Fichiers
rocm-systems/tests/workloads/roof_only_Axes3/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.kd000217141217141335544322560043241600x00x7f2001204280000000000.00000000008388608.00000000004194304.00000000000.00000000000.0000000000310.00000000004128768.00000000004128768.0000000000000000000.00000000000017512325752018174826421857341751247605034317512476140283
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00221714121714132768256001224138880x00x7f2001223f80000000008192.000000000016384.00000000000.00000000000.00000000000.00000000008262.00000000000.00000000000.0000000000000000000.00000000000017512482013263175124760503431751248237695617512482390423
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0052171412171414194304256001224143360x7f20042db3800x7f2001223fc000000026214402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097340.00000000000.00000000000.0000000000000000000.00000000000017512482980408175124823769561751248366928717512483670420
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0082171412171414194304256001624150400x7f20042db2000x7f200122400000000026214404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194609.00000000000.00000000000.0000000000000000000.00000000000017512484271755175124836692871751248498241817512484983826
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00112171412171414194304256001624154880x7f20042db0800x7f2001224040000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194597.00000000000.00000000000.000000000000262144000000.00000000000017512485579851175124849824181751248620498817512486205045
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00142171412171414194304256001224159360x7f2001c39f000x7f200122408000262144000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097346.00000000000.00000000000.0000000000000000000.00000000000017512486802400175124862049881751248736387817512487363815
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00172171412171414194304256001224163840x7f2001c39d800x7f20012240c0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097346.00000000000.00000000000.0000000000000000000.00000000000017512487958480175124873638781751248854916817512488549045
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00202171412171414194304256001224170880x7f2001c39c000x7f200122410000000065536002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097339.00000000000.00000000000.0000000000000000000.00000000000017512489158329175124885491681751248973845917512489738594
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00232171412171414194304256001624177920x7f2001c39a800x7f200122414000000078643204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194602.00000000000.00000000000.0000000000000000000.00000000000017512490334009175124897384591751249098854917512490988382
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00262171412171414194304256001624184960x7f2001c399000x7f2001224180000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194603.00000000000.00000000000.000000000000786432000000.00000000000017512491584957175124909885491751249225560017512492255360
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00292171412171414194304256001624192000x7f2001c397800x7f20012241c000786432000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097343.00000000000.00000000000.0000000000000000000.00000000000017512492849934175124922556001751249342953017512493429349
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00322171412171414194304256001624199040x7f2001c396000x7f2001224200000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097344.00000000000.00000000000.0000000000000000000.00000000000017512494025744175124934295301751249466762117512494667428
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00352171412171414194304256001224206080x7f20042db4800x7f2001224240000000104857602097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097345.00000000000.00000000000.0000000000000000000.00000000000017512495271932175124946676211751249584171117512495841667
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00382171412171414194304256001624213120x7f20042db3000x7f2001224280000000131072004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194603.00000000000.00000000000.0000000000000000000.00000000000017512496437202175124958417111751249714220217512497144694
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00412171412171414194304256001624220160x7f20042db1800x7f20012242c0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194611.00000000000.00000000000.0000000000001310720000000.00000000000017512497737718175124971422021751249842845317512498428420
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00442171412171414194304256001624227200x7f20042db0000x7f2001224300001310720000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097345.00000000000.00000000000.0000000000000000000.00000000000017512499023645175124984284531751249962878317512499628580
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00472171412171414194304256001224234240x7f2001c39e800x7f2001224340000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097344.00000000000.00000000000.0000000000000000000.00000000000017512500224014175124996287831751250084415317512500843918
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00502171412171414194304256001224241280x7f2001c39d000x7f2001224380000000144179202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097343.00000000000.00000000000.0000000000000000000.00000000000017512501448603175125008441531751250205200417512502051817
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00532171412171414194304256001624248320x7f2001c39b800x7f20012243c0000000183500804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194614.00000000000.00000000000.0000000000000000000.00000000000017512502646832175125020520041751250333665517512503336564
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00562171412171414194304256001624255360x7f2001c39a000x7f2001224400000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194606.00000000000.00000000000.0000000000001835008000000.00000000000017512503930909175125033366551751250463874617512504638441
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00592171412171414194304256001224262400x7f2001c398800x7f2001224440001835008000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097344.00000000000.00000000000.0000000000000000000.00000000000017512505234466175125046387461751250582835617512505828310
