Dateien
rocm-systems/tests/workloads/HBM/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.kd000875773875778335544322560083264640x00x7efd0fa0418000012075446198050940120754464424240621207544644274710012075446442857662
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00287577387577832768256002424124800x00x7efd0fa3510000012075446457398255120754464576977411207544645770430112075446457709524
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0048757738757784194304256002424129280x7efe3faf39000x7efd0fa3514000012075446457773643120754464579931001207544645813053912075446458134884
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0068757738757784194304256003624136320x7efe3faf38000x7efd0fa3518000012075446458208241120754464583810981207544645863277612075446458701497
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0088757738757784194304256002824140800x7efe3faf37000x7efd0fa351c000012075446458730321120754464589198151207544645917389312075446459243465
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00108757738757784194304256002424145280x7efe3faf36000x7efd0fa3520000012075446459272058120754464594551721207544645959357112075446459597212
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00128757738757784194304256002424149760x7efe3faf35000x7efd0fa3524000012075446459647926120754464598084501207544645994540912075446459949016
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00148757738757784194304256002424154240x7efe3faf34000x7efd0fa3528000012075446460032160120754464601967681207544646032940712075446460333300
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00168757738757784194304256002824161280x7efe3faf33000x7efd0fa352c000012075446460377302120754464605569261207544646081484512075446460856252
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00188757738757784194304256002824168320x7efe3faf3a000x7efd0fa3530000012075446460882020120754464610687641207544646132748212075446461369135
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00208757738757784194304256002424175360x7efe3faf39000x7efd0fa3534000012075446461396947120754464615892411207544646172268012075446461726479
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00228757738757784194304256002424182400x7efe3faf38000x7efd0fa3538000012075446461775320120754464619500391207544646208859812075446462092439
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00248757738757784194304256002424189440x7efe3faf37000x7efd0fa353c000012075446462156067120754464623215571207544646245659612075446462460273
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00268757738757784194304256002824199040x7efe3faf36000x7efd0fa3540000012075446462509094120754464626730751207544646292763412075446462994105
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00288757738757784194304256002824206080x7efe3faf35000x7efd0fa3544000012075446463023369120754464632052321207544646346011112075446463528929
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00308757738757784194304256002424213120x7efe3faf34000x7efd0fa3548000012075446463551541120754464637341901207544646386714912075446463870784
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00328757738757784194304256002424220160x7efe3faf33000x7efd0fa354c000012075446463919925120754464641010681207544646423866712075446464242735
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00348757738757784194304256002424227200x7efe3faf3a000x7efd0fa3550000012075446464307376120754464644689061207544646459978512075446464603576
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00368757738757784194304256002824236800x7efe3faf39000x7efd0fa3554000012075446464653188120754464648255441207544646507866312075446465147166
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00388757738757784194304256002824243840x7efe3faf38000x7efd0fa3558000012075446465171031120754464653593011207544646561130012075446465653627
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00408757738757784194304256002424250880x7efe3faf37000x7efd0fa355c000012075446465676841120754464658576991207544646598825812075446465992006
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00428757738757784194304256002424257920x7efe3faf36000x7efd0fa3560000012075446466043853120754464662092171207544646634489612075446466348850
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00448757738757784194304256002424264960x7efe3faf35000x7efd0fa3564000012075446466410013120754464665730551207544646670457412075446466708428
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00468757738757784194304256002824277120x7efe3faf34000x7efd0fa3568000012075446466759372120754464669224931207544646718457212075446467253801
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00488757738757784194304256002824284160x7efe3faf33000x7efd0fa356c000012075446467281653120754464674703301207544646772664912075446467793514
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00508757738757784194304256002424291200x7efe3faf3a000x7efd0fa3570000012075446467820154120754464679989671207544646812696712075446468131002
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00528757738757784194304256002424300800x7efe3faf39000x7efd0fa3574000012075446468179111120754464683514461207544646848520512075446468489047
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00548757738757784194304256002424307840x7efe3faf38000x7efd0fa3578000012075446468551142120754464687143241207544646884808312075446468851851
