Files
rocm-systems/tests/workloads/roof_only_SQC/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.kd000144607144607335544322560043241600x00x7fe7c7c04280000000000.00000000008388608.00000000004194304.00000000000.00000000000.0000000000310.00000000004128768.00000000004128768.0000000000000000000.00000000000016054221396415160248176723301605436549255316054365604704
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00214460714460732768256001224138880x00x7fe7c7c23f80000000008192.000000000016384.00000000000.00000000000.00000000000.00000000008261.00000000000.00000000000.0000000000000000000.00000000000016054371227310160543654925531605437159231416054371599322
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051446071446074194304256001224143360x7fe7ee31a3800x7fe7c7c23fc000000026214402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097412.00000000000.00000000000.0000000000000000000.00000000000016054372190658160543715923141605437273889016054372738546
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081446071446074194304256001624150400x7fe7ee31a2000x7fe7c7c2400000000026214404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194608.00000000000.00000000000.0000000000000000000.00000000000016054373340513160543727388901605437408610816054374090246
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111446071446074194304256001624154880x7fe7ee31a0800x7fe7c7c24040000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194596.00000000000.00000000000.000000000000262144000000.00000000000016054374680723160543740861081605437535252516054375351948
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141446071446074194304256001224159360x7fe7ec14df000x7fe7c7c2408000262144000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097346.00000000000.00000000000.0000000000000000000.00000000000016054375946215160543753525251605437652646116054376525772
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171446071446074194304256001224163840x7fe7ec14dd800x7fe7c7c240c0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097344.00000000000.00000000000.0000000000000000000.00000000000016054377118559160543765264611605437772007716054377719665
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201446071446074194304256001224170880x7fe7ec14dc000x7fe7c7c2410000000065536002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097338.00000000000.00000000000.0000000000000000000.00000000000016054378326412160543777200771605437896841416054378968007
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231446071446074194304256001624177920x7fe7ec14da800x7fe7c7c2414000000078643204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194602.00000000000.00000000000.0000000000000000000.00000000000016054379561394160543789684141605438029627216054380299048
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261446071446074194304256001624184960x7fe7ec14d9000x7fe7c7c24180000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194579.00000000000.00000000000.000000000000786432000000.00000000000016054380889185160543802962721605438158460916054381584119
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291446071446074194304256001624192000x7fe7ec14d7800x7fe7c7c241c000786432000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097344.00000000000.00000000000.0000000000000000000.00000000000016054382178566160543815846091605438281486616054382813772
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321446071446074194304256001624199040x7fe7ec14d6000x7fe7c7c24200000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097341.00000000000.00000000000.0000000000000000000.00000000000016054383407809160543828148661605438401584216054384014636
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351446071446074194304256001224206080x7fe7ee31a4800x7fe7c7c24240000000104857602097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097345.00000000000.00000000000.0000000000000000000.00000000000016054384617122160543840158421605438523217816054385230989
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381446071446074194304256001624213120x7fe7ee31a3000x7fe7c7c24280000000131072004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194601.00000000000.00000000000.0000000000000000000.00000000000016054385825885160543852321781605438655123616054386550259
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411446071446074194304256001624220160x7fe7ee31a1800x7fe7c7c242c0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194593.00000000000.00000000000.0000000000001310720000000.00000000000016054387145866160543865512361605438783861416054387839641
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441446071446074194304256001624227200x7fe7ee31a0000x7fe7c7c24300001310720000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097347.00000000000.00000000000.0000000000000000000.00000000000016054388432218160543878386141605438906551016054389064394
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471446071446074194304256001224234240x7fe7ec14de800x7fe7c7c24340000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097349.00000000000.00000000000.0000000000000000000.00000000000016054389658270160543890655101605439029192716054390290516
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501446071446074194304256001224241280x7fe7ec14dd000x7fe7c7c24380000000144179202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097342.00000000000.00000000000.0000000000000000000.00000000000016054390892053160543902919271605439150282316054391501530
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531446071446074194304256001624248320x7fe7ec14db800x7fe7c7c243c0000000183500804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194610.00000000000.00000000000.0000000000000000000.00000000000016054392096106160543915028231605439282732116054392825670
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561446071446074194304256001624255360x7fe7ec14da000x7fe7c7c24400000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194592.00000000000.00000000000.0000000000001835008000000.00000000000016054393419237160543928273211605439416893916054394168220
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591446071446074194304256001224262400x7fe7ec14d8800x7fe7c7c24440001835008000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097336.00000000000.00000000000.0000000000000000000.00000000000016054394762937160543941689391605439537791516054395376764
