Files
rocm-systems/tests/workloads/mixbench2/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.kd000765313765318335544322560083264640x00x7ff8ae40418000012073468737376926120734689852131881207346898553718612073468985669598
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00276531376531832768256002424124800x00x7ff8ae43510000012073469000047208120734690003507511207346900035667112073469000362053
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0047653137653184194304256002424129280x7ff9ba03a9000x7ff8ae43514000012073469000421423120734690006275501207346900075682912073469000760573
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0067653137653184194304256003624136320x7ff9ba03a8000x7ff8ae43518000012073469000826586120734690009992281207346900125378712073469001325323
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0087653137653184194304256002824140800x7ff9ba03a7000x7ff8ae4351c000012073469001350409120734690015392251207346900179538412073469001863443
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00107653137653184194304256002424145280x7ff9ba03a6000x7ff8ae43520000012073469001890072120734690020790631207346900221090212073469002214886
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00127653137653184194304256002424149760x7ff9ba03a5000x7ff8ae43524000012073469002264839120734690024309011207346900256050012073469002564105
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00147653137653184194304256002424154240x7ff9ba03a4000x7ff8ae43528000012073469002644184120734690028046591207346900293617912073469002939763
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00167653137653184194304256002824161280x7ff9ba03a3000x7ff8ae4352c000012073469002990097120734690031670571207346900342161612073469003463867
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00187653137653184194304256002824168320x7ff9ba03aa000x7ff8ae43530000012073469003492410120734690036673751207346900391489412073469003955811
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00207653137653184194304256002424175360x7ff9ba03a9000x7ff8ae43534000012073469003980247120734690041795321207346900430977212073469004313316
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00227653137653184194304256002424182400x7ff9ba03a8000x7ff8ae43538000012073469004363379120734690045278511207346900466113012073469004664619
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00247653137653184194304256002424189440x7ff9ba03a7000x7ff8ae4353c000012073469004727746120734690048913691207346900502256812073469005026050
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00267653137653184194304256002824199040x7ff9ba03a6000x7ff8ae43540000012073469005076885120734690052435271207346900550384612073469005572356
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00287653137653184194304256002824206080x7ff9ba03a5000x7ff8ae43544000012073469005599215120734690057756841207346900602960312073469006097922
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00307653137653184194304256002424213120x7ff9ba03a4000x7ff8ae43548000012073469006123760120734690063051221207346900643616112073469006439757
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00327653137653184194304256002424220160x7ff9ba03a3000x7ff8ae4354c000012073469006489951120734690066537601207346900678703912073469006790609
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00347653137653184194304256002424227200x7ff9ba03aa000x7ff8ae43550000012073469006857143120734690070246381207346900715663812073469007160497
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00367653137653184194304256002824236800x7ff9ba03a9000x7ff8ae43554000012073469007213295120734690073751961207346900763679512073469007703726
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00387653137653184194304256002824243840x7ff9ba03a8000x7ff8ae43558000012073469007729224120734690079079941207346900816575312073469008235154
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00407653137653184194304256002424250880x7ff9ba03a7000x7ff8ae4355c000012073469008259549120734690084404711207346900857279012073469008576388
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00427653137653184194304256002424257920x7ff9ba03a6000x7ff8ae43560000012073469008624828120734690087907091207346900892302912073469008926569
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00447653137653184194304256002424264960x7ff9ba03a5000x7ff8ae43564000012073469008988444120734690091591881207346900928734712073469009291347
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00467653137653184194304256002824277120x7ff9ba03a4000x7ff8ae43568000012073469009342913120734690095030261207346900975774512073469009825439
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00487653137653184194304256002824284160x7ff9ba03a3000x7ff8ae4356c000012073469009852620120734690100393431207346901029518212073469010364802
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00507653137653184194304256002424291200x7ff9ba03aa000x7ff8ae43570000012073469010391341120734690105687811207346901070110012073469010704663
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00527653137653184194304256002424300800x7ff9ba03a9000x7ff8ae43574000012073469010755297120734690109172591207346901105261812073469011056627
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00547653137653184194304256002424307840x7ff9ba03a8000x7ff8ae43578000012073469011117911120734690112802971207346901140829612073469011411958
