Files
rocm-systems/tests/workloads/no_roof_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.kd000152567152567335544322560043241600x00x7f7117c04280304336829556303840036552428823847796938042038042038664982.037830227.011.04089548.00.00.00.0524288.033554432.033554432.00.033554432.00.00.0104.08388608.013312.08242176.00.08388608.0314404782.00.01469333319.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.019094396.016255303836302162632726279791626327286510116255451542868
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00215256715256732768256001224138880x00x7f7117c23f802089681113561076857512130572626120261201683791.0192332.0180.00.00.00.00.04096.065536.065536.065536.00.00.00.0104.016384.0104.015240.00.016384.07508346.08929386.00.08192.00.00.00.00.00.00.00.00.00.00.00.00.08192.00.00.094902.016255457325460162632778883321626327789617216255457561965
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051525671525674194304256001224143360x7f713e3883800x7f7117c23fc01363064123615815988066655368727003817038217038216306243.014590160.024287.0807059.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0208.02097152.06820.02025717.00.02097152.0991611334.02296375566.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011623527.016255458107063162632779678531626327806033316255458436986
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081525671525674194304256001624150400x7f713e3882000x7f7117c2400024779602373950307299116553622658924730974430974431097539.029868130.00.01089111.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012997.08246529.00.08388608.0881353585.03772935906.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020746150.016255458980164162632781088141626327828929516255459559411
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111525671525674194304256001624154880x7f713e3880800x7f7117c2404025236402391060309634246553622949557631545431545431320021.030067789.00.0920217.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012950.08246849.00.08388608.0859158811.03902746807.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020801879.016255460094889162632783164951626327849729616255460515060
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141525671525674194304256001224159360x7f713c149f000x7f7117c240801326928122509315833666655369978044916586516586516162411.014968225.023381.01019483.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06647.02027510.00.02097152.01033272702.02219541221.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012323012.016255461051998162632785227361626327861537716255461489429
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171525671525674194304256001224163840x7f713c149d800x7f7117c240c01318696121493815703890655369178442416483616483616030357.014877356.022417.01487286.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0208.02097152.06733.02026987.00.02097152.01007611968.02267418905.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011710975.016255462024637162632786420971626327873361816255462497646
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201525671525674194304256001224170880x7f713c149c000x7f7117c2410013805681262082163358046553611114053717257017257016643255.014222276.024768.0473106.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06650.02029077.00.02097152.01030975795.02352429265.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011665263.016255463047054162632787774581626327886913816255463376967
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231525671525674194304256001624177920x7f713c149a800x7f7117c2414024808082377420308047216553623249577731010031010031142571.029928769.00.0823150.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0208.08388608.012945.08247224.00.08388608.0871615518.03718009728.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.021035836.016255463914005162632788969791626327907682016255464452703
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261525671525674194304256001624184960x7f713c1499000x7f7117c2418025098802385476308945716553622657374331373431373431247325.030007207.00.0952258.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012454.08252439.00.08388608.0872102066.03958396847.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020247728.016255464986591162632791089801626327928882116255465390992
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291525671525674194304256001624192000x7f713c1497800x7f7117c241c013128961207992156338066553610137715716411116411115940098.014709143.024884.0714406.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06650.02059917.00.02097152.01009044555.02248538592.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011586643.016255465928150162632793219411626327941410216255466332611
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321525671525674194304256001624199040x7f713c1496000x7f7117c2420013137521210031156591936553610369021316421816421815966683.014789204.022939.01255611.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06469.02057333.00.02097152.01014725345.02283944742.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012279931.016255466867629162632794533021626327954530316255467326319
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351525671525674194304256001224206080x7f713e3884800x7f7117c2424013597841238327160326976553611579582116997216997216334453.014939583.021948.01257939.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06645.02030206.00.02097152.01034110817.02191531514.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012175219.016255467869427162632795793831626327967090416255468192690
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381525671525674194304256001624213120x7f713e3883000x7f7117c2428024743282365972306608666553623129581830929030929030993955.029788585.00.0820773.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0208.08388608.012948.08247119.00.08388608.0859467216.03869757729.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020691554.016255468730209162632797070641626327988818516255469225338
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411525671525674194304256001624220160x7f713e3881800x7f7117c242c024480402346470304056436553622114977330600430600430740325.029526269.00.01021976.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0208.08388608.012447.08252458.00.08388608.0875087505.03938750552.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020796877.016255469762176162632799283451626328010706616255470242165
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441525671525674194304256001624227200x7f713e3880000x7f7117c2430013166081212994156871256553610615603116457516457516005033.014796790.022978.01178876.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0208.02097152.06645.02059182.00.02097152.01040110475.02224834090.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011743162.016255470780333162632801357071626328022802716255471175305
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471525671525674194304256001224234240x7f713c149e800x7f7117c2434013203361211930156924626553611376775716504116504115991175.014803430.022199.01362601.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06640.02031344.00.02097152.01040765405.02209028144.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011633200.016255471710903162632802590671626328035074816255472110814
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501525671525674194304256001224241280x7f713c149d000x7f7117c2438013207521212514156966096553611104976916509316509315999027.014829177.022245.01444267.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0208.02097152.06605.02029915.00.02097152.01027477418.02330372762.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012176440.016255472654132162632803849881626328047666916255473063803
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531525671525674194304256001624248320x7f713c149b800x7f7117c243c024823522375252307692696553623174475831029331029331114361.029850518.00.0845283.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012854.08248206.00.08388608.0893875527.03657928321.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020670752.016255473599591162632805053091626328068563016255474092450