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621446071446074194304256001224269440x7fe7ec14d7000x7fe7c7c24480000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097351.00000000000.00000000000.0000000000000000000.00000000000016054395969910160543953779151605439657441216054396573017
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651446071446074194304256001224276480x7fe7ee31a5800x7fe7c7c244c0000000183500802097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097340.00000000000.00000000000.0000000000000000000.00000000000016054397174744160543965744121605439776850816054397767431
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681446071446074194304256001624286080x7fe7ee31a4000x7fe7c7c24500000000235929604194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194606.00000000000.00000000000.0000000000000000000.00000000000016054398362347160543977685081605439906548516054399064502
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711446071446074194304256001624293120x7fe7ee31a2800x7fe7c7c24540000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194577.00000000000.00000000000.0000000000002359296000000.00000000000016054399657849160543990654851605440034950216054400348343
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741446071446074194304256001224300160x7fe7ee31a1000x7fe7c7c24580002359296000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097342.00000000000.00000000000.0000000000000000000.00000000000016054400941680160544003495021605440153863816054401537497
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077144607144607419430425600824309760x7fe7ec14df800x7fe7c7c245c0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097350.00000000000.00000000000.0000000000000000000.00000000000016054402132484160544015386381605440272265416054402721421
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801446071446074194304256001224316800x7fe7ec14de000x7fe7c7c24600000000222822402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097347.00000000000.00000000000.0000000000000000000.00000000000016054403322627160544027226541605440392571116054403924504
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831446071446074194304256001624326400x7fe7ec14dc800x7fe7c7c24640000000288358404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194595.00000000000.00000000000.0000000000000000000.00000000000016054404518231160544039257111605440521644816054405215575
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861446071446074194304256001224336000x7fe7ec14db000x7fe7c7c24680000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194603.00000000000.00000000000.0000000000002883584000000.00000000000016054405809292160544052164481605440651902616054406518166
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891446071446074194304256001224345600x7fe7ec14d9800x7fe7c7c246c0002883584000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097350.00000000000.00000000000.0000000000000000000.00000000000016054407111083160544065190261605440770960216054407708210
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092144607144607419430425600824355200x7fe7ec14d8000x7fe7c7c24700000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097355.00000000000.00000000000.0000000000000000000.00000000000016054408301207160544077096021605440890833816054408906903
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951446071446074194304256001224362240x7fe7ec14d6800x7fe7c7c24740000000262144002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097348.00000000000.00000000000.0000000000000000000.00000000000016054409508240160544089083381605441010707416054410106286
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981446071446074194304256001224371840x7fe7ee31a5000x7fe7c7c24780000000340787204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194597.00000000000.00000000000.0000000000000000000.00000000000016054410700763160544101070741605441139381216054411392218
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011446071446074194304256001224381440x7fe7ee31a3800x7fe7c7c247c0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194579.00000000000.00000000000.0000000000003407872000000.00000000000016054411985905160544113938121605441267142916054412669959
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041446071446074194304256001224391040x7fe7ee31a2000x7fe7c7c24800003407872000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097345.00000000000.00000000000.0000000000000000000.00000000000016054413263566160544126714291605441382840416054413827244
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107144607144607419430425600824403200x7fe7ee31a0800x7fe7c7c24840000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097353.00000000000.00000000000.0000000000000000000.00000000000016054414421681160544138284041605441502362016054415022337
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101446071446074194304256001224412800x7fe7ec14df000x7fe7c7c24880000000301465602097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097342.00000000000.00000000000.0000000000000000000.00000000000016054415624014160544150236201605441623451716054416232810
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131446071446074194304256001224422400x7fe7ec14dd800x7fe7c7c248c0000000393216004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194584.00000000000.00000000000.0000000000000000000.00000000000016054416826617160544162345171605441751357416054417512012
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161446071446074194304256001224432000x7fe7ec14dc000x7fe7c7c24900000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194597.00000000000.00000000000.0000000000003932160000000.00000000000016054418106589160544175135741605441878543116054418783894
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119144607144607419430425600824441600x7fe7ec14da800x7fe7c7c24940003932160000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097352.00000000000.00000000000.0000000000000000000.00000000000016054419376911160544187854311605441998896816054419987387
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221446071446074194304256001224453760x7fe7ec14d9000x7fe7c7c24980000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097358.00000000000.00000000000.0000000000000000000.00000000000016054420580924160544199889681605442119762416054421195890
