Files
rocm-systems/tests/workloads/SQ/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.kd000852909852914335544322560083264640x00x7fae9280418050372750372716747402982452428836700242238243020148280793212074903397207541120749036460842671207490364640778512074903646560960
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00285290985291432768256002424124800x00x7fae928351002744127441203062195365121140556764550457646012074903661224461120749036615840671207490366159046712074903661596843
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0048529098529144194304256002424129280x7fafc28029000x7fae92835140219572219572207801756584655361291302191589265051833925612074903661670540120749036619997451207490366213414412074903662139852
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0068529098529144194304256003624136320x7fafc28028000x7fae928351803917883917883304831343126553626712529329650540107031927212074903662217136120749036625019821207490366275126112074903662822230
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0088529098529144194304256002824140800x7fafc28027000x7fae928351c04084044084042858632672406553626930232830855990107902552412074903662853528120749036631669391207490366342677712074903663495872
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00108529098529144194304256002424145280x7fafc28026000x7fae92835200218828218828225551750632655361334102441582077053545709212074903663527711120749036638238951207490366395765512074903663962339
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00128529098529144194304256002424149760x7fafc28025000x7fae92835240221268221268195871770152655361340437261603190053799169212074903664033531120749036643157331207490366445157212074903664456247
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00148529098529144194304256002424154240x7fafc28024000x7fae92835280224820224820224661798568655361350752841632441054211458012074903664541375120749036648046901207490366494245012074903664947309
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00168529098529144194304256002824161280x7fafc28023000x7fae928352c03985483985482904531883926553632157039430135300128810030412074903665016698120749036653162081207490366557012612074903665614229
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00188529098529144194304256002824168320x7fafc2802a000x7fae928353003995003995003271731960086553633403503730189430133795616012074903665641629120749036659382841207490366619252312074903666234351
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00208529098529144194304256002424175360x7fafc28029000x7fae92835340215228215228186961721832655361529558491554599061363938812074903666279966120749036665552411207490366668708112074903666691901
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00228529098529144194304256002424182400x7fafc28028000x7fae92835380217732217732228261741864655361429627201564799057366574012074903666754237120749036670461191207490366717907812074903667183855
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00248529098529144194304256002424189440x7fafc28027000x7fae928353c0212852212852218721702824655361557809381532668062493949212074903667257913120749036675384361207490366766851612074903667673465
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00268529098529144194304256002824199040x7fafc28026000x7fae928354003937163937163340531497366553634629100929814360138698216812074903667735601120749036680289941207490366828019212074903668348840
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00288529098529144194304256002824206080x7fafc28025000x7fae928354403982443982443171231859606553635757230130221020143210722012074903668381982120749036686776301207490366893170912074903669007775
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00308529098529144194304256002424213120x7fafc28024000x7fae92835480220660220660233221765288655361381640231596059055447319212074903669038953120749036693417871207490366947714612074903669481936
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00328529098529144194304256002424220160x7fafc28023000x7fae928354c0223628223628216351789032655361427247041625333057271466012074903669535015120749036698243451207490366996178412074903669966837
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00348529098529144194304256002424227200x7fafc2802a000x7fae92835500214556214556226591716456655361437423921549413057679113212074903670049070120749036703227421207490367045378112074903670458741
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00368529098529144194304256002824236800x7fafc28029000x7fae928355404052044052042574932416406553627825826630698120111485209612074903670518232120749036708072201207490367106673812074903671108599
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00388529098529144194304256002824243840x7fafc28028000x7fae928355803915643915643178531325206553635682591329701940142912132812074903671156137120749036714396961207490367168993512074903671758697
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00408529098529144194304256002424250880x7fafc28027000x7fae928355c0216876216876189021735016655361502648601553086060288281212074903671789565120749036720926531207490367222545212074903672230394
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00428529098529144194304256002424257920x7fafc28026000x7fae92835600217892217892199741743144655361557890371566148062497228812074903672291117120749036725758511207490367270977012074903672714724
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00448529098529144194304256002424264960x7fafc28025000x7fae92835640216044216044233841728360655361517943121561087060899550812074903672783902120749036730827281207490367321504712074903673219843
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00468529098529144194304256002824277120x7fafc28024000x7fae928356803898523898523133431188246553634760199429582100139222488412074903673282289120749036735624051207490367381248412074903673881682
