431521120753726068121121207537260693739112075355806971084
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020287149987150441943042560024241427840x7f4cf17576000x7f4be5a36a0026250322475226655363679409929971992232812832812869042155365667328128000237181952428800524288524288005242885201949440177471732946000125792056020971523402329432209715200339450029033808267500000052428812075355807233221120753726069663511207537260721114812075355807911421
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020487149987150441943042560024241447680x7f4cf17575000x7f4be5a36a40184091216621706553624542925152111744230113230113215996442090100223011300019271105524288005242885242880052428820003370198982427472203740011789205002097152318122157220971520025191001949790661750000052428812075355808118436120753726072716281207537260739994612075355808670672
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020687149987150441943042560020241457280x7f4cf17574000x7f4be5a36a8041261763604740655365369405143824458151577151577123249588148002344532436252800131924752428800524288524288000871354050210887174680040013412200802097152334351224320971520016688004228920380165600000012075355808922930120753726074281061207537260773450312075355809736091
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020887149987150441943042560028241477120x7f4cf17573000x7f4be5a36ac031934643015716655364489823935442792639918239918244008432439862473991820003507871652428800524288524288000445761214456971674740401400126032433020971523339400494209715200337920036261508413200000012075355809929581120753726077735431207537260802074012075355810659778
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021087149987150441943042560024241496960x7f4cf1757a000x7f4be5a36b00179504016179666553623813308154923549224379224379211914112065648222437900018042955524288005242885242880052428820072652199695067172226760011904201802097152289922612720971520024875001889790624540000052428812075355810846334120753726080645801207537260819209912075355811397759
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021287149987150441943042560024241521920x7f4cf17579000x7f4be5a36b4028580642694517655363999112232503741535725735725769382955349472357257000235929052428800524288524288005242885121705432091776335680600128302432020971522922353488209715200368580031576208308030000052428812075355811657512120753726082199391207537260844745612075355812363083
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021487149987150441943042560024241541760x7f4cf17578000x7f4be5a36b80181366416483626553624227120149072045226707226707207250861981336022670700019221541524288005242885242880052428820370453202644077172209720011649204902097152383121753820971520025877002010320755530000052428812075355812569376120753726085032961207537260863017512075355813103318
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021687149987150441943042560020241556480x7f4cf17577000x7f4be5a36bc043631683867703655365759699947203802254539554539523058084144940614830376235800142736052428800524288524288000866238649567907475018140012000243102097152345650076920971520044322004541340381273000000012075355813356829120753726086580141207537260901561112075355814181442
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021887149987150441943042560028241576320x7f4cf17576000x7f4be5a36c003258656307750065536456858302718680664073314073314324015742892386407331000365119705242880052428852428800043426798434144107173969800012911206502097152290838916520971520035893003598120387000000012075355814366465120753726090591301207537260931400812075355815096662
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022087149987150441943042560024241596160x7f4cf17575000x7f4be5a36c40181733616457416553624253287154002812227166227166204408181953994222716600017451520524288005242885242880052428818721933185705147472144460011665206402097152289722033720971520027336001908990851830000052428812075355815281536120753726093586481207537260948664612075355815817772
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022287149987150441943042560024241623680x7f4cf17574000x7f4be5a36c8030566322898715655364308876035225344838207838207867065765152620382078000243366052428800524288524288005242885083195429733071738085200130942064020971522892378654209715200371420033864008314870000052428812075355816058760120753726095191261207537260976376412075355816717474
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022487149987150441943042560024241646080x7f4cf17573000x7f4be5a36cc01807736163044765536238878591677208752259662259661938325018234880225966000163343705242880052428852428800524288177859871755723976322207800124872051020971522796217173209715200267320018621801872180000052428812075355816869446120753726098218431207537260995080212075355817393029
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022687149987150441943042560020241663360x7f4cf1757a000x7f4be5a36d004581904442339865536659551215416045965727375727372369433114697726572737000128506152428800524288524288000909886253400937175734680014207206002097152277457073920971520048867005192600386149500000012075355817627134120753726099784821207537261035383812075355818407965
