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

50 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_fillBuffer.kd000875961875968335544322560083264640x00x7f3be160418050305150305117342402441652428837261418838218110150528274412075447457147475120754476979729451207544769829646312075447698391406
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00287596187596832768256002424124800x00x7f3be16351002825228252210782260245121138227760410456715612075447712841591120754477132066291207544771321286912075447713218441
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0048759618759684194304256002424129280x7f3ced1839000x7f3be1635140215268215268201961722152655361459299201553929058553779612075447713295545120754477135568671207544771368806712075447713692583
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0068759618759684194304256003624136320x7f3ced1838000x7f3be1635180395492395492224143163944655361715525652979609068802737212075447713777280120754477140416651207544771429302412075447714364381
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0088759618759684194304256002824140800x7f3ced1837000x7f3be16351c03990283990283541431922326553628185327930143340112922948012075447714393064120754477146608621207544771491398112075447714983562
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00108759618759684194304256002424145280x7f3ced1836000x7f3be1635200217252217252199221738024655361372124871563170055066380012075447715013367120754477152770191207544771540965812075447715414192
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00128759618759684194304256002424149760x7f3ced1835000x7f3be1635240212940212940190931703528655361507049291528029060463681612075447715470116120754477157198971207544771584965612075447715854300
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00148759618759684194304256002424154240x7f3ced1834000x7f3be1635280213452213452216881707624655361460508271533037058602162812075447715946481120754477161830941207544771631269412075447716317050
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00168759618759684194304256002824161280x7f3ced1833000x7f3be16352c03917643917643373231341206553634602267929586440138590468012075447716379767120754477166480521207544771689717112075447716940950
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00188759618759684194304256002824168320x7f3ced183a000x7f3be16353003967083967082315031736726553628994862129821080116161160412075447716972037120754477172389291207544771749172812075447717564258
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00208759618759684194304256002424175360x7f3ced1839000x7f3be1635340215172215172212611721384655361490394571549997059797591612075447717589134120754477178578061207544771798900612075447717993516
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00228759618759684194304256002424182400x7f3ced1838000x7f3be1635380219428219428216051755432655361421368701583345057036486812075447718048929120754477183109241207544771844484312075447718449533
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00248759618759684194304256002424189440x7f3ced1837000x7f3be16353c0214556214556206791716456655361444367811541344057956702412075447718524923120754477187626021207544771889348112075447718898077
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00268759618759684194304256002824199040x7f3ced1836000x7f3be16354004020124020123069932161046553630982946430335680124113490412075447718958249120754477192117201207544771946755812075447719539559
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00288759618759684194304256002824206080x7f3ced1835000x7f3be1635440394524394524247333156200655362262204692967825090669913612075447719560267120754477198289971207544772007987512075447720149452
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00308759618759684194304256002424213120x7f3ced1834000x7f3be1635480211604211604225191692840655361551465671511456062240421612075447720168047120754477204374741207544772056643312075447720570956
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00328759618759684194304256002424220160x7f3ced1833000x7f3be16354c0213532213532230951708264655361585499891533060063602011212075447720625808120754477208749111207544772100483112075447721011034
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00348759618759684194304256002424227200x7f3ced183a000x7f3be1635500215748215748226791725992655361484342711548288059555344812075447721082326120754477213259491207544772145730912075447721462142
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00368759618759684194304256002824236800x7f3ced1839000x7f3be16355403959643959643454131677206553636348830529943410145576993212075447721518176120754477217648271207544772201746612075447722087514
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00388759618759684194304256002824243840x7f3ced1838000x7f3be16355803935883935883103131487126553626179035729710220104897761612075447722106600120754477223729841207544772262402312075447722692869
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00408759618759684194304256002424250880x7f3ced1837000x7f3be16355c0209156209156202711673256655361610256321490972064592642812075447722713357120754477229787411207544772310562112075447723110806
