Comhaid
rocm-systems/tests/workloads/kernels/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.kd000889519889524335544322560083264640x00x7fade3204180505329505329524288629145679287710156147612075726469398590120757267148024151207572671512705312075726715240096
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00288951988952432768256002424124800x00x7fade3235100287062870651281929185117598812075726729418195120757267297332141207572672973993412075726729747417
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0048895198895244194304256002424129280x7faf1355c9000x7fade3235140213227213227655369175041396531787543612075726729813149120757267300452121207572673017497112075726730179210
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0068895198895244194304256003624136320x7faf1355c8000x7fade32351803939853939856553612451841811552316696412075726730254830120757267304301701207572673068056912075726730725675
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0088895198895244194304256002824140800x7faf1355c7000x7fade32351c0395251395251655369830401360091739925212075726730758526120757267309436071207572673119544612075726731239480
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00108895198895244194304256002424145280x7faf1355c6000x7fade32352002159212159216553610485761593842041351212075726731273814120757267314612041207572673159384412075726731597335
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00128895198895244194304256002424149760x7faf1355c5000x7fade3235240220531220531655369830401549651978926012075726731653419120757267318205621207572673195496212075726731958717
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00148895198895244194304256002424154240x7faf1355c4000x7fade32352802135052135056553610485761464861877367612075726732051710120757267322285601207572673235896012075726732362878
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00168895198895244194304256002824161280x7faf1355c3000x7fade32352c03919153919156553615728642298012942316012075726732422238120757267325944781207572673284439712075726732912960
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00188895198895244194304256002824168320x7faf1355ca000x7fade32353003959373959376553611796481589732029131212075726732942415120757267331437551207572673339607412075726733465988
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00208895198895244194304256002424175360x7faf1355c9000x7fade32353402163312163316553611141121594772045485212075726733499731120757267336898321207572673382199212075726733825967
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00228895198895244194304256002424182400x7faf1355c8000x7fade32353802184972184976553611141121571592009371212075726733880839120757267340554301207572673418919012075726734193220
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00248895198895244194304256002424189440x7faf1355c7000x7fade32353c02115312115316553611796481680492144916012075726734263731120757267344317481207572673456038812075726734564299
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00268895198895244194304256002824199040x7faf1355c6000x7fade32354004057374057376553618350082567373282140412075726734618921120757267347887071207572673504790512075726735093132
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00288895198895244194304256002824206080x7faf1355c5000x7fade32354403895713895716553613107201780052277836412075726735122406120757267353127041207572673556086212075726735602258
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00308895198895244194304256002424213120x7faf1355c4000x7fade32354802150252150256553612451841767892258552412075726735635831120757267358079011207572673593974012075726735943522
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00328895198895244194304256002424220160x7faf1355c3000x7fade32354c02102592102596553613107201817812319842812075726736006149120757267361752591207572673630357812075726736307469
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00348895198895244194304256002424227200x7faf1355ca000x7fade32355002153372153376553613107201828682338678012075726736377609120757267365490171207572673668069612075726736685010
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00368895198895244194304256002824236800x7faf1355c9000x7fade32355404011794011796553620971522944973760655212075726736747657120757267369157351207572673717205412075726737241875
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00388895198895244194304256002824243840x7faf1355c8000x7fade32355803952733952736553614417921944592497126012075726737273534120757267374562121207572673770837112075726737750250
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00408895198895244194304256002424250880x7faf1355c7000x7fade32355c02153952153956553613762561969052517894412075726737782340120757267379592501207572673809108912075726738094911
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00428895198895244194304256002424257920x7faf1355c6000x7fade32356002142732142736553615073282063052645245612075726738150544120757267383261281207572673845732712075726738461281
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00448895198895244194304256002424264960x7faf1355c5000x7fade32356402092912092916553614417922039192610280012075726738527605120757267386938061207572673882084512075726738824717
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00468895198895244194304256002824277120x7faf1355c4000x7fade32356803914093914096553623592963228624134395212075726738881753120757267390526841207572673930260212075726739345825
