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

40 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_LDSSQ_INST_LEVEL_LDSSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000891318891323335544322560083264640x00x7fc0d7a0418000012075752974042678120757532217336521207575322206021112075753222176363
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00289131889132332768256002424124800x00x7fc0d7a3510000012075753236901319120757532372187451207575323722530512075753237239437
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0048913188913234194304256002424129280x7fc207c549000x7fc0d7a3514000012075753237289390120757532375501031207575323768962312075753237693862
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0068913188913234194304256003624136320x7fc207c548000x7fc0d7a3518000012075753237762269120757532379589011207575323821346012075753238286703
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0088913188913234194304256002824140800x7fc207c547000x7fc0d7a351c000012075753238322139120757532385456191207575323880305812075753238873684
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00108913188913234194304256002424145280x7fc207c546000x7fc0d7a3520000012075753238901356120757532391297761207575323926865612075753239272275
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00128913188913234194304256002424149760x7fc207c545000x7fc0d7a3524000012075753239322809120757532395345751207575323967249412075753239676196
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00148913188913234194304256002424154240x7fc207c544000x7fc0d7a3528000012075753239750063120757532399321731207575324006433212075753240067863
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00168913188913234194304256002824161280x7fc207c543000x7fc0d7a352c000012075753240116454120757532403350511207575324062881012075753240674902
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00188913188913234194304256002824168320x7fc207c54a000x7fc0d7a3530000012075753240701922120757532409289691207575324118080812075753241226076
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00208913188913234194304256002424175360x7fc207c549000x7fc0d7a3534000012075753241253727120757532415006461207575324163296612075753241636569
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00228913188913234194304256002424182400x7fc207c548000x7fc0d7a3538000012075753241690810120757532418990451207575324203376412075753242037444
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00248913188913234194304256002424189440x7fc207c547000x7fc0d7a353c000012075753242101874120757532423004831207575324243008212075753242434281
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00268913188913234194304256002824199040x7fc207c546000x7fc0d7a3540000012075753242480888120757532426974411207575324294496012075753243020912
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00288913188913234194304256002824206080x7fc207c545000x7fc0d7a3544000012075753243049645120757532432732791207575324353151712075753243602312
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00308913188913234194304256002424213120x7fc207c544000x7fc0d7a3548000012075753243629563120757532438623961207575324399071612075753243994210
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00328913188913234194304256002424220160x7fc207c543000x7fc0d7a354c000012075753244042510120757532442558341207575324439055412075753244394595
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00348913188913234194304256002424227200x7fc207c54a000x7fc0d7a3550000012075753244456510120757532446582331207575324479135212075753244795039
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00368913188913234194304256002824236800x7fc207c549000x7fc0d7a3554000012075753244841245120757532450572711207575324531391012075753245385456
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00388913188913234194304256002824243840x7fc207c548000x7fc0d7a3558000012075753245412236120757532456427081207575324589854712075753245942381
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00408913188913234194304256002424250880x7fc207c547000x7fc0d7a355c000012075753245967748120757532462033461207575324633726512075753246341232
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00428913188913234194304256002424257920x7fc207c546000x7fc0d7a3560000012075753246389332120757532466038241207575324673710412075753246740975
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00448913188913234194304256002424264960x7fc207c545000x7fc0d7a3564000012075753246800035120757532470041431207575324713422212075753247138314
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00468913188913234194304256002824277120x7fc207c544000x7fc0d7a3568000012075753247191593120757532474012611207575324765150012075753247722289
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00488913188913234194304256002824284160x7fc207c543000x7fc0d7a356c000012075753247748287120757532479686181207575324822333712075753248294392
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00508913188913234194304256002424291200x7fc207c54a000x7fc0d7a3570000012075753248323927120757532485457361207575324867645512075753248680159
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00528913188913234194304256002424300800x7fc207c549000x7fc0d7a3574000012075753248726836120757532489428541207575324907949412075753249083609
