Comhaid
rocm-systems/tests/workloads/Axes2/mi100/SQ_IFETCH_LEVEL.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

46 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjGRBM_COUNTGRBM_GUI_ACTIVESQ_WAVESSQ_IFETCHSQ_IFETCH_LEVELSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000904528904533335544322560083264640x00x7f5a30e04180506681506681524288629145679256210154925612076012262816271120760125035537921207601250387923012076012503985002
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00290452890453332768256002424124800x00x7f5a30e35100281042810451281929287118343612076012518518923120760125188309841207601251883738412076012518847614
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0049045289045334194304256002424129280x7f5b3c9cb9000x7f5a30e35140226931226931655369175041433221838072812076012518910841120760125191468221207601251928586112076012519290988
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0069045289045334194304256003624136320x7f5b3c9cb8000x7f5a30e351803908173908176553612451841845272361723212076012519363292120760125195442591207601251979257812076012519844096
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0089045289045334194304256002824140800x7f5b3c9cb7000x7f5a30e351c0391371391371655369830401426891829456012076012519875625120760125200772161207601252032537512076012520377567
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00109045289045334194304256002424145280x7f5b3c9cb6000x7f5a30e352002213772213776553610485761573972010885212076012520404267120760125206066531207601252074265312076012520746363
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00129045289045334194304256002424149760x7f5b3c9cb5000x7f5a30e35240219828219828655369830401489551904812412076012520801014120760125209866511207601252112121012076012521125087
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00149045289045334194304256002424154240x7f5b3c9cb4000x7f5a30e352802164332164336553610485761486311905800012076012521210335120760125213818491207601252151448812076012521518528
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00169045289045334194304256002824161280x7f5b3c9cb3000x7f5a30e352c04058764058766553615728642322602967858812076012521568861120760125217583271207601252201688512076012522043974
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00189045289045334194304256002824168320x7f5b3c9cba000x7f5a30e353003850493850496553611796481594982035370012076012522092044120760125222732041207601252251864212076012522568830
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00209045289045334194304256002424175360x7f5b3c9cb9000x7f5a30e353402163402163406553611141121613312068696812076012522594848120760125227842411207601252291656012076012522920223
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00229045289045334194304256002424182400x7f5b3c9cb8000x7f5a30e353802264812264816553611141121597732045260412076012522974013120760125231642391207601252330343812076012523307382
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00249045289045334194304256002424189440x7f5b3c9cb7000x7f5a30e353c02132922132926553611796481665782137323612076012523377603120760125235565571207601252368679612076012523690725
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00269045289045334194304256002824199040x7f5b3c9cb6000x7f5a30e354003976653976656553618350082628473350639212076012523743523120760125239295141207601252418343312076012524235347
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00289045289045334194304256002824206080x7f5b3c9cb5000x7f5a30e354404064194064196553613107201787742289671612076012524259442120760125244576711207601252471639012076012524765132
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00309045289045334194304256002424213120x7f5b3c9cb4000x7f5a30e354802151932151936553612451841735872221851612076012524793895120760125249703081207601252510214812076012525105584
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00329045289045334194304256002424220160x7f5b3c9cb3000x7f5a30e354c02216992216996553613107201827792346582412076012525153634120760125253458261207601252548166612076012525485120
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00349045289045334194304256002424227200x7f5b3c9cba000x7f5a30e355002163452163456553613107201805292309992012076012525551964120760125257306241207601252586326312076012525866699
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00369045289045334194304256002824236800x7f5b3c9cb9000x7f5a30e355403972043972046553620971522954803775622012076012525919537120760125261051821207601252635862112076012526407594
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00389045289045334194304256002824243840x7f5b3c9cb8000x7f5a30e355804561374561376553614417921981382537282812076012526435556120760125266269391207601252691957712076012526967605
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00409045289045334194304256002424250880x7f5b3c9cb7000x7f5a30e355c02225562225566553613762561940122475854812076012527007940120760125271885361207601252732421512076012527328025
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00429045289045334194304256002424257920x7f5b3c9cb6000x7f5a30e356002121372121376553615073282081362665815612076012527376835120760125275755741207601252770549312076012527708932
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00449045289045334194304256002424264960x7f5b3c9cb5000x7f5a30e356402193882193886553614417921998362559029212076012527776197120760125279566911207601252809077112076012528094479