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00568757738757784194304256002824320000x7efe3faf37000x7efd0fa357c000012075446468899871120754464690808821207544646934104112075446469408346
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00588757738757784194304256002824329600x7efe3faf36000x7efd0fa3580000012075446469431819120754464696189591207544646987511812075446469943089
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00608757738757784194304256002424339200x7efe3faf35000x7efd0fa3584000012075446469967104120754464701640761207544647029559612075446470299532
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00628757738757784194304256002424348800x7efe3faf34000x7efd0fa3588000012075446470343724120754464705176741207544647065367412075446470657577
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00648757738757784194304256002424358400x7efe3faf33000x7efd0fa358c000012075446470720594120754464708834321207544647101591212075446471019720
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00668757738757784194304256002824373120x7efe3faf3a000x7efd0fa3590000012075446471064634120754464712387911207544647150054912075446471568400
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00688757738757784194304256002824382720x7efe3faf39000x7efd0fa3594000012075446471595180120754464717725481207544647203190612075446472074851
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00708757738757784194304256002424392320x7efe3faf38000x7efd0fa3598000012075446472099136120754464722872651207544647242342412075446472427186
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00728757738757784194304256002424401920x7efe3faf37000x7efd0fa359c000012075446472476608120754464726411831207544647277846312075446472782476
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00748757738757784194304256002424411520x7efe3faf36000x7efd0fa35a0000012075446472843500120754464730063011207544647313574112075446473139860
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00768757738757784194304256002824426240x7efe3faf35000x7efd0fa35a4000012075446473191436120754464733666201207544647362885812075446473696906
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00788757738757784194304256002824435840x7efe3faf34000x7efd0fa35a8000012075446473720680120754464739014971207544647415829512075446474228083
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00808757738757784194304256002424445440x7efe3faf33000x7efd0fa35ac000012075446474251837120754464744394141207544647456805312075446474572052
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00828757738757784194304256002424457600x7efe3faf3a000x7efd0fa35b0000012075446474623628120754464747862921207544647492789112075446474931650
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00848757738757784194304256002424467200x7efe3faf39000x7efd0fa35b4000012075446474992894120754464751656501207544647529764912075446475301548
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00868757738757784194304256002824484480x7efe3faf38000x7efd0fa35b8000012075446475350779120754464755144481207544647578452712075446475827155
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00888757738757784194304256002824494080x7efe3faf37000x7efd0fa35bc000012075446475849777120754464760370061207544647629828412075446476365786
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00908757738757784194304256002424503680x7efe3faf36000x7efd0fa35c0000012075446476389409120754464765678831207544647669668212075446476700437
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00928757738757784194304256002424515840x7efe3faf35000x7efd0fa35c4000012075446476749268120754464769184411207544647706372012075446477067900
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00948757738757784194304256002424525440x7efe3faf34000x7efd0fa35c8000012075446477129785120754464772915591207544647742243812075446477426337
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00968757738757784194304256002824542720x7efe3faf33000x7efd0fa35cc000012075446477475939120754464776475571207544647791555612075446477983011
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00988757738757784194304256002824554880x7efe3faf3a000x7efd0fa35d0000012075446478013187120754464781969941207544647845219312075446478522624
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001008757738757784194304256002424567040x7efe3faf39000x7efd0fa35d4000012075446478545647120754464787286721207544647885843112075446478862175
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001028757738757784194304256002424581760x7efe3faf38000x7efd0fa35d8000012075446478910906120754464790869101207544647922994912075446479233866
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001048757738757784194304256002424593920x7efe3faf37000x7efd0fa35dc000012075446479294749120754464794579481207544647959186712075446479595598
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001068757738757784194304256002824613760x7efe3faf36000x7efd0fa35e0000012075446479637466120754464798131461207544648007986512075446480147644
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001088757738757784194304256002824625920x7efe3faf35000x7efd0fa35e4000012075446480171919120754464803534631207544648060930212075446480675365
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001108757738757784194304256002424638080x7efe3faf34000x7efd0fa35e8000012075446480700872120754464808763401207544648100850012075446481012351