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00622171412171414194304256001224269440x7f2001c397000x7f2001224480000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097352.00000000000.00000000000.0000000000000000000.00000000000017512506422995175125058283561751250704580617512507045589
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00652171412171414194304256001224276480x7f20042db5800x7f20012244c0000000183500802097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097338.00000000000.00000000000.0000000000000000000.00000000000017512507652094175125070458061751250826629717512508266158
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00682171412171414194304256001624286080x7f20042db4000x7f2001224500000000235929604194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194615.00000000000.00000000000.0000000000000000000.00000000000017512508861962175125082662971751250955862817512509558355
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00712171412171414194304256001624293120x7f20042db2800x7f2001224540000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194604.00000000000.00000000000.0000000000002359296000000.00000000000017512510156009175125095586281751251085271917512510852551
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00742171412171414194304256001224300160x7f20042db1000x7f2001224580002359296000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097347.00000000000.00000000000.0000000000000000000.00000000000017512511447956175125108527191751251204280917512512042671
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077217141217141419430425600824309760x7f2001c39f800x7f20012245c0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097350.00000000000.00000000000.0000000000000000000.00000000000017512512638246175125120428091751251324217917512513242110
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00802171412171414194304256001224316800x7f2001c39e000x7f2001224600000000222822402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097348.00000000000.00000000000.0000000000000000000.00000000000017512513845005175125132421791751251446747017512514467369
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00832171412171414194304256001624326400x7f2001c39c800x7f2001224640000000288358404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194606.00000000000.00000000000.0000000000000000000.00000000000017512515062663175125144674701751251576508117512515764865
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00862171412171414194304256001224336000x7f2001c39b000x7f2001224680000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194603.00000000000.00000000000.0000000000002883584000000.00000000000017512516359640175125157650811751251705485217512517054592
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00892171412171414194304256001224345600x7f2001c399800x7f20012246c0002883584000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097353.00000000000.00000000000.0000000000000000000.00000000000017512517649467175125170548521751251826590217512518265691
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092217141217141419430425600824355200x7f2001c398000x7f2001224700000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097351.00000000000.00000000000.0000000000000000000.00000000000017512518861026175125182659021751251947935217512519479190
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00952171412171414194304256001224362240x7f2001c396800x7f2001224740000000262144002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097344.00000000000.00000000000.0000000000000000000.00000000000017512520081614175125194793521751252066544217512520665129
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00982171412171414194304256001224371840x7f20042db5000x7f2001224780000000340787204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194598.00000000000.00000000000.0000000000000000000.00000000000017512521260564175125206654421751252194353317512521942967
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001012171412171414194304256001224381440x7f20042db3800x7f20012247c0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194603.00000000000.00000000000.0000000000003407872000000.00000000000017512522539961175125219435331751252322386417512523223614
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001042171412171414194304256001224391040x7f20042db2000x7f2001224800003407872000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097345.00000000000.00000000000.0000000000000000000.00000000000017512523826698175125232238641751252441667417512524416543
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107217141217141419430425600824403200x7f20042db0800x7f2001224840000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097361.00000000000.00000000000.0000000000000000000.00000000000017512525015097175125244166741751252562260517512525622292
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001102171412171414194304256001224412800x7f2001c39f000x7f2001224880000000301465602097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097351.00000000000.00000000000.0000000000000000000.00000000000017512526230556175125256226051751252684789517512526847520
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001132171412171414194304256001224422400x7f2001c39d800x7f20012248c0000000393216004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194603.00000000000.00000000000.0000000000000000000.00000000000017512527443435175125268478951751252812694617512528126487
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001162171412171414194304256001224432000x7f2001c39c000x7f2001224900000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194605.00000000000.00000000000.0000000000003932160000000.00000000000017512528722912175125281269461751252940615717512529405964
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119217141217141419430425600824441600x7f2001c39a800x7f2001224940003932160000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097356.00000000000.00000000000.0000000000000000000.00000000000017512530005759175125294061571751253063528717512530634853
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001222171412171414194304256001224453760x7f2001c399000x7f2001224980000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097354.00000000000.00000000000.0000000000000000000.00000000000017512531230557175125306352871751253183241817512531831992