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00428759618759684194304256002424257920x7f3ced1836000x7f3be1635600213124213124224521705000655361618346251532655064915982412075447723171970120754477234315391207544772356161812075447723566373
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00448759618759684194304256002424264960x7f3ced1835000x7f3be1635640215948215948202191727592655361556058821558098062423989212075447723635671120754477238656171207544772399729612075447724008023
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00468759618759684194304256002824277120x7f3ced1834000x7f3be16356804004524004523030732036246553631381443430251390125707367612075447724055301120754477243028951207544772455905312075447724629318
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00488759618759684194304256002824284160x7f3ced1833000x7f3be16356c0392452392452315283139624655362435047672963185097583562012075447724649456120754477249032121207544772515345112075447725225787
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00508759618759684194304256002424291200x7f3ced183a000x7f3be1635700217828217828196001742632655361520553971568159061003847612075447725244321120754477255006491207544772563376812075447725638484
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00528759618759684194304256002424300800x7f3ced1839000x7f3be1635740215412215412201731723304655361500518801536591060202394412075447725695039120754477259353671207544772606704612075447726072280
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00548759618759684194304256002424307840x7f3ced1838000x7f3be1635780218052218052247671744424655361549935661571649062179186412075447726145806120754477263769651207544772651008412075447726514912
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00568759618759684194304256002824320000x7f3ced1837000x7f3be16357c04059244059242787832474006553629023270630660410116274940412075447726569263120754477268225621207544772708272112075447727154150
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00588759618759684194304256002824329600x7f3ced1836000x7f3be16358004530844530841669936246806553634031999529916160136309619212075447727174178120754477274331191207544772772383812075447727793509
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00608759618759684194304256002424339200x7f3ced1835000x7f3be1635840219164219164245631753320655361517264451566996060872499212075447727811482120754477280711961207544772820463612075447728209752
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00628759618759684194304256002424348800x7f3ced1834000x7f3be1635880214548214548253791716392655361493096231536648059906685612075447728262560120754477285081541207544772863967312075447728644480
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00648759618759684194304256002424358400x7f3ced1833000x7f3be16358c0209372209372194101674984655361553416371510186062319470012075447728717225120754477289439921207544772907199112075447729077224
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00668759618759684194304256002824373120x7f3ced183a000x7f3be16359004072764072762951932582166553630552830230792080122394508412075447729130113120754477293807901207544772964206912075447729711293
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00688759618759684194304256002824382720x7f3ced1839000x7f3be16359404641564641561614937132566553629965337530750010120043122412075447729730709120754477299902271207544773028878512075447730359367
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00708759618759684194304256002424392320x7f3ced1838000x7f3be1635980278764278764165122230120655361511191751536145060631188412075447730378002120754477306393441207544773081262312075447730817368
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00728759618759684194304256002424401920x7f3ced1837000x7f3be16359c0223044223044220201784360655361557490751601473062484415212075447730870918120754477311204611207544773125806112075447731262926
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00748759618759684194304256002424411520x7f3ced1836000x7f3be1635a00209964209964225211679720655361598885281506192064137490812075447731332766120754477315631791207544773169149912075447731696202
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00768759618759684194304256002824426240x7f3ced1835000x7f3be1635a403992923992922818131943446553630993793730222050124157914412075447731755321120754477319937371207544773225021612075447732319199
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00788759618759684194304256002824435840x7f3ced1834000x7f3be1635a804016044016043324232128406553628004488830180740112199568012075447732338235120754477325919741207544773284749312075447732917321
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00808759618759684194304256002424445440x7f3ced1833000x7f3be1635ac0220828220828224811766632655361503430981570254060319843212075447732936737120754477331980511207544773333149112075447733336460
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00828759618759684194304256002424457600x7f3ced183a000x7f3be1635b00216468216468246871731752655361533719341547116061531727212075447733395099120754477336402891207544773377356812075447733778000
