Files
rocm-systems/tests/workloads/dev1/mi100/SQ_INST_LEVEL_SMEM.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

43 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_SMEMSQ_INST_LEVEL_SMEMSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000925952925957335544322560083264640x00x7f43b7c041804194304321299041131333612076418192507764120764184396400951207641843996489312076418440076455
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00292595292595732768256002424124800x00x7f43b7c3510051223098295640012076418454529462120764184548268201207641845483338012076418454838606
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0049259529259574194304256002424129280x7f43c79e49000x7f43b7c35140655361710042196200012076418454902736120764184551228181207641845525817712076418455262033
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0069259529259574194304256003624136320x7f43c79e48000x7f43b7c35180655361774922282645612076418455329128120764184554984961207641845575337512076418455821633
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0089259529259574194304256002824140800x7f43c79e47000x7f43b7c351c0655361767842254259212076418455853733120764184560565741207641845631177212076418456380852
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00109259529259574194304256002424145280x7f43c79e46000x7f43b7c35200655361748962233132812076418456408894120764184565925711207641845672889012076418456732746
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00129259529259574194304256002424149760x7f43c79e45000x7f43b7c35240655361885802406818412076418456775395120764184569538491207641845708664912076418457090140
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00149259529259574194304256002424154240x7f43c79e44000x7f43b7c352801310722483703191018412076418457169227120764184573421671207641845747640712076418457479925
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00169259529259574194304256002824161280x7f43c79e43000x7f43b7c352c01310722317622970755212076418457529877120764184576949661207641845795560412076418457997697
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00189259529259574194304256002824168320x7f43c79e4a000x7f43b7c35300655361774382260352812076418458021781120764184582120831207641845846568212076418458507554
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00209259529259574194304256002424175360x7f43c79e49000x7f43b7c353401310722506383207712812076418458530126120764184587180011207641845885160012076418458855150
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00229259529259574194304256002424182400x7f43c79e48000x7f43b7c353801310722508583208927212076418458903289120764184590800791207641845921591812076418459219858
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00249259529259574194304256002424189440x7f43c79e47000x7f43b7c353c01310722446603122494412076418459281823120764184594469571207641845958199612076418459585828
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00269259529259574194304256002824199040x7f43c79e46000x7f43b7c354001310722195462808812812076418459633787120764184598045551207641846006151412076418460130229
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00289259529259574194304256002824206080x7f43c79e45000x7f43b7c35440655361846342369096012076418460149565120764184603397531207641846058999112076418460657138
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00309259529259574194304256002424213120x7f43c79e44000x7f43b7c354801310722490903189268812076418460680011120764184608605501207641846099239012076418460996078
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00329259529259574194304256002424220160x7f43c79e43000x7f43b7c354c01310722587383304536012076418461045660120764184612184681207641846135126812076418461354945
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00349259529259574194304256002424227200x7f43c79e4a000x7f43b7c355001310722608223342108812076418461414746120764184615755871207641846170982612076418461713431
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00369259529259574194304256002824236800x7f43c79e49000x7f43b7c355401310722071522651662412076418461760409120764184619314251207641846218422412076418462252122
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00389259529259574194304256002824243840x7f43c79e48000x7f43b7c35580655361751682235744812076418462270296120764184624640621207641846271510112076418462782458
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00409259529259574194304256002424250880x7f43c79e47000x7f43b7c355c01310722651863413364812076418462808486120764184629923801207641846312805912076418463131987
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00429259529259574194304256002424257920x7f43c79e46000x7f43b7c356001310722649363400903212076418463181609120764184633509381207641846348709712076418463490914
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00449259529259574194304256002424264960x7f43c79e45000x7f43b7c356401310722422843117036812076418463552849120764184637157361207641846384581612076418463849360
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00469259529259574194304256002824277120x7f43c79e44000x7f43b7c356801310722305042951556812076418463897279120764184640726951207641846432885312076418464397699
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00489259529259574194304256002824284160x7f43c79e43000x7f43b7c356c0655361735042216819212076418464423918120764184646005321207641846485589112076418464923306
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00509259529259574194304256002424291200x7f43c79e4a000x7f43b7c357001310722444583160848012076418464950035120764184651341291207641846526308912076418465266774
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00529259529259574194304256002424300800x7f43c79e49000x7f43b7c357401310722657163392036012076418465315535120764184654795681207641846561348712076418465617275
