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

39 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000896557896562335544322560083264640x00x7f1e26a0418012075850856331131120758508563741941207585085669675112075850856805743
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00289655789656232768256002424124800x00x7f1e26a3510012075850872219850120758508723300121207585087233641212075850872341927
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0048965578965624194304256002424129280x7f1f56b4e9000x7f1e26a3514012075850872399754120758508724143321207585087254601012075850872549482
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0068965578965624194304256003624136320x7f1f56b4e8000x7f1e26a3518012075850872602281120758508726148101207585087285672812075850872954465
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0088965578965624194304256002824140800x7f1f56b4e7000x7f1e26a351c012075850872987466120758508730000861207585087328200412075850873382440
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00108965578965624194304256002424145280x7f1f56b4e6000x7f1e26a3520012075850873416424120758508734288831207585087355480112075850873557977
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00128965578965624194304256002424149760x7f1f56b4e5000x7f1e26a3524012075850873592461120758508736069611207585087373304012075850873736008
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00148965578965624194304256002424154240x7f1f56b4e4000x7f1e26a3528012075850873796159120758508738109591207585087393495812075850873937382
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00168965578965624194304256002824161280x7f1f56b4e3000x7f1e26a352c012075850873973779120758508739895181207585087423415512075850874332496
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00188965578965624194304256002824168320x7f1f56b4ea000x7f1e26a3530012075850874377840120758508743906341207585087463783212075850874735485
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00208965578965624194304256002424175360x7f1f56b4e9000x7f1e26a3534012075850874763717120758508747755911207585087489975012075850874902826
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00228965578965624194304256002424182400x7f1f56b4e8000x7f1e26a3538012075850874936459120758508749491891207585087507414812075850875077370
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00248965578965624194304256002424189440x7f1f56b4e7000x7f1e26a353c012075850875126261120758508751381471207585087526294612075850875265941
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00268965578965624194304256002824199040x7f1f56b4e6000x7f1e26a3540012075850875299153120758508753165461207585087556742412075850875640998
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00288965578965624194304256002824206080x7f1f56b4e5000x7f1e26a3544012075850875670873120758508756831031207585087596310012075850876033417
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00308965578965624194304256002424213120x7f1f56b4e4000x7f1e26a3548012075850876088099120758508761018191207585087622677812075850876229772
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00328965578965624194304256002424220160x7f1f56b4e3000x7f1e26a354c012075850876262012120758508762768571207585087640181612075850876404998
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00348965578965624194304256002424227200x7f1f56b4ea000x7f1e26a3550012075850876449811120758508764659761207585087659093512075850876593678
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00368965578965624194304256002824236800x7f1f56b4e9000x7f1e26a3554012075850876626660120758508766419741207585087688805212075850876960390
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00388965578965624194304256002824243840x7f1f56b4e8000x7f1e26a3558012075850876989434120758508770014911207585087724468912075850877316592
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00408965578965624194304256002424250880x7f1f56b4e7000x7f1e26a355c012075850877359061120758508773730081207585087749700712075850877499953
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00428965578965624194304256002424257920x7f1f56b4e6000x7f1e26a3560012075850877532653120758508775474061207585087767300512075850877675850
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00448965578965624194304256002424264960x7f1f56b4e5000x7f1e26a3564012075850877720032120758508777320451207585087785684312075850877859932
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00468965578965624194304256002824277120x7f1f56b4e4000x7f1e26a3568012075850877894015120758508779062831207585087815732112075850878255587
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00488965578965624194304256002824284160x7f1f56b4e3000x7f1e26a356c012075850878284791120758508782981201207585087854339712075850878612610
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00508965578965624194304256002424291200x7f1f56b4ea000x7f1e26a3570012075850878643458120758508786553961207585087877955512075850878782486
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00528965578965624194304256002424300800x7f1f56b4e9000x7f1e26a3574012075850878814536120758508788261151207585087895091412075850878953674
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00548965578965624194304256002424307840x7f1f56b4e8000x7f1e26a3578012075850878995422120758508790075531207585087913235212075850879135112
