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

50 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_CYCLESSQ_BUSY_CYCLESSQ_WAVESGRBM_COUNTGRBM_GUI_ACTIVECPF_CPF_STAT_BUSYCPF_CPF_STAT_STALLCPF_CPF_TCIU_BUSYCPF_CPF_TCIU_STALLCPF_CPF_STAT_IDLECPF_CPF_TCIU_IDLECPF_CMP_UTCL1_STALL_ON_TRANSLATIONDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000870326870331335544322560083264640x00x7faa94c04180403681638324835242885046015046015046010419300503524012075333171398844120753373267129131207533732703595012075333417182692
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00287032687033132768256002424124800x00x7faa94c3510022295277688512278682786827868022740024307012075333431726747120753373419103731207533734191725312075333432073060
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0048703268703314194304256002424129280x7faba08f59000x7faa94c3514017341761571525655362167712167712167710225800222232012075333432135907120753373419780521207533734211485112075333432497238
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0068703268703314194304256003624136320x7faba08f58000x7faa94c3518031778083012740655363972253972253972250238400390819012075333432564523120753373421759701207533734242300812075333433065594
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0088703268703314194304256002824140800x7faba08f57000x7faa94c351c031938963024352655363992363992363992360245900392324012075333433097293120753373425585271207533734280652412075333433618712
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00108703268703314194304256002424145280x7faba08f56000x7faa94c3520017775521622780655362221932221932221930227600221856012075333433642927120753373429399631207533734306492212075333433975656
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00128703268703314194304256002424149760x7faba08f55000x7faa94c3524017329041570212655362166122166122166120228500220248012075333434032191120753373431089221207533734323356012075333434358467
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00148703268703314194304256002424154240x7faba08f54000x7faa94c3528016618401503968655362077292077292077290231700212241012075333434441361120753373433054001207533734342987912075333434749333
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00168703268703314194304256002824161280x7faba08f53000x7faa94c352c031529922977801655363941233941233941230245200403193012075333434798434120753373434743581207533734371787612075333435273477
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00188703268703314194304256002824168320x7faba08f5a000x7faa94c3530031721763015801655363965213965213965210242800449307012075333435291330120753373438471551207533734409067312075333435790127
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00208703268703314194304256002424175360x7faba08f59000x7faa94c3534017122321548926655362140282140282140280228400212503012075333435813781120753373442253911207533734435035012075333436139366
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00228703268703314194304256002424182400x7faba08f58000x7faa94c3538017444641587554655362180572180572180570233600213206012075333436187846120753373443911501207533734451594912075333436507811
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00248703268703314194304256002424189440x7faba08f57000x7faa94c353c016827201522805655362103392103392103390229900211947012075333436571108120753373445673081207533734469162712075333436872869
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00268703268703314194304256002824199040x7faba08f56000x7faa94c3540031820963012279655363977613977613977610248600404354012075333436922020120753373447322671207533734498442412075333437438300
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00288703268703314194304256002824206080x7faba08f55000x7faa94c3544031608722987912655363951083951083951080240100398298012075333437463006120753373450951431207533734534426112075333437970989
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00308703268703314194304256002424213120x7faba08f54000x7faa94c3548017117601559597655362139692139692139690227800214842012075333437994583120753373454436201207533734556857912075333438325588
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00328703268703314194304256002424220160x7faba08f53000x7faa94c354c017274561561000655362159312159312159310230800214008012075333438368268120753373456104991207533734573641712075333438692700
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00348703268703314194304256002424227200x7faba08f5a000x7faa94c3550017034401538779655362129292129292129290230300215508012075333438754064120753373457879371207533734591257612075333439056657
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00368703268703314194304256002824236800x7faba08f59000x7faa94c3554031010242932205655363876273876273876270240700398619012075333439101821120753373459533751207533734620025312075333439604785
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00388703268703314194304256002824243840x7faba08f58000x7faa94c3558032001443038776655364000174000174000170239700400529012075333439624181120753373463031321207533734654633012075333440115174
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00408703268703314194304256002424250880x7faba08f57000x7faa94c355c016957761535084655362119712119712119710233600215872012075333440138727120753373466428091207533734676760812075333440466416
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00428703268703314194304256002424257920x7faba08f56000x7faa94c3560016481441488977655362060172060172060170230900282492012075333440516078120753373468084081207533734693336612075333440823119
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00448703268703314194304256002424264960x7faba08f55000x7faa94c3564016962881535758655362120352120352120350231500210176012075333440885234120753373469834461207533734710728512075333441202434
