Files
rocm-systems/tests/workloads/roof_only_dev0/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.kd000228689228689335544322560043241600x00x7fab9ca04280000000000.00000000008388608.00000000004194304.00000000000.00000000000.0000000000309.00000000004128768.00000000004128768.0000000000000000000.00000000000017695745996020176662849589291769589373194217695893846323
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00222868922868932768256001224138880x00x7fab9ca23f80000000008192.000000000016384.00000000000.00000000000.00000000000.00000000008260.00000000000.00000000000.0000000000000000000.00000000000017695899546920176958937319421769589990800817695899915190
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0052286892286894194304256001224143360x7fab9f92d3800x7fab9ca23fc000000026214402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097342.00000000000.00000000000.0000000000000000000.00000000000017695900506745176958999080081769590116850117695901168529
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0082286892286894194304256001624150400x7fab9f92d2000x7fab9ca2400000000026214404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194579.00000000000.00000000000.0000000000000000000.00000000000017695901769584176959011685011769590246915517695902467586
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00112286892286894194304256001624154880x7fab9f92d0800x7fab9ca24040000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194604.00000000000.00000000000.000000000000262144000000.00000000000017695903063681176959024691551769590372884917695903728244
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00142286892286894194304256001224159360x7fab9d1cdf000x7fab9ca2408000262144000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097343.00000000000.00000000000.0000000000000000000.00000000000017695904323509176959037288491769590492134217695904920284
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00172286892286894194304256001224163840x7fab9d1cdd800x7fab9ca240c0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097344.00000000000.00000000000.0000000000000000000.00000000000017695905514109176959049213421769590612087417695906120744
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00202286892286894194304256001224170880x7fab9d1cdc000x7fab9ca2410000000065536002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097338.00000000000.00000000000.0000000000000000000.00000000000017695906727059176959061208741769590732952717695907328614
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00232286892286894194304256001624177920x7fab9d1cda800x7fab9ca2414000000078643204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194597.00000000000.00000000000.0000000000000000000.00000000000017695907923599176959073295271769590863706217695908636221
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00262286892286894194304256001624184960x7fab9d1cd9000x7fab9ca24180000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194585.00000000000.00000000000.000000000000786432000000.00000000000017695909230926176959086370621769590992795517695909926728
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00292286892286894194304256001624192000x7fab9d1cd7800x7fab9ca241c000786432000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097344.00000000000.00000000000.0000000000000000000.00000000000017695910521443176959099279551769591112140817695911119348
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00322286892286894194304256001624199040x7fab9d1cd6000x7fab9ca24200000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097339.00000000000.00000000000.0000000000000000000.00000000000017695911713204176959111214081769591228526117695912282969
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00352286892286894194304256001224206080x7fab9f92d4800x7fab9ca24240000000104857602097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097346.00000000000.00000000000.0000000000000000000.00000000000017695912885794176959122852611769591347455417695913472579
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00382286892286894194304256001624213120x7fab9f92d3000x7fab9ca24280000000131072004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194604.00000000000.00000000000.0000000000000000000.00000000000017695914066235176959134745541769591477616817695914774067
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00412286892286894194304256001624220160x7fab9f92d1800x7fab9ca242c0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194594.00000000000.00000000000.0000000000001310720000000.00000000000017695915369512176959147761681769591603938117695916037355
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00442286892286894194304256001624227200x7fab9f92d0000x7fab9ca24300001310720000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097343.00000000000.00000000000.0000000000000000000.00000000000017695916632040176959160393811769591719475417695917192936
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00472286892286894194304256001224234240x7fab9d1cde800x7fab9ca24340000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097345.00000000000.00000000000.0000000000000000000.00000000000017695917787521176959171947541769591840388717695918402115
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00502286892286894194304256001224241280x7fab9d1cdd000x7fab9ca24380000000144179202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097343.00000000000.00000000000.0000000000000000000.00000000000017695919004350176959184038871769591960533917695919603605
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00532286892286894194304256001624248320x7fab9d1cdb800x7fab9ca243c0000000183500804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194574.00000000000.00000000000.0000000000000000000.00000000000017695920197770176959196053391769592085495317695920853334
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00562286892286894194304256001624255360x7fab9d1cda000x7fab9ca24400000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194574.00000000000.00000000000.0000000000001835008000000.00000000000017695921447889176959208549531769592213832717695922136621
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00592286892286894194304256001224262400x7fab9d1cd8800x7fab9ca24440001835008000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097345.00000000000.00000000000.0000000000000000000.00000000000017695922731996176959221383271769592333802017695923335761