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001252171412171414194304256001224463360x7f2001c397800x7f20012249c0000000340787202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097355.00000000000.00000000000.0000000000000000000.00000000000017512532434707175125318324181751253301834817512533018012
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001282171412171414194304256001224475520x7f2001c396000x7f2001224a00000000445644804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194600.00000000000.00000000000.0000000000000000000.00000000000017512533614946175125330183481751253432827917512534328068
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001312171412171414194304256001224485120x7f20042db4800x7f2001224a40000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194569.00000000000.00000000000.0000000000004456448000000.00000000000017512534922673175125343282791751253558077017512535580296
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134217141217141419430425600824494720x7f20042db3000x7f2001224a80004456448000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097358.00000000000.00000000000.0000000000000000000.00000000000017512536175860175125355807701751253676574017512536765635
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001372171412171414194304256001224506880x7f20042db1800x7f2001224ac0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097356.00000000000.00000000000.0000000000000000000.00000000000017512537361840175125367657401751253796831017512537967484
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001402171412171414194304256001224516480x7f20042db0000x7f2001224b00000000380108802097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097345.00000000000.00000000000.0000000000000000000.00000000000017512538572789175125379655401751253917674317512539183243
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001432171412171414194304256001224528640x7f2001c39e800x7f2001224b40000000498073604194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194586.00000000000.00000000000.0000000000000000000.00000000000017512539774368175125391767431751254046282617512540465250
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001462171412171414194304256001224540800x7f2001c39d000x7f2001224b80000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194569.00000000000.00000000000.0000000000004980736000000.00000000000017512541060965175125404628261751254175979017512541762177
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149217141217141419430425600824552960x7f2001c39b800x7f2001224bc0004980736000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097357.00000000000.00000000000.0000000000000000000.00000000000017512542359712175125417597901751254296747417512542970026
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001522171412171414194304256001224567680x7f2001c39a000x7f2001224c00000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097369.00000000000.00000000000.0000000000000000000.00000000000017512543566021175125429674741751254417259817512544175025
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001552171412171414194304256001224577280x7f2001c398800x7f2001224c40000000419430402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097358.00000000000.00000000000.0000000000000000000.00000000000017512544777840175125441725981751254534796117512545350215
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001582171412171414194304256001224589440x7f2001c397000x7f2001224c80000000550502404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194588.00000000000.00000000000.0000000000000000000.00000000000017512545945010175125453479611751254661532517512546617702
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001612171412171414194304256001224601600x7f20042db5800x7f2001224cc0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194579.00000000000.00000000000.0000000000005505024000000.00000000000017512547213237175125466153251751254789564917512547897979
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164217141217141419430425600824613760x7f20042db4000x7f2001224d00005505024000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097357.00000000000.00000000000.0000000000000000000.00000000000017512548494274175125478956491751254910941317512549111568
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001672171412171414194304256001224628480x7f20042db2800x7f2001224d40000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097357.00000000000.00000000000.0000000000000000000.00000000000017512549707973175125491094131751255031309617512550316187
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001702171412171414194304256001224638080x7f20042db1000x7f2001224d80000000458752002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097354.00000000000.00000000000.0000000000000000000.00000000000017512550921082175125503130961751255149854017512551500757
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001732171412171414194304256001224650240x7f2001c39f800x7f2001224dc0000000602931204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194587.00000000000.00000000000.0000000000000000000.00000000000017512552096191175125514985401751255277214417512552774614
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001762171412171414194304256001224662400x7f2001c39e000x7f2001224e00000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194574.00000000000.00000000000.0000000000006029312000000.00000000000017512553370418175125527721441751255405502817512554057241
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179217141217141419430425600824674560x7f2001c39c800x7f2001224e40006029312000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097359.00000000000.00000000000.0000000000000000000.00000000000017512554653435175125540550281751255527039217512555272639
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001822171412171414194304256001224689280x7f2001c39b000x7f2001224e80000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097363.00000000000.00000000000.0000000000000000000.00000000000017512555871034175125552703921751255646303517512556465359
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001852171412171414194304256001224701440x7f2001c399800x7f2001224ec0000000498073602097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097356.00000000000.00000000000.0000000000000000000.00000000000017512557079823175125564630351751255770943917512557711727