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00848759618759684194304256002424467200x7f3ced1839000x7f3be1635b40217324217324218141738600655361536933201557561061660964412075447733850615120754477340908471207544773422348612075447734228688
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00868759618759684194304256002824484480x7f3ced1838000x7f3be1635b804106284106282963732850326553627755394531012420111203122412075447734282809120754477345273251207544773479196312075447734861133
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00888759618759684194304256002824494080x7f3ced1837000x7f3be1635bc03988123988123154231905046553631519315430206050126258502012075447734880509120754477351358021207544773539148012075447735462271
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00908759618759684194304256002424503680x7f3ced1836000x7f3be1635c00209356209356208431674856655361680019761501403067383699612075447735481747120754477357327591207544773586091812075447735865700
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00928759618759684194304256002424515840x7f3ced1835000x7f3be1635c40219860219860277551758888655361656529391564370066443436012075447735920602120754477361705171207544773630539612075447736310327
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00948759618759684194304256002424525440x7f3ced1834000x7f3be1635c80216468216468232521731752655361531360851559152061435982812075447736382821120754477366090741207544773674187412075447736746598
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00968759618759684194304256002824542720x7f3ced1833000x7f3be1635cc04112844112843463832902806553633446946231097140133969496012075447736800307120754477370625121207544773732747112075447737400282
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00988759618759684194304256002824554880x7f3ced183a000x7f3be1635d003873163873162713230985366553632446254129292230129966706812075447737417935120754477376775491207544773792602812075447737994897
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001008759618759684194304256002424567040x7f3ced1839000x7f3be1635d40219204219204244571753640655361504465301574300060361140812075447738019373120754477382783461207544773841274612075447738417533
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001028759618759684194304256002424581760x7f3ced1838000x7f3be1635d80225028225028262731800232655361706865211614983068461957612075447738472485120754477387165841207544773885546412075447738860556
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001048759618759684194304256002424593920x7f3ced1837000x7f3be1635dc0210556210556231121684456655361505155711515073060389733612075447738931779120754477391729021207544773930186112075447739306986
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001068759618759684194304256002824613760x7f3ced1836000x7f3be1635e004048124048123111332385046553629091008230483670116546092012075447739360034120754477396049001207544773986569912075447739935284
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001088759618759684194304256002824625920x7f3ced1835000x7f3be1635e403966043966043125831728406553631535675429900050126324427612075447739953397120754477402229771207544774047753612075447740548523
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001108759618759684194304256002424638080x7f3ced1834000x7f3be1635e80219124219124237511753000655361538601781574181061730362412075447740568801120754477408269741207544774096121312075447740966119
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001128759618759684194304256002424652800x7f3ced1833000x7f3be1635ec0225804225804253861806440655361778905791612133071342703612075447741036660120754477412781721207544774141785112075447741422638
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001148759618759684194304256002424664960x7f3ced183a000x7f3be1635f00220548220548248911764392655361525964501576091061221088012075447741496054120754477417208891207544774185544912075447741860401
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001168759618759684194304256002824684800x7f3ced1839000x7f3be1635f404026284026283465032210326553634103312730293620136596920412075447741914362120754477421688871207544774242776612075447742498908
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001188759618759684194304256002824696960x7f3ced1838000x7f3be1635f803926443926442978731411606553630082602329551940120513530012075447742519376120754477427720841207544774302392312075447743093924
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001208759618759684194304256002424709120x7f3ced1837000x7f3be1635fc0215204215204213331721640655361702865811541003068300780412075447743113480120754477433752811207544774350728112075447743512041
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001228759618759684194304256002424723840x7f3ced1836000x7f3be1636000223276223276267371786216655361843892831610737073941396812075447743572714120754477438219991207544774396039912075447743965203
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001248759618759684194304256002424736000x7f3ced1835000x7f3be1636040210740210740245691685928655361625369141504333065197828412075447744047506120754477442739971207544774440263612075447744407425