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00622286892286894194304256001224269440x7fab9d1cd7000x7fab9ca24480000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097351.00000000000.00000000000.0000000000000000000.00000000000017695923931096176959233380201769592454363317695924541821
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00652286892286894194304256001224276480x7fab9f92d5800x7fab9ca244c0000000183500802097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097348.00000000000.00000000000.0000000000000000000.00000000000017695925143846176959245436331769592575548617695925753780
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00682286892286894194304256001624286080x7fab9f92d4000x7fab9ca24500000000235929604194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194593.00000000000.00000000000.0000000000000000000.00000000000017695926349935176959257554861769592702077917695927019149
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00712286892286894194304256001624293120x7fab9f92d2800x7fab9ca24540000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194586.00000000000.00000000000.0000000000002359296000000.00000000000017695927614344176959270207791769592833887317695928336975
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00742286892286894194304256001224300160x7fab9f92d1000x7fab9ca24580002359296000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097345.00000000000.00000000000.0000000000000000000.00000000000017695928933650176959283388731769592957696717695929575224
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077228689228689419430425600824309760x7fab9d1cdf800x7fab9ca245c0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097350.00000000000.00000000000.0000000000000000000.00000000000017695930171099176959295769671769593078882017695930787444
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00802286892286894194304256001224316800x7fab9d1cde000x7fab9ca24600000000222822402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097345.00000000000.00000000000.0000000000000000000.00000000000017695931390949176959307888201769593200147317695931999963
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00832286892286894194304256001624326400x7fab9d1cdc800x7fab9ca24640000000288358404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194594.00000000000.00000000000.0000000000000000000.00000000000017695932594799176959320014731769593331364717695933312011
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00862286892286894194304256001224336000x7fab9d1cdb000x7fab9ca24680000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194580.00000000000.00000000000.0000000000002883584000000.00000000000017695933907106176959333136471769593462118117695934619378
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00892286892286894194304256001224345600x7fab9d1cd9800x7fab9ca246c0002883584000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097355.00000000000.00000000000.0000000000000000000.00000000000017695935215003176959346211811769593581991417695935818338
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092228689228689419430425600824355200x7fab9d1cd8000x7fab9ca24700000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097349.00000000000.00000000000.0000000000000000000.00000000000017695936412743176959358199141769593702376717695937022247
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00952286892286894194304256001224362240x7fab9d1cd6800x7fab9ca24740000000262144002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097344.00000000000.00000000000.0000000000000000000.00000000000017695937624182176959370237671769593823450017695938233077
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00982286892286894194304256001224371840x7fab9f92d5000x7fab9ca24780000000340787204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194594.00000000000.00000000000.0000000000000000000.00000000000017695938828502176959382345001769593951899417695939517185
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001012286892286894194304256001224381440x7fab9f92d3800x7fab9ca247c0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194573.00000000000.00000000000.0000000000003407872000000.00000000000017695940111590176959395189941769594078396717695940782093
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001042286892286894194304256001224391040x7fab9f92d2000x7fab9ca24800003407872000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097351.00000000000.00000000000.0000000000000000000.00000000000017695941377798176959407839671769594199566017695941993762
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107228689228689419430425600824403200x7fab9f92d0800x7fab9ca24840000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097355.00000000000.00000000000.0000000000000000000.00000000000017695942589747176959419956601769594318111317695943179232
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001102286892286894194304256001224412800x7fab9d1cdf000x7fab9ca24880000000301465602097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097345.00000000000.00000000000.0000000000000000000.00000000000017695943781927176959431811131769594439232617695944390392
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001132286892286894194304256001224422400x7fab9d1cdd800x7fab9ca248c0000000393216004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194590.00000000000.00000000000.0000000000000000000.00000000000017695944985367176959443923261769594564401917695945642170
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001162286892286894194304256001224432000x7fab9d1cdc000x7fab9ca24900000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194569.00000000000.00000000000.0000000000003932160000000.00000000000017695946238505176959456440191769594696323417695946961417
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119228689228689419430425600824441600x7fab9d1cda800x7fab9ca24940003932160000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097353.00000000000.00000000000.0000000000000000000.00000000000017695947556172176959469632341769594816516617695948163587
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001222286892286894194304256001224453760x7fab9d1cd9000x7fab9ca24980000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097356.00000000000.00000000000.0000000000000000000.00000000000017695948757152176959481651661769594935413917695949352317
