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

66 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_VALU_ADD_F16SQ_INSTS_VALU_MUL_F16SQ_INSTS_VALU_FMA_F16SQ_INSTS_VALU_TRANS_F16SQ_INSTS_VALU_ADD_F32SQ_INSTS_VALU_MUL_F32SQ_INSTS_VALU_FMA_F32SQ_INSTS_VALU_TRANS_F32TCP_TCC_READ_REQ_sumTCP_TOTAL_CACHE_ACCESSES_sumTCP_TCC_WRITE_REQ_sumTCP_TCC_ATOMIC_WITH_RET_REQ_sumTCC_EA_RDREQ_32B_sumTCC_EA_RDREQ_sumTCC_EA_WRREQ_64B_sumTCC_EA_WRREQ_sumSQ_INSTS_VALU_ADD_F64SQ_INSTS_VALU_MUL_F64SQ_INSTS_VALU_FMA_F64SQ_INSTS_VALU_TRANS_F64SQ_INSTS_VALU_MFMA_MOPS_F16SQ_INSTS_VALU_MFMA_MOPS_BF16SQ_INSTS_VALU_MFMA_MOPS_F32SQ_INSTS_VALU_MFMA_MOPS_F64TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sumSQ_LDS_IDX_ACTIVESQ_LDS_BANK_CONFLICTDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000174459174459335544322560043241600x00x7ff75ae04280000000000.00000000008388608.00000000004194304.00000000000.00000000000.0000000000311.00000000004128768.00000000004128768.0000000000000000000.00000000000016783573042989167541485411921678372466961016783724755920
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00217445917445932768256001224138880x00x7ff75ae23f80000000008192.000000000016384.00000000000.00000000000.00000000000.00000000008261.00000000000.00000000000.0000000000000000000.00000000000016783730483369167837246696101678373084739216783730853797
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051744591744594194304256001224143360x7ff75dd333800x7ff75ae23fc000000026214402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097343.00000000000.00000000000.0000000000000000000.00000000000016783731445389167837308473921678373209011716783732090038
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081744591744594194304256001624150400x7ff75dd332000x7ff75ae2400000000026214404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194584.00000000000.00000000000.0000000000000000000.00000000000016783732688510167837320901171678373341412216783733413417
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111744591744594194304256001624154880x7ff75dd330800x7ff75ae24040000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194593.00000000000.00000000000.000000000000262144000000.00000000000016783734008268167837334141221678373464836616783734647098
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141744591744594194304256001224159360x7ff75b703f000x7ff75ae2408000262144000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097340.00000000000.00000000000.0000000000000000000.00000000000016783735242269167837346483661678373580325116783735802581
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171744591744594194304256001224163840x7ff75b703d800x7ff75ae240c0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097344.00000000000.00000000000.0000000000000000000.00000000000016783736395552167837358032511678373697685516783736976124
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201744591744594194304256001224170880x7ff75b703c000x7ff75ae2410000000065536002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097345.00000000000.00000000000.0000000000000000000.00000000000016783737582405167837369768551678373816821916783738168006
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231744591744594194304256001624177920x7ff75b703a800x7ff75ae2414000000078643204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194581.00000000000.00000000000.0000000000000000000.00000000000016783738762947167837381682191678373943254416783739431606
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261744591744594194304256001624184960x7ff75b7039000x7ff75ae24180000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194587.00000000000.00000000000.000000000000786432000000.00000000000016783740026258167837394325441678374068278916783740681437
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291744591744594194304256001624192000x7ff75b7037800x7ff75ae241c000786432000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097341.00000000000.00000000000.0000000000000000000.00000000000016783741276838167837406827891678374181895316783741817151
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321744591744594194304256001624199040x7ff75b7036000x7ff75ae24200000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097340.00000000000.00000000000.0000000000000000000.00000000000016783742412302167837418189531678374295319716783742951785
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351744591744594194304256001224206080x7ff75dd334800x7ff75ae24240000000104857602097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097339.00000000000.00000000000.0000000000000000000.00000000000016783743554646167837429531971678374411144216783744109469
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381744591744594194304256001624213120x7ff75dd333000x7ff75ae24280000000131072004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194597.00000000000.00000000000.0000000000000000000.00000000000016783744704680167837441114421678374533208616783745330600
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411744591744594194304256001624220160x7ff75dd331800x7ff75ae242c0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194595.00000000000.00000000000.0000000000001310720000000.00000000000016783745924682167837453320861678374660777116783746605850
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441744591744594194304256001624227200x7ff75dd330000x7ff75ae24300001310720000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097343.00000000000.00000000000.0000000000000000000.00000000000016783747201551167837466077711678374777753516783747775543
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471744591744594194304256001224234240x7ff75b703e800x7ff75ae24340000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097343.00000000000.00000000000.0000000000000000000.00000000000016783748370165167837477775351678374900010016783748998105
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501744591744594194304256001224241280x7ff75b703d000x7ff75ae24380000000144179202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097340.00000000000.00000000000.0000000000000000000.00000000000016783749600396167837490001001678375012682416783750125069
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531744591744594194304256001624248320x7ff75b703b800x7ff75ae243c0000000183500804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194567.00000000000.00000000000.0000000000000000000.00000000000016783750721020167837501268241678375136794816783751366500