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00468703268703314194304256002824277120x7faba08f54000x7faa94c3568031909923035225655363988733988733988730243100401357012075333441249902120753373471487241207533734740296212075333441753558
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00488703268703314194304256002824284160x7faba08f53000x7faa94c356c032036163015640655364004514004514004510251100394162012075333441776370120753373474767211207533734772183912075333442295856
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00508703268703314194304256002424291200x7faba08f5a000x7faa94c3570016864801531056655362108092108092108090235000213240012075333442319229120753373478179981207533734794231712075333442644253
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00528703268703314194304256002424300800x7faba08f59000x7faa94c3574017838401617793655362229792229792229790235000276641012075333442693995120753373479816771207533734810695612075333443010393
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00548703268703314194304256002424307840x7faba08f58000x7faa94c3578017236641547596655362154572154572154570230800211431012075333443075204120753373481602351207533734828455412075333443379259
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00568703268703314194304256002824320000x7faba08f57000x7faa94c357c03606432301507465536450803450803450803158242900392649012075333443430193120753373483247141207533734857063112075333443943206
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00588703268703314194304256002824329600x7faba08f56000x7faa94c3580031710882994927655363963853963853963850480500459950012075333443969475120753373486538311207533734890134812075333444485995
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00608703268703314194304256002424339200x7faba08f55000x7faa94c3584017176721562388655362147082147082147080233500211306012075333444509689120753373490133471207533734913766612075333444833160
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00628703268703314194304256002424348800x7faba08f54000x7faa94c3588017171361559196655362146412146412146410232400215384012075333444882812120753373491787861207533734930454512075333445198289
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00648703268703314194304256002424358400x7faba08f53000x7faa94c358c016991761534205655362123962123962123960230300210654012075333445260805120753373493573441207533734948214312075333445565160
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00668703268703314194304256002824373120x7faba08f5a000x7faa94c3590031463842981959655363932973932973932970226100399767012075333445614752120753373495216631207533734976982012075333446118839
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00688703268703314194304256002824382720x7faba08f59000x7faa94c3594031262402967265655363907793907793907790243600387976012075333446143535120753373498606991207533735010453712075333446659113
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00708703268703314194304256002424392320x7faba08f58000x7faa94c3598017737121611755655362217132217132217130228000217162012075333446684480120753373501957361207533735032021512075333447019122
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00728703268703314194304256002424401920x7faba08f57000x7faa94c359c017524161589448655362190512190512190510232700226138012075333447067472120753373503606951207533735048661412075333447385703
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00748703268703314194304256002424411520x7faba08f56000x7faa94c35a0017190561565300655362148812148812148810230200212163012075333447446656120753373505357331207533735065925212075333447751483
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00768703268703314194304256002824426240x7faba08f55000x7faa94c35a4031298962956062655363912363912363912360461800395884012075333447800033120753373507003721207533735095076912075333448295494
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00788703268703314194304256002824435840x7faba08f54000x7faa94c35a8031079202933350655363884893884893884890250200444773012075333448319057120753373510486891207533735129220612075333448830498
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00808703268703314194304256002424445440x7faba08f53000x7faa94c35ac017152401557087655362144042144042144040231000215538012075333448852699120753373513701261207533735149508412075333449184395
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00828703268703314194304256002424457600x7faba08f5a000x7faa94c35b0017182241554236655362147772147772147770233300218704012075333449233226120753373515376441207533735166356312075333449550846
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00848703268703314194304256002424467200x7faba08f59000x7faa94c35b4017289361575429655362161162161162161160232400212795012075333449612831120753373517130021207533735183748112075333449920623
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00868703268703314194304256002824484480x7faba08f58000x7faa94c35b8032329123065038655364041134041134041130249300412948012075333449973562120753373518789211207533735213075912075333450479822
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00888703268703314194304256002824494080x7faba08f57000x7faa94c35bc031706643012849655363963323963323963320251100395531012075333450503587120753373522134781207533735246003612075333451017261
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00908703268703314194304256002424503680x7faba08f56000x7faa94c35c0017280801565874655362160092160092160090228900219526012075333451040905120753373525153951207533735263987412075333451365097
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00928703268703314194304256002424515840x7faba08f55000x7faa94c35c4017494161581674655362186762186762186760232600223835012075333451414940120753373526806741207533735280739212075333451733292