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022887149987150441943042560028241685760x7f4cf17579000x7f4be5a36d40329919231333966553646529690322370858412398412398433838704313097341239800032989059524288005242885242880004317837343125142747410638001296820670209715228964073772097152003755000354843014441000000012075355818573402120753726103995981207537261065207512075355819241894
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023087149987150441943042560024241708160x7f4cf17578000x7f4be5a36d801757920159332365536233988471705067782197392197391804219516444737219739000165306145242880052428852428800524288172090581694061571722926800121892051020971523389226036209715200278460019128402061200000052428812075355819402112120753726106939951207537261082215312075355819887133
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023287149987150441943042560024241740800x7f4cf17577000x7f4be5a36dc034831043317681655364939673140518789243538743538768301785271139435387000226428752428800524288524288005242885049301422918274143389200132911988020971523016432170209715200402680038837208020600000052428812075355820121088120753726108498331207537261112855112075355820802705
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023487149987150441943042560024241765760x7f4cf17576000x7f4be5a36e001741344158606465536234012761866354012176672176671424730012252081217667000964408752428800524288524288005242889809507920124971722247600123322060020971522813221380209715200263000019144603602830000052428812075355820981306120753726111880701207537261132214912075355821457662
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023687149987150441943042560020241777920x7f4cf17575000x7f4be5a36e4051396644985066655367439492061225880464245764245723970849147818806424570001608318524288005242885242880009160288537257010196792540014784206702097152315364147220971520052279005863940388074100000012075355821683702120753726113501481207537261177318412075355822529944
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023887149987150441943042560028241802880x7f4cf17574000x7f4be5a36e80328152830632076553645382344287869219410190410190314881643018096741019000027174117524288005242885242880003765733937483572774417739001254920480209715228924020932097152003481400372679026501300000012075355822693929120753726118226241207537261208150112075355823348926
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024087149987150441943042560024241827840x7f4cf17573000x7f4be5a36ec0175969616004066553623706402189666095219961219961135653551151064121996100093341525242880052428852428800524288105802671000662375422513500117982051020971522793220385209715200282360019181205805400000052428812075355823517780120753726121290211207537261226518012075355823980790
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024287149987150441943042560024241863040x7f4cf1757a000x7f4be5a36f0039031363741956655365568286745586218448789148789168786915258946487891000224238952428800524288524288005242885032244426971674748696600137422059020971522895485403209715200167300043918807753560000052428812075355824217590120753726122931791207537261263701612075355824927459
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024487149987150441943042560024241893120x7f4cf17579000x7f4be5a36f4019307041774031655362636048921308991624133724133774715775107890241337000200331752428800524288524288005242884883852402460771724140400120381977020971523459239622209715200280400020781008640070000052428812075355825107373120753726126971751207537261284853412075355825586233
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024687149987150441943042560020241907840x7f4cf17578000x7f4be5a36f8062810326114394655369119509074937847778512878512824951013151917277851280001345249524288005242885242880008552017467832910198098620011677243702097152291778133320971520059836007184260393805500000012075355825815469120753726128765341207537261339332912075355826745768
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024887149987150441943042560028241937920x7f4cf17577000x7f4be5a36fc0364485634622006553651181456365884431455606455606250988742356018645560600016625109524288005242885242880002195382421470426774461299001317020650209715229224562952097152004401300410483043653200000012075355826916715120753726134434081207537261374212512075355827621084
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025087149987150441943042560024241968000x7f4cf17576000x7f4be5a3700019708321816159655362700416721706341224635324635373218184975904246353000160049652428800524288524288005242884786339392988275424599900121272067020971522790243283209715200289140021191208354750000052428812075355827785540120753726137875651207537261394116312075355828284226
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025287149987150441943042560024242010880x7f4cf17575000x7f4be5a3704047460404585018655366838741556025846059325459325468257335353138593254000234065152428800524288524288005242885212234443145674759467000142432060020971523349629148209715200491740053827609682030000052428812075355828509365120753726139744431207537261435971912075355829303811