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561744591744594194304256001624255360x7ff75b703a000x7ff75ae24400000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194594.00000000000.00000000000.0000000000001835008000000.00000000000016783751961821167837513679481678375259323316783752591871
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591744591744594194304256001224262400x7ff75b7038800x7ff75ae24440001835008000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097345.00000000000.00000000000.0000000000000000000.00000000000016783753184742167837525932331678375374459716783753743365
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621744591744594194304256001224269440x7ff75b7037000x7ff75ae24480000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097348.00000000000.00000000000.0000000000000000000.00000000000016783754337776167837537445971678375489676216783754895388
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651744591744594194304256001224276480x7ff75dd335800x7ff75ae244c0000000183500802097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097343.00000000000.00000000000.0000000000000000000.00000000000016783755497119167837548967621678375605420616783756052782
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681744591744594194304256001624286080x7ff75dd334000x7ff75ae24500000000235929604194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194579.00000000000.00000000000.0000000000000000000.00000000000016783756647213167837560542061678375729949116783757298443
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711744591744594194304256001624293120x7ff75dd332800x7ff75ae24540000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194604.00000000000.00000000000.0000000000002359296000000.00000000000016783757892154167837572994911678375852045516783758519134
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741744591744594194304256001224300160x7ff75dd331000x7ff75ae24580002359296000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097344.00000000000.00000000000.0000000000000000000.00000000000016783759113075167837585204551678375966653916783759665048
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077174459174459419430425600824309760x7ff75b703f800x7ff75ae245c0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097347.00000000000.00000000000.0000000000000000000.00000000000016783760259549167837596665391678376081918416783760817682
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801744591744594194304256001224316800x7ff75b703e000x7ff75ae24600000000222822402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097350.00000000000.00000000000.0000000000000000000.00000000000016783761419663167837608191841678376197470816783761973275
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831744591744594194304256001624326400x7ff75b703c800x7ff75ae24640000000288358404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194590.00000000000.00000000000.0000000000000000000.00000000000016783762568046167837619747081678376323647316783763235045
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861744591744594194304256001224336000x7ff75b703b000x7ff75ae24680000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194591.00000000000.00000000000.0000000000002883584000000.00000000000016783763828666167837632364731678376447999716783764478526
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891744591744594194304256001224345600x7ff75b7039800x7ff75ae246c0002883584000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097349.00000000000.00000000000.0000000000000000000.00000000000016783765071947167837644799971678376563328216783765631629
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092174459174459419430425600824355200x7ff75b7038000x7ff75ae24700000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097354.00000000000.00000000000.0000000000000000000.00000000000016783766226300167837656332821678376678880616783766787233
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951744591744594194304256001224362240x7ff75b7036800x7ff75ae24740000000262144002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097343.00000000000.00000000000.0000000000000000000.00000000000016783767388484167837667888061678376795569016783767954186
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981744591744594194304256001224371840x7ff75dd335000x7ff75ae24780000000340787204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194583.00000000000.00000000000.0000000000000000000.00000000000016783768548587167837679556901678376919377516783769192517
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011744591744594194304256001224381440x7ff75dd333800x7ff75ae247c0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194578.00000000000.00000000000.0000000000003407872000000.00000000000016783769785598167837691937751678377044017916783770438798
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041744591744594194304256001224391040x7ff75dd332000x7ff75ae24800003407872000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097349.00000000000.00000000000.0000000000000000000.00000000000016783771033179167837704401791678377161570416783771614051
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107174459174459419430425600824403200x7ff75dd330800x7ff75ae24840000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097359.00000000000.00000000000.0000000000000000000.00000000000016783772209592167837716157041678377278018816783772778814
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101744591744594194304256001224412800x7ff75b703f000x7ff75ae24880000000301465602097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097349.00000000000.00000000000.0000000000000000000.00000000000016783773380585167837727801881678377394675216783773945217
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131744591744594194304256001224422400x7ff75b703d800x7ff75ae248c0000000393216004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194588.00000000000.00000000000.0000000000000000000.00000000000016783774539648167837739467521678377518307716783775181798
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161744591744594194304256001224432000x7ff75b703c000x7ff75ae24900000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194594.00000000000.00000000000.0000000000003932160000000.00000000000016783775775350167837751830771678377642164216783776420099