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001252286892286894194304256001224463360x7fab9d1cd7800x7fab9ca249c0000000340787202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097352.00000000000.00000000000.0000000000000000000.00000000000017695949954852176959493541391769595056023217695950558477
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001282286892286894194304256001224475520x7fab9d1cd6000x7fab9ca24a00000000445644804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194573.00000000000.00000000000.0000000000000000000.00000000000017695951153792176959505602321769595183368617695951832095
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001312286892286894194304256001224485120x7fab9f92d4800x7fab9ca24a40000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194576.00000000000.00000000000.0000000000004456448000000.00000000000017695952428070176959518336861769595312890017695953127143
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134228689228689419430425600824494720x7fab9f92d3000x7fab9ca24a80004456448000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097349.00000000000.00000000000.0000000000000000000.00000000000017695953722028176959531289001769595433931317695954337392
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001372286892286894194304256001224506880x7fab9f92d1800x7fab9ca24ac0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097359.00000000000.00000000000.0000000000000000000.00000000000017695954932707176959543393131769595550828517695955506753
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001402286892286894194304256001224516480x7fab9f92d0000x7fab9ca24b00000000380108802097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097352.00000000000.00000000000.0000000000000000000.00000000000017695956109387176959555046381769595670512217695956711552
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001432286892286894194304256001224528640x7fab9d1cde800x7fab9ca24b40000000498073604194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194577.00000000000.00000000000.0000000000000000000.00000000000017695957301967176959567051221769595799024617695957991950
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001462286892286894194304256001224540800x7fab9d1cdd000x7fab9ca24b80000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194576.00000000000.00000000000.0000000000004980736000000.00000000000017695958587575176959579902461769595927729117695959279268
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149228689228689419430425600824552960x7fab9d1cdb800x7fab9ca24bc0004980736000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097349.00000000000.00000000000.0000000000000000000.00000000000017695959873743176959592772911769596049105517695960492857
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001522286892286894194304256001224567680x7fab9d1cda000x7fab9ca24c00000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097360.00000000000.00000000000.0000000000000000000.00000000000017695961088572176959604910551769596168578017695961687877
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001552286892286894194304256001224577280x7fab9d1cd8800x7fab9ca24c40000000419430402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097353.00000000000.00000000000.0000000000000000000.00000000000017695962290722176959616857801769596287538417695962877327
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001582286892286894194304256001224589440x7fab9d1cd7000x7fab9ca24c80000000550502404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194576.00000000000.00000000000.0000000000000000000.00000000000017695963473352176959628753841769596418114917695964182794
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001612286892286894194304256001224601600x7fab9f92d5800x7fab9ca24cc0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194558.00000000000.00000000000.0000000000005505024000000.00000000000017695964779209176959641811491769596545283317695965454642
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164228689228689419430425600824613760x7fab9f92d4000x7fab9ca24d00005505024000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097351.00000000000.00000000000.0000000000000000000.00000000000017695966048847176959654528331769596667843817695966680271
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001672286892286894194304256001224628480x7fab9f92d2800x7fab9ca24d40000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097355.00000000000.00000000000.0000000000000000000.00000000000017695967277896176959666784381769596788644217695967888181
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001702286892286894194304256001224638080x7fab9f92d1000x7fab9ca24d80000000458752002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097354.00000000000.00000000000.0000000000000000000.00000000000017695968491946176959678864421769596908404617695969085941
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001732286892286894194304256001224650240x7fab9d1cdf800x7fab9ca24dc0000000602931204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194574.00000000000.00000000000.0000000000000000000.00000000000017695969681056176959690840461769597038421117695970385749
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001762286892286894194304256001224662400x7fab9d1cde000x7fab9ca24e00000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194566.00000000000.00000000000.0000000000006029312000000.00000000000017695970981464176959703842111769597167285617695971674596
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179228689228689419430425600824674560x7fab9d1cdc800x7fab9ca24e40006029312000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097351.00000000000.00000000000.0000000000000000000.00000000000017695972269371176959716728561769597286358017695972865656
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001822286892286894194304256001224689280x7fab9d1cdb000x7fab9ca24e80000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097356.00000000000.00000000000.0000000000000000000.00000000000017695973460531176959728635801769597405670417695974058916
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001852286892286894194304256001224701440x7fab9d1cd9800x7fab9ca24ec0000000498073602097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097352.00000000000.00000000000.0000000000000000000.00000000000017695974673961176959740567041769597528134917695975283165