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001882171412171414194304256001224716160x7f2001c398000x7f2001224f00000000655360004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194560.00000000000.00000000000.0000000000000000000.00000000000017512558313141175125577094391751255900208317512559004414
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001912171412171414194304256001224728320x7f2001c396800x7f2001224f40000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194567.00000000000.00000000000.0000000000006553600000000.00000000000017512559602358175125590020831751256028208717512560284621
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194217141217141419430425600824740480x7f20042db5000x7f2001224f80006553600000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097362.00000000000.00000000000.0000000000000000000.00000000000017512560881245175125602820871751256152417117512561526609
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001972171412171414194304256001224757760x7f20042db3800x7f2001224fc0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097351.00000000000.00000000000.0000000000000000000.00000000000017512562122654175125615241711751256272497417512562727558
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002002171412171414194304256001224769920x7f20042db2000x7f2001225000000000537395202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097352.00000000000.00000000000.0000000000000000000.00000000000017512563330672175125627249741751256393057817512563932887
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002032171412171414194304256001224784640x7f20042db0800x7f2001225040000000707788804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194564.00000000000.00000000000.0000000000000000000.00000000000017512564530042175125639305781751256521234217512565214564
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002062171412171414194304256001224799360x7f2001c39f000x7f2001225080000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194557.00000000000.00000000000.0000000000007077888000000.00000000000017512565811509175125652123421751256648706617512566489801
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209217141217141419430425600824814080x7f2001c39d800x7f20012250c0007077888000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097360.00000000000.00000000000.0000000000000000000.00000000000017512567084526175125664870661751256769155017512567693820
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002122171412171414194304256001224831360x7f2001c39c000x7f2001225100000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097348.00000000000.00000000000.0000000000000000000.00000000000017512568290815175125676915501751256888563317512568887950
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002152171412171414194304256001224843520x7f2001c39a800x7f2001225140000000576716802097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097360.00000000000.00000000000.0000000000000000000.00000000000017512569497884175125688856331751257008339717512570086239
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002182171412171414194304256001224858240x7f2001c399000x7f2001225180000000760217604194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194588.00000000000.00000000000.0000000000000000000.00000000000017512570690334175125700833971751257137300117512571375336
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002212171412171414194304256001224872960x7f2001c397800x7f20012251c0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194577.00000000000.00000000000.0000000000007602176000000.00000000000017512571976440175125713730011751257271108517512572713692
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002242171412171414194304256001224887680x7f2001c396000x7f2001225200007602176000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097360.00000000000.00000000000.0000000000000000000.00000000000017512573308776175125727110851751257390340917512573905971
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002272171412171414194304256001224907520x7f20042db4800x7f2001225240000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097347.00000000000.00000000000.0000000000000000000.00000000000017512574503826175125739034091751257510517217512575107740
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002302171412171414194304256001224919680x7f20042db3000x7f2001225280000000616038402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097354.00000000000.00000000000.0000000000000000000.00000000000017512575711475175125751051721751257629941617512576301759
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002332171412171414194304256001224934400x7f20042db1800x7f20012252c0000000812646404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194605.00000000000.00000000000.0000000000000000000.00000000000017512576897904175125762994161751257759078017512577593056
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002362171412171414194304256001224949120x7f20042db0000x7f2001225300000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194574.00000000000.00000000000.0000000000008126464000000.00000000000017512578189201175125775907801751257886486417512578867414
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002392171412171414194304256001224963840x7f2001c39e800x7f2001225340008126464000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097367.00000000000.00000000000.0000000000000000000.00000000000017512579464048175125788648641751258006166717512580064273
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002422171412171414194304256001224983680x7f2001c39d000x7f2001225380000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097341.00000000000.00000000000.0000000000000000000.00000000000017512580658688175125800616671751258130311117512581305301
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002452171412171414194304256001224995840x7f2001c39b800x7f20012253c0000000655360002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097355.00000000000.00000000000.0000000000000000000.00000000000017512581910065175125813031111751258251031517512582512640
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024821714121714141943042560012241013120x7f2001c39a000x7f2001225400000000865075204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194574.00000000000.00000000000.0000000000000000000.00000000000017512583109454175125825103151751258378807917512583790417
