Files
rocm-systems/tests/workloads/L2/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.kd000878965878970335544322560083264640x00x7f2dc4404180503729503729524288629145679067010135920012075512902723943120755131487271441207551314905034212075513149160654
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00287896587897032768256002424124800x00x7f2dc4435100278872788751281929675123974812075513163481509120755131637954961207551316380189612075513163809909
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0048789658789704194304256002424129280x7f2ed00c29000x7f2dc4435140225939225939655369175041340151716079612075513163869921120755131641044541207551316424269312075513164246831
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0068789658789704194304256003624136320x7f2ed00c28000x7f2dc44351803928413928416553612451841764982258882012075513164318495120755131644945321207551316474589012075513164813545
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0088789658789704194304256002824140800x7f2ed00c27000x7f2dc44351c0404219404219655369830401359311740482012075513164844773120755131650527681207551316531036712075513165378815
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00108789658789704194304256002424145280x7f2ed00c26000x7f2dc44352002174652174656553610485761541551973722812075513165405064120755131655985251207551316573196512075513165735538
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00128789658789704194304256002424149760x7f2ed00c25000x7f2dc4435240217427217427655369830401486811902302812075513165788587120755131659660431207551316609916212075513166102831
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00148789658789704194304256002424154240x7f2ed00c24000x7f2dc44352802160972160976553610485761477121884695212075513166186516120755131663674811207551316649996012075513166503706
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00168789658789704194304256002824161280x7f2ed00c23000x7f2dc44352c03980433980436553615728642251882883376412075513166555913120755131667397991207551316699451712075513167036836
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00188789658789704194304256002824168320x7f2ed00c2a000x7f2dc44353004036814036816553611796481618182071321212075513167069778120755131672690761207551316752731412075513167593291
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00208789658789704194304256002424175360x7f2ed00c29000x7f2dc44353402150672150676553611141121579932013620012075513167620732120755131678090721207551316794027212075513167944002
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00228789658789704194304256002424182400x7f2ed00c28000x7f2dc44353802226892226896553611141121564162004266412075513167997001120755131681797901207551316831643012075513168320312
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00248789658789704194304256002424189440x7f2ed00c27000x7f2dc44353c02185792185796553611796481729872214353612075513168385583120755131685562681207551316868778712075513168691461
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00268789658789704194304256002824199040x7f2ed00c26000x7f2dc44354004012494012496553618350082594443316339212075513168749099120755131689228261207551316918042512075513169248146
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00288789658789704194304256002824206080x7f2ed00c25000x7f2dc44354404052914052916553613107201849092361161212075513169273203120755131694657031207551316972458112075513169791305
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00308789658789704194304256002424213120x7f2ed00c24000x7f2dc44354802127532127536553612451841740792227415612075513169814839120755131700015401207551317013161912075513170135686
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00328789658789704194304256002424220160x7f2ed00c23000x7f2dc44354c02139952139956553613107201861832379904012075513170187061120755131703656981207551317049673712075513170500443
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00348789658789704194304256002424227200x7f2ed00c2a000x7f2dc44355002129852129856553613107201808672314322012075513170565274120755131707320961207551317086233512075513170866003
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00368789658789704194304256002824236800x7f2ed00c29000x7f2dc44355403958753958756553620971522875543681660412075513170919813120755131711004131207551317135353212075513171420082
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00388789658789704194304256002824243840x7f2ed00c28000x7f2dc44355804002974002976553614417922036452617696412075513171444047120755131716324101207551317188840912075513171954666
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00408789658789704194304256002424250880x7f2ed00c27000x7f2dc44355c02126592126596553613762561902542444945612075513171978009120755131721696871207551317229976612075513172303594
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00428789658789704194304256002424257920x7f2ed00c26000x7f2dc44356002166492166496553615073282098222689510812075513172357435120755131725368851207551317266984412075513172673502
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00448789658789704194304256002424264960x7f2ed00c25000x7f2dc44356402155792155796553614417922010862571181612075513172738463120755131729063231207551317303800212075513173042007
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00468789658789704194304256002824277120x7f2ed00c24000x7f2dc44356804029374029376553623592963179264073684412075513173092901120755131732762411207551317353479912075513173601056