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00948703268703314194304256002424525440x7faba08f54000x7faa94c35c8017100961556074655362137612137612137610228700207584012075333451794766120753373528582721207533735298355112075333452095605
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00968703268703314194304256002824542720x7faba08f53000x7faa94c35cc032502723065507655364062834062834062830264800418638012075333452146459120753373530313901207533735328386812075333452655665
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00988703268703314194304256002824554880x7faba08f5a000x7faa94c35d0031056162924046655363882013882013882010243900400778012075333452679309120753373533419471207533735359058512075333453180140
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001008703268703314194304256002424567040x7faba08f59000x7faa94c35d4016908561531360655362113562113562113560229300215761012075333453205717120753373536405051207533735376530412075333453525101
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001028703268703314194304256002424581760x7faba08f58000x7faa94c35d8017539361591290655362192412192412192410229400218008012075333453575334120753373538065831207533735393634212075333453887985
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001048703268703314194304256002424593920x7faba08f57000x7faa94c35dc017234241561085655362154272154272154270229400212733012075333453949810120753373539854621207533735411042012075333454259165
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001068703268703314194304256002824613760x7faba08f56000x7faa94c35e0032556963067431655364069614069614069610239300397868012075333454303337120753373541520201207533735441073812075333454813355
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001088703268703314194304256002824625920x7faba08f55000x7faa94c35e4030789522916805655363848683848683848680237100382844012075333454837089120753373544672171207533735471489512075333455347828
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001108703268703314194304256002424638080x7faba08f54000x7faa94c35e8016986401541271655362123292123292123290231600218695012075333455372353120753373547688141207533735489361312075333455695935
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001128703268703314194304256002424652800x7faba08f53000x7faa94c35ec017879441622863655362234922234922234920237600222634012075333455744405120753373549342531207533735506257212075333456063407
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001148703268703314194304256002424664960x7faba08f5a000x7faa94c35f0016902561533136655362112812112812112810231500212443012075333456130021120753373551134511207533735523841012075333456430429
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001168703268703314194304256002824684800x7faba08f59000x7faa94c35f4032594323078572655364074284074284074280251200397353012075333456479751120753373552776101207533735553520712075333456984409
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001188703268703314194304256002824696960x7faba08f58000x7faa94c35f8031400482977647655363925053925053925050248300398673012075333457014024120753373555932871207533735584064412075333457525334
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001208703268703314194304256002424709120x7faba08f57000x7faa94c35fc016999441531453655362124922124922124920231700217529012075333457549108120753373558945641207533735601936312075333457874212
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001228703268703314194304256002424723840x7faba08f56000x7faa94c3600018123041652102655362265372265372265370231600217721012075333457925107120753373560611221207533735619728112075333458261732
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001248703268703314194304256002424736000x7faba08f55000x7faa94c3604017322001568790655362165242165242165240233200209912012075333458325000120753373562467211207533735637184012075333458629946
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001268703268703314194304256002824758400x7faba08f54000x7faa94c3608032569763082297655364071214071214071210252600414263012075333458679408120753373564126391207533735667071712075333459185158
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001288703268703314194304256002824770560x7faba08f53000x7faa94c360c030678722889680655363834833834833834830240600393604012075333459209924120753373567227161207533735696815412075333459711576
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001308703268703314194304256002424782720x7faba08f5a000x7faa94c3610017122081550526655362140252140252140250232400205223012075333459740660120753373570255941207533735715055212075333460064332
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001328703268703314194304256002424800000x7faba08f59000x7faa94c3614018299281667347655362287402287402287400233400231337012075333460113503120753373571931121207533735733519112075333460437786
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001348703268703314194304256002424812160x7faba08f58000x7faa94c3618017028641539630655362128572128572128570229300213489012075333460500232120753373573852701207533735750990912075333460800069
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001368703268703314194304256002824834560x7faba08f57000x7faa94c361c032427203059645655364053394053394053390242900411768012075333460850102120753373575492691207533735780798612075333461340763
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001388703268703314194304256002824849280x7faba08f56000x7faa94c3620031845923006462655363980733980733980730275000395222012075333461363946120753373578611061207533735810846412075333461861872
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001408703268703314194304256002424864000x7faba08f55000x7faa94c3624017051281542701655362131402131402131400233200214976012075333461885065120753373581692631207533735829422212075333462216310
