Files
rocm-systems/tests/workloads/L2/mi100/SQ_LEVEL_WAVES.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

50 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjGRBM_COUNTGRBM_GUI_ACTIVECPC_ME1_BUSY_FOR_PACKET_DECODESQ_CYCLESSQ_WAVESSQ_WAVE_CYCLESSQ_BUSY_CYCLESSQ_LEVEL_WAVESSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000880957880964335544322560083264640x00x7fbbc980418051127051127018203409016852428837100939438890640149883013212075540475152851120755407220859121207554072241455012075540722536682
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00288095788096432768256002424124800x00x7fbbc98351002866428664212882293205121163551792110466827212075540737022053120755407373457591207554073735247912075540737361113
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0048809578809644194304256002424129280x7fbcd54c29000x7fbbc9835140219356219356252361754856655361520212071580132060989296412075540737433828120755407376676771207554073780079612075540737804818
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0068809578809644194304256003624136320x7fbcd54c28000x7fbbc98351803879083879082485931032726553626363176429247490105634265612075540737881440120755407380862351207554073833311412075540738404702
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0088809578809644194304256002824140800x7fbcd54c27000x7fbbc98351c04440284440281607135522326553633763737529311170135236714012075540738441010120755407386391931207554073892319112075540738991663
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00108809578809644194304256002424145280x7fbcd54c26000x7fbbc9835200221156221156214231769256655361471710531595265059049684012075540739017822120755407392284701207554073936286912075540739366640
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00128809578809644194304256002424149760x7fbcd54c25000x7fbbc9835240214692214692224971717544655361513437171550493060719179212075540739425620120755407396183881207554073974974712075540739753319
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00148809578809644194304256002424154240x7fbcd54c24000x7fbbc9835280218748218748222991749992655361609704841570441064569326812075540739843346120755407400331061207554074016606512075540740169873
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00168809578809644194304256002824161280x7fbcd54c23000x7fbbc98352c04018284018283094332146326553632321329930347250129467071612075540740227801120755407404308641207554074068734312075540740729072
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00188809578809644194304256002824168320x7fbcd54c2a000x7fbbc98353003924283924283385631394326553634432363729619860137911157212075540740766552120755407409553421207554074120446012075540741271771
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00208809578809644194304256002424175360x7fbcd54c29000x7fbbc9835340221796221796228901774376655361499565721583324060163653612075540741296707120755407415018991207554074163597812075540741639554
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00228809578809644194304256002424182400x7fbcd54c28000x7fbbc9835380217132217132232251737064655361602546731567945064283566812075540741699365120755407418924571207554074202493712075540742028537
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00248809578809644194304256002424189440x7fbcd54c27000x7fbbc98353c0211524211524230341692200655361634273621527480065552556412075540742100761120755407422826951207554074241181512075540742415386
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00268809578809644194304256002824199040x7fbcd54c26000x7fbbc98354003903723903722903731229846553631788688929383340127336501612075540742475398120755407426668541207554074291469212075540742981649
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00288809578809644194304256002824206080x7fbcd54c25000x7fbbc98354403958523958522885231668246553627312940329861590109433397212075540743012305120755407432246111207554074347693012075540743545927
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00308809578809644194304256002424213120x7fbcd54c24000x7fbbc9835480212716212716229141701736655361651259461526962066232320012075540743568499120755407437706881207554074389980812075540743903422
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00328809578809644194304256002424220160x7fbcd54c23000x7fbbc98354c0217084217084226561736680655361649033141567295066142452412075540743962341120755407441598061207554074429228612075540744296071
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00348809578809644194304256002424227200x7fbcd54c2a000x7fbbc9835500216020216020243391728168655361607969541554010064500224012075540744366873120755407445478051207554074467900412075540744682640
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00368809578809644194304256002824236800x7fbcd54c29000x7fbbc98355403954283954282613431634326553630283703429859540121317364812075540744741770120755407449297231207554074518220212075540745249303
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00388809578809644194304256002824243840x7fbcd54c28000x7fbbc98355804007244007243421932058006553627552062130084940110389951612075540745273598120755407454759601207554074572891912075540745795428