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00567653137653184194304256002824320000x7ff9ba03a7000x7ff8ae4357c000012073469011463734120734690116262151207346901188749412073469011955147
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00587653137653184194304256002824329600x7ff9ba03a6000x7ff8ae43580000012073469011980204120734690121679731207346901242509112073469012494169
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00607653137653184194304256002424339200x7ff9ba03a5000x7ff8ae43584000012073469012521961120734690126961301207346901282524912073469012829001
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00627653137653184194304256002424348800x7ff9ba03a4000x7ff8ae43588000012073469012877682120734690130594881207346901318988812073469013193589
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00647653137653184194304256002424358400x7ff9ba03a3000x7ff8ae4358c000012073469013256015120734690134186861207346901358956612073469013593282
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00667653137653184194304256002824373120x7ff9ba03aa000x7ff8ae43590000012073469013645989120734690138039641207346901410284312073469014172748
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00687653137653184194304256002824382720x7ff9ba03a9000x7ff8ae43594000012073469014200249120734690143740421207346901462236012073469014690050
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00707653137653184194304256002424392320x7ff9ba03a8000x7ff8ae43598000012073469014716028120734690148908391207346901502363812073469015027477
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00727653137653184194304256002424401920x7ff9ba03a7000x7ff8ae4359c000012073469015081036120734690152524371207346901538363712073469015387536
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00747653137653184194304256002424411520x7ff9ba03a6000x7ff8ae435a0000012073469015449221120734690156087551207346901574171512073469015745421
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00767653137653184194304256002824426240x7ff9ba03a5000x7ff8ae435a4000012073469015796235120734690159666741207346901622379212073469016292438
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00787653137653184194304256002824435840x7ff9ba03a4000x7ff8ae435a8000012073469016319568120734690165087511207346901676027012073469016828053
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00807653137653184194304256002424445440x7ff9ba03a3000x7ff8ae435ac000012073469016853711120734690170356281207346901716810812073469017171842
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00827653137653184194304256002424457600x7ff9ba03aa000x7ff8ae435b0000012073469017227555120734690173876271207346901752554612073469017529276
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00847653137653184194304256002424467200x7ff9ba03a9000x7ff8ae435b4000012073469017590249120734690177482651207346901788138412073469017884967
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00867653137653184194304256002824484480x7ff9ba03a8000x7ff8ae435b8000012073469017933407120734690181029831207346901837098212073469018440670
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00887653137653184194304256002824494080x7ff9ba03a7000x7ff8ae435bc000012073469018470245120734690186426601207346901889833912073469018940338
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00907653137653184194304256002424503680x7ff9ba03a6000x7ff8ae435c0000012073469018965555120734690191493781207346901928233712073469019286431
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00927653137653184194304256002424515840x7ff9ba03a5000x7ff8ae435c4000012073469019338548120734690194957761207346901963337512073469019637013
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00947653137653184194304256002424525440x7ff9ba03a4000x7ff8ae435c8000012073469019698708120734690198552941207346901998697412073469019990610
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00967653137653184194304256002824542720x7ff9ba03a3000x7ff8ae435cc000012073469020043869120734690202100131207346902047881112073469020547124
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00987653137653184194304256002824554880x7ff9ba03aa000x7ff8ae435d0000012073469020573563120734690207461701207346902100552912073469021074354
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001007653137653184194304256002424567040x7ff9ba03a9000x7ff8ae435d4000012073469021099551120734690212773671207346902140632712073469021410118
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001027653137653184194304256002424581760x7ff9ba03a8000x7ff8ae435d8000012073469021463778120734690216218461207346902176264512073469021766320
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001047653137653184194304256002424593920x7ff9ba03a7000x7ff8ae435dc000012073469021828586120734690219895241207346902211896312073469022122893
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001067653137653184194304256002824613760x7ff9ba03a6000x7ff8ae435e0000012073469022171583120734690223394421207346902261288112073469022656885
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001087653137653184194304256002824625920x7ff9ba03a5000x7ff8ae435e4000012073469022683134120734690228584791207346902311463812073469023184065
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001107653137653184194304256002424638080x7ff9ba03a4000x7ff8ae435e8000012073469023207589120734690233853571207346902351847612073469023522253
