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

90 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_CYCLESSQ_BUSY_CYCLESSQ_BUSY_CU_CYCLESSQ_WAVESSQ_WAVE_CYCLESGRBM_COUNTGRBM_GUI_ACTIVETCP_GATE_EN1_sumTCP_GATE_EN2_sumTCP_TD_TCP_STALL_CYCLES_sumTCP_TCR_TCP_STALL_CYCLES_sumTCP_READ_TAGCONFLICT_STALL_CYCLES_sumTCP_WRITE_TAGCONFLICT_STALL_CYCLES_sumTCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sumTCP_TA_TCP_STATE_READ_sumTCP_VOLATILE_sumTCP_TOTAL_ACCESSES_sumTCP_TOTAL_READ_sumTCP_TOTAL_WRITE_sumTCP_TOTAL_ATOMIC_WITH_RET_sumTCP_TOTAL_ATOMIC_WITHOUT_RET_sumTCP_TOTAL_WRITEBACK_INVALIDATES_sumTCP_TOTAL_CACHE_ACCESSES_sumTCP_UTCL1_TRANSLATION_MISS_sumTCP_UTCL1_TRANSLATION_HIT_sumTCP_UTCL1_PERMISSION_MISS_sumTCP_UTCL1_REQUEST_sumTCP_TCP_LATENCY_sumTCP_TCC_READ_REQ_LATENCY_sumTCP_TCC_WRITE_REQ_LATENCY_sumTCP_TCC_READ_REQ_sumTCP_TCC_WRITE_REQ_sumTCP_TCC_ATOMIC_WITH_RET_REQ_sumTCP_TCC_ATOMIC_WITHOUT_RET_REQ_sumTCP_TCC_NC_READ_REQ_sumTCP_TCC_NC_WRITE_REQ_sumTCP_TCC_NC_ATOMIC_REQ_sumTCP_TCC_UC_READ_REQ_sumTCP_TCC_UC_WRITE_REQ_sumTCP_TCC_UC_ATOMIC_REQ_sumTCP_TCC_CC_READ_REQ_sumTCP_TCC_CC_WRITE_REQ_sumTCP_TCC_CC_ATOMIC_REQ_sumTCP_TCC_RW_READ_REQ_sumTCP_TCC_RW_WRITE_REQ_sumTCP_TCC_RW_ATOMIC_REQ_sumTCP_PENDING_STALL_CYCLES_sumDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000151449151449335544322560043241600x00x7f022a604280307651229895743884201352428824212188938456338456339106410.038083768.03.04067115.00.00.00.0524288.033554432.033554432.00.033554432.00.00.0104.08388608.013284.08242484.00.08388608.0313264439.00.01463068751.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.019128712.016219564975519162275629006591622756313906016219710251567
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00215144915144932768256001224138880x00x7f022a623f802650081690561410267512175615733125331252433904.0174869.0208.00.00.00.00.04096.065536.065536.065536.00.00.00.0104.016384.0104.015240.00.016384.03868580.05430964.00.08192.00.00.00.00.00.00.00.00.00.00.00.00.08192.00.00.0124860.016219715974101162275679360471622756794948716219716213625
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051514491514494194304256001224143360x7f022d5aa3800x7f022a623fc01390672125789016244343655369513883317383317383316588733.013862093.023826.0680816.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0208.02097152.06560.02028965.00.02097152.0894852738.02174316602.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011602704.016219716751753162275680195671622756811220816219717067306
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081514491514494194304256001624150400x7f022d5aa2000x7f022a62400024994322374679307556756553621291487931242831242831107159.028741345.00.0572006.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0208.08388608.012853.08248294.00.08388608.0854492054.03923958668.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020553314.016219717610354162275681469281622756832548916219718027305
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111514491514494194304256001624154880x7f022d5aa0800x7f022a62404024973282392794309822196553622678414831216531216531342537.029793298.00.0641236.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012902.08247484.00.08388608.0850784226.03853370502.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020646198.016219718564363162275683509291622756853061016219719066582
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141514491514494194304256001224159360x7f022af09f000x7f022a6240801395672127440516452085655367993473617445817445816804975.013765491.024080.0422181.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0208.02097152.06612.02027824.00.02097152.0994245048.02214385136.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011607319.016219719601950162275685552501622756864901116219719931123
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171514491514494194304256001224163840x7f022af09d800x7f022a6240c01333088122674715857629655368208356416663516663516183757.014566834.023494.0973484.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06593.02028813.00.02097152.0983783794.02310020724.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012337788.016219720467601162275686742911622756876629116219720909051
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201514491514494194304256001224170880x7f022af09c000x7f022a62410014310481328751172177886553611578205417888017888017509757.014249171.025266.0327616.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06606.02031204.00.02097152.01004688991.02215423101.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011846944.016219721455469162275688062921622756889877216219721795641
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231514491514494194304256001624177920x7f022af09a800x7f022a62414024770962371831307352506553622786640630963630963631070005.029507529.00.0910440.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0208.08388608.012809.08248606.00.08388608.0825473681.03946828205.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020650851.016219722331500162275689307721622756911077316219722860388
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261514491514494194304256001624184960x7f022af099000x7f022a62418024680322345045303888646553621302938930850330850330721839.028564368.00.0404286.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012618.08250932.00.08388608.0847029950.03986558870.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020983551.016219723394486162275691395731622756932101416219723791618
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291514491514494194304256001624192000x7f022af097800x7f022a6241c01318560121582615738282655369048431616481916481916041953.014400932.024885.0561732.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0208.02097152.06628.02049765.00.02097152.01011554299.02365821621.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011392083.016219724327956162275693496551622756944309516219724780966
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321514491514494194304256001624199040x7f022af096000x7f022a62420014696881368233177089836553611431914618371018371018023205.014525386.024026.0816644.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0208.02097152.06615.02051730.00.02097152.0978769267.02303738539.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012258186.016219725315504162275694832551622756957637616219725643457
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351514491514494194304256001224206080x7f022d5aa4800x7f022a62424013096241207786156371836553610606705016370216370215937303.014409292.024436.0551561.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06648.02029425.00.02097152.0999115972.02280322338.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011479658.016219726189695162275696208561622756971445716219726639415
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381514491514494194304256001624213120x7f022d5aa3000x7f022a62428024825282375471307985466553622524445631031531031531117195.029558235.00.0998336.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012870.08247855.00.08388608.0875980685.03813849219.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.021148176.016219727175193162275697542971622756993317816219727682662
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411514491514494194304256001624220160x7f022d5aa1800x7f022a6242c024763762370338307057156553622054185730954630954631050479.029482297.00.01002719.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012562.08251222.00.08388608.0855156177.03959307381.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020077740.016219728218010162275699715781622757015109916219728697009
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441514491514494194304256001624227200x7f022d5aa0000x7f022a6243001322456121513715723453655368457873316530616530616033035.014461100.024317.0578277.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06615.02054320.00.02097152.0987775405.02355093222.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.013127425.016219729233027162275701792591622757027366016219729617169
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471514491514494194304256001224234240x7f022af09e800x7f022a6243401309352120713015633719655369313377716366816366815928827.014392001.024210.0948052.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06574.02031545.00.02097152.01002515839.02322675189.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012229625.016219730152807162275703115801622757040502116219730543418
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501514491514494194304256001224241280x7f022af09d000x7f022a6243801309840120461215577651655369352282816372916372915896145.014285915.024405.0767208.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06564.02029713.00.02097152.0982095459.02316806402.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012178509.016219731086046162275704381411622757053142116219731489457
