Files
rocm-systems/tests/workloads/mixbench1/mi100/SQ_INST_LEVEL_VMEM.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

43 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_VMEMSQ_INST_LEVEL_VMEMSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000760119760124335544322560083264640x00x7f8d7a804180104857611210730143451903212073372448537795120733726937519821207337269407662012073372694185923
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00276011976012432768256002424124800x00x7f8d7a83510040961275701633632412073372708597826120733727089027891207337270890934912073372708914554
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0047601197601244194304256002424129280x7f8eaa8039000x7f8d7a83514052428812691811162451465212073372709024839120733727092061471207337270933734712073372709341438
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0067601197601244194304256003624136320x7f8eaa8038000x7f8d7a83518052428813468026172389300812073372709411658120733727095794251207337270982918412073372709897471
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0087601197601244194304256002824140800x7f8eaa8037000x7f8d7a8351c052428814350897183688500812073372709934079120733727101122231207337271036822212073372710442093
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00107601197601244194304256002424145280x7f8eaa8036000x7f8d7a83520052428811805261151105897212073372710480374120733727106565401207337271079094012073372710794508
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00127601197601244194304256002424149760x7f8eaa8035000x7f8d7a83524052428811802375151061141612073372710845994120733727110094991207337271114325812073372711147003
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00147601197601244194304256002424154240x7f8eaa8034000x7f8d7a83528052428810978924140534607612073372711228905120733727114006971207337271153877612073372711542538
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00167601197601244194304256002824161280x7f8eaa8033000x7f8d7a8352c052428814242644182301154812073372711592251120733727117682151207337271202101412073372712088513
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00187601197601244194304256002824168320x7f8eaa803a000x7f8d7a83530052428813321725170511346412073372712116335120733727122966921207337271258917112073372712656128
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00207601197601244194304256002424175360x7f8eaa8039000x7f8d7a83534052428813763139176169129212073372712682427120733727128691701207337271299492912073372712998725
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00227601197601244194304256002424182400x7f8eaa8038000x7f8d7a83538052428811766278150610802012073372713047976120733727132341281207337271336900712073372713372880
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00247601197601244194304256002424189440x7f8eaa8037000x7f8d7a8353c052428812158666155624310012073372713435286120733727135958861207337271372724612073372713730685
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00267601197601244194304256002824199040x7f8eaa8036000x7f8d7a83540052428814123029180775572012073372713782531120733727139422851207337271419588312073372714264667
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00287601197601244194304256002824206080x7f8eaa8035000x7f8d7a83544052428814000345179208211212073372714289183120733727144699621207337271471988112073372714785695
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00307601197601244194304256002424213120x7f8eaa8034000x7f8d7a83548052428812965724165965612012073372714811523120733727149917201207337271512051912073372715124515
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00327601197601244194304256002424220160x7f8eaa8033000x7f8d7a8354c052428813037608166881434812073372715174869120733727153358781207337271546515712073372715468965
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00347601197601244194304256002424227200x7f8eaa803a000x7f8d7a83550052428812503164160035287612073372715530459120733727156896361207337271582035612073372715824055
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00367601197601244194304256002824236800x7f8eaa8039000x7f8d7a83554052428814159083181231812412073372715873647120733727160502751207337271630515312073372716374147
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00387601197601244194304256002824243840x7f8eaa8038000x7f8d7a83558052428814231930182166653612073372716400106120733727165835521207337271683379112073372716874377
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00407601197601244194304256002424250880x7f8eaa8037000x7f8d7a8355c052428813250796169607058412073372716901978120733727170824301207337271721106912073372717214960
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00427601197601244194304256002424257920x7f8eaa8036000x7f8d7a83560052428813291744170132878812073372717265063120733727174342681207337271756210712073372717565672
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00447601197601244194304256002424264960x7f8eaa8035000x7f8d7a83564052428812183946155946721612073372717627096120733727177873861207337271791986612073372717923497
