Files
rocm-systems/tests/workloads/dev0/mi200/SQ_INST_LEVEL_LDS.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

38 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_LDSSQ_INST_LEVEL_LDSSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000225145225145335544322560043241600x00x7f601120428000017617373642292176166573580661761752151073017617521624110
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00222514522514532768256001224138880x00x7f6011223f8000017617526822058176175215107301761752694977217617526954185
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0052251452251454194304256001224143360x7f601422d3800x7f6011223fc000017617526989654176175269497721761752731617217617527318486
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0082251452251454194304256001624150400x7f601422d2000x7f601122400000017617527355035176175273161721761752771745217617527719416
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00112251452251454194304256001624154880x7f601422d0800x7f601122404000017617527752475176175277174521761752811217217617528114156
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00142251452251454194304256001224159360x7f6011acdf000x7f601122408000017617528147005176175281121721761752841905217617528421068
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00172251452251454194304256001224163840x7f6011acdd800x7f60112240c000017617528454017176175284190521761752871969217617528721660
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00202251452251454194304256001224170880x7f6011acdc000x7f601122410000017617528765359176175287196921761752901905217617529020973
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00232251452251454194304256001624177920x7f6011acda800x7f601122414000017617529052832176175290190521761752940737317617529409783
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00262251452251454194304256001624184960x7f6011acd9000x7f601122418000017617529441212176175294073731761752979665317617529798663
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00292251452251454194304256001624192000x7f6011acd7800x7f60112241c000017617529830222176175297966531761753011617317617530118345
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00322251452251454194304256001624199040x7f6011acd6000x7f601122420000017617530150604176175301161731761753042865317617530431017
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00352251452251454194304256001224206080x7f601422d4800x7f601122424000017617530470706176175304286531761753072529317617530726820
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00382251452251454194304256001624213120x7f601422d3000x7f601122428000017617530760449176175307252931761753108929317617531090840
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00412251452251454194304256001624220160x7f601422d1800x7f60112242c000017617531123289176175310892931761753145057317617531452141
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00442251452251454194304256001624227200x7f601422d0000x7f601122430000017617531484590176175314505731761753172529417617531726804
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00472251452251454194304256001224234240x7f6011acde800x7f601122434000017617531758603176175317252941761753200945417617532010787
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00502251452251454194304256001224241280x7f6011acdd000x7f601122438000017617532049466176175320094541761753228433417617532285800
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00532251452251454194304256001624248320x7f6011acdb800x7f60112243c000017617532318189176175322843341761753264609417617532647451
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00562251452251454194304256001624255360x7f6011acda000x7f601122440000017617532679750176175326460941761753300705417617533008542
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00592251452251454194304256001224262400x7f6011acd8800x7f601122444000017617533040051176175330070541761753328513417617533286845
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00622251452251454194304256001224269440x7f6011acd7000x7f601122448000017617533318864176175332851341761753355633417617533557708
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00652251452251454194304256001224276480x7f601422d5800x7f60112244c000017617533596337176175335563341761753382753417617533829061
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00682251452251454194304256001624286080x7f601422d4000x7f601122450000017617533860670176175338275341761753418961517617534191042
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00712251452251454194304256001624293120x7f601422d2800x7f601122454000017617534223531176175341896151761753455249517617534553882
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00742251452251454194304256001224300160x7f601422d1000x7f601122458000017617534584972176175345524951761753482865517617534830085
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077225145225145419430425600824309760x7f6011acdf800x7f60112245c000017617534862085176175348286551761753510289517617535104478
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00802251452251454194304256001224316800x7f6011acde000x7f601122460000017617535143677176175351028951761753537457517617535376091
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00832251452251454194304256001624326400x7f6011acdc800x7f601122464000017617535409341176175353745751761753573169517617535733162
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00862251452251454194304256001224336000x7f6011acdb000x7f601122468000017617535764342176175357316951761753608865517617536090333
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00892251452251454194304256001224345600x7f6011acd9800x7f60112246c000017617536122022176175360886551761753636545517617536367116
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092225145225145419430425600824355200x7f6011acd8000x7f601122470000017617536398155176175363654551761753665137517617536652909
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00952251452251454194304256001224362240x7f6011acd6800x7f601122474000017617536690968176175366513751761753692769617617536929142