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531514491514494194304256001624248320x7f022af09b800x7f022a6243c024757762374375307871416553622878666130947130947131103181.029539627.00.01002057.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.013000.08246973.00.08388608.0868946855.03811280101.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.021025000.016219732025446162275705632621622757074182316219732495585
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561514491514494194304256001624255360x7f022af09a000x7f022a62440024593682354063304807086553621905073430742030742030839047.029328167.00.0956809.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012605.08251073.00.08388608.0879923556.03768310018.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020839794.016219733030434162275707739831622757095462416219733501953
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591514491514494194304256001224262400x7f022af098800x7f022a62444013062001205334155986566553610450824416327416327415905453.014356968.024565.0895349.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06576.02030919.00.02097152.0984336727.02238119997.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012299914.016219734037241162275709837441622757107734516219734418793
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621514491514494194304256001224269440x7f022af097000x7f022a6244801312176120823815626051655369537414316402116402115943257.014311337.024289.0843243.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06595.02029585.00.02097152.0967331056.02325847979.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012203795.016219734954771162275711074251622757120086516219735324493
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651514491514494194304256001224276480x7f022d5aa5800x7f022a6244c013093201204304155965726553610210514116366416366415892050.014418891.023608.0822941.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06588.02031537.00.02097152.0973140143.02212813454.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012256527.016219735867201162275712355851622757132774616219736255022
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681514491514494194304256001624286080x7f022d5aa4000x7f022a62450024642962356943305382976553622384048330803630803630876409.029309993.00.0960404.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012964.08247316.00.08388608.0859123508.03759240854.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020612663.016219736791410162275713744661622757155398716219737258190
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711514491514494194304256001624293120x7f022d5aa2800x7f022a62454024459602340092303020856553621821160430574430574430657541.029018539.00.0871605.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012500.08252156.00.08388608.0858131332.03858441631.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020893663.016219737793388162275715807071622757176230816219738290517
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741514491514494194304256001224300160x7f022d5aa1000x7f022a6245801299736119588615470360655369599854216246616246615782707.014328440.024867.0750403.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06579.02031211.00.02097152.0981897361.02361801752.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012215142.016219738825885162275717882291622757187990916219739203177
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077151449151449419430425600824309760x7f022af09f800x7f022a6245c01295848119025615387236655368888739916198016198015709517.014233296.024395.0737599.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06577.02030299.00.02097152.0967374776.02200958427.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012236236.016219739737975162275719064691622757199847016219740118977
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801514491514494194304256001224316800x7f022af09e000x7f022a6246001309984119498115451431655368846115916374716374715771059.014239389.024642.0619284.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06549.02031181.00.02097152.0987993748.02190604012.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012172597.016219740661415162275720328701622757212583116219741037266
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831514491514494194304256001624326400x7f022af09c800x7f022a62464024648162352130304517326553622412803230810130810130813853.029313398.00.0950130.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012954.08247532.00.08388608.0861565952.03883785747.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020801209.016219741571864162275721520711622757233207216219742030714
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861514491514494194304256001224336000x7f022af09b000x7f022a62468024610402353515304687706553622281028630762930762930831793.029281718.00.0859965.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012740.08249616.00.08388608.0864131064.03929041828.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020802873.016219742567252162275723573521622757253639316219743037772
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891514491514494194304256001224345600x7f022af099800x7f022a6246c01311424120329915571527655369441530716392716392715878933.014331553.025015.0633741.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06532.02031390.00.02097152.0993698799.02371012542.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012123084.016219743572970162275725632731622757265687416219743959442
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092151449151449419430425600824355200x7f022af098000x7f022a6247001319528120992015605494655368814270616494016494015964967.014370138.023510.0845440.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06527.02029706.00.02097152.0939606021.02214493828.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012171489.016219744494780162275726818341622757277543416219744883721
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951514491514494194304256001224362240x7f022af096800x7f022a6247401307264120270215563142655369929987916340716340715871367.014256907.024128.0950974.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06541.02031476.00.02097152.0975310312.02274414300.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012176774.016219745425769162275728093541622757290231516219745810661
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981514491514494194304256001224371840x7f022d5aa5000x7f022a62478024392402337398302734216553622685949930490430490430622207.029126087.00.0456659.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012852.08248431.00.08388608.0858822988.03816408485.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020616744.016219746347219162275729264751622757310567616219746818369
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011514491514494194304256001224381440x7f022d5aa3800x7f022a6247c024703522362938306210666553622388263230879330879330954331.029384532.00.0903614.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012887.08248325.00.08388608.0861091734.03887824660.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020643359.016219747354267162275731325561622757331319716219747813877
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041514491514494194304256001224391040x7f022d5aa2000x7f022a6248001311088120911015638101655369526825316388516388515954619.014327993.024847.0671677.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06593.02029227.00.02097152.0958652993.02318105086.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012036825.016219748348935162275733389581622757343239816219748747716
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107151449151449419430425600824403200x7f022d5aa0800x7f022a6248401298192119584115434838655368979588516227316227315782161.014199814.024947.0529713.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06577.02055912.00.02097152.0906927897.02158742201.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012181887.016219749282544162275734576781622757355191916219749654726
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101514491514494194304256001224412800x7f022af09f000x7f022a62488013115921207133156166296553610601494916394816394815928931.014311051.022655.01085245.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06585.02030156.00.02097152.0988291070.02236204364.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012049512.016219750198574162275735850391622757367783916219750587955
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131514491514494194304256001224422400x7f022af09d800x7f022a6248c024536642348433304337996553622356148830670730670730765779.029221696.00.0955032.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012835.08248492.00.08388608.0866108711.03766349436.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020775908.016219751122583162275737028001622757388200116219751596203
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161514491514494194304256001224432000x7f022af09c000x7f022a62490024455442334470302270636553622138325730569230569230584247.029112372.00.0841994.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012868.08248559.00.08388608.0866721897.03815007948.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020688479.016219752132251162275739088811622757408872216219752601090