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00469045289045334194304256002824277120x7f5b3c9cb4000x7f5a30e356804044654044656553623592963218524124079212076012528147808120760125283381291207601252859732812076012528645924
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00489045289045334194304256002824284160x7f5b3c9cb3000x7f5a30e356c03930363930366553615728642108942702814412076012528675358120760125288520461207601252910292512076012529151694
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00509045289045334194304256002424291200x7f5b3c9cba000x7f5a30e357002166972166976553615073282101752693422812076012529181840120760125293810031207601252951428212076012529517794
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00529045289045334194304256002424300800x7f5b3c9cb9000x7f5a30e357402172602172606553617039362359773024793612076012529571774120760125297554011207601252988884012076012529892300
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00549045289045334194304256002424307840x7f5b3c9cb8000x7f5a30e357802094012094016553615728642116192715480012076012529958022120760125301416391207601253027011812076012530273679
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00569045289045334194304256002824320000x7f5b3c9cb7000x7f5a30e357c03981793981796553626214403668004700016812076012530327288120760125305115571207601253076659512076012530813943
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00589045289045334194304256002824329600x7f5b3c9cb6000x7f5a30e358004052654052656553617039362299562943434812076012530839320120760125310361941207601253129539212076012531346022
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00609045289045334194304256002424339200x7f5b3c9cb5000x7f5a30e358402137882137886553616384002228582852724012076012531372501120760125315611511207601253169203012076012531695391
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00629045289045334194304256002424348800x7f5b3c9cb4000x7f5a30e358802271452271456553619005442844293636748412076012531752076120760125319272291207601253206754812076012532071189
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00649045289045334194304256002424358400x7f5b3c9cb3000x7f5a30e358c02159632159636553617039362448433133423212076012532136641120760125323166661207601253244866612076012532452157
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00669045289045334194304256002824373120x7f5b3c9cba000x7f5a30e359003984653984656553628835843933705038236812076012532506278120760125326965041207601253295186312076012533007119
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00689045289045334194304256002824382720x7f5b3c9cb9000x7f5a30e359404032204032206553618350082447053130890412076012533036704120760125332243411207601253348194012076012533530552
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00709045289045334194304256002424392320x7f5b3c9cb8000x7f5a30e359802250972250976553617694722676363422668812076012533552332120760125337416181207601253388033712076012533883808
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00729045289045334194304256002424401920x7f5b3c9cb7000x7f5a30e359c02271792271796553620971523220134118649212076012533933290120760125341230561207601253426321512076012534266610
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00749045289045334194304256002424411520x7f5b3c9cb6000x7f5a30e35a002122572122576553618350082601683331804812076012534331921120760125345091341207601253463921312076012534642568
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00769045289045334194304256002824426240x7f5b3c9cb5000x7f5a30e35a404089644089646553631457284182395365758412076012534690287120760125348788921207601253514097012076012535191308
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00789045289045334194304256002824435840x7f5b3c9cb4000x7f5a30e35a803988093988096553619660802629523362891612076012535212177120760125354072091207601253566272712076012535712066
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00809045289045334194304256002424445440x7f5b3c9cb3000x7f5a30e35ac02135322135326553619005442642053376016012076012535735770120760125359289661207601253606016512076012536063619
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00829045289045334194304256002424457600x7f5b3c9cba000x7f5a30e35b002212652212656553622937603098333966352812076012536119363120760125363020841207601253643888312076012536442363
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00849045289045334194304256002424467200x7f5b3c9cb9000x7f5a30e35b402111082111086553619660802749853518752412076012536508055120760125366852811207601253681472112076012536818412
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00869045289045334194304256002824484480x7f5b3c9cb8000x7f5a30e35b804175774175776553634078724751436085961612076012536866481120760125370593591207601253732783812076012537376199
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00889045289045334194304256002824494080x7f5b3c9cb7000x7f5a30e35bc03947083947086553620971522797613560326412076012537396376120760125375883161207601253784111512076012537862452
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00909045289045334194304256002424503680x7f5b3c9cb6000x7f5a30e35c002149932149936553620316162876113677186412076012537908428120760125380910331207601253822351312076012538227050
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00929045289045334194304256002424515840x7f5b3c9cb5000x7f5a30e35c402245642245646553624903683453014416688812076012538280750120760125384670311207601253860591012076012538609320