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00548913188913234194304256002424307840x7fc207c548000x7fc0d7a3578000012075753249145033120757532493473321207575324947501212075753249479144
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00568913188913234194304256002824320000x7fc207c547000x7fc0d7a357c000012075753249526282120757532497391711207575324999309012075753250064382
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00588913188913234194304256002824329600x7fc207c546000x7fc0d7a3580000012075753250092063120757532503202881207575325057756712075753250649359
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00608913188913234194304256002424339200x7fc207c545000x7fc0d7a3584000012075753250675948120757532508956461207575325102828512075753251032060
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00628913188913234194304256002424348800x7fc207c544000x7fc0d7a3588000012075753251084337120757532512940441207575325143420312075753251438255
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00648913188913234194304256002424358400x7fc207c543000x7fc0d7a358c000012075753251498146120757532516988421207575325183052212075753251834962
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00668913188913234194304256002824373120x7fc207c54a000x7fc0d7a3590000012075753251881929120757532521095611207575325240907912075753252480281
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00688913188913234194304256002824382720x7fc207c549000x7fc0d7a3594000012075753252506871120757532527316381207575325299147712075753253061862
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00708913188913234194304256002424392320x7fc207c548000x7fc0d7a3598000012075753253088382120757532533113151207575325345131512075753253454933
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00728913188913234194304256002424401920x7fc207c547000x7fc0d7a359c000012075753253502972120757532537167541207575325385723312075753253861058
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00748913188913234194304256002424411520x7fc207c546000x7fc0d7a35a0000012075753253919937120757532541234721207575325425707112075753254260881
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00768913188913234194304256002824426240x7fc207c545000x7fc0d7a35a4000012075753254308629120757532545271501207575325478442912075753254855355
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00788913188913234194304256002824435840x7fc207c544000x7fc0d7a35a8000012075753254882336120757532551258681207575325538570612075753255456963
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00808913188913234194304256002424445440x7fc207c543000x7fc0d7a35ac000012075753255486318120757532557063451207575325584122412075753255844995
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00828913188913234194304256002424457600x7fc207c54a000x7fc0d7a35b0000012075753255895809120757532561237831207575325625962312075753256263472
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00848913188913234194304256002424467200x7fc207c549000x7fc0d7a35b4000012075753256324165120757532565237821207575325665786112075753256661903
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00868913188913234194304256002824484480x7fc207c548000x7fc0d7a35b8000012075753256707668120757532569196201207575325719177912075753257262910
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00888913188913234194304256002824494080x7fc207c547000x7fc0d7a35bc000012075753257288327120757532575140171207575325781193612075753257856122
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00908913188913234194304256002424503680x7fc207c546000x7fc0d7a35c0000012075753257880748120757532581034551207575325823689412075753258241178
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00928913188913234194304256002424515840x7fc207c545000x7fc0d7a35c4000012075753258288786120757532585047331207575325864457212075753258648735
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00948913188913234194304256002424525440x7fc207c544000x7fc0d7a35c8000012075753258712724120757532589084111207575325904201112075753259045843
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00968913188913234194304256002824542720x7fc207c543000x7fc0d7a35cc000012075753259094624120757532593122501207575325958184812075753259652601
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00988913188913234194304256002824554880x7fc207c54a000x7fc0d7a35d0000012075753259678850120757532599002471207575326015896612075753260230104
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001008913188913234194304256002424567040x7fc207c549000x7fc0d7a35d4000012075753260258327120757532604759241207575326060632412075753260610151
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001028913188913234194304256002424581760x7fc207c548000x7fc0d7a35d8000012075753260658811120757532608757631207575326101784212075753261021605
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001048913188913234194304256002424593920x7fc207c547000x7fc0d7a35dc000012075753261083009120757532612772011207575326140504012075753261408955
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001068913188913234194304256002824613760x7fc207c546000x7fc0d7a35e0000012075753261455371120757532616683991207575326193879812075753261984815
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001088913188913234194304256002824625920x7fc207c545000x7fc0d7a35e4000012075753262016073120757532622394371207575326249687612075753262541590