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001268759618759684194304256002824758400x7f3ced1834000x7f3be16360804049324049323313232394646553633393244730442990133754806012075447744461605120754477447059951207544774496679412075447745036043
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001288759618759684194304256002824770560x7f3ced1833000x7f3be16360c04000284000282930932002326553631749053030269710127177827212075447745056932120754477453079121207544774556567112075447745634636
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001308759618759684194304256002424782720x7f3ced183a000x7f3be1636100211212211212200671689704655361631053931502684065426943612075447745654112120754477459079091207544774603750812075447746042654
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001328759618759684194304256002424800000x7f3ced1839000x7f3be1636140233540233540274091868328655361952881251692207078303892012075447746104769120754477463480671207544774649286612075447746497669
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001348759618759684194304256002424812160x7f3ced1838000x7f3be1636180217324217324222611738600655361689453021562523067761513612075447746572418120754477467962251207544774693014412075447746934942
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001368759618759684194304256002824834560x7f3ced1837000x7f3be16361c04140524140523200433124246553628506948331063650114209514812075447746995144120754477472536621207544774752150112075447747590551
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001388759618759684194304256002824849280x7f3ced1836000x7f3be16362003943003943003020431544086553632686985629815230130930621612075447747609937120754477478634191207544774811749812075447748188061
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001408759618759684194304256002424864000x7f3ced1835000x7f3be1636240216508216508235281732072655361610579401563790064610107612075447748207487120754477484651761207544774859861612075447748603423
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001428759618759684194304256002424881280x7f3ced1834000x7f3be1636280241188241188280881929512655362093100081758356083911154812075447748657834120754477488981341207544774904837412075447749053600
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001448759618759684194304256002424896000x7f3ced1833000x7f3be16362c0216356216356237901730856655361685303701556147067596232812075447749147674120754477493570121207544774949013112075447749495050
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001468759618759684194304256002824920960x7f3ced183a000x7f3be16363004044524044523452232356246553633716730730616090135051868812075447749546596120754477497870901207544775004868912075447750121103
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001488759618759684194304256002824935680x7f3ced1839000x7f3be16363403945163945163344531561366553634434862729906810137921348412075447750140760120754477504000471207544775065460612075447750697394
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001508759618759684194304256002424950400x7f3ced1838000x7f3be1636380224996224996248511799976655361663028831623733066708366812075447750724585120754477509715641207544775111044412075447751115572
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001528759618759684194304256002424967680x7f3ced1837000x7f3be16363c0253012253012285252024104655362235495801854668089605317212075447751170083120754477514138021207544775157220112075447751576909
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001548759618759684194304256002424982400x7f3ced1836000x7f3be1636400213812213812242991710504655361620490381533085065005406412075447751650155120754477518762001207544775200771912075447752012639
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015687596187596841943042560028241007360x7f3ced1835000x7f3be16364404141244141243340533130006553629560498431035600118423636812075447752066439120754477523110781207544775257891612075447752647398
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015887596187596841943042560028241022080x7f3ced1834000x7f3be1636480394908394908272193159272655362401485412971900096241436812075447752667035120754477529169951207544775317139312075447753242565
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016087596187596841943042560024241036800x7f3ced1833000x7f3be16364c0215508215508241181724072655361568680361528119062932247212075447753261961120754477535193921207544775365123112075447753656093
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016287596187596841943042560024241056640x7f3ced183a000x7f3be1636500264188264188287012113512655362346235531948346094035006412075447753710093120754477539529901207544775411874912075447754124133
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016487596187596841943042560024241071360x7f3ced1839000x7f3be1636540218196218196252501745576655361651856671544076066261241212075447754194944120754477544269071207544775455890712075447754564010
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016687596187596841943042560028241098880x7f3ced1838000x7f3be16365804157724157723868133261846553631593729831030750126560277612075447754618892120754477548609851207544775512786412075447755197878