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001882286892286894194304256001224716160x7fab9d1cd8000x7fab9ca24f00000000655360004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194548.00000000000.00000000000.0000000000000000000.00000000000017695975877730176959752813491769597656791417695976569783
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001912286892286894194304256001224728320x7fab9d1cd6800x7fab9ca24f40000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194559.00000000000.00000000000.0000000000006553600000000.00000000000017695977162688176959765679141769597783415817695977836151
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194228689228689419430425600824740480x7fab9f92d5000x7fab9ca24f80006553600000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097350.00000000000.00000000000.0000000000000000000.00000000000017695978430636176959778341581769597902232317695979024321
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001972286892286894194304256001224757760x7fab9f92d3800x7fab9ca24fc0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097354.00000000000.00000000000.0000000000000000000.00000000000017695979618796176959790223231769598021320717695980214731
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002002286892286894194304256001224769920x7fab9f92d2000x7fab9ca25000000000537395202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097351.00000000000.00000000000.0000000000000000000.00000000000017695980818276176959802132071769598140153117695981403481
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002032286892286894194304256001224784640x7fab9f92d0800x7fab9ca25040000000707788804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194554.00000000000.00000000000.0000000000000000000.00000000000017695981998956176959814015311769598270857617695982710598
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002062286892286894194304256001224799360x7fab9d1cdf000x7fab9ca25080000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194551.00000000000.00000000000.0000000000007077888000000.00000000000017695983305603176959827085761769598401818117695984019865
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209228689228689419430425600824814080x7fab9d1cdd800x7fab9ca250c0007077888000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097358.00000000000.00000000000.0000000000000000000.00000000000017695984614420176959840181811769598520394517695985205816
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002122286892286894194304256001224831360x7fab9d1cdc000x7fab9ca25100000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097347.00000000000.00000000000.0000000000000000000.00000000000017695985799221176959852039451769598641786917695986419495
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002152286892286894194304256001224843520x7fab9d1cda800x7fab9ca25140000000576716802097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097353.00000000000.00000000000.0000000000000000000.00000000000017695987022520176959864178691769598762699417695987628805
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002182286892286894194304256001224858240x7fab9d1cd9000x7fab9ca25180000000760217604194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194557.00000000000.00000000000.0000000000000000000.00000000000017695988224950176959876269941769598890811817695988910123
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002212286892286894194304256001224872960x7fab9d1cd7800x7fab9ca251c0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194574.00000000000.00000000000.0000000000007602176000000.00000000000017695989504438176959889081181769599018300317695990185121
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002242286892286894194304256001224887680x7fab9d1cd6000x7fab9ca25200007602176000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097360.00000000000.00000000000.0000000000000000000.00000000000017695990779036176959901830031769599136172717695991363491
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002272286892286894194304256001224907520x7fab9f92d4800x7fab9ca25240000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097350.00000000000.00000000000.0000000000000000000.00000000000017695991958886176959913617271769599258797217695992589930
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002302286892286894194304256001224919680x7fab9f92d3000x7fab9ca25280000000616038402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097355.00000000000.00000000000.0000000000000000000.00000000000017695993192925176959925879721769599379405617695993795860
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002332286892286894194304256001224934400x7fab9f92d1800x7fab9ca252c0000000812646404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194572.00000000000.00000000000.0000000000000000000.00000000000017695994391485176959937940561769599509406117695995095927
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002362286892286894194304256001224949120x7fab9f92d0000x7fab9ca25300000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194561.00000000000.00000000000.0000000000008126464000000.00000000000017695995691102176959950940611769599638526617695996387135
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002392286892286894194304256001224963840x7fab9d1cde800x7fab9ca25340008126464000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097362.00000000000.00000000000.0000000000000000000.00000000000017695996981100176959963852661769599755759017695997559275
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002422286892286894194304256001224983680x7fab9d1cdd000x7fab9ca25380000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097339.00000000000.00000000000.0000000000000000000.00000000000017695998155000176959975575901769599878735417695998789004
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002452286892286894194304256001224995840x7fab9d1cdb800x7fab9ca253c0000000655360002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097355.00000000000.00000000000.0000000000000000000.00000000000017695999390769176959987873541769599999535917695999997264
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024822868922868941943042560012241013120x7fab9d1cda000x7fab9ca25400000000865075204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194563.00000000000.00000000000.0000000000000000000.00000000000017696000591609176959999953591769600126528317696001266922