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001108913188913234194304256002424638080x7fc207c544000x7fc0d7a35e8000012075753262567157120757532628075941207575326293815412075753262941774
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001128913188913234194304256002424652800x7fc207c543000x7fc0d7a35ec000012075753262989042120757532632146331207575326335607212075753263360221
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001148913188913234194304256002424664960x7fc207c54a000x7fc0d7a35f0000012075753263418159120757532636242311207575326375623012075753263760185
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001168913188913234194304256002824684800x7fc207c549000x7fc0d7a35f4000012075753263809276120757532640272691207575326428950812075753264361111
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001188913188913234194304256002824696960x7fc207c548000x7fc0d7a35f8000012075753264388041120757532646136671207575326487094612075753264942532
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001208913188913234194304256002424709120x7fc207c547000x7fc0d7a35fc000012075753264967859120757532652040641207575326534022412075753265343948
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001228913188913234194304256002424723840x7fc207c546000x7fc0d7a3600000012075753265392378120757532656133421207575326575174212075753265755934
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001248913188913234194304256002424736000x7fc207c545000x7fc0d7a3604000012075753265817628120757532660128611207575326614278012075753266146540
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001268913188913234194304256002824758400x7fc207c544000x7fc0d7a3608000012075753266195080120757532664080591207575326667717812075753266747436
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001288913188913234194304256002824770560x7fc207c543000x7fc0d7a360c000012075753266772222120757532669958961207575326724933512075753267321774
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001308913188913234194304256002424782720x7fc207c54a000x7fc0d7a3610000012075753267348103120757532675742941207575326771077312075753267714624
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001328913188913234194304256002424800000x7fc207c549000x7fc0d7a3614000012075753267763945120757532679790921207575326812341212075753268127742
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001348913188913234194304256002424812160x7fc207c548000x7fc0d7a3618000012075753268189737120757532683845301207575326852101012075753268525350
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001368913188913234194304256002824834560x7fc207c547000x7fc0d7a361c000012075753268571246120757532687822891207575326905524812075753269126418
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001388913188913234194304256002824849280x7fc207c546000x7fc0d7a3620000012075753269151474120757532693773261207575326963044512075753269701326
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001408913188913234194304256002424864000x7fc207c545000x7fc0d7a3624000012075753269729939120757532699493241207575327008084312075753270085019
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001428913188913234194304256002424881280x7fc207c544000x7fc0d7a3628000012075753270134571120757532703517221207575327050212112075753270505981
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001448913188913234194304256002424896000x7fc207c543000x7fc0d7a362c000012075753270586371120757532707693201207575327090292012075753270907007
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001468913188913234194304256002824920960x7fc207c54a000x7fc0d7a3630000012075753270956569120757532711736381207575327144339712075753271514165
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001488913188913234194304256002824935680x7fc207c549000x7fc0d7a3634000012075753271540284120757532717645161207575327202403512075753272095305
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001508913188913234194304256002424950400x7fc207c548000x7fc0d7a3638000012075753272121364120757532723571531207575327249187312075753272495519
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001528913188913234194304256002424967680x7fc207c547000x7fc0d7a363c000012075753272543147120757532727574721207575327291587112075753272919687
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001548913188913234194304256002424982400x7fc207c546000x7fc0d7a3640000012075753272979769120757532731872301207575327332146912075753273325041
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015689131889132341943042560028241007360x7fc207c545000x7fc0d7a3644000012075753273372018120757532735877081207575327385714712075753273928001
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015889131889132341943042560028241022080x7fc207c544000x7fc0d7a3648000012075753273952376120757532741835451207575327444594412075753274490296
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016089131889132341943042560024241036800x7fc207c543000x7fc0d7a364c000012075753274514321120757532747389031207575327487714212075753274880972
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016289131889132341943042560024241056640x7fc207c54a000x7fc0d7a3650000012075753274928641120757532751517011207575327531810112075753275322332
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016489131889132341943042560024241071360x7fc207c549000x7fc0d7a3654000012075753275380771120757532755817791207575327571473912075753275718909