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119174459174459419430425600824441600x7ff75b703a800x7ff75ae24940003932160000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097350.00000000000.00000000000.0000000000000000000.00000000000016783777013880167837764216421678377756804616783777566413
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221744591744594194304256001224453760x7ff75b7039000x7ff75ae24980000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097357.00000000000.00000000000.0000000000000000000.00000000000016783778160714167837775680461678377873365016783778732116
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251744591744594194304256001224463360x7ff75b7037800x7ff75ae249c0000000340787202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097350.00000000000.00000000000.0000000000000000000.00000000000016783779333567167837787336501678377987989516783779878190
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281744591744594194304256001224475520x7ff75b7036000x7ff75ae24a00000000445644804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194582.00000000000.00000000000.0000000000000000000.00000000000016783780472471167837798798951678378111317916783781111471
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311744591744594194304256001224485120x7ff75dd334800x7ff75ae24a40000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194578.00000000000.00000000000.0000000000004456448000000.00000000000016783781706262167837811131791678378236470416783783617402
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134174459174459419430425600824494720x7ff75dd333000x7ff75ae24a80004456448000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097349.00000000000.00000000000.0000000000000000000.00000000000016783783636851167837823647041678378434423116783784342159
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371744591744594194304256001224506880x7ff75dd331800x7ff75ae24ac0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097361.00000000000.00000000000.0000000000000000000.00000000000016783784936950167837843442311678378545511516783785453554
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401744591744594194304256001224516480x7ff75dd330000x7ff75ae24b00000000380108802097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097346.00000000000.00000000000.0000000000000000000.00000000000016783786055585167837854551151678378659368016783786591678
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431744591744594194304256001224528640x7ff75b703e800x7ff75ae24b40000000498073604194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194576.00000000000.00000000000.0000000000000000000.00000000000016783787185599167837865900051678378780296116783787808490
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461744591744594194304256001224540800x7ff75b703d000x7ff75ae24b80000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194578.00000000000.00000000000.0000000000004980736000000.00000000000016783788398271167837878029611678378901863516783789020191
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149174459174459419430425600824552960x7ff75b703b800x7ff75ae24bc0004980736000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097351.00000000000.00000000000.0000000000000000000.00000000000016783789613623167837890186351678379013703216783790138936
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521744591744594194304256001224567680x7ff75b703a000x7ff75ae24c00000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097359.00000000000.00000000000.0000000000000000000.00000000000016783790733687167837901370321678379127718816783791279120
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551744591744594194304256001224577280x7ff75b7038800x7ff75ae24c40000000419430402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097356.00000000000.00000000000.0000000000000000000.00000000000016783791880481167837912771881678379241302416783792414924
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581744591744594194304256001224589440x7ff75b7037000x7ff75ae24c80000000550502404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194561.00000000000.00000000000.0000000000000000000.00000000000016783793008976167837924130241678379363654016783793638606
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611744591744594194304256001224601600x7ff75dd335800x7ff75ae24cc0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194561.00000000000.00000000000.0000000000005505024000000.00000000000016783794233687167837936365401678379489397516783794896046
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164174459174459419430425600824613760x7ff75dd334000x7ff75ae24d00005505024000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097358.00000000000.00000000000.0000000000000000000.00000000000016783795489367167837948939751678379604005216783796042240
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671744591744594194304256001224628480x7ff75dd332800x7ff75ae24d40000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097358.00000000000.00000000000.0000000000000000000.00000000000016783796636851167837960400521678379720724816783797209233
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701744591744594194304256001224638080x7ff75dd331000x7ff75ae24d80000000458752002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097354.00000000000.00000000000.0000000000000000000.00000000000016783797812154167837972072481678379839684416783798399005
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731744591744594194304256001224650240x7ff75b703f800x7ff75ae24dc0000000602931204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194570.00000000000.00000000000.0000000000000000000.00000000000016783798994336167837983968441678379963091916783799633086
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761744591744594194304256001224662400x7ff75b703e000x7ff75ae24e00000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194567.00000000000.00000000000.0000000000006029312000000.00000000000016783800226647167837996309191678380087603516783800878297
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179174459174459419430425600824674560x7ff75b703c800x7ff75ae24e40006029312000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097355.00000000000.00000000000.0000000000000000000.00000000000016783801472508167838008760351678380202195116783802023881