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00467601197601244194304256002824277120x7f8eaa8034000x7f8d7a83568052428813929286178292640012073372717970955120733727181429051207337271839250312073372718461657
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00487601197601244194304256002824284160x7f8eaa8033000x7f8d7a8356c052428813903244177962014812073372718491412120733727186640221207337271891730112073372718983516
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00507601197601244194304256002424291200x7f8eaa803a000x7f8d7a83570052428812670095162176483612073372719014093120733727191905801207337271932113912073372719324991
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00527601197601244194304256002424300800x7f8eaa8039000x7f8d7a83574052428812908441165233298812073372719373972120733727195398581207337271966897712073372719672677
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00547601197601244194304256002424307840x7f8eaa8038000x7f8d7a83578052428812524967160320558412073372719732999120733727198969761207337272002689612073372720030973
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00567601197601244194304256002824320000x7f8eaa8037000x7f8d7a8357c052428814154135181172917212073372720080355120733727202569751207337272051425312073372720581216
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00587601197601244194304256002824329600x7f8eaa8036000x7f8d7a83580052428814270762182662410012073372720608947120733727207876921207337272103809112073372721084852
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00607601197601244194304256002424339200x7f8eaa8035000x7f8d7a83584052428812666728162137679612073372721112924120733727212884901207337272141840912073372721422178
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00627601197601244194304256002424348800x7f8eaa8034000x7f8d7a8358805242889931334127117795612073372721475678120733727216344081207337272181824712073372721822012
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00647601197601244194304256002424358400x7f8eaa8033000x7f8d7a8358c052428812592603161194056812073372721884678120733727220486461207337272217872512073372722182812
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00667601197601244194304256002824373120x7f8eaa803a000x7f8d7a83590052428813634617174520423212073372722234899120733727223955241207337272264944312073372722716203
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00687601197601244194304256002824382720x7f8eaa8039000x7f8d7a83594052428814080574180230142812073372722740629120733727229198421207337272317360112073372723240898
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00707601197601244194304256002424392320x7f8eaa8038000x7f8d7a83598052428813211074169107040012073372723267788120733727234439991207337272357311912073372723576983
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00727601197601244194304256002424401920x7f8eaa8037000x7f8d7a8359c052428812804987163904012812073372723627767120733727238004781207337272393023712073372723934147
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00747601197601244194304256002424411520x7f8eaa8036000x7f8d7a835a0052428812707068162639864412073372723995701120733727241617561207337272429215512073372724295779
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00767601197601244194304256002824426240x7f8eaa8035000x7f8d7a835a4052428814105107180543093212073372724344700120733727245105541207337272476863312073372724810425
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00787601197601244194304256002824435840x7f8eaa8034000x7f8d7a835a8052428813794128176561828012073372724837345120733727250087921207337272526271112073372725330401
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00807601197601244194304256002424445440x7f8eaa8033000x7f8d7a835ac052428811103533142122036412073372725356490120733727255310301207337272566750912073372725671255
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00827601197601244194304256002424457600x7f8eaa803a000x7f8d7a835b0052428812656244162000471612073372725720146120733727258814281207337272601262712073372726016306
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00847601197601244194304256002424467200x7f8eaa8039000x7f8d7a835b4052428812053309154278901212073372726078532120733727262372661207337272637102612073372726374702
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00867601197601244194304256002824484480x7f8eaa8038000x7f8d7a835b8052428814232256182173656812073372726422120120733727265892651207337272685678312073372726924173
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00887601197601244194304256002824494080x7f8eaa8037000x7f8d7a835bc052428814114755180671981212073372726950783120733727271319821207337272738606112073372727454639
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00907601197601244194304256002424503680x7f8eaa8036000x7f8d7a835c0052428812787300163677183212073372727480607120733727276615791207337272779053912073372727794210
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00927601197601244194304256002424515840x7f8eaa8035000x7f8d7a835c4052428811374170145586295612073372727842319120733727280081381207337272814509712073372728148939