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025487149987150441943042560024242046080x7f4cf17574000x7f4be5a3708022273842069647655363078113225054689227842227842275439795211632278422000158788052428800524288524288005242884885579403450271727756400122652051020971523247276586209715200308350024184808676800000052428812075355829486220120753726144240391207537261459971712075355829987692
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025687149987150441943042560020242060800x7f4cf17573000x7f4be5a370c073924007235436655361079952728887093739240499240492457803414786002924049000126296752428800524288524288000850317446519677479249820016414230402097152289392265220971520070560008502020391584700000012075355830215054120753726146291571207537261525251112075355831218338
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025887149987150441943042560028242096000x7f4cf1757a000x7f4be5a3710040043443845538655365716113846317451550054250054217702892157923715005420007338113524288005242885242880001352926512846718717501004001374320490209715229065006002097152004381200453271065537100000012075355831360562120753726152992301207537261565538712075355832118771
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026087149987150441943042560024242131200x7f4cf17579000x7f4be5a3714022578482099771655363124971325484351228223028223075070115176974282230000152596852428800524288524288005242884659660380001774728023800122952052020971522781277949209715200306680024503608371840000052428812075355832284269120753726157056271207537261588354512075355832794066
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026287149987150441943042560024242181760x7f4cf17578000x7f4be5a3718055749045417855655368086581866454418969686269686268908655381620696862000245547452428800524288524288005242885226887450425471769882000150362051020971522891694918209715200550600063824408918660000052428812075355833032860120753726159155451207537261637026012075355833884432
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026487149987150441943042560024242222080x7f4cf17577000x7f4be5a371c025065122343281655363487026628480125731331331331373561135046030313313000159293452428800524288524288005242884756058390820874731287000124422060020971522884311749209715200319140027513208677320000052428812075355834072762120753726164334601207537261663361812075355834665183
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026687149987150441943042560020242239360x7f4cf17576000x7f4be5a37200858747283590526553612474623410283973161073433107343324849439148213251010773626600011798695242880052428852428800090381085155984717106482000175282058020971522914106275220971520076176009828920395092400000012075355834829939120753726166771371207537261738113012075355835945001
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026887149987150441943042560028242279680x7f4cf17575000x7f4be5a37240455980043754406553665169894515132633569974569974157898941393886156997400044913175242880052428852428800012211612115044211019606950001409020030209715227905669482097152004809600513034070065600000012075355836113474120753726174288101207537261780080612075355836879277
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027087149987150441943042560024242320000x7f4cf17574000x7f4be5a3728025304402374359655363533963428877589031630431630473149304939369316304000165141152428800524288524288005242884652277389185879131929800123112050020971522808315682209715200327370027977608398670000052428812075355837052719120753726178468861207537261804880412075355837648136
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027287149987150441943042560024242378240x7f4cf17573000x7f4be5a372c064179766257577655369338563576858588680224680224670808615528320802246000261398452428800524288524288005242885433029470402176880212900157262058020971522892803094209715200623880073543409233610000052428812075355837815967120753726180984041207537261862447812075355838752418
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027487149987150441943042560024242423680x7f4cf1757a000x7f4be5a3730027822882628926655363914081731991345534778534778571770014933073347785000149907052428800524288524288005242884843168401766974734819800126272018020971522905347385209715200341410030941608591690000052428812075355838928805120753726186873581207537261891103612075355839557574
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027687149987150441943042560020242435840x7f4cf17579000x7f4be5a37340967956094861346553614166069511696619421209944120994425484974152802121147349625950093789552428800524288524288000876566548505747171206876001842220560209715237841204818209715200844300011161460397627200000012075355839724494120753726189575951207537261975710812075355840925545
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027887149987150441943042560028242481280x7f4cf17578000x7f4be5a37380511035249398856553673632199603230709638793638793160468091403292663879300041393675242880052428852428800011697727109647881019670486001467620650209715228016360812097152005289800578520070146000000012075355841093618120753726198052671207537262022654312075355841904805
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028087149987150441943042560024242526720x7f4cf17577000x7f4be5a373c028103122655595655363953227132298513935128835128873370724971271351288000152473152428800524288524288005242884742472388169977435227500125712065020971522893350829209715200344070031231208578980000052428812075355842065083120753726202799831207537262050510012075355842706665