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00488789658789704194304256002824284160x7f2ed00c23000x7f2dc44356c04030114030116553615728642181792794749212075513173625090120755131738106381207551317406807612075513174135599
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00508789658789704194304256002424291200x7f2ed00c2a000x7f2dc44357002122732122736553615073282044812623880012075513174159644120755131743536751207551317448407412075513174487774
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00528789658789704194304256002424300800x7f2ed00c29000x7f2dc44357402189152189156553617039362410543103781612075513174540151120755131747171921207551317485175212075513174855547
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00548789658789704194304256002424307840x7f2ed00c28000x7f2dc44357802180332180336553615728642198542820460012075513174919546120755131750944701207551317522647012075513175230384
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00568789658789704194304256002824320000x7f2ed00c27000x7f2dc44357c03997473997476553626214403565834573876412075513175285116120755131754674281207551317572422712075513175790655
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00588789658789704194304256002824329600x7f2ed00c26000x7f2dc44358004012574012576553617039362290412931428412075513175817846120755131759999051207551317625734412075513176326351
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00608789658789704194304256002424339200x7f2ed00c25000x7f2dc44358402116032116036553616384002286952932234012075513176351127120755131765386221207551317666838112075513176672053
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00628789658789704194304256002424348800x7f2ed00c24000x7f2dc44358802249452249456553619005442879563676259612075513176723649120755131768991001207551317703829912075513177042291
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00648789658789704194304256002424358400x7f2ed00c23000x7f2dc44358c02150672150676553617039362367933029826012075513177107532120755131772768581207551317740885712075513177412459
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00668789658789704194304256002824373120x7f2ed00c2a000x7f2dc44359004090414090416553628835843995145126212012075513177464476120755131776445361207551317790613412075513177972861
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00688789658789704194304256002824382720x7f2ed00c29000x7f2dc44359403893953893956553618350082434933120190812075513177997196120755131781912521207551317844069112075513178508436
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00708789658789704194304256002424392320x7f2ed00c28000x7f2dc44359802213932213936553617694722749763511333212075513178531148120755131787195691207551317885604912075513178859719
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00728789658789704194304256002424401920x7f2ed00c27000x7f2dc44359c02148672148676553620971523037443879450412075513178912507120755131790869271207551317921908612075513179222964
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00748789658789704194304256002424411520x7f2ed00c26000x7f2dc4435a002161612161616553618350082695093447368812075513179287283120755131794549251207551317958772412075513179591649
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00768789658789704194304256002824426240x7f2ed00c25000x7f2dc4435a403992753992756553631457284257845452630012075513179643275120755131798194031207551318007684112075513180146500
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00788789658789704194304256002824435840x7f2ed00c24000x7f2dc4435a803959373959376553619660802610903344933212075513180170986120755131803622801207551318061667812075513180683979
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00808789658789704194304256002424445440x7f2ed00c23000x7f2dc4435ac02184432184436553619005442564313291686412075513180706341120755131809035571207551318103779612075513181041644
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00828789658789704194304256002424457600x7f2ed00c2a000x7f2dc4435b002235372235376553622937603098493974420812075513181095414120755131812734751207551318141171412075513181415519
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00848789658789704194304256002424467200x7f2ed00c29000x7f2dc4435b402173392173396553619660802866413662022412075513181478816120755131816433921207551318177651212075513181780306
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00868789658789704194304256002824484480x7f2ed00c28000x7f2dc4435b804098734098736553634078724601025886555212075513181832103120755131820061101207551318227106912075513182338544
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00888789658789704194304256002824494080x7f2ed00c27000x7f2dc4435bc04015394015396553620971522762013546948812075513182363641120755131825509071207551318280898612075513182849333
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00908789658789704194304256002424503680x7f2ed00c26000x7f2dc4435c002221532221536553620316162923603739910812075513182880100120755131830705841207551318320754312075513183211516
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00928789658789704194304256002424515840x7f2ed00c25000x7f2dc4435c402209952209956553624903683389924334350812075513183265296120755131834413021207551318357778112075513183581604
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00948789658789704194304256002424525440x7f2ed00c24000x7f2dc4435c802089612089616553620971523001083843308012075513183645373120755131838113801207551318393969912075513183943657