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025121714121714141943042560012241027840x7f2001c398800x7f2001225440000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194594.00000000000.00000000000.0000000000008650752000000.00000000000017512584386731175125837880791751258508088317512585083143
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025421714121714141943042560012241042560x7f2001c397000x7f2001225480008650752000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097366.00000000000.00000000000.0000000000000000000.00000000000017512585681898175125850808831751258631416617512586316172
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025721714121714141943042560012241062400x7f20042db5800x7f20012254c0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097334.00000000000.00000000000.0000000000000000000.00000000000017512586919436175125863141661751258755593017512587557950
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026021714121714141943042560012241077120x7f20042db4000x7f2001225500000000694681602097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097361.00000000000.00000000000.0000000000000000000.00000000000017512588167094175125875559301751258875305417512588755109
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026321714121714141943042560016241094400x7f20042db2800x7f2001225540000000917504004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194554.00000000000.00000000000.0000000000000000000.00000000000017512589356064175125887530541751259005193817512590054956
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026621714121714141943042560016241111680x7f20042db1000x7f2001225580000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194591.00000000000.00000000000.0000000000009175040000000.00000000000017512590653660175125900519381751259134778217512591350062
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002692171412171414194304256008241128960x7f2001c39f800x7f20012255c0009175040000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097361.00000000000.00000000000.0000000000000000000.00000000000017512591946747175125913477821751259254890517512592551171
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027221714121714141943042560012241151360x7f2001c39e000x7f2001225600000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097342.00000000000.00000000000.0000000000000000000.00000000000017512593148626175125925489051751259375642917512593758540
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027521714121714141943042560012241166080x7f2001c39c800x7f2001225640000000734003202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097363.00000000000.00000000000.0000000000000000000.00000000000017512594362295175125937564291751259494107317512594943330
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027821714121714141943042560016241183360x7f2001c39b000x7f2001225680000000969932804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194569.00000000000.00000000000.0000000000000000000.00000000000017512595538215175125949410731751259616139617512596163709
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028121714121714141943042560016241200640x7f2001c399800x7f20012256c0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194602.00000000000.00000000000.0000000000009699328000000.00000000000017512596757153175125961613961751259742092017512597423136
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028421714121714141943042560012241217920x7f2001c398000x7f2001225700009699328000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097362.00000000000.00000000000.0000000000000000000.00000000000017512598017351175125974209201751259860828417512598610656
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028721714121714141943042560012241240320x7f2001c396800x7f2001225740000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097332.00000000000.00000000000.0000000000000000000.00000000000017512599205261175125986082841751259980972817512599811975
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029021714121714141943042560012241255040x7f20042db5000x7f2001225780000000812646402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097370.00000000000.00000000000.0000000000000000000.00000000000017512600416300175125998097281751260097917117512600981405
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029321714121714141943042560012241274880x7f20042db3800x7f20012257c00000001074790404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194600.00000000000.00000000000.0000000000000000000.00000000000017512601581720175126009794681751260225003217512602256552
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029621714121714141943042560012241292160x7f20042db2000x7f2001225800000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194584.00000000000.00000000000.00000000000010747904000000.00000000000017512602851307175126022500321751260351339617512603515230
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029921714121714141943042560012241309440x7f20042db0800x7f20012258400010747904000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097363.00000000000.00000000000.0000000000000000000.00000000000017512604113065175126035133961751260467772017512604679640
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030221714121714141943042560012241334400x7f2001c39f000x7f2001225880000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097337.00000000000.00000000000.0000000000000000000.00000000000017512605281595175126046777201751260592652517512605928608
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030521714121714141943042560012241349120x7f2001c39d800x7f20012258c0000000891289602097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097366.00000000000.00000000000.0000000000000000000.00000000000017512606533632175126059265251751260711404917512607116067
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030821714121714141943042560012241368960x7f2001c39c000x7f20012259000000001179648004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194613.00000000000.00000000000.0000000000000000000.00000000000017512607714782175126071140491751260840733317512608409424