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00488529098529144194304256002824284160x7fafc28023000x7fae928356c03937403937403185331499286553635650601629882260142784074412074903673910506120749036742147221207490367446640112074903674535698
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00508529098529144194304256002424291200x7fafc2802a000x7fae92835700211804211804235941694440655361589379241530970063757070812074903674565854120749036748691191207490367499839812074903675010881
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00528529098529144194304256002424300800x7fafc28029000x7fae92835740208932208932236241671464655361660882771505388066617397612074903675068919120749036753571161207490367548543612074903675490482
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00548529098529144194304256002424307840x7fafc28028000x7fae92835780217220217220204781737768655361540113071561946061786360812074903675559911120749036758286341207490367596191312074903675966817
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00568529098529144194304256002824320000x7fafc28027000x7fae928357c04042284042283142632338326553628643173930671030114754251212074903676034724120749036763182311207490367657711012074903676619911
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00588529098529144194304256002824329600x7fafc28026000x7fae928358004091644091642746232733206553628311936830777660113429578412074903676654295120749036769503881207490367721006712074903677279106
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00608529098529144194304256002424339200x7fafc28025000x7fae92835840216740216740252071733928655361450305911568491058195020012074903677309593120749036775961451207490367772910412074903677734092
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00628529098529144194304256002424348800x7fafc28024000x7fae92835880217228217228230081737832655361468860531565419058939677612074903677797049120749036780836621207490367821710212074903678222359
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00648529098529144194304256002424358400x7fafc28023000x7fae928358c0210596210596222101684776655361549179771522991062149132812074903678292069120749036785692601207490367869805912074903678703072
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00668529098529144194304256002824373120x7fafc2802a000x7fae928359003982363982363291631858966553635152903430154630140793458412074903678764557120749036790596571207490367931501612074903679384799
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00688529098529144194304256002824382720x7fafc28029000x7fae928359403966523966522652631732246553628648566729917530114775990012074903679415767120749036797382141207490367999181312074903680062048
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00708529098529144194304256002424392320x7fafc28028000x7fae92835980219908219908232051759272655361443109931592503057907846012074903680089569120749036803828511207490368051773012074903680522654
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00728529098529144194304256002424401920x7fafc28027000x7fae928359c0223300223300207361786408655361452254541599898058272561612074903680582956120749036808724481207490368101020712074903681015199
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00748529098529144194304256002424411520x7fafc28026000x7fae92835a00219444219444219161755560655361416150081595298056828038812074903681085660120749036813630061207490368149820512074903681502996
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00768529098529144194304256002824426240x7fafc28025000x7fae92835a403967483967482715631739926553628324938329895390113481624812074903681563578120749036818450831207490368209980212074903682168913
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00788529098529144194304256002824435840x7fafc28024000x7fae92835a804027724027723355032221846553631548305630490330126374851612074903682198438120749036824932401207490368275083812074903682820564
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00808529098529144194304256002424445440x7fafc28023000x7fae92835ac0214644214644221681717160655361482872471557692059497089612074903682849207120749036831569161207490368328923612074903683294064
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00828529098529144194304256002424457600x7fafc2802a000x7fae92835b00227812227812239051822504655361506932621639538060459634412074903683356801120749036836444341207490368378555312074903683790517
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00848529098529144194304256002424467200x7fafc28029000x7fae92835b40212228212228230171697832655361540755821531205061816525212074903683859064120749036841458711207490368427611112074903684281189
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00868529098529144194304256002824484480x7fafc28028000x7fae92835b804153964153963566433231766553632495016031485730130161362812074903684341200120749036846197891207490368488746812074903684929373
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00888529098529144194304256002824494080x7fafc28027000x7fae92835bc04026364026363032232210966553633530690630566780134304243212074903684974707120749036852620261207490368552042412074903685590101
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00908529098529144194304256002424503680x7fafc28026000x7fae92835c00208820208820227291670568655361613134281505774064707854812074903685620057120749036859167421207490368604490212074903686049865
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00928529098529144194304256002424515840x7fafc28025000x7fae92835c40216660216660272641733288655361500295951559990060195051212074903686111931120749036863940201207490368652761912074903686532723
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00948529098529144194304256002424525440x7fafc28024000x7fae92835c80217580217580219051740648655361454832771572775058375198012074903686603063120749036868760971207490368701001712074903687015109