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00968789658789704194304256002824542720x7f2ed00c23000x7f2dc4435cc04127234127236553636700164928876316869612075513183995894120755131841846581207551318445089612075513184519637
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00988789658789704194304256002824554880x7f2ed00c2a000x7f2dc4435d003969453969456553622282242959203785016812075513184543892120755131847273751207551318498289312075513185049703
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001008789658789704194304256002424567040x7f2ed00c29000x7f2dc4435d402106592106596553621626883219974116810012075513185073577120755131852608111207551318538993112075513185393752
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001028789658789704194304256002424581760x7f2ed00c28000x7f2dc4435d802192732192736553626869763756144798720812075513185445949120755131856184091207551318575408912075513185757919
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001048789658789704194304256002424593920x7f2ed00c27000x7f2dc4435dc02768992768996553622282243152534032500412075513185822028120755131859849671207551318615632612075513186160407
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001068789658789704194304256002824613760x7f2ed00c26000x7f2dc4435e003986173986176553639321605425376947994812075513186216020120755131863926451207551318664992312075513186691153
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001088789658789704194304256002824625920x7f2ed00c25000x7f2dc4435e404463634463636553623592963291834216027612075513186721940120755131868972821207551318718576012075513187227109
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001108789658789704194304256002424638080x7f2ed00c24000x7f2dc4435e802171292171296553622937603488224460053612075513187259910120755131874348791207551318756815812075513187571900
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001128789658789704194304256002424652800x7f2ed00c23000x7f2dc4435ec02273472273476553628835844174495324630012075513187624388120755131878009571207551318794223612075513187946015
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001148789658789704194304256002424664960x7f2ed00c2a000x7f2dc4435f002215452215456553623592963430294397430812075513188016657120755131881831951207551318831999412075513188324268
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001168789658789704194304256002824684800x7f2ed00c29000x7f2dc4435f404025634025636553641943045680867283146412075513188378940120755131885529521207551318881311112075513188880031
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001188789658789704194304256002824696960x7f2ed00c28000x7f2dc4435f803940493940496553624903683286974215485212075513188907903120755131890942291207551318934830812075513189415596
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001208789658789704194304256002424709120x7f2ed00c27000x7f2dc4435fc02187072187076553624248323582114595880812075513189443328120755131896262261207551318976110512075513189764976
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001228789658789704194304256002424723840x7f2ed00c26000x7f2dc44360002273692273696553630801924473175716608812075513189821330120755131899828641207551319012430312075513190128301
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001248789658789704194304256002424736000x7f2ed00c25000x7f2dc44360402173632173636553624903683430484402907612075513190193212120755131903588621207551319049054112075513190494612
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001268789658789704194304256002824758400x7f2ed00c24000x7f2dc44360804053214053216553644564485947897608555212075513190548903120755131907239801207551319098557812075513191028774
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001288789658789704194304256002824770560x7f2ed00c23000x7f2dc44360c03915873915876553626214403459054426733612075513191054322120755131912478171207551319149981512075513191565853
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001308789658789704194304256002424782720x7f2ed00c2a000x7f2dc44361002223452223456553625559043887164970732812075513191589156120755131917727741207551319190973312075513191913509
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001328789658789704194304256002424800000x7f2ed00c29000x7f2dc44361402333632333636553632768004725586032171612075513191967409120755131921442921207551319228909112075513192293254
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001348789658789704194304256002424812160x7f2ed00c28000x7f2dc44361802110892110896553626214403806084862651212075513192358696120755131925223691207551319265196912075513192655868
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001368789658789704194304256002824834560x7f2ed00c27000x7f2dc44361c04038994038996553647185926217717954211612075513192707524120755131928793271207551319314076612075513193209397
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001388789658789704194304256002824849280x7f2ed00c26000x7f2dc44362003917053917056553627525123613054619775612075513193236678120755131934183641207551319367100312075513193738510
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001408789658789704194304256002424864000x7f2ed00c25000x7f2dc44362402216512216516553626869764233805422948812075513193761613120755131939479611207551319408476012075513194088671
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001428789658789704194304256002424881280x7f2ed00c24000x7f2dc44362802413532413536553634734085139706606833212075513194141730120755131943165991207551319446731812075513194471162