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00408809578809644194304256002424250880x7fbcd54c27000x7fbbc98355c0218604218604266421748840655361613370851562307064716869212075540745820885120755407460247581207554074615675712075540746160677
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00428809578809644194304256002424257920x7fbcd54c26000x7fbbc9835600217684217684223541741480655361587238821574914063671179612075540746219556120755407464221961207554074655531512075540746558957
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00448809578809644194304256002424264960x7fbcd54c25000x7fbbc9835640212796212796236791702376655361651636101532190066247046412075540746628276120755407468039541207554074693419312075540746937731
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00468809578809644194304256002824277120x7fbcd54c24000x7fbbc98356803939083939082912231512726553632287964529608150129333606412075540746995238120755407471901921207554074744107112075540747509794
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00488809578809644194304256002824284160x7fbcd54c23000x7fbbc98356c03902123902123177331217046553634900452029509800139783584412075540747534420120755407477351501207554074798426812075540748052292
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00508809578809644194304256002424291200x7fbcd54c2a000x7fbbc9835700212476212476256651699816655361604660331533625064368413212075540748080785120755407482858671207554074841546612075540748419164
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00528809578809644194304256002424300800x7fbcd54c29000x7fbbc9835740217580217580277451740648655361719221441548125068949978412075540748477452120755407486652251207554074879722512075540748800713
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00548809578809644194304256002424307840x7fbcd54c28000x7fbbc9835780212684212684214141701480655361614736141530432064771048012075540748872617120755407490543431207554074918426312075540749188023
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00568809578809644194304256002824320000x7fbcd54c27000x7fbbc98357c04056044056042904932448406553629498597030642710118176155212075540749242043120755407494417021207554074970170012075540749768832
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00588809578809644194304256002824329600x7fbcd54c26000x7fbbc98358003973243973243045731786006553630834022030032490123517739212075540749791003120755407499893791207554075024281812075540750312302
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00608809578809644194304256002424339200x7fbcd54c25000x7fbbc9835840212828212828233771702632655361577609781537601063286268812075540750334153120755407505328961207554075066329612075540750667102
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00628809578809644194304256002424348800x7fbcd54c24000x7fbbc9835880215452215452237291723624655361724157471541662069149662812075540750726472120755407509112951207554075104345412075540751047268
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00648809578809644194304256002424358400x7fbcd54c23000x7fbbc98358c0207812207812234681662504655361650789151497692066213994012075540751117228120755407513007331207554075142777212075540751431622
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00668809578809644194304256002824373120x7fbcd54c2a000x7fbbc98359003914363914363283131314966553633570453629482390134463860412075540751488739120755407516770511207554075192729012075540751994408
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00688809578809644194304256002824382720x7fbcd54c29000x7fbbc98359403896363896363158731170966553630687795929499440122932692012075540752018834120755407522280881207554075247736712075540752544250
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00708809578809644194304256002424392320x7fbcd54c28000x7fbbc9835980216028216028226131728232655361621970451555128065060558412075540752566201120755407527645661207554075289624512075540752900162
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00728809578809644194304256002424401920x7fbcd54c27000x7fbbc98359c0215868215868235631726952655361703966301559113068341730412075540752956767120755407531557641207554075328888312075540753292781
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00748809578809644194304256002424411520x7fbcd54c26000x7fbbc9835a00214260214260259121714088655361600969181535587064220680812075540753363202120755407535388021207554075366936212075540753673188
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00768809578809644194304256002824426240x7fbcd54c25000x7fbbc9835a404013564013562720432108566553626831062030329750107506251612075540753731376120755407539172001207554075417511912075540754244470
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00788809578809644194304256002824435840x7fbcd54c24000x7fbbc9835a804481004481001677735848086553635941143129775320143946265212075540754269066120755407544685581207554075475591612075540754823596
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00808809578809644194304256002424445440x7fbcd54c23000x7fbbc9835ac0216372216372245691730984655361639690311553235065769522812075540754845838120755407550477551207554075517911412075540755183104