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001428703268703314194304256002424881280x7faba08f54000x7faa94c3628019376161769423655362422012422012422010232500239265012075333462258419120753373583342221207533735848334012075333462597879
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001448703268703314194304256002424896000x7faba08f53000x7faa94c362c017082561546953655362135312135312135310236800211783012075333462680062120753373585529391207533735867805812075333462979999
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001468703268703314194304256002824920960x7faba08f5a000x7faa94c3630032319523032603655364039934039934039930244700418010012075333463030874120753373587172581207533735897405612075333463525743
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001488703268703314194304256002824935680x7faba08f59000x7faa94c3634031660482999510655363957553957553957550245400396056012075333463550259120753373590393351207533735928493312075333464016746
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001508703268703314194304256002424950400x7faba08f58000x7faa94c3638017056801538578655362132092132092132090231000223266012075333464057481120753373593414121207533735946749112075333464360775
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001528703268703314194304256002424967680x7faba08f57000x7faa94c363c020101521854020655362512682512682512680231700248913012075333464411840120753373595079711207533735966524912075333464745239
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001548703268703314194304256002424982400x7faba08f56000x7faa94c364001758160157408965536219769219769219769022840021080615812075333464805632120753373597151691207533735983980812075333465111179
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015687032687033141943042560028241007360x7faba08f55000x7faa94c3644033514563169686655364189314189314189310237200414945012075333465163026120753373598796471207533736013612512075333465638890
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015887032687033141943042560028241022080x7faba08f54000x7faa94c3648031493922969327655363936733936733936730251600392798012075333465678794120753373601943641207533736043836212075333466126807
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016087032687033141943042560024241036800x7faba08f53000x7faa94c364c017887041629149655362235872235872235870229900214390012075333466169997120753373604940421207533736062028012075333466479943
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016287032687033141943042560024241056640x7faba08f5a000x7faa94c3650021140641958664655362642572642572642570232000261304012075333466524425120753373606620401207533736082715912075333466873434
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016487032687033141943042560024241071360x7faba08f59000x7faa94c3654017629201603173655362203642203642203640227900217046012075333466937272120753373608761181207533736100123712075333467243992
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016687032687033141943042560028241098880x7faba08f58000x7faa94c3658032348963038070655364043614043614043610242900413025012075333467293003120753373610420371207533736129819412075333467768607
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016887032687033141943042560028241113600x7faba08f57000x7faa94c365c032030403023913655364003794003794003790242300400762012075333467817879120753373613529141207533736163787112075333468275148
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017087032687033141943042560024241128320x7faba08f56000x7faa94c3660017577761583843655362197212197212197210228200218999012075333468321254120753373616873111207533736181306912075333468628074
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017287032687033141943042560024241148160x7faba08f55000x7faa94c3664022022082043802655362752752752752752750230200272264012075333468672196120753373618532291207533736202570812075333469029580
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017487032687033141943042560024241162880x7faba08f54000x7faa94c3668017729441610741655362216172216172216170233600219538012075333469093740120753373620767471207533736220298612075333469402744
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017687032687033141943042560028241190400x7faba08f53000x7faa94c366c031886482999076655363985803985803985800250400404303012075333469451344120753373622425061207533736249594312075333469904536
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017887032687033141943042560028241207680x7faba08f5a000x7faa94c3670031451682968212655363931453931453931450244600384976012075333469949670120753373625500231207533736279450012075333470405928
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018087032687033141943042560024241224960x7faba08f59000x7faa94c3674017543361589542655362192912192912192910227000222587012075333470447775120753373628484201207533736297369912075333470751329
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018287032687033141943042560024241247360x7faba08f58000x7faa94c3678023099042155063655362887372887372887370228600286481012075333470799228120753373630178581207533736320057712075333471162393
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018487032687033141943042560024241264640x7faba08f57000x7faa94c367c017744401618527655362218042218042218040228700224360012075333471222735120753373632512961207533736337705512075333471529566
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018687032687033141943042560020241279360x7faba08f56000x7faa94c3680032615203101513655364076894076894076890247100407516012075333471578446120753373634175351207533736368201212075333472056024
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018887032687033141943042560028241296640x7faba08f55000x7faa94c368403144224294703565536393027393027393027048500038794715812075333472097481120753373637348121207533736398105012075333472539983