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00982251452251454194304256001224371840x7f601422d5000x7f601122478000017617536961961176175369276961761753728785617617537289353
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001012251452251454194304256001224381440x7f601422d3800x7f60112247c000017617537321362176175372878561761753765009617617537651613
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001042251452251454194304256001224391040x7f601422d2000x7f601122480000017617537683823176175376500961761753792513617617537926746
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107225145225145419430425600824403200x7f601422d0800x7f601122484000017617537958656176175379251361761753820769617617538209129
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001102251452251454194304256001224412800x7f6011acdf000x7f601122488000017617538249708176175382076961761753848401617617538485432
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001132251452251454194304256001224422400x7f6011acdd800x7f60112248c000017617538518491176175384840161761753884465617617538846203
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001162251452251454194304256001224432000x7f6011acdc000x7f601122490000017617538877072176175388446561761753920817717617539209674
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119225145225145419430425600824441600x7f6011acda800x7f601122494000017617539241083176175392081771761753947889717617539480317
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001222251452251454194304256001224453760x7f6011acd9000x7f601122498000017617539511686176175394788971761753975025717617539751870
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001252251452251454194304256001224463360x7f6011acd7800x7f60112249c000017617539789489176175397502571761754002513717617540026513
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001282251452251454194304256001224475520x7f6011acd6000x7f6011224a0000017617540058182176175400251371761754038113717617540382644
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001312251452251454194304256001224485120x7f601422d4800x7f6011224a4000017617540414813176175403811371761754074001717617540741505
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134225145225145419430425600824494720x7f601422d3000x7f6011224a8000017617540773014176175407400171761754101233717617541013728
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001372251452251454194304256001224506880x7f601422d1800x7f6011224ac000017617541045667176175410123371761754128433717617541285751
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001402251452251454194304256001224516480x7f601422d0000x7f6011224b0000017617541323680176175412843371761754155905717617541560504
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001432251452251454194304256001224528640x7f6011acde800x7f6011224b4000017617541591823176175415590571761754191825817617541919735
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001462251452251454194304256001224540800x7f6011acdd000x7f6011224b8000017617541953424176175419182581761754229089817617542292496
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149225145225145419430425600824552960x7f6011acdb800x7f6011224bc000017617542323815176175422908981761754256545817617542566939
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001522251452251454194304256001224567680x7f6011acda000x7f6011224c0000017617542597968176175425654581761754283761817617542839042
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001552251452251454194304256001224577280x7f6011acd8800x7f6011224c4000017617542877741176175428376181761754311185817617543113295
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001582251452251454194304256001224589440x7f6011acd7000x7f6011224c8000017617543145394176175431118581761754346977817617543471166
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001612251452251454194304256001224601600x7f601422d5800x7f6011224cc000017617543502855176175434697781761754382897817617543830397
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164225145225145419430425600824613760x7f601422d4000x7f6011224d0000017617543861706176175438289781761754409969817617544101090
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001672251452251454194304256001224628480x7f601422d2800x7f6011224d4000017617544133159176175440996981761754437665917617544377983
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001702251452251454194304256001224638080x7f601422d1000x7f6011224d8000017617544417452176175443766591761754465633917617544657766
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001732251452251454194304256001224650240x7f6011acdf800x7f6011224dc000017617544689525176175446563391761754501729917617545018867
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001762251452251454194304256001224662400x7f6011acde000x7f6011224e0000017617545050856176175450172991761754537297917617545374468
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179225145225145419430425600824674560x7f6011acdc800x7f6011224e4000017617545405597176175453729791761754564337917617545644811
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001822251452251454194304256001224689280x7f6011acdb000x7f6011224e8000017617545676170176175456433791761754592993917617545931253
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001852251452251454194304256001224701440x7f6011acd9800x7f6011224ec000017617545968743176175459299391761754621073917617546212246
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001882251452251454194304256001224716160x7f6011acd8000x7f6011224f0000017617546243966176175462107391761754657505917617546576377
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001912251452251454194304256001224728320x7f6011acd6800x7f6011224f4000017617546608446176175465750591761754693538017617546936818
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194225145225145419430425600824740480x7f601422d5000x7f6011224f8000017617546967947176175469353801761754720706017617547208651