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00828809578809644194304256002424457600x7fbcd54c2a000x7fbbc9835b00221204221204252601769640655361674693521603978067169936812075540755242565120755407554354331207554075557207312075540755575714
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00848809578809644194304256002424467200x7fbcd54c29000x7fbbc9835b40209996209996200701679976655361665593181479508066806959212075540755645303120755407558197511207554075594583112075540755949479
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00868809578809644194304256002824484480x7fbcd54c28000x7fbbc9835b804167724167723332233341846553634227195231638900137090518012075540756012496120755407562016701207554075646950812075540756536189
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00888809578809644194304256002824494080x7fbcd54c27000x7fbbc9835bc03957963957962845131663766553626559258329816880106418803612075540756560594120755407567546271207554075700790612075540757075141
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00908809578809644194304256002424503680x7fbcd54c26000x7fbbc9835c00217956217956229861743656655361666761211579712066854205612075540757098304120755407573040641207554075743798412075540757441622
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00928809578809644194304256002424515840x7fbcd54c25000x7fbbc9835c40219996219996278341759976655361731833821568137069456664012075540757499289120755407576935031207554075782758212075540757831236
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00948809578809644194304256002424525440x7fbcd54c24000x7fbbc9835c80217836217836224421742696655361593949521553821063939506412075540757902007120755407580802211207554075821254012075540758216392
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00968809578809644194304256002824542720x7fbcd54c23000x7fbbc9835cc04133164133163231633065366553631202626231134070124992552012075540758274950120755407584688591207554075873429812075540758800667
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00988809578809644194304256002824554880x7fbcd54c2a000x7fbbc9835d004574524574521637936596246553625132815729604240100713100812075540758826966120755407590298161207554075932405512075540759391986
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001008809578809644194304256002424567040x7fbcd54c29000x7fbbc9835d40210628210628254401685032655361641593481504342065846520412075540759417454120755407596152541207554075974293312075540759746916
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001028809578809644194304256002424581760x7fbcd54c28000x7fbbc9835d80220388220388258171763112655361758184351599379070513371212075540759805515120755407599901321207554076012661112075540760130409
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001048809578809644194304256002424593920x7fbcd54c27000x7fbbc9835dc0219916219916233391759336655361657906641589556066501474412075540760200549120755407603763701207554076051092912075540760514563
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001068809578809644194304256002824613760x7fbcd54c26000x7fbbc9835e004033484033482896932267926553627832424830458490111511551212075540760570967120755407607563681207554076101588712075540761083300
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001088809578809644194304256002824625920x7fbcd54c25000x7fbbc9835e403974443974443736931795606553627877449029895230111691440412075540761107915120755407613054861207554076155828412075540761625567
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001108809578809644194304256002424638080x7fbcd54c24000x7fbbc9835e80211172211172251241689384655361649239501518585066152077612075540761648069120755407618542831207554076198372212075540761987420
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001128809578809644194304256002424652800x7fbcd54c23000x7fbbc9835ec0220700220700275651765608655361840117591595630073791677612075540762046299120755407622448411207554076238084012075540762384618
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001148809578809644194304256002424664960x7fbcd54c2a000x7fbbc9835f00219532219532251131756264655361683416721581829067518904412075540762454498120755407626310791207554076276595912075540762770024
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001168809578809644194304256002824684800x7fbcd54c29000x7fbbc9835f403976443976443266031811606553633512691129892870134232591212075540762827812120755407630147581207554076327091612075540763339633
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001188809578809644194304256002824696960x7fbcd54c28000x7fbbc9835f803890203890202638231121686553629989911129257760120142247212075540763362926120755407635609951207554076381059412075540763877122
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001208809578809644194304256002424709120x7fbcd54c27000x7fbbc9835fc0215804215804241321726440655361632773201560965065496188812075540763900245120755407641027521207554076423507212075540764238864
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001228809578809644194304256002424723840x7fbcd54c26000x7fbbc9836000222252222252264611778024655361895205471608731075995191612075540764293656120755407644859511207554076462355012075540764627446