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00968529098529144194304256002824542720x7fafc28023000x7fae92835cc04157164157163152633257366553630515050131344660122242449612074903687075682120749036873634551207490368763065412074903687700773
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00988529098529144194304256002824554880x7fafc2802a000x7fae92835d003977163977163259131817366553635027991530169900140293643212074903687735818120749036880290521207490368828425012074903688354628
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001008529098529144194304256002424567040x7fafc28029000x7fae92835d40216748216748234071733992655361459506641563749058562345612074903688384133120749036886848881207490368881816712074903688823239
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001028529098529144194304256002424581760x7fafc28028000x7fae92835d80225452225452277291803624655361587525271625289063684265612074903688884473120749036891748061207490368931448512074903689319532
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001048529098529144194304256002424593920x7fafc28027000x7fae92835dc0208452208452232271667624655361573279271498497063114869612074903689389221120749036896557631207490368978392312074903689788994
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001068529098529144194304256002824613760x7fafc28026000x7fae92835e004022604022603150532180886553632674867230367840130882110012074903689849877120749036901412011207490369040055912074903690470230
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001088529098529144194304256002824625920x7fafc28025000x7fae92835e403862603862603213830900886553634803042429203750139393864012074903690499344120749036907957571207490369104391612074903691113445
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001108529098529144194304256002424638080x7fafc28024000x7fae92835e80211276211276252331690216655361566727981517546062856087212074903691144603120749036914359141207490369156567312074903691570605
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001128529098529144194304256002424652800x7fafc28023000x7fae92835ec0228420228420296611827368655361690657071628402067809839212074903691635696120749036919168721207490369205703112074903692062008
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001148529098529144194304256002424664960x7fafc2802a000x7fae92835f00218540218540192251748328655361595502441576010064004321212074903692134353120749036924023091207490369253718812074903692542190
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001168529098529144194304256002824684800x7fafc28029000x7fae92835f404121564121563410832972566553634631084131295690138707174412074903692599958120749036928859871207490369315206512074903693194463
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001188529098529144194304256002824696960x7fafc28028000x7fae92835f804044284044283016432354326553630805661730594380123404451612074903693237753120749036935178231207490369377750212074903693846324
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001208529098529144194304256002424709120x7fafc28027000x7fae92835fc0222980222980263431783848655361502009241607195060267008812074903693876891120749036941802201207490369431717912074903694322279
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001228529098529144194304256002424723840x7fafc28026000x7fae92836000225396225396275861803176655361876843961629280075258808012074903694384775120749036946774981207490369481749712074903694822478
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001248529098529144194304256002424736000x7fafc28025000x7fae92836040221548221548249701772392655361495177781603989059989725612074903694892278120749036951787751207490369531509412074903695320494
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001268529098529144194304256002824758400x7fafc28024000x7fae928360804111004111003451232888086553630613089531177540122634634412074903695378952120749036956682121207490369593365112074903696009123
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001288529098529144194304256002824770560x7fafc28023000x7fae928360c03893803893803279531150486553635458006529511680142013822812074903696043036120749036963339691207490369658468812074903696654132
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001308529098529144194304256002424782720x7fafc2802a000x7fae92836100209660209660235891677288655361620593911512897065008702012074903696683937120749036969698061207490369709876512074903697103828
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001328529098529144194304256002424800000x7fafc28029000x7fae92836140231124231124267361849000655361996996821686496080067591612074903697167045120749036974472431207490369759140312074903697596443
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001348529098529144194304256002424812160x7fafc28028000x7fae92836180222324222324226271778600655361476036681614720059224467212074903697665592120749036979371611207490369807428012074903698079491
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001368529098529144194304256002824834560x7fafc28027000x7fae928361c04216364216363299733730966553630819407931896400123461379212074903698138681120749036984270781207490369869939712074903698768752
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001388529098529144194304256002824849280x7fafc28026000x7fae928362004005324005323098032042646553631164891230380540124841076012074903698799549120749036990992351207490369935651412074903699425472
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001408529098529144194304256002424864000x7fafc28025000x7fae92836240220796220796257601766376655361537247971599224061676572412074903699455869120749036997496321207490369988563112074903699890767
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001428529098529144194304256002424881280x7fafc28024000x7fae92836280243940243940283971951528655362042260931776433081877862412074903699954375120749037002429091207490370039490812074903700399973