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019087032687033141943042560024241313920x7faba08f54000x7faa94c3688017063201537975655362132892132892132890229500218736012075333472588313120753373640399291207533736416664812075333472892288
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019287032687033141943042560024241336320x7faba08f53000x7faa94c368c024141122253785655363017633017633017630228400298368012075333472940607120753373642077671207533736439912612075333473349427
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019487032687033141943042560024241353600x7faba08f5a000x7faa94c3690018187681629649655362273452273452273450238500215281012075333473406092120753373644620051207533736458856412075333473717040
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019687032687033141943042560020241368320x7faba08f59000x7faa94c3694035064083337374655364383004383004383000240300432097012075333473767053120753373646287241207533736491080112075333474258126
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019887032687033141943042560028241385600x7faba08f58000x7faa94c3698031664162997442655363958013958013958010240300397314012075333474301536120753373649668001207533736521447812075333474751402
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020087032687033141943042560024241402880x7faba08f57000x7faa94c369c017376401567463655362172042172042172040228000225753012075333474793470120753373652680781207533736539351712075333475097786
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020287032687033141943042560024241427840x7faba08f56000x7faa94c36a0026324642471310655363290573290573290570228000326705012075333475148219120753373654347961207533736564535412075333475558502
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020487032687033141943042560024241447680x7faba08f55000x7faa94c36a4017519041585130655362189872189872189870227000213169012075333475625827120753373657098341207533736583799212075333475941083
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020687032687033141943042560020241457280x7faba08f54000x7faa94c36a8037634723598171655364704334704334704330242000509695012075333475990394120753373658805521207533736618678912075333476505732
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020887032687033141943042560028241477120x7faba08f53000x7faa94c36ac031433282965555655363929153929153929150246000400257012075333476547910120753373662520691207533736650246612075333476988539
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021087032687033141943042560024241496960x7faba08f5a000x7faa94c36b0017820321616309655362227532227532227530229500225745012075333477038352120753373665607061207533736668726512075333477348658
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021287032687033141943042560024241521920x7faba08f59000x7faa94c36b4028568082693964655363571003571003571000241300352559012075333477397890120753373667271041207533736695494212075333477822428
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021487032687033141943042560024241541760x7faba08f58000x7faa94c36b8017723681609769655362215452215452215450231600222497012075333477881258120753373670234221207533736715014012075333478195221
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021687032687033141943042560020241556480x7faba08f57000x7faa94c36bc04038568387181665536504820504820504820024520054108215812075333478244603120753373671907801207533736751941712075333478777072
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021887032687033141943042560028241576320x7faba08f56000x7faa94c36c0031961763014279655363995213995213995210249500396344012075333478820182120753373675736561207533736782133412075333479270078
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022087032687033141943042560024241596160x7faba08f55000x7faa94c36c4017877441623759655362234672234672234670230700227919012075333479311866120753373678742941207533736800245312075333479621782
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022287032687033141943042560024241623680x7faba08f54000x7faa94c36c8030513442890372655363814173814173814170250400378989012075333479669661120753373680440521207533736832149012075333480120348
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022487032687033141943042560024241646080x7faba08f53000x7faa94c36cc018136001644123655362266992266992266990231800223121012075333480176042120753373683854891207533736851492812075333480491478
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022687032687033141943042560020241663360x7faba08f5a000x7faa94c36d0045950244424426655365743775743775743770251200570059012075333480539387120753373685566871207533736893252412075333481116629
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022887032687033141943042560028241685760x7faba08f59000x7faa94c36d4031735362972334655363966913966913966910245200400401012075333481161453120753373689859641207533736924308112075333481611840
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023087032687033141943042560024241708160x7faba08f58000x7faa94c36d8018159521656977655362269932269932269930229200226179012075333481651864120753373692974811207533736942659912075333481961409
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023287032687033141943042560024241740800x7faba08f57000x7faa94c36dc034722883311147655364340354340354340350242100430473012075333482014999120753373694673991207533736974547712075333482512113
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023487032687033141943042560024241765760x7faba08f56000x7faa94c36e0018205601639632655362275692275692275690230400224939012075333482569900120753373698101161207533736994595512075333482885096
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023687032687033141943042560020241777920x7faba08f55000x7faa94c36e4051545924995260655366443236443236443230245500643597012075333482934507120753373699862741207533737040899012075333483561653