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00488895198895244194304256002824284160x7faf1355c3000x7fade32356c03938113938116553615728642111932698096012075726739377925120757267395558811207572673980692012075726739848009
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00508895198895244194304256002424291200x7faf1355ca000x7fade32357002091532091536553615073282066422638209612075726739882413120757267400701181207572674019763712075726740201866
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00528895198895244194304256002424300800x7faf1355c9000x7fade32357402108992108996553617039362348872999416812075726740256528120757267404337961207572674056291612075726740566764
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00548895198895244194304256002424307840x7faf1355c8000x7fade32357802159372159376553615728642126202724628812075726740632286120757267407987541207572674093139412075726740935139
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00568895198895244194304256002824320000x7faf1355c7000x7fade32357c04021394021396553626214403757664811428012075726740988498120757267411667521207572674142387112075726741491593
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00588895198895244194304256002824329600x7faf1355c6000x7fade32358004029774029776553617039362305692945509212075726741516720120757267417013091207572674195842812075726741999156
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00608895198895244194304256002424339200x7faf1355c5000x7fade32358402142272142276553616384002272992905541612075726742042357120757267422117071207572674234242612075726742346582
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00628895198895244194304256002424348800x7faf1355c4000x7fade32358802143532143536553619005442721863478396012075726742399490120757267425675451207572674269954412075726742703445
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00648895198895244194304256002424358400x7faf1355c3000x7fade32358c02116352116356553617039362318432966330012075726742769578120757267429361831207572674306530212075726743069586
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00668895198895244194304256002824373120x7faf1355ca000x7fade32359004435934435936553628835843965165086824412075726743124157120757267433046611207572674359009912075726743631270
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00688895198895244194304256002824382720x7faf1355c9000x7fade32359403907153907156553618350082500973203278412075726743666225120757267438361781207572674408529712075726744153991
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00708895198895244194304256002424392320x7faf1355c8000x7fade32359802228652228656553617694722601873325296012075726744182194120757267443694551207572674450625412075726744510223
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00728895198895244194304256002424401920x7faf1355c7000x7fade32359c02152192152196553620971523212124112568812075726744565446120757267447292931207572674486193212075726744865533
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00748895198895244194304256002424411520x7faf1355c6000x7fade3235a002102572102576553618350082501623198566012075726744931115120757267451110511207572674524001012075726745243977
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00768895198895244194304256002824426240x7faf1355c5000x7fade3235a404070754070756553631457284279495492172012075726745297436120757267454718491207572674573248812075726745776937
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00788895198895244194304256002824435840x7faf1355c4000x7fade3235a803924653924656553619660802672053415336412075726745804008120757267459838461207572674623488512075726746278059
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00808895198895244194304256002424445440x7faf1355c3000x7fade3235ac02106992106996553619005442652803400042812075726746311531120757267464939241207572674662304312075726746626857
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00828895198895244194304256002424457600x7faf1355ca000x7fade3235b002129532129536553622937603200214090063212075726746685847120757267468504021207572674698192112075726746985764
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00848895198895244194304256002424467200x7faf1355c9000x7fade3235b402111712111716553619660802733783504940012075726747053329120757267472214401207572674735023912075726747354409
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00868895198895244194304256002824484480x7faf1355c8000x7fade3235b803948653948656553634078724564225830256012075726747408690120757267475748781207572674782911712075726747870057
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00888895198895244194304256002824494080x7faf1355c7000x7fade3235bc03902833902836553620971522758663538773212075726747902608120757267480809551207572674833071412075726748372561
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00908895198895244194304256002424503680x7faf1355c6000x7fade3235c002175292175296553620316162904673719601212075726748406184120757267485753531207572674870895212075726748712824
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00928895198895244194304256002424515840x7faf1355c5000x7fade3235c402271712271716553624903683444894397114812075726748767034120757267489295911207572674906959012075726749073594
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00948895198895244194304256002424525440x7faf1355c4000x7fade3235c802101372101376553620971522996163837975612075726749141470120757267493119891207572674944094812075726749444804