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001972251452251454194304256001224757760x7f601422d3800x7f6011224fc000017617547239860176175472070601761754749442017617547495814
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002002251452251454194304256001224769920x7f601422d2000x7f601122500000017617547534863176175474944201761754776738017617547768937
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002032251452251454194304256001224784640x7f601422d0800x7f601122504000017617547800396176175477673801761754813154017617548133078
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002062251452251454194304256001224799360x7f6011acdf000x7f601122508000017617548165057176175481315401761754849234017617548493869
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209225145225145419430425600824814080x7f6011acdd800x7f60112250c000017617548525858176175484923401761754876898017617548770372
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002122251452251454194304256001224831360x7f6011acdc000x7f601122510000017617548801051176175487689801761754906290017617549064304
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002152251452251454194304256001224843520x7f6011acda800x7f601122514000017617549113433176175490629001761754933746117617549338857
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002182251452251454194304256001224858240x7f6011acd9000x7f601122518000017617549370096176175493374611761754971074117617549712198
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002212251452251454194304256001224872960x7f6011acd7800x7f60112251c000017617549743687176175497107411761755007202117617550073539
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002242251452251454194304256001224887680x7f6011acd6000x7f601122520000017617550105618176175500720211761755035058117617550352101
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002272251452251454194304256001224907520x7f601422d4800x7f601122524000017617550383471176175503505811761755065090117617550652284
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002302251452251454194304256001224919680x7f601422d3000x7f601122528000017617550690823176175506509011761755093298117617550934397
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002332251452251454194304256001224934400x7f601422d1800x7f60112252c000017617550966226176175509329811761755129554117617551297107
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002362251452251454194304256001224949120x7f601422d0000x7f601122530000017617551329177176175512955411761755165890117617551660368
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002392251452251454194304256001224963840x7f6011acde800x7f601122534000017617551692067176175516589011761755193362217617551935011
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002422251452251454194304256001224983680x7f6011acdd000x7f601122538000017617551966931176175519336221761755223714217617552238644
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002452251452251454194304256001224995840x7f6011acdb800x7f60112253c000017617552277203176175522371421761755250978217617552511337
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024822514522514541943042560012241013120x7f6011acda000x7f601122540000017617552542106176175525097821761755286562217617552867108
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025122514522514541943042560012241027840x7f6011acd8800x7f601122544000017617552898317176175528656221761755322418217617553225649
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025422514522514541943042560012241042560x7f6011acd7000x7f601122548000017617553257078176175532241821761755349778217617553499362
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025722514522514541943042560012241062400x7f601422d5800x7f60112254c000017617553530831176175534977821761755382146217617553823013
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026022514522514541943042560012241077120x7f601422d4000x7f601122550000017617553861702176175538214621761755410066217617554102266
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026322514522514541943042560016241094400x7f601422d2800x7f601122554000017617554135076176175541006621761755446626317617554467857
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026622514522514541943042560016241111680x7f601422d1000x7f601122558000017617554500836176175544662631761755482642317617554827978
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002692251452251454194304256008241128960x7f6011acdf800x7f60112255c000017617554859567176175548264231761755510002317617555101551
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027222514522514541943042560012241151360x7f6011acde000x7f601122560000017617555132730176175551000231761755541458317617555416003
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027522514522514541943042560012241166080x7f6011acdc800x7f601122564000017617555454622176175554145831761755568738317617555688946
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027822514522514541943042560016241183360x7f6011acdb000x7f601122568000017617555719795176175556873831761755604370317617556045387
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028122514522514541943042560016241200640x7f6011acd9800x7f60112256c000017617556076296176175560437031761755640322317617556404758
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028422514522514541943042560012241217920x7f6011acd8000x7f601122570000017617556436007176175564032231761755667730317617556678691
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028722514522514541943042560012241240320x7f6011acd6800x7f601122574000017617556709920176175566773031761755700418417617557005703
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029022514522514541943042560012241255040x7f601422d5000x7f601122578000017617557047552176175570041841761755727746417617557278956
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029322514522514541943042560012241274880x7f601422d3800x7f60112257c000017617557310195176175572774641761755763538417617557636777
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029622514522514541943042560012241292160x7f601422d2000x7f601122580000017617557669036176175576353841761755799298417617557994588