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251446071446074194304256001224463360x7fe7ec14d7800x7fe7c7c249c0000000340787202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097350.00000000000.00000000000.0000000000000000000.00000000000016054421797997160544211976241605442240516016054422403974
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281446071446074194304256001224475520x7fe7ec14d6000x7fe7c7c24a00000000445644804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194592.00000000000.00000000000.0000000000000000000.00000000000016054422998130160544224051601605442369749816054423696125
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311446071446074194304256001224485120x7fe7ee31a4800x7fe7c7c24a40000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194574.00000000000.00000000000.0000000000004456448000000.00000000000016054424289202160544236974981605442498599516054424984506
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134144607144607419430425600824494720x7fe7ee31a3000x7fe7c7c24a80004456448000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097356.00000000000.00000000000.0000000000000000000.00000000000016054425578503160544249859951605442614745116054426146051
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371446071446074194304256001224506880x7fe7ee31a1800x7fe7c7c24ac0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097358.00000000000.00000000000.0000000000000000000.00000000000016054426740677160544261474511605442733162716054427329684
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401446071446074194304256001224516480x7fe7ee31a0000x7fe7c7c24b00000000380108802097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097355.00000000000.00000000000.0000000000000000000.00000000000016054427930901160544273282091605442856085716054428566677
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431446071446074194304256001224528640x7fe7ec14de800x7fe7c7c24b40000000498073604194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194578.00000000000.00000000000.0000000000000000000.00000000000016054429156264160544285608571605442981734516054429818819
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461446071446074194304256001224540800x7fe7ec14dd000x7fe7c7c24b80000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194565.00000000000.00000000000.0000000000004980736000000.00000000000016054430412546160544298173451605443112343416054431125360
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149144607144607419430425600824552960x7fe7ec14db800x7fe7c7c24bc0004980736000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097354.00000000000.00000000000.0000000000000000000.00000000000016054431719007160544311234341605443230312216054432304654
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521446071446074194304256001224567680x7fe7ec14da000x7fe7c7c24c00000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097361.00000000000.00000000000.0000000000000000000.00000000000016054432897901160544323031221605443346457016054433465948
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551446071446074194304256001224577280x7fe7ec14d8800x7fe7c7c24c40000000419430402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097352.00000000000.00000000000.0000000000000000000.00000000000016054434067075160544334645701605443467369816054434675302
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581446071446074194304256001224589440x7fe7ec14d7000x7fe7c7c24c80000000550502404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194586.00000000000.00000000000.0000000000000000000.00000000000016054435269768160544346736981605443594810616054435949963
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611446071446074194304256001224601600x7fe7ee31a5800x7fe7c7c24cc0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194573.00000000000.00000000000.0000000000005505024000000.00000000000016054436543370160544359481061605443722491516054437226995
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164144607144607419430425600824613760x7fe7ee31a4000x7fe7c7c24d00005505024000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097353.00000000000.00000000000.0000000000000000000.00000000000016054437820842160544372249151605443843148316054438433758
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671446071446074194304256001224628480x7fe7ee31a2800x7fe7c7c24d40000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097359.00000000000.00000000000.0000000000000000000.00000000000016054439028165160544384314831605443962381116054439625532
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701446071446074194304256001224638080x7fe7ee31a1000x7fe7c7c24d80000000458752002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097356.00000000000.00000000000.0000000000000000000.00000000000016054440227368160544396238111605444082813916054440830135
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731446071446074194304256001224650240x7fe7ec14df800x7fe7c7c24dc0000000602931204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194587.00000000000.00000000000.0000000000000000000.00000000000016054441424542160544408281391605444214558816054442148786
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761446071446074194304256001224662400x7fe7ec14de000x7fe7c7c24e00000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194571.00000000000.00000000000.0000000000006029312000000.00000000000016054442742683160544421455881605444353071816054443533585
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179144607144607419430425600824674560x7fe7ec14dc800x7fe7c7c24e40006029312000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097356.00000000000.00000000000.0000000000000000000.00000000000016054444127342160544435307181605444482336616054444826246
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821446071446074194304256001224689280x7fe7ec14db000x7fe7c7c24e80000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097352.00000000000.00000000000.0000000000000000000.00000000000016054445419683160544448233661605444614433516054446147907
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851446071446074194304256001224701440x7fe7ec14d9800x7fe7c7c24ec0000000498073602097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097356.00000000000.00000000000.0000000000000000000.00000000000016054446760113160544461443351605444746450416054447467587