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00568965578965624194304256002824320000x7f1f56b4e7000x7f1e26a357c012075850879168343120758508791857921207585087943746912075850879535476
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00588965578965624194304256002824329600x7f1f56b4e6000x7f1e26a3580012075850879563548120758508795752281207585087981922612075850879917956
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00608965578965624194304256002424339200x7f1f56b4e5000x7f1e26a3584012075850879944916120758508799577851207585088008274412075850880085928
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00628965578965624194304256002424348800x7f1f56b4e4000x7f1e26a3588012075850880119401120758508801310631207585088025666212075850880259862
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00648965578965624194304256002424358400x7f1f56b4e3000x7f1e26a358c012075850880301259120758508803169821207585088044146112075850880444285
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00668965578965624194304256002824373120x7f1f56b4ea000x7f1e26a3590012075850880477927120758508804923401207585088073761812075850880815785
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00688965578965624194304256002824382720x7f1f56b4e9000x7f1e26a3594012075850880841873120758508808579371207585088110225512075850881184470
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00708965578965624194304256002424392320x7f1f56b4e8000x7f1e26a3598012075850881214807120758508812273741207585088135217312075850881355037
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00728965578965624194304256002424401920x7f1f56b4e7000x7f1e26a359c012075850881388239120758508814000121207585088152609112075850881529321
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00748965578965624194304256002424411520x7f1f56b4e6000x7f1e26a35a0012075850881571359120758508815832101207585088170752912075850881709997
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00768965578965624194304256002824426240x7f1f56b4e5000x7f1e26a35a4012075850881742417120758508817564891207585088201024712075850882043036
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00788965578965624194304256002824435840x7f1f56b4e4000x7f1e26a35a8012075850882075797120758508820900861207585088233328412075850882362990
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00808965578965624194304256002424445440x7f1f56b4e3000x7f1e26a35ac012075850882391123120758508824062431207585088253168212075850882534499
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00828965578965624194304256002424457600x7f1f56b4ea000x7f1e26a35b0012075850882569174120758508825830421207585088270928112075850882712179
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00848965578965624194304256002424467200x7f1f56b4e9000x7f1e26a35b4012075850882756642120758508827707201207585088289631912075850882899527
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00868965578965624194304256002824484480x7f1f56b4e8000x7f1e26a35b8012075850882931777120758508829460781207585088320383612075850883233248
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00888965578965624194304256002824494080x7f1f56b4e7000x7f1e26a35bc012075850883265508120758508832790351207585088352399312075850883547903
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00908965578965624194304256002424503680x7f1f56b4e6000x7f1e26a35c0012075850883574843120758508835889531207585088371295212075850883715574
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00928965578965624194304256002424515840x7f1f56b4e5000x7f1e26a35c4012075850883748004120758508837614311207585088388815012075850883890710
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00948965578965624194304256002424525440x7f1f56b4e4000x7f1e26a35c8012075850883933399120758508839463901207585088407086812075850884073439
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00968965578965624194304256002824542720x7f1f56b4e3000x7f1e26a35cc012075850884108905120758508841238281207585088437966612075850884400758
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00988965578965624194304256002824554880x7f1f56b4ea000x7f1e26a35d0012075850884430042120758508844441451207585088469038312075850884717616
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001008965578965624194304256002424567040x7f1f56b4e9000x7f1e26a35d4012075850884748464120758508847630221207585088488782112075850884890798
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001028965578965624194304256002424581760x7f1f56b4e8000x7f1e26a35d8012075850884924631120758508849380611207585088506542012075850885068048
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001048965578965624194304256002424593920x7f1f56b4e7000x7f1e26a35dc012075850885111959120758508851260591207585088525149812075850885254324
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001068965578965624194304256002824613760x7f1f56b4e6000x7f1e26a35e0012075850885286383120758508853002981207585088555645512075850885577134
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001088965578965624194304256002824625920x7f1f56b4e5000x7f1e26a35e4012075850885613020120758508856278151207585088590893212075850885932444
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001108965578965624194304256002424638080x7f1f56b4e4000x7f1e26a35e8012075850885961719120758508859756521207585088610125112075850886104193