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119151449151449419430425600824441600x7f022af09a800x7f022a6249401304096120071315527437655369596985716301116301115845393.014236919.025197.0536579.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06540.02031346.00.02097152.0975175277.02355118236.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012124156.016219753136159162275741165621622757420968316219753509510
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221514491514494194304256001224453760x7f022af099000x7f022a6249801311072120574815553796655369485784116388316388315911043.014180696.024656.0647722.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06528.02039994.00.02097152.0913820381.02186871184.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012135155.016219754044578162275742343231622757432856316219754438870
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251514491514494194304256001224463360x7f022af097800x7f022a6249c01298696119743115492579655369474040416233616233615802701.014283324.024505.0696834.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06577.02039878.00.02097152.0949445577.02270478807.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012129176.016219754982268162275743612031622757445496416219755357780
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281514491514494194304256001224475520x7f022af096000x7f022a624a0024480482334370302287576553622448511730600530600530582999.028980189.00.0909024.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012848.08248474.00.08388608.0860180550.03834278799.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020652987.016219755893918162275744815241622757466024516219756350208
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311514491514494194304256001224485120x7f022d5aa4800x7f022a624a4024329602326981301319286553621546908930411930411930486825.028939745.00.0872080.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012645.08250828.00.08388608.0838707203.03955193369.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020312206.016219756885186162275746861651622757486520616219757342356
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134151449151449419430425600824494720x7f022d5aa3000x7f022a624a801286848118357715300193655369386142016085516085515622755.014149041.024779.0622851.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06553.02029900.00.02097152.0958692124.02149141255.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012162566.016219757878014162275748900061622757498216716219758256776
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371514491514494194304256001224506880x7f022d5aa1800x7f022a624ac01295024118984915355502655369825359716187716187715704369.014126873.024557.0310527.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06558.02038901.00.02097152.0880149001.02076149406.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011947699.016219758792574162275750096871622757510296816219759162436
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401514491514494194304256001224516480x7f022d5aa0000x7f022a624b001286720118273815290160655369008220416083916083915611835.014142719.023678.0833033.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06573.02040365.00.02097152.0965794496.02324855464.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012057246.016219759705544162275751375281622757522952816219760111875
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431514491514494194304256001224528640x7f022af09e800x7f022a624b4024244402320895300754166553622333753530305430305430407915.028851208.00.0799050.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012826.08248641.00.08388608.0862331490.03789100824.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020231972.016219760647623162275752559291622757543385016219761110702
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461514491514494194304256001224540800x7f022af09d000x7f022a624b8024344002323534300858066553620917983230429930429930442209.028879337.00.0867859.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012690.08250459.00.08388608.0859808284.03778500683.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020240943.016219761645701162275754596101622757563833116219762099820
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149151449151449419430425600824552960x7f022af09b800x7f022a624bc01297288119276115404671655368534669116216016216015742147.014154608.025105.0461337.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06546.02029877.00.02097152.0971222586.02238987538.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012112097.016219762634809162275756634511622757575737116219763013200
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521514491514494194304256001224567680x7f022af09a000x7f022a624c001307696120266415510892655369932767816346116346115870795.014184483.023832.0203416.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06632.02056712.00.02097152.0747123847.01918330928.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011960418.016219763548309162275757839321622757587913216219763919430
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551514491514494194304256001224577280x7f022af098800x7f022a624c401296296118918615366738655368177232016203616203615695503.014139377.024724.0627761.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06563.02040150.00.02097152.0958762749.02235061754.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012005722.016219764462938162275759112921622757600601316219764838770
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581514491514494194304256001224589440x7f022af097000x7f022a624c8024096482308209299073986553622038913530120530120530242815.028759086.00.0726652.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012645.08250976.00.08388608.0861539121.03917854615.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020374341.016219765374098162275760316131622757621129416219765840328
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611514491514494194304256001224601600x7f022d5aa5800x7f022a624cc024081682304648298400406553621391200130102030102030196613.028543447.00.0729950.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012525.08252227.00.08388608.0863511517.03847176018.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020263919.016219766376676162275762370541622757641737516219766845406
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164151449151449419430425600824613760x7f022d5aa4000x7f022a624d001307152119562315409126655369045094216339316339315779483.014143889.023989.0613524.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06556.02029114.00.02097152.0960514284.02235439976.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012069092.016219767381584162275764418551622757653673616219767746016
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671514491514494194304256001224628480x7f022d5aa2800x7f022a624d4013531281250748161205776553610518398116914016914016495991.014534404.023336.0137863.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06595.02039153.00.02097152.0618563159.01616404296.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012077538.016219768280874162275765636161622757666313716219768653606
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701514491514494194304256001224638080x7f022d5aa1000x7f022a624d801298696119593015454670655369788220016233616233615783279.014214457.023675.0783833.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06558.02039835.00.02097152.0925940726.02171519463.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011979198.016219769195864162275766960971622757678921716219769610035
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731514491514494194304256001224650240x7f022af09f800x7f022a624dc024178802314150299585456553622154596530223430223430320217.028778389.00.0673379.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012695.08250280.00.08388608.0858986522.03848639526.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020399392.016219770146443162275768178571622757699609816219770624152
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761514491514494194304256001224662400x7f022af09e000x7f022a624e0024266162319778300491196553621438923630332630332630393251.028924482.00.0807506.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012600.08251338.00.08388608.0858337177.03949592840.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020201435.016219771158890162275770216991622757720314016219771625190
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179151449151449419430425600824674560x7f022af09c800x7f022a624e401303272119432315401440655369224467516290816290815762245.014129232.024883.0473910.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06568.02028511.00.02097152.0931089039.02228193978.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012075551.016219772160788162275772279401622757732266016219772539380