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821744591744594194304256001224689280x7ff75b703b000x7ff75ae24e80000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097355.00000000000.00000000000.0000000000000000000.00000000000016783802619032167838020219511678380319698716783803199044
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851744591744594194304256001224701440x7ff75b7039800x7ff75ae24ec0000000498073602097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097357.00000000000.00000000000.0000000000000000000.00000000000016783803813864167838031969871678380439202316783804394386
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881744591744594194304256001224716160x7ff75b7038000x7ff75ae24f00000000655360004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194555.00000000000.00000000000.0000000000000000000.00000000000016783804989177167838043920231678380562337916783805625517
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911744591744594194304256001224728320x7ff75b7036800x7ff75ae24f40000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194548.00000000000.00000000000.0000000000006553600000000.00000000000016783806220689167838056233791678380687265516783806874608
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194174459174459419430425600824740480x7ff75dd335000x7ff75ae24f80006553600000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097359.00000000000.00000000000.0000000000000000000.00000000000016783807468499167838068726551678380802817116783808030221
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971744591744594194304256001224757760x7ff75dd333800x7ff75ae24fc0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097355.00000000000.00000000000.0000000000000000000.00000000000016783808624642167838080281711678380919024716783809192294
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001744591744594194304256001224769920x7ff75dd332000x7ff75ae25000000000537395202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097361.00000000000.00000000000.0000000000000000000.00000000000016783809794655167838091902471678381035312316783810355738
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031744591744594194304256001224784640x7ff75dd330800x7ff75ae25040000000707788804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194568.00000000000.00000000000.0000000000000000000.00000000000016783810950719167838103531231678381160735916783811609428
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061744591744594194304256001224799360x7ff75b703f000x7ff75ae25080000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194556.00000000000.00000000000.0000000000007077888000000.00000000000016783812203659167838116073591678381285311416783812855139
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209174459174459419430425600824814080x7ff75b703d800x7ff75ae250c0007077888000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097360.00000000000.00000000000.0000000000000000000.00000000000016783813449760167838128531141678381399151116783813993333
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121744591744594194304256001224831360x7ff75b703c000x7ff75ae25100000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097341.00000000000.00000000000.0000000000000000000.00000000000016783814588604167838139915111678381517262716783815174546
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151744591744594194304256001224843520x7ff75b703a800x7ff75ae25140000000576716802097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097360.00000000000.00000000000.0000000000000000000.00000000000016783815776157167838151726271678381634110316783816343049
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181744591744594194304256001224858240x7ff75b7039000x7ff75ae25180000000760217604194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194579.00000000000.00000000000.0000000000000000000.00000000000016783816936800167838163411031678381757773816783817579960
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211744591744594194304256001224872960x7ff75b7037800x7ff75ae251c0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194570.00000000000.00000000000.0000000000007602176000000.00000000000016783818174011167838175777381678381879021416783818792282
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241744591744594194304256001224887680x7ff75b7036000x7ff75ae25200007602176000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097357.00000000000.00000000000.0000000000000000000.00000000000016783819385993167838187902141678381995581016783819957835
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271744591744594194304256001224907520x7ff75dd334800x7ff75ae25240000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097354.00000000000.00000000000.0000000000000000000.00000000000016783820552326167838199558101678382111756616783821119458
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301744591744594194304256001224919680x7ff75dd333000x7ff75ae25280000000616038402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097354.00000000000.00000000000.0000000000000000000.00000000000016783821722219167838211175661678382229196216783822294901
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331744591744594194304256001224934400x7ff75dd331800x7ff75ae252c0000000812646404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194575.00000000000.00000000000.0000000000000000000.00000000000016783822889022167838222919621678382352059816783823522672
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361744591744594194304256001224949120x7ff75dd330000x7ff75ae25300000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194581.00000000000.00000000000.0000000000008126464000000.00000000000016783824117213167838235205981678382476315416783824765333
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391744591744594194304256001224963840x7ff75b703e800x7ff75ae25340008126464000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097364.00000000000.00000000000.0000000000000000000.00000000000016783825359434167838247631541678382592699016783825929246
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421744591744594194304256001224983680x7ff75b703d000x7ff75ae25380000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097348.00000000000.00000000000.0000000000000000000.00000000000016783826523767167838259269901678382710986616783827112069
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451744591744594194304256001224995840x7ff75b703b800x7ff75ae253c0000000655360002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097352.00000000000.00000000000.0000000000000000000.00000000000016783827712800167838271098661678382827386216783828275912