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001448789658789704194304256002424896000x7f2ed00c23000x7f2dc44362c02189312189316553627525124470455717762812075513194556290120755131947189971207551319485435612075513194858021
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001468789658789704194304256002824920960x7f2ed00c2a000x7f2dc44363004151214151216553649807366607008486610012075513194912773120755131950874751207551319535675312075513195405208
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001488789658789704194304256002824935680x7f2ed00c29000x7f2dc44363404564114564116553628835843779414846853212075513195430314120755131956180311207551319591275012075513195979084
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001508789658789704194304256002424950400x7f2ed00c28000x7f2dc44363802209532209536553628180484368745601809212075513196007377120755131961946681207551319632874712075513196332852
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001528789658789704194304256002424967680x7f2ed00c27000x7f2dc44363c02526912526916553636700165567037137506812075513196388766120755131965620261207551319672042512075513196724129
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001548789658789704194304256002424982400x7f2ed00c26000x7f2dc44364002176172176176553628835844047005181502812075513196788689120755131969517841207551319708618312075513197090740
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015687896587897041943042560028241007360x7f2ed00c25000x7f2dc44364404117074117076553651773446826368743822412075513197142647120755131973186621207551319758538012075513197633038
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015887896587897041943042560028241022080x7f2ed00c24000x7f2dc44364803879453879456553630146563955005064508412075513197656822120755131978386591207551319808905712075513198139479
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016087896587897041943042560024241036800x7f2ed00c23000x7f2dc44364c02191552191556553629491204314435518598812075513198162642120755131983551361207551319849049512075513198494259
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016287896587897041943042560024241056640x7f2ed00c2a000x7f2dc44365002645132645136553638666245426166948992812075513198545604120755131987202531207551319888697312075513198891066
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016487896587897041943042560024241071360x7f2ed00c29000x7f2dc44365402154112154116553630146564101575254430012075513198954564120755131991242511207551319925657012075513199260533
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016687896587897041943042560028241098880x7f2ed00c28000x7f2dc44365804181214181216553654394887189359240026812075513199313531120755131994868091207551319975624712075513199805465
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016887896587897041943042560028241113600x7f2ed00c27000x7f2dc44365c03946753946756553631457284178785350584412075513199829210120755132000130461207551320026712512075513200318349
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017087896587897041943042560024241128320x7f2ed00c26000x7f2dc44366002186332186336553630801924334295553286412075513200342784120755132005346431207551320067000212075513200673899
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017287896587897041943042560024241148160x7f2ed00c25000x7f2dc44366402766912766916553640632325578447126474412075513200731026120755132008944811207551320106872012075513201072941
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017487896587897041943042560024241162880x7f2ed00c24000x7f2dc44366802226252226256553631457284618185915413212075513201138924120755132013005591207551320143831812075513201442267
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017687896587897041943042560028241190400x7f2ed00c23000x7f2dc44366c040505940505965536570163278084310020671612075513201497530120755132016663161207551320192807512075513201975939
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017887896587897041943042560028241207680x7f2ed00c2a000x7f2dc44367003962173962176553632768004293795495044012075513202008209120755132021936731207551320244951212075513202498410
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018087896587897041943042560024241224960x7f2ed00c29000x7f2dc44367402230112230116553632112645112246540824012075513202522545120755132027055101207551320284311012075513202847178
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018287896587897041943042560024241247360x7f2ed00c28000x7f2dc44367802895292895296553642598406075757759772412075513202897632120755132030720681207551320325590712075513203259996
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018487896587897041943042560024241264640x7f2ed00c27000x7f2dc44367c02258192258196553632768004768746109249212075513203324646120755132034901461207551320362790512075513203631827
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018687896587897041943042560020241279360x7f2ed00c26000x7f2dc443680041032141032165536773324897473912486370812075513203689534120755132038562241207551320412294212075513204173413
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018887896587897041943042560028241296640x7f2ed00c25000x7f2dc44368403963233963236553634078724415505670903612075513204200353120755132043826211207551320463877912075513204687589
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019087896587897041943042560024241313920x7f2ed00c24000x7f2dc44368802187292187296553633423365064476479165212075513204709499120755132048963781207551320503189712075513205035996