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00949045289045334194304256002424525440x7f5b3c9cb4000x7f5a30e35c802174812174816553620971522899713708458012076012538673490120760125388508691207601253898478812076012538988285
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00969045289045334194304256002824542720x7f5b3c9cb3000x7f5a30e35cc04116924116926553636700164929996314839212076012539042044120760125392303871207601253949518512076012539546562
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00989045289045334194304256002824554880x7f5b3c9cba000x7f5a30e35d004577854577856553622282242981403807464412076012539573532120760125397585441207601254005358212076012540105050
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001009045289045334194304256002424567040x7f5b3c9cb9000x7f5a30e35d402190202190206553621626883088373953346412076012540130718120760125403302211207601254046430012076012540467864
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001029045289045334194304256002424581760x7f5b3c9cb8000x7f5a30e35d802267692267696553626869764345725563710812076012540521574120760125406927791207601254083389812076012540837351
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001049045289045334194304256002424593920x7f5b3c9cb7000x7f5a30e35dc02180432180436553622282243056803903226012076012540901590120760125410852561207601254122013612076012541223839
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001069045289045334194304256002824613760x7f5b3c9cb6000x7f5a30e35e004186574186576553639321605234256672580412076012541276407120760125414630141207601254173341312076012541757120
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001089045289045334194304256002824625920x7f5b3c9cb5000x7f5a30e35e404070284070286553623592963091083956912412076012541797986120760125419711711207601254223213012076012542281695
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001109045289045334194304256002424638080x7f5b3c9cb4000x7f5a30e35e802162972162976553622937603156754037508412076012542307022120760125424966081207601254262988712076012542633629
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001129045289045334194304256002424652800x7f5b3c9cb3000x7f5a30e35ec02295482295486553628835844158175321964412076012542689383120760125428734061207601254301548512076012543019266
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001149045289045334194304256002424664960x7f5b3c9cba000x7f5a30e35f002158412158416553623592963468744437634412076012543084167120760125432599641207601254339324312076012543396667
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001169045289045334194304256002824684800x7f5b3c9cb9000x7f5a30e35f404152754152756553641943045814927457558812076012543443384120760125436319621207601254389948012076012543947110
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001189045289045334194304256002824696960x7f5b3c9cb8000x7f5a30e35f803983933983936553624903683261344183672412076012543973650120760125441618791207601254441755712076012544467598
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001209045289045334194304256002424709120x7f5b3c9cb7000x7f5a30e35fc02300202300206553624248323479094453680812076012544487034120760125446794761207601254482091512076012544824631
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001229045289045334194304256002424723840x7f5b3c9cb6000x7f5a30e360002238732238736553630801924611955898886812076012544873071120760125450789931207601254521803312076012545221719
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001249045289045334194304256002424736000x7f5b3c9cb5000x7f5a30e360402246912246916553624903683463804429974412076012545287722120760125454631511207601254560155012076012545605021
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001269045289045334194304256002824758400x7f5b3c9cb4000x7f5a30e360804197534197536553644564485854507498551212076012545658190120760125458329091207601254610378812076012546152208
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001289045289045334194304256002824770560x7f5b3c9cb3000x7f5a30e360c04053314053316553626214403469144447395212076012546180241120760125463701861207601254663034512076012546677956
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001309045289045334194304256002424782720x7f5b3c9cba000x7f5a30e361002149532149536553625559043603054607888012076012546703393120760125468893831207601254702202212076012547025552
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001329045289045334194304256002424800000x7f5b3c9cb9000x7f5a30e361402301152301156553632768004715856060866412076012547078420120760125472642611207601254740762012076012547411168
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001349045289045334194304256002424812160x7f5b3c9cb8000x7f5a30e361802128252128256553626214403496264481948812076012547475177120760125476500191207601254778121812076012547785123
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001369045289045334194304256002824834560x7f5b3c9cb7000x7f5a30e361c04163154163156553647185926421348210176012076012547838833120760125480272971207601254829641512076012548347118
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001389045289045334194304256002824849280x7f5b3c9cb6000x7f5a30e362004015774015776553627525123617334646296812076012548366754120760125485604141207601254881881212076012548867294
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001409045289045334194304256002424864000x7f5b3c9cb5000x7f5a30e362402241952241956553626869764152615307821212076012548893202120760125490884111207601254922665012076012549230429
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001429045289045334194304256002424881280x7f5b3c9cb4000x7f5a30e362802410092410096553634734084961326349447612076012549284790120760125494580081207601254960856812076012549612098