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025122868922868941943042560012241027840x7fab9d1cd8800x7fab9ca25440000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194587.00000000000.00000000000.0000000000008650752000000.00000000000017696001861457176960012652831769600254736817696002549380
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025422868922868941943042560012241042560x7fab9d1cd7000x7fab9ca25480008650752000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097363.00000000000.00000000000.0000000000000000000.00000000000017696003144805176960025473681769600374033217696003742129
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025722868922868941943042560012241062400x7fab9f92d5800x7fab9ca254c0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097344.00000000000.00000000000.0000000000000000000.00000000000017696004337824176960037403321769600497345717696004975268
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026022868922868941943042560012241077120x7fab9f92d4000x7fab9ca25500000000694681602097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097357.00000000000.00000000000.0000000000000000000.00000000000017696005577233176960049734571769600623106117696006232697
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026322868922868941943042560016241094400x7fab9f92d2800x7fab9ca25540000000917504004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194560.00000000000.00000000000.0000000000000000000.00000000000017696006829592176960062310611769600750818617696007509855
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026622868922868941943042560016241111680x7fab9f92d1000x7fab9ca25580000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194598.00000000000.00000000000.0000000000009175040000000.00000000000017696008104360176960075081861769600877203117696008774053
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002692286892286894194304256008241128960x7fab9d1cdf800x7fab9ca255c0009175040000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097363.00000000000.00000000000.0000000000000000000.00000000000017696009368648176960087720311769600996803517696009969913
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027222868922868941943042560012241151360x7fab9d1cde000x7fab9ca25600000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097334.00000000000.00000000000.0000000000000000000.00000000000017696010565478176960099680351769601121043917696011212242
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027522868922868941943042560012241166080x7fab9d1cdc800x7fab9ca25640000000734003202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097356.00000000000.00000000000.0000000000000000000.00000000000017696011813877176960112104391769601241556417696012417322
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027822868922868941943042560016241183360x7fab9d1cdb000x7fab9ca25680000000969932804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194569.00000000000.00000000000.0000000000000000000.00000000000017696013012137176960124155641769601369684817696013698699
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028122868922868941943042560016241200640x7fab9d1cd9800x7fab9ca256c0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194589.00000000000.00000000000.0000000000009699328000000.00000000000017696014294454176960136968481769601497749317696014979317
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028422868922868941943042560012241217920x7fab9d1cd8000x7fab9ca25700009699328000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097359.00000000000.00000000000.0000000000000000000.00000000000017696015573772176960149774931769601616405717696016165557
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028722868922868941943042560012241240320x7fab9d1cd6800x7fab9ca25740000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097331.00000000000.00000000000.0000000000000000000.00000000000017696016760892176960161640571769601740134217696017402936
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029022868922868941943042560012241255040x7fab9f92d5000x7fab9ca25780000000812646402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097358.00000000000.00000000000.0000000000000000000.00000000000017696018004871176960174013421769601861814617696018620006
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029322868922868941943042560012241274880x7fab9f92d3800x7fab9ca257c00000001074790404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194599.00000000000.00000000000.0000000000000000000.00000000000017696019215381176960186176101769601990481217696019906893
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029622868922868941943042560012241292160x7fab9f92d2000x7fab9ca25800000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194590.00000000000.00000000000.00000000000010747904000000.00000000000017696020502268176960199048121769602118097617696021183201
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029922868922868941943042560012241309440x7fab9f92d0800x7fab9ca258400010747904000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097357.00000000000.00000000000.0000000000000000000.00000000000017696021778676176960211809761769602236977917696022371961
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030222868922868941943042560012241334400x7fab9d1cdf000x7fab9ca25880000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097330.00000000000.00000000000.0000000000000000000.00000000000017696022967446176960223697791769602362994217696023632120
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030522868922868941943042560012241349120x7fab9d1cdd800x7fab9ca258c0000000891289602097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097362.00000000000.00000000000.0000000000000000000.00000000000017696024235165176960236299421769602481778617696024819870
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030822868922868941943042560012241368960x7fab9d1cdc000x7fab9ca259000000001179648004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194606.00000000000.00000000000.0000000000000000000.00000000000017696025414385176960248177861769602610466917696026107048