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016689131889132341943042560028241098880x7fc207c548000x7fc0d7a3658000012075753275764574120757532759800181207575327625329712075753276323613
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016889131889132341943042560028241113600x7fc207c547000x7fc0d7a365c000012075753276349802120757532765740951207575327686209412075753276932685
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017089131889132341943042560024241128320x7fc207c546000x7fc0d7a3660000012075753276960176120757532771926521207575327732721212075753277331406
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017289131889132341943042560024241148160x7fc207c545000x7fc0d7a3664000012075753277380217120757532775904111207575327776561012075753277769711
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017489131889132341943042560024241162880x7fc207c544000x7fc0d7a3668000012075753277829372120757532780372891207575327817168812075753278175685
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017689131889132341943042560028241190400x7fc207c543000x7fc0d7a366c000012075753278223264120757532784392071207575327870192612075753278747298
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017889131889132341943042560028241207680x7fc207c54a000x7fc0d7a3670000012075753278773456120757532789881651207575327924416412075753279314962
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018089131889132341943042560024241224960x7fc207c549000x7fc0d7a3674000012075753279342494120757532795563221207575327969072212075753279694909
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018289131889132341943042560024241247360x7fc207c548000x7fc0d7a3678000012075753279742948120757532799529611207575328013712012075753280142160
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018489131889132341943042560024241264640x7fc207c547000x7fc0d7a367c000012075753280203554120757532804030391207575328054047812075753280544277
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018689131889132341943042560020241279360x7fc207c546000x7fc0d7a3680000012075753280592016120757532808067171207575328107311612075753281144973
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018889131889132341943042560028241296640x7fc207c545000x7fc0d7a3684000012075753281170030120757532814001541207575328165551312075753281725903
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019089131889132341943042560024241313920x7fc207c544000x7fc0d7a3688000012075753281751090120757532819678321207575328210399112075753282108063
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019289131889132341943042560024241336320x7fc207c543000x7fc0d7a368c000012075753282155471120757532823716701207575328256350912075753282634141
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019489131889132341943042560024241353600x7fc207c54a000x7fc0d7a3690000012075753282672572120757532828772681207575328301310712075753283017003
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019689131889132341943042560020241368320x7fc207c549000x7fc0d7a3694000012075753283064431120757532832812661207575328356590512075753283635853
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019889131889132341943042560028241385600x7fc207c548000x7fc0d7a3698000012075753283661470120757532838806241207575328414222312075753284213035
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020089131889132341943042560024241402880x7fc207c547000x7fc0d7a369c000012075753284242771120757532844639811207575328460430112075753284608150
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020289131889132341943042560024241427840x7fc207c546000x7fc0d7a36a0000012075753284657071120757532848718631207575328508370212075753285158763
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020489131889132341943042560024241447680x7fc207c545000x7fc0d7a36a4000012075753285193718120757532854086601207575328554801912075753285551773
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020689131889132341943042560020241457280x7fc207c544000x7fc0d7a36a8000012075753285600574120757532858148981207575328615153712075753286221959
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020889131889132341943042560028241477120x7fc207c543000x7fc0d7a36ac000012075753286250201120757532864707351207575328672833412075753286797839
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021089131889132341943042560024241496960x7fc207c54a000x7fc0d7a36b0000012075753286824859120757532870488131207575328718673312075753287190779
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021289131889132341943042560024241521920x7fc207c549000x7fc0d7a36b4000012075753287238508120757532874510521207575328768017112075753287725092
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021489131889132341943042560024241541760x7fc207c548000x7fc0d7a36b8000012075753287764435120757532879716901207575328811248912075753288115909
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021689131889132341943042560020241556480x7fc207c547000x7fc0d7a36bc000012075753288166212120757532883803281207575328871168712075753288781916
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021889131889132341943042560028241576320x7fc207c546000x7fc0d7a36c0000012075753288807414120757532890339261207575328928688512075753289357266
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022089131889132341943042560024241596160x7fc207c545000x7fc0d7a36c4000012075753289385097120757532896038431207575328974576312075753289749705