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023887032687033141943042560028241802880x7faba08f54000x7faa94c36e8032017442998195655364002174002174002170244500412162012075333483607358120753373704729901207533737074018712075333484057734
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024087032687033141943042560024241827840x7faba08f53000x7faa94c36ec017670081601154655362208752208752208750230900221546012075333484100444120753373707936271207533737092946612075333484405240
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024287032687033141943042560024241863040x7faba08f5a000x7faa94c36f003912272375031465536489033489033489033024760048555915812075333484454181120753373709685051207533737128274212075333484970631
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024487032687033141943042560024241893120x7faba08f59000x7faa94c36f4019350801779046655362418842418842418840232600238242012075333485036223120753373713537821207533737150530012075333485361187
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024687032687033141943042560020241907840x7faba08f58000x7faa94c36f8062779686114231655367847457847457847450243000781032012075333485410097120753373715457801207533737206225512075333486139423
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024887032687033141943042560028241937920x7faba08f57000x7faa94c36fc037003843479029655364625474625474625470247900453223012075333486186871120753373721217751207533737241729212075333486679967
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025087032687033141943042560024241968000x7faba08f56000x7faa94c3700020057121825134655362507132507132507130232600242386012075333486728537120753373724753711207533737262881012075333487056757
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025287032687033141943042560024242010880x7faba08f55000x7faa94c3704047491604584834655365936445936445936440235600589240012075333487106850120753373726696101207533737305360612075333487707266
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025487032687033141943042560024242046080x7faba08f54000x7faa94c3708022102562052756655362762812762812762810227300273824012075333487767267120753373731232051207533737329936412075333488114563
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025687032687033141943042560020242060800x7faba08f53000x7faa94c370c07540008723053465536942500942500942500158244000923089012075333488161159120753373733390431207533737394895812075333488985621
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025887032687033141943042560028242096000x7faba08f5a000x7faa94c3710040037923826272655365004735004735004730254100499560012075333489033730120753373740065571207533737433311412075333489555861
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026087032687033141943042560024242131200x7faba08f59000x7faa94c3714022653202107157655362831642831642831640231800279179012075333489599341120753373743958341207533737457343212075333489945455
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026287032687033141943042560024242181760x7faba08f58000x7faa94c371805576208541943565536697025697025697025023650069510415812075333489997491120753373746150321207533737509134712075333490660263
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026487032687033141943042560024242222080x7faba08f57000x7faa94c371c025106882348133655363138353138353138350229100310038012075333490720685120753373751620671207533737536030512075333491117242
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026687032687033141943042560020242239360x7faba08f56000x7faa94c37200852148883620266553610651851065185106518502432001061977012075333491163588120753373754166241207533737611837812075333492061106
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026887032687033141943042560028242279680x7faba08f55000x7faa94c372404850720437909965536606339606339606339158243000562903012075333492108043120753373761801371207533737655261412075333492698340
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027087032687033141943042560024242320000x7faba08f54000x7faa94c372802986576238274565536373321373321373321158232800315168012075333492742422120753373766102131207533737681133212075333493169235
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027287032687033141943042560024242378240x7faba08f53000x7faa94c372c064239126258329655368029888029888029880247800800785012075333493213818120753373768695711207533737739484612075333493930069
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027487032687033141943042560024242423680x7faba08f5a000x7faa94c3730027926562639582655363490813490813490810243800346945012075333493990250120753373774756451207533737769964312075333494411233
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027687032687033141943042560020242435840x7faba08f59000x7faa94c3734096714569494217655361208931120893112089311582362001204077012075333494455695120753373777575631207533737855563512075333495444462
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027887032687033141943042560028242481280x7faba08f58000x7faa94c3738051130404942735655366391296391296391290238600636344012075333495494105120753373786161151207533737903819112075333496111762
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028087032687033141943042560024242526720x7faba08f57000x7faa94c373c028173122659717655363521633521633521630239800348261012075333496161064120753373790986701207533737932442812075333496578750
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028287032687033141943042560024242592640x7faba08f56000x7faa94c374007431760711668365536928969928969928969158244500906995012075333496630456120753373793839481207533737998058212075333497438207
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028487032687033141943042560024242648320x7faba08f55000x7faa94c374403345320317532565536418164418164418164024710041276615812075333497499441120753373800511421207533738031993912075333497964725