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001448529098529144194304256002424896000x7fafc28023000x7fae928362c0221020221020258261768168655361528486451597374061325176812074903700497224120749037007321871207490370086850612074903700874014
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001468529098529144194304256002824920960x7fafc2802a000x7fae928363004104204104203628332833686553630606367830922790122609135212074903700933585120749037012190641207490370148434312074903701554008
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001488529098529144194304256002824935680x7fafc28029000x7fae928363404630364630361554737042966553630873160630752180123674371612074903701585476120749037018742611207490370217361912074903702243509
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001508529098529144194304256002424950400x7fafc28028000x7fae92836380221452221452237721771624655361525934701600120061222679612074903702273124120749037025715371207490370270785612074903702712951
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001528529098529144194304256002424967680x7fafc28027000x7fae928363c0252204252204284382017640655362183336311851706087518046012074903702773364120749037030641751207490370322225412074903703227377
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001548529098529144194304256002424982400x7fafc28026000x7fae92836400212444212444240031699560655361542795571527719061895025212074903703300353120749037035731321207490370370401112074903703709103
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015685290985291441943042560028241007360x7fafc28025000x7fae928364404218844218843693733750806553634430056131658590137902180812074903703769495120749037040672101207490370433856812074903704408382
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015885290985291441943042560028241022080x7fafc28024000x7fae928364803958443958442581331667606553633842229029727510135550983212074903704439019120749037047297661207490370498496512074903705054844
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016085290985291441943042560024241036800x7fafc28023000x7fae928364c0222244222244254091777960655361531317531612696061443016812074903705083146120749037053854431207490370552288212074903705527923
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016285290985291441943042560024241056640x7fafc2802a000x7fae92836500262804262804283422102440655362342925381945997093901380412074903705587323120749037058766401207490370604239912074903706047769
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016485290985291441943042560024241071360x7fafc28029000x7fae92836540217892217892245281743144655361587798151576182063696052812074903706119813120749037063964781207490370653103712074903706535816
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016685290985291441943042560028241098880x7fafc28028000x7fae928365804089804089803489932718486553635298192631077120141375731212074903706594435120749037068777551207490370714271412074903707212213
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016885290985291441943042560028241113600x7fafc28027000x7fae928365c03941003941002859831528086553631949996929675410127982340412074903707242239120749037075350321207490370778911112074903707829861
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017085290985291441943042560024241128320x7fafc28026000x7fae92836600219740219740250771757928655361431903071589996057460812012074903707867210120749037081607891207490370829678812074903708301918
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017285290985291441943042560024241148160x7fafc28025000x7fae92836640277556277556293672220456655362432182792057849097473368412074903708365927120749037086452661207490370882046512074903708825651
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017485290985291441943042560024241162880x7fafc28024000x7fae92836680210972210972219991687784655361585616391510760063609421612074903708895020120749037091815681207490370931148812074903709319619
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017685290985291441943042560028241190400x7fafc28023000x7fae928366c04032444032443632832259606553632171102730432530128867145212074903709377567120749037096622051207490370992300412074903709963596
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017885290985291441943042560028241207680x7fafc2802a000x7fae928367003988843988843247231910806553631328540130185220125495758012074903710010513120749037102943621207490371055180112074903710592925
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018085290985291441943042560024241224960x7fafc28029000x7fae92836740219780219780250681758248655361535895841589952061622566812074903710630766120749037109135601207490371104955912074903711053932
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018285290985291441943042560024241247360x7fafc28028000x7fae928367802892682892683095823141526553625192054521498330100952084812074903711116779120749037113996381207490371158267712074903711587454
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018485290985291441943042560024241264640x7fafc28027000x7fae928367c0227588227588247571820712655361547144481659778062074063212074903711680156120749037119381961207490371207931512074903712083716
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018685290985291441943042560020241279360x7fafc28026000x7fae928368004097404097403572832779286553637613650631083510150637436012074903712145010120749037124327541207490371269867312074903712766595
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018885290985291441943042560028241296640x7fafc28025000x7fae928368403980283980282918931842326553628418228329997280113854847212074903712800999120749037131053911207490371336251012074903713430869
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019085290985291441943042560024241313920x7fafc28024000x7fae92836880229492229492274121835944655361483434941645185059524358012074903713460805120749037137556281207490371389626812074903713900642