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881446071446074194304256001224716160x7fe7ec14d8000x7fe7c7c24f00000000655360004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194647.00000000000.00000000000.0000000000000000000.00000000000016054448060754160544474645041605444872723316054448730089
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911446071446074194304256001224728320x7fe7ec14d6800x7fe7c7c24f40000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194565.00000000000.00000000000.0000000000006553600000000.00000000000016054449326626160544487272331605445006772216054450070090
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194144607144607419430425600824740480x7fe7ee31a5000x7fe7c7c24f80006553600000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097358.00000000000.00000000000.0000000000000000000.00000000000016054450664846160544500677221605445129637016054451298512
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971446071446074194304256001224757760x7fe7ee31a3800x7fe7c7c24fc0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097354.00000000000.00000000000.0000000000000000000.00000000000016054451893419160544512963701605445253125916054452533345
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001446071446074194304256001224769920x7fe7ee31a2000x7fe7c7c25000000000537395202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097355.00000000000.00000000000.0000000000000000000.00000000000016054453136772160544525312591605445377158716054453774157
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031446071446074194304256001224784640x7fe7ee31a0800x7fe7c7c25040000000707788804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194559.00000000000.00000000000.0000000000000000000.00000000000016054454370144160544537715871605445508903616054455091328
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061446071446074194304256001224799360x7fe7ec14df000x7fe7c7c25080000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194570.00000000000.00000000000.0000000000007077888000000.00000000000016054455686415160544550890361605445639208516054456394819
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209144607144607419430425600824814080x7fe7ec14dd800x7fe7c7c250c0007077888000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097361.00000000000.00000000000.0000000000000000000.00000000000016054456987846160544563920851605445760153316054457603952
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121446071446074194304256001224831360x7fe7ec14dc000x7fe7c7c25100000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097347.00000000000.00000000000.0000000000000000000.00000000000016054458199769160544576015331605445883866116054458840725
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151446071446074194304256001224843520x7fe7ec14da800x7fe7c7c25140000000576716802097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097359.00000000000.00000000000.0000000000000000000.00000000000016054459442342160544588386611605446008027016054460082648
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181446071446074194304256001224858240x7fe7ec14d9000x7fe7c7c25180000000760217604194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194594.00000000000.00000000000.0000000000000000000.00000000000016054460676234160544600802701605446138171816054461383809
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211446071446074194304256001224872960x7fe7ec14d7800x7fe7c7c251c0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194571.00000000000.00000000000.0000000000007602176000000.00000000000016054461976636160544613817181605446270588716054462707939
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241446071446074194304256001224887680x7fe7ec14d6000x7fe7c7c25200007602176000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097362.00000000000.00000000000.0000000000000000000.00000000000016054463302776160544627058871605446392285616054463924842
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271446071446074194304256001224907520x7fe7ee31a4800x7fe7c7c25240000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097347.00000000000.00000000000.0000000000000000000.00000000000016054464519699160544639228561605446517070416054465172315
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301446071446074194304256001224919680x7fe7ee31a3000x7fe7c7c25280000000616038402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097354.00000000000.00000000000.0000000000000000000.00000000000016054465775371160544651707041605446640335216054466405057
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331446071446074194304256001224934400x7fe7ee31a1800x7fe7c7c252c0000000812646404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194569.00000000000.00000000000.0000000000000000000.00000000000016054466999714160544664033521605446771280116054467714738
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361446071446074194304256001224949120x7fe7ee31a0000x7fe7c7c25300000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194557.00000000000.00000000000.0000000000008126464000000.00000000000016054468309955160544677128011605446901345016054469015399
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391446071446074194304256001224963840x7fe7ec14de800x7fe7c7c25340008126464000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097364.00000000000.00000000000.0000000000000000000.00000000000016054469608156160544690134501605447023585816054470237692
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421446071446074194304256001224983680x7fe7ec14dd000x7fe7c7c25380000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097332.00000000000.00000000000.0000000000000000000.00000000000016054470832109160544702358581605447150306716054471505304
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451446071446074194304256001224995840x7fe7ec14db800x7fe7c7c253c0000000655360002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097358.00000000000.00000000000.0000000000000000000.00000000000016054472106871160544715030671605447272403516054472725787
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024814460714460741943042560012241013120x7fe7ec14da000x7fe7c7c25400000000865075204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194600.00000000000.00000000000.0000000000000000000.00000000000016054473319704160544727240351605447401764416054474019618