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019287896587897041943042560024241336320x7f2ed00c23000x7f2dc44368c03039953039956553644564486733648594086012075513205088394120755132052650161207551320545829412075513205505379
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019487896587897041943042560024241353600x7f2ed00c2a000x7f2dc44369002197212197216553635389445243476709854012075513205542377120755132057053331207551320584149212075513205845390
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019687896587897041943042560020241368320x7f2ed00c29000x7f2dc4436940435739435739655368978432112807914441126812075513205895073120755132060738111207551320635780912075513206405281
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019887896587897041943042560028241385600x7f2ed00c28000x7f2dc44369803895453895456553636700164971266356716812075513206428674120755132066149281207551320686724612075513206888078
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020087896587897041943042560024241402880x7f2ed00c27000x7f2dc44369c02228512228516553636044805831817464202812075513206933723120755132071136451207551320725188412075513207255972
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020287896587897041943042560024241427840x7f2ed00c26000x7f2dc4436a003287613287616553648496647246069300334012075513207306856120755132074816431207551320769204212075513207739260
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020487896587897041943042560024241447680x7f2ed00c25000x7f2dc4436a402261872261876553638010886167467899832412075513207776088120755132079451601207551320808547912075513208089551
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020687896587897041943042560020241457280x7f2ed00c24000x7f2dc4436a804703374703376553614548992182765823380903212075513208141828120755132083240381207551320863187612075513208679548
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020887896587897041943042560028241477120x7f2ed00c23000x7f2dc4436ac04049154049156553639321605104226532865612075513208706568120755132088877151207551320914979312075513209198242
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021087896587897041943042560024241496960x7f2ed00c2a000x7f2dc4436b002221132221136553638666245751537368705212075513209223488120755132094077121207551320954547112075513209549364
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021287896587897041943042560024241521920x7f2ed00c29000x7f2dc4436b404086194086196553652428807688539814247612075513209601271120755132097744291207551321003714812075513210085080
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021487896587897041943042560024241541760x7f2ed00c28000x7f2dc4436b802286892286896553640632326579178411994812075513210120335120755132102966661207551321043842612075513210442394
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021687896587897041943042560020241556480x7f2ed00c27000x7f2dc4436bc05059635059636553610027008125726316122785612075513210493759120755132106680241207551321099954212075513211021550
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021887896587897041943042560028241576320x7f2ed00c26000x7f2dc4436c004014254014256553641943045575727125124012075513211080089120755132112480211207551321150849912075513211556254
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022087896587897041943042560024241596160x7f2ed00c25000x7f2dc4436c402192992192996553641287686443448241506412075513211583324120755132117624891207551321189640912075513211903549
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022287896587897041943042560024241623680x7f2ed00c24000x7f2dc4436c8038224938224965536563609679360510166041612075513211954464120755132121384861207551321238472512075513212433284
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022487896587897041943042560024241646080x7f2ed00c23000x7f2dc4436cc02270672270676553645875206439428244990812075513212470954120755132126386441207551321277976312075513212783014
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022687896587897041943042560020241663360x7f2ed00c2a000x7f2dc4436d005747055747056553611075584139255417828035212075513212838106120755132130084021207551321338664112075513213435086
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022887896587897041943042560028241685760x7f2ed00c29000x7f2dc4436d404059794059796553647185926275798003847212075513213462066120755132136448791207551321390839812075513213954280
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023087896587897041943042560024241708160x7f2ed00c28000x7f2dc4436d802273852273856553646530566422848225662012075513213977484120755132141707971207551321431239612075513214315872
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023287896587897041943042560024241740800x7f2ed00c27000x7f2dc4436dc048189948189965536642252888372011388807612075513214367979120755132145432751207551321485495412075513214901711
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023487896587897041943042560024241765760x7f2ed00c26000x7f2dc4436e0022980922980965536511180880450810291848012075513214937688120755132151167121207551321525943212075513215262692
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023687896587897041943042560020241777920x7f2ed00c25000x7f2dc4436e406445476445476553615007744188518624144576012075513215313436120755132154917511207551321591654912075513215962823
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023887896587897041943042560028241802880x7f2ed00c24000x7f2dc4436e804002654002656553652428806885018814254012075513215987810120755132161859871207551321644598612075513216494862