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001128757738757784194304256002424652800x7efe3faf33000x7efd0fa35ec000012075446481063356120754464812305791207544648136929812075446481373172
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001148757738757784194304256002424664960x7efe3faf3a000x7efd0fa35f0000012075446481433824120754464815961771207544648173345612075446481737258
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001168757738757784194304256002824684800x7efe3faf39000x7efd0fa35f4000012075446481784917120754464819577751207544648222033312075446482289464
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001188757738757784194304256002824696960x7efe3faf38000x7efd0fa35f8000012075446482314050120754464824942521207544648275761112075446482824138
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001208757738757784194304256002424709120x7efe3faf37000x7efd0fa35fc000012075446482842342120754464830324891207544648316688812075446483170893
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001228757738757784194304256002424723840x7efe3faf36000x7efd0fa3600000012075446483221006120754464833942471207544648353216712075446483535941
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001248757738757784194304256002424736000x7efe3faf35000x7efd0fa3604000012075446483597576120754464837590451207544648389488512075446483898745
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001268757738757784194304256002824758400x7efe3faf34000x7efd0fa3608000012075446483947245120754464841200031207544648439296212075446484442656
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001288757738757784194304256002824770560x7efe3faf33000x7efd0fa360c000012075446484467222120754464846494411207544648490223912075446484924762
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001308757738757784194304256002424782720x7efe3faf3a000x7efd0fa3610000012075446484967532120754464851339181207544648526767812075446485271517
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001328757738757784194304256002424800000x7efe3faf39000x7efd0fa3614000012075446485324395120754464854948761207544648563855612075446485642346
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001348757738757784194304256002424812160x7efe3faf38000x7efd0fa3618000012075446485703760120754464858652741207544648600207412075446486007023
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001368757738757784194304256002824834560x7efe3faf37000x7efd0fa361c000012075446486055734120754464862275131207544648649887112075446486548690
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001388757738757784194304256002824849280x7efe3faf36000x7efd0fa3620000012075446486574668120754464867492701207544648700446812075446487053398
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001408757738757784194304256002424864000x7efe3faf35000x7efd0fa3624000012075446487077513120754464872625471207544648739822612075446487402086
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001428757738757784194304256002424881280x7efe3faf34000x7efd0fa3628000012075446487455926120754464876167851207544648776750412075446487771252
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001448757738757784194304256002424896000x7efe3faf33000x7efd0fa362c000012075446487853785120754464880215831207544648816014212075446488164132
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001468757738757784194304256002824920960x7efe3faf3a000x7efd0fa3630000012075446488213584120754464883839811207544648865598012075446488678729
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001488757738757784194304256002824935680x7efe3faf39000x7efd0fa3634000012075446488716429120754464888740591207544648913101712075446489180712
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001508757738757784194304256002424950400x7efe3faf38000x7efd0fa3638000012075446489197673120754464893897361207544648952125512075446489525172
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001528757738757784194304256002424967680x7efe3faf37000x7efd0fa363c000012075446489577459120754464897378941207544648989485312075446489898576
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001548757738757784194304256002424982400x7efe3faf36000x7efd0fa3640000012075446489959910120754464901257321207544649025981212075446490263784
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015687577387577841943042560028241007360x7efe3faf35000x7efd0fa3644000012075446490307375120754464904815701207544649074716912075446490795122
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015887577387577841943042560028241022080x7efe3faf34000x7efd0fa3648000012075446490825508120754464910273281207544649128812612075446491337650
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016087577387577841943042560024241036800x7efe3faf33000x7efd0fa364c000012075446491362076120754464915433251207544649168396412075446491687891
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016287577387577841943042560024241056640x7efe3faf3a000x7efd0fa3650000012075446491735980120754464919010831207544649206652212075446492070602
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016487577387577841943042560024241071360x7efe3faf39000x7efd0fa3654000012075446492133329120754464922978811207544649243308012075446492437023
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016687577387577841943042560028241098880x7efe3faf38000x7efd0fa3658000012075446492480003120754464926559591207544649292427812075446492946791
