Files
rocm-systems/tests/workloads/HBM/mi200/SQ_INST_LEVEL_SMEM.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

41 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_SMEMSQ_INST_LEVEL_SMEMSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000168845168845335544322560043241600x00x7f758e8042803670016309068834596942416685107292208166795197716091668525552191316685255636172
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00216884516884532768256001224138880x00x7f758e823f805121016561138291216685260804240166852555219131668526093212516685260936516
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051688451688454194304256001224143360x7f75917ec3800x7f758e823fc0655366302027053036816685260970545166852609321251668526128956316685261292034
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081688451688454194304256001624150400x7f75917ec2000x7f758e824000655366751107568500016685261327103166852612895631668526168924116685261691481
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111688451688454194304256001624154880x7f75917ec0800x7f758e824040655366654107469905616685261723020166852616892411668526207707916685262090297
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141688451688454194304256001224159360x7f758f14df000x7f758e824080655366646187447720816685262110907166852620770791668526238571816685262388008
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171688451688454194304256001224163840x7f758f14dd800x7f758e8240c0655366241846990436816685262418907166852623857181668526268875616685262691098
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201688451688454194304256001224170880x7f758f14dc000x7f758e8241001310726669207475687216685262734426166852626887561668526298955516685262991708
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231688451688454194304256001624177920x7f758f14da800x7f758e8241401310727119587973286416685263022407166852629895551668526338203316685263384315
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261688451688454194304256001624184960x7f758f14d9000x7f758e824180655366666887474173616685263416333166852633820331668526377003116685263772282
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291688451688454194304256001624192000x7f758f14d7800x7f758e8241c01310727070847921291216685263801621166852637700311668526408138916685264083581
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321688451688454194304256001624199040x7f758f14d6000x7f758e8242001310727078067931832816685264115050166852640813891668526437978816685264382061
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351688451688454194304256001224206080x7f75917ec4800x7f758e8242401310726993567852423216685264422210166852643797881668526467866616685264680952
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381688451688454194304256001624213120x7f75917ec3000x7f758e8242801310727101247964318416685264711630166852646786661668526506650416685265068719
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411688451688454194304256001624220160x7f75917ec1800x7f758e8242c0655366674227475057616685265100528166852650665041668526545162216685265453976
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441688451688454194304256001624227200x7f75917ec0000x7f758e8243001310727056007905231216685265485295166852654516221668526575018116685265752286
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471688451688454194304256001224234240x7f758f14de800x7f758e8243401310727011327848512816685265785175166852657501811668526605369916685266055766
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501688451688454194304256001224241280x7f758f14dd000x7f758e8243801310727033907879444016685266110354166852660536991668526639513816685266397535
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531688451688454194304256001624248320x7f758f14db800x7f758e8243c01310727092347955296816685266427924166852663951381668526676569616685266767142
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561688451688454194304256001624255360x7f758f14da000x7f758e824400655366825687646710416685266797821166852667656961668526713321416685267134920
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591688451688454194304256001224262400x7f758f14d8800x7f758e8244401310727091327929677616685267165419166852671332141668526740441316685267406001
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621688451688454194304256001224269440x7f758f14d7000x7f758e8244801310727067387915028016685267436660166852674044131668526767545116685267677032
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651688451688454194304256001224276480x7f75917ec5800x7f758e8244c01310726777187596744816685267715141166852676754511668526794649016685267948183
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681688451688454194304256001624286080x7f75917ec4000x7f758e8245001310727013807860236016685267980442166852679464901668526830824816685268309861
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711688451688454194304256001624293120x7f75917ec2800x7f758e824540655366633007441276816685268340180166852683082481668526867400616685268675559
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741688451688454194304256001224300160x7f75917ec1000x7f758e8245801310726860227678440016685268707058166852686740061668526894456516685268946210
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077168845168845419430425600824309760x7f758f14df800x7f758e8245c01310726864567684774416685268975909166852689445651668526921320316685269214871