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016887596187596841943042560028241113600x7f3ced1837000x7f3be16365c03933563933563460431468566553632379103229540860129699424412075447755217565120754477554757021207544775572882112075447755797342
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017087596187596841943042560024241128320x7f3ced1836000x7f3be1636600218036218036255511744296655361630334141566661065399744412075447755816819120754477560820991207544775621633912075447756221370
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017287596187596841943042560024241148160x7f3ced1835000x7f3be1636640277572277572312112220584655362451764962040908098256331212075447756273868120754477565176171207544775669169612075447756696814
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017487596187596841943042560024241162880x7f3ced1834000x7f3be1636680220428220428238511763432655361539063481584436061744691212075447756770651120754477569952151207544775713121412075447757136511
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017687596187596841943042560028241190400x7f3ced1833000x7f3be16366c04040044040043551832320406553631301551330360410125388980412075447757190632120754477574398531207544775770065112075447757770099
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017887596187596841943042560028241207680x7f3ced183a000x7f3be16367004006604006602921132052886553625912329530124780103831388012075447757799944120754477580510501207544775830912812075447758380974
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018087596187596841943042560024241224960x7f3ced1839000x7f3be1636740215908215908228061727272655361575438041551197063202891212075447758401803120754477586537671207544775878640612075447758791387
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018287596187596841943042560024241247360x7f3ced1838000x7f3be16367802895802895803107823166486553625963663321497410104039321212075447758846469120754477590974441207544775928064412075447759285535
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018487596187596841943042560024241264640x7f3ced1837000x7f3be16367c0224972224972250501799784655361723905201616633069143256412075447759390891120754477596014421207544775974032112075447759745400
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018687596187596841943042560020241279360x7f3ced1836000x7f3be16368004100684100683533932805526553637678928731093400150897734412075447759797687120754477600494401207544776031503912075447760386151
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018887596187596841943042560028241296640x7f3ced1835000x7f3be16368403953803953802979931630486553625261434329737110101227596812075447760404184120754477606620221207544776091690112075447760990003
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019087596187596841943042560024241313920x7f3ced1834000x7f3be1636880226532226532221521812264655361597331301631820064078651212075447761017354120754477612736981207544776141369812075447761417958
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019287596187596841943042560024241336320x7f3ced1833000x7f3be16368c03031563031563238624252566553627215896422556000109047894812075447761470907120754477617140161207544776190601612075447761948725
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019487596187596841943042560024241353600x7f3ced183a000x7f3be1636900220036220036248541760296655361636768471577236065656848012075447761996844120754477622412141207544776237641412075447762381309
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019687596187596841943042560020241368320x7f3ced1839000x7f3be16369404357004357004008734856086553640331213133157300161506864812075447762433866120754477626786521207544776296185112075447763030816
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019887596187596841943042560028241385600x7f3ced1838000x7f3be16369804555084555081583736440726553629608555230206420118617309612075447763049340120754477633052101207544776360040912075447763668501
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020087596187596841943042560024241402880x7f3ced1837000x7f3be16369c0220380220380259191763048655361594172441580619063951682012075447763686975120754477639405671207544776407592712075447764080937
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020287596187596841943042560024241427840x7f3ced1836000x7f3be1636a003319163319163425826553366553630175557924826540120887663212075447764137172120754477643909651207544776460136412075447764670032
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020487596187596841943042560024241447680x7f3ced1835000x7f3be1636a40228828228828272171830632655361732427651642626069486284412075447764705849120754477649445631207544776508536212075447765089972
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020687596187596841943042560020241457280x7f3ced1834000x7f3be1636a804704924704924155537639446553643801998435928820175389942012075447765143652120754477653896811207544776569640012075447765764777
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020887596187596841943042560028241477120x7f3ced1833000x7f3be1636ac03919723919723581431357846553635652865329551320142794047612075447765785595120754477660463181207544776629927712075447766368869
