ファイル
rocm-systems/tests/workloads/invdev/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.kd000937062937067335544322560083264640x00x7f30a560418049967449967416219399740052428837176883438019670150185902812076634246773666120766344922937891207663449261570912076634492722711
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00293706293706732768256002424124800x00x7f30a56351002746727467202142197445121126759753660452100012076634507281913120766345076096741207663450761591412076634507624380
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0049370629370674194304256002424129280x7f31b11919000x7f30a5635140217853217853216331742832655361336710071576099053649869612076634507695903120766345079343141207663450806711312076634508071402
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0069370629370674194304256003624136320x7f31b11918000x7f30a56351803896213896212680431169766553625306081429482710101405836412076634508150749120766345083544731207663450860295212076634508672009
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0089370629370674194304256002824140800x7f31b11917000x7f30a56351c04037724037722643632301846553627610521130522430110623863212076634508705912120766345089120721207663450916855112076634509238653
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00109370629370674194304256002424145280x7f31b11916000x7f30a5635200217957217957191061743664655361335456211580634053599828412076634509266064120766345094738301207663450960727012076634509610645
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00129370629370674194304256002424149760x7f31b11915000x7f30a5635240229069229069199691832560655361210946891662134048618714812076634509672260120766345098696691207663451000998912076634510013484
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00149370629370674194304256002424154240x7f31b11914000x7f30a5635280212108212108186021696872655361561947651531178062659655212076634510103422120766345102885481207663451041846812076634510421754
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00169370629370674194304256002824161280x7f31b11913000x7f30a56352c03954933954933119331639526553635021422829946770140267335212076634510485032120766345106821481207663451093398712076634510974372
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00189370629370674194304256002824168320x7f31b1191a000x7f30a56353004675164675161717337401366553630455443430420450122003266012076634511021389120766345112216661207663451152038612076634511586971
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00209370629370674194304256002424175360x7f31b11919000x7f30a5635340225357225357226061802864655361268844041624746050934712812076634511614202120766345118216651207663451195862512076634511961738
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00229370629370674194304256002424182400x7f31b11918000x7f30a5635380214853214853199431718832655361381560491552593055443938812076634512019917120766345122272641207663451235862412076634512362043
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00249370629370674194304256002424189440x7f31b11917000x7f30a56353c0212085212085217091696688655361626778541518896065253031212076634512440970120766345126215031207663451275030312076634512753651
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00269370629370674194304256002824199040x7f31b11916000x7f30a56354004485894485891490335887206553635242980529801950141153666412076634512815597120766345130079021207663451329430212076634513361963
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00289370629370674194304256002824206080x7f31b11915000x7f30a56354403983653983653040731869286553632239937630154540129141213612076634513388011120766345135968611207663451385062112076634513916414
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00309370629370674194304256002424213120x7f31b11914000x7f30a5635480212733212733214161701872655361522009361534437061062049612076634513941962120766345141543001207663451428422012076634514287725
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00329370629370674194304256002424220160x7f31b11913000x7f30a56354c0212636212636213371701096655361603910481536825064337937612076634514348127120766345145453391207663451467541912076634514678532
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00349370629370674194304256002424227200x7f31b1191a000x7f30a5635500222621222621218731780976655361449583561613854058164586812076634514752189120766345149323781207663451506917812076634515072334
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00369370629370674194304256002824236800x7f31b11919000x7f30a56355403975563975563013631804566553634112102430027530136630144812076634515133218120766345153277371207663451558133712076634515646482
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00389370629370674194304256002824243840x7f31b11918000x7f30a5635580403172403172240873225384655362247074613040116090064800012076634515675667120766345158714161207663451612933612076634516199712
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00409370629370674194304256002424250880x7f31b11917000x7f30a56355c0216284216284240621730280655361269886761563585050977033612076634516228164120766345164261351207663451655829512076634516561545
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00429370629370674194304256002424257920x7f31b11916000x7f30a5635600219124219124228671753000655361368624291589426054926701212076634516622708120766345168131741207663451694805412076634516951169
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00449370629370674194304256002424264960x7f31b11915000x7f30a5635640213709213709223491709680655361575536941533157063203167612076634517030537120766345172114131207663451734149312076634517344561
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00469370629370674194304256002824277120x7f31b11914000x7f30a56356803999813999812823031998566553629221843930250470117069164012076634517402739120766345175949321207663451785093212076634517917136