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019285290985291441943042560024241336320x7fafc28023000x7fae928368c03033403033403235524267286553627400822222610190109788217212074903713963269120749037142537061207490371444618512074903714514553
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019485290985291441943042560024241353600x7fafc2802a000x7fae92836900223276223276222961786216655361576647811606406063255103212074903714553856120749037148385041207490371497690312074903714981321
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019685290985291441943042560020241368320x7fafc28029000x7fae928369404362684362684018034901526553640481130733203180162106578012074903715041653120749037153338621207490371561770012074903715686231
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019885290985291441943042560028241385600x7fafc28028000x7fae928369804612044612041595736896406553627103751630411620108597192812074903715715445120749037160092191207490371630857812074903716376854
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020085290985291441943042560024241402880x7fafc28027000x7fae928369c0225460225460275971803688655361533931501617746061546664412074903716406329120749037167004161207490371683945512074903716843632
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020285290985291441943042560024241427840x7fafc28026000x7fae92836a003289643289643321826317206553629703046324689720118997030812074903716907109120749037172002541207490371741017312074903717451722
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020485290985291441943042560024241447680x7fafc28025000x7fae92836a40221396221396261261771176655361584148941586613063552759612074903717504961120749037177735321207490371790889112074903717913249
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020685290985291441943042560020241457280x7fafc28024000x7fae92836a804729804729804207137838486553644127676936140160176692704012074903717975004120749037182722491207490371858120812074903718649948
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020885290985291441943042560028241477120x7fafc28023000x7fae92836ac04010444010443350032083606553630787373230179300123331307612074903718677259120749037189760871207490371923512612074903719303583
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021085290985291441943042560024241496960x7fafc2802a000x7fae92836b00216180216180231751729448655361597357291551784064081770812074903719335332120749037196434441207490371977736312074903719781882
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021285290985291441943042560024241521920x7fafc28029000x7fae92836b403572763572763583028582166553632082439726833670128514824812074903719843466120749037201330421207490372036104112074903720429035
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021485290985291441943042560024241541760x7fafc28028000x7fae92836b80229508229508260241836072655361597054201662341064068581612074903720469680120749037207515991207490372089431912074903720898707
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021685290985291441943042560020241556480x7fafc28027000x7fae92836bc05037405037404351540299286553647254692938688190189200812812074903720960993120749037212608771207490372159063612074903721659601
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021885290985291441943042560028241576320x7fafc28026000x7fae92836c003994043994043583731952406553632748345830157220131176037212074903721691901120749037219827941207490372224151312074903722309920
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022085290985291441943042560024241596160x7fafc28025000x7fae92836c40227852227852261161822824655361565724111629935062815392012074903722340647120749037226403911207490372278199112074903722786686
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022285290985291441943042560024241623680x7fafc28024000x7fae92836c803834843834843693930678806553635290598129046960141347700812074903722847499120749037231384691207490372338470812074903723453365
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022485290985291441943042560024241646080x7fafc28023000x7fae92836cc0227260227260256811818088655361656930361633576066465173612074903723494301120749037237794271207490372392102612074903723925502
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022685290985291441943042560020241663360x7fafc2802a000x7fae92836d005752605752604894346020886553654184997844344390216921964412074903723986235120749037242805451207490372465846312074903724726711
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022885290985291441943042560028241685760x7fafc28029000x7fae92836d403970683970683493431765526553634557045730084080138410408812074903724753751120749037250544611207490372531206012074903725381017
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023085290985291441943042560024241708160x7fafc28028000x7fae92836d80220708220708249721765672655361792457961582858071886159212074903725408759120749037257078991207490372584517812074903725849798
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023285290985291441943042560024241740800x7fafc28027000x7fae92836dc04346924346924028534775446553640079286633084350160501267212074903725913406120749037261976571207490372647733612074903726546253
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023485290985291441943042560024241765760x7fafc28026000x7fae92836e00217052217052248691736424655361845589171574400074012366812074903726586067120749037268624541207490372699749312074903727012850
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023685290985291441943042560020241777920x7fafc28025000x7fae92836e406791806791801595554334486553661185272749910070244923181212074903727062312120749037273475721207490372779557012074903727864011
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023885290985291441943042560028241802880x7fafc28024000x7fae92836e804093724093723532332749846553633423163630762560133875076812074903727894177120749037282046881207490372846980712074903728512637