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021087596187596841943042560024241496960x7f3ced183a000x7f3be1636b00226196226196251751809576655361709932601624867068586323612075447766388385120754477666416761207544776678151512075447766785884
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021287596187596841943042560024241521920x7f3ced1839000x7f3be1636b403572523572523623628580246553632587087726831530130531945612075447766849122120754477670904741207544776731831312075447767386560
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021487596187596841943042560024241541760x7f3ced1838000x7f3be1636b80221812221812261161774504655361654597041594515066369792012075447767421866120754477676651921207544776780215112075447767806240
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021687596187596841943042560020241556480x7f3ced1837000x7f3be1636bc05077005077004551340616086553647125117038831100188682552812075447767860441120754477681239101207544776845494812075447768524676
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021887596187596841943042560028241576320x7f3ced1836000x7f3be1636c004028924028923299532231446553630669853630285710122861460012075447768543651120754477687947871207544776905462612075447769124661
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022087596187596841943042560024241596160x7f3ced1835000x7f3be1636c40226284226284258401810280655361706500631632973068448177612075447769143205120754477693960651207544776953622412075447769540604
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022287596187596841943042560024241623680x7f3ced1834000x7f3be1636c803832763832763778230662166553634977687228948800140094902812075447769593081120754477698389431207544777008454212075447770156208
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022487596187596841943042560024241646080x7f3ced1833000x7f3be1636cc0221140221140247261769128655361713920311584083068744547612075447770191523120754477704341401207544777057078012075447770575277
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022687596187596841943042560020241663360x7f3ced183a000x7f3be1636d005764605764604979546116886553654122015544382670216670117212075447770629678120754477708710981207544777124901712075447771292499
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022887596187596841943042560028241685760x7f3ced1839000x7f3be1636d404011404011403642232091286553633031189530341330132310475612075447771330180120754477715739761207544777183349412075447771901832
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023087596187596841943042560024241708160x7f3ced1838000x7f3be1636d80226604226604278021812840655361837215281633038073678300412075447771921318120754477721893331207544777232965212075447772334376
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023287596187596841943042560024241740800x7f3ced1837000x7f3be1636dc04361484361484125134891926553640430370233155750161907363212075447772387755120754477726301311207544777291077012075447772979635
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023487596187596841943042560024241765760x7f3ced1836000x7f3be1636e00223892223892262391791144655361801599831608792072253397212075447773020581120754477732605291207544777339940812075447773403623
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023687596187596841943042560020241777920x7f3ced1835000x7f3be1636e406792926792921674154343446553660985764549854720244125127212075447773457082120754477736998871207544777414724512075447774216173
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023887596187596841943042560028241802880x7f3ced1834000x7f3be1636e804014364014363607332114966553633368830930203790133658853212075447774242803120754477745013231207544777476020212075447774828942
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024087596187596841943042560024241827840x7f3ced1833000x7f3be1636ec0222732222732276861781864655361754210691606429070356566012075447774846855120754477751142811207544777525252012075447775257078
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024287596187596841943042560024241863040x7f3ced183a000x7f3be1636f004896764896764415939174166553645680444637463160182906903212075447775310837120754477755597191207544777587667812075447775944675
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024487596187596841943042560024241893120x7f3ced1839000x7f3be1636f40243540243540285861948328655362152248071778082086279519212075447775980752120754477762325161207544777638467612075447776389302
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024687596187596841943042560020241907840x7f3ced1838000x7f3be1636f807852847852846094262822806553674998049861081830300174332012075447776443052120754477766864341207544777720387212075447777273204
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024887596187596841943042560028241937920x7f3ced1837000x7f3be1636fc04557644557643947136461206553636686970234484730146933534412075447777291959120754477775565111207544777785394912075447777923152
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025087596187596841943042560024241968000x7f3ced1836000x7f3be1637000249796249796284811998376655362181013221803735087429172412075447777942348120754477782128281207544777836738712075447778372247