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001449045289045334194304256002424896000x7f5b3c9cb3000x7f5a30e362c02191642191646553627525123912015007997212076012549695383120760125498716061207601255000680512076012550010739
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001469045289045334194304256002824920960x7f5b3c9cba000x7f5a30e363004160334160336553649807366737288612184812076012550064008120760125502485641207601255051800212076012550565601
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001489045289045334194304256002824935680x7f5b3c9cb9000x7f5a30e363403897633897636553628835843796074878212012076012550591839120760125507752811207601255102647912076012551077091
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001509045289045334194304256002424950400x7f5b3c9cb8000x7f5a30e363802211052211056553628180484142155298313212076012551102288120760125512915981207601255142855712076012551432021
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001529045289045334194304256002424967680x7f5b3c9cb7000x7f5a30e363c02526592526596553636700165493067035165612076012551484969120760125516600761207601255181831512076012551821825
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001549045289045334194304256002424982400x7f5b3c9cb6000x7f5a30e364002148092148096553628835843949115045996412076012551886886120760125520783131207601255221111312076012552214986
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015690452890453341943042560028241007360x7f5b3c9cb5000x7f5a30e364404110194110196553651773446757498636815612076012552268786120760125524499911207601255271575012076012552762363
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015890452890453341943042560028241022080x7f5b3c9cb4000x7f5a30e364804512334512336553630146564006765126508412076012552787760120760125529736681207601255326598712076012553314810
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016090452890453341943042560024241036800x7f5b3c9cb3000x7f5a30e364c02212202212206553629491204060535199807212076012553338915120760125535410251207601255367702412076012553680840
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016290452890453341943042560024241056640x7f5b3c9cba000x7f5a30e365002642812642816553638666245535067106791612076012553733879120760125539074231207601255407318212076012554077056
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016490452890453341943042560024241071360x7f5b3c9cb9000x7f5a30e365402192362192366553630146563985285092980412076012554143410120760125543213411207601255445638012076012554460088
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016690452890453341943042560028241098880x7f5b3c9cb8000x7f5a30e3658040936940936965536543948878279710020226412076012554511774120760125546936581207601255495877712076012555018807
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016890452890453341943042560028241113600x7f5b3c9cb7000x7f5a30e365c04002994002996553631457284341195546760012076012555043663120760125552389351207601255549701412076012555545365
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017090452890453341943042560024241128320x7f5b3c9cb6000x7f5a30e366002204492204496553630801925137256575926412076012555570532120760125557568521207601255589333212076012555897179
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017290452890453341943042560024241148160x7f5b3c9cb5000x7f5a30e366402759402759406553640632325644327241652412076012555950117120760125561333301207601255630708912076012556311289
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017490452890453341943042560024241162880x7f5b3c9cb4000x7f5a30e366802180892180896553631457284241625437601212076012556376850120760125565544481207601255668852712076012556692667
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017690452890453341943042560028241190400x7f5b3c9cb3000x7f5a30e366c039799639799665536570163279626710197218812076012556741979120760125569288461207601255718628412076012557235406
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017890452890453341943042560028241207680x7f5b3c9cba000x7f5a30e367004022014022016553632768004296115506646812076012557261925120760125574507631207601255771028112076012557731809
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018090452890453341943042560024241224960x7f5b3c9cb9000x7f5a30e367402290832290836553632112644601205890078412076012557777423120760125579499601207601255809155912076012558095635
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018290452890453341943042560024241247360x7f5b3c9cb8000x7f5a30e367802878892878896553642598405757287331203612076012558150847120760125583269181207601255850963712076012558513612
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018490452890453341943042560024241264640x7f5b3c9cb7000x7f5a30e367c02273322273326553632768005724797325509212076012558579775120760125587525151207601255889315412076012558896994
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018690452890453341943042560020241279360x7f5b3c9cb6000x7f5a30e3680041294541294565536773324897738012484852812076012558945134120760125591334731207601255940163212076012559451264
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018890452890453341943042560028241296640x7f5b3c9cb5000x7f5a30e368404014764014766553634078724510825772627612076012559478525120760125596611501207601255992018912076012559968576
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019090452890453341943042560024241313920x7f5b3c9cb4000x7f5a30e368802188252188256553633423364863616218064412076012559991779120760125601945871207601256033010612076012560334075