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00489370629370674194304256002824284160x7f31b11913000x7f30a56356c04054134054132875132433126553629348811030587580117576855612076634517942824120766345181491711207663451840757012076634518473942
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00509370629370674194304256002424291200x7f31b1191a000x7f30a5635700210541210541185601684336655361582314581524200063474412812076634518498998120766345186962101207663451882549012076634518828672
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00529370629370674194304256002424300800x7f31b11919000x7f30a5635740221165221165250931769328655361536721971587171061650194412076634518889094120766345190776491207663451921220912076634519215481
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00549370629370674194304256002424307840x7f31b11918000x7f30a5635780214733214733202441717872655361462700571557059058689532012076634519290751120766345194675681207663451959956812076634519602501
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00569370629370674194304256002824320000x7f31b11917000x7f30a56357c03951483951483116131611926553634891717329877880139748822012076634519664046120766345198565271207663452010980712076634520179775
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00589370629370674194304256002824329600x7f31b11916000x7f30a56358003917173917173069931337446553635235285929707950141122977212076634520210833120766345204053261207663452065620512076634520723025
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00609370629370674194304256002424339200x7f31b11915000x7f30a5635840211165211165223561689328655361591419921519622063839112012076634520747351120766345209464451207663452107540512076634521078877
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00629370629370674194304256002424348800x7f31b11914000x7f30a5635880222669222669223581781360655361407443001613811056481320412076634521142015120766345213219641207663452145972412076634521462892
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00649370629370674194304256002424358400x7f31b11913000x7f30a56358c0210276210276226341682216655361388111941514446055707336012076634521536088120766345217125231207663452184116312076634521844321
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00669370629370674194304256002824373120x7f31b1191a000x7f30a56359004103814103812411932830566553630921318630953220123866566812076634521904974120766345220994021207663452236292212076634522429620
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00689370629370674194304256002824382720x7f31b11919000x7f30a56359403977003977002903631816086553629094682830132110116560019212076634522455268120766345226597211207663452291364012076634522980154
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00709370629370674194304256002424392320x7f31b11918000x7f30a5635980222484222484220181779880655361289903491612365051780186412076634523013546120766345232106001207663452334787912076634523351094
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00729370629370674194304256002424401920x7f31b11917000x7f30a56359c0222764222764242041782120655361463317421615165058716369212076634523411156120766345236016391207663452373891912076634523742191
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00749370629370674194304256002424411520x7f31b11916000x7f30a5635a00212021212021225501696176655361571515241525336063042356012076634523815207120766345239910781207663452412147812076634524125254
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00769370629370674194304256002824426240x7f31b11915000x7f30a5635a404010454010452640232083686553633639014530046540134737674012076634524185225120766345243750771207663452463203712076634524698570
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00789370629370674194304256002824435840x7f31b11914000x7f30a5635a804019004019002639032152086553629568794330494720118456805212076634524722816120766345249184361207663452517619512076634525244576
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00809370629370674194304256002424445440x7f31b11913000x7f30a5635ac0211773211773253021694192655361506061011519106060427430412076634525273139120766345254678751207663452559715412076634525600558
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00829370629370674194304256002424457600x7f31b1191a000x7f30a5635b00220996220996256711767976655361555399141586010062398073212076634525660279120766345258528341207663452598803412076634525991365
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00849370629370674194304256002424467200x7f31b11919000x7f30a5635b40218309218309231551746480655361531864531572643061457788812076634526065333120766345262430731207663452637667312076634526380178
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00869370629370674194304256002824484480x7f31b11918000x7f30a5635b804136524136523335233092246553628876758831352200115688712812076634526440901120766345266256321207663452689219212076634526958564
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00889370629370674194304256002824494080x7f31b11917000x7f30a5635bc03983163983163363831865366553634078211230132660136494287212076634526986887120766345271872311207663452744195012076634527482839
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00909370629370674194304256002424503680x7f31b11916000x7f30a5635c00205276205276211191642216655361714036071481515068743885612076634527516492120766345277150701207663452784114912076634527844392
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00929370629370674194304256002424515840x7f31b11915000x7f30a5635c40220756220756264191766056655361598271761589517064114450412076634527905185120766345281203491207663452825634912076634528259995
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00949370629370674194304256002424525440x7f31b11914000x7f30a5635c80214117214117220631712944655361485789421546808059613377612076634528333842120766345285147481207663452864626812076634528649429