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801688451688454194304256001224316800x7f758f14de000x7f758e8246001310726978787806028816685269252480166852692132031668526948360216685269485282
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831688451688454194304256001624326400x7f758f14dc800x7f758e8246401310726641347448888816685269515521166852694836021668526984440016685269846000
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861688451688454194304256001224336000x7f758f14db000x7f758e824680655366595887378924816685269876609166852698444001668527020727816685270209138
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891688451688454194304256001224345600x7f758f14d9800x7f758e8246c01310727024867870915216685270240667166852702072781668527048359716685270485359
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092168845168845419430425600824355200x7f758f14d8000x7f758e8247001310727042067897430416685270515818166852704835971668527075543616685270757070
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951688451688454194304256001224362240x7f758f14d6800x7f758e8247401310727027287870949616685270796069166852707554361668527102743416685271028951
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981688451688454194304256001224371840x7f75917ec5000x7f758e8247801310726623087414459216685271060050166852710274341668527138951316685271391029
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011688451688454194304256001224381440x7f75917ec3800x7f758e8247c0655366648327443520016685271422658166852713895131668527174951116685271751207
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041688451688454194304256001224391040x7f75917ec2000x7f758e8248001310727007787855585616685271782906166852717495111668527202310916685272024598
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107168845168845419430425600824403200x7f75917ec0800x7f758e8248401310727008167850516016685272056107166852720231091668527229606816685272297659
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101688451688454194304256001224412800x7f758f14df000x7f758e8248801310726984787823851216685272335867166852722960681668527256966716685272571260
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131688451688454194304256001224422400x7f758f14dd800x7f758e8248c01310727077267926476816685272601409166852725696671668527293254516685272934178
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161688451688454194304256001224432000x7f758f14dc000x7f758e824900655366371227138673616685272964757166852729325451668527330214316685273303735
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119168845168845419430425600824441600x7f758f14da800x7f758e8249401310727099627949796816685273334754166852733021431668527357494216685273576406
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221688451688454194304256001224453760x7f758f14d9000x7f758e8249801310727077747927637616685273607015166852735749421668527384950016685273851067
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251688451688454194304256001224463360x7f758f14d7800x7f758e8249c01310727026587868692816685273888766166852738495001668527412373916685274125428
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281688451688454194304256001224475520x7f758f14d6000x7f758e824a001310727075807928419216685274157407166852741237391668527449013716685274491846
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311688451688454194304256001224485120x7f75917ec4800x7f758e824a40655366610007404776016685274522915166852744901371668527485077516685274852344
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134168845168845419430425600824494720x7f75917ec3000x7f758e824a801310726710527523642416685274882923166852748507751668527512149416685275123115
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371688451688454194304256001224506880x7f75917ec1800x7f758e824ac01310726613807399839216685275154004166852751214941668527539525216685275396686
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401688451688454194304256001224516480x7f75917ec0000x7f758e824b001310726698687508375216685275437155166852753952521668527567269116685275674267
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431688451688454194304256001224528640x7f758f14de800x7f758e824b401310727548228456432816685275704336166852756726911668527603284916685276034525
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461688451688454194304256001224540800x7f758f14dd000x7f758e824b80655366762187582119216685276064324166852760328491668527638980816685276391503
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149168845168845419430425600824552960x7f758f14db800x7f758e824bc01310726987967833733616685276422252166852763898081668527666292616685276664494
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521688451688454194304256001224567680x7f758f14da000x7f758e824c001310727004987829043216685276695273166852766629261668527693604516685276937655
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551688451688454194304256001224577280x7f758f14d8800x7f758e824c401310726997647850997616685276975003166852769360451668527720948316685277211056
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581688451688454194304256001224589440x7f758f14d7000x7f758e824c801310726726027533812016685277241575166852772094831668527756964216685277571084
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611688451688454194304256001224601600x7f75917ec5800x7f758e824cc0655366626527419915216685277602483166852775696421668527792564016685277927342
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164168845168845419430425600824613760x7f75917ec4000x7f758e824d001310726955507787820816685277957691166852779256401668527820179816685278203563