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00947601197601244194304256002424525440x7f8eaa8034000x7f8d7a835c8052428811234826143816720412073372728211746120733727283710161207337272850845512073372728512244
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00967601197601244194304256002824542720x7f8eaa8033000x7f8d7a835cc052428812941228165642522012073372728561055120733727287196541207337272898477312073372729030798
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00987601197601244194304256002824554880x7f8eaa803a000x7f8d7a835d0052428814174204181426242012073372729059021120733727292345321207337272948605112073372729552137
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001007601197601244194304256002424567040x7f8eaa8039000x7f8d7a835d4052428812696213162507782812073372729579448120733727297546891207337272988460912073372729888292
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001027601197601244194304256002424581760x7f8eaa8038000x7f8d7a835d805242889463144121127270812073372729937593120733727301046081207337273024748712073372730251547
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001047601197601244194304256002424593920x7f8eaa8037000x7f8d7a835dc052428811046839141395886812073372730314013120733727304762861207337273061324512073372730617347
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001067601197601244194304256002824613760x7f8eaa8036000x7f8d7a835e0052428814176018181453669612073372730665546120733727308308441207337273109340312073372731160857
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001087601197601244194304256002824625920x7f8eaa8035000x7f8d7a835e4052428814244431182323978012073372731186344120733727313689221207337273162124112073372731687956
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001107601197601244194304256002424638080x7f8eaa8034000x7f8d7a835e8052428811814263151224700412073372731715527120733727318877991207337273202139912073372732025393
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001127601197601244194304256002424652800x7f8eaa8033000x7f8d7a835ec05242889403496120362480012073372732079324120733727322362781207337273237483712073372732378520
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001147601197601244194304256002424664960x7f8eaa803a000x7f8d7a835f0052428811359653145403045612073372732439483120733727325993161207337273273419512073372732737988
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001167601197601244194304256002824684800x7f8eaa8039000x7f8d7a835f4052428813884510177715880812073372732787660120733727329453941207337273320363312073372733271910
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001187601197601244194304256002824696960x7f8eaa8038000x7f8d7a835f8052428813801510176657534812073372733299561120733727334730721207337273372747112073372733794441
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001207601197601244194304256002424709120x7f8eaa8037000x7f8d7a835fc052428811039708141299731212073372733821531120733727339956291207337273413370912073372734137889
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001227601197601244194304256002424723840x7f8eaa8036000x7f8d7a8360005242887949552101744292812073372734187872120733727343493881207337273449146712073372734495233
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001247601197601244194304256002424736000x7f8eaa8035000x7f8d7a83604052428811433152146332208812073372734555595120733727347119461207337273484778512073372734851565
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001267601197601244194304256002824758400x7f8eaa8034000x7f8d7a83608052428812558325160747025212073372734900516120733727350708241207337273533946312073372735389034
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001287601197601244194304256002824770560x7f8eaa8033000x7f8d7a8360c052428814226292182093530412073372735414762120733727355913021207337273584618112073372735895065
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001307601197601244194304256002424782720x7f8eaa803a000x7f8d7a83610052428812129328155259950012073372735921464120733727361106591207337273624409912073372736247810
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001327601197601244194304256002424800000x7f8eaa8039000x7f8d7a836140524288697456289275167212073372736297342120733727364572181207337273660025712073372736604092
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001347601197601244194304256002424812160x7f8eaa8038000x7f8d7a83618052428812154812155577001612073372736666468120733727368220161207337273695449512073372736958290
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001367601197601244194304256002824834560x7f8eaa8037000x7f8d7a8361c052428813981219178962131212073372737012090120733727371727341207337273743161312073372737461135
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001387601197601244194304256002824849280x7f8eaa8036000x7f8d7a83620052428813800235176627573612073372737502812120733727376589721207337273791129112073372737936749
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001407601197601244194304256002424864000x7f8eaa8035000x7f8d7a83624052428812732624162977828412073372737980720120733727381431301207337273827240912073372738276530