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00968895198895244194304256002824542720x7faf1355c3000x7fade3235cc04020434020436553636700164977726388480812075726749500347120757267496734271207572674993198512075726749976191
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00988895198895244194304256002824554880x7faf1355ca000x7fade3235d003892573892576553622282242977793813758812075726750009553120757267501956641207572675044558212075726750514462
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001008895198895244194304256002424567040x7faf1355c9000x7fade3235d402177952177956553621626883200684086808412075726750539548120757267507207811207572675085470012075726750858301
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001028895198895244194304256002424581760x7faf1355c8000x7fade3235d802305612305616553626869763743054788057612075726750912922120757267510860591207572675122877812075726751232747
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001048895198895244194304256002424593920x7faf1355c7000x7fade3235dc02170272170276553622282242977223814229612075726751299902120757267514639771207572675159709612075726751601001
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001068895198895244194304256002824613760x7faf1355c6000x7fade3235e003998013998016553639321605265556721990012075726751656514120757267518209351207572675207837412075726752120256
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001088895198895244194304256002824625920x7faf1355c5000x7fade3235e403853873853876553623592963155164035379212075726752153197120757267523294121207572675257661112075726752616889
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001108895198895244194304256002424638080x7faf1355c4000x7fade3235e802149692149696553622937603396604350514812075726752649880120757267528161301207572675294844912075726752952483
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001128895198895244194304256002424652800x7faf1355c3000x7fade3235ec02251872251876553628835844275575466296412075726753011182120757267531890881207572675332844712075726753332509
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001148895198895244194304256002424664960x7faf1355ca000x7fade3235f002163052163056553623592963294314218317612075726753399153120757267535636461207572675369660512075726753700463
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001168895198895244194304256002824684800x7faf1355c9000x7fade3235f404157234157236553641943045708097327509212075726753753682120757267539247641207572675419244212075726754263058
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001188895198895244194304256002824696960x7faf1355c8000x7fade3235f803926653926656553624903683297144214406012075726754289127120757267544748411207572675472747912075726754795087
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001208895198895244194304256002424709120x7faf1355c7000x7fade3235fc02122192122196553624248323349964289556412075726754824652120757267550025181207572675513243712075726755136622
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001228895198895244194304256002424723840x7faf1355c6000x7fade32360002298972298976553630801924606505884636012075726755195662120757267553607561207572675550331512075726755507211
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001248895198895244194304256002424736000x7faf1355c5000x7fade32360402163312163316553624903683336924275177212075726755573494120757267557372341207572675587003312075726755873962
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001268895198895244194304256002824758400x7faf1355c4000x7fade32360804105134105136553644564485935657565393612075726755926610120757267561141921207572675637899112075726756403647
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001288895198895244194304256002824770560x7faf1355c3000x7fade32360c03954353954356553626214403445684411719612075726756452748120757267566170691207572675687130812075726756892024
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001308895198895244194304256002424782720x7faf1355ca000x7fade32361002149132149136553625559043915105007838412075726756941346120757267571015471207572675723386612075726757237747
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001328895198895244194304256002424800000x7faf1355c9000x7fade32361402343792343796553632768005066046493456012075726757292919120757267574588251207572675760458412075726757608466
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001348895198895244194304256002424812160x7faf1355c8000x7fade32361802142892142896553626214403910214999010812075726757675160120757267578388231207572675797066212075726757974616
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001368895198895244194304256002824834560x7faf1355c7000x7fade32361c04086514086516553647185926498838313421212075726758033185120757267582066611207572675847097912075726758521853
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001388895198895244194304256002824849280x7faf1355c6000x7fade32362003994253994256553627525123617234624970012075726758549184120757267587272981207572675898473712075726759035478
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001408895198895244194304256002424864000x7faf1355c5000x7fade32362402140912140916553626869763694684726838412075726759060174120757267592480951207572675937929512075726759383244
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001428895198895244194304256002424881280x7faf1355c4000x7fade32362802417212417216553634734085179626616693612075726759437635120757267596015331207572675975257312075726759756478