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016887577387577841943042560028241113600x7efe3faf37000x7efd0fa365c000012075446492988278120754464931554761207544649340923512075446493458872
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017087577387577841943042560024241128320x7efe3faf36000x7efd0fa3660000012075446493475894120754464936671541207544649380555312075446493809664
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017287577387577841943042560024241148160x7efe3faf35000x7efd0fa3664000012075446493860389120754464940293921207544649420267112075446494206842
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017487577387577841943042560024241162880x7efe3faf34000x7efd0fa3668000012075446494268557120754464944317901207544649456874912075446494572833
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017687577387577841943042560028241190400x7efe3faf33000x7efd0fa366c000012075446494622264120754464947927481207544649505386712075446495103849
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017887577387577841943042560028241207680x7efe3faf3a000x7efd0fa3670000012075446495132012120754464953095451207544649557226412075446495619608
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018087577387577841943042560024241224960x7efe3faf39000x7efd0fa3674000012075446495644614120754464958233031207544649596234212075446495966393
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018287577387577841943042560024241247360x7efe3faf38000x7efd0fa3678000012075446496020723120754464961969011207544649637994012075446496383948
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018487577387577841943042560024241264640x7efe3faf37000x7efd0fa367c000012075446496445663120754464966068181207544649674889812075446496752744
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018687577387577841943042560020241279360x7efe3faf36000x7efd0fa3680000012075446496802076120754464969690571207544649723673512075446497286856
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018887577387577841943042560028241296640x7efe3faf35000x7efd0fa3684000012075446497311793120754464974952941207544649775305212075446497800551
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019087577387577841943042560024241313920x7efe3faf34000x7efd0fa3688000012075446497823013120754464980096911207544649814969012075446498153848
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019287577387577841943042560024241336320x7efe3faf33000x7efd0fa368c000012075446498198050120754464983816891207544649857464812075446498622869
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019487577387577841943042560024241353600x7efe3faf3a000x7efd0fa3690000012075446498658415120754464988188071207544649895832612075446498962460
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019687577387577841943042560020241368320x7efe3faf39000x7efd0fa3694000012075446499017312120754464991778451207544649946248412075446499485883
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019887577387577841943042560028241385600x7efe3faf38000x7efd0fa3698000012075446499527941120754464996853621207544649994424112075446499992405
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020087577387577841943042560024241402880x7efe3faf37000x7efd0fa369c000012075446500020427120754465002020001207544650034167912075446500345811
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020287577387577841943042560024241427840x7efe3faf36000x7efd0fa36a0000012075446500395985120754465005610381207544650077255712075446500820604
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020487577387577841943042560024241447680x7efe3faf35000x7efd0fa36a4000012075446500856701120754465010235951207544650116183512075446501166156
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020687577387577841943042560020241457280x7efe3faf34000x7efd0fa36a8000012075446501215397120754465013874341207544650169479212075446501743409
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020887577387577841943042560028241477120x7efe3faf33000x7efd0fa36ac000012075446501765680120754465019447111207544650220246912075446502254168
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021087577387577841943042560024241496960x7efe3faf3a000x7efd0fa36b0000012075446502273694120754465024581481207544650259270712075446502596935
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021287577387577841943042560024241521920x7efe3faf39000x7efd0fa36b4000012075446502650154120754465028122261207544650303974512075446503090492
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021487577387577841943042560024241541760x7efe3faf38000x7efd0fa36b8000012075446503125798120754465032895041207544650342854312075446503432848
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021687577387577841943042560020241556480x7efe3faf37000x7efd0fa36bc000012075446503482591120754465036541421207544650401334012075446504042001
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021887577387577841943042560028241576320x7efe3faf36000x7efd0fa36c0000012075446504085572120754465042475791207544650451045712075446504558280
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022087577387577841943042560024241596160x7efe3faf35000x7efd0fa36c4000012075446504579850120754465047642161207544650490437512075446504908471