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031122868922868941943042560012241388800x7fab9d1cda800x7fab9ca25940000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194596.00000000000.00000000000.00000000000011796480000000.00000000000017696026701543176960261046691769602738115317696027383556
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031422868922868941943042560012241408640x7fab9d1cd9000x7fab9ca259800011796480000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097356.00000000000.00000000000.0000000000000000000.00000000000017696027977561176960273811531769602857667617696028578626
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031722868922868941943042560012241436160x7fab9d1cd7800x7fab9ca259c0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097333.00000000000.00000000000.0000000000000000000.00000000000017696029171691176960285766761769602982083917696029822894
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032022868922868941943042560012241453440x7fab9d1cd6000x7fab9ca25a00000000969932802097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097365.00000000000.00000000000.0000000000000000000.00000000000017696030426979176960298208391769603100580217696031007454
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032322868922868941943042560012241475840x7fab9f92d4800x7fab9ca25a400000001284505604194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194603.00000000000.00000000000.0000000000000000000.00000000000017696031601779176960310058021769603224484617696032246963
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032622868922868941943042560012241495680x7fab9f92d3000x7fab9ca25a80000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194608.00000000000.00000000000.00000000000012845056000000.00000000000017696032841688176960322448461769603349876917696033500572
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032922868922868941943042560012241515520x7fab9f92d1800x7fab9ca25ac00012845056000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097342.00000000000.00000000000.0000000000000000000.00000000000017696034095817176960334987691769603467829217696034680342
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033222868922868941943042560012241543040x7fab9f92d0000x7fab9ca25b00000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097329.00000000000.00000000000.0000000000000000000.00000000000017696035274417176960346782921769603597141617696035973159
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033522868922868941943042560012241562880x7fab9d1cde800x7fab9ca25b400000001127219202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097357.00000000000.00000000000.0000000000000000000.00000000000017696036575214176960359714161769603714709917696037149580
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033822868922868941943042560012241587840x7fab9d1cdd000x7fab9ca25b800000001494220804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194630.00000000000.00000000000.0000000000000000000.00000000000017696037743535176960371470991769603842614217696038429057
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034122868922868941943042560012241610240x7fab9d1cdb800x7fab9ca25bc0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194638.00000000000.00000000000.00000000000014942208000000.00000000000017696039022803176960384261421769603971366617696039715965
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034422868922868941943042560012241632640x7fab9d1cda000x7fab9ca25c000014942208000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097328.00000000000.00000000000.0000000000000000000.00000000000017696040311740176960397136661769604092726917696040929525
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034722868922868941943042560012241665280x7fab9d1cd8800x7fab9ca25c40000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097337.00000000000.00000000000.0000000000000000000.00000000000017696041524120176960409272691769604223111317696042298180
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035022868922868941943042560012241685120x7fab9d1cd7000x7fab9ca25c800000001284505602097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097342.00000000000.00000000000.0000000000000000000.00000000000017696042836557176960422311131769604345079617696043452921
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035322868922868941943042560012241712640x7fab9f92d5800x7fab9ca25cc00000001703936004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194632.00000000000.00000000000.0000000000000000000.00000000000017696044048106176960434507961769604474327917696044748079
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035622868922868941943042560012241737600x7fab9f92d4000x7fab9ca25d00000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194643.00000000000.00000000000.00000000000017039360000000.00000000000017696045340904176960447432791769604601864317696046023227
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035922868922868941943042560012241762560x7fab9f92d2800x7fab9ca25d400017039360000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097346.00000000000.00000000000.0000000000000000000.00000000000017696046616132176960460186431769604725240617696047254736
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036222868922868941943042560012241797760x7fab9f92d1000x7fab9ca25d80000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097343.00000000000.00000000000.0000000000000000000.00000000000017696047849071176960472524061769604858601017696048651751
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036522868922868941943042560012241822720x7fab9d1cdf800x7fab9ca25dc00000001599078402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097340.00000000000.00000000000.0000000000000000000.00000000000017696049191037176960485860101769604985353317696049856020
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036822868922868941943042560012241855360x7fab9d1cde000x7fab9ca25e000000002123366404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194655.00000000000.00000000000.0000000000000000000.00000000000017696050451725176960498535331769605112665717696051191997
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037122868922868941943042560012241885440x7fab9d1cdc800x7fab9ca25e40000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194638.00000000000.00000000000.00000000000021233664000000.00000000000017696051723543176960511266571769605241978017696052491434