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024817445917445941943042560012241013120x7ff75b703a000x7ff75ae25400000000865075204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194582.00000000000.00000000000.0000000000000000000.00000000000016783828869883167838282738621678382951577816783829517723
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025117445917445941943042560012241027840x7ff75b7038800x7ff75ae25440000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194580.00000000000.00000000000.0000000000008650752000000.00000000000016783830112064167838295157781678383075497416783830757234
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025417445917445941943042560012241042560x7ff75b7037000x7ff75ae25480008650752000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097364.00000000000.00000000000.0000000000000000000.00000000000016783831351265167838307549741678383191209016783831914197
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025717445917445941943042560012241062400x7ff75dd335800x7ff75ae254c0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097340.00000000000.00000000000.0000000000000000000.00000000000016783832507959167838319120901678383307432616783833076281
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026017445917445941943042560012241077120x7ff75dd334000x7ff75ae25500000000694681602097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097361.00000000000.00000000000.0000000000000000000.00000000000016783833677252167838330743261678383423992216783834242234
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026317445917445941943042560016241094400x7ff75dd332800x7ff75ae25540000000917504004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194563.00000000000.00000000000.0000000000000000000.00000000000016783834836395167838342399221678383548087816783835482975
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026617445917445941943042560016241111680x7ff75dd331000x7ff75ae25580000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194581.00000000000.00000000000.0000000000009175040000000.00000000000016783836077546167838354808781678383670999416783836711816
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691744591744594194304256008241128960x7ff75b703f800x7ff75ae255c0009175040000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097363.00000000000.00000000000.0000000000000000000.00000000000016783837306147167838367099941678383787847016783837880469
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027217445917445941943042560012241151360x7ff75b703e000x7ff75ae25600000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097336.00000000000.00000000000.0000000000000000000.00000000000016783838474970167838378784701678383905974616783839061972
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027517445917445941943042560012241166080x7ff75b703c800x7ff75ae25640000000734003202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097356.00000000000.00000000000.0000000000000000000.00000000000016783839663273167838390597461678384021750216783840219745
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027817445917445941943042560016241183360x7ff75b703b000x7ff75ae25680000000969932804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194575.00000000000.00000000000.0000000000000000000.00000000000016783840814056167838402175021678384145173716783841453996
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028117445917445941943042560016241200640x7ff75b7039800x7ff75ae256c0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194591.00000000000.00000000000.0000000000009699328000000.00000000000016783842047067167838414517371678384268309316783842684927
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028417445917445941943042560012241217920x7ff75b7038000x7ff75ae25700009699328000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097360.00000000000.00000000000.0000000000000000000.00000000000016783843278758167838426830931678384387268916783843874710
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028717445917445941943042560012241240320x7ff75b7036800x7ff75ae25740000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097325.00000000000.00000000000.0000000000000000000.00000000000016783844469881167838438726891678384507988516783845081852
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029017445917445941943042560012241255040x7ff75dd335000x7ff75ae25780000000812646402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097357.00000000000.00000000000.0000000000000000000.00000000000016783845683653167838450798851678384622964116783846232295
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029317445917445941943042560012241274880x7ff75dd333800x7ff75ae257c00000001074790404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194598.00000000000.00000000000.0000000000000000000.00000000000016783846825067167838462296411678384747187716783847473956
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029617445917445941943042560012241292160x7ff75dd332000x7ff75ae25800000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194597.00000000000.00000000000.00000000000010747904000000.00000000000016783848068187167838474718771678384874019316783848742266
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029917445917445941943042560012241309440x7ff75dd330800x7ff75ae258400010747904000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097364.00000000000.00000000000.0000000000000000000.00000000000016783849336898167838487401931678384990434916783849906330
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030217445917445941943042560012241334400x7ff75b703f000x7ff75ae25880000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097331.00000000000.00000000000.0000000000000000000.00000000000016783850501571167838499041851678385110001916783851102072
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030517445917445941943042560012241349120x7ff75b703d800x7ff75ae258c0000000891289602097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097365.00000000000.00000000000.0000000000000000000.00000000000016783851703743167838511000191678385223809516783852240166
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030817445917445941943042560012241368960x7ff75b703c000x7ff75ae259000000001179648004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194603.00000000000.00000000000.0000000000000000000.00000000000016783852833487167838522380951678385346833116783853470377