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001248809578809644194304256002424736000x7fbcd54c25000x7fbbc9836040221116221116237621768936655361686099841596390067628888812075540764697967120755407648726691207554076500770812075540765011891
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001268809578809644194304256002824758400x7fbcd54c24000x7fbbc98360804094524094523451832756246553629958604130866130120016483612075540765068306120755407652624271207554076552690612075540765593552
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001288809578809644194304256002824770560x7fbcd54c23000x7fbbc98360c03944923944923474931559446553628879905229847090115701200812075540765617616120755407658109041207554076606354312075540766132253
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001308809578809644194304256002424782720x7fbcd54c2a000x7fbbc9836100214844214844223871718760655361723108001552313069106094412075540766155065120755407663531421207554076648562112075540766489286
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001328809578809644194304256002424800000x7fbcd54c29000x7fbbc9836140233836233836281241870696655361970792591670945079016759212075540766547475120755407667347401207554076687745912075540766881225
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001348809578809644194304256002424812160x7fbcd54c28000x7fbbc9836180213516213516249071708136655361669748871541167066972139612075540766951165120755407671329781207554076726465712075540767268565
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001368809578809644194304256002824834560x7fbcd54c27000x7fbbc98361c04058284058283720032466326553631291383630514770125347415612075540767325050120755407675193761207554076778081512075540767847771
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001388809578809644194304256002824849280x7fbcd54c26000x7fbbc9836200393844393844340343150760655362313095932979646092705656012075540767870944120755407680681741207554076832161212075540768389608
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001408809578809644194304256002424864000x7fbcd54c25000x7fbbc9836240211540211540254391692328655361678452241520645067325071212075540768414575120755407686131311207554076874257012075540768746321
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001428809578809644194304256002424881280x7fbcd54c24000x7fbbc9836280242420242420287071939368655362099329191760320084158838012075540768804890120755407689884891207554076913888912075540769143008
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001448809578809644194304256002424896000x7fbcd54c23000x7fbbc98362c0215876215876240901727016655361650079861555104066187026412075540769232284120755407694075271207554076953984712075540769543693
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001468809578809644194304256002824920960x7fbcd54c2a000x7fbbc98363004097724097723499032781846553631685898730849810126925232012075540769599026120755407697859261207554077005056412075540770119533
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001488809578809644194304256002824935680x7fbcd54c29000x7fbbc98363403876203876203474931009686553635172203829268390140870760812075540770142937120755407703412831207554077058992212075540770657944
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001508809578809644194304256002424950400x7fbcd54c28000x7fbbc9836380225108225108244121800872655361666362551614726066839587612075540770679173120755407708777601207554077101504012075540771018834
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001528809578809644194304256002424967680x7fbcd54c27000x7fbbc98363c0257132257132312782057064655362230371011867441089399778412075540771078195120755407712675191207554077142639812075540771430269
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001548809578809644194304256002424982400x7fbcd54c26000x7fbbc9836400211444211444251151691560655361622327901525805065077115212075540771500480120755407716769571207554077180719612075540771810826
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015688095788096441943042560028241007360x7fbcd54c25000x7fbbc98364404127004127003695733016086553630395210030894390121762727612075540771867462120755407720705551207554077233679412075540772403929
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015888095788096441943042560028241022080x7fbcd54c24000x7fbbc98364803926523926523083131412246553634368268529597130137657898012075540772428123120755407726243121207554077287695112075540772943471
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016088095788096441943042560024241036800x7fbcd54c23000x7fbbc98364c0215004215004229821720040655361600555331531918064206216812075540772965422120755407731686301207554077330030912075540773304442
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016288095788096441943042560024241056640x7fbcd54c2a000x7fbbc9836500263844263844283242110760655362357239851948188094473970012075540773360286120755407735516681207554077371758712075540773721477
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016488095788096441943042560024241071360x7fbcd54c29000x7fbbc9836540217148217148278401737192655361728814431544069069336724012075540773791076120755407739668661207554077409870512075540774102896