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001427601197601244194304256002424881280x7f8eaa8034000x7f8d7a836280524288523771167036713612073372738325501120733727384909681207337273864056712073372738644394
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001447601197601244194304256002424896000x7f8eaa8033000x7f8d7a8362c052428812461005159497303212073372738721648120733727388780061207337273900968612073372739013720
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001467601197601244194304256002824920960x7f8eaa803a000x7f8d7a83630052428813321008170506064012073372739063573120733727392309641207337273949736312073372739522516
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001487601197601244194304256002824935680x7f8eaa8039000x7f8d7a83634052428814111440180622410412073372739565987120733727397199221207337273996824112073372739994253
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001507601197601244194304256002424950400x7f8eaa8038000x7f8d7a83638052428810933119139938898812073372740043464120733727402186401207337274035687912073372740360854
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001527601197601244194304256002424967680x7f8eaa8037000x7f8d7a8363c0524288499999764001959612073372740409584120733727405728781207337274073079712073372740734608
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001547601197601244194304256002424982400x7f8eaa8036000x7f8d7a83640052428811544440147770537212073372740798066120733727409559161207337274109111612073372741095178
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015676011976012441943042560028241007360x7f8eaa8035000x7f8d7a83644052428811018177141026006412073372741149279120733727413064751207337274157623312073372741602511
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015876011976012441943042560028241022080x7f8eaa8034000x7f8d7a83648052428813479111172522017612073372741655480120733727418205521207337274207591112073372742104143
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016076011976012441943042560024241036800x7f8eaa8033000x7f8d7a8364c052428811797527151015443212073372742154477120733727423139901207337274244774912073372742451559
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016276011976012441943042560024241056640x7f8eaa803a000x7f8d7a836500524288360837546173914412073372742502884120733727426687081207337274283494712073372742838899
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016476011976012441943042560024241071360x7f8eaa8039000x7f8d7a83654052428812994460166326455212073372742901465120733727430675861207337274319702612073372743201082
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016676011976012441943042560028241098880x7f8eaa8038000x7f8d7a83658052428810733564137392859212073372743251395120733727434163851207337274367942312073372743703205
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016876011976012441943042560028241113600x7f8eaa8037000x7f8d7a8365c052428814080602180229222012073372743746956120733727439016621207337274415206112073372744178869
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017076011976012441943042560024241128320x7f8eaa8036000x7f8d7a83660052428810375787132814388012073372744221548120733727443832601207337274452261912073372744526695
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017276011976012441943042560024241148160x7f8eaa8035000x7f8d7a836640524288347137944415513212073372744575937120733727447354181207337274490981712073372744913705
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017476011976012441943042560024241162880x7f8eaa8034000x7f8d7a83668052428812224924156471373612073372744974928120733727451389361207337274527205612073372745275858
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017676011976012441943042560028241190400x7f8eaa8033000x7f8d7a8366c05242889914541126907620012073372745325340120733727454901351207337274575237312073372745776368
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017876011976012441943042560028241207680x7f8eaa803a000x7f8d7a83670052428814196982181713136812073372745822483120733727459768521207337274623093112073372746258143
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018076011976012441943042560024241224960x7f8eaa8039000x7f8d7a83674052428811169860142972740812073372746302165120733727464616501207337274659796912073372746601882
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018276011976012441943042560024241247360x7f8eaa8038000x7f8d7a836780524288344792744136444412073372746649230120733727468149281207337274699764812073372747011313
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018476011976012441943042560024241264640x7f8eaa8037000x7f8d7a8367c052428811451586146585671212073372747063931120733727472224461207337274735844612073372747362325
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018676011976012441943042560020241279360x7f8eaa8036000x7f8d7a836800524288426612454601677612073372747410865120733727475768451207337274784340412073372747866913
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018876011976012441943042560028241296640x7f8eaa8035000x7f8d7a83684052428813986290179023016412073372747909582120733727480637221207337274831348112073372748339772