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025287596187596841943042560024242010880x7f3ced1835000x7f3be16370405943725943724954047549846553656146255645819070224770491212075447778429493120754477786785861207544777906434412075447779133582
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025487596187596841943042560024242046080x7f3ced1834000x7f3be1637080277588277588300882220712655362486532892054279099650348012075447779175770120754477794155431207544777959138212075447779595721
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025687596187596841943042560020242060800x7f3ced1833000x7f3be16370c09247249247246785973978006553688978327772323450356095395612075447779650022120754477798966611207544778050769812075447780578677
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025887596187596841943042560028242096000x7f3ced183a000x7f3be16371004983484983484285539867926553645883301738193200183716855212075447780598574120754477808606571207544778118737612075447781256587
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026087596187596841943042560024242131200x7f3ced1839000x7f3be16371402819722819723107122557846553625207072420866220101015962012075447781275452120754477815297741207544778170817312075447781712605
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026287596187596841943042560024242181760x7f3ced1838000x7f3be16371806991646991645473855933206553666492751254256940266156499212075447781772326120754477820091321207544778246577012075447782536316
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026487596187596841943042560024242222080x7f3ced1837000x7f3be16371c03154043154043221725232406553628636679423566760114736386412075447782573074120754477828091291207544778301040812075447783079655
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026687596187596841943042560020242239360x7f3ced1836000x7f3be16372001068524106852476313854820065536102791969283577630411349885612075447783099953120754477833542471207544778405888412075447784127563
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026887596187596841943042560028242279680x7f3ced1835000x7f3be16372405677005677004759745416086553652887216543690130211732066412075447784146157120754477844060821207544778477968112075447784847120
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027087596187596841943042560024242320000x7f3ced1834000x7f3be16372803192683192683185325541526553629041641023916110116355652412075447784867258120754477851374391207544778534127812075447785411429
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027287596187596841943042560024242378240x7f3ced1833000x7f3be16372c08043088043086083064344726553676972934962687810308077068812075447785441845120754477856889571207544778621615512075447786285584
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027487596187596841943042560024242423680x7f3ced183a000x7f3be16373003501643501643443528013206553632029680826345760128308547612075447786321891120754477865599931207544778678447212075447786852016
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027687596187596841943042560020242435840x7f3ced1839000x7f3be16373401207300120730085225965840865536116790200994917590467342864412075447786872745120754477871438311207544778794366812075447788021179
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027887596187596841943042560028242481280x7f3ced1838000x7f3be16373806380766380765166551046166553660317365549418250241452958012075447788047478120754477883036661207544778872526412075447788793344
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028087596187596841943042560024242526720x7f3ced1837000x7f3be16373c03542523542523464728340246553632453009426673720130001657612075447788813091120754477890806231207544778930830212075447789378792
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028287596187596841943042560024242592640x7f3ced1836000x7f3be16374009099249099246711772794006553687370286371153640349666630412075447789398549120754477896657401207544779026349812075447790333476
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028487596187596841943042560024242648320x7f3ced1835000x7f3be16374404201484201484019533611926553638773059731849650155282796412075447790373250120754477906182161207544779088845512075447790956574
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028687596187596841943042560020242663040x7f3ced1834000x7f3be16374801487772148777210081811902184655361447290865117347710579098468012075447790980950120754477912441341207544779223053012075447792299580
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028887596187596841943042560028242718720x7f3ced1833000x7f3be16374c07787807787806088462302486553674057982560521210296415827612075447792332451120754477925783681207544779309484612075447793163406
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029087596187596841943042560024242774400x7f3ced183a000x7f3be16375004235244235244067533882006553639110010532176580156629700812075447793189434120754477934457251207544779371820412075447793786283