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016688095788096441943042560028241098880x7fbcd54c28000x7fbbc98365804120444120443409432963606553632576390231148180130488037612075540774161104120755407743507041207554077461726312075540774684617
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016888095788096441943042560028241113600x7fbcd54c27000x7fbbc98365c03992523992522923031940246553626799478730012980107379538012075540774709173120755407749036611207554077516030012075540775227676
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017088095788096441943042560024241128320x7fbcd54c26000x7fbbc9836600215492215492238161723944655361719238731549648068956166012075540775251471120755407754482991207554077558109812075540775584810
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017288095788096441943042560024241148160x7fbcd54c25000x7fbbc9836640276996276996307442215976655362447947692047402098101478412075540775644621120755407758281371207554077600205612075540776005943
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017488095788096441943042560024241162880x7fbcd54c24000x7fbbc9836680214492214492251011715944655361651631231548975066249228412075540776074761120755407762486151207554077638093412075540776384817
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017688095788096441943042560028241190400x7fbcd54c23000x7fbbc98366c04009804009803729632078486553633029817030048180132303895612075540776440761120755407766335731207554077689181212075540776937945
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017888095788096441943042560028241207680x7fbcd54c2a000x7fbbc98367003945723945723381331565846553631627671329823490126693050812075540776970545120755407771620511207554077741629012075540777460255
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018088095788096441943042560024241224960x7fbcd54c29000x7fbbc9836740222356222356277801778856655361714831411599713068779012412075540777496222120755407776790081207554077781612812075540777819934
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018288095788096441943042560024241247360x7fbcd54c28000x7fbbc98367802896442896443100323171606553625692080321488580102954070012075540777875968120755407780703661207554077825308612075540778257136
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018488095788096441943042560024241264640x7fbcd54c27000x7fbbc98367c0211132211132223661689064655361649649891505698066169848012075540778347514120755407785313241207554077866092412075540778664794
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018688095788096441943042560020241279360x7fbcd54c26000x7fbbc98368004092204092203538532737686553637513292631030160150235632012075540778721299120755407789052431207554077917052112075540779218423
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018888095788096441943042560028241296640x7fbcd54c25000x7fbbc98368403983883983882844631871126553629056998229913910116410670812075540779248739120755407794410801207554077969739912075540779741375
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019088095788096441943042560024241313920x7fbcd54c24000x7fbbc9836880209012209012216721672104655361648122621496349066112280012075540779775979120755407799564381207554078008523712075540780089342
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019288095788096441943042560024241336320x7fbcd54c23000x7fbbc98368c03039243039243279424314006553627430652722622900109906561212075540780148141120755407803346761207554078052651512075540780551581
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019488095788096441943042560024241353600x7fbcd54c2a000x7fbbc9836900215476215476273531723816655361636015311550915065626914412075540780619647120755407807948341207554078092795312075540780931597
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019688095788096441943042560020241368320x7fbcd54c29000x7fbbc98369404376604376603973935012886553640432830433099360161913427612075540780989825120755407811873121207554078146987012075540781495004
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019888095788096441943042560028241385600x7fbcd54c28000x7fbbc98369804023084023083069932184726553625994834230273240104161843212075540781557480120755407817309891207554078199098812075540782016914
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020088095788096441943042560024241402880x7fbcd54c27000x7fbbc98369c0272548272548161672180392655361670316031533326067000264012075540782076985120755407822530671207554078242330612075540782427076
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020288095788096441943042560024241427840x7fbcd54c26000x7fbbc9836a003308763308763376626470166553629868789124762710119660454412075540782485875120755407826724251207554078288266412075540782907299
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020488095788096441943042560024241447680x7fbcd54c25000x7fbbc9836a40225596225596288941804776655361694880051614362067981840012075540782972921120755407831535421207554078329194212075540783296071
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020688095788096441943042560020241457280x7fbcd54c24000x7fbbc9836a804746764746764181637974166553643854870336076590175601533612075540783355241120755407835409011207554078384873912075540783873785