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00969370629370674194304256002824542720x7f31b11913000x7f30a5635cc04140364140363247733122966553632693911131264240130957322012076634528709702120766345289040271207663452917058712076634529238565
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00989370629370674194304256002824554880x7f31b1191a000x7f30a5635d003897333897333105931178726553634172960929539170136873625212076634529266878120766345294630661207663452971378512076634529779682
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001009370629370674194304256002424567040x7f31b11919000x7f30a5635d40219156219156227791753256655361517488261574610060882262012076634529804548120766345300000251207663453013426412076634530137818
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001029370629370674194304256002424581760x7f31b11918000x7f30a5635d80223341223341268081786736655361598496441611787064124694412076634530199333120766345303873841207663453052562412076634530529216
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001049370629370674194304256002424593920x7f31b11917000x7f30a5635dc0214917214917254431719344655361623467521524728065120845612076634530601581120766345307782631207663453090802312076634530911397
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001069370629370674194304256002824613760x7f31b11916000x7f30a5635e004084844084843125832678806553632032965730923660128313982412076634530971860120766345311651421207663453142882212076634531469916
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001089370629370674194304256002824625920x7f31b11915000x7f30a5635e403927563927563302731420566553633452119329724560133990158012076634531509049120766345316872211207663453193970012076634532015320
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001109370629370674194304256002424638080x7f31b11914000x7f30a5635e80279308279308146002234472655361442216951546141057870816812076634532041669120766345322502601207663453242497912076634532428349
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001129370629370674194304256002424652800x7f31b11913000x7f30a5635ec0226748226748294571813992655361780933561602668071423571212076634532488801120766345326763391207663453281425812076634532817633
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001149370629370674194304256002424664960x7f31b1191a000x7f30a5635f00212613212613243691700912655361610560551531647064606534812076634532892883120766345330763381207663453320705812076634533210664
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001169370629370674194304256002824684800x7f31b11919000x7f30a5635f404123094123093285832984806553633431393731223890133910721212076634533272058120766345334609771207663453372641612076634533793017
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001189370629370674194304256002824696960x7f31b11918000x7f30a5635f803983713983713251031869766553634021948730158340136269233612076634533821500120766345340150561207663453427137512076634534338342
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001209370629370674194304256002424709120x7f31b11917000x7f30a5635fc0228188228188267411825512655361492099861647545059870701612076634534364611120766345345628951207663453470289412076634534706386
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001229370629370674194304256002424723840x7f31b11916000x7f30a5636000225708225708279961805672655361772509031624430071084352412076634534768331120766345349564941207663453509681312076634535100429
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001249370629370674194304256002424736000x7f31b11915000x7f30a5636040211220211220224751689768655361602540321514284064285477612076634535174577120766345353539331207663453548321312076634535486688
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001269370629370674194304256002824758400x7f31b11914000x7f30a56360804127894127893405433023206553629673332331211280118876622012076634535547371120766345357328121207663453599953112076634536067077
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001289370629370674194304256002824770560x7f31b11913000x7f30a56360c0398948398948266923191592655362494302623001335099953922812076634536092825120766345362950511207663453655185012076634536615818
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001309370629370674194304256002424782720x7f31b1191a000x7f30a5636100219732219732218101757864655361467294881589753058878234412076634536640754120766345368376101207663453697312912076634536976529
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001329370629370674194304256002424800000x7f31b11919000x7f30a5636140231853231853269091854832655361969777401689369078978175612076634537038584120766345372264091207663453737024812076634537373768
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001349370629370674194304256002424812160x7f31b11918000x7f30a5636180217245217245223661737968655361498488991578330060123593612076634537446193120766345376216081207663453775584712076634537759095
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001369370629370674194304256002824834560x7f31b11917000x7f30a56361c04127894127893382333023206553632837887731367240131533196812076634537819016120766345380110471207663453827824612076634538344273
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001389370629370674194304256002824849280x7f31b11916000x7f30a56362004432284432281422435458326553635213463729579120141036188412076634538370261120766345385702461207663453885728512076634538923270
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001409370629370674194304256002424864000x7f31b11915000x7f30a5636240222836222836246411782696655361457100361601147058470756412076634538947946120766345391512041207663453928768412076634539291164
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001429370629370674194304256002424881280x7f31b11914000x7f30a5636280239925239925259881919408655362085097621760336083590966812076634539352438120766345395393641207663453968944312076634539692852