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001128965578965624194304256002424652800x7f1f56b4e3000x7f1e26a35ec012075850886140120120758508861532501207585088628124912075850886283777
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001148965578965624194304256002424664960x7f1f56b4ea000x7f1e26a35f0012075850886329853120758508863454081207585088647068712075850886473169
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001168965578965624194304256002824684800x7f1f56b4e9000x7f1e26a35f4012075850886505850120758508865196471207585088677404512075850886797892
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001188965578965624194304256002824696960x7f1f56b4e8000x7f1e26a35f8012075850886826055120758508868396441207585088708860212075850887116515
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001208965578965624194304256002424709120x7f1f56b4e7000x7f1e26a35fc012075850887145448120758508871594811207585088728444012075850887287072
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001228965578965624194304256002424723840x7f1f56b4e6000x7f1e26a3600012075850887318450120758508873322801207585088746843812075850887471314
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001248965578965624194304256002424736000x7f1f56b4e5000x7f1e26a3604012075850887514184120758508875281181207585088765259712075850887655196
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001268965578965624194304256002824758400x7f1f56b4e4000x7f1e26a3608012075850887688878120758508877029961207585088796155412075850887984608
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001288965578965624194304256002824770560x7f1f56b4e3000x7f1e26a360c012075850888020404120758508880341931207585088828027112075850888310013
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001308965578965624194304256002424782720x7f1f56b4ea000x7f1e26a3610012075850888341812120758508883561111207585088848122912075850888483966
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001328965578965624194304256002424800000x7f1f56b4e9000x7f1e26a3614012075850888516546120758508885300291207585088867194812075850888674590
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001348965578965624194304256002424812160x7f1f56b4e8000x7f1e26a3618012075850888716198120758508887306671207585088885626612075850888858873
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001368965578965624194304256002824834560x7f1f56b4e7000x7f1e26a361c012075850888892405120758508889047461207585088915562412075850889183616
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001388965578965624194304256002824849280x7f1f56b4e6000x7f1e26a3620012075850889212119120758508892249031207585088946986112075850889498662
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001408965578965624194304256002424864000x7f1f56b4e5000x7f1e26a3624012075850889525572120758508895399401207585088966537912075850889667956
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001428965578965624194304256002424881280x7f1f56b4e4000x7f1e26a3628012075850889701278120758508897152991207585088986457712075850889867147
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001448965578965624194304256002424896000x7f1f56b4e3000x7f1e26a362c012075850889929522120758508899424971207585089006793512075850890071126
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001468965578965624194304256002824920960x7f1f56b4ea000x7f1e26a3630012075850890105590120758508901200951207585089038457312075850890409164
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001488965578965624194304256002824935680x7f1f56b4e9000x7f1e26a3634012075850890437797120758508904516121207585089069833012075850890721354
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001508965578965624194304256002424950400x7f1f56b4e8000x7f1e26a3638012075850890749216120758508907629691207585089088840812075850890891250
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001528965578965624194304256002424967680x7f1f56b4e7000x7f1e26a363c012075850890922608120758508909362481207585089109256612075850891095890
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001548965578965624194304256002424982400x7f1f56b4e6000x7f1e26a3640012075850891138179120758508911519261207585089127656512075850891279121
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015689655789656241943042560028241007360x7f1f56b4e5000x7f1e26a3644012075850891312002120758508913248841207585089158136212075850891608783
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015889655789656241943042560028241022080x7f1f56b4e4000x7f1e26a3648012075850891638238120758508916519211207585089189847912075850891921835
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016089655789656241943042560024241036800x7f1f56b4e3000x7f1e26a364c012075850891952522120758508919663191207585089209143812075850892094115
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016289655789656241943042560024241056640x7f1f56b4ea000x7f1e26a3650012075850892128529120758508921423171207585089230695612075850892309616
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016489655789656241943042560024241071360x7f1f56b4e9000x7f1e26a3654012075850892352375120758508923656751207585089249159412075850892494239
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016689655789656241943042560028241098880x7f1f56b4e8000x7f1e26a3658012075850892526389120758508925403941207585089280039112075850892823811