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020888095788096441943042560028241477120x7fbcd54c23000x7fbbc9836ac03954763954763130331638166553627234443829785990109119721612075540783927204120755407841122581207554078436809712075540784393290
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021088095788096441943042560024241496960x7fbcd54c2a000x7fbbc9836b00220988220988263071767912655361727313061596178069279639612075540784446349120755407846186561207554078475497512075540784758850
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021288095788096441943042560024241521920x7fbcd54c29000x7fbbc9836b403579883579883563228639126553632787384126973680131334985212075540784814683120755407850002471207554078522872612075540785257747
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021488095788096441943042560024241541760x7fbcd54c28000x7fbbc9836b80224676224676268801797416655361759766381624883070578200012075540785318810120755407854964041207554078563528312075540785638424
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021688095788096441943042560020241556480x7fbcd54c27000x7fbbc9836bc05043165043164390940345366553647101893138697130188589564012075540785693687120755407858847221207554078621496112075540786242757
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021888095788096441943042560028241576320x7fbcd54c26000x7fbbc9836c003953643953643500631629206553633519569029848930134260795212075540786293161120755407864652001207554078672087912075540786744850
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022088095788096441943042560024241596160x7fbcd54c25000x7fbbc9836c40225908225908278291807272655361792816781614352071901852012075540786797338120755407869682381207554078710679712075540787110049
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022288095788096441943042560024241623680x7fbcd54c24000x7fbbc9836c803823163823163741030585366553635020570728912410140266958812075540787169349120755407873595961207554078760455512075540787631098
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022488095788096441943042560024241646080x7fbcd54c23000x7fbbc9836cc0221796221796282871774376655361810350191599265072602511212075540787693103120755407878682341207554078800583412075540788009481
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022688095788096441943042560020241663360x7fbcd54c2a000x7fbbc9836d006131086131081657549048726553654136732244311450216728897212075540788069272120755407882573531207554078865943112075540788684255
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022888095788096441943042560028241685760x7fbcd54c29000x7fbbc9836d403992203992203530231937686553631767433430108550127252454412075540788737884120755407889085501207554078916582912075540789191277
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023088095788096441943042560024241708160x7fbcd54c28000x7fbbc9836d80232852232852295431862824655361879214311677655075359260012075540789242622120755407894147881207554078955990812075540789563338
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023288095788096441943042560024241740800x7fbcd54c27000x7fbbc9836dc04356124356124039634849046553640478254833191500162098139612075540789622939120755407898063071207554079008662612075540790114904
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023488095788096441943042560024241765760x7fbcd54c26000x7fbbc9836e00229580229580279191836648655361877528331663296075290837212075540790176518120755407903525451207554079049558412075540790499198
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023688095788096441943042560020241777920x7fbcd54c25000x7fbbc9836e406476926476925380651815446553661360784550092260245624993212075540790555653120755407907416631207554079116758112075540791192917
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023888095788096441943042560028241802880x7fbcd54c24000x7fbbc9836e804023084023083747432184726553632332647230159290129513171612075540791245124120755407914243801207554079168533912075540791709798
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024088095788096441943042560024241827840x7fbcd54c23000x7fbbc9836ec0223764223764260391790120655361817691941605406072895855212075540791767455120755407919440581207554079208229812075540792085696
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024288095788096441943042560024241863040x7fbcd54c2a000x7fbbc9836f004888684888684335239109526553645573296937388990182478912412075540792141790120755407923355771207554079265109612075540792678177
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024488095788096441943042560024241893120x7fbcd54c29000x7fbbc9836f40246052246052279181968424655362146377551780484086045016812075540792743258120755407929165341207554079306837412075540793071999
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024688095788096441943042560020241907840x7fbcd54c28000x7fbbc9836f807844847844845972062758806553674966819461067120300049346412075540793131420120755407933206931207554079383797112075540793863320
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024888095788096441943042560028241937920x7fbcd54c27000x7fbbc9836fc04630044630044122637040406553637222742835038370149077228812075540793917200120755407940930101207554079439476912075540794422790