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001449370629370674194304256002424896000x7f31b11913000x7f30a56362c0222461222461244851779696655361487995511614425059703721612076634539780374120766345399568031207663454009376212076634540097414
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001469370629370674194304256002824920960x7f31b1191a000x7f30a56363004138604138603281633108886553634207920331461670137018758812076634540157266120766345403448021207663454061344112076634540679657
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001489370629370674194304256002824935680x7f31b11919000x7f30a56363404005084005083036432040726553632560123630337290130422361212076634540707349120766345409009601207663454115904012076634541228759
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001509370629370674194304256002424950400x7f31b11918000x7f30a5636380215420215420228101723368655361525859671559429061221269212076634541255168120766345414569591207663454159007912076634541593427
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001529370629370674194304256002424967680x7f31b11917000x7f30a56363c0255541255541306102044336655362222868161859187089099150412076634541652958120766345418399981207663454199839812076634542006746
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001549370629370674194304256002424982400x7f31b11916000x7f30a5636400216668216668220701733352655361557410101570265062484151212076634542076425120766345422540771207663454238815712076634542391301
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015693706293706741943042560028241007360x7f31b11915000x7f30a56364404176284176283407433410326553633321675831180390133468300812076634542450792120766345426403171207663454291071612076634542957294
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015893706293706741943042560028241022080x7f31b11914000x7f30a56364803973243973243082431786006553633712877130185030135033445612076634542981539120766345431865551207663454344335512076634543488522
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016093706293706741943042560024241036800x7f31b11913000x7f30a56364c0225229225229242901801840655361424486071626904057163782812076634543530180120766345437049541207663454384399412076634543847129
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016293706293706741943042560024241056640x7f31b1191a000x7f30a5636500262797262797280812102384655362338302711940837093717059212076634543909976120766345441161531207663454428159312076634544284773
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016493706293706741943042560024241071360x7f31b11919000x7f30a5636540221141221141244161769136655361445137111597678057989661212076634544358721120766345445377521207663454467375212076634544677273
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016693706293706741943042560028241098880x7f31b11918000x7f30a56365804084854084853644832678886553632400580030771030129786970812076634544736423120766345449318321207663454519647112076634545265778
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016893706293706741943042560028241113600x7f31b11917000x7f30a56365c03980843980843808531846806553633587048829892720134529608412076634545291696120766345454871901207663454574175012076634545808177
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017093706293706741943042560024241128320x7f31b11916000x7f30a5636600225389225389233661803120655361432014391633713057466890412076634545835267120766345460340691207663454617422912076634546177504
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017293706293706741943042560024241148160x7f31b11915000x7f30a5636640274788274788300152198312655362458349072034390098520514012076634546240341120766345464263881207663454659934812076634546602735
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017493706293706741943042560024241162880x7f31b11914000x7f30a5636680212845212845217681702768655361549908141519836062181482412076634546674859120766345468510271207663454698238712076634546985697
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017693706293706741943042560028241190400x7f31b11913000x7f30a56366c04069244069243647832554006553631562073730561850126431473612076634547046330120766345472395061207663454750238612076634547567880
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017893706293706741943042560028241207680x7f31b1191a000x7f30a56367003956053956053208831648486553631810419729842560127423581212076634547596163120766345477883051207663454804430512076634548112944
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018093706293706741943042560024241224960x7f31b11919000x7f30a5636740228092228092253361824744655361436309601655089057638105612076634548138692120766345483393441207663454848030412076634548483744
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018293706293706741943042560024241247360x7f31b11918000x7f30a56367802887652887652996423101286553625992581521491410104155952412076634548543705120766345487281431207663454891166312076634548915016
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018493706293706741943042560024241264640x7f31b11917000x7f30a56367c0226421226421253981811376655361450203141625891058198122012076634549021955120766345492038221207663454934334212076634549347000
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018693706293706741943042560020241279360x7f31b11916000x7f30a56368004118854118853692332950886553637737946431183430151133839612076634549406931120766345495942211207663454986142112076634549902813
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018893706293706741943042560028241296640x7f31b11915000x7f30a56368404007724007722901932061846553627066136630121490108446686412076634549939552120766345501313401207663455039005912076634550456674
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019093706293706741943042560024241313920x7f31b11914000x7f30a5636880223493223493286411787952655361567473371596842062884176012076634550483403120766345506810991207663455081821812076634550821683