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821514491514494194304256001224689280x7f022af09b000x7f022a624e8014121041305934168283546553610623542717651217651217213383.014801046.022256.025242.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06592.02038049.00.02097152.0551601396.01440944113.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012439709.016219773074328162275773469811622757745098116219773458739
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851514491514494194304256001224701440x7f022af099800x7f022a624ec01299296119324115414346655369003304016241116241115748231.014175165.025042.0556509.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06588.02039320.00.02097152.0972212096.02262054696.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011952722.016219774001647162275774839411622757757658216219774385959
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881514491514494194304256001224716160x7f022af098000x7f022a624f0024263282321039300613026553622325161830329030329030409709.028781812.00.0860217.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012893.08248498.00.08388608.0865044281.03702500514.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020371320.016219774921447162275776036221622757778458316219775376577
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911514491514494194304256001224728320x7f022af096800x7f022a624f4024098562301491298128196553621398566530123130123130155429.028587607.00.0727672.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012770.08249594.00.08388608.0853820426.03857684297.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020331146.016219775912055162275778113031622757799210416219776374425
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194151449151449419430425600824740480x7f022d5aa5000x7f022a624f801291784118427115272426655369080926116147216147215631621.014109839.025203.0562857.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06581.02054437.00.02097152.0882331580.02228907050.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012018981.016219776909213162275780175441622757811146516219777272215
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971514491514494194304256001224757760x7f022d5aa3800x7f022a624fc014682561356085174703146553610663066018353118353117865307.015211524.021000.031741.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06627.02038740.00.02097152.0453914947.01232673301.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012612789.016219777807793162275781369051622757824410616219778190725
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001514491514494194304256001224769920x7f022d5aa2000x7f022a6250001300600118846615346128655368815458916257416257415686169.014103254.024296.0771340.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06603.02039724.00.02097152.0921400274.02175937398.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011930099.016219778744933162275782761061622757837034616219779225442
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031514491514494194304256001224784640x7f022d5aa0800x7f022a62504023901922287023296079086553621404304929877329877329967657.028341357.00.0595137.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012828.08249268.00.08388608.0857372074.03940281788.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020004403.016219779759260162275783954671622757857466816219780303538
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061514491514494194304256001224799360x7f022af09f000x7f022a62508024150482311865299081156553621931193930188030188030290421.028682376.00.0704809.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012604.08251349.00.08388608.0860055341.03886937349.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020053039.016219780838286162275785997881622757877978916219781366535
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209151449151449419430425600824814080x7f022af09d800x7f022a6250c01307144120227315481136655369615406316339216339215865621.014205129.023404.0859588.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06554.02039305.00.02097152.0894786817.02088151272.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011988116.016219781898993162275788055491622757890058916219782376542
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121514491514494194304256001224831360x7f022af09c000x7f022a62510015301201425532183820186553612499756419126419126418768105.015066495.020602.012787.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06605.02040657.00.02097152.0405847945.01086293038.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012374115.016219782912040162275789263501622757904187016219783322941
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151514491514494194304256001224843520x7f022af09a800x7f022a6251401289264118654215336373655368878087916115716115715661261.014051505.024897.0596696.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06573.02040575.00.02097152.0903089125.02117114075.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011966132.016219783864579162275790892301622757918347116219784230881
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181514491514494194304256001224858240x7f022af099000x7f022a62518024201362319058300358806553622207623530251630251630383917.028735757.00.0675692.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012862.08248861.00.08388608.0857197498.03725512611.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020252958.016219784766479162275792092311622757938875216219785217529
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211514491514494194304256001224872960x7f022af097800x7f022a6251c024204162314504299497696553621916731030255130255130324793.028690256.00.0756125.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012786.08249494.00.08388608.0852356339.03864633940.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020182737.016219785752327162275794148321622757959307316219786244866
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241514491514494194304256001224887680x7f022af096000x7f022a6252001311960120514815544083655369399386016399416399415903009.014190021.024195.0573527.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06591.02038116.00.02097152.0900279295.02099581988.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011913336.016219786780595162275796194741622757971403416219787177456
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271514491514494194304256001224907520x7f022d5aa4800x7f022a62524016202881505610193718706553613047273620253520253519809275.015677290.019926.03036.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06605.02041353.00.02097152.0406093592.01066208965.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012722717.016219787713134162275797399541622757986059516219788121305
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301514491514494194304256001224919680x7f022d5aa3000x7f022a6252801296104119092215373326655369048823516201216201215718045.014102390.024187.0701320.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06533.02040284.00.02097152.0930763493.02195117432.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011988426.016219788662633162275798935551622757998779616219789115013
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331514491514494194304256001224934400x7f022d5aa1800x7f022a6252c024233682317145300160766553622235156230292030292030359191.028643546.00.01153339.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012767.08250074.00.08388608.0852424396.03963589340.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020169334.016219789650412162275800122761622758019259716219790189910
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361514491514494194304256001224949120x7f022d5aa0000x7f022a62530024125362302099298203906553621557975230156630156630163541.028600348.00.0815167.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012686.08250283.00.08388608.0852741481.03903009546.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020098939.016219790726108162275802178771622758039947816219791202937
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391514491514494194304256001224963840x7f022af09e800x7f022a6253401307160119607315405106655369531907316339416339415785125.014099371.024327.0548725.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06556.02039410.00.02097152.0874046192.02054254792.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012025575.016219791737615162275804244381622758051995916219792104177
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421514491514494194304256001224983680x7f022af09d000x7f022a62538016851281579919203669436553613406881121064021064020775253.016052343.019505.01533.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06638.02040941.00.02097152.0341220755.0961141474.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012783405.016219792637535162275805461991622758067228016219793127374
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451514491514494194304256001224995840x7f022af09b800x7f022a6253c01294240119139115371231655368661319016177916177915724103.014102579.024725.0593318.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06553.02040741.00.02097152.0914268468.02295688039.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011961263.016219793670632162275807042801622758079852016219794066974