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022287577387577841943042560024241623680x7efe3faf34000x7efd0fa36c8000012075446504957322120754465051366741207544650538275312075446505437163
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022487577387577841943042560024241646080x7efe3faf33000x7efd0fa36cc000012075446505471487120754465056457911207544650578643012075446505789859
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022687577387577841943042560020241663360x7efe3faf3a000x7efd0fa36d0000012075446505839291120754465060080291207544650638450712075446506434898
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022887577387577841943042560028241685760x7efe3faf39000x7efd0fa36d4000012075446506457900120754465066379461207544650690834512075446506954584
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023087577387577841943042560024241708160x7efe3faf38000x7efd0fa36d8000012075446506976534120754465071621041207544650730322312075446507306808
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023287577387577841943042560024241740800x7efe3faf37000x7efd0fa36dc000012075446507358755120754465075214621207544650780146112075446507848785
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023487577387577841943042560024241765760x7efe3faf36000x7efd0fa36e0000012075446507887497120754465080566601207544650819585912075446508199617
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023687577387577841943042560020241777920x7efe3faf35000x7efd0fa36e4000012075446508241525120754465084174581207544650886609612075446508916530
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023887577387577841943042560028241802880x7efe3faf34000x7efd0fa36e8000012075446508942207120754465091326551207544650939681412075446509446425
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024087577387577841943042560024241827840x7efe3faf33000x7efd0fa36ec000012075446509472874120754465096510531207544650979121212075446509794742
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024287577387577841943042560024241863040x7efe3faf3a000x7efd0fa36f0000012075446509844454120754465100104111207544651032721012075446510377765
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024487577387577841943042560024241893120x7efe3faf39000x7efd0fa36f4000012075446510413702120754465105854491207544651073744812075446510740950
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024687577387577841943042560020241907840x7efe3faf38000x7efd0fa36f8000012075446510790593120754465109582471207544651147632512075446511526210
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024887577387577841943042560028241937920x7efe3faf37000x7efd0fa36fc000012075446511553450120754465117304041207544651203120212075446512079638
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025087577387577841943042560024241968000x7efe3faf36000x7efd0fa3700000012075446512103302120754465122912011207544651244720012075446512450708
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025287577387577841943042560024242010880x7efe3faf35000x7efd0fa3704000012075446512499208120754465126673591207544651305439812075446513077042
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025487577387577841943042560024242046080x7efe3faf34000x7efd0fa3708000012075446513142013120754465133065571207544651348303612075446513486563
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025687577387577841943042560020242060800x7efe3faf33000x7efd0fa370c000012075446513536285120754465136982351207544651430991212075446514359165
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025887577387577841943042560028242096000x7efe3faf3a000x7efd0fa3710000012075446514385233120754465145703911207544651489951012075446514949842
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026087577387577841943042560024242131200x7efe3faf39000x7efd0fa3714000012075446514981201120754465151603081207544651533966812075446515343985
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026287577387577841943042560024242181760x7efe3faf38000x7efd0fa3718000012075446515394859120754465155739071207544651603102512075446516081275
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026487577387577841943042560024242222080x7efe3faf37000x7efd0fa371c000012075446516118444120754465162798231207544651647934312075446516527625
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026687577387577841943042560020242239360x7efe3faf36000x7efd0fa3720000012075446516557921120754465167310211207544651743485812075446517485405
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026887577387577841943042560028242279680x7efe3faf35000x7efd0fa3724000012075446517515140120754465176882971207544651806061612075446518111709
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027087577387577841943042560024242320000x7efe3faf34000x7efd0fa3728000012075446518142315120754465183228541207544651852589412075446518575040
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027287577387577841943042560024242378240x7efe3faf33000x7efd0fa372c000012075446518603763120754465187815721207544651930813012075446519359788
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027487577387577841943042560024242423680x7efe3faf3a000x7efd0fa3730000012075446519396627120754465195594891207544651978460812075446519831916
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027687577387577841943042560020242435840x7efe3faf39000x7efd0fa3734000012075446519849999120754465200615671207544652086124312075446520912834