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028287149987150441943042560024242592640x7f4cf17576000x7f4be5a37400728116871163196553610624717787493008791014591014574229705837470910145000276001152428800524288524288005242885685174491382375490992700164142314020971522914906167209715200670930083529209061370000052428812075355842874938120753726205558201207537262115149412075355843879955
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028487149987150441943042560024242648320x7f4cf17575000x7f4be5a37440334298431860226553647383616386680345417872417872762367854616304178720002126269524288005242885242880052428852477124384814747419574001332720510209715229004147662097152004039500373822010445410000052428812075355844062164120753726212116541207537262148061112075355844726618
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028687149987150441943042560020242663040x7f4cf17574000x7f4be5a3748011906016117404286553617524301314459161331488251148825125188835148947181488251000903918524288005242885242880009025064513540271714853000020328205102097152289814857832097152001019400013810270398571700000012075355844891875120753726215265311207537262251228112075355846301264
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028887149987150441943042560028242718720x7f4cf17573000x7f4be5a374c0620628860412796553690149329738984464775785775785147288871286574177578500044208335242880052428852428800011366976106988051019803454001568020510209715227877745022097152006057100710520072253500000012075355846469787120753726225594811207537262307483612075355847384036
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029087149987150441943042560024242774400x7f4cf1757a000x7f4be5a3750033784883212961655364779318839065656042231042231075786555440515422310000219921152428800524288524288005242885297962443960377442065100131831996020971523330419079209715200409690037525809755030000052428812075355847547620120753726231258751207537262339723312075355848218707
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029287149987150441943042560012242799360x7f4cf17579000x7f4be5a3754090049208848443655361321149841090846001112561411256141868600486242011125614000715696524288005242885242880052428876765813987787754112528700177692049020971522902112323520971520079890001040676037641060000052428812075355848356553120753726234437921207537262418170512075355849514565
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029487149987150441943042560024242865280x7f4cf17578000x7f4be5a37580389492037387436553655690707456593272486864486864754785453843744868640002070120524288005242885242880052428851237754268686747487030001399220430209715229124855692097152004343800439084010034690000052428812075355849691694120753726242423441207537262455770112075355850393739
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029687149987150441943042560020242880000x7f4cf17577000x7f4be5a375c0141642961398196765536208831282172533510817705361770536260089041507872617705360001349939524288005242885242880009074413510588171717669320021971205902097152399817648202097152001184460016442100403813300000012075355850557152120753726246029811207537262577689012075355852118654
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029887149987150441943042560032242945920x7f4cf17576000x7f4be5a37600737742472174606553610763110280703583492217792217716039021139095859221770004230009524288005242885242880001141360110693666764921445001619220670209715228979156892097152006508000851395076537700000012075355852286686120753726258236091207537262643464312075355853302984
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030087149987150441943042560024243011840x7f4cf17575000x7f4be5a37640393912837836816553656374641461998681492390492390742623154250744923900002009422524288005242885242880052428851634524297767717491244001414520520209715227404908622097152004425900444440010048580000052428812075355853463974120753726264868031207537262680712012075355854187899
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030287149987150441943042560012243049600x7f4cf17574000x7f4be5a3768010690312105309006553615728536912995538251336288133628818053779834980813362880006160095242880052428852428800524288782765041065361019133588600193982051020971522899133383120971520093100001238252037350160000052428812075355854356362120753726268523991207537262773031112075355855632503
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030487149987150441943042560024243136000x7f4cf17573000x7f4be5a376c0504532848761186553672590309596630222630665630665759668153715106306650002013067524288005242885242880052428850878314272182774628339001465720510209715228926277092097152001710200569490010141450000052428812075355855811636120753726277983101207537262823174612075355856631078
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030687149987150441943042560020243148160x7f4cf1757a000x7f4be5a37700186556961849830865536276314236228504726823319612331961256682671500467422693666259500804289524288005242885242880008925646500192497223314770025753259502097152289723295452097152001530320021756480401886200000012075355856795454120753726282832661207537262983525112075355858745397