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001448895198895244194304256002424896000x7faf1355c3000x7fade32362c02174352174356553627525123896464981490012075726759840414120757267600023311207572676013561012075726760139710
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001468895198895244194304256002824920960x7faf1355ca000x7fade32363004122574122576553649807366563498388632012075726760193991120757267603690491207572676063560812075726760658935
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001488895198895244194304256002824935680x7faf1355c9000x7fade32363403886753886756553628835843796514856544012075726760706654120757267608687271207572676111928512075726761141662
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001508895198895244194304256002424950400x7faf1355c8000x7fade32363802178252178256553628180484086665225549212075726761188910120757267613504841207572676148504312075726761488947
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001528895198895244194304256002424967680x7faf1355c7000x7fade32363c02532592532596553636700165627187229610012075726761536776120757267617119221207572676187048112075726761874414
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001548895198895244194304256002424982400x7faf1355c6000x7fade32364002159212159216553628835843888754971470412075726761940286120757267621039201207572676223735912075726762241456
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015688951988952441943042560028241007360x7faf1355c5000x7fade32364404021234021236553651773447122629122086012075726762295396120757267624667981207572676272711712075726762751033
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015888951988952441943042560028241022080x7faf1355c4000x7fade32364803858173858176553630146564142635289130012075726762797720120757267629594351207572676320855412075726763257775
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016088951988952441943042560024241036800x7faf1355c3000x7fade32364c02181472181476553629491204102715249615612075726763283983120757267634723931207572676360711212075726763611151
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016288951988952441943042560024241056640x7faf1355ca000x7fade32365002651772651776553638666246146227826682412075726763664010120757267638346311207572676400199012075726764007428
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016488951988952441943042560024241071360x7faf1355c9000x7fade32365402206832206836553630146564272475474146012075726764073801120757267642407081207572676437686812075726764380802
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016688951988952441943042560028241098880x7faf1355c8000x7fade32365804012734012736553654394887485239583440812075726764433400120757267646186261207572676487894512075726764899826
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016888951988952441943042560028241113600x7faf1355c7000x7fade32365c03890033890036553631457284232825422794012075726764947395120757267651144641207572676536502212075726765386140
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017088951988952441943042560024241128320x7faf1355c6000x7fade32366002222972222976553630801925339136829106012075726765434861120757267655955811207572676573318012075726765737203
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017288951988952441943042560024241148160x7faf1355c5000x7fade32366402777872777876553640632325753437394474412075726765791253120757267659550991207572676612997812075726766134220
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017488951988952441943042560024241162880x7faf1355c4000x7fade32366802129452129456553631457284510715778744412075726766203469120757267663677371207572676649909612075726766503056
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017688951988952441943042560028241190400x7faf1355c3000x7fade32366c03991633991636553657016327461529539692812075726766556395120757267667291751207572676698725412075726767016811
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017888951988952441943042560028241207680x7faf1355ca000x7fade32367003908973908976553632768004447275689591612075726767062906120757267672315721207572676748373112075726767504507
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018088951988952441943042560024241224960x7faf1355c9000x7fade32367402799312799316553632112644928876316186412075726767556934120757267677195701207572676789540912075726767899411
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018288951988952441943042560024241247360x7faf1355c8000x7fade32367802905692905696553642598406132597856871612075726767952440120757267681338081207572676831684712075726768320834
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018488951988952441943042560024241264640x7faf1355c7000x7fade32367c02170672170676553632768005012076421388412075726768388169120757267685506051207572676868436512075726768688237
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018688951988952441943042560020241279360x7faf1355c6000x7fade323680041089741089765536773324898108512559379212075726768741746120757267689117231207572676917812212075726769200639
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018888951988952441943042560028241296640x7faf1355c5000x7fade32368403908433908436553634078724536015815475212075726769249570120757267694134811207572676966627912075726769687875
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019088951988952441943042560024241313920x7faf1355c4000x7fade32368802771692771696553633423364574135850033612075726769736906120757267699011581207572677007523712075726770079613