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029922514522514541943042560012241309440x7f601422d0800x7f601122584000017617558025727176175579929841761755828418417617558285720
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030222514522514541943042560012241334400x7f6011acdf000x7f601122588000017617558317880176175582841841761755862418417617558625842
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030522514522514541943042560012241349120x7f6011acdd800x7f60112258c000017617558664591176175586241841761755889634417617558897775
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030822514522514541943042560012241368960x7f6011acdc000x7f601122590000017617558928904176175588963441761755925442417617559255826
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031122514522514541943042560012241388800x7f6011acda800x7f601122594000017617559287155176175592544241761755961042517617559611857
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031422514522514541943042560012241408640x7f6011acd9000x7f601122598000017617559643026176175596104251761755989186517617559893430
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031722514522514541943042560012241436160x7f6011acd7800x7f60112259c000017617559924479176175598918651761756024178517617560243271
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032022514522514541943042560012241453440x7f6011acd6000x7f6011225a0000017617560281790176175602417851761756051682517617560518504
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032322514522514541943042560012241475840x7f601422d4800x7f6011225a4000017617560549803176175605168251761756087538517617560876855
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032622514522514541943042560012241495680x7f601422d3000x7f6011225a8000017617560909014176175608753851761756123250517617561233876
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032922514522514541943042560012241515520x7f601422d1800x7f6011225ac000017617561265565176175612325051761756152034517617561522008
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033222514522514541943042560012241543040x7f601422d0000x7f6011225b0000017617561553348176175615203451761756187954617617561881059
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033522514522514541943042560012241562880x7f6011acde800x7f6011225b4000017617561919758176175618795461761756216130617617562162862
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033822514522514541943042560012241587840x7f6011acdd000x7f6011225b8000017617562196041176175621613061761756252610617617562527573
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034122514522514541943042560012241610240x7f6011acdb800x7f6011225bc000017617562559762176175625261061761756288626617617562887624
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034422514522514541943042560012241632640x7f6011acda000x7f6011225c0000017617562919813176175628862661761756319570617617563197286
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034722514522514541943042560012241665280x7f6011acd8800x7f6011225c4000017617563228415176175631957061761756358130617617563627295
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035022514522514541943042560012241685120x7f6011acd7000x7f6011225c8000017617563645865176175635813061761756390690617617563908268
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035322514522514541943042560012241712640x7f601422d5800x7f6011225cc000017617563940177176175639069061761756427074617617564272239
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035622514522514541943042560012241737600x7f601422d4000x7f6011225d0000017617564304178176175642707461761756463506717617564636509
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035922514522514541943042560012241762560x7f601422d2800x7f6011225d4000017617564668449176175646350671761756494914717617564950451
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036222514522514541943042560012241797760x7f601422d1000x7f6011225d8000017617564981881176175649491471761756536034717617565403230
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036522514522514541943042560012241822720x7f6011acdf800x7f6011225dc000017617565422010176175653603471761756571170717617565713132
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036822514522514541943042560012241855360x7f6011acde000x7f6011225e0000017617565744121176175657117071761756608402717617566086623
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037122514522514541943042560012241885440x7f6011acdc800x7f6011225e4000017617566118272176175660840271761756646242717617566485903
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037422514522514541943042560012241915520x7f6011acdb000x7f6011225e8000017617566498042176175664624271761756681858817617566820094
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037722514522514541943042560012241958400x7f6011acd9800x7f6011225ec000017617566851333176175668185881761756728130817617567302392
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038022514522514541943042560012241985920x7f6011acd8000x7f6011225f0000017617567321261176175672813081761756761778817617567619214
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038322514522514541943042560012242023680x7f6011acd6800x7f6011225f4000017617567650873176175676177881761756800946817617568029683
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038622514522514541943042560012242058880x7f601422d5000x7f6011225f8000017617568043053176175680094681761756840226817617568422443
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038922514522514541943042560012242094080x7f601422d3800x7f6011225fc000017617568435943176175684022681761756877650817617568777964
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039222514522514541943042560012242144640x7f601422d2000x7f601122600000017617568809754176175687765081761756929346817617569313371
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039522514522514541943042560012242177280x7f601422d0800x7f601122604000017617569334100176175692934681761756964690917617569648382