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031121714121714141943042560012241388800x7f2001c39a800x7f2001225940000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194585.00000000000.00000000000.00000000000011796480000000.00000000000017512609005059175126084073331751260967981817512609681742
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031421714121714141943042560012241408640x7f2001c399000x7f20012259800011796480000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097360.00000000000.00000000000.0000000000000000000.00000000000017512610277716175126096798181751261087550217512610877571
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031721714121714141943042560012241436160x7f2001c397800x7f20012259c0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097340.00000000000.00000000000.0000000000000000000.00000000000017512611471555175126108755021751261211966717512612121609
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032021714121714141943042560012241453440x7f2001c396000x7f2001225a00000000969932802097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097363.00000000000.00000000000.0000000000000000000.00000000000017512612724723175126121196671751261331183117512613313748
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032321714121714141943042560012241475840x7f20042db4800x7f2001225a400000001284505604194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194608.00000000000.00000000000.0000000000000000000.00000000000017512613908442175126133118311751261459807617512614599965
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032621714121714141943042560012241495680x7f20042db3000x7f2001225a80000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194602.00000000000.00000000000.00000000000012845056000000.00000000000017512615195249175126145980761751261584336017512615845233
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032921714121714141943042560012241515520x7f20042db1800x7f2001225ac00012845056000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097342.00000000000.00000000000.0000000000000000000.00000000000017512616447997175126158433601751261701744417512617019403
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033221714121714141943042560012241543040x7f20042db0000x7f2001225b00000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097340.00000000000.00000000000.0000000000000000000.00000000000017512617623167175126170174441751261826672917512618269300
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033521714121714141943042560012241562880x7f2001c39e800x7f2001225b400000001127219202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097365.00000000000.00000000000.0000000000000000000.00000000000017512618874685175126182667291751261948337317512619485489
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033821714121714141943042560012241587840x7f2001c39d000x7f2001225b800000001494220804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194642.00000000000.00000000000.0000000000000000000.00000000000017512620082834175126194833731751262077025817512620775276
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034121714121714141943042560012241610240x7f2001c39b800x7f2001225bc0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194645.00000000000.00000000000.00000000000014942208000000.00000000000017512621371181175126207702581751262201058217512622012534
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034421714121714141943042560012241632640x7f2001c39a000x7f2001225c000014942208000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097340.00000000000.00000000000.0000000000000000000.00000000000017512622609029175126220105821751262322514617512623227193
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034721714121714141943042560012241665280x7f2001c398800x7f2001225c40000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097344.00000000000.00000000000.0000000000000000000.00000000000017512623829308175126232251461751262450851117512624574019
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035021714121714141943042560012241685120x7f2001c397000x7f2001225c800000001284505602097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097348.00000000000.00000000000.0000000000000000000.00000000000017512625113995175126245085111751262568467517512625686760
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035321714121714141943042560012241712640x7f20042db5800x7f2001225cc00000001703936004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194640.00000000000.00000000000.0000000000000000000.00000000000017512626286965175126256846751751262694788017512626953127
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035621714121714141943042560012241737600x7f20042db4000x7f2001225d00000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194642.00000000000.00000000000.00000000000017039360000000.00000000000017512627547132175126269478801751262821220417512628216435
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035921714121714141943042560012241762560x7f20042db2800x7f2001225d400017039360000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097335.00000000000.00000000000.0000000000000000000.00000000000017512628811610175126282122041751262940068817512629402565
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036221714121714141943042560012241797760x7f20042db1000x7f2001225d80000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097352.00000000000.00000000000.0000000000000000000.00000000000017512630002189175126294006881751263073445317512630799479
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036521714121714141943042560012241822720x7f2001c39f800x7f2001225dc00000001599078402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097336.00000000000.00000000000.0000000000000000000.00000000000017512631345345175126307344531751263194885817512631950839
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036821714121714141943042560012241855360x7f2001c39e000x7f2001225e000000002123366404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194650.00000000000.00000000000.0000000000000000000.00000000000017512632552404175126319488581751263324854217512633312944
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037121714121714141943042560012241885440x7f2001c39c800x7f2001225e40000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194621.00000000000.00000000000.00000000000021233664000000.00000000000017512633846170175126332485421751263452406717512634564792