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001127653137653184194304256002424652800x7ff9ba03a3000x7ff8ae435ec000012073469023573368120734690237309551207346902386535412073469023869048
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001147653137653184194304256002424664960x7ff9ba03aa000x7ff8ae435f0000012073469023930953120734690240987931207346902423015312073469024234246
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001167653137653184194304256002824684800x7ff9ba03a9000x7ff8ae435f4000012073469024284891120734690244440711207346902470759012073469024756657
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001187653137653184194304256002824696960x7ff9ba03a8000x7ff8ae435f8000012073469024783657120734690249562291207346902525734712073469025308383
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001207653137653184194304256002424709120x7ff9ba03a7000x7ff8ae435fc000012073469025336044120734690255091861207346902564246612073469025646110
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001227653137653184194304256002424723840x7ff9ba03a6000x7ff8ae43600000012073469025698127120734690258560641207346902599846412073469026007251
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001247653137653184194304256002424736000x7ff9ba03a5000x7ff8ae43604000012073469026065830120734690262266231207346902636310212073469026366789
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001267653137653184194304256002824758400x7ff9ba03a4000x7ff8ae43608000012073469026416472120734690265738211207346902684278012073469026865226
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001287653137653184194304256002824770560x7ff9ba03a3000x7ff8ae4360c000012073469026909408120734690270717381207346902733077712073469027381415
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001307653137653184194304256002424782720x7ff9ba03aa000x7ff8ae43610000012073469027406011120734690275810161207346902771109512073469027714805
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001327653137653184194304256002424800000x7ff9ba03a9000x7ff8ae43614000012073469027767533120734690279350941207346902807925312073469028083269
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001347653137653184194304256002424812160x7ff9ba03a8000x7ff8ae43618000012073469028145174120734690283018121207346902843461212073469028438359
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001367653137653184194304256002824834560x7ff9ba03a7000x7ff8ae4361c000012073469028488803120734690286498111207346902892452912073469028973955
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001387653137653184194304256002824849280x7ff9ba03a6000x7ff8ae43620000012073469028999412120734690291787681207346902943876712073469029489152
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001407653137653184194304256002424864000x7ff9ba03a5000x7ff8ae43624000012073469029513167120734690296880451207346902982420512073469029827922
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001427653137653184194304256002424881280x7ff9ba03a4000x7ff8ae43628000012073469029879347120734690300507641207346903020100312073469030204842
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001447653137653184194304256002424896000x7ff9ba03a3000x7ff8ae4362c000012073469030286304120734690304493221207346903057924112073469030582915
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001467653137653184194304256002824920960x7ff9ba03aa000x7ff8ae43630000012073469030633168120734690307946001207346903105779912073469031109002
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001487653137653184194304256002824935680x7ff9ba03a9000x7ff8ae43634000012073469031138167120734690313109171207346903156499612073469031613911
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001507653137653184194304256002424950400x7ff9ba03a8000x7ff8ae43638000012073469031638406120734690318161951207346903195235412073469031956157
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001527653137653184194304256002424967680x7ff9ba03a7000x7ff8ae4363c000012073469032014906120734690321699531207346903232691212073469032330903
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001547653137653184194304256002424982400x7ff9ba03a6000x7ff8ae43640000012073469032397978120734690325731511207346903270739012073469032711130
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015676531376531841943042560028241007360x7ff9ba03a5000x7ff8ae43644000012073469032762335120734690329190691207346903318546812073469033236316
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015876531376531841943042560028241022080x7ff9ba03a4000x7ff8ae43648000012073469033263506120734690334419471207346903370178512073469033750070
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016076531376531841943042560024241036800x7ff9ba03a3000x7ff8ae4364c000012073469033775908120734690339489841207346903408450412073469034088680
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016276531376531841943042560024241056640x7ff9ba03aa000x7ff8ae43650000012073469034141598120734690342993821207346903446322212073469034466953
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016476531376531841943042560024241071360x7ff9ba03a9000x7ff8ae43654000012073469034527295120734690346856211207346903481650012073469034820460
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016676531376531841943042560028241098880x7ff9ba03a8000x7ff8ae43658000012073469034868709120734690350348991207346903529697712073469035326240