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019290452890453341943042560024241336320x7f5b3c9cb3000x7f5a30e368c03023953023956553644564486204407937194412076012560388175120760125605637051207601256075522412076012560803467
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019490452890453341943042560024241353600x7f5b3c9cba000x7f5a30e369002214652214656553635389445129396564844812076012560842760120760125610264221207601256116354112076012561167403
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019690452890453341943042560020241368320x7f5b3c9cb9000x7f5a30e36940437292437292655368978432113053014470800412076012561212868120760125614061001207601256169057812076012561712807
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019890452890453341943042560028241385600x7f5b3c9cb8000x7f5a30e369804059854059856553636700165211986666837612076012561757650120760125619299371207601256219249612076012562240778
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020090452890453341943042560024241402880x7f5b3c9cb7000x7f5a30e369c02279872279876553636044805300456784721612076012562267618120760125624553741207601256259649312076012562600497
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020290452890453341943042560024241427840x7f5b3c9cb6000x7f5a30e36a003297293297296553648496647254239296457612076012562654277120760125628259321207601256303601112076012563084556
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020490452890453341943042560024241447680x7f5b3c9cb5000x7f5a30e36a402193232193236553638010885246316707677212076012563124781120760125633032091207601256343872812076012563442572
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020690452890453341943042560020241457280x7f5b3c9cb4000x7f5a30e36a804706894706896553614548992182771023408070012076012563497093120760125636830471207601256399088512076012564042016
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020890452890453341943042560028241477120x7f5b3c9cb3000x7f5a30e36ac04054444054446553639321605174296619615612076012564060570120760125642558441207601256451760212076012564566320
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021090452890453341943042560024241496960x7f5b3c9cba000x7f5a30e36b002234252234256553638666246043347732720812076012564593270120760125647780811207601256491696012076012564920649
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021290452890453341943042560024241521920x7f5b3c9cb9000x7f5a30e36b403555153555156553652428807531719688098812076012564973467120760125651481591207601256537471712076012565426409
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021490452890453341943042560024241541760x7f5b3c9cb8000x7f5a30e36b802285132285136553640632326521998340042812076012565465782120760125656435161207601256578559512076012565789353
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021690452890453341943042560020241556480x7f5b3c9cb7000x7f5a30e36bc05041485041486553610027008126167916145932812076012565841961120760125660302341207601256635951212076012566407592
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021890452890453341943042560028241576320x7f5b3c9cb6000x7f5a30e36c004073374073376553641943045454016963823212076012566433250120760125666204741207601256688463312076012566935684
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022090452890453341943042560024241596160x7f5b3c9cb5000x7f5a30e36c402175562175566553641287685957747634958012076012566958776120760125671529501207601256728735012076012567291144
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022290452890453341943042560024241623680x7f5b3c9cb4000x7f5a30e36c8038208938208965536563609679713610147345212076012567347178120760125675311881207601256777614712076012567821560
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022490452890453341943042560024241646080x7f5b3c9cb3000x7f5a30e36cc02208752208756553645875206716408594140412076012567860031120760125680486251207601256818558512076012568189674
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022690452890453341943042560020241663360x7f5b3c9cba000x7f5a30e36d005761135761136553611075584139431917838170412076012568235189120760125684287831207601256880702112076012568854910
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022890452890453341943042560028241685760x7f5b3c9cb9000x7f5a30e36d404135724135726553647185926179067903713612076012568875829120760125690779001207601256934653812076012569396377
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023090452890453341943042560024241708160x7f5b3c9cb8000x7f5a30e36d802216252216256553646530566949678892404412076012569415713120760125696174171207601256975517612076012569759111
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023290452890453341943042560024241740800x7f5b3c9cb7000x7f5a30e36dc043293243293265536642252889284811407848012076012569813582120760125699826951207601257026189312076012570284407
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023490452890453341943042560024241765760x7f5b3c9cb6000x7f5a30e36e0022532122532165536511180881617010443637612076012570344459120760125705236521207601257066413112076012570668140
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023690452890453341943042560020241777920x7f5b3c9cb5000x7f5a30e36e406442276442276553615007744188393924098074812076012570722161120760125708977301207601257132108712076012571369323
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023890452890453341943042560028241802880x7f5b3c9cb4000x7f5a30e36e804061294061296553652428806941708917241212076012571388018120760125715967661207601257186044412076012571908636