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024085290985291441943042560024241827840x7fafc28023000x7fae92836ec0224308224308267371794472655361827711341610023073297531612074903728556538120749037288402061207490372898004512074903728984554
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024285290985291441943042560024241863040x7fafc2802a000x7fae92836f005309885309881609742479126553645233153137349910181116786012074903729048693120749037293379641207490372968244212074903729750437
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024485290985291441943042560024241893120x7fafc28029000x7fae92836f40247684247684302531981480655362155056841796981086392268412074903729789870120749037300848411207490373023844012074903730242912
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024685290985291441943042560020241907840x7fafc28028000x7fae92836f807843887843886003162751126553675101935061093730300589835212074903730307092120749037305955591207490373111411612074903731183640
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024885290985291441943042560028241937920x7fafc28027000x7fae92836fc04544364544363746036354966553637872603434561870151675382812074903731216532120749037315125151207490373181043412074903731878201
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025085290985291441943042560024241968000x7fafc28026000x7fae92837000246100246100276301968808655362182503861807997087487289612074903731906774120749037322205121207490373237507112074903732379904
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025285290985291441943042560024242010880x7fafc28025000x7fae928370405932605932604873747460886553656124073745818740224682664412074903732441177120749037327254701207490373311138812074903733180511
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025485290985291441943042560024242046080x7fafc28024000x7fae92837080278788278788305992230312655362431063302065136097430770812074903733220456120749037335059471207490373368242612074903733686902
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025685290985291441943042560020242060800x7fafc28023000x7fae928370c09433809433801508775470486553689044606872353370356360563612074903733745602120749037340403441207490373466450212074903734706718
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025885290985291441943042560028242096000x7fafc2802a000x7fae928371005020765020764584840166166553646373307638297300185678004412074903734742314120749037350365001207490373536417912074903735432086
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026085290985291441943042560024242131200x7fafc28029000x7fae928371402824442824443093222595606553625179475720952300100904594812074903735462803120749037357526571207490373593185612074903735936603
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026285290985291441943042560024242181760x7fafc28028000x7fae928371806981966981965468155855766553666505420454264190266206064012074903735999771120749037362912151207490373674817312074903736816659
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026485290985291441943042560024242222080x7fafc28027000x7fae928371c03130443130443154425043606553628397113723474110113777911212074903736855090120749037371513711207490373735169112074903737420381
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026685290985291441943042560020242239360x7fafc28026000x7fae928372001063924106392475213851140065536102944402983535190411959696812074903737450657120749037377385691207490373844304612074903738511919
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026885290985291441943042560028242279680x7fafc28025000x7fae928372405689965689964713945519766553653631474543920130214709336812074903738542426120749037388382441207490373921328312074903739280948
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027085290985291441943042560024242320000x7fafc28024000x7fae928372803178363178363173925426966553628821230423834290115473460012074903739311234120749037396120011207490373981520012074903739884249
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027285290985291441943042560024242378240x7fafc28023000x7fae928372c08283888283881480366271126553676934898362719080307924014412074903739914856120749037402161591207490374075999712074903740828725
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027485290985291441943042560024242423680x7fafc2802a000x7fae928373003499963499963459027999766553632013469926268540128242488412074903740868308120749037411583951207490374138207412074903741451171
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027685290985291441943042560020242435840x7fafc28029000x7fae928373401205644120564483838964516065536116951601394894270467988342412074903741481808120749037417740721207490374257470912074903742642856
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027885290985291441943042560028242481280x7fafc28028000x7fae928373806364126364125117250913046553659784050349311740239320530812074903742676158120749037429807871207490374340142612074903743469332
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028085290985291441943042560024242526720x7fafc28027000x7fae928373c03549083549083435328392726553632523452026793080130285558412074903743498646120749037437966241207490374402462312074903744092891
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028285290985291441943042560024242592640x7fafc28026000x7fae928374009095729095726730772765846553687512049071180270350233027212074903744124008120749037444201411207490374501821912074903745087349
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028485290985291441943042560024242648320x7fafc28025000x7fae928374404652684652681485037221526553638680163931900390154910706012074903745128695120749037454164571207490374571805612074903745785867