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024815144915144941943042560012241013120x7f022af09a000x7f022a62540023875922280836295444416553621526699129844829844829886979.028375499.00.0774008.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012623.08250921.00.08388608.0846767258.03985418536.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019892485.016219794602162162275808242801622758100444116219795151530
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025115144915144941943042560012241027840x7f022af098800x7f022a62544023802482274563294666356553620795404329753029753029805651.028234637.00.01079919.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012899.08248124.00.08388608.0836221181.03907628955.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020032883.016219795687228162275810302021622758121148316219796160748
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025415144915144941943042560012241042560x7f022af097000x7f022a6254801296880119275315383880655369898688416210916210915741913.014131820.024695.0320199.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06580.02038676.00.02097152.0846276884.02032979124.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012005310.016219796694716162275812343631622758132844316219797064578
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025715144915144941943042560012241062400x7f022d5aa5800x7f022a6254c017534961641233211864716553613851307421918621918621572205.016206550.019310.0863.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06650.02040920.00.02097152.0330571494.0956523667.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012964537.016219797598056162275813524431622758148284416219798086345
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026015144915144941943042560012241077120x7f022d5aa4000x7f022a6255001281848117839415215963655368898692116023016023015555207.014037554.024111.0587058.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06581.02039152.00.02097152.0928400600.02230697208.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011878655.016219798629133162275815154841622758160892516219799078403
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026315144915144941943042560016241094400x7f022d5aa2800x7f022a62554024082882300604297750426553621630043730103530103530144171.028522451.00.0958174.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012746.08249584.00.08388608.0842417997.03922977125.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019824251.016219799613331162275816362851622758181660616219800151739
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026615144915144941943042560016241111680x7f022d5aa1000x7f022a62558023831682276718294868876553620630808029789529789529833627.028262562.00.01003021.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012661.08250524.00.08388608.0841571821.03871572306.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019850784.016219800687178162275818420461622758202060716219801171247
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691514491514494194304256008241128960x7f022af09f800x7f022a6255c012958161192617153764346553610373523016197616197615740171.013985348.024461.0181166.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06618.02056129.00.02097152.0799613757.01974236783.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011970622.016219801707835162275820447671622758213964816219802090606
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027215144915144941943042560012241151360x7f022af09e000x7f022a62560018414641728722223227726553614097462923018223018222709757.016109697.019429.01095.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06635.02041038.00.02097152.0296456265.0885327925.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012497550.016219802619585162275821642881622758230396916219803122584
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027515144915144941943042560012241166080x7f022af09c800x7f022a6256401302904118637515304407655369217140816286216286215659077.014048515.024869.0516583.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06529.02042365.00.02097152.0915956710.02232559636.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011889613.016219803664042162275823362891622758243021016219804108922
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027815144915144941943042560016241183360x7f022af09b000x7f022a62568023960482288713296153606553621497612429950529950529989601.028361454.00.0740978.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012646.08250707.00.08388608.0842002963.03883247178.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019853018.016219804642200162275824540501622758263341116219805176288
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028115144915144941943042560016241200640x7f022af099800x7f022a6256c023785682271501294344216553620621248429732029732029765689.028184698.00.0779860.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012792.08249394.00.08388608.0841013645.03867741619.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019867880.016219805712836162275826577311622758283805216219806164106
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028415144915144941943042560012241217920x7f022af098000x7f022a62570013117601208346156100756553610203360016396916396915944713.014296360.024149.0205012.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06584.02059916.00.02097152.0690270346.01851929382.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012134233.016219806699664162275828623721622758295949316219807099396
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028715144915144941943042560012241240320x7f022af096800x7f022a62574019246161811263234103066553614965823024057624057623782673.016110181.019562.01735.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06648.02041011.00.02097152.0286590133.0866632224.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012744783.016219807632844162275829865331622758313149416219808145423
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029015144915144941943042560012241255040x7f022d5aa5000x7f022a6257801294096118439815260579655369451624116176116176115633415.013943258.024205.0532879.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06577.02038600.00.02097152.0892287951.02163436623.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011854066.016219808688471162275831647741622758325965416219809083542
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029315144915144941943042560012241274880x7f022d5aa3800x7f022a6257c023817122275981294635586553620543417029771329771329824007.028229141.00.0752891.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012694.08250365.00.08388608.0828221905.03967057109.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019730091.016219809618320162275832849351622758346573616219810159288
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029615144915144941943042560012241292160x7f022d5aa2000x7f022a62580023856562274566294473096553620769118629820629820629805547.028211537.00.0754133.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012798.08248927.00.08388608.0833783454.03908117120.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019784758.016219810695216162275834910161622758367181716219811176386
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029915144915144941943042560012241309440x7f022d5aa0800x7f022a62584013763681268074163682946553610168557117204517204516721229.014923259.022510.0121672.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06611.02039055.00.02097152.0617334945.01614362380.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012668077.016219811712494162275836980571622758379773816219812091165
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030215144915144941943042560012241334400x7f022af09f000x7f022a62588020727521960284253372876553617065125725909325909325719725.016039375.020430.0848.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06663.02039779.00.02097152.0285592163.0861971418.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012164681.016219812626513162275838236581622758397901916219813145352
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030515144915144941943042560012241349120x7f022af09d800x7f022a6258c01302016118863215302770655369861303116275116275115688405.014020635.023920.0302483.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06579.02039559.00.02097152.0825563204.02032120735.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011849932.016219813688270162275840114991622758410637916219814124130
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030815144915144941943042560012241368960x7f022af09c000x7f022a62590023619682254982291594156553621032495929524529524529550851.027909635.00.0731219.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012520.08252057.00.08388608.0834581061.03880645666.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019562519.016219814625239162275841319791622758431134016219815192497