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016889655789656241943042560028241113600x7f1f56b4e7000x7f1e26a365c012075850892851974120758508928650311207585089311030912075850893137434
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017089655789656241943042560024241128320x7f1f56b4e6000x7f1e26a3660012075850893165476120758508931797481207585089330454712075850893307360
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017289655789656241943042560024241148160x7f1f56b4e5000x7f1e26a3664012075850893339410120758508933517461207585089352390512075850893526487
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017489655789656241943042560024241162880x7f1f56b4e4000x7f1e26a3668012075850893570749120758508935843841207585089371014312075850893712834
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017689655789656241943042560028241190400x7f1f56b4e3000x7f1e26a366c012075850893744963120758508937591031207585089401062112075850894038910
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017889655789656241943042560028241207680x7f1f56b4ea000x7f1e26a3670012075850894067743120758508940816601207585089432981812075850894353184
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018089655789656241943042560024241224960x7f1f56b4e9000x7f1e26a3674012075850894384141120758508943976571207585089452373612075850894526596
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018289655789656241943042560024241247360x7f1f56b4e8000x7f1e26a3678012075850894558555120758508945714161207585089475333412075850894756403
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018489655789656241943042560024241264640x7f1f56b4e7000x7f1e26a367c012075850894797850120758508948109341207585089493749212075850894940154
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018689655789656241943042560020241279360x7f1f56b4e6000x7f1e26a3680012075850894972054120758508949858121207585089524869012075850895276409
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018889655789656241943042560028241296640x7f1f56b4e5000x7f1e26a3684012075850895305604120758508953198891207585089556548712075850895588790
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019089655789656241943042560024241313920x7f1f56b4e4000x7f1e26a3688012075850895620128120758508956338061207585089575924512075850895762102
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019289655789656241943042560024241336320x7f1f56b4e3000x7f1e26a368c012075850895795214120758508958090051207585089599988312075850896008400
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019489655789656241943042560024241353600x7f1f56b4ea000x7f1e26a3690012075850896045258120758508960590831207585089618548112075850896188334
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019689655789656241943042560020241368320x7f1f56b4e9000x7f1e26a3694012075850896219803120758508962352411207585089651811812075850896542062
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019889655789656241943042560028241385600x7f1f56b4e8000x7f1e26a3698012075850896568932120758508965821181207585089682803612075850896851657
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020089655789656241943042560024241402880x7f1f56b4e7000x7f1e26a369c012075850896877695120758508968913951207585089701923412075850897022454
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020289655789656241943042560024241427840x7f1f56b4e6000x7f1e26a36a0012075850897058582120758508970717141207585089728035212075850897308456
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020489655789656241943042560024241447680x7f1f56b4e5000x7f1e26a36a4012075850897347979120758508973613111207585089749059012075850897493640
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020689655789656241943042560020241457280x7f1f56b4e4000x7f1e26a36a8012075850897527022120758508975395491207585089787618612075850897900396
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020889655789656241943042560028241477120x7f1f56b4e3000x7f1e26a36ac012075850897928678120758508979430661207585089819266412075850898218307
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021089655789656241943042560024241496960x7f1f56b4ea000x7f1e26a36b0012075850898245547120758508982595431207585089838770212075850898390547
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021289655789656241943042560024241521920x7f1f56b4e9000x7f1e26a36b4012075850898423117120758508984365021207585089866417912075850898684112
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021489655789656241943042560024241541760x7f1f56b4e8000x7f1e26a36b8012075850898721843120758508987348991207585089886241812075850898865049
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021689655789656241943042560020241556480x7f1f56b4e7000x7f1e26a36bc012075850898897689120758508989120171207585089924065412075850899268929
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021889655789656241943042560028241576320x7f1f56b4e6000x7f1e26a36c0012075850899298104120758508993120141207585089956081212075850899584055
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022089655789656241943042560024241596160x7f1f56b4e5000x7f1e26a36c4012075850899615093120758508996291311207585089975809012075850899760884