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019288951988952441943042560024241336320x7faf1355c3000x7fade32368c03040113040116553644564486747668592532412075726770140005120757267703027561207572677049491512075726770543545
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019488951988952441943042560024241353600x7faf1355ca000x7fade32369002203692203696553635389445286126756012012075726770586184120757267707493131207572677088579312075726770889849
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019688951988952441943042560020241368320x7faf1355c9000x7fade3236940435859435859655368978432113151014473204412075726770948678120757267711144321207572677139779012075726771445451
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019888951988952441943042560028241385600x7faf1355c8000x7fade32369803970413970416553636700165049796460326012075726771470708120757267716534691207572677191010712075726771931635
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020088951988952441943042560024241402880x7faf1355c7000x7fade32369c02298592298596553636044805870087504052812075726771979944120757267721517061207572677229394512075726772298036
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020288951988952441943042560024241427840x7faf1355c6000x7fade3236a003308813308816553648496647017269043660412075726772353118120757267725187441207572677272946312075726772751048
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020488951988952441943042560024241447680x7faf1355c5000x7fade3236a402223712223716553638010886179127908871212075726772811891120757267729765021207572677311394112075726773118370
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020688951988952441943042560020241457280x7faf1355c4000x7fade3236a804721294721296553614548992182943923409059612075726773171549120757267733494601207572677365825812075726773679814
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020888951988952441943042560028241477120x7faf1355c3000x7fade3236ac03884193884196553639321605340866795730012075726773729686120757267738915371207572677414257512075726774193408
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021088951988952441943042560024241496960x7faf1355ca000x7fade3236b002249052249056553638666246208637947504812075726774221671120757267744051341207572677454465312075726774548638
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021288951988952441943042560024241521920x7faf1355c9000x7fade3236b403561793561796553652428807713819842123612075726774602058120757267747728121207572677500065112075726775028690
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021488951988952441943042560024241541760x7faf1355c8000x7fade3236b802210252210256553640632325932967598187212075726775091507120757267752616091207572677539840912075726775402515
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021688951988952441943042560020241556480x7faf1355c7000x7fade3236bc05085235085236553610027008126013416141114812075726775455724120757267756260871207572677595824612075726775979527
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021888951988952441943042560028241576320x7faf1355c6000x7fade3236c003890973890976553641943045937977586964412075726776035391120757267761995241207572677645152312075726776475649
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022088951988952441943042560024241596160x7faf1355c5000x7fade3236c402228512228516553641287685939267603786012075726776520212120757267766844821207572677682256112075726776826782
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022288951988952441943042560024241623680x7faf1355c4000x7fade3236c8038309738309765536563609680082110220269612075726776879460120757267770683201207572677731439812075726777336519
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022488951988952441943042560024241646080x7faf1355c3000x7fade3236cc02223712223716553645875207086519065426812075726777398324120757267775628771207572677770079612075726777704854
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022688951988952441943042560020241663360x7faf1355ca000x7fade3236d005738255738256553611075584139187117826407212075726777758373120757267779251831207572677830134212075726778354982
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022888951988952441943042560028241685760x7faf1355c9000x7fade3236d404038834038836553647185926286718041514812075726778377895120757267785679001207572677882949812075726778850503
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023088951988952441943042560024241708160x7faf1355c8000x7fade3236d802310732310736553646530567718469881391612075726778899484120757267790653371207572677920933712075726779213297
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023288951988952441943042560024241740800x7faf1355c7000x7fade3236dc043441143441165536642252891138811640373612075726779268059120757267794346161207572677971413412075726779735558
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023488951988952441943042560024241765760x7faf1355c6000x7fade3236e002175692175696553651118087614709749732812075726779796691120757267799614931207572678009669312075726780100296
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023688951988952441943042560020241777920x7faf1355c5000x7fade3236e406480916480916553615007744188057624084621212075726780153485120757267803304521207572678075653012075726780777204
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023888951988952441943042560028241802880x7faf1355c4000x7fade3236e804040734040736553652428807405729478772012075726780828569120757267809934891207572678125588812075726781277694