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029287596187596841943042560012242799360x7f3ced1839000x7f3be16375401127628112762880645902103265536109047794588431090436373641612075447793812312120754477940670021207544779480507912075447794876860
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029487596187596841943042560024242865280x7f3ced1838000x7f3be16375804895084895084411839160726553645552764737461530182400977612075447794912396120754477951687581207544779548539612075447795555100
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029687596187596841943042560020242880000x7f3ced1837000x7f3be16375c01767652176765211775714141224655361725147546139764870690241033212075447795575048120754477958317951207544779700331012075447797072691
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029887596187596841943042560032242945920x7f3ced1836000x7f3be16376009229889229886555773839126553680493617872077410322159975612075447797092207120754477973493881207544779796202612075447798030651
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030087596187596841943042560024243011840x7f3ced1835000x7f3be16376404920684920684386839365526553645913173437671800183841682012075447798048865120754477983007451207544779861946312075447798689215
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030287596187596841943042560012243049600x7f3ced1834000x7f3be1637680133746013374609259810699688655361298823433105284490519712009612075447798714061120754477989586621207544779983769812075447799908601
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030487596187596841943042560024243136000x7f3ced1833000x7f3be16376c06640846640841668053126806553659325534048590200237491646412075447799944829120754478001890571207544780062249512075447800691947
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030687596187596841943042560020243148160x7f3ced183a000x7f3be1637700233413223341328116718673064655362283587233184935140913616854412075447800711493120754478009752931207544780252504712075447802595605
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030887596187596841943042560020243175680x7f3ced1839000x7f3be16377401202204120220486742961764065536116119043094414520464658605212075447802619960120754478028828051207544780367992212075447803752345
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031087596187596841943042560012243203200x7f3ced1838000x7f3be16377806406046406045196451248406553660620109749496230242663246012075447803779485120754478040423211207544780445687912075447804528527
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031287596187596841943042560012243240960x7f3ced1837000x7f3be16377c01758004175800411653214064040655361714361681138981030685927349212075447804559445120754478048117571207544780597063312075447806039565
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031487596187596841943042560012243288960x7f3ced1836000x7f3be16378001198388119838884343958711265536116088309594172210464535768812075447806081824120754478063218311207544780710710812075447807176228
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031687596187596841943042560020243301120x7f3ced1835000x7f3be163784045847964584796282843366783766553645135798003650461401805613978012075447807195363120754478074623061207544781051365412075447810582639
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031887596187596841943042560020243328640x7f3ced1834000x7f3be16378802324516232451615097018596136655362276347616184274910910721258012075447810616051120754478108638921207544781240724612075447812480055
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032087596187596841943042560012243356160x7f3ced1833000x7f3be16378c01202012120201283553961610465536116544939394529200466362142012075447812505512120754478127635641207544781355236112075447813621867
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032287596187596841943042560012243393920x7f3ced183a000x7f3be163790034446123444612216560275569046553633852501262738045001354282756012075447813650109120754478139093201207544781619155012075447816263797
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032487596187596841943042560012243441920x7f3ced1839000x7f3be16379402323932232393215074018591464655362274444278184159950909960540012075447816305083120754478165497891207544781808514212075447818154951
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032687596187596841943042560020243454080x7f3ced1838000x7f3be163798090873889087388544580726991126553689768972387253091603590941011212075447818185789120754478184389931207544782449609012075447824568962
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032887596187596841943042560020243481600x7f3ced1837000x7f3be16379c045731724573172283170365853846553645021166543641520601801028935612075447824590502120754478248538471207544782789655612075447827967808
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033087596187596841943042560012243509120x7f3ced1836000x7f3be1637a002329324232932415071318634600655362280652361184649640912443574012075447827993265120754478282570341207544782979670812075447829866527
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332875961875968419430425600122400x7f3ced1835000x7f3be1637a4068143006814300412842545144086553667240411675433885802689798809612075447829898196120754478301610271207544783469028912075447834762245