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019076011976012441943042560024241313920x7f8eaa8034000x7f8d7a83688052428811557568147931543212073372748381008120733727485382801207337274867412012073372748678231
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019276011976012441943042560024241336320x7f8eaa8033000x7f8d7a8368c0524288316561740514012012073372748725709120733727488891591207337274908147812073372749109081
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019476011976012441943042560024241353600x7f8eaa803a000x7f8d7a83690052428811401183145933548012073372749161499120733727493195571207337274945491612073372749458901
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019676011976012441943042560020241368320x7f8eaa8039000x7f8d7a836940524288282730936194988412073372749506340120733727496771551207337274996179312073372749985210
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019876011976012441943042560028241385600x7f8eaa8038000x7f8d7a83698052428813780982176393700812073372750048527120733727502145921207337275047075112073372750497431
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020076011976012441943042560024241402880x7f8eaa8037000x7f8d7a8369c052428811326705144987286012073372750538157120733727506937901207337275083042912073372750834528
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020276011976012441943042560024241427840x7f8eaa8036000x7f8d7a836a00524288330476542292097612073372750881625120733727510541081207337275126514712073372751289383
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020476011976012441943042560024241447680x7f8eaa8035000x7f8d7a836a4052428811053031141483466412073372751345748120733727515088261207337275164466512073372751648791
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020676011976012441943042560020241457280x7f8eaa8034000x7f8d7a836a80524288254741532612071612073372751697942120733727518569841207337275216466312073372752192401
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020876011976012441943042560028241477120x7f8eaa8033000x7f8d7a836ac052428814100099180476630812073372752233307120733727523920221207337275264802112073372752671151
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021076011976012441943042560024241496960x7f8eaa803a000x7f8d7a836b0052428812274170157108845612073372752715413120733727528715401207337275300481912073372753008919
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021276011976012441943042560024241521920x7f8eaa8039000x7f8d7a836b40524288320460641023715612073372753057108120733727532249781207337275345249712073372753477680
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021476011976012441943042560024241541760x7f8eaa8038000x7f8d7a836b8052428811505013147260486012073372753534876120733727536928161207337275382577512073372753829674
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021676011976012441943042560020241556480x7f8eaa8037000x7f8d7a836bc0524288245342031392922412073372753878174120733727540470541207337275437761212073372754405454
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021876011976012441943042560028241576320x7f8eaa8036000x7f8d7a836c0052428814016165179407848412073372754447492120733727546068911207337275486209012073372754885757
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022076011976012441943042560024241596160x7f8eaa8035000x7f8d7a836c405242889772026125080494412073372754928857120733727550888091207337275523184812073372755235787
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022276011976012441943042560024241623680x7f8eaa8034000x7f8d7a836c80524288322356041263143212073372755283766120733727554529671207337275569808612073372755721810
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022476011976012441943042560024241646080x7f8eaa8033000x7f8d7a836cc05242889414037120493934412073372755785288120733727559443251207337275608592412073372756090205
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022676011976012441943042560020241663360x7f8eaa803a000x7f8d7a836d00524288236770830305765612073372756139547120733727563113651207337275671408412073372756741115
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022876011976012441943042560028241685760x7f8eaa8039000x7f8d7a836d4052428813662015174869818012073372756780818120733727569411221207337275720496112073372757230464
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023076011976012441943042560024241708160x7f8eaa8038000x7f8d7a836d805242889988810127850950012073372757272863120733727574302411207337275756928012073372757571558
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023276011976012441943042560024241740800x7f8eaa8037000x7f8d7a836dc0524288324975141596796812073372757619307120733727577968001207337275807647912073372758103176
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023476011976012441943042560024241765760x7f8eaa8036000x7f8d7a836e005242888173585104619466412073372758156775120733727583225581207337275846463812073372758466992
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023676011976012441943042560020241777920x7f8eaa8035000x7f8d7a836e40524288235224830100974012073372758516594120733727586833571207337275910783612073372759130836