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671688451688454194304256001224628480x7f75917ec2800x7f758e824d401310727085927942100016685278235442166852782017981668527848771716685278489203
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701688451688454194304256001224638080x7f75917ec1000x7f758e824d801310727048167897727216685278528632166852784877171668527876707616685278768724
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731688451688454194304256001224650240x7f758f14df800x7f758e824dc01310726869907702280016685278799913166852787670761668527912659416685279128242
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761688451688454194304256001224662400x7f758f14de000x7f758e824e00655366333027093308816685279159141166852791265941668527948387216685279485480
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179168845168845419430425600824674560x7f758f14dc800x7f758e824e401310727094587932484016685279515719166852794838721668527975427116685279755781
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821688451688454194304256001224689280x7f758f14db000x7f758e824e801310727020347863752816685279787010166852797542711668528003490916685280036582
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851688451688454194304256001224701440x7f758f14d9800x7f758e824ec01310726737067548194416685280075681166852800349091668528030514816685280306823
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881688451688454194304256001224716160x7f758f14d8000x7f758e824f001310727061847912131216685280337422166852803051481668528066466616685280666151
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911688451688454194304256001224728320x7f758f14d6800x7f758e824f40655366619187405795216685280696460166852806646661668528102178416685281023329
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194168845168845419430425600824740480x7f75917ec5000x7f758e824f801310726617667414642416685281053178166852810217841668528129890316685281300350
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971688451688454194304256001224757760x7f75917ec3800x7f758e824fc01310726809407621156816685281331199166852812989031668528158434116685281585970
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001688451688454194304256001224769920x7f75917ec2000x7f758e8250001310727017347867961616685281624219166852815843411668528185778016685281859541
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031688451688454194304256001224784640x7f75917ec0800x7f758e8250401310727054807903168816685281890250166852818577801668528221793816685282219519
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061688451688454194304256001224799360x7f758f14df000x7f758e825080655366679567488288016685282252258166852822179381668528257905716685282580887
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209168845168845419430425600824814080x7f758f14dd800x7f758e8250c01310727149548011331216685282610706166852825790571668528285185516685282853538
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121688451688454194304256001224831360x7f758f14dc000x7f758e8251001310727247588105262416685282884057166852828518551668528314273416685283144279
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151688451688454194304256001224843520x7f758f14da800x7f758e8251401310727090287951488816685283192887166852831427341668528341649216685283418170
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181688451688454194304256001224858240x7f758f14d9000x7f758e8251801310727042267895556016685283450359166852834164921668528377921016685283781008
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211688451688454194304256001224872960x7f758f14d7800x7f758e8251c0655366688367491100016685283811067166852837792101668528414256916685284144256
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241688451688454194304256001224887680x7f758f14d6000x7f758e8252001310726960987798533616685284173895166852841425691668528441680716685284418456
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271688451688454194304256001224907520x7f75917ec4800x7f758e8252401310727141187994264816685284450285166852844168071668528471856616685284720216
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301688451688454194304256001224919680x7f75917ec3000x7f758e8252801310727122587988853616685284757635166852847185661668528499088416685284992457
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331688451688454194304256001224934400x7f75917ec1800x7f758e8252c01310727003027844005616685285023316166852849908841668528535392316685285355485
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361688451688454194304256001224949120x7f75917ec0000x7f758e825300655366722187511152816685285386104166852853539231668528571088116685285712434
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391688451688454194304256001224963840x7f758f14de800x7f758e8253401310727098167953200016685285742313166852857108811668528598879916685285990434
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421688451688454194304256001224983680x7f758f14dd000x7f758e8253801310726991407831203216685286020173166852859887991668528630495816685286306804
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451688451688454194304256001224995840x7f758f14db800x7f758e8253c01310727060447905706416685286343783166852863049581668528658799616685286589484
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024816884516884541943042560012241013120x7f758f14da000x7f758e8254001310726703267515788816685286619073166852865879961668528695119516685286952702