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031115144915144941943042560012241388800x7f022af09a800x7f022a62594023741202271593294031716553621486288229676429676429767041.028085929.00.0881623.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012744.08249579.00.08388608.0833190342.03941580227.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019648762.016219815728155162275843379011622758451886216219816210644
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031415144915144941943042560012241408640x7f022af099000x7f022a62598014292721323293170736256553611539542817865817865817438985.015502393.020388.086383.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06593.02038801.00.02097152.0500920151.01306042559.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.013165532.016219816745662162275845436621622758464958216219817132694
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031715144915144941943042560012241436160x7f022af097800x7f022a6259c022384802131260275735266553619890039827980927980927942439.015928520.019826.0540.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06658.02039571.00.02097152.0278987645.0848934530.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012199316.016219817668552162275846758231622758484606416219818117382
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032015144915144941943042560012241453440x7f022af096000x7f022a625a001296712118611215307081655369978558816208816208815655619.014008832.024358.0129949.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06602.02040512.00.02097152.0702582409.01893385961.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011840023.016219818659700162275848798241622758497518416219819116070
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032315144915144941943042560012241475840x7f022d5aa4800x7f022a625a4023699442266390293022756553620981189829624229624229699285.027905071.00.0629919.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012553.08251338.00.08388608.0822273036.03861566467.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019532204.016219819651268162275850019041622758518270516219820199896
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032615144915144941943042560012241495680x7f022d5aa3000x7f022a625a8023765202267169293301506553621256623929706429706429709347.028034635.00.0596830.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012895.08247930.00.08388608.0830030512.03827283834.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019420499.016219820735524162275852075061622758539038716219821211924
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032915144915144941943042560012241515520x7f022d5aa1800x7f022a625ac015139201399868180428296553611088160718923918923918434551.016498181.016214.040740.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06608.02039842.00.02097152.0382265530.01074569572.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.014026935.016219821746942162275854167871622758552654716219822171882
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033215144915144941943042560012241543040x7f022d5aa0000x7f022a625b0023988802289132296121266553621197424029985929985929994645.016041525.020507.01699.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06675.02039795.00.02097152.0281864938.0843075827.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012341998.016219822707971162275855515081622758573278916219823263198
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033515144915144941943042560012241562880x7f022af09e800x7f022a625b4013763521272081163921426553610296770717204317204316773307.014818207.021820.062082.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06600.02038354.00.02097152.0565025646.01495169250.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012494518.016219823806306162275857649491622758586590916219824206697
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033815144915144941943042560012241587840x7f022af09d000x7f022a625b8023736242255282291359836553617939873929670229670229554803.027826065.00.0477487.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012058.08257000.00.08388608.0822707405.03895083721.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019470343.016219824741666162275858911901622758607567116219825199525
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034115144915144941943042560012241610240x7f022af09b800x7f022a625bc023828482259173291747276553618230900929785529785529605451.027847377.00.0725119.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012342.08253820.00.08388608.0802974972.03975344206.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019479280.016219825734663162275861076711622758628991216219826203133
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034415144915144941943042560012241632640x7f022af09a000x7f022a625c0016536481535786198037716553612787893320670520670520201407.018082545.016394.0771.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06621.02038368.00.02097152.0374130242.01087739349.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.015691401.016219826738251162275863147121622758643663316219827174272
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034715144915144941943042560012241665280x7f022af098800x7f022a625c4027235842610224337498656553624153936834044734044734169101.016125139.020466.0470.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06721.02040646.00.02097152.0281576314.0839809061.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012599226.016219827708730162275864631931622758666975416219828225628
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035015144915144941943042560012241685120x7f022af097000x7f022a625c8014790321370606176690906553611048905018487818487818054041.015824405.019579.020626.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06611.02036975.00.02097152.0381221320.01049199941.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.013304598.016219828730877162275867179141622758682927516219829125818
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035315144915144941943042560012241712640x7f022d5aa5800x7f022a625cc023780722256557291227306553618709758429725829725829571469.027708084.00.0745182.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012289.08254448.00.08388608.0815020417.03782217130.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019157106.016219829661336162275868553551622758703807616219830119846
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035615144915144941943042560012241737600x7f022d5aa4000x7f022a625d0023808322262208292013256553618721333629760329760329644815.027774643.00.0699148.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012185.08255452.00.08388608.0808884780.03888404480.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019251290.016219830655544162275870625561622758724735716219831121024
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035915144915144941943042560012241762560x7f022d5aa2800x7f022a625d4018033121691637218318086553614974375422541322541322227587.019592942.016033.02073.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0312.02097152.06626.02031494.00.02097152.0273281337.0855795257.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.016243998.016219831656082162275872737571622758740783816219832066033
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036215144915144941943042560012241797760x7f022d5aa1000x7f022a625d8030392802929589379035736553627730962337990937990938320781.016234358.019715.02267.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06704.02040269.00.02097152.0275834307.0833101307.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012617186.016219832600412162275874347181622758766704016219833162139
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036515144915144941943042560012241822720x7f022af09f800x7f022a625dc016927121584018204595286553613919859821158821158820828501.017993573.017964.01280.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0208.02097152.06649.02050388.00.02097152.0305586407.0909552176.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.014773197.016219833663078162275877144001622758784096116219834070029
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036815144915144941943042560012241855360x7f022af09e000x7f022a625e0024753842350344302674926553618578270530942230942230790739.028088658.00.0274320.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0208.08388608.012530.08251296.00.08388608.0671589942.03282607082.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019429239.016219834605407162275878667211622758805616216219835162345
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037115144915144941943042560012241885440x7f022af09c800x7f022a625e4024923042350468302480536553618509367131153731153730792143.028574087.00.0342407.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0208.08388608.012598.08250588.00.08388608.0635100783.03169307743.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019975147.016219835697263162275880822421622758827408316219836269311