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022289131889132341943042560024241623680x7fc207c544000x7fc0d7a36c8000012075753289795961120757532900123221207575329025712112075753290328561
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022489131889132341943042560024241646080x7fc207c543000x7fc0d7a36cc000012075753290366461120757532905844801207575329072191912075753290725859
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022689131889132341943042560020241663360x7fc207c54a000x7fc0d7a36d0000012075753290773087120757532909835181207575329136031712075753291431661
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022889131889132341943042560028241685760x7fc207c549000x7fc0d7a36d4000012075753291458401120757532916838351207575329195087412075753292032437
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023089131889132341943042560024241708160x7fc207c548000x7fc0d7a36d8000012075753292060449120757532922899131207575329243151212075753292435136
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023289131889132341943042560024241740800x7fc207c547000x7fc0d7a36dc000012075753292482043120757532926958311207575329297599012075753293025463
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023489131889132341943042560024241765760x7fc207c546000x7fc0d7a36e0000012075753293064165120757532932726291207575329341534912075753293418804
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023689131889132341943042560020241777920x7fc207c545000x7fc0d7a36e4000012075753293466593120757532936745481207575329412174612075753294191991
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023889131889132341943042560028241802880x7fc207c544000x7fc0d7a36e8000012075753294218029120757532944420651207575329470926412075753294779272
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024089131889132341943042560024241827840x7fc207c543000x7fc0d7a36ec000012075753294805822120757532950401421207575329518158212075753295185537
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024289131889132341943042560024241863040x7fc207c54a000x7fc0d7a36f0000012075753295232675120757532954459011207575329576126012075753295831678
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024489131889132341943042560024241893120x7fc207c549000x7fc0d7a36f4000012075753295869298120757532960934181207575329624589812075753296249414
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024689131889132341943042560020241907840x7fc207c548000x7fc0d7a36f8000012075753296296221120757532965111771207575329702877512075753297099334
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024889131889132341943042560028241937920x7fc207c547000x7fc0d7a36fc000012075753297125913120757532973449331207575329764445212075753297714587
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025089131889132341943042560024241968000x7fc207c546000x7fc0d7a3700000012075753297741698120757532979706911207575329812685012075753298130881
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025289131889132341943042560024242010880x7fc207c545000x7fc0d7a3704000012075753298177698120757532983934091207575329877948812075753298849737
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025489131889132341943042560024242046080x7fc207c544000x7fc0d7a3708000012075753298887487120757532991070071207575329928556612075753299289414
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025689131889132341943042560020242060800x7fc207c543000x7fc0d7a370c000012075753299336412120757532995537251207575330016412312075753300234921
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025889131889132341943042560028242096000x7fc207c54a000x7fc0d7a3710000012075753300260880120757533004844411207575330081596012075753300886152
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026089131889132341943042560024242131200x7fc207c549000x7fc0d7a3714000012075753300914765120757533011513191207575330133147812075753301335667
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026289131889132341943042560024242181760x7fc207c548000x7fc0d7a3718000012075753301384127120757533016031571207575330205979512075753302130594
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026489131889132341943042560024242222080x7fc207c547000x7fc0d7a371c000012075753302170078120757533023788341207575330257931312075753302649639
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026689131889132341943042560020242239360x7fc207c546000x7fc0d7a3720000012075753302676579120757533028905121207575330359994912075753303671638
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026889131889132341943042560028242279680x7fc207c545000x7fc0d7a3724000012075753303696525120757533039217081207575330429658712075753304367522
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027089131889132341943042560024242320000x7fc207c544000x7fc0d7a3728000012075753304395564120757533046170651207575330482138512075753304891285
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027289131889132341943042560024242378240x7fc207c543000x7fc0d7a372c000012075753304916792120757533051444231207575330567050112075753305740754
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027489131889132341943042560024242423680x7fc207c54a000x7fc0d7a3730000012075753305781159120757533059893801207575330624777912075753306318117
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027689131889132341943042560020242435840x7fc207c549000x7fc0d7a3734000012075753306345598120757533065634581207575330736297512075753307433480