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00549259529259574194304256002424307840x7f43c79e48000x7f43b7c357801310722444743143413612076418465677628120764184658387661207641846596820512076418465971964
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00569259529259574194304256002824320000x7f43c79e47000x7f43b7c357c01310722062402641936812076418466025995120764184662053241207641846646292312076418466504223
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00589259529259574194304256002824329600x7f43c79e46000x7f43b7c35800655361707502186446412076418466527607120764184667061221207641846699460012076418467062661
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00609259529259574194304256002424339200x7f43c79e45000x7f43b7c358401310722472443172103212076418467086606120764184672675591207641846739763812076418467401320
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00629259529259574194304256002424348800x7f43c79e44000x7f43b7c358801310722428463118476812076418467455832120764184676149171207641846775427712076418467757863
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00649259529259574194304256002424358400x7f43c79e43000x7f43b7c358c01310722485383185478412076418467817885120764184679782751207641846811235512076418468116720
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00669259529259574194304256002824373120x7f43c79e4a000x7f43b7c359001310722345843002343212076418468158688120764184683361941207641846859683212076418468663806
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00689259529259574194304256002824382720x7f43c79e49000x7f43b7c35940655361767722254759212076418468690807120764184688662711207641846911747012076418469185406
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00709259529259574194304256002424392320x7f43c79e48000x7f43b7c359801310722425503109600812076418469211133120764184693939491207641846953106812076418469534594
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00729259529259574194304256002424401920x7f43c79e47000x7f43b7c359c01310722622763368433612076418469583155120764184697456271207641846987890612076418469882461
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00749259529259574194304256002424411520x7f43c79e46000x7f43b7c35a001310722553823260932812076418469943194120764184701093051207641847024018412076418470244013
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00769259529259574194304256002824426240x7f43c79e45000x7f43b7c35a401310722155222759284812076418470295759120764184704595431207641847071506212076418470781762
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00789259529259574194304256002824435840x7f43c79e44000x7f43b7c35a80655361873822394490412076418470808221120764184709822611207641847123378012076418471302029
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00809259529259574194304256002424445440x7f43c79e43000x7f43b7c35ac01310722470023144940012076418471326354120764184715051381207641847163617812076418471639716
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00829259529259574194304256002424457600x7f43c79e4a000x7f43b7c35b001310722530883250225612076418471687866120764184718489771207641847198865612076418471992141
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00849259529259574194304256002424467200x7f43c79e49000x7f43b7c35b401310722560223274748812076418472056691120764184722187351207641847235409412076418472358031
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00869259529259574194304256002824484480x7f43c79e48000x7f43b7c35b801310722063942638592012076418472409717120764184725656131207641847283185212076418472898345
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00889259529259574194304256002824494080x7f43c79e47000x7f43b7c35bc0655361757322257532812076418472924073120764184731128101207641847336496912076418473433570
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00909259529259574194304256002424503680x7f43c79e46000x7f43b7c35c001310722453563126184812076418473456703120764184736344081207641847377168712076418473775244
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00929259529259574194304256002424515840x7f43c79e45000x7f43b7c35c401310722501163196720812076418473826500120764184739936061207641847413360512076418474137407
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00949259529259574194304256002424525440x7f43c79e44000x7f43b7c35c801310722527283233727212076418474197850120764184743609641207641847449616412076418474499681
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00969259529259574194304256002824542720x7f43c79e43000x7f43b7c35cc01310722133202728850412076418474551587120764184747113631207641847497456112076418475020438
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00989259529259574194304256002824554880x7f43c79e4a000x7f43b7c35d00655361766242250120812076418475048520120764184752267201207641847547999912076418475546876
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001009259529259574194304256002424567040x7f43c79e49000x7f43b7c35d401310722644903389267212076418475572915120764184757558381207641847588991712076418475893470
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001029259529259574194304256002424581760x7f43c79e48000x7f43b7c35d801310722522843224269612076418475941420120764184761043161207641847624479512076418476248971
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001049259529259574194304256002424593920x7f43c79e47000x7f43b7c35dc01310722274222920924012076418476309083120764184764687941207641847660527312076418476608890
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001069259529259574194304256002824613760x7f43c79e46000x7f43b7c35e001310722525483221407212076418476657380120764184768228721207641847708287112076418477150065
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001089259529259574194304256002824625920x7f43c79e45000x7f43b7c35e40655361752942236461612076418477173259120764184773535901207641847764286812076418477710166