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025114460714460741943042560012241027840x7fe7ec14d8800x7fe7c7c25440000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194570.00000000000.00000000000.0000000000008650752000000.00000000000016054474614835160544740176441605447531093316054475313170
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025414460714460741943042560012241042560x7fe7ec14d7000x7fe7c7c25480008650752000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097361.00000000000.00000000000.0000000000000000000.00000000000016054475906756160544753109331605447654150116054476543022
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025714460714460741943042560012241062400x7fe7ee31a5800x7fe7c7c254c0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097332.00000000000.00000000000.0000000000000000000.00000000000016054477137219160544765415011605447776342916054477765315
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026014460714460741943042560012241077120x7fe7ee31a4000x7fe7c7c25500000000694681602097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097361.00000000000.00000000000.0000000000000000000.00000000000016054478367931160544777634291605447899623816054478997727
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026314460714460741943042560016241094400x7fe7ee31a2800x7fe7c7c25540000000917504004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194568.00000000000.00000000000.0000000000000000000.00000000000016054479592634160544789962381605448029480616054480296849
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026614460714460741943042560016241111680x7fe7ee31a1000x7fe7c7c25580000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194563.00000000000.00000000000.0000000000009175040000000.00000000000016054480891245160544802948061605448157161516054481573630
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691446071446074194304256008241128960x7fe7ec14df800x7fe7c7c255c0009175040000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097365.00000000000.00000000000.0000000000000000000.00000000000016054482169277160544815716151605448284682416054482849812
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027214460714460741943042560012241151360x7fe7ec14de000x7fe7c7c25600000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097425.00000000000.00000000000.0000000000000000000.00000000000016054483444829160544828468241605448405547216054484058095
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027514460714460741943042560012241166080x7fe7ec14dc800x7fe7c7c25640000000734003202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097358.00000000000.00000000000.0000000000000000000.00000000000016054484661442160544840554721605448533548016054485338477
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027814460714460741943042560016241183360x7fe7ec14db000x7fe7c7c25680000000969932804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194652.00000000000.00000000000.0000000000000000000.00000000000016054485931474160544853354801605448659516916054486597879
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028114460714460741943042560016241200640x7fe7ec14d9800x7fe7c7c256c0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194587.00000000000.00000000000.0000000000009699328000000.00000000000016054487193786160544865951691605448799309816054487996128
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028414460714460741943042560012241217920x7fe7ec14d8000x7fe7c7c25700009699328000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097362.00000000000.00000000000.0000000000000000000.00000000000016054488589375160544879930981605448932478716054489327658
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028714460714460741943042560012241240320x7fe7ec14d6800x7fe7c7c25740000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097333.00000000000.00000000000.0000000000000000000.00000000000016054489921635160544893247871605449064255616054490644989
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029014460714460741943042560012241255040x7fe7ee31a5000x7fe7c7c25780000000812646402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097364.00000000000.00000000000.0000000000000000000.00000000000016054491247606160544906421291605449196901616054491971880
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029314460714460741943042560012241274880x7fe7ee31a3800x7fe7c7c257c00000001074790404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194604.00000000000.00000000000.0000000000000000000.00000000000016054492566977160544919690161605449325878416054493261731
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029614460714460741943042560012241292160x7fe7ee31a2000x7fe7c7c25800000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194585.00000000000.00000000000.00000000000010747904000000.00000000000016054493855958160544932587841605449459287216054494595242
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029914460714460741943042560012241309440x7fe7ee31a0800x7fe7c7c258400010747904000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097362.00000000000.00000000000.0000000000000000000.00000000000016054495190408160544945928721605449583463916054495837124
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030214460714460741943042560012241334400x7fe7ec14df000x7fe7c7c25880000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097321.00000000000.00000000000.0000000000000000000.00000000000016054496431481160544958346391605449710616716054497108426
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030514460714460741943042560012241349120x7fe7ec14dd800x7fe7c7c258c0000000891289602097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097362.00000000000.00000000000.0000000000000000000.00000000000016054497711472160544971061671605449835593416054498358898
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030814460714460741943042560012241368960x7fe7ec14dc000x7fe7c7c259000000001179648004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194613.00000000000.00000000000.0000000000000000000.00000000000016054498953985160544983559341605449967002216054499672199
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031114460714460741943042560012241388800x7fe7ec14da800x7fe7c7c25940000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194584.00000000000.00000000000.00000000000011796480000000.00000000000016054500266556160544996700221605450098907016054500991470