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022289655789656241943042560024241623680x7f1f56b4e4000x7f1e26a36c8012075850899791561120758508998049691207585090004944712075850900074727
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022489655789656241943042560024241646080x7f1f56b4e3000x7f1e26a36cc012075850900112637120758509001275271207585090025616512075850900259430
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022689655789656241943042560020241663360x7f1f56b4ea000x7f1e26a36d0012075850900292482120758509003065651207585090068128212075850900708324
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022889655789656241943042560028241685760x7f1f56b4e9000x7f1e26a36d4012075850900737198120758509007499211207585090100255912075850901030734
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023089655789656241943042560024241708160x7f1f56b4e8000x7f1e26a36d8012075850901057824120758509010726381207585090120303712075850901206059
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023289655789656241943042560024241740800x7f1f56b4e7000x7f1e26a36dc012075850901238019120758509012513571207585090152895412075850901551752
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023489655789656241943042560024241765760x7f1f56b4e6000x7f1e26a36e0012075850901592147120758509016052731207585090174191212075850901744610
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023689655789656241943042560020241777920x7f1f56b4e5000x7f1e26a36e4012075850901777040120758509017908721207585090221406812075850902240712
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023889655789656241943042560028241802880x7f1f56b4e4000x7f1e26a36e8012075850902268634120758509022823881207585090253710512075850902564294
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024089655789656241943042560024241827840x7f1f56b4e3000x7f1e26a36ec012075850902590733120758509026051051207585090274158312075850902744499
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024289655789656241943042560024241863040x7f1f56b4ea000x7f1e26a36f0012075850902776628120758509027899031207585090310302012075850903132540
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024489655789656241943042560024241893120x7f1f56b4e9000x7f1e26a36f4012075850903170530120758509031836601207585090333597812075850903339264
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024689655789656241943042560020241907840x7f1f56b4e8000x7f1e26a36f8012075850903371634120758509033860581207585090390285312075850903926465
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024889655789656241943042560028241937920x7f1f56b4e7000x7f1e26a36fc012075850903955940120758509039700531207585090426685012075850904299308
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025089655789656241943042560024241968000x7f1f56b4e6000x7f1e26a3700012075850904331428120758509043450891207585090449852812075850904501694
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025289655789656241943042560024242010880x7f1f56b4e5000x7f1e26a3704012075850904533022120758509045460471207585090493068412075850904954646
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025489655789656241943042560024242046080x7f1f56b4e4000x7f1e26a3708012075850904991965120758509050055631207585090518092212075850905184163
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025689655789656241943042560020242060800x7f1f56b4e3000x7f1e26a370c012075850905217374120758509052308411207585090584059612075850905868334
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025889655789656241943042560028242096000x7f1f56b4ea000x7f1e26a3710012075850905895054120758509059081151207585090623387312075850906266504
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026089655789656241943042560024242131200x7f1f56b4e9000x7f1e26a3714012075850906294526120758509063076321207585090648587012075850906489138
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026289655789656241943042560024242181760x7f1f56b4e8000x7f1e26a3718012075850906521748120758509065346701207585090698938612075850907021487
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026489655789656241943042560024242222080x7f1f56b4e7000x7f1e26a371c012075850907068915120758509070817051207585090728058312075850907309202
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026689655789656241943042560020242239360x7f1f56b4e6000x7f1e26a3720012075850907339318120758509073527431207585090805609612075850908084533
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026889655789656241943042560028242279680x7f1f56b4e5000x7f1e26a3724012075850908116652120758509081300161207585090850281312075850908529920
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027089655789656241943042560024242320000x7f1f56b4e4000x7f1e26a3728012075850908560597120758509085738521207585090877673012075850908803429
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027289655789656241943042560024242378240x7f1f56b4e3000x7f1e26a372c012075850908831060120758509088436101207585090936936512075850909401410
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027489655789656241943042560024242423680x7f1f56b4ea000x7f1e26a3730012075850909439972120758509094528841207585090967608212075850909702991
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027689655789656241943042560020242435840x7f1f56b4e9000x7f1e26a3734012075850909733056120758509097468021207585091054423412075850910573168