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028687032687033141943042560020242663040x7faba08f54000x7faa94c374801189595211736932655361486993148699314869930426800148503315812075333498013917120753373803788191207533738136313012075333499241618
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028887032687033141943042560028242718720x7faba08f53000x7faa94c374c062277446059869655367784677784677784670247800775232012075333499271604120753373814200891207533738195048412075333500050962
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029087032687033141943042560024242774400x7faba08f5a000x7faa94c3750033778083222045655364222254222254222250236200420493012075333500082280120753373820127241207533738228424112075333500607907
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029287032687033141943042560012242799360x7faba08f59000x7faa94c37540900656888433726553611258201125820112582002445001123937012075333500631330120753373823471211207533738308407412075333501625287
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029487032687033141943042560024242865280x7faba08f58000x7faa94c375804271952374010265536533993533993533993158241200487763012075333501667896120753373831552731207533738346967012075333502250800
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029687032687033141943042560020242880000x7faba08f57000x7faa94c375c0141501761397971065536176877117687711768771158241200176444515812075333502274494120753373835272701207533738469797912075333503701505
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029887032687033141943042560032242945920x7faba08f56000x7faa94c3760073500967173407655369187619187619187610246700920328012075333503731531120753373847605381207533738537061312075333504598302
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030087032687033141943042560024243011840x7faba08f55000x7faa94c3764039387843777180655364923474923474923470243700489849012075333504623068120753373854326921207533738575124912075333505204969
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030287032687033141943042560012243049600x7faba08f54000x7faa94c3768010690320105276856553613362891336289133628902426001331774012075333505229935120753373858104491207533738668772112075333506362590
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030487032687033141943042560024243136000x7faba08f53000x7faa94c376c050341444866775655366292676292676292670245800631616012075333506398877120753373867651601207533738717571612075333507064554
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030687032687033141943042560020243148160x7faba08f5a000x7faa94c3770018652112184929486553623315132331513233151304315002329207012075333507094219120753373872369961207533738878594112075333508901527
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030887032687033141943042560020243175680x7faba08f59000x7faa94c37740959901694368476553611998761199876119987602519001197109012075333508928237120753373888892511207533738968316412075333510025907
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031087032687033141943042560012243203200x7faba08f58000x7faa94c3778051216804957887655366402096402096402090299700636943012075333510061323120753373897876421207533739020091912075333510723363
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031287032687033141943042560012243240960x7faba08f57000x7faa94c377c01405508013897304655361756884175688417568840266400175467115812075333510749732120753373903109981207533739146922912075333512162747
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031487032687033141943042560012243288960x7faba08f56000x7faa94c3780096057129423905655361200713120071312007131582435001194384012075333512211007120753373915841081207533739236922112075333513239829
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031687032687033141943042560020243301120x7faba08f55000x7faa94c37840366774803650482665536458468445846844584684158245100457960715812075333513271047120753373924743401207533739552535612075333516576449
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031887032687033141943042560020243328640x7faba08f54000x7faa94c378801858446418426379655362323057232305723230571584289002322363012075333516605032120753373956304751207533739717174212075333518407180
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032087032687033141943042560012243356160x7faba08f53000x7faa94c378c0963324894595986553612041551204155120415502445001199105012075333518433489120753373972765411207533739806549512075333519487127
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032287032687033141943042560012243393920x7faba08f5a000x7faa94c379002753896027379153655363442369344236934423690301600343777815812075333519518175120753373981707741207533740045187612075333522053225
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032487032687033141943042560012243441920x7faba08f59000x7faa94c3794018580064184189336553623225072322507232250702405002320600012075333522100353120753374005662751207533740210178212075333523872505
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032687032687033141943042560020243454080x7faba08f58000x7faa94c3798072689296725271796553690861619086161908616102316009083384012075333523904295120753374022083411207533740826301212075333530221753
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032887032687033141943042560020243481600x7faba08f57000x7faa94c379c03658359236419575655364572948457294845729481582462004567712012075333530253763120753374083692511207533741141066712075333533564154
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033087032687033141943042560012243509120x7faba08f56000x7faa94c37a0018625360184584696553623281692328169232816902517002323842012075333533589671120753374115161061207533741305481312075333535391770
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332870326870331419430425600122400x7faba08f55000x7faa94c37a4054491744543331536553668114676811467681146702779006807296012075333535424030120753374131597721207533741768517612075333540205033