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031414460714460741943042560012241408640x7fe7ec14d9000x7fe7c7c259800011796480000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097358.00000000000.00000000000.0000000000000000000.00000000000016054501586307160545009890701605450222523816054502227322
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031714460714460741943042560012241436160x7fe7ec14d7800x7fe7c7c259c0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097331.00000000000.00000000000.0000000000000000000.00000000000016054502821579160545022252381605450351116516054503513444
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032014460714460741943042560012241453440x7fe7ec14d6000x7fe7c7c25a00000000969932802097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097367.00000000000.00000000000.0000000000000000000.00000000000016054504115740160545035111651605450471725316054504719217
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032314460714460741943042560012241475840x7fe7ee31a4800x7fe7c7c25a400000001284505604194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194624.00000000000.00000000000.0000000000000000000.00000000000016054505313434160545047172531605450601646016054506018608
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032614460714460741943042560012241495680x7fe7ee31a3000x7fe7c7c25a80000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194597.00000000000.00000000000.00000000000012845056000000.00000000000016054506614485160545060164601605450733406816054507336219
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032914460714460741943042560012241515520x7fe7ee31a1800x7fe7c7c25ac00012845056000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097340.00000000000.00000000000.0000000000000000000.00000000000016054507931606160545073340681605450857231616054508574662
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033214460714460741943042560012241543040x7fe7ee31a0000x7fe7c7c25b00000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097329.00000000000.00000000000.0000000000000000000.00000000000016054509169428160545085723161605450987968416054509881363
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033514460714460741943042560012241562880x7fe7ec14de800x7fe7c7c25b400000001127219202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097358.00000000000.00000000000.0000000000000000000.00000000000016054510484769160545098796841605451118209216054511183814
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033814460714460741943042560012241587840x7fe7ec14dd000x7fe7c7c25b800000001494220804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194634.00000000000.00000000000.0000000000000000000.00000000000016054511778840160545111820921605451246241916054512464175
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034114460714460741943042560012241610240x7fe7ec14db800x7fe7c7c25bc0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194632.00000000000.00000000000.00000000000014942208000000.00000000000016054513057862160545124624191605451375298716054513754856
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034414460714460741943042560012241632640x7fe7ec14da000x7fe7c7c25c000014942208000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097337.00000000000.00000000000.0000000000000000000.00000000000016054514349233160545137529871605451497011416054514971859
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034714460714460741943042560012241665280x7fe7ec14d8800x7fe7c7c25c40000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097334.00000000000.00000000000.0000000000000000000.00000000000016054515565186160545149701141605451628724216054516349859
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035014460714460741943042560012241685120x7fe7ec14d7000x7fe7c7c25c800000001284505602097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097352.00000000000.00000000000.0000000000000000000.00000000000016054516891787160545162872421605451749749016054517499253
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035314460714460741943042560012241712640x7fe7ee31a5800x7fe7c7c25cc00000001703936004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194637.00000000000.00000000000.0000000000000000000.00000000000016054518097010160545174974901605451881125716054518813524
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035614460714460741943042560012241737600x7fe7ee31a4000x7fe7c7c25d00000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194639.00000000000.00000000000.00000000000017039360000000.00000000000016054519407281160545188112571605452012438516054520126755
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035914460714460741943042560012241762560x7fe7ee31a2800x7fe7c7c25d400017039360000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097328.00000000000.00000000000.0000000000000000000.00000000000016054520720412160545201243851605452138439316054521386457
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036214460714460741943042560012241797760x7fe7ee31a1000x7fe7c7c25d80000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097338.00000000000.00000000000.0000000000000000000.00000000000016054521981034160545213843931605452272536116054522791556
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036514460714460741943042560012241822720x7fe7ec14df800x7fe7c7c25dc00000001599078402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097339.00000000000.00000000000.0000000000000000000.00000000000016054523331374160545227253611605452399128916054523993739
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036814460714460741943042560012241855360x7fe7ec14de000x7fe7c7c25e000000002123366404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194643.00000000000.00000000000.0000000000000000000.00000000000016054524587646160545239912891605452530361616054525367499
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037114460714460741943042560012241885440x7fe7ec14dc800x7fe7c7c25e40000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194635.00000000000.00000000000.00000000000021233664000000.00000000000016054525898887160545253036161605452662618416054526690819