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031117445917445941943042560012241388800x7ff75b703a800x7ff75ae25940000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194590.00000000000.00000000000.00000000000011796480000000.00000000000016783854064248167838534683311678385470560616783854707758
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031417445917445941943042560012241408640x7ff75b7039000x7ff75ae259800011796480000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097362.00000000000.00000000000.0000000000000000000.00000000000016783855301509167838547056061678385582096216783855822722
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031717445917445941943042560012241436160x7ff75b7037800x7ff75ae259c0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097339.00000000000.00000000000.0000000000000000000.00000000000016783856416494167838558209621678385701759816783857019465
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032017445917445941943042560012241453440x7ff75b7036000x7ff75ae25a00000000969932802097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097369.00000000000.00000000000.0000000000000000000.00000000000016783857621516167838570175981678385816255316783858164759
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032317445917445941943042560012241475840x7ff75dd334800x7ff75ae25a400000001284505604194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194621.00000000000.00000000000.0000000000000000000.00000000000016783858759290167838581625531678385937822916783859380550
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032617445917445941943042560012241495680x7ff75dd333000x7ff75ae25a80000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194595.00000000000.00000000000.00000000000012845056000000.00000000000016783859974362167838593782291678386062254416783860624861
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032917445917445941943042560012241515520x7ff75dd331800x7ff75ae25ac00012845056000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097350.00000000000.00000000000.0000000000000000000.00000000000016783861219662167838606225441678386178462016783861786604
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033217445917445941943042560012241543040x7ff75dd330000x7ff75ae25b00000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097331.00000000000.00000000000.0000000000000000000.00000000000016783862381586167838617846201678386303101616783863033255
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033517445917445941943042560012241562880x7ff75b703e800x7ff75ae25b400000001127219202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097362.00000000000.00000000000.0000000000000000000.00000000000016783863634516167838630310161678386420605116783864208598
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033817445917445941943042560012241587840x7ff75b703d000x7ff75ae25b800000001494220804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194637.00000000000.00000000000.0000000000000000000.00000000000016783864802039167838642060511678386544972716783865453219
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034117445917445941943042560012241610240x7ff75b703b800x7ff75ae25bc0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194630.00000000000.00000000000.00000000000014942208000000.00000000000016783866045520167838654497271678386671740216783866720129
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034417445917445941943042560012241632640x7ff75b703a000x7ff75ae25c000014942208000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097342.00000000000.00000000000.0000000000000000000.00000000000016783867313720167838667174021678386790315816783867905401
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034717445917445941943042560012241665280x7ff75b7038800x7ff75ae25c40000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097344.00000000000.00000000000.0000000000000000000.00000000000016783868499302167838679031581678386913675316783869201640
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035017445917445941943042560012241685120x7ff75b7037000x7ff75ae25c800000001284505602097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097347.00000000000.00000000000.0000000000000000000.00000000000016783869740833167838691367531678387031386916783870316225
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035317445917445941943042560012241712640x7ff75dd335800x7ff75ae25cc00000001703936004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194632.00000000000.00000000000.0000000000000000000.00000000000016783870911016167838703138691678387155178416783871557256
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035617445917445941943042560012241737600x7ff75dd334000x7ff75ae25d00000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194647.00000000000.00000000000.00000000000017039360000000.00000000000016783872147707167838715517841678387280010016783872804216
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035917445917445941943042560012241762560x7ff75dd332800x7ff75ae25d400017039360000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097334.00000000000.00000000000.0000000000000000000.00000000000016783873396698167838728001001678387399753516783873999799
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036217445917445941943042560012241797760x7ff75dd331000x7ff75ae25d80000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097344.00000000000.00000000000.0000000000000000000.00000000000016783874595530167838739975351678387531449016783875380445
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036517445917445941943042560012241822720x7ff75b703f800x7ff75ae25dc00000001599078402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097331.00000000000.00000000000.0000000000000000000.00000000000016783875919288167838753144901678387651256616783876514930
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036817445917445941943042560012241855360x7ff75b703e000x7ff75ae25e000000002123366404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194643.00000000000.00000000000.0000000000000000000.00000000000016783877108581167838765125661678387777320116783877838848
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037117445917445941943042560012241885440x7ff75b703c800x7ff75ae25e40000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194633.00000000000.00000000000.00000000000021233664000000.00000000000016783878369711167838777732011678387902887716783879094388