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016876531376531841943042560028241113600x7ff9ba03a7000x7ff8ae4365c000012073469035370442120734690355324961207346903578817512073469035809167
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017076531376531841943042560024241128320x7ff9ba03a6000x7ff8ae43660000012073469035855343120734690360115341207346903614817312073469036152525
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017276531376531841943042560024241148160x7ff9ba03a5000x7ff8ae43664000012073469036204562120734690363664121207346903653937112073469036543111
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017476531376531841943042560024241162880x7ff9ba03a4000x7ff8ae43668000012073469036603894120734690367617701207346903689617012073469036899994
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017676531376531841943042560028241190400x7ff9ba03a3000x7ff8ae4366c000012073469036950468120734690371196881207346903738336712073469037413298
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017876531376531841943042560028241207680x7ff9ba03aa000x7ff8ae43670000012073469037455687120734690376158461207346903787168512073469037895634
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018076531376531841943042560024241224960x7ff9ba03a9000x7ff8ae43674000012073469037940478120734690381008041207346903823984312073469038244042
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018276531376531841943042560024241247360x7ff9ba03a8000x7ff8ae43678000012073469038295317120734690384523221207346903863536112073469038639086
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018476531376531841943042560024241264640x7ff9ba03a7000x7ff8ae4367c000012073469038699498120734690388568001207346903898975912073469038993455
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018676531376531841943042560020241279360x7ff9ba03a6000x7ff8ae43680000012073469039041113120734690392084781207346903947615712073469039503182
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018876531376531841943042560028241296640x7ff9ba03a5000x7ff8ae43684000012073469039541333120734690397102361207346903996591412073469039987282
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019076531376531841943042560024241313920x7ff9ba03a4000x7ff8ae43688000012073469040038296120734690401943931207346904032863212073469040332724
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019276531376531841943042560024241336320x7ff9ba03a3000x7ff8ae4368c000012073469040383288120734690405428711207346904073407012073469040754858
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019476531376531841943042560024241353600x7ff9ba03aa000x7ff8ae43690000012073469040812114120734690409708691207346904111230912073469041117171
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019676531376531841943042560020241368320x7ff9ba03a9000x7ff8ae43694000012073469041168246120734690413265471207346904160926612073469041656884
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019876531376531841943042560028241385600x7ff9ba03a8000x7ff8ae43698000012073469041683504120734690418559851207346904211806412073469042170118
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020076531376531841943042560024241402880x7ff9ba03a7000x7ff8ae4369c000012073469042194754120734690423721421207346904250510212073469042509128
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020276531376531841943042560024241427840x7ff9ba03a6000x7ff8ae436a0000012073469042560864120734690427167811207346904292653912073469042951821
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020476531376531841943042560024241447680x7ff9ba03a5000x7ff8ae436a4000012073469043015629120734690431758181207346904331645812073469043320346
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020676531376531841943042560020241457280x7ff9ba03a4000x7ff8ae436a8000012073469043370008120734690435380561207346904387517512073469043900734
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020876531376531841943042560028241477120x7ff9ba03a3000x7ff8ae436ac000012073469043946610120734690441082941207346904436973212073469044395383
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021076531376531841943042560024241496960x7ff9ba03aa000x7ff8ae436b0000012073469044439926120734690445972511207346904473437012073469044738561
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021276531376531841943042560024241521920x7ff9ba03a9000x7ff8ae436b4000012073469044785799120734690449514891207346904517868812073469045207603
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021476531376531841943042560024241541760x7ff9ba03a8000x7ff8ae436b8000012073469045262315120734690454215671207346904555932612073469045563154
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021676531376531841943042560020241556480x7ff9ba03a7000x7ff8ae436bc000012073469045614239120734690457722851207346904610124412073469046134485
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021876531376531841943042560028241576320x7ff9ba03a6000x7ff8ae436c0000012073469046176253120734690463401231207346904660540112073469046632962
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022076531376531841943042560024241596160x7ff9ba03a5000x7ff8ae436c4000012073469046676553120734690468332401207346904696667912073469046970769