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037422868922868941943042560012241915520x7fab9d1cdb000x7fab9ca25e800021233664000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097343.00000000000.00000000000.0000000000000000000.00000000000017696053016651176960524197801769605367914417696053681274
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037722868922868941943042560012241958400x7fab9d1cd9800x7fab9ca25ec0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097351.00000000000.00000000000.0000000000000000000.00000000000017696054276019176960536791441769605510794717696055173647
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038022868922868941943042560012241985920x7fab9d1cd8000x7fab9ca25f000000001913651202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097330.00000000000.00000000000.0000000000000000000.00000000000017696055713173176960551079471769605635883117696056360867
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038322868922868941943042560012242023680x7fab9d1cd6800x7fab9ca25f400000002542796804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194633.00000000000.00000000000.0000000000000000000.00000000000017696056954812176960563588311769605764955417696057716753
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038622868922868941943042560012242058880x7fab9f92d5000x7fab9ca25f80000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194614.00000000000.00000000000.00000000000025427968000000.00000000000017696058247339176960576495541769605895275817696059019010
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038922868922868941943042560012242094080x7fab9f92d3800x7fab9ca25fc00025427968000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097344.00000000000.00000000000.0000000000000000000.00000000000017696059549726176960589527581769606024828117696060313617
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039222868922868941943042560012242144640x7fab9f92d2000x7fab9ca26000000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097367.00000000000.00000000000.0000000000000000000.00000000000017696060846344176960602482811769606169500517696061761171
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039522868922868941943042560012242177280x7fab9f92d0800x7fab9ca260400000002228224002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097334.00000000000.00000000000.0000000000000000000.00000000000017696062301217176960616950051769606293436817696062936981
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039822868922868941943042560012242220160x7fab9d1cdf000x7fab9ca260800000002962227204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194622.00000000000.00000000000.0000000000000000000.00000000000017696063532756176960629343681769606426173217696064305167
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040122868922868941943042560012242260480x7fab9d1cdd800x7fab9ca260c0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194604.00000000000.00000000000.00000000000029622272000000.00000000000017696064858283176960642617321769606559741617696065660843
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040422868922868941943042560012242300800x7fab9d1cdc000x7fab9ca261000029622272000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097342.00000000000.00000000000.0000000000000000000.00000000000017696066195120176960655974161769606690909917696066975180
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040722868922868941943042560012242359040x7fab9d1cda800x7fab9ca26140000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097376.00000000000.00000000000.0000000000000000000.00000000000017696067506117176960669090991769606839694317696068463283
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041022868922868941943042560012242394240x7fab9d1cd9000x7fab9ca261800000002542796802097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097349.00000000000.00000000000.0000000000000000000.00000000000017696069003079176960683969431769606969902717696069700931
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041322868922868941943042560012242442240x7fab9d1cd7800x7fab9ca261c00000003381657604194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194611.00000000000.00000000000.0000000000000000000.00000000000017696070296256176960696990271769607103279017696071098286
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041622868922868941943042560012242487680x7fab9d1cd6000x7fab9ca26200000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194603.00000000000.00000000000.00000000000033816576000000.00000000000017696071629683176960710327901769607238159417696072448122
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041922868922868941943042560012242533120x7fab9f92d4800x7fab9ca262400033816576000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097349.00000000000.00000000000.0000000000000000000.00000000000017696072979109176960723815941769607372351817696073789159
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004222286892286894194304256008242555520x7fab9f92d3000x7fab9ca26280000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097322.00000000000.00000000000.0000000000000000000.00000000000017696074322005176960737235181769607525296217696075318680
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042522868922868941943042560012242598400x7fab9f92d1800x7fab9ca262c00000003171942402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097353.00000000000.00000000000.0000000000000000000.00000000000017696075858536176960752529621769607657664517696076643297
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042822868922868941943042560012242656640x7fab9f92d0000x7fab9ca263000000004220518404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194592.00000000000.00000000000.0000000000000000000.00000000000017696077174333176960765766451769607798624917696078052391
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043122868922868941943042560012242712320x7fab9d1cde800x7fab9ca26340000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194606.00000000000.00000000000.00000000000042205184000000.00000000000017696078583968176960779862491769607936497317696079428947
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004342286892286894194304256008242732160x7fab9d1cdd000x7fab9ca263800042205184000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097327.00000000000.00000000000.0000000000000000000.00000000000017696079961403176960793649731769608077121717696080813882