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024087896587897041943042560024241827840x7f2ed00c23000x7f2dc4436ec022617122617165536517734481923310477401212075513216519608120755132167112651207551321685190412075513216855131
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024287896587897041943042560024241863040x7f2ed00c2a000x7f2dc4436f00488225488225655367208960101283112981032012075513216906587120755132170963831207551321741238212075513217460617
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024487896587897041943042560024241893120x7f2ed00c29000x7f2dc4436f4024297124297165536616038488631011339902412075513217496984120755132176693401207551321782134012075513217824643
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024687896587897041943042560020241907840x7f2ed00c28000x7f2dc4436f807837457837456553617104896214545827469402412075513217876049120755132180536591207551321857157612075513218618729
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024887896587897041943042560028241937920x7f2ed00c27000x7f2dc4436fc045761945761965536629145688571811348517612075513218642924120755132188269351207551321912613412075513219173370
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025087896587897041943042560024241968000x7f2ed00c26000x7f2dc443700024877724877765536622592089000811386756812075513219197324120755132193824521207551321953685212075513219540111
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025287896587897041943042560024242010880x7f2ed00c25000x7f2dc4437040593595593595655368781824124374115847396812075513219595985120755132197725311207551322015908912075513220181003
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025487896587897041943042560024242046080x7f2ed00c24000x7f2dc4437080280249280249655367208960110343714130077612075513220243459120755132204125281207551322058996712075513220593158
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025687896587897041943042560020242060800x7f2ed00c23000x7f2dc44370c09436999436996553619202048240313130810318012075513220645085120755132208202061207551322144404312075513221493522
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025887896587897041943042560028242096000x7f2ed00c2a000x7f2dc443710050076150076165536734003298867712664846412075513221518588120755132217098021207551322203828012075513222084971
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026087896587897041943042560024242131200x7f2ed00c29000x7f2dc4437140283667283667655367274496109759514060466412075513222110428120755132223017991207551322248163812075513222485235
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026287896587897041943042560024242181760x7f2ed00c28000x7f2dc44371807009217009216553610354688146379218787845612075513222540177120755132227086771207551322316499512075513223213398
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026487896587897041943042560024242222080x7f2ed00c27000x7f2dc44371c0314899314899655368257536125158816027136812075513223256288120755132234232341207551322362467312075513223670868
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026687896587897041943042560020242239360x7f2ed00c26000x7f2dc4437200107531310753136553621299200267136234175965212075513223694212120755132238793911207551322459154812075513224644768
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026887896587897041943042560028242279680x7f2ed00c25000x7f2dc4437240572171572171655368388608119361815192204412075513224673412120755132248713871207551322524722512075513225296830
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027087896587897041943042560024242320000x7f2ed00c24000x7f2dc4437280320073320073655368323072131987816888872412075513225321556120755132255072241207551322571154312075513225758308
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027287896587897041943042560024242378240x7f2ed00c23000x7f2dc44372c08062838062836553611927552169021021572430012075513225781040120755132259645021207551322649153912075513226540201
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027487896587897041943042560024242423680x7f2ed00c2a000x7f2dc4437300350593350593655369306112142065418171446412075513226576358120755132267484981207551322697393712075513227021736
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027687896587897041943042560020242435840x7f2ed00c29000x7f2dc4437340120680312068036553629163520365170446757918812075513227046422120755132272324961207551322803265212075513228099619
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027887896587897041943042560028242481280x7f2ed00c28000x7f2dc4437380638433638433655369437184124922916092115212075513228123644120755132283155311207551322873760912075513228803818
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028087896587897041943042560024242526720x7f2ed00c27000x7f2dc44373c0352611352611655369371648137637117617151212075513228827462120755132290228871207551322924912612075513229317001
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028287896587897041943042560024242592640x7f2ed00c26000x7f2dc44374009084979084976553613500416186279423935276812075513229342369120755132295267251207551323012368212075513230190364
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028487896587897041943042560024242648320x7f2ed00c25000x7f2dc44374404184914184916553611403264169595921705058012075513230225089120755132304112011207551323068095912075513230747760
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028687896587897041943042560020242663040x7f2ed00c24000x7f2dc4437480148774514877456553633357824417453953451236412075513230769401120755132309615981207551323194783412075513232016989