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001109259529259574194304256002424638080x7f43c79e44000x7f43b7c35e801310722478983167868812076418477731957120764184779150271207641847805086612076418478054566
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001129259529259574194304256002424652800x7f43c79e43000x7f43b7c35ec01310722661743400119212076418478105230120764184782748651207641847841438512076418478417821
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001149259529259574194304256002424664960x7f43c79e4a000x7f43b7c35f001310722486963186689612076418478478344120764184786377441207641847877310312076418478776708
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001169259529259574194304256002824684800x7f43c79e49000x7f43b7c35f401310722465703153193612076418478823665120764184789878221207641847925566112076418479324296
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001189259529259574194304256002824696960x7f43c79e48000x7f43b7c35f80655362000682559861612076418479343872120764184795279791207641847977981812076418479846696
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001209259529259574194304256002424709120x7f43c79e47000x7f43b7c35fc01310722722303496842412076418479872484120764184800495771207641848018189612076418480185887
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001229259529259574194304256002424723840x7f43c79e46000x7f43b7c360001310722459383119780012076418480235940120764184804006151207641848054141412076418480544994
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001249259529259574194304256002424736000x7f43c79e45000x7f43b7c360401310722497783202660012076418480604825120764184807673331207641848089933312076418480902859
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001269259529259574194304256002824758400x7f43c79e44000x7f43b7c360801310722054102637042412076418480951690120764184811278111207641848139149012076418481439757
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001289259529259574194304256002824770560x7f43c79e43000x7f43b7c360c0655361730322219704812076418481464813120764184816466891207641848190124812076418481949654
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001309259529259574194304256002424782720x7f43c79e4a000x7f43b7c361001310722443343136328012076418481971755120764184821559661207641848228940612076418482292992
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001329259529259574194304256002424800000x7f43c79e49000x7f43b7c361401310722079662672692012076418482341572120764184825082851207641848265292412076418482656748
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001349259529259574194304256002424812160x7f43c79e48000x7f43b7c361801310722466663150874412076418482716739120764184828762831207641848301340212076418483017488
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001369259529259574194304256002824834560x7f43c79e47000x7f43b7c361c01310722109082676976812076418483067090120764184832354811207641848349612012076418483545840
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001389259529259574194304256002824849280x7f43c79e46000x7f43b7c36200655361716202188210412076418483568512120764184837461991207641848400091712076418484023678
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001409259529259574194304256002424864000x7f43c79e45000x7f43b7c362401310722464823137386412076418484071256120764184842325961207641848436779612076418484371685
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001429259529259574194304256002424881280x7f43c79e44000x7f43b7c362801310722060982632325612076418484424212120764184845865151207641848473691412076418484740720
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001449259529259574194304256002424896000x7f43c79e43000x7f43b7c362c01310722451963144803212076418484818575120764184849762731207641848510859212076418485112732
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001469259529259574194304256002824920960x7f43c79e4a000x7f43b7c363001310722173182773579212076418485162674120764184853335511207641848560299012076418485651984
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001489259529259574194304256002824935680x7f43c79e49000x7f43b7c36340655361723922195929612076418485675327120764184858517881207641848611002712076418486160348
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001509259529259574194304256002424950400x7f43c79e48000x7f43b7c363801310722417123106898412076418486184303120764184863636261207641848649738512076418486500721
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001529259529259574194304256002424967680x7f43c79e47000x7f43b7c363c01310722460723152728812076418486549722120764184867097041207641848686714312076418486870859
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001549259529259574194304256002424982400x7f43c79e46000x7f43b7c364001310722729983489786412076418486933866120764184871025021207641848723802212076418487241708
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015692595292595741943042560028241007360x7f43c79e45000x7f43b7c364401310722088222678048012076418487293684120764184874516211207641848771721912076418487739763
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015892595292595741943042560028241022080x7f43c79e44000x7f43b7c36480655361722502209584812076418487786941120764184879485781207641848820601712076418488255972
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016092595292595741943042560024241036800x7f43c79e43000x7f43b7c364c01310722741523501541612076418488282181120764184884597761207641848859641512076418488599791
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016292595292595741943042560024241056640x7f43c79e4a000x7f43b7c365001310722587143306707212076418488649854120764184888191341207641848898457312076418488988323
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016492595292595741943042560024241071360x7f43c79e49000x7f43b7c365401310722433243119428812076418489050389120764184892111321207641848934601112076418489349995