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030887149987150441943042560020243175680x7f4cf17579000x7f4be5a377409616224943930765536140903454116121424812020271202027251882661491457711386496337800139148352428800524288524288000857602246775917471199478001813624270209715227991196659209715200839320011094480396861300000012075355858912327120753726299083701207537263070404212075355860114010
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031087149987150441943042560012243203200x7f4cf17578000x7f4be5a37780511188849544786553673916129607401855638985638985185927048740560638985000573249524288005242885242880052428877388834024179717638612001459520500209715238096716012097152005050700581992037947760000052428812075355860277835120753726307811621207537263119571812075355861069896
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031287149987150441943042560012243240960x7f4cf17577000x7f4be5a377c014052600138964326553620756569417148870511756574175657418429648839665317565740006914105242880052428852428800524288757486338757647471757206002200720670209715229051758073209715200116535001634588037339440000052428812075355861252486120753726312692351207537263242826512075355862800522
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031487149987150441943042560012243288960x7f4cf17576000x7f4be5a3780095748649420515655361406470011160720397119685711968571892392687093771196857000673982524288005242885242880052428877356164058148717119709200182692058020971522909119465220971520084550001109114037392740000052428812075355862980106120753726325349831207537263332025712075355864167242
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031687149987150441943042560020243301120x7f4cf17575000x7f4be5a3784036670520365077876553654555245145152965894583814458381426657449155982194520828629860012591045242880052428852428800088309034875387101945828220040728204302097152366445806742097152002132720042958240400651400000012075355864333310120753726334103361207537263646391112075355867785936
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031887149987150441943042560020243328640x7f4cf17574000x7f4be5a3788018599248184286626553627524253122758746292324905232490525350810148355392324905000859644524288005242885242880008832398488930177423259070025813205002097152314323220022097152001511330021672400396561700000012075355867951573120753726365584701207537263810053712075355869890226
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032087149987150441943042560012243356160x7f4cf17573000x7f4be5a378c096141369457158655361412470841166431675120176612017661880846586661861201766000510487524288005242885242880052428877883944005724752120175300181912051020971522901119974920971520083831001112653038484640000052428812075355870060773120753726381962161207537263898581012075355871241807
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032287149987150441943042560012243393920x7f4cf1757a000x7f4be5a3790027542776273798736553640909712633852708223442846344284618213216844006834428460007552595242880052428852428800524288739847140720987473443798003345920520209715229073439279209715200215256003221058035646680000052428812075355871408867120753726390805291207537264136259012075355874082756
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032487149987150441943042560012243441920x7f4cf17579000x7f4be5a3794018576992184179166553627514906322748867022322123232212319324876880547823221230008084535242880052428852428800524288752338239077537172322772001843023780209715234432321390209715200150861002166242037813120000052428812075355874258583120753726414654691207537264300177612075355876185252
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032687149987150441943042560020243454080x7f4cf17578000x7f4be5a37980726823607252847865536108403249989775741669085294908529425823393149970289085294000680871524288005242885242880008779835481324174790872380063253238102097152321590832182097152005444650085391330401783900000012075355876351431120753726430916961207537264914908512075355882817777
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032887149987150441943042560020243481600x7f4cf17577000x7f4be5a379c036581512364128746553654415727245024135084572688457268824185433144981124572688000759793524288005242885242880008459023476816573145714940040772200402097152290645697762097152002837270042842100383216000000012075355882981641120753726492386851207537265228121912075355886437483
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033087149987150441943042560012243509120x7f4cf17576000x7f4be5a37a00186212801846497765536275879354228148848223276592327659189761978608138232765900063402752428800524288524288005242887819928404686310352326950002568125040209715229102324740209715200149470002172146037792720000052428812075355886599233120753726523701791207537265390920612075355888529470
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332871499871504419430425600122400x7f4cf17575000x7f4be5a37a40544903205433355365536812031466672367688368112896811289180241558230517681128900063283352428800524288524288005242887586756402135710996812574005592320670209715233016809109209715200411163006395187035580320000052428812075355888696149120753726539984851207537265852452812075355893627833