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024088951988952441943042560024241827840x7faf1355c3000x7fade3236ec023147523147565536517734485097610892906012075726781325823120757267814896461207572678163364612075726781637122
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024288951988952441943042560024241863040x7faf1355ca000x7fade3236f00489801489801655367208960105147913541116812075726781690281120757267818632451207572678217972312075726782229793
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024488951988952441943042560024241893120x7faf1355c9000x7fade3236f4024585124585165536616038494273512064586412075726782273224120757267824390821207572678259300212075726782596385
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024688951988952441943042560020241907840x7faf1355c8000x7fade3236f807841057841056553617104896214493827468195212075726782648902120757267828243601207572678334163812075726783390230
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024888951988952441943042560028241937920x7faf1355c7000x7fade3236fc046383546383565536629145687658111266393212075726783415467120757267835984371207572678390067612075726783921938
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025088951988952441943042560024241968000x7faf1355c6000x7fade323700024662524662565536622592091030811647622012075726783969717120757267841403551207572678429571412075726784299500
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025288951988952441943042560024242010880x7faf1355c5000x7fade3237040593859593859655368781824126830816257022812075726784354672120757267845329931207572678491907112075726784939149
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025488951988952441943042560024242046080x7faf1355c4000x7fade3237080280913280913655367208960112210914361739612075726785007045120757267851753901207572678535314912075726785356785
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025688951988952441943042560020242060800x7faf1355c3000x7fade32370c09429639429636553619202048242026630798624412075726785410134120757267855837081207572678620594512075726786254724
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025888951988952441943042560028242096000x7faf1355ca000x7fade323710050036950036965536734003297704912491644012075726786280191120757267864718641207572678679954312075726786847405
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026088951988952441943042560024242131200x7faf1355c9000x7fade3237140283963283963655367274496107183813718370012075726786876549120757267870717011207572678725090112075726787254912
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026288951988952441943042560024242181760x7faf1355c8000x7fade32371806981056981056553610354688144289518461512412075726787314062120757267874813001207572678793745812075726787958590
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026488951988952441943042560024242222080x7faf1355c7000x7fade32371c0313987313987655368257536120576815423137612075726788031235120757267881992161207572678839921612075726788422873
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026688951988952441943042560020242239360x7faf1355c6000x7fade3237200106490510649056553621299200266878934170147612075726788479218120757267886472141207572678935137112075726789372848
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026888951988952441943042560028242279680x7faf1355c5000x7fade3237240568435568435655368388608111849714347598012075726789428111120757267895937701207572678996736812075726789987441
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027088951988952441943042560024242320000x7faf1355c4000x7fade3237280318833318833655368323072126595016200014412075726790055537120757267902219271207572679042576612075726790473364
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027288951988952441943042560024242378240x7faf1355c3000x7fade32372c08041878041876553611927552165193621364813612075726790504972120757267906872051207572679121440312075726791264744
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027488951988952441943042560024242423680x7faf1355ca000x7fade3237300350545350545655369306112141635418133579212075726791309397120757267914748821207572679169952112075726791722976
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027688951988952441943042560020242435840x7faf1355c9000x7fade3237340120693912069396553629163520365146946747483212075726791773340120757267919340801207572679273279612075726792757318
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027888951988952441943042560028242481280x7faf1355c8000x7fade3237380639033639033655369437184134937317291686012075726792802212120757267929649551207572679338687312075726793408649
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028088951988952441943042560024242526720x7faf1355c7000x7fade32373c0406083406083655369371648143235918319528412075726793457630120757267936227121207572679388415112075726793905482
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028288951988952441943042560024242592640x7faf1355c6000x7fade32374009114259114256553613500416189313324427423612075726793953732120757267941204701207572679471902712075726794767324
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028488951988952441943042560024242648320x7faf1355c5000x7fade32374404195314195316553611403264180384223092466812075726794812017120757267949777461207572679524782512075726795297549
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028688951988952441943042560020242663040x7faf1355c4000x7fade3237480148744914874496553633357824417522553460428012075726795330120120757267955084641207572679649293912075726796534759