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016692595292595741943042560028241098880x7f43c79e48000x7f43b7c365801310722317102971944012076418489394999120764184895685701207641848983112912076418489880080
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016892595292595741943042560028241113600x7f43c79e47000x7f43b7c365c0655361748022244288012076418489905548120764184901074481207641849035960612076418490407651
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017092595292595741943042560024241128320x7f43c79e46000x7f43b7c366001310722500023193334412076418490430733120764184906082451207641849074232512076418490746210
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017292595292595741943042560024241148160x7f43c79e45000x7f43b7c366401310722479483193068812076418490796233120764184909525631207641849112696312076418491130814
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017492595292595741943042560024241162880x7f43c79e44000x7f43b7c366801310722486923167542412076418491191908120764184913517621207641849148920112076418491492947
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017692595292595741943042560028241190400x7f43c79e43000x7f43b7c366c01310722226262836002412076418491540856120764184917060001207641849196327912076418492018173
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017892595292595741943042560028241207680x7f43c79e4a000x7f43b7c36700655361720842197832812076418492041567120764184922240771207641849247559612076418492524624
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018092595292595741943042560024241224960x7f43c79e49000x7f43b7c367401310722481863185667212076418492547156120764184927287151207641849286375412076418492867281
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018292595292595741943042560024241247360x7f43c79e48000x7f43b7c367801310722583843317825612076418492919759120764184930866331207641849326887212076418493272935
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018492595292595741943042560024241264640x7f43c79e47000x7f43b7c367c01310722494443202014412076418493334209120764184934931911207641849363143012076418493635258
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018692595292595741943042560020241279360x7f43c79e46000x7f43b7c368001310722417383116136812076418493675272120764184938515891207641849411878812076418494167467
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018892595292595741943042560028241296640x7f43c79e45000x7f43b7c36840655361944702495623212076418494194066120764184943703071207641849462454612076418494671714
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019092595292595741943042560024241313920x7f43c79e44000x7f43b7c368801310722504403193656012076418494697412120764184948736641207641849501318412076418495017346
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019292595292595741943042560024241336320x7f43c79e43000x7f43b7c368c01310722502903207932812076418495067029120764184952287031207641849542134212076418495468124
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019492595292595741943042560024241353600x7f43c79e4a000x7f43b7c369001310722733283489799212076418495506565120764184956666211207641849580342012076418495807134
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019692595292595741943042560020241368320x7f43c79e49000x7f43b7c369401310722493323204081612076418495852668120764184960258191207641849631173712076418496340415
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019892595292595741943042560028241385600x7f43c79e48000x7f43b7c36980655361967062514672012076418496381201120764184965426161207641849680437512076418496828792
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020092595292595741943042560024241402880x7f43c79e47000x7f43b7c369c01310722535983255468812076418496870580120764184970326941207641849716917312076418497173042
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020292595292595741943042560024241427840x7f43c79e46000x7f43b7c36a001310722567203280016812076418497225560120764184973848521207641849759509112076418497619401
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020492595292595741943042560024241447680x7f43c79e45000x7f43b7c36a401310722687843439011212076418497674604120764184978325301207641849797028912076418497974271
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020692595292595741943042560020241457280x7f43c79e44000x7f43b7c36a801310722676183429508012076418498030646120764184981904481207641849849876712076418498526227
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020892595292595741943042560028241477120x7f43c79e43000x7f43b7c36ac0655361848002363830412076418498565079120764184987274061207641849898244412076418499013332
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021092595292595741943042560024241496960x7f43c79e4a000x7f43b7c36b001310722452423141440012076418499055129120764184992176431207641849935684312076418499360687
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021292595292595741943042560024241521920x7f43c79e49000x7f43b7c36b401310722503483221616012076418499411932120764184995701211207641849979812012076418499818999
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021492595292595741943042560024241541760x7f43c79e48000x7f43b7c36b801310722524163218863212076418499874913120764185000440391207641850017827912076418500182524
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021692595292595741943042560020241556480x7f43c79e47000x7f43b7c36bc01310722594943316020812076418500230984120764185004041971207641850073651612076418500760999
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021892595292595741943042560028241576320x7f43c79e46000x7f43b7c36c00655361793882301428012076418500808588120764185009691551207641850126067312076418501291415
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022092595292595741943042560024241596160x7f43c79e45000x7f43b7c36c401310722432323153453612076418501332301120764185014937921207641850163171112076418501635514