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037415144915144941943042560012241915520x7f022af09b000x7f022a625e8021287922018073260771066553618163735126609826609826471125.020592292.019540.02304.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0208.02097152.06629.02026502.00.02097152.0273723171.0832191068.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.016462443.016219836734560162275882992031622758845936416219837169531
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037715144915144941943042560012241958400x7f022af099800x7f022a625ec036961523582117463566676553633995266946201846201846803775.016991707.019800.01465.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0208.02097152.06699.02040297.00.02097152.0273970859.0830440245.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.013239934.016219837704159162275884854441622758876912616219838337515
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038015144915144941943042560012241985920x7f022af098000x7f022a625f0019541681840290237829156553616326160924427024427024159985.021957269.013589.02136.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0208.02097152.06626.02046877.00.02097152.0264938725.0840726964.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.019458012.016219838816524162275888155261622758896512716219839254785
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038315144915144941943042560012242023680x7f022af096800x7f022a625f4026717122553256329070686553620657504033396333396333428673.028880019.00.0134000.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0312.08388608.012733.08248873.00.08388608.0593852460.02988233438.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019835324.016219839788803162275889905671622758919840816219840334861
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038615144915144941943042560012242058880x7f022d5aa5000x7f022a625f8026727762537300327257256553620841480333409633409633221063.030691318.00.0111520.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012871.08247362.00.08388608.0514751356.02762116087.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.021745286.016219840806520162275892398491622758944849016219841362378
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038915144915144941943042560012242094080x7f022d5aa3800x7f022a625fc024625442344819302905616553621655993230781730781730718771.021464175.018577.07595.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0208.02097152.06636.02026842.00.02097152.0273519955.0831291496.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.016517203.016219841835118162275894852901622758967073116219842328707
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039215144915144941943042560012242144640x7f022d5aa2000x7f022a62600043410564227350547377266553641136856854263154263155191713.017325839.019954.0965.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0208.02097152.06721.02040411.00.02097152.0279573371.0834417420.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.013271479.016219842863065162275896969711622759003185316219843574429
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039515144915144941943042560012242177280x7f022d5aa0800x7f022a62604021773202066737267449626553619463587927216427216427103679.019491514.016862.02470.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06622.02048254.00.02097152.0271022605.0837825037.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.015361401.016219844056199162275900750541622759024353416219844499989
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039815144915144941943042560012242220160x7f022af09f000x7f022a62608029420162816991362396606553623756062436775136775136857241.029757768.00.075208.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0208.08388608.012864.08247366.00.08388608.0492402124.02529841229.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020303382.016219845034847162275902700951622759049793616219845611034
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040115144915144941943042560012242260480x7f022af09d800x7f022a6260c030230002899454373755706553625463431037787437787437928987.033227352.00.094951.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012875.08247287.00.08388608.0446390129.02339605746.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.024390657.016219846091663162275905324961622759076177716219846519594
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040415144915144941943042560012242300800x7f022af09c000x7f022a62610029439202782004358162216553618887010636798936798936402215.021227256.020706.027809.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0208.02097152.06642.02026415.00.02097152.0269400773.0821764953.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.017133462.016219847064632162275907993781622759101073916219847531032
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040715144915144941943042560012242359040x7f022af09a800x7f022a62614051332724973821640850206553639360029064165864165864896031.019888208.017894.09856.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0208.02097152.06713.02040557.00.02097152.0283969437.0839500578.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.013372715.016219848065850162275910483391622759143362116219848809193
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041015144915144941943042560012242394240x7f022af099000x7f022a62618025138482379428307387556553620853000931423031423031168675.021269464.015620.01068.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0208.02097152.06631.02046603.00.02097152.0271776895.0833512025.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.016267379.016219849258653162275914758621622759166290316219849691634
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041315144915144941943042560012242442240x7f022af097800x7f022a6261c032390083101777400004296553627012712540487540487540559407.030817688.00.022819.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012882.08247088.00.08388608.0443804390.02276081643.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.021197808.016219850228162162275916885031622759193970416219850716251
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041615144915144941943042560012242487680x7f022af096000x7f022a62620032142163070848396698346553626723892240177640177640157421.034976550.00.030118.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.013179.08243652.00.08388608.0286997515.01736664034.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.023798994.016219851254819162275919741041622759222098616219851735139
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041915144915144941943042560012242533120x7f022d5aa4800x7f022a62624031023362988478386451896553628397288138779138779139086325.022090625.017605.02707.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06642.02027237.00.02097152.0275270907.0826129812.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.016982263.016219852270857162275922590661622759249586716219852904593
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221514491514494194304256008242555520x7f022d5aa3000x7f022a62628057494645634927729240966553654821775871868271868273490227.068537275.0857.00.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.07030.02065643.00.02097152.0228670470.0794441573.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.063300950.016219853374762162275925301081622759298355016219854239883
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042515144915144941943042560012242598400x7f022d5aa1800x7f022a6262c030149202875025370144476553622587206037686437686437611605.024095224.014030.011274.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06645.02045051.00.02097152.0266189850.0822562785.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.018220229.016219854688083162275930262701622759325187216219855151813
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042815144915144941943042560012242656640x7f022d5aa0000x7f022a62630038780243742871482871386553631842070248475248475248894513.035826624.00.01115.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.013078.08244761.00.08388608.0289332855.01691499382.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.021770169.016219855688341162275932891521622759358771416219856289678
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043115144915144941943042560012242712320x7f022af09e800x7f022a62634039349363795964489513976553630996486249186649186649583721.030845155.00.00.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.013005.08245594.00.08388608.0339998104.01944398579.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020975187.016219856761288162275936251541622759392403616219857380174
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341514491514494194304256008242732160x7f022af09d000x7f022a62638040062883890703503306676553636778265450078550078550815419.047091396.01628.00.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0208.02097152.07610.02063898.00.02097152.0232173547.0798636548.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.044379083.016219857829694162275939645161622759426115816219858442720