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019293706293706741943042560024241336320x7f31b11913000x7f30a56368c03007483007483143224059926553627250064022484580109184998412076634550885241120766345510737381207663455126445712076634551332072
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019493706293706741943042560024241353600x7f31b1191a000x7f30a5636900221837221837248411774704655361546542681601667062048281212076634551376685120766345515543771207663455169149712076634551694897
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019693706293706741943042560020241368320x7f31b11919000x7f30a56369404368934368933978434951526553640228502233248290161096077612076634551755520120766345519414161207663455222509512076634552292028
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019893706293706741943042560028241385600x7f31b11918000x7f30a56369804004294004293358432034406553632996024330084730132168334412076634552320531120766345525156551207663455277309412076634552839366
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020093706293706741943042560024241402880x7f31b11917000x7f30a56369c0220708220708274691765672655361514318051583632060756016012076634552864162120766345530761331207663455321245312076634553215966
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020293706293706741943042560024241427840x7f31b11916000x7f30a5636a003303083303083288326424726553630045778724798190120368914812076634553276469120766345534674931207663455367805212076634553744239
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020493706293706741943042560024241447680x7f31b11915000x7f30a5636a40223524223524235561788200655361577769741611436063299745212076634553780316120766345539642911207663455410253112076634554106102
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020693706293706741943042560020241457280x7f31b11914000x7f30a5636a804701734701734040837613926553643790168835952510175342699612076634554166254120766345543545311207663455466173012076634554727688
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020893706293706741943042560028241477120x7f31b11913000x7f30a5636ac04052454052453416132419686553633514071430632590134238942812076634554754929120766345549511691207663455521324912076634555279745
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021093706293706741943042560024241496960x7f31b1191a000x7f30a5636b00225836225836221821806696655361540060341634745061789890812076634555304291120766345555034661207663455564394612076634555651266
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021293706293706741943042560024241521920x7f31b11919000x7f30a5636b403566533566533578128532326553632538972226833650130341536412076634555706769120766345558937041207663455612122312076634556189638
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021493706293706741943042560024241541760x7f31b11918000x7f30a5636b80218700218700257141749608655361540469071576350061806322412076634556229913120766345564093831207663455654490212076634556548375
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021693706293706741943042560020241556480x7f31b11917000x7f30a5636bc05037975037974395840303846553647189430038657470188939783212076634556611292120766345568012221207663455713082112076634557200308
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021893706293706741943042560028241576320x7f31b11916000x7f30a5636c004073404073402864032587286553631270280330523680125262911612076634557226436120766345574244211207663455768842012076634557729282
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022093706293706741943042560024241596160x7f31b11915000x7f30a5636c40226132226132258771809064655361530785981635564061418549212076634557772462120766345579503391207663455809017912076634558093649
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022293706293706741943042560024241623680x7f31b11914000x7f30a5636c803819243819243644930554006553634984437328879480140122525212076634558156556120766345583407381207663455858617812076634558653100
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022493706293706741943042560024241646080x7f31b11913000x7f30a5636cc0225636225636284521805096655361630048181620463065390186412076634558689598120766345588682571207663455900857712076634559012278
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022693706293706741943042560020241663360x7f31b1191a000x7f30a5636d005750535750534690946004326553654230478344446230217103753212076634559063984120766345592602561207663455963833612076634559704396
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022893706293706741943042560028241685760x7f31b11919000x7f30a5636d404075804075803372332606486553630054076330694340120399874012076634559729943120766345599314551207663456019593412076634560262333
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023093706293706741943042560024241708160x7f31b11918000x7f30a5636d80221692221692258541773544655361618176871597624064914934812076634560287300120766345604864941207663456062457312076634560628034
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023293706293706741943042560024241740800x7f31b11917000x7f30a5636dc04796524796521606838372246553640091945132970560160552867612076634560680361120766345608724131207663456118265212076634561253146
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023493706293706741943042560024241765760x7f31b11916000x7f30a5636e00226229226229276041809840655361718302921631065068921954412076634561291798120766345614821711207663456162201112076634561625890
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023693706293706741943042560020241777920x7f31b11915000x7f30a5636e406423086423084998651384726553661010950849829080244225902412076634561686523120766345618730501207663456229737012076634562320632
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023893706293706741943042560028241802880x7f31b11914000x7f30a5636e804050854050853814932406886553631617161130099710126652997612076634562375825120766345625552891207663456281640812076634562837233