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022292595292595741943042560024241623680x7f43c79e44000x7f43b7c36c801310722446003140737612076418501684816120764185018464301207641850209202912076418502117660
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022492595292595741943042560024241646080x7f43c79e43000x7f43b7c36cc01310722513803231392012076418502172723120764185023371481207641850247874712076418502482488
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022692595292595741943042560020241663360x7f43c79e4a000x7f43b7c36d001310722445403117632012076418502530577120764185026973021207641850307442112076418503103482
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022892595292595741943042560028241685760x7f43c79e49000x7f43b7c36d40655361864202385796812076418503148436120764185033088191207641850357105712076418503594925
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023092595292595741943042560024241708160x7f43c79e48000x7f43b7c36d801310722424243102604012076418503642824120764185038052961207641850394225612076418503945607
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023292595292595741943042560024241740800x7f43c79e47000x7f43b7c36dc01310722502543187340012076418503994618120764185041708951207641850445057412076418504476834
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023492595292595741943042560024241765760x7f43c79e46000x7f43b7c36e001310722351243018584012076418504535102120764185046950531207641850483073212076418504834328
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023692595292595741943042560020241777920x7f43c79e45000x7f43b7c36e401310722297482925212012076418504882017120764185050544111207641850550224912076418505530752
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023892595292595741943042560028241802880x7f43c79e44000x7f43b7c36e80655361769222265176012076418505572610120764185057360081207641850599888712076418506023789
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024092595292595741943042560024241827840x7f43c79e43000x7f43b7c36ec01310722450983144733612076418506075384120764185062376061207641850637664512076418506380081
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024292595292595741943042560024241863040x7f43c79e4a000x7f43b7c36f001310722683183433872812076418506429883120764185065923251207641850690720312076418506931385
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024492595292595741943042560024241893120x7f43c79e49000x7f43b7c36f401310722543003250188812076418506987579120764185071544021207641850730768212076418507311040
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024692595292595741943042560020241907840x7f43c79e48000x7f43b7c36f801310722502243188783212076418507363127120764185075216011207641850804127812076418508067376
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024892595292595741943042560028241937920x7f43c79e47000x7f43b7c36fc0655361995922548564012076418508109133120764185082692771207641850857087612076418508595287
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025092595292595741943042560024241968000x7f43c79e46000x7f43b7c370001310722629483358044012076418508637385120764185087963151207641850895119412076418508954554
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025292595292595741943042560024242010880x7f43c79e45000x7f43b7c370401310722592103317572012076418509009056120764185091860731207641850957295212076418509600605
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025492595292595741943042560024242046080x7f43c79e44000x7f43b7c370801310722525583233528812076418509652912120764185098126311207641850998911012076418509992834
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025692595292595741943042560020242060800x7f43c79e43000x7f43b7c370c01310722412083106616812076418510040402120764185102091091207641851082110612076418510849826
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025892595292595741943042560028242096000x7f43c79e4a000x7f43b7c37100655361743722225566412076418510889039120764185110558251207641851138686412076418511412472
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026092595292595741943042560024242131200x7f43c79e49000x7f43b7c371401310722491583205358412076418511453909120764185116132631207641851183118212076418511855355
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026292595292595741943042560024242181760x7f43c79e48000x7f43b7c371801310722703623464945612076418511906049120764185120763011207641851253229912076418512560295
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026492595292595741943042560024242222080x7f43c79e47000x7f43b7c371c01310722489803217934412076418512612542120764185127738981207641851297469712076418512997898
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026692595292595741943042560020242239360x7f43c79e46000x7f43b7c372001310722491323189536012076418513048321120764185132095761207641851391965312076418513969303
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026892595292595741943042560028242279680x7f43c79e45000x7f43b7c37240655361753642235300812076418513993147120764185141862121207641851456045012076418514609242
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027092595292595741943042560024242320000x7f43c79e44000x7f43b7c372801310722537243248794412076418514631674120764185148180491207641851502284812076418515048959
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027292595292595741943042560024242378240x7f43c79e43000x7f43b7c372c01310722606903330192012076418515091899120764185152543671207641851578108512076418515828277
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027492595292595741943042560024242423680x7f43c79e4a000x7f43b7c373001310722629403353528812076418515866879120764185160391641207641851626348312076418516313328
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027692595292595741943042560020242435840x7f43c79e49000x7f43b7c373401310722467323157889612076418516340048120764185165182021207641851731803912076418517367537