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037421714121714141943042560012241915520x7f2001c39b000x7f2001225e800021233664000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097346.00000000000.00000000000.0000000000000000000.00000000000017512635124608175126345240671751263577703117512635778981
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037721714121714141943042560012241958400x7f2001c399800x7f2001225ec0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097354.00000000000.00000000000.0000000000000000000.00000000000017512636375565175126357770311751263712167617512637186355
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038021714121714141943042560012241985920x7f2001c398000x7f2001225f000000001913651202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097340.00000000000.00000000000.0000000000000000000.00000000000017512637724951175126371216761751263838008117512638382614
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038321714121714141943042560012242023680x7f2001c396800x7f2001225f400000002542796804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194640.00000000000.00000000000.0000000000000000000.00000000000017512638980259175126383800811751263968120517512639745779
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038621714121714141943042560012242058880x7f20042db5000x7f2001225f80000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194613.00000000000.00000000000.00000000000025427968000000.00000000000017512640281555175126396812051751264095161017512641014786
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038921714121714141943042560012242094080x7f20042db3800x7f2001225fc00025427968000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097375.00000000000.00000000000.0000000000000000000.00000000000017512641551433175126409516101751264223817417512642242225
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039221714121714141943042560012242144640x7f20042db2000x7f2001226000000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097372.00000000000.00000000000.0000000000000000000.00000000000017512642835099175126422381741751264361897917512643681008
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039521714121714141943042560012242177280x7f20042db0800x7f20012260400000002228224002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097351.00000000000.00000000000.0000000000000000000.00000000000017512644222954175126436189791751264484970417512644851447
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039821714121714141943042560012242220160x7f2001c39f000x7f20012260800000002962227204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194631.00000000000.00000000000.0000000000000000000.00000000000017512645448062175126448497041751264617514817512646239472
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040121714121714141943042560012242260480x7f2001c39d800x7f20012260c0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194596.00000000000.00000000000.00000000000029622272000000.00000000000017512646775358175126461751481751264749067317512647554188
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040421714121714141943042560012242300800x7f2001c39c000x7f20012261000029622272000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097376.00000000000.00000000000.0000000000000000000.00000000000017512648098334175126474906731751264876779817512648831545
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040721714121714141943042560012242359040x7f2001c39a800x7f2001226140000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097375.00000000000.00000000000.0000000000000000000.00000000000017512649370241175126487677981751265045788417512650523752
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041021714121714141943042560012242394240x7f2001c399000x7f20012261800000002542796802097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097351.00000000000.00000000000.0000000000000000000.00000000000017512651091657175126504578841751265235373017512652355394
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041321714121714141943042560012242442240x7f2001c397800x7f20012261c00000003381657604194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194614.00000000000.00000000000.0000000000000000000.00000000000017512652965449175126523537301751265424461717512654310604
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041621714121714141943042560012242487680x7f2001c396000x7f2001226200000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194606.00000000000.00000000000.00000000000033816576000000.00000000000017512654857780175126542446171751265613870417512656201796
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041921714121714141943042560012242533120x7f20042db4800x7f20012262400033816576000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097380.00000000000.00000000000.0000000000000000000.00000000000017512656750102175126561387041751265802207117512658095867
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004222171412171414194304256008242555520x7f20042db3000x7f2001226280000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097319.00000000000.00000000000.0000000000000000000.00000000000017512658635643175126580220711751265986495717512659928140
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042521714121714141943042560012242598400x7f20042db1800x7f20012262c00000003171942402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097364.00000000000.00000000000.0000000000000000000.00000000000017512660472806175126598649571751266117600217512661238436
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042821714121714141943042560012242656640x7f20042db0000x7f20012263000000004220518404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194642.00000000000.00000000000.0000000000000000000.00000000000017512661773393175126611760021751266259680717512662661210
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043121714121714141943042560012242712320x7f2001c39e800x7f2001226340000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194615.00000000000.00000000000.00000000000042205184000000.00000000000017512663194276175126625968071751266396897217512664012325
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004342171412171414194304256008242732160x7f2001c39d000x7f20012263800042205184000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097334.00000000000.00000000000.0000000000000000000.00000000000017512664564271175126639763691751266533319017512665381670