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025116884516884541943042560012241027840x7f758f14d8800x7f758e825440655366697707500610416685286983291166852869511951668528730895316685287310700
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025416884516884541943042560012241042560x7f758f14d7000x7f758e8254801310726697787490923216685287340239166852873089531668528758687116685287588521
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025716884516884541943042560012241062400x7f75917ec5800x7f758e8254c01310726798247610051216685287618590166852875868711668528789615016685287897731
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026016884516884541943042560012241077120x7f75917ec4000x7f758e8255001310726622127422913616685287935550166852878961501668528816766916685288169282
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026316884516884541943042560016241094400x7f75917ec2800x7f758e8255401310727007007856818416685288199361166852881676691668528853422716685288535880
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026616884516884541943042560016241111680x7f75917ec1000x7f758e825580655366633127433672816685288566379166852885342271668528889006516685288891858
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691688451688454194304256008241128960x7f758f14df800x7f758e8255c01310727043567891767216685288922287166852888900651668528916382416685289165369
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027216884516884541943042560012241151360x7f758f14de000x7f758e8256001310727000187844430416685289195118166852891638241668528948206216685289483488
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027516884516884541943042560012241166080x7f758f14dc800x7f758e8256401310727083207936388016685289520737166852894820621668528975646116685289757999
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027816884516884541943042560016241183360x7f758f14db000x7f758e8256801310727042747881233616685289787648166852897564611668529012477916685290126667
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028116884516884541943042560016241200640x7f758f14d9800x7f758e8256c0655366595647402875216685290157576166852901247791668529049021716685290491795
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028416884516884541943042560012241217920x7f758f14d8000x7f758e8257001310727037927882454416685290521294166852904902171668529077213516685290773616
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028716884516884541943042560012241240320x7f758f14d6800x7f758e8257401310727019367847373616685290803585166852907721351668529109501416685291096625
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029016884516884541943042560012241255040x7f75917ec5000x7f758e8257801310727067827925449616685291133764166852910950141668529136813216685291369616
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029316884516884541943042560012241274880x7f75917ec3800x7f758e8257c01310727042707890567216685291400235166852913681321668529172829116685291729854
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029616884516884541943042560012241292160x7f75917ec2000x7f758e825800655366709887508136816685291760293166852917282911668529208524916685292086812
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029916884516884541943042560012241309440x7f75917ec0800x7f758e8258401310726774647586273616685292116971166852920852491668529236668716685292368123
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030216884516884541943042560012241334400x7f758f14df000x7f758e8258801310726719927529956016685292397962166852923666871668529270380616685292705461
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030516884516884541943042560012241349120x7f758f14dd800x7f758e8258c0131072104260011659068016685292743190166852927038061668529298460416685292986212
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030816884516884541943042560012241368960x7f758f14dc000x7f758e8259001310726649607446401616685293015911166852929846041668529334236316685293344050
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031116884516884541943042560012241388800x7f758f14da800x7f758e825940655366605827387540816685293373639166852933423631668529370172116685293703188
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031416884516884541943042560012241408640x7f758f14d9000x7f758e8259801310727022447874165616685293732897166852937017211668529398619916685293987639
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031716884516884541943042560012241436160x7f758f14d7800x7f758e8259c01310727021427860634416685294017228166852939861991668529434331816685294345087
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032016884516884541943042560012241453440x7f758f14d6000x7f758e825a00131072104817411754185616685294382696166852943433181668529462539616685294626878
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032316884516884541943042560012241475840x7f75917ec4800x7f758e825a401310727054327896313616685294656827166852946253961668529498587416685294987496
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032616884516884541943042560012241495680x7f75917ec3000x7f758e825a80655366625367410252016685295018225166852949858741668529534155316685295343284
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032916884516884541943042560012241515520x7f75917ec1800x7f758e825ac01310726653647445543216685295373003166852953415531668529563179116685295633394
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033216884516884541943042560012241543040x7f75917ec0000x7f758e825b001310727049807894567216685295663003166852956317911668529599706916685295998532