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037414460714460741943042560012241915520x7fe7ec14db000x7fe7c7c25e800021233664000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097327.00000000000.00000000000.0000000000000000000.00000000000016054527222677160545266261841605452789275216054527895043
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037714460714460741943042560012241958400x7fe7ec14d9800x7fe7c7c25ec0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097352.00000000000.00000000000.0000000000000000000.00000000000016054528488309160545278927521605452943612116054529456038
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038014460714460741943042560012241985920x7fe7ec14d8000x7fe7c7c25f000000001913651202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097342.00000000000.00000000000.0000000000000000000.00000000000016054530041195160545294361211605453082205016054530824108
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038314460714460741943042560012242023680x7fe7ec14d6800x7fe7c7c25f400000002542796804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194626.00000000000.00000000000.0000000000000000000.00000000000016054531420554160545308220501605453213997816054532157658
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038614460714460741943042560012242058880x7fe7ee31a5000x7fe7c7c25f80000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194612.00000000000.00000000000.00000000000025427968000000.00000000000016054532734485160545321399781605453359502616054533618146
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038914460714460741943042560012242094080x7fe7ee31a3800x7fe7c7c25fc00025427968000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097336.00000000000.00000000000.0000000000000000000.00000000000016054534193533160545335950261605453488191416054534899927
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039214460714460741943042560012242144640x7fe7ee31a2000x7fe7c7c26000000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097367.00000000000.00000000000.0000000000000000000.00000000000016054535476764160545348819141605453645472416054536471372
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039514460714460741943042560012242177280x7fe7ee31a0800x7fe7c7c260400000002228224002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097344.00000000000.00000000000.0000000000000000000.00000000000016054537057879160545364547241605453784305216054537845152
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039814460714460741943042560012242220160x7fe7ec14df000x7fe7c7c260800000002962227204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194624.00000000000.00000000000.0000000000000000000.00000000000016054538440999160545378430521605453918514016054539227711
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040114460714460741943042560012242260480x7fe7ec14dd800x7fe7c7c260c0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194600.00000000000.00000000000.00000000000029622272000000.00000000000016054539781379160545391851401605454052498816054540565992
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040414460714460741943042560012242300800x7fe7ec14dc000x7fe7c7c261000029622272000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097371.00000000000.00000000000.0000000000000000000.00000000000016054541120309160545405249881605454197891716054542001220
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040714460714460741943042560012242359040x7fe7ec14da800x7fe7c7c26140000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097377.00000000000.00000000000.0000000000000000000.00000000000016054542576217160545419789171605454344724616054543467817
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041014460714460741943042560012242394240x7fe7ec14d9000x7fe7c7c261800000002542796802097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097353.00000000000.00000000000.0000000000000000000.00000000000016054544049804160545434472461605454486693416054544868966
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041314460714460741943042560012242442240x7fe7ec14d7800x7fe7c7c261c00000003381657604194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194611.00000000000.00000000000.0000000000000000000.00000000000016054545462132160545448669341605454635446316054546418221
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041614460714460741943042560012242487680x7fe7ec14d6000x7fe7c7c26200000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194605.00000000000.00000000000.00000000000033816576000000.00000000000016054546950109160545463544631605454783127216054547847919
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041914460714460741943042560012242533120x7fe7ee31a4800x7fe7c7c262400033816576000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097354.00000000000.00000000000.0000000000000000000.00000000000016054548427147160545478312721605454929400116054549311147
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221446071446074194304256008242555520x7fe7ee31a3000x7fe7c7c26280000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097318.00000000000.00000000000.0000000000000000000.00000000000016054549888904160545492940011605455098937116054551031489
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042514460714460741943042560012242598400x7fe7ee31a1800x7fe7c7c262c00000003171942402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097357.00000000000.00000000000.0000000000000000000.00000000000016054551596426160545509893711605455229657916054552337280
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042814460714460741943042560012242656640x7fe7ee31a0000x7fe7c7c263000000004220518404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194624.00000000000.00000000000.0000000000000000000.00000000000016054552893518160545522965791605455371338716054553755748
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043114460714460741943042560012242712320x7fe7ec14de800x7fe7c7c26340000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194610.00000000000.00000000000.00000000000042205184000000.00000000000016054554310286160545537133441605455511847116054555159977
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341446071446074194304256008242732160x7fe7ec14dd000x7fe7c7c263800042205184000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097321.00000000000.00000000000.0000000000000000000.00000000000016054555715315160545551184711605455651800016054556559616