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024093706293706741943042560024241827840x7f31b11913000x7f30a5636ec0224084224084254721792680655361814192191619155072755437212076634562893057120766345630757681207663456321544712076634563219103
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024293706293706741943042560024241863040x7f31b1191a000x7f30a5636f004865884865884286238927126553645489808137285150182145001612076634563280988120766345634808871207663456379592612076634563817416
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024493706293706741943042560024241893120x7f31b11919000x7f30a5636f40242541242541264661940336655362133328541779150085522818012076634563892296120766345640770461207663456422920512076634564232879
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024693706293706741943042560020241907840x7f31b11918000x7f30a5636f807841087841086001562728726553675033800561059560300317300412076634564285056120766345644882451207663456500552312076634565048666
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024893706293706741943042560028241937920x7f31b11917000x7f30a5636fc04623254623254138136986086553639524021235274630158280260412076634565094482120766345652746431207663456557720212076634565643924
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025093706293706741943042560024241968000x7f31b11916000x7f30a5637000246109246109277841968880655362171681091806572087055389212076634565678829120766345658652021207663456601976112076634566023700
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025293706293706741943042560024242010880x7f31b11915000x7f30a56370405929335929334802147434726553656006396345829440224211292812076634566085235120766345662698411207663456665624012076634566723241
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025493706293706741943042560024242046080x7f31b11914000x7f30a5637080280285280285322852242288655362492082302057641099871999212076634566764228120766345669426391207663456711815912076634567121853
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025693706293706741943042560020242060800x7f31b11913000x7f30a56370c09417569417561410175340566553689043297472314620356355318412076634567184139120766345673818381207663456800615712076634568057143
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025893706293706741943042560028242096000x7f31b1191a000x7f30a56371005076605076604304040612886553646130560238903390184706766812076634568083071120766345682797561207663456861143512076634568675082
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026093706293706741943042560024242131200x7f31b11919000x7f30a56371402804052804052859622432486553625333645020873460101523306412076634568699477120766345688941551207663456907287412076634569076559
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026293706293706741943042560024242181760x7f31b11918000x7f30a56371806975976975975453755807846553666419141154176580265861890012076634569137282120766345693247141207663456978071312076634569820142
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026493706293706741943042560024242222080x7f31b11917000x7f30a56371c03119083119083011624952726553628487894423438780114140200012076634569871588120766345700555921207663457025559212076634570322897
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026693706293706741943042560020242239360x7f31b11916000x7f30a56372001074565107456515319859652865536102682508983618060410912120012076634570348595120766345705434311207663457125462912076634571321024
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026893706293706741943042560028242279680x7f31b11915000x7f30a56372405696535696534802145572326553653037193443838640212332856012076634571346331120766345715498291207663457192390812076634571989848
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027093706293706741943042560024242320000x7f31b11914000x7f30a56372803172453172453103625379686553628932664123815240115920480812076634572019904120766345722279071207663457243190712076634572500057
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027293706293706741943042560024242378240x7f31b11913000x7f30a56372c08022138022136027264177126553676804003462535770307401550412076634572524202120766345727195861207663457324550512076634573312158
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027493706293706741943042560024242423680x7f31b1191a000x7f30a56373003477973477973262727823846553631878964226239360127704925212076634573353665120766345735296641207663457375318412076634573818800
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027693706293706741943042560020242435840x7f31b11919000x7f30a56373401208453120845386374966763265536116833236694884160467515049612076634573846241120766345740539831207663457485382112076634574922784
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027893706293706741943042560028242481280x7f31b11918000x7f30a56373806387966387965086251103766553660405432049523000241806022812076634574954663120766345751597411207663457558230012076634575648644
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028093706293706741943042560024242526720x7f31b11917000x7f30a56373c03535803535803394828286486553632411246426659530129834042012076634575673781120766345758701391207663457609717812076634576165074
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028293706293706741943042560024242592640x7f31b11916000x7f30a56374009079729079726666872637846553687180820471001720348908258012076634576192956120766345763926981207663457698917612076634577055932
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028493706293706741943042560024242648320x7f31b11915000x7f30a56374404200294200293958033602406553638660737831707860154833381212076634577092850120766345772795761207663457754901512076634577615372