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024090452890453341943042560024241827840x7f5b3c9cb3000x7f5a30e36ec022934722934765536517734486666911093344812076012571933512120760125721385231207601257228140212076012572285446
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024290452890453341943042560024241863040x7f5b3c9cba000x7f5a30e36f00487033487033655367208960102392713085460012076012572338044120760125725214011207601257283547912076012572883407
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024490452890453341943042560024241893120x7f5b3c9cb9000x7f5a30e36f4024494024494065536616038495618412236925212076012572920847120760125731031571207601257325643712076012573260468
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024690452890453341943042560020241907840x7f5b3c9cb8000x7f5a30e36f807853377853376553617104896214752227471924412076012573305261120760125734949951207601257401195212076012574059573
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024890452890453341943042560028241937920x7f5b3c9cb7000x7f5a30e36fc046069246069265536629145691198511650610812076012574086964120760125742753111207601257457546912076012574622629
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025090452890453341943042560024241968000x7f5b3c9cb6000x7f5a30e3700024561724561765536622592087155511145399612076012574646824120760125748337081207601257498842712076012574992106
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025290452890453341943042560024242010880x7f5b3c9cb5000x7f5a30e37040633203633203655368781824121551615631562812076012575042780120760125752385061207601257564954312076012575698499
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025490452890453341943042560024242046080x7f5b3c9cb4000x7f5a30e37080279761279761655367208960101095712936555212076012575738523120760125759202621207601257609738112076012576101458
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025690452890453341943042560020242060800x7f5b3c9cb3000x7f5a30e370c09268609268606553619202048241128230825484412076012576154166120760125763442601207601257695529612076012577007381
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025890452890453341943042560028242096000x7f5b3c9cba000x7f5a30e37100503617503617655367340032100825812909137212076012577027308120760125772280951207601257755737312076012577607256
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026090452890453341943042560024242131200x7f5b3c9cb9000x7f5a30e37140281387281387655367274496107670813786779212076012577633084120760125778220111207601257800089012076012578007630
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026290452890453341943042560024242181760x7f5b3c9cb8000x7f5a30e371806970976970976553610354688147477918882921212076012578064847120760125782399291207601257869544712076012578746123
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026490452890453341943042560024242222080x7f5b3c9cb7000x7f5a30e371c0312755312755655368257536120824115457742812076012578792198120760125789703251207601257917032412076012579219332
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026690452890453341943042560020242239360x7f5b3c9cb6000x7f5a30e37200106411310641136553621299200266886834167796012076012579244078120760125794357631207601258013831912076012580186790
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026890452890453341943042560028242279680x7f5b3c9cb5000x7f5a30e37240567884567884655368388608120946415508940012076012580206427120760125804152771207601258078887512076012580837710
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027090452890453341943042560024242320000x7f5b3c9cb4000x7f5a30e37280317825317825655368323072124292515914973212076012580862877120760125810797541207601258128231212076012581332640
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027290452890453341943042560024242378240x7f5b3c9cb3000x7f5a30e372c08291088291086553611927552167647121524685612076012581358017120760125815539911207601258209718812076012582145069
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027490452890453341943042560024242423680x7f5b3c9cba000x7f5a30e37300349809349809655369306112140383717974890412076012582184483120760125823627861207601258258742512076012582634910
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027690452890453341943042560020242435840x7f5b3c9cb9000x7f5a30e37340120802012080206553629163520365487346796857612076012582661730120760125828458241207601258364501912076012583696994
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027890452890453341943042560028242481280x7f5b3c9cb8000x7f5a30e37380637209637209655369437184134769717148353212076012583724805120760125839134981207601258433365612076012584384982
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028090452890453341943042560024242526720x7f5b3c9cb7000x7f5a30e373c0351051351051655369371648133716817116751612076012584411241120760125846030941207601258482805312076012584875624
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028290452890453341943042560024242592640x7f5b3c9cb6000x7f5a30e374009098339098336553613500416190771024471085212076012584894169120760125850974911207601258569524812076012585743908
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028490452890453341943042560024242648320x7f5b3c9cb5000x7f5a30e374404182754182756553611403264176123622545407212076012585781147120760125859589271207601258622836512076012586277299