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033516884516884541943042560012241562880x7f758f14de800x7f758e825b40131072100134811211088816685296036221166852959970691668529628026816685296281893
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033816884516884541943042560012241587840x7f758f14dd000x7f758e825b801310727013507862040816685296311462166852962802681668529664202616685296643691
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034116884516884541943042560012241610240x7f758f14db800x7f758e825bc0655366662947456178416685296672900166852966420261668529700186416685297003689
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034416884516884541943042560012241632640x7f758f14da000x7f758e825c001310726583827375827216685297033398166852970018641668529730218316685297303609
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034716884516884541943042560012241665280x7f758f14d8800x7f758e825c401310726657247456663216685297333118166852973021831668529769258116685297712625
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035016884516884541943042560012241685120x7f758f14d7000x7f758e825c80131072104638211715451216685297731135166852976925811668529798953916685297991086
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035316884516884541943042560012241712640x7f75917ec5800x7f758e825cc01310726666487458992016685298021005166852979895391668529836105716685298362734
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035616884516884541943042560012241737600x7f75917ec4000x7f758e825d00655366695207497559216685298393893166852983610571668529872393616685298725492
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035916884516884541943042560012241762560x7f75917ec2800x7f758e825d401310726790627600953616685298755701166852987239361668529904201416685299043721
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036216884516884541943042560012241797760x7f75917ec1000x7f758e825d801310727073627925161616685299073690166852990420141668529945369216685299497876
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036516884516884541943042560012241822720x7f758f14df800x7f758e825dc0131072100243411216561616685299516225166852994536921668529979945016685299801036
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036816884516884541943042560012241855360x7f758f14de000x7f758e825e001310727083907944493616685299830895166852997994501668530017048816685300214692
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037116884516884541943042560012241885440x7f758f14dc800x7f758e825e40655366675787484907216685300224482166853001704881668530057688616685300618049
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037416884516884541943042560012241915520x7f758f14db000x7f758e825e801310726678727484396816685300628578166853005768861668530094600416685300947558
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037716884516884541943042560012241958400x7f758f14d9800x7f758e825ec01310726729747536068016685300977167166853009460041668530140904216685301427932
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038016884516884541943042560012241985920x7f758f14d8000x7f758e825f00131072103717011626857616685301448331166853014090421668530174088116685301742331
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038316884516884541943042560012242023680x7f758f14d6800x7f758e825f40131072100180011209974416685301772210166853017408811668530213111916685302149138
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038616884516884541943042560012242058880x7f75917ec5000x7f758e825f80655366532087317731216685302161878166853021311191668530253367716685302550585
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038916884516884541943042560012242094080x7f75917ec3800x7f758e825fc01310726690227499202416685302564854166853025336771668530290631516685302907843
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039216884516884541943042560012242144640x7f75917ec2000x7f758e8260001310726655787451177616685302938022166853029063151668530342087216685303437125
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039516884516884541943042560012242177280x7f75917ec0800x7f758e826040131072104895411743504816685303460494166853034208721668530377927016685303780964
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039816884516884541943042560012242220160x7f758f14df000x7f758e826080131072103090211555051216685303810643166853037792701668530419078816685304207240
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040116884516884541943042560012242260480x7f758f14dd800x7f758e8260c0655366705667509359216685304224039166853041907881668530460438616685304621546
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040416884516884541943042560012242300800x7f758f14dc000x7f758e8261001310726663807464311216685304635645166853046043861668530500070416685305018943
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040716884516884541943042560012242359040x7f758f14da800x7f758e8261401310726629567438227216685305032112166853050007041668530557302116685305589814
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041016884516884541943042560012242394240x7f758f14d9000x7f758e826180131072103740011624987216685305612373166853055730211668530594389916685305945332
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041316884516884541943042560012242442240x7f758f14d7800x7f758e8261c013107299226811114193616685305975511166853059438991668530638693716685306414076