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028887896587897041943042560028242718720x7f2ed00c23000x7f2dc44374c07786517786516553611534336157441920134356412075513232047476120755132322319921207551323274799012075513232814281
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029087896587897041943042560024242774400x7f2ed00c2a000x7f2dc44375004200014200016553611534336169392821672027212075513232841481120755132330287881207551323330030712075513233368892
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029287896587897041943042560012242799360x7f2ed00c29000x7f2dc4437540112653111265316553619267584241746930977320812075513233393618120755132335799861207551323431902212075513234386092
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029487896587897041943042560024242865280x7f2ed00c28000x7f2dc44375804902734902736553613500416211363427049491212075513234422169120755132345948611207551323491262012075513234979244
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029687896587897041943042560020242880000x7f2ed00c27000x7f2dc44375c0176969917696996553637552128469877660162757612075513235010442120755132351935781207551323636621312075513236433738
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029887896587897041943042560032242945920x7f2ed00c26000x7f2dc44376009197379197376553613631488182683823405943612075513236464314120755132366518121207551323726284912075513237329482
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030087896587897041943042560024243011840x7f2ed00c25000x7f2dc44376404938914938916553613631488209891826859619212075513237358406120755132375494071207551323786988612075513237936110
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030287896587897041943042560012243049600x7f2ed00c24000x7f2dc4437680133632113363216553621692416273931035030072012075513237959413120755132381530841207551323903180012075513239100163
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030487896587897041943042560024243136000x7f2ed00c23000x7f2dc44376c06327876327876553617694720280144335861054012075513239135709120755132393141991207551323972699712075513239794423
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030687896587897041943042560020243148160x7f2ed00c2a000x7f2dc4437700233257723325776553657475072719142392086724812075513239824169120755132400073161207551324155786912075513241624745
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030887896587897041943042560020243175680x7f2ed00c29000x7f2dc4437740120053112005316553619660800247164831622968412075513241652486120755132418445871207551324263930312075513242708238
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031087896587897041943042560012243203200x7f2ed00c28000x7f2dc44377806402976402976553620381696256977032895305612075513242733044120755132429196221207551324333482012075513243400926
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031287896587897041943042560012243240960x7f2ed00c27000x7f2dc44377c0175765917576596553628704768361256546270120012075513243428206120755132436117791207551324477097312075513244837896
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031487896587897041943042560012243288960x7f2ed00c26000x7f2dc4437800119779311977936553636634624462145459162322012075513244877500120755132450503321207551324583560812075513245903497
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031687896587897041943042560020243301120x7f2ed00c25000x7f2dc4437840458456345845636553610584064013241924169493392812075513245932581120755132461325671207551324918487312075513249253392
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031887896587897041943042560020243328640x7f2ed00c24000x7f2dc4437880232492123249216553638535168483999461899898812075513249284440120755132494709511207551325101446412075513251081770
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032087896587897041943042560012243356160x7f2ed00c23000x7f2dc44378c0120728312072836553639124992491302262913813212075513251111195120755132512975031207551325208901912075513252156728
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032287896587897041943042560012243393920x7f2ed00c2a000x7f2dc4437900344326534432656553655771136700302389640569212075513252181875120755132523728581207551325465508712075513254722837
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032487896587897041943042560012243441920x7f2ed00c29000x7f2dc44379402323219232321965536725483529108623116603531612075513254766158120755132549328461207551325646835912075513256537640
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032687896587897041943042560020243454080x7f2ed00c28000x7f2dc4437980908894590889456553621069824026350757337264043612075513256570491120755132567577971207551326281584912075513262886669
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032887896587897041943042560020243481600x7f2ed00c27000x7f2dc44379c04572939457293965536762839049558355122192718812075513262916144120755132631139281207551326615711312075513266230794
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033087896587897041943042560012243509120x7f2ed00c26000x7f2dc4437a002328177232817765536773980169698756124149242812075513266257313120755132664542321207551326799374512075513268062127
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332878965878970419430425600122400x7f2ed00c25000x7f2dc4437a40681401168140116553611082137613881937177704244412075513268092905120755132682787031207551327280620212075513272877296