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025088095788096441943042560024241968000x7fbcd54c26000x7fbbc9837000246100246100272461968808655362189799071806346087781176812075540794472041120755407946424481207554079479684712075540794800411
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025288095788096441943042560024242010880x7fbcd54c25000x7fbbc98370405942765942764975947542166553656113554145791610224639658012075540794857257120755407950522061207554079543780512075540795462903
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025488095788096441943042560024242046080x7fbcd54c24000x7fbbc98370802783562783562965022268566553624984691920619180100127509212075540795527503120755407957021241207554079587860312075540795881951
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025688095788096441943042560020242060800x7fbcd54c23000x7fbbc98370c09254849254846878974038806553688803743072350590355397088012075540795936583120755407961365221207554079674771912075540796794497
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025888095788096441943042560028242096000x7fbcd54c2a000x7fbbc98371005051965051964604040415766553646150945138520030184788150012075540796817540120755407970142781207554079734515712075540797389473
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026088095788096441943042560024242131200x7fbcd54c29000x7fbbc98371402825002825003052222600086553625380739920894960101711286412075540797424578120755407976097961207554079778787512075540797791300
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026288095788096441943042560024242181760x7fbcd54c28000x7fbbc98371807015327015325360056122646553666649512954301700266783684412075540797849789120755407980369941207554079849395312075540798540512
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026488095788096441943042560024242222080x7fbcd54c27000x7fbbc98371c03159643159643396625277206553628476094723438050114092845612075540798587520120755407987670721207554079896675112075540799025774
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026688095788096441943042560020242239360x7fbcd54c26000x7fbbc98372001064324106432475411851460065536102949927183524820411981778812075540799051782120755407992566701207554079996114712075540800028878
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026888095788096441943042560028242279680x7fbcd54c25000x7fbbc98372405666605666604745545332886553653241481543678810213150348012075540800062080120755408002563461207554080062930412075540800694445
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027088095788096441943042560024242320000x7fbcd54c24000x7fbbc98372803181403181403089325451286553629058280123888220116422710012075540800717518120755408009121831207554080111570212075540801184316
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027288095788096441943042560024242378240x7fbcd54c23000x7fbbc98372c08052768052766155964422166553677031947962688440308312003612075540801208000120755408014061011207554080193329912075540801999951
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027488095788096441943042560024242423680x7fbcd54c2a000x7fbbc98373003479883479883281427839126553631947164226258480127977678812075540802039264120755408022243381207554080244785712075540802515329
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027688095788096441943042560020242435840x7fbcd54c29000x7fbbc98373401208124120812486256966500065536116909014294837750467818082812075540802538182120755408027334561207554080353169312075540803599314
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027888095788096441943042560028242481280x7fbcd54c28000x7fbbc98373806391086391085192351128726553660397394049419680241775568012075540803630592120755408038273721207554080424945012075540804318611
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028088095788096441943042560024242526720x7fbcd54c27000x7fbbc98373c03547723547723547128381846553632250868326715710129191773212075540804349328120755408045465691207554080477360812075540804840180
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028288095788096441943042560024242592640x7fbcd54c26000x7fbbc98374009286689286681405274293526553687354652271112570349603664812075540804867360120755408050668871207554080567712412075540805745953
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028488095788096441943042560024242648320x7fbcd54c25000x7fbbc98374404202044202043993633616406553638693611731866240154965507612075540805780427120755408059664031207554080623632212075540806304421
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028688095788096441943042560020242663040x7fbcd54c24000x7fbbc98374801487292148729210110911898344655361447008370117323420578985328812075540806328506120755408065244811207554080751071712075540807579491
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028888095788096441943042560028242718720x7fbcd54c23000x7fbbc98374c08044368044361619064354966553674006857760560020296211818012075540807603846120755408078137561207554080834559412075540808413160
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029088095788096441943042560024242774400x7fbcd54c2a000x7fbbc98375004217404217404014833739286553638798179631966440155381545212075540808436073120755408086433531207554080891455212075540808980975