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027887577387577841943042560028242481280x7efe3faf38000x7efd0fa3738000012075446520938041120754465211249221207544652154652012075446521596755
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028087577387577841943042560024242526720x7efe3faf37000x7efd0fa373c000012075446521621010120754465218025191207544652203035812075446522081536
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028287577387577841943042560024242592640x7efe3faf36000x7efd0fa3740000012075446522109368120754465222879571207544652288571412075446522954719
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028487577387577841943042560024242648320x7efe3faf35000x7efd0fa3744000012075446522992880120754465231661931207544652343563212075446523505302
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028687577387577841943042560020242663040x7efe3faf34000x7efd0fa3748000012075446523529147120754465237071511207544652469242612075446524761116
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028887577387577841943042560028242718720x7efe3faf33000x7efd0fa374c000012075446524784179120754465249711451207544652550362312075446525573837
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029087577387577841943042560024242774400x7efe3faf3a000x7efd0fa3750000012075446525602370120754465257852211207544652605786012075446526128968
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029287577387577841943042560012242799360x7efe3faf39000x7efd0fa3754000012075446526160286120754465263333791207544652707177612075446527139927
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029487577387577841943042560024242865280x7efe3faf38000x7efd0fa3758000012075446527179501120754465273424941207544652765833312075446527727329
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029687577387577841943042560020242880000x7efe3faf37000x7efd0fa375c000012075446527755802120754465279349721207544652910552712075446529176342
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029887577387577841943042560032242945920x7efe3faf36000x7efd0fa3760000012075446529202160120754465293967251207544653000616312075446530075202
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030087577387577841943042560024243011840x7efe3faf35000x7efd0fa3764000012075446530104056120754465302826411207544653062952012075446530697038
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030287577387577841943042560012243049600x7efe3faf34000x7efd0fa3768000012075446530723968120754465309005591207544653177863512075446531848177
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030487577387577841943042560024243136000x7efe3faf33000x7efd0fa376c000012075446531885446120754465320568741207544653248983212075446532559189
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030687577387577841943042560020243148160x7efe3faf3a000x7efd0fa3770000012075446532583183120754465327731901207544653432118412075446534390672
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030887577387577841943042560020243175680x7efe3faf39000x7efd0fa3774000012075446534422261120754465346040621207544653539861912075446535467013
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031087577387577841943042560012243203200x7efe3faf38000x7efd0fa3778000012075446535489234120754465356755781207544653609029612075446536159089
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031287577387577841943042560012243240960x7efe3faf37000x7efd0fa377c000012075446536189575120754465363678951207544653752612912075446537594967
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031487577387577841943042560012243288960x7efe3faf36000x7efd0fa3780000012075446537639009120754465378037281207544653859012512075446538660828
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031687577387577841943042560020243301120x7efe3faf35000x7efd0fa3784000012075446538687778120754465388683631207544654191763012075446541988312
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031887577387577841943042560020243328640x7efe3faf34000x7efd0fa3788000012075446542023147120754465422123491207544654375426212075446543824665
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032087577387577841943042560012243356160x7efe3faf33000x7efd0fa378c000012075446543855933120754465440449811207544654483441712075446544904261
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032287577387577841943042560012243393920x7efe3faf3a000x7efd0fa3790000012075446544931282120754465451204961207544654740240612075446547471933
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032487577387577841943042560012243441920x7efe3faf39000x7efd0fa3794000012075446547515855120754465476804841207544654921663812075446549284933
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032687577387577841943042560020243454080x7efe3faf38000x7efd0fa3798000012075446549315059120754465494956761207544655554973012075446555618353
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032887577387577841943042560020243481600x7efe3faf37000x7efd0fa379c000012075446555649601120754465558225281207544655886427512075446558934917
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033087577387577841943042560012243509120x7efe3faf36000x7efd0fa37a0000012075446558964882120754465591522741207544656069082712075446560761722
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332875773875778419430425600122400x7efe3faf35000x7efd0fa37a4000012075446560791858120754465609713061207544656549848512075446565569106