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022276531376531841943042560024241623680x7ff9ba03a4000x7ff8ae436c8000012073469047030791120734690471909981207346904743643712073469047465699
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022476531376531841943042560024241646080x7ff9ba03a3000x7ff8ae436cc000012073469047523236120734690476797961207346904781851512073469047822402
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022676531376531841943042560020241663360x7ff9ba03aa000x7ff8ae436d0000012073469047869971120734690480469191207346904842323812073469048455469
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022876531376531841943042560028241685760x7ff9ba03a9000x7ff8ae436d4000012073469048487739120734690486547561207346904891731512073469048937154
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023076531376531841943042560024241708160x7ff9ba03a8000x7ff8ae436d8000012073469048981146120734690491443541207346904928787312073469049290771
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023276531376531841943042560024241740800x7ff9ba03a7000x7ff8ae436dc000012073469049340323120734690495006721207346904977987112073469049802712
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023476531376531841943042560024241765760x7ff9ba03a6000x7ff8ae436e0000012073469049859648120734690500301101207346905016979012073469050173341
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023676531376531841943042560020241777920x7ff9ba03a5000x7ff8ae436e4000012073469050221731120734690503923491207346905081682712073469050841834
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023876531376531841943042560028241802880x7ff9ba03a4000x7ff8ae436e8000012073469050885334120734690510496261207346905131490512073469051341522
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024076531376531841943042560024241827840x7ff9ba03a3000x7ff8ae436ec000012073469051383801120734690515432251207346905168018412073469051683387
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024276531376531841943042560024241863040x7ff9ba03aa000x7ff8ae436f0000012073469051735344120734690518926631207346905220754212073469052234832
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024476531376531841943042560024241893120x7ff9ba03a9000x7ff8ae436f4000012073469052286408120734690524491411207346905260018012073469052603297
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024676531376531841943042560020241907840x7ff9ba03a8000x7ff8ae436f8000012073469052651997120734690528145801207346905333441812073469053361917
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024876531376531841943042560028241937920x7ff9ba03a7000x7ff8ae436fc000012073469053404516120734690535670571207346905386497612073469053887684
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025076531376531841943042560024241968000x7ff9ba03a6000x7ff8ae43700000012073469053933369120734690541001751207346905425377412073469054257090
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025276531376531841943042560024242010880x7ff9ba03a5000x7ff8ae43704000012073469054312052120734690544708931207346905488129212073469054904363
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025476531376531841943042560024242046080x7ff9ba03a4000x7ff8ae43708000012073469054961590120734690551291311207346905530497012073469055308104
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025676531376531841943042560020242060800x7ff9ba03a3000x7ff8ae4370c000012073469055357846120734690555184091207346905614160712073469056166238
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025876531376531841943042560028242096000x7ff9ba03aa000x7ff8ae43710000012073469056211012120734690563712061207346905669824512073469056722392
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026076531376531841943042560024242131200x7ff9ba03a9000x7ff8ae43714000012073469056767125120734690569236841207346905710144312073469057104813
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026276531376531841943042560024242181760x7ff9ba03a8000x7ff8ae43718000012073469057154775120734690573262421207346905778208012073469057805956
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026476531376531841943042560024242222080x7ff9ba03a7000x7ff8ae4371c000012073469057863482120734690580297591207346905823039912073469058257745
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026676531376531841943042560020242239360x7ff9ba03a6000x7ff8ae43720000012073469058302228120734690584659181207346905916927512073469059194566
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026876531376531841943042560028242279680x7ff9ba03a5000x7ff8ae43724000012073469059239550120734690593967941207346905977167312073469059795463
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027076531376531841943042560024242320000x7ff9ba03a4000x7ff8ae43728000012073469059837651120734690599939121207346906019695112073469060224099
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027276531376531841943042560024242378240x7ff9ba03a3000x7ff8ae4372c000012073469060267470120734690604299101207346906095630812073469060979834
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027476531376531841943042560024242423680x7ff9ba03aa000x7ff8ae43730000012073469061045406120734690612067071207346906143006612073469061457421
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027676531376531841943042560020242435840x7ff9ba03a9000x7ff8ae43734000012073469061500541120734690616572651207346906245662212073469062485422