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027889655789656241943042560028242481280x7f1f56b4e8000x7f1e26a3738012075850910607732120758509106213541207585091103975012075850911068959
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028089655789656241943042560024242526720x7f1f56b4e7000x7f1e26a373c012075850911104976120758509111194291207585091134502712075850911369377
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028289655789656241943042560024242592640x7f1f56b4e6000x7f1e26a3740012075850911402389120758509114152671207585091201190212075850912041006
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028489655789656241943042560024242648320x7f1f56b4e5000x7f1e26a3744012075850912081281120758509120946211207585091236373812075850912391447
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028689655789656241943042560020242663040x7f1f56b4e4000x7f1e26a3748012075850912423146120758509124344581207585091341812912075850913446578
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028889655789656241943042560028242718720x7f1f56b4e3000x7f1e26a374c012075850913476734120758509134904481207585091402276412075850914051332
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029089655789656241943042560024242774400x7f1f56b4ea000x7f1e26a3750012075850914086347120758509140997231207585091437124112075850914398697
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029289655789656241943042560012242799360x7f1f56b4e9000x7f1e26a3754012075850914428453120758509144414801207585091517843412075850915207931
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029489655789656241943042560024242865280x7f1f56b4e8000x7f1e26a3758012075850915249498120758509152627531207585091557747012075850915604578
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029689655789656241943042560020242880000x7f1f56b4e7000x7f1e26a375c012075850915634193120758509156469091207585091681793912075850916847508
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029889655789656241943042560032242945920x7f1f56b4e6000x7f1e26a3760012075850916880129120758509168937781207585091750337312075850917538132
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030089655789656241943042560024243011840x7f1f56b4e5000x7f1e26a3764012075850917571293120758509175849721207585091790416912075850917933016
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030289655789656241943042560012243049600x7f1f56b4e4000x7f1e26a3768012075850917962460120758509179760091207585091885264112075850918885175
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030489655789656241943042560024243136000x7f1f56b4e3000x7f1e26a376c012075850918926702120758509189397951207585091937195212075850919405572
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030689655789656241943042560020243148160x7f1f56b4ea000x7f1e26a3770012075850919435849120758509194490701207585092099785912075850921071418
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030889655789656241943042560020243175680x7f1f56b4e9000x7f1e26a3774012075850921104089120758509211186581207585092191241212075850921985166
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031089655789656241943042560012243203200x7f1f56b4e8000x7f1e26a3778012075850922030801120758509220448911207585092245832812075850922531592
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031289655789656241943042560012243240960x7f1f56b4e7000x7f1e26a377c012075850922562409120758509225764081207585092373479912075850923808385
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031489655789656241943042560012243288960x7f1f56b4e6000x7f1e26a3780012075850923851395120758509238658381207585092465047312075850924725389
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031689655789656241943042560020243301120x7f1f56b4e5000x7f1e26a3784012075850924759082120758509247733521207585092782389012075850927896893
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031889655789656241943042560020243328640x7f1f56b4e4000x7f1e26a3788012075850927931187120758509279448491207585092948531812075850929561206
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032089655789656241943042560012243356160x7f1f56b4e3000x7f1e26a378c012075850929593747120758509296081971207585093039651112075850930468903
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032289655789656241943042560012243393920x7f1f56b4ea000x7f1e26a3790012075850930503898120758509305174701207585093279889412075850932871628
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032489655789656241943042560012243441920x7f1f56b4e9000x7f1e26a3794012075850932913827120758509329272131207585093446208212075850934538176
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032689655789656241943042560020243454080x7f1f56b4e8000x7f1e26a3798012075850934566338120758509345817611207585094063563712075850940708222
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032889655789656241943042560020243481600x7f1f56b4e7000x7f1e26a379c012075850940741394120758509407545171207585094379449512075850943867684
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033089655789656241943042560012243509120x7f1f56b4e6000x7f1e26a37a0012075850943900685120758509439156141207585094545496312075850945530144
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332896557896562419430425600122400x7f1f56b4e5000x7f1e26a37a4012075850945560240120758509455740021207585095010068912075850950173914