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039822514522514541943042560012242220160x7f6011acdf000x7f601122608000017617569679902176175696469091761757005842917617570097621
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040122514522514541943042560012242260480x7f6011acdd800x7f60112260c000017617570110081176175700584291761757050498917617570550000
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040422514522514541943042560012242300800x7f6011acdc000x7f601122610000017617570562439176175705049891761757093138917617570978869
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040722514522514541943042560012242359040x7f6011acda800x7f601122614000017617570991138176175709313891761757153122917617571573424
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041022514522514541943042560012242394240x7f6011acd9000x7f601122618000017617571592223176175715312291761757192563017617571927005
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041322514522514541943042560012242442240x7f6011acd7800x7f60112261c000017617571958424176175719256301761757235603017617572399003
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041622514522514541943042560012242487680x7f6011acd6000x7f601122620000017617572411482176175723560301761757281715017617572859911
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041922514522514541943042560012242533120x7f601422d4800x7f601122624000017617572871331176175728171501761757326435017617573306480
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004222251452251454194304256008242555520x7f601422d3000x7f601122628000017617573318479176175732643501761757392771017617573947643
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042522514522514541943042560012242598400x7f601422d1800x7f60112262c000017617573969173176175739277101761757434419017617574391252
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042822514522514541943042560012242656640x7f601422d0000x7f601122630000017617574403462176175743441901761757486147117617574905879
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043122514522514541943042560012242712320x7f6011acde800x7f601122634000017617574916769176175748614711761757537683117617575423176
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004342251452251454194304256008242732160x7f6011acdd000x7f601122638000017617575434706176175753768311761757588739117617575929613
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004372251452251454194304256008242757120x7f6011acdb800x7f60112263c000017617575941063176175758873911761757665315117617576695054
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044022514522514541943042560012242807680x7f6011acda000x7f601122640000017617576714243176175766531511761757712931217617577171232
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044322514522514541943042560012242876160x7f6011acd8800x7f601122644000017617577183371176175771293121761757769011217617577732907
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044622514522514541943042560012242942080x7f6011acd7000x7f601122648000017617577745047176175776901121761757825379217617578298543
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004492251452251454194304256008242969600x7f601422d5800x7f60112264c000017617578311273176175782537921761757881987217617578863899
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004522251452251454194304256008242999680x7f601422d4000x7f601122650000017617578875309176175788198721761757969219317617579737037
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004552251452251454194304256008243027200x7f601422d2800x7f601122654000017617579756256176175796921931761758035171317617580394280
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045822514522514541943042560012243054720x7f601422d1000x7f601122658000017617580405870176175803517131761758102371317617581066433
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046122514522514541943042560012243082240x7f6011acdf800x7f60112265c000017617581077973176175810237131761758170003317617581742536
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004642251452251454194304256008243109760x7f6011acde000x7f601122660000017617581753926176175817000331761758236067417617582407249
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004672251452251454194304256008243132160x7f6011acdc800x7f601122664000017617582419829176175823606741761758345763417617583504071
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004702251452251454194304256008243159680x7f6011acdb000x7f601122668000017617583524191176175834574731761758455507317617584626223
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047322514522514541943042560012243187200x7f6011acd9800x7f60112266c000017617584637902176175845550731761758569123317617585755844
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047622514522514541943042560012243214720x7f6011acd8000x7f601122670000017617585768084176175856912331761758681715317617586888225
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004792251452251454194304256008243242240x7f6011acd6800x7f601122674000017617586900485176175868171531761758793635317617588002997
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004822251452251454194304256008243264640x7f601422d5000x7f601122678000017617588015017176175879363531761758988563317617589953588
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004852251452251454194304256008243292160x7f601422d3800x7f60112267c000017617589973427176175898856331761759181203317617591884639
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048822514522514541943042560012243319680x7f601422d2000x7f601122680000017617591896388176175918120331761759380307317617593868648
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049122514522514541943042560012243347200x7f601422d0800x7f601122684000017617593880348176175938030731761759576595317617595838408
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004942251452251454194304256008243374720x7f6011acdf000x7f601122688000017617595851508176175957659531761759770051417617597768509
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049722514522514541943042560082400x7f6011acdd800x7f60112268c000017617597780579176175977005141761760130835417617601387817