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004372286892286894194304256008242757120x7fab9d1cdb800x7fab9ca263c0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097322.00000000000.00000000000.0000000000000000000.00000000000017696081368948176960807729111769608241004017696082481410
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044022868922868941943042560012242807680x7fab9d1cda000x7fab9ca264000000003801088002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097384.00000000000.00000000000.0000000000000000000.00000000000017696083013637176960824100401769608376236617696083826496
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044322868922868941943042560012242876160x7fab9d1cd8800x7fab9ca264400000005059379204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194621.00000000000.00000000000.0000000000000000000.00000000000017696084358003176960837623661769608521293417696085277790
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044622868922868941943042560012242942080x7fab9d1cd7000x7fab9ca26480000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194621.00000000000.00000000000.00000000000050593792000000.00000000000017696085808897176960852129341769608667054217696086734303
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004492286892286894194304256008242969600x7fab9f92d5800x7fab9ca264c00050593792000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097333.00000000000.00000000000.0000000000000000000.00000000000017696087265940176960866705421769608812479017696088166557
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004522286892286894194304256008242999680x7fab9f92d4000x7fab9ca26500000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097327.00000000000.00000000000.0000000000000000000.00000000000017696088719873176960881247901769608988015917696089944502
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004552286892286894194304256008243027200x7fab9f92d2800x7fab9ca265400000006737100802097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097332.00000000000.00000000000.0000000000000000000.00000000000017696090484269176960898801591769609143536717696091498373
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045822868922868941943042560012243054720x7fab9f92d1000x7fab9ca265800000006737100804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194554.00000000000.00000000000.0000000000000000000.00000000000017696092031670176960914353671769609298769617696093049824
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046122868922868941943042560012243082240x7fab9d1cdf800x7fab9ca265c0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194556.00000000000.00000000000.00000000000067371008000000.00000000000017696093582421176960929876961769609454498417696094609835
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004642286892286894194304256008243109760x7fab9d1cde000x7fab9ca266000067371008000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097331.00000000000.00000000000.0000000000000000000.00000000000017696095140142176960945449841769609616083317696096224884
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004672286892286894194304256008243132160x7fab9d1cdc800x7fab9ca26640000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097313.00000000000.00000000000.0000000000000000000.00000000000017696096756371176960961608331769609812324317696098188195
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004702286892286894194304256008243159680x7fab9d1cdb000x7fab9ca2668000000013447987202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097326.00000000000.00000000000.0000000000000000000.00000000000017696098726891176960981232431769610010805417696100171635
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047322868922868941943042560012243187200x7fab9d1cd9800x7fab9ca266c000000013447987204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194547.00000000000.00000000000.0000000000000000000.00000000000017696100703482176961001080541769610209558517696102149826
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047622868922868941943042560012243214720x7fab9d1cd8000x7fab9ca26700000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194545.00000000000.00000000000.000000000000134479872000000.00000000000017696102690562176961020955851769610409047517696104155305
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004792286892286894194304256008243242240x7fab9d1cd6800x7fab9ca2674000134479872000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097329.00000000000.00000000000.0000000000000000000.00000000000017696104685722176961040904751769610606264617696106129306
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004822286892286894194304256008243264640x7fab9f92d5000x7fab9ca26780000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097313.00000000000.00000000000.0000000000000000000.00000000000017696106657812176961060626461769610885610117696108920345
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004852286892286894194304256008243292160x7fab9f92d3800x7fab9ca267c000000026869760002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097322.00000000000.00000000000.0000000000000000000.00000000000017696109466212176961088561011769611162427617696111694816
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048822868922868941943042560012243319680x7fab9f92d2000x7fab9ca2680000000026869760004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194547.00000000000.00000000000.0000000000000000000.00000000000017696112221192176961116242761769611444541117696114515674
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049122868922868941943042560012243347200x7fab9f92d0800x7fab9ca26840000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194542.00000000000.00000000000.000000000000268697600000000.00000000000017696115042441176961144454111769611728862617696117353873
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004942286892286894194304256008243374720x7fab9d1cdf000x7fab9ca2688000268697600000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097321.00000000000.00000000000.0000000000000000000.00000000000017696117884560176961172886261769612008224117696120153423
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049722868922868941943042560082400x7fab9d1cdd800x7fab9ca268c0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097313.00000000000.00000000000.0000000000000000000.00000000000017696120678200176961200822411769612455234517696124620781