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028693706293706741943042560020242663040x7f31b11914000x7f30a5637480148618814861889924011889512655361446440968117359670578758552412076634577639457120766345778358951207663457882229212076634578892327
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028893706293706741943042560028242718720x7f31b11913000x7f30a56374c07794697794696201862357606553674119097960506950296660036412076634578918406120766345791192521207663457963493112076634579684581
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029093706293706741943042560024242774400x7f31b1191a000x7f30a56375004214524214523844433716246553639003324232110480156201904812076634579709507120766345799048501207663458017764912076634580247919
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029293706293706741943042560012242799360x7f31b11919000x7f30a56375401125589112558979521900472065536108854176688429820435599202412076634580276031120766345804736491207663458121284712076634581268868
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029493706293706741943042560024242865280x7f31b11918000x7f30a56375804871974871974251638975846553645490274837362890182150367612076634581309874120766345814890061207663458180532612076634581854848
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029693706293706741943042560020242880000x7f31b11917000x7f30a56375c01768453176845311791714147632655361724990770139791840690178392812076634581883371120766345820928451207663458326708212076634583563887
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029893706293706741943042560032242945920x7f31b11916000x7f30a56376009186929186926476873495446553680767593571727180323255755212076634583598371120766345837987211207663458441040012076634584459012
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030093706293706741943042560024243011840x7f31b11915000x7f30a56376404951884951884486139615126553646256539137917430185217255212076634584494178120766345846795191207663458500079812076634585094735
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030293706293706741943042560012243049600x7f31b11914000x7f30a5637680133632413363249120010690600655361298621629105268060519631335212076634585122847120766345853295981207663458620831612076634586259401
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030493706293706741943042560024243136000x7f31b11913000x7f30a56376c06303806303805386950430486553659058119548638190236422492812076634586306950120766345864887951207663458689935412076634586946790
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030693706293706741943042560020243148160x7f31b1191a000x7f30a56377002331940233194014960118655528655362284557933184957180914005338812076634586979761120766345871903941207663458874095012076634588791461
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030893706293706741943042560020243175680x7f31b11919000x7f30a56377401199868119986885074959895265536116149824694333580464781361212076634588825635120766345890302291207663458982654812076634589875217
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031093706293706741943042560012243203200x7f31b11918000x7f30a56377806391246391245005151130006553660808429549522970243417187212076634589900133120766345901052671207663459052030612076634590569148
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031293706293706741943042560012243240960x7f31b11917000x7f30a56377c01757892175789211715814063144655361714873517138965550686131916812076634590598723120766345907907051207663459195006312076634592004989
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031493706293706741943042560012243288960x7f31b11916000x7f30a56378001197780119778082504958224865536116223171294202470465075294812076634592045584120766345922263821207663459301278012076634593059921
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031693706293706741943042560020243301120x7f31b11915000x7f30a563784045838124583812211273366705046553645154946363650439701806379983212076634593107028120766345932823801207663459633789312076634596388553
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031893706293706741943042560020243328640x7f31b11914000x7f30a56378802324436232443615149318595496655362275127854184212630910233300012076634596420652120766345966177321207663459816412912076634598235348
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032093706293706741943042560012243356160x7f31b11913000x7f30a56378c01201508120150882495961207265536116412249494540920465831394812076634598267928120766345984626881207663459925324612076634599321308
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032293706293706741943042560012243393920x7f31b1191a000x7f30a563790034432683443268214620275461526553633853573092738142001354325948812076634599342307120766345995582061207663460184108112076634601909913
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032493706293706741943042560012243441920x7f31b11919000x7f30a56379402323188232318814919718585512655362274824901184134180910112885212076634601955628120766346021462001207663460368155612076634603750837
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032693706293706741943042560020243454080x7f31b11918000x7f30a563798090855969085596472686726847766553689765609457252382603590806446012076634603782336120766346039823561207663461004250212076634610114464
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032893706293706741943042560020243481600x7f31b11917000x7f30a56379c045725724572572211846365805846553645025710043641622401801210872012076634610150401120766346103500211207663461339753512076634613464596
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033093706293706741943042560012243509120x7f31b11916000x7f30a5637a002327092232709214986418616744655362280060719184551170912206776412076634613497297120766346136949741207663461523481012076634615302405
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332937062937067419430425600122400x7f31b11915000x7f30a5637a4068118286811828339834544946326553667229269385433448802689353582412076634615338832120766346155336671207663462006309812076634620137478