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028888951988952441943042560028242718720x7faf1355c3000x7fade32374c07808197808196553611534336167123121345703212075726796568902120757267967486181207572679726525612075726797306503
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029088951988952441943042560024242774400x7faf1355ca000x7fade32375004235134235136553611534336182409723347556412075726797350064120757267975161351207572679778941312075726797829855
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029288951988952441943042560012242799360x7faf1355c9000x7fade3237540112667511266756553619267584242247431016172012075726797869158120757267980422121207572679878076912075726798823001
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029488951988952441943042560024242865280x7faf1355c8000x7fade32375804888254888256553613500416206292126408762012075726798872994120757267990434881207572679936012612075726799427885
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029688951988952441943042560020242880000x7faf1355c7000x7fade32375c0176914717691476553637552128470676060162414812075726799458662120757267996370851207572680080828012075726800876768
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029888951988952441943042560032242945920x7faf1355c6000x7fade32376009172419172416553613631488185946023818001212075726800910100120757268010986791207572680170731612075726801773875
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030088951988952441943042560024243011840x7faf1355c5000x7fade32376405347475347476553613631488208344926666023212075726801801817120757268019933951207572680233995312075726802383157
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030288951988952441943042560012243049600x7faf1355c4000x7fade3237680133835313383536553621692416275149235179873612075726802416469120757268025911521207572680347002812075726803538094
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030488951988952441943042560024243136000x7faf1355c3000x7fade32376c06354436354436553617694720290310437157535212075726803584851120757268037519471207572680416586512075726804233797
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030688951988952441943042560020243148160x7faf1355ca000x7fade3237700233325723332576553657475072719243292082835212075726804266197120757268044493841207572680599641712075726806065010
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030888951988952441943042560020243175680x7faf1355c9000x7fade3237740120125112012516553619660800247119331643107612075726806097540120757268062759351207572680707081212075726807119139
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031088951988952441943042560012243203200x7faf1355c8000x7fade32377806393936393936553620381696256904432906123212075726807156328120757268073218511207572680773640912075726807803050
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031288951988952441943042560012243240960x7faf1355c7000x7fade32377c0175898717589876553628704768360995846236820812075726807838666120757268080048881207572680916424312075726809233348
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031488951988952441943042560012243288960x7faf1355c6000x7fade3237800119785711978576553636634624463358059300176012075726809284123120757268094514411207572681023735812075726810279352
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031688951988952441943042560020243301120x7faf1355c5000x7fade3237840458422745842276553610584064013240511169491467612075726810316050120757268104991171207572681354982312075726813618177
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031888951988952441943042560020243328640x7faf1355c4000x7fade3237880232593723259376553638535168482985661786272412075726813653242120757268138343021207572681537621512075726815445313
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032088951988952441943042560012243356160x7faf1355c3000x7fade32378c0120494712049476553639124992491223562884126412075726815478835120757268156646931207572681645477012075726816522635
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032288951988952441943042560012243393920x7faf1355ca000x7fade3237900344376934437696553655771136700224589621729212075726816554655120757268167322091207572681901475812075726819064629
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032488951988952441943042560012243441920x7faf1355c9000x7fade32379402324179232417965536725483529114392116658133612075726819113480120757268192808371207572682081731012075726820884992
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032688951988952441943042560020243454080x7faf1355c8000x7fade3237980908739390873936553621069824026364644337265787612075726820916561120757268211149091207572682717008212075726827241636
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032888951988952441943042560020243481600x7faf1355c7000x7fade32379c04572507457250765536762839049542460122190097612075726827275669120757268274609611207572683050270712075726830574390
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033088951988952441943042560012243509120x7faf1355c6000x7fade3237a002329041232904165536773980169697470124133163212075726830602933120757268307999861207572683233981912075726832409751
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332889519889524419430425600122400x7faf1355c5000x7fade3237a40681377168137716553611082137613887674177759111212075726832448342120757268326153371207572683714347712075726837214971