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027876531376531841943042560028242481280x7ff9ba03a8000x7ff8ae43738000012073469062533361120734690627025411207346906312286012073469063150938
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028076531376531841943042560024242526720x7ff9ba03a7000x7ff8ae4373c000012073469063193678120734690633516591207346906357773812073469063601666
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028276531376531841943042560024242592640x7ff9ba03a6000x7ff8ae43740000012073469063650948120734690638087771207346906440557512073469064458008
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028476531376531841943042560024242648320x7ff9ba03a5000x7ff8ae43744000012073469064499334120734690646593341207346906492845312073469065113596
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028676531376531841943042560020242663040x7ff9ba03a4000x7ff8ae43748000012073469065146667120734690653183711207346906630284812073469066371674
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028876531376531841943042560028242718720x7ff9ba03a3000x7ff8ae4374c000012073469066410035120734690665713261207346906708556412073469067153998
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029076531376531841943042560024242774400x7ff9ba03aa000x7ff8ae43750000012073469067190205120734690673519631207346906762396212073469067690234
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029276531376531841943042560012242799360x7ff9ba03a9000x7ff8ae43754000012073469067725580120734690678871611207346906862555912073469068696514
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029476531376531841943042560024242865280x7ff9ba03a8000x7ff8ae43758000012073469068745455120734690689084371207346906922427612073469069293504
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029676531376531841943042560020242880000x7ff9ba03a7000x7ff8ae4375c000012073469069329070120734690694906751207346907066331112073469070732408
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029876531376531841943042560032242945920x7ff9ba03a6000x7ff8ae43760000012073469070769176120734690709474701207346907155706712073469071628022
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030076531376531841943042560024243011840x7ff9ba03a5000x7ff8ae43764000012073469071652217120734690718385061207346907215850512073469072229941
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030276531376531841943042560012243049600x7ff9ba03a4000x7ff8ae43768000012073469072261800120734690724378641207346907331626012073469073384987
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030476531376531841943042560024243136000x7ff9ba03a3000x7ff8ae4376c000012073469073433427120734690735978591207346907401017812073469074079167
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030676531376531841943042560020243148160x7ff9ba03aa000x7ff8ae43770000012073469074114193120734690742768971207346907582665112073469075895252
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030876531376531841943042560020243175680x7ff9ba03a9000x7ff8ae43774000012073469075931580120734690761004101207346907689640712073469076966303
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031076531376531841943042560012243203200x7ff9ba03a8000x7ff8ae43778000012073469077007549120734690771773651207346907761496412073469077683195
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031276531376531841943042560012243240960x7ff9ba03a7000x7ff8ae4377c000012073469077720995120734690778808831207346907903911812073469079107712
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031476531376531841943042560012243288960x7ff9ba03a6000x7ff8ae43780000012073469079155221120734690793181571207346908010535412073469080174495
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031676531376531841943042560020243301120x7ff9ba03a5000x7ff8ae43784000012073469080205542120734690803824731207346908343478112073469083504062
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031876531376531841943042560020243328640x7ff9ba03a4000x7ff8ae43788000012073469083533327120734690837194201207346908526309412073469085331619
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032076531376531841943042560012243356160x7ff9ba03a3000x7ff8ae4378c000012073469085363428120734690855414931207346908633237012073469086401026
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032276531376531841943042560012243393920x7ff9ba03aa000x7ff8ae43790000012073469086431022120734690866091691207346908889204012073469088960773
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032476531376531841943042560012243441920x7ff9ba03a9000x7ff8ae43794000012073469089011978120734690891749191207346909071059312073469090781286
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032676531376531841943042560020243454080x7ff9ba03a8000x7ff8ae43798000012073469090854162120734690910150721207346909707456912073469097144822
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032876531376531841943042560020243481600x7ff9ba03a7000x7ff8ae4379c000012073469097178314120734690973568071207346910040255612073469100472526
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033076531376531841943042560012243509120x7ff9ba03a6000x7ff8ae437a0000012073469100503294120734691006809551207346910222078912073469102289593
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332765313765318419430425600122400x7ff9ba03a5000x7ff8ae437a4000012073469102322043120734691024998281207346910702685012073469107098019