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023876011976012441943042560028241802880x7f8eaa8034000x7f8d7a836e8052428810898634139508646412073372759174397120733727593334351207337275959759512073372759619824
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024076011976012441943042560024241827840x7f8eaa8033000x7f8d7a836ec0524288763217297683522812073372759670418120733727598308741207337275997183412073372759974513
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024276011976012441943042560024241863040x7f8eaa803a000x7f8d7a836f00524288340097643523410012073372760030417120733727601887931207337276050415212073372760529755
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024476011976012441943042560024241893120x7f8eaa8039000x7f8d7a836f40524288332444242552883612073372760582393120733727607425521207337276093423112073372760955847
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024676011976012441943042560020241907840x7f8eaa8038000x7f8d7a836f80524288230329629480596012073372760998907120733727611593501207337276167678912073372761702555
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024876011976012441943042560028241937920x7f8eaa8037000x7f8d7a836fc05242887972976102045868012073372761744433120733727618999881207337276219870812073372762226188
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025076011976012441943042560024241968000x7f8eaa8036000x7f8d7a837000524288314839240294585212073372762266202120733727624255871207337276258094612073372762583432
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025276011976012441943042560024242010880x7f8eaa8035000x7f8d7a837040524288346588044362310812073372762631792120733727627961461207337276318174512073372763204857
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025476011976012441943042560024242046080x7f8eaa8034000x7f8d7a837080524288290746837226076412073372763263205120733727634275041207337276360494412073372763607625
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025676011976012441943042560020242060800x7f8eaa8033000x7f8d7a8370c0524288231740429662542812073372763655674120733727638227031207337276443310112073372764459027
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025876011976012441943042560028242096000x7f8eaa803a000x7f8d7a837100524288409254652378108012073372764504201120733727646639811207337276499374012073372765016754
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026076011976012441943042560024242131200x7f8eaa8039000x7f8d7a837140524288305046039042897212073372765065384120733727652250991207337276540429912073372765406819
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026276011976012441943042560024242181760x7f8eaa8038000x7f8d7a837180524288315361540363042812073372765459938120733727656162981207337276607213712073372766096721
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026476011976012441943042560024242222080x7f8eaa8037000x7f8d7a8371c0524288298745138234915612073372766156041120733727663161361207337276651693612073372766538392
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026676011976012441943042560020242239360x7f8eaa8036000x7f8d7a837200524288232037429690744012073372766585660120733727667414151207337276744541312073372767468911
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026876011976012441943042560028242279680x7f8eaa8035000x7f8d7a837240524288348913844658444012073372767512762120733727676700531207337276804365212073372768067624
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027076011976012441943042560024242320000x7f8eaa8034000x7f8d7a837280524288313307340095368412073372768116334120733727682783711207337276848141012073372768502872
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027276011976012441943042560024242378240x7f8eaa8033000x7f8d7a8372c0524288439987056321329212073372768552915120733727687124501207337276923868812073372769261673
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027476011976012441943042560024242423680x7f8eaa803a000x7f8d7a837300524288307008239297418812073372769322315120733727694834881207337276970892712073372769731526
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027676011976012441943042560020242435840x7f8eaa8039000x7f8d7a837340524288229147829328166012073372769775898120733727699318061207337277073036412073372770758895
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027876011976012441943042560028242481280x7f8eaa8038000x7f8d7a837380524288347718344508978012073372770799260120733727709606041207337277138204212073372771405497
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028076011976012441943042560024242526720x7f8eaa8037000x7f8d7a8373c0524288311899239923468412073372771448426120733727716172421207337277184444112073372771867655
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028276011976012441943042560024242592640x7f8eaa8036000x7f8d7a837400524288433547455494661212073372771910695120733727720718001207337277266987912073372772696786
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028476011976012441943042560024242648320x7f8eaa8035000x7f8d7a837440524288321995341226162812073372772749895120733727729084381207337277317899712073372773204179