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037417445917445941943042560012241915520x7ff75b703b000x7ff75ae25e800021233664000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097337.00000000000.00000000000.0000000000000000000.00000000000016783879624861167838790288771678388025751216783880259871
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037717445917445941943042560012241958400x7ff75b7039800x7ff75ae25ec0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097351.00000000000.00000000000.0000000000000000000.00000000000016783880853622167838802575121678388164678716783881712705
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038017445917445941943042560012241985920x7ff75b7038000x7ff75ae25f000000001913651202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097333.00000000000.00000000000.0000000000000000000.00000000000016783882252908167838816467871678388286598316783882868529
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038317445917445941943042560012242023680x7ff75b7036800x7ff75ae25f400000002542796804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194643.00000000000.00000000000.0000000000000000000.00000000000016783883462330167838828659831678388412837816783884194237
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038617445917445941943042560012242058880x7ff75dd335000x7ff75ae25f80000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194607.00000000000.00000000000.00000000000025427968000000.00000000000016783884724800167838841283781678388538645316783885452307
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038917445917445941943042560012242094080x7ff75dd333800x7ff75ae25fc00025427968000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097335.00000000000.00000000000.0000000000000000000.00000000000016783885981680167838853864531678388665284916783886718597
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039217445917445941943042560012242144640x7ff75dd332000x7ff75ae26000000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097366.00000000000.00000000000.0000000000000000000.00000000000016783887250830167838866528491678388805412416783888121213
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039517445917445941943042560012242177280x7ff75dd330800x7ff75ae260400000002228224002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097334.00000000000.00000000000.0000000000000000000.00000000000016783888659566167838880541241678388928499916783889287276
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039817445917445941943042560012242220160x7ff75b703f000x7ff75ae260800000002962227204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194610.00000000000.00000000000.0000000000000000000.00000000000016783889881208167838892849991678389059235416783890658263
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040117445917445941943042560012242260480x7ff75b703d800x7ff75ae260c0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194600.00000000000.00000000000.00000000000029622272000000.00000000000016783891189366167838905923541678389189954916783891965392
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040417445917445941943042560012242300800x7ff75b703c000x7ff75ae261000029622272000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097369.00000000000.00000000000.0000000000000000000.00000000000016783892495705167838918995491678389315506516783893221122
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040717445917445941943042560012242359040x7ff75b703a800x7ff75ae26140000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097376.00000000000.00000000000.0000000000000000000.00000000000016783893751296167838931550651678389459057916783894656777
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041017445917445941943042560012242394240x7ff75b7039000x7ff75ae261800000002542796802097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097359.00000000000.00000000000.0000000000000000000.00000000000016783895195410167838945905791678389584929516783895851099
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041317445917445941943042560012242442240x7ff75b7037800x7ff75ae261c00000003381657604194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194613.00000000000.00000000000.0000000000000000000.00000000000016783896446050167838958492951678389717985016783897245685
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041617445917445941943042560012242487680x7ff75b7036000x7ff75ae26200000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194593.00000000000.00000000000.00000000000033816576000000.00000000000016783897776268167838971798501678389850560516783898571593
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041917445917445941943042560012242533120x7ff75dd334800x7ff75ae262400033816576000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097379.00000000000.00000000000.0000000000000000000.00000000000016783899102576167838985056051678390002191916783900088245
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221744591744594194304256008242555520x7ff75dd333000x7ff75ae26280000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097323.00000000000.00000000000.0000000000000000000.00000000000016783900634378167839000219191678390213423216783902202479
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042517445917445941943042560012242598400x7ff75dd331800x7ff75ae262c00000003171942402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097353.00000000000.00000000000.0000000000000000000.00000000000016783902769041167839021342321678390399406516783904058490
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042817445917445941943042560012242656640x7ff75dd330000x7ff75ae263000000004220518404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194600.00000000000.00000000000.0000000000000000000.00000000000016783904607053167839039940651678390593117816783905995679
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043117445917445941943042560012242712320x7ff75b703e800x7ff75ae26340000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194609.00000000000.00000000000.00000000000042205184000000.00000000000016783906542422167839059311781678390784573116783907911999
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341744591744594194304256008242732160x7ff75b703d000x7ff75ae263800042205184000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097328.00000000000.00000000000.0000000000000000000.00000000000016783908457011167839078457311678390964348416783909709122