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371446071446074194304256008242757120x7fe7ec14db800x7fe7c7c263c0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097323.00000000000.00000000000.0000000000000000000.00000000000016054557114694160545565180001605455818553016054558227779
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044014460714460741943042560012242807680x7fe7ec14da000x7fe7c7c264000000003801088002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097362.00000000000.00000000000.0000000000000000000.00000000000016054558792007160545581855301605455956777816054559587649
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044314460714460741943042560012242876160x7fe7ec14d8800x7fe7c7c264400000005059379204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194610.00000000000.00000000000.0000000000000000000.00000000000016054560161826160545595677781605456116682716054561184114
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044614460714460741943042560012242942080x7fe7ec14d7000x7fe7c7c26480000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194618.00000000000.00000000000.00000000000050593792000000.00000000000016054561762241160545611668271605456274731716054562788818
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491446071446074194304256008242969600x7fe7ee31a5800x7fe7c7c264c00050593792000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097334.00000000000.00000000000.0000000000000000000.00000000000016054563343536160545627473171605456432364616054564340684
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521446071446074194304256008242999680x7fe7ee31a4000x7fe7c7c26500000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097333.00000000000.00000000000.0000000000000000000.00000000000016054564919231160545643236461605456620397716054566270451
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551446071446074194304256008243027200x7fe7ee31a2800x7fe7c7c265400000006737100802097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097326.00000000000.00000000000.0000000000000000000.00000000000016054566810569160545662039771605456775502616054567796687
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045814460714460741943042560012243054720x7fe7ee31a1000x7fe7c7c265800000006737100804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194554.00000000000.00000000000.0000000000000000000.00000000000016054568352465160545677550261605456932751616054569369802
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046114460714460741943042560012243082240x7fe7ec14df800x7fe7c7c265c0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194554.00000000000.00000000000.00000000000067371008000000.00000000000016054569923510160545693275161605457102896616054571093484
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641446071446074194304256008243109760x7fe7ec14de000x7fe7c7c266000067371008000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097328.00000000000.00000000000.0000000000000000000.00000000000016054571625552160545710289661605457270305616054572719988
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671446071446074194304256008243132160x7fe7ec14dc800x7fe7c7c26640000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097316.00000000000.00000000000.0000000000000000000.00000000000016054573298405160545727030561605457479570816054574860680
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701446071446074194304256008243159680x7fe7ec14db000x7fe7c7c2668000000013447987202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097323.00000000000.00000000000.0000000000000000000.00000000000016054575400509160545747957081605457688740116054576904885
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047314460714460741943042560012243187200x7fe7ec14d9800x7fe7c7c266c000000013447987204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194545.00000000000.00000000000.0000000000000000000.00000000000016054577482912160545768874011605457900053316054579066307
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047614460714460741943042560012243214720x7fe7ec14d8000x7fe7c7c26700000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194545.00000000000.00000000000.000000000000134479872000000.00000000000016054579597415160545790005331605458094806516054580970825
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791446071446074194304256008243242240x7fe7ec14d6800x7fe7c7c2674000134479872000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097322.00000000000.00000000000.0000000000000000000.00000000000016054581544152160545809480651605458291495716054582981940
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821446071446074194304256008243264640x7fe7ee31a5000x7fe7c7c26780000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097315.00000000000.00000000000.0000000000000000000.00000000000016054583512628160545829149571605458573641316054585780278
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851446071446074194304256008243292160x7fe7ee31a3800x7fe7c7c267c000000026869760002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097322.00000000000.00000000000.0000000000000000000.00000000000016054586348505160545857364131605458851819016054588561236
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048814460714460741943042560012243319680x7fe7ee31a2000x7fe7c7c2680000000026869760004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194543.00000000000.00000000000.0000000000000000000.00000000000016054589114184160545885181901605459148060716054591528610
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049114460714460741943042560012243347200x7fe7ee31a0800x7fe7c7c26840000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194542.00000000000.00000000000.000000000000268697600000000.00000000000016054592077038160545914806071605459443854516054594508434
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941446071446074194304256008243374720x7fe7ec14df000x7fe7c7c2688000268697600000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097328.00000000000.00000000000.0000000000000000000.00000000000016054595036342160545944385451605459719392116054597240584
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049714460714460741943042560082400x7fe7ec14dd800x7fe7c7c268c0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097315.00000000000.00000000000.0000000000000000000.00000000000016054597790111160545971939211605460163602816054601714004