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028685290985291441943042560020242663040x7fafc28024000x7fae928374801488228148822810122211905832655361447347602117381590579121108812074903745816474120749037461340541207490374712013012074903747189475
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028885290985291441943042560028242718720x7fafc28023000x7fae928374c07817167817166448462537366553673542700560550970294355845612074903747223308120749037475215691207490374803724612074903748107171
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029085290985291441943042560024242774400x7fafc2802a000x7fae928375004219404219404008433755286553639015800832068420156252383212074903748143398120749037484394851207490374871164412074903748780271
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029285290985291441943042560012242799360x7fafc28029000x7fae928375401132908113290815992906327265536108969014988499130436058184012074903748810578120749037491111621207490374985355912074903749923817
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029485290985291441943042560024242865280x7fafc28028000x7fae928375804901484901484427839211926553645762645437495050183240170012074903749963821120749037502551571207490375057211612074903750641400
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029685290985291441943042560020242880000x7fafc28027000x7fae928375c0176824417682444738114145960655361725448318139827190690361456812074903750674652120749037509737141207490375214554912074903752215716
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029885290985291441943042560032242945920x7fafc28026000x7fae928376009200209200206578273601686553681343517471816240325559154812074903752251813120749037525444281207490375315530512074903753225382
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030085290985291441943042560024243011840x7fafc28025000x7fae928376404953404953404503639627286553646232775537924650185119836812074903753262942120749037535545041207490375387562212074903753944468
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030285290985291441943042560012243049600x7fafc28024000x7fae92837680133971613397169472110717736655361298640061105335060519638810412074903753974524120749037542761011207490375515481712074903755224427
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030485290985291441943042560024243136000x7fafc28023000x7fae928376c06337086337085350150696726553659803571649034250239404218412074903755271164120749037555584951207490375597145412074903756040794
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030685290985291441943042560020243148160x7fafc2802a000x7fae928377002332012233201215039918656104655362284461290184958310913966518012074903756077422120749037563738521207490375792216612074903757991449
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030885290985291441943042560020243175680x7fafc28029000x7fae928377401201348120134884507961079265536116365051394471910465642602012074903758032465120749037583336841207490375912920112074903759198713
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031085290985291441943042560012243203200x7fafc28028000x7fae928377806410366410365218351282966553660714082349660500243039036412074903759234670120749037595359191207490375995095712074903760020600
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031285290985291441943042560012243240960x7fafc28027000x7fae928377c01758828175882811830714070632655361714787455139071420686097256812074903760058170120749037603509561207490376151047112074903761580319
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031485290985291441943042560012243288960x7fafc28026000x7fae928378001199756119975685728959805665536116030330194299670464303520012074903761622116120749037619152691207490376270182612074903762770851
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031685290985291441943042560020243301120x7fafc28025000x7fae9283784045834764583476281213366678166553645148419433650502401806118953612074903762800055120749037631090241207490376615925212074903766229769
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031885290985291441943042560020243328640x7fafc28024000x7fae928378802324964232496414999618599720655362277055741184351650911004908812074903766260416120749037665658101207490376810996312074903768179352
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032085290985291441943042560012243356160x7fafc28023000x7fae928378c01205692120569285552964554465536116692669994701450466953298812074903768217022120749037685122021207490376930403912074903769374323
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032285290985291441943042560012243393920x7fafc2802a000x7fae9283790034446923444692217015275575446553633849179362738701701354149638812074903769410550120749037697069161207490377198914712074903772062538
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032485290985291441943042560012243441920x7fafc28029000x7fae928379402324428232442815153518595432655362274612431184237950910027325612074903772105528120749037723985841207490377393441812074903774006852
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032685290985291441943042560020243454080x7fafc28028000x7fae9283798090874209087420544354726993686553689773279127253171703591113265612074903774040083120749037743377771207490378039295312074903780462719
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032885290985291441943042560020243481600x7fafc28027000x7fae928379c045735484573548282566365883926553645028456883642194501801320681612074903780499738120749037807942311207490378383821912074903783909064
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033085290985291441943042560012243509120x7fafc28026000x7fae92837a002331036233103615257418648296655362280467792184691650912369645212074903783943247120749037842426971207490378578381112074903785853086
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332852909852914419430425600122400x7fafc28025000x7fae92837a4068133966813396412964545071766553667242737635434303702689892226412074903785886999120749037861943701207490379072235212074903790792425