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371744591744594194304256008242757120x7ff75b703b800x7ff75ae263c0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097324.00000000000.00000000000.0000000000000000000.00000000000016783910243605167839096434841678391125675816783911322411
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044017445917445941943042560012242807680x7ff75b703a000x7ff75ae264000000003801088002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097356.00000000000.00000000000.0000000000000000000.00000000000016783911861074167839112567581678391259851316783912663608
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044317445917445941943042560012242876160x7ff75b7038800x7ff75ae264400000005059379204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194615.00000000000.00000000000.0000000000000000000.00000000000016783913195352167839125999471678391398570516783914055704
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044617445917445941943042560012242942080x7ff75b7037000x7ff75ae26480000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194617.00000000000.00000000000.00000000000050593792000000.00000000000016783914580758167839139857051678391538394216783915449260
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491744591744594194304256008242969600x7ff75dd335800x7ff75ae264c00050593792000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097338.00000000000.00000000000.0000000000000000000.00000000000016783915978804167839153839421678391679226016783916858706
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521744591744594194304256008242999680x7ff75dd334000x7ff75ae26500000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097329.00000000000.00000000000.0000000000000000000.00000000000016783917388179167839167922601678391850729716783918572552
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551744591744594194304256008243027200x7ff75dd332800x7ff75ae265400000006737100802097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097331.00000000000.00000000000.0000000000000000000.00000000000016783919112675167839185072971678392003145516783920096174
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045817445917445941943042560012243054720x7ff75dd331000x7ff75ae265800000006737100804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194558.00000000000.00000000000.0000000000000000000.00000000000016783920626607167839200314551678392155353316783921616026
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046117445917445941943042560012243082240x7ff75b703f800x7ff75ae265c0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194547.00000000000.00000000000.00000000000067371008000000.00000000000016783922149719167839215535331678392306537016783923130188
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641744591744594194304256008243109760x7ff75b703e000x7ff75ae266000067371008000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097333.00000000000.00000000000.0000000000000000000.00000000000016783923659791167839230653701678392454264816783924606721
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671744591744594194304256008243132160x7ff75b703c800x7ff75ae26640000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097317.00000000000.00000000000.0000000000000000000.00000000000016783925136644167839245426481678392646152616783926529590
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701744591744594194304256008243159680x7ff75b703b000x7ff75ae2668000000013447987202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097326.00000000000.00000000000.0000000000000000000.00000000000016783927064924167839264615261678392834888316783928412051
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047317445917445941943042560012243187200x7ff75b7039800x7ff75ae266c000000013447987204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194545.00000000000.00000000000.0000000000000000000.00000000000016783928943134167839283488831678393029176016783930356440
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047617445917445941943042560012243214720x7ff75b7038000x7ff75ae26700000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194546.00000000000.00000000000.000000000000134479872000000.00000000000016783930887493167839302917601678393222103716783932286369
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791744591744594194304256008243242240x7ff75b7036800x7ff75ae2674000134479872000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097324.00000000000.00000000000.0000000000000000000.00000000000016783932815462167839322210371678393411127416783934176879
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821744591744594194304256008243264640x7ff75dd335000x7ff75ae26780000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097316.00000000000.00000000000.0000000000000000000.00000000000016783934706173167839341112741678393685031016783936913753
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851744591744594194304256008243292160x7ff75dd333800x7ff75ae267c000000026869760002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097325.00000000000.00000000000.0000000000000000000.00000000000016783937460266167839368503101678393959526616783939659896
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048817445917445941943042560012243319680x7ff75dd332000x7ff75ae2680000000026869760004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194547.00000000000.00000000000.0000000000000000000.00000000000016783940191279167839395952661678394235846216783942426789
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049117445917445941943042560012243347200x7ff75dd330800x7ff75ae26840000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194543.00000000000.00000000000.000000000000268697600000000.00000000000016783942953192167839423584621678394513861816783945203361
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941744591744594194304256008243374720x7ff75b703f000x7ff75ae2688000268697600000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097329.00000000000.00000000000.0000000000000000000.00000000000016783945733834167839451386181678394788309416783947951435
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049717445917445941943042560082400x7ff75b703d800x7ff75ae268c0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097313.00000000000.00000000000.0000000000000000000.00000000000016783948477998167839478830941678395229284816783952363745