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371514491514494194304256008242757120x7f022af09b800x7f022a6263c072050487087577917690226553669692455290063090063092374807.076360550.0924.00.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0208.02097152.06805.02064295.00.02097152.0231254245.0798457139.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.068051101.016219858893110162275943014781622759486052116219859776411
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044015144915144941943042560012242807680x7f022af09a000x7f022a62640035234003381613436422806553628009842144042444042444198107.027545754.015788.0903.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0208.02097152.06646.02028468.00.02097152.0255703461.0808191674.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.022261989.016219860235120162275949312411622759519508316219860784428
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044315144915144941943042560012242876160x7f022af098800x7f022a62644045412564428970572991266553641801250256765656765657813007.030059845.00.00.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0208.08388608.012997.08245698.00.08388608.0297335799.01731071241.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020958792.016219861259388162275952578031622759560820516219861884104
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044615144915144941943042560012242942080x7f022af097000x7f022a62648044111364304921557093696553641270072655139155139156200227.034972209.00.00.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0208.08388608.012952.08246248.00.08388608.0327839873.01889998441.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.023245274.016219862383463162275956813261622759603124816219863129007
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491514491514494194304256008242969600x7f022d5aa5800x7f022a6264c045176164393986568506266553641934177756470156470157357929.055054737.01120.00.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0208.02097152.07533.02064255.00.02097152.0231198422.0800210974.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.051823166.016219863622516162275960933281622759644053016219864315610
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521514491514494194304256008242999680x7f022d5aa4000x7f022a626500834208882238281064946056553681435117910427601042760107145927.082434498.0850.00.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0208.02097152.06821.02063450.00.02097152.0230498603.0799820451.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.073686879.016219864805270162275964808501622759714325416219865809648
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551514491514494194304256008243027200x7f022d5aa2800x7f022a62654057751845657731732614726553654196716372189772189773786523.068226236.0916.00.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0208.02097152.07418.02063945.00.02097152.0231236438.0801511684.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.062609866.016219866289497162275971910941622759763845716219867086909
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045815144915144941943042560012243054720x7f022d5aa1000x7f022a62658057926485671703734411136553655193882672408072408073968081.068731664.00.00.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0208.08388608.013119.08244299.00.08388608.0234039716.01574827706.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.057752338.016219867557129162275976770171622759814166016219868367811
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046115144915144941943042560012243082240x7f022af09f800x7f022a6265c057756965663164732988966553654998244772196172196173857165.068901581.00.00.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.013095.08244563.00.08388608.0235975217.01585751903.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.057750376.016219868838680162275982085401622759866934316219869647282
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641514491514494194304256008243109760x7f022af09e000x7f022a62660058164405701944737975396553655810343872705472705474361383.068630119.0907.00.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0208.02097152.07539.02063485.00.02097152.0231071865.0800648334.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.063097051.016219870118932162275987082231622759916022616219870961583
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671514491514494194304256008243132160x7f022af09c800x7f022a626640109367761081747014018331265536107486760513670961367096140863429.095503701.0932.00.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06814.02064736.00.02097152.0234245316.0808126574.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.082989187.016219871432983162275992245461622760009335116219872660276
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701514491514494194304256008243159680x7f022af09b000x7f022a626680109656881084627214055898665536108402922513707101370710141237673.091480724.0975.00.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.07421.02063269.00.02097152.0236928084.0817722907.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.081212259.016219873133176162276001666311622760102119616219874338549
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047315144915144941943042560012243187200x7f022af099800x7f022a6266c0109733041085588614069739565536107983962713716621371662141362707.095168903.00.00.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.013274.08242594.00.08388608.0234291149.01575991244.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.078402344.016219874808629162276010867971622760197112216219876033002
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047615144915144941943042560012243214720x7f022af098000x7f022a626700109764801084848514059711065536108042754413720591372059141266533.096014378.00.00.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.013220.08243188.00.08388608.0235545859.01581107717.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.078393460.016219876504451162276020101621622760289080716219877723334
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791514491514494194304256008243242240x7f022af096800x7f022a626740109973521088795014105682665536108654273513746681374668141779487.093748346.0847.00.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.07526.02063175.00.02097152.0236828553.0816738942.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.081376342.016219878196694162276029548071622760381497216219879401607
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821514491514494194304256008243264640x7f022d5aa5000x7f022a626780213250562118468927456346065536212440140726656312665631275637055.0111219877.0578.00.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06777.02064990.00.02097152.0240153833.0828982023.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.093342953.016219879870956162276038776931622760557722216219881921821
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851514491514494194304256008243292160x7f022d5aa3800x7f022a6267c0213457522122552027511335365536212939541426682182668218276167845.0127697277.0631.00.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.07878.02061871.00.02097152.0238795484.0833342642.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.0110759528.016219882395461162276056761031622760734107316219884406846
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048815144915144941943042560012243319680x7f022d5aa2000x7f022a626800213842722124142427522199965536212713289126730332673033276374701.0131113682.00.00.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.013270.08242638.00.08388608.0234503902.01594138317.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.0109026919.016219884879746162276074293931622760915420316219886961880
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049115144915144941943042560012243347200x7f022d5aa0800x7f022a626840213456322123363027514020665536211967641226682032668203276273353.0136020978.00.00.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.013215.08243243.00.08388608.0235332429.01600140738.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.0111360128.016219887429640162276092516441622761096861316219889490044
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941514491514494194304256008243374720x7f022af09f000x7f022a626880213927362126629827564211765536213617259026740912674091276698089.0126882908.0593.00.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.07880.02061927.00.02097152.0239117756.0834344180.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.0108076478.016219889959233162276110658941622761274014416219892013528
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049715144915144941943042560082400x7f022af09d800x7f022a6268c0420460644192578754340145165536422539659352557575255757545271329.0110224321.0509.00.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06751.02065864.00.02097152.0241277972.0837879749.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.098808014.016219892473018162276128281441622761618576316219896186936