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004372171412171414194304256008242757120x7f2001c39b800x7f20012263c0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097328.00000000000.00000000000.0000000000000000000.00000000000017512665921436175126653331901751266696489417512667023348
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044021714121714141943042560012242807680x7f2001c39a000x7f20012264000000003801088002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097371.00000000000.00000000000.0000000000000000000.00000000000017512667563774175126669648941751266831115417512668366773
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044321714121714141943042560012242876160x7f2001c398800x7f20012264400000005059379204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194619.00000000000.00000000000.0000000000000000000.00000000000017512668899100175126683111541751266969885517512669755058
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044621714121714141943042560012242942080x7f2001c397000x7f2001226480000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194623.00000000000.00000000000.00000000000050593792000000.00000000000017512670289324175126696988551751267113407717512671189041
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004492171412171414194304256008242969600x7f20042db5800x7f20012264c00050593792000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097335.00000000000.00000000000.0000000000000000000.00000000000017512671726977175126711340771751267256641917512672598764
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004522171412171414194304256008242999680x7f20042db4000x7f2001226500000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097331.00000000000.00000000000.0000000000000000000.00000000000017512673161890175126725664191751267431380617512674370828
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004552171412171414194304256008243027200x7f20042db2800x7f20012265400000006737100802097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097329.00000000000.00000000000.0000000000000000000.00000000000017512674915804175126743138061751267586583017512675921899
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045821714121714141943042560012243054720x7f20042db1000x7f20012265800000006737100804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194561.00000000000.00000000000.0000000000000000000.00000000000017512676461305175126758658301751267740281317512677459119
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046121714121714141943042560012243082240x7f2001c39f800x7f20012265c0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194556.00000000000.00000000000.00000000000067371008000000.00000000000017512677994245175126774028131751267896923717512679026059
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004642171412171414194304256008243109760x7f2001c39e000x7f20012266000067371008000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097335.00000000000.00000000000.0000000000000000000.00000000000017512679568295175126789692371751268055246117512680609658
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004672171412171414194304256008243132160x7f2001c39c800x7f2001226640000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097318.00000000000.00000000000.0000000000000000000.00000000000017512681140785175126805524611751268248609117512682544279
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004702171412171414194304256008243159680x7f2001c39b000x7f200122668000000013447987202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097325.00000000000.00000000000.0000000000000000000.00000000000017512683083575175126824860911751268440036017512684455930
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047321714121714141943042560012243187200x7f2001c399800x7f20012266c000000013447987204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194553.00000000000.00000000000.0000000000000000000.00000000000017512684988976175126844003601751268633319017512686390370
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047621714121714141943042560012243214720x7f2001c398000x7f2001226700000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194548.00000000000.00000000000.000000000000134479872000000.00000000000017512686928786175126863331901751268829322017512688350090
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004792171412171414194304256008243242240x7f2001c396800x7f200122674000134479872000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097326.00000000000.00000000000.0000000000000000000.00000000000017512688883986175126882932201751269022812917512690287700
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004822171412171414194304256008243264640x7f20042db5000x7f2001226780000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097319.00000000000.00000000000.0000000000000000000.00000000000017512690825486175126902281291751269299825117512693054939
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004852171412171414194304256008243292160x7f20042db3800x7f20012267c000000026869760002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097328.00000000000.00000000000.0000000000000000000.00000000000017512693611354175126929982511751269577573417512695838917
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048821714121714141943042560012243319680x7f20042db2000x7f200122680000000026869760004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194556.00000000000.00000000000.0000000000000000000.00000000000017512696369904175126957757341751269858921717512698650725
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049121714121714141943042560012243347200x7f20042db0800x7f2001226840000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194551.00000000000.00000000000.000000000000268697600000000.00000000000017512699179081175126985892171751270142014017512701477422
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004942171412171414194304256008243374720x7f2001c39f000x7f200122688000268697600000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097335.00000000000.00000000000.0000000000000000000.00000000000017512702008109175127014201401751270418114217512704243991
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049721714121714141943042560082400x7f2001c39d800x7f20012268c0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097318.00000000000.00000000000.0000000000000000000.00000000000017512704769067175127041811421751270860713017512708668707