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041616884516884541943042560012242487680x7f758f14d6000x7f758e826200655366673147471666416685306425376166853063869371668530683781516685306880801
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041916884516884541943042560012242533120x7f75917ec4800x7f758e8262401310726670567464012816685306891191166853068378151668530728709316685307329196
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221688451688454194304256008242555520x7f75917ec3000x7f758e826280131072104246211682927216685307339536166853072870931668530794900916685307992244
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042516884516884541943042560012242598400x7f75917ec1800x7f758e8262c0131072103782011627688816685308010913166853079490091668530838692716685308428390
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042816884516884541943042560012242656640x7f75917ec0000x7f758e82630013107298871211069582416685308439089166853083869271668530889732516685308938553
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043116884516884541943042560012242712320x7f758f14de800x7f758e826340655366628687431507216685308949092166853088973251668530940260216685309444736
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341688451688454194304256008242732160x7f758f14dd000x7f758e826380131072101582611381549616685309454566166853094026021668530990932016685309926050
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371688451688454194304256008242757120x7f758f14db800x7f758e8263c0131072103734211629624016685309940009166853099093201668531065443616685310698764
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044016884516884541943042560012242807680x7f758f14da000x7f758e826400131072100310011228429616685310716864166853106544361668531114051316685311184678
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044316884516884541943042560012242876160x7f758f14d8800x7f758e826440131072103857011648004016685311194838166853111405131668531170371116685311745849
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044616884516884541943042560012242942080x7f758f14d7000x7f758e826480655366709347519944016685311755859166853117037111668531226354816685312304971
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491688451688454194304256008242969600x7f75917ec5800x7f758e8264c0131072104509811717057616685312315391166853122635481668531282530516685312866452
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521688451688454194304256008242999680x7f75917ec4000x7f758e826500131072108636012162344016685312877172166853128253051668531369170116685313733554
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551688451688454194304256008243027200x7f75917ec2800x7f758e826540131072104451211683600816685313751943166853136917011668531434561716685314390692
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045816884516884541943042560012243054720x7f75917ec1000x7f758e826580131072104090611632789616685314401361166853143456171668531502353416685315067789
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046116884516884541943042560012243082240x7f758f14df800x7f758e8265c0655366976627823706416685315078099166853150235341668531569665116685315738377
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641688451688454194304256008243109760x7f758f14de000x7f758e826600131072103690211608327216685315748667166853156966511668531635456716685316395885
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671688451688454194304256008243132160x7f758f14dc800x7f758e826640131072103892611637376816685316405785166853163545671668531744688216685317491019
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701688451688454194304256008243159680x7f758f14db000x7f758e826680131072103892411625121616685317509938166853174469091668531852690416685318578773
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047316884516884541943042560012243187200x7f758f14d9800x7f758e8266c0131072102904011551780816685318589762166853185269041668531964849716685319715205
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047616884516884541943042560012243214720x7f758f14d8000x7f758e826700655366630687423335216685319725365166853196484971668532078833216685320854467
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791688451688454194304256008243242240x7f758f14d6800x7f758e826740131072104621011716395216685320864537166853207883321668532189264616685321955961
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821688451688454194304256008243264640x7f75917ec5000x7f758e826780131072104412611681130416685321966510166853218926461668532384239616685323909426
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851688451688454194304256008243292160x7f75917ec3800x7f758e8267c0131072104398011678359216685323927515166853238423961668532576046716685325831362
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048816884516884541943042560012243319680x7f75917ec2000x7f758e826800131072103786211599348816685325842122166853257604671668532773933716685327810026
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049116884516884541943042560012243347200x7f75917ec0800x7f758e826840655366689487494185616685327821406166853277393371668532971996716685329784841
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941688451688454194304256008243374720x7f758f14df000x7f758e826880131072103851611649032016685329795630166853297199671668533165067816685331721976
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049716884516884541943042560082400x7f758f14dd800x7f758e8268c0131072104342211708600016685331732436166853316506781668533526650016685335341486