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029288095788096441943042560012242799360x7fbcd54c29000x7fbbc98375401126596112659679320901277665536109042869988486250436353966012075540809011753120755408092051111207554080994430812075540810018824
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029488095788096441943042560024242865280x7fbcd54c28000x7fbbc98375804913484913484559239307926553645705998837519260183014006812075540810053218120755408102407871207554081055838512075540810625201
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029688095788096441943042560020242880000x7fbcd54c27000x7fbbc98375c0176927617692764734514154216655361724647435139886770690040967212075540810642263120755408108473441207554081202030012075540812089242
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029888095788096441943042560032242945920x7fbcd54c26000x7fbbc98376009198369198366575973586966553681590620371740500326547358412075540812115511120755408123177381207554081292781612075540812995256
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030088095788096441943042560024243011840x7fbcd54c25000x7fbbc98376404919724919724338739357846553645853285937668180183602724012075540813031643120755408132250951207554081354429412075540813614456
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030288095788096441943042560012243049600x7fbcd54c24000x7fbbc9837680133778813377889278610702312655361299360379105303980519926944012075540813643340120755408138385331207554081471772912075540814786635
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030488095788096441943042560024243136000x7fbcd54c23000x7fbbc98376c06305966305965241450447766553659623259148763720238681888412075540814820889120755408150057281207554081541692612075540815484412
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030688095788096441943042560020243148160x7fbcd54c2a000x7fbbc98377002334012233401215192718672104655362284074939184961510913812037212075540815506443120755408157084451207554081725867912075540817327237
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030888095788096441943042560020243175680x7fbcd54c29000x7fbbc98377401206156120615615357964925665536116254984794400560465202253212075540817355679120755408175623581207554081836155512075540818430156
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031088095788096441943042560012243203200x7fbcd54c28000x7fbbc98377806414286414285163751314326553660896149149533400243768075612075540818460423120755408186562741207554081907179212075540819139965
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031288095788096441943042560012243240960x7fbcd54c27000x7fbbc98377c01758292175829211683714066344655361714636859139006440686037395212075540819173377120755408193653911207554082052506612075540820593056
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031488095788096441943042560012243288960x7fbcd54c26000x7fbbc98378001199524119952484981959620065536116063457694254130464436672812075540820637819120755408208183451207554082160394212075540821674065
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031688095788096441943042560020243301120x7fbcd54c25000x7fbbc983784045865724586572283169366925846553645157727113650758801806491214412075540821705594120755408219012211207554082495640912075540825026595
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031888095788096441943042560020243328640x7fbcd54c24000x7fbbc98378802327452232745215085918619624655362276145368184278840910640524812075540825059537120755408252538481207554082679896212075540826867757
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032088095788096441943042560012243356160x7fbcd54c23000x7fbbc98378c01203548120354883988962839265536116595289694557280466563827612075540826895198120755408270996011207554082788967712075540827959175
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032288095788096441943042560012243393920x7fbcd54c2a000x7fbbc983790034450363445036216081275602966553633843018842738292301353903435612075540827995613120755408282005561207554083048198712075540830551032
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032488095788096441943042560012243441920x7fbcd54c29000x7fbbc98379402323388232338815010918587112655362275009742184186850910186200012075540830597519120755408307773461207554083231270012075540832381604
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032688095788096441943042560020243454080x7fbcd54c28000x7fbbc983798090888209088820474446727105686553689775130907253111303591187303212075540832410478120755408326157391207554083867203512075540838743628
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032888095788096441943042560020243481600x7fbcd54c27000x7fbbc98379c045751724575172282963366013846553645035721883642488201801611474812075540838764667120755408389713941207554084201666212075540842086410
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033088095788096441943042560012243509120x7fbcd54c26000x7fbbc9837a00232938023293807953918635048655362280672348184660970912451320412075540842109663120755408423169811207554084385665512075540843924737
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332880957880964419430425600122400x7fbcd54c25000x7fbbc9837a4068158206815820414476545265686553667239468645433087702689761212412075540843951847120755408441602151207554084868723912075540848763800