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027889131889132341943042560028242481280x7fc207c548000x7fc0d7a3738000012075753307459849120757533076924131207575330813705212075753308208229
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028089131889132341943042560024242526720x7fc207c547000x7fc0d7a373c000012075753308240880120757533084672901207575330869497012075753308765044
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028289131889132341943042560024242592640x7fc207c546000x7fc0d7a3740000012075753308791333120757533090279281207575330962536612075753309696736
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028489131889132341943042560024242648320x7fc207c545000x7fc0d7a3744000012075753309731851120757533099530451207575331022232412075753310292824
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028689131889132341943042560020242663040x7fc207c544000x7fc0d7a3748000012075753310318722120757533105431221207575331152791912075753311598420
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028889131889132341943042560028242718720x7fc207c543000x7fc0d7a374c000012075753311625430120757533118579971207575331237399512075753312444823
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029089131889132341943042560024242774400x7fc207c54a000x7fc0d7a3750000012075753312473566120757533127013541207575331297495312075753313045870
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029289131889132341943042560012242799360x7fc207c549000x7fc0d7a3754000012075753313071387120757533132971921207575331403590912075753314106571
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029489131889132341943042560024242865280x7fc207c548000x7fc0d7a3758000012075753314146205120757533143587881207575331467526612075753314745348
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029689131889132341943042560020242880000x7fc207c547000x7fc0d7a375c000012075753314772328120757533149978251207575331616790112075753316238423
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029889131889132341943042560032242945920x7fc207c546000x7fc0d7a3760000012075753316265614120757533164979791207575331710837712075753317179963
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030089131889132341943042560024243011840x7fc207c545000x7fc0d7a3764000012075753317212013120757533174336561207575331775269512075753317823168
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030289131889132341943042560012243049600x7fc207c544000x7fc0d7a3768000012075753317854296120757533180808531207575331896021012075753319031153
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030489131889132341943042560024243136000x7fc207c543000x7fc0d7a376c000012075753319079493120757533192853291207575331969764712075753319767552
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030689131889132341943042560020243148160x7fc207c54a000x7fc0d7a3770000012075753319794572120757533200280461207575332157652012075753321648458
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030889131889132341943042560020243175680x7fc207c549000x7fc0d7a3774000012075753321677361120757533219051581207575332270067512075753322771244
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031089131889132341943042560012243203200x7fc207c548000x7fc0d7a3778000012075753322797453120757533230273941207575332344291312075753323514095
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031289131889132341943042560012243240960x7fc207c547000x7fc0d7a377c000012075753323540183120757533237638711207575332492290712075753324994055
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031489131889132341943042560012243288960x7fc207c546000x7fc0d7a3780000012075753325039379120757533252574661207575332604402212075753326115419
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031689131889132341943042560020243301120x7fc207c545000x7fc0d7a3784000012075753326148070120757533263688211207575332941808912075753329490031
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031889131889132341943042560020243328640x7fc207c544000x7fc0d7a3788000012075753329521008120757533297508881207575333129152212075753331362350
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032089131889132341943042560012243356160x7fc207c543000x7fc0d7a378c000012075753331395983120757533316180811207575333240783812075753332479737
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032289131889132341943042560012243393920x7fc207c54a000x7fc0d7a3790000012075753332505705120757533327340771207575333501502812075753335087053
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032489131889132341943042560012243441920x7fc207c549000x7fc0d7a3794000012075753335133639120757533353419071207575333687758112075753336948923
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032689131889132341943042560020243454080x7fc207c548000x7fc0d7a3798000012075753336981042120757533372129391207575334326699612075753343342144
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032889131889132341943042560020243481600x7fc207c547000x7fc0d7a379c000012075753343369926120757533435970751207575334663882312075753346714552
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033089131889132341943042560012243509120x7fc207c546000x7fc0d7a37a0000012075753346744267120757533469743491207575334851354512075753348589326
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332891318891323419430425600122400x7fc207c545000x7fc0d7a37a4000012075753348617769120757533488449031207575335337272912075753353447224