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027892595292595741943042560028242481280x7f43c79e48000x7f43b7c37380655361772922258166412076418517396822120764185175735581207641851799451612076418518044686
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028092595292595741943042560024242526720x7f43c79e47000x7f43b7c373c01310722641583394630412076418518074611120764185182554751207641851848363412076418518532943
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028292595292595741943042560024242592640x7f43c79e46000x7f43b7c374001310722532283223148812076418518559402120764185187341931207641851934475012076418519394103
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028492595292595741943042560024242648320x7f43c79e45000x7f43b7c374401310722492243205779212076418519432104120764185195953091207641851986346812076418519912156
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028692595292595741943042560020242663040x7f43c79e44000x7f43b7c374801310722594403335966412076418519937292120764185201311471207641852111578212076418521185612
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028892595292595741943042560028242718720x7f43c79e43000x7f43b7c374c0655361741602224953612076418521216409120764185213985011207641852193049912076418521997942
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029092595292595741943042560024242774400x7f43c79e4a000x7f43b7c375001310722639803369133612076418522031083120764185222072981207641852248041712076418522549226
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029292595292595741943042560012242799360x7f43c79e49000x7f43b7c375401310722856303660790412076418522575345120764185227517751207641852349129212076418523559674
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029492595292595741943042560024242865280x7f43c79e48000x7f43b7c375801310722537323240272012076418523602603120764185237708111207641852408713012076418524155882
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029692595292595741943042560020242880000x7f43c79e47000x7f43b7c375c01310722601643331772012076418524187280120764185243661681207641852553672312076418525605545
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029892595292595741943042560032242945920x7f43c79e46000x7f43b7c37600655361845582344756812076418525636543120764185258109621207641852642008012076418526489949
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030092595292595741943042560024243011840x7f43c79e45000x7f43b7c376401310722482103178076812076418526521337120764185267021581207641852702247712076418527090875
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030292595292595741943042560012243049600x7f43c79e44000x7f43b7c376801310722532463224736812076418527120721120764185273002361207641852818007212076418528249228
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030492595292595741943042560024243136000x7f43c79e43000x7f43b7c376c01310722448123141172012076418528292238120764185284555911207641852886646912076418528932888
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030692595292595741943042560020243148160x7f43c79e4a000x7f43b7c377001310722478343182725612076418528957093120764185291496681207641853069702112076418530765944
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030892595292595741943042560020243175680x7f43c79e49000x7f43b7c37740655361849902356164812076418530797142120764185309779801207641853177477712076418531843887
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031092595292595741943042560012243203200x7f43c79e48000x7f43b7c377801310722454603157353612076418531867241120764185320590961207641853247445412076418532542636
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031292595292595741943042560012243240960x7f43c79e47000x7f43b7c377c01310722448303117276812076418532566480120764185327451731207641853390628812076418533973274
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031492595292595741943042560012243288960x7f43c79e46000x7f43b7c378001310722499943228264812076418534017927120764185341805261207641853496756312076418535036350
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031692595292595741943042560020243301120x7f43c79e45000x7f43b7c378401310722647943387251212076418535070132120764185352440421207641853829490912076418538363262
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031892595292595741943042560020243328640x7f43c79e44000x7f43b7c37880655361813022330283212076418538395001120764185385739481207641854011634112076418540184826
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032092595292595741943042560012243356160x7f43c79e43000x7f43b7c378c01310722491843202068012076418540215313120764185403947401207641854118609612076418541254825
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032292595292595741943042560012243393920x7f43c79e4a000x7f43b7c379001310722440243126136812076418541290551120764185414721751207641854375520512076418543823919
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032492595292595741943042560012243441920x7f43c79e49000x7f43b7c379401310722756203512598412076418543867510120764185440390441207641854557583812076418545646405
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032692595292595741943042560020243454080x7f43c79e48000x7f43b7c379801310722514543196827212076418545677964120764185458529571207641855190765112076418551977009
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032892595292595741943042560020243481600x7f43c79e47000x7f43b7c379c0655362015702589301612076418552013767120764185521956491207641855524107612076418555311264
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033092595292595741943042560012243509120x7f43c79e46000x7f43b7c37a001310722552943256962412076418555340629120764185555189951207641855705802912076418557127630
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332925952925957419430425600122400x7f43c79e45000x7f43b7c37a401310722478863167540012076418557157275120764185573381871207641856186664812076418561939611