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028690452890453341943042560020242663040x7f5b3c9cb4000x7f5a30e37480148736914873696553633357824417587553457307212076012586297246120760125864963641207601258748115812076012587530127
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028890452890453341943042560028242718720x7f5b3c9cb3000x7f5a30e374c07778687778686553611534336156907720095795212076012587556106120760125877534771207601258826755412076012588317070
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029090452890453341943042560024242774400x7f5b3c9cba000x7f5a30e375004210174210176553611534336171791821992920412076012588342247120760125885352321207601258880723112076012588855611
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029290452890453341943042560012242799360x7f5b3c9cb9000x7f5a30e37540112725111272516553619267584242696831038208412076012588889313120760125890800291207601258981858512076012589869014
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029490452890453341943042560024242865280x7f5b3c9cb8000x7f5a30e375804883694883696553613500416209049726755679212076012589907436120760125900913841207601259040850212076012590456736
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029690452890453341943042560020242880000x7f5b3c9cb7000x7f5a30e375c0176816317681636553637552128469868260161326412076012590483606120760125906677011207601259183841412076012591887556
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029890452890453341943042560032242945920x7f5b3c9cb6000x7f5a30e376009179139179136553613631488186781123979302012076012591916900120760125920982531207601259270704912076012592757943
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030090452890453341943042560024243011840x7f5b3c9cb5000x7f5a30e376404921714921716553613631488204953226231085212076012592790043120760125929756881207601259329424612076012593346126
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030290452890453341943042560012243049600x7f5b3c9cb4000x7f5a30e37680133671313367136553621692416274021535079670012076012593372425120760125935688051207601259444736012076012594497947
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030490452890453341943042560024243136000x7f5b3c9cb3000x7f5a30e376c06278836278836553617694720266221034077938012076012594538512120760125947169581207601259512671612076012595175105
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030690452890453341943042560020243148160x7f5b3c9cba000x7f5a30e37700233140923314096553657475072719611192089783212076012595200743120760125953964751207601259694494612076012596996190
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030890452890453341943042560020243175680x7f5b3c9cb9000x7f5a30e37740120070812007086553619660800246917331632802012076012597033539120760125972367841207601259803150012076012598083110
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031090452890453341943042560012243203200x7f5b3c9cb8000x7f5a30e377806744496744496553620381696256651832853652012076012598107074120760125983039791207601259874189612076012598789613
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031290452890453341943042560012243240960x7f5b3c9cb7000x7f5a30e377c0175902817590286553628704768361586146277688012076012598814840120760125990116551207601260017036812076012600221864
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031490452890453341943042560012243288960x7f5b3c9cb6000x7f5a30e37800119937711993776553636634624465451759555870412076012600263301120760126004442871207601260123100212076012601280081
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031690452890453341943042560020243301120x7f5b3c9cb5000x7f5a30e37840458438745843876553610584064013242226169495022812076012601312541120760126015030011207601260455146412076012604601985
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031890452890453341943042560020243328640x7f5b3c9cb4000x7f5a30e37880232342523234256553638535168483674261863549612076012604627803120760126048233031207601260636585412076012606417729
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032090452890453341943042560012243356160x7f5b3c9cb3000x7f5a30e378c0120349212034926553639124992491816062942103612076012606442425120760126066388131207601260742888812076012607478731
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032290452890453341943042560012243393920x7f5b3c9cba000x7f5a30e37900344287334428736553655771136700549689691334812076012607507675120760126076856871207601260996775412076012610018221
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032490452890453341943042560012243441920x7f5b3c9cb9000x7f5a30e379402322924232292465536725483529110319116566994812076012610059588120760126102379931207601261177334412076012611823225
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032690452890453341943042560020243454080x7f5b3c9cb8000x7f5a30e37980908679390867936553621069824026358456337263662012076012611852790120760126120331831207601261808610912076012618137750
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032890452890453341943042560020243481600x7f5b3c9cb7000x7f5a30e379c04571892457189265536762839049551914122347756012076012618168788120760126183421081207601262138609112076012621435800
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033090452890453341943042560012243509120x7f5b3c9cb6000x7f5a30e37a002330121233012165536773980169704797124214157612076012621466076120760126216598501207601262319968112076012623249090
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332904528904533419430425600122400x7f5b3c9cb5000x7f5a30e37a40681283668128366553611082137613878603177662967612076012623278975120760126234521601207601262797901512076012628030926