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028676011976012441943042560020242663040x7f8eaa8034000x7f8d7a837480524288230589429531911612073372773246398120733727734111571207337277439643412073372774462939
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028876011976012441943042560028242718720x7f8eaa8033000x7f8d7a8374c0524288338982543387688012073372774493836120733727746751531207337277519083212073372775258497
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029076011976012441943042560024242774400x7f8eaa803a000x7f8d7a837500524288332655642566734012073372775290286120733727754676311207337277574139012073372775806525
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029276011976012441943042560012242799360x7f8eaa8039000x7f8d7a837540524288221402328336318412073372775829288120733727760050701207337277674394812073372776812805
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029476011976012441943042560024242865280x7f8eaa8038000x7f8d7a837580524288337442943184536812073372776849003120733727770101871207337277732714612073372777392783
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029676011976012441943042560020242880000x7f8eaa8037000x7f8d7a8375c0524288229516029378371212073372777419042120733727776005851207337277877066212073372778838059
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029876011976012441943042560032242945920x7f8eaa8036000x7f8d7a837600524288334597442841582012073372778868746120733727790525811207337277966106012073372779728614
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030076011976012441943042560024243011840x7f8eaa8035000x7f8d7a837640524288314406640243103612073372779757508120733727799364191207337278025497812073372780323960
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030276011976012441943042560012243049600x7f8eaa8034000x7f8d7a837680524288221276028335990812073372780348827120733727805292171207337278140729512073372781473727
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030476011976012441943042560024243136000x7f8eaa8033000x7f8d7a8376c0524288316125340462807612073372781517579120733727816794541207337278209209312073372782158720
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030676011976012441943042560020243148160x7f8eaa803a000x7f8d7a837700524288231188129584396812073372782190700120733727823671321207337278391576812073372783982299
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030876011976012441943042560020243175680x7f8eaa8039000x7f8d7a837740524288226879629028782012073372784019047120733727842005671207337278499656512073372785064630
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031076011976012441943042560012243203200x7f8eaa8038000x7f8d7a837780524288218243627927292412073372785101349120733727852632841207337278567896312073372785745556
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031276011976012441943042560012243240960x7f8eaa8037000x7f8d7a8377c0524288224528328726986412073372785783176120733727859436021207337278710247912073372787170494
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031476011976012441943042560012243288960x7f8eaa8036000x7f8d7a837800524288223354328586064412073372787219375120733727873807191207337278816679612073372788233860
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031676011976012441943042560020243301120x7f8eaa8035000x7f8d7a837840524288267509234248833212073372788265078120733727884415161207337279149222712073372791558839
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031876011976012441943042560020243328640x7f8eaa8034000x7f8d7a837880524288230441929507839612073372791591420120733727917651861207337279330694212073372793373502
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032076011976012441943042560012243356160x7f8eaa8033000x7f8d7a8378c0524288219781428128932412073372793400181120733727935864621207337279437605912073372794443189
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032276011976012441943042560012243393920x7f8eaa803a000x7f8d7a837900524288253969832502410412073372794474427120733727946445391207337279692693212073372796993469
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032476011976012441943042560012243441920x7f8eaa8039000x7f8d7a837940524288236662430298557212073372797042600120733727972061321207337279874164712073372798809233
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032676011976012441943042560020243454080x7f8eaa8038000x7f8d7a837980524288288316436905595212073372798841824120733727990138071207337280506979012073372805140178
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032876011976012441943042560020243481600x7f8eaa8037000x7f8d7a8379c0524288303441738835723612073372805169373120733728053518691207337280839346112073372808462623
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033076011976012441943042560012243509120x7f8eaa8036000x7f8d7a837a00524288228989329296404812073372808493390120733728086709001207337281020961612073372810276133
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332760119760124419430425600122400x7f8eaa8035000x7f8d7a837a40524288255549632706262012073372810305418120733728104833751207337281501056312073372815077105