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561525671525674194304256001624255360x7f713c149a000x7f7117c2440024390002338017303004926553622040817130487430487430630163.029459030.00.0859713.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0208.08388608.012576.08251175.00.08388608.0877284230.03977014695.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020695046.016255474629308162632807350701626328091395216255475110747
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591525671525674194304256001224262400x7f713c1498800x7f7117c2444013194481217313157552676553610750575816493016493016061089.014843758.020874.01775573.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06647.02031240.00.02097152.01027033606.02270008447.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012245966.016255475646386162632809600321626328105251316255476030917
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621525671525674194304256001224269440x7f713c1497000x7f7117c2448013044721203300155646466553610756052616305816305815879063.014673297.024415.0818286.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06625.02030429.00.02097152.01017675973.02270134028.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012147736.016255476566985162632810809931626328117283316255476950237
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651525671525674194304256001224276480x7f713e3885800x7f7117c244c012963361194290154573446553610974211716204116204115762037.014636726.023788.0914789.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0208.02097152.06641.02032239.00.02097152.01028766683.02270603673.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012131650.016255477493595162632812069141626328129795416255477903806
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681525671525674194304256001624286080x7f713e3884000x7f7117c2450024684402360376305926606553622992312430855430855430921103.029702427.00.0617191.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012937.08247286.00.08388608.0884402468.03640006591.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020607047.016255478440794162632813229141626328150211516255478920663
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711525671525674194304256001624293120x7f713e3882800x7f7117c2454024503922345023304023616553622353800930629830629830721605.029521136.00.0948989.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012479.08252480.00.08388608.0869070947.03905828880.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020456316.016255479456652162632815277161626328170787716255479980540
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741525671525674194304256001224300160x7f713e3881000x7f7117c245801293808119104815428160655369924776416172516172515719969.014608417.025373.0759631.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06632.02029974.00.02097152.01011808472.02304396609.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012107981.016255480516548162632817320371626328182371716255480893470
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077152567152567419430425600824309760x7f713c149f800x7f7117c245c01302032120009615513321655369144702116275316275315837619.014695602.023274.01125094.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06626.02030563.00.02097152.01000535046.02229911639.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011933435.016255481429598162632818486781626328193987816255481816849
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801525671525674194304256001224316800x7f713c149e000x7f7117c2460013063121199360155268446553611111718016328816328815827869.014677331.023113.01055611.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06604.02030188.00.02097152.01002444947.02351198614.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012197473.016255482359907162632819721981626328206435916255482759448
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831525671525674194304256001624326400x7f713c149c800x7f7117c2464024582562353444304938306553622971294030728130728130830883.029709663.00.0822141.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0208.08388608.012825.08248703.00.08388608.0892801323.03642915055.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019929033.016255483295026162632820985991626328227796016255483769016
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861525671525674194304256001224336000x7f713c149b000x7f7117c2468024620082349680304414856553622382219930775030775030782081.029592227.00.0986849.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0208.08388608.012655.08250599.00.08388608.0866746445.04005125854.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020739248.016255484305674162632823032411626328248340216255484778534
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891525671525674194304256001224345600x7f713c1499800x7f7117c246c01299040119323515446699655369982778716237916237915748153.014552780.023695.01196009.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06634.02031069.00.02097152.01016392676.02333348009.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012161020.016255485313572162632825083621626328260084316255485703293
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092152567152567419430425600824355200x7f713c1498000x7f7117c2470013142001208968155991596553610024978416427416427415952851.014689208.023307.01111969.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06619.02030051.00.02097152.0982602351.02364534179.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012069877.016255486239891162632826248431626328271700316255486653922
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951525671525674194304256001224362240x7f713c1496800x7f7117c2474013050481203642155772606553610959599116313016313015883457.014692105.023739.01039919.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06625.02031325.00.02097152.01026811844.02207019372.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012089112.016255487197490162632827501231626328284244416255487585162
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981525671525674194304256001224371840x7f713e3885000x7f7117c2478024473842344696303990226553622964606230592230592230717133.029531087.00.0923639.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012937.08247491.00.08388608.0870412994.03793852210.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020735315.016255488120720162632828667641626328304532516255488591099
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011525671525674194304256001224381440x7f713e3883800x7f7117c247c024598002356925305094476553622357006630747430747430876045.029646352.00.01016321.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012894.08247926.00.08388608.0887668956.03814480286.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020561057.016255489126968162632830694861626328324932716255489602657
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041525671525674194304256001224391040x7f713e3882000x7f7117c2480012979201195837154607176553610225621216223916223915782135.014591216.023641.0921281.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06601.02030006.00.02097152.01012545910.02280435468.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012212342.016255490143485162632832741271626328336660716255490552076
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107152567152567419430425600824403200x7f713e3880800x7f7117c248401292592118590715308184655369278675216157316157315653071.014436537.024614.0664708.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06652.02056481.00.02097152.0951721147.02159017714.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012013769.016255491088084162632833902881626328348228816255491475646
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101525671525674194304256001224412800x7f713c149f000x7f7117c2488013115921208891156369976553610099515116394816394815951629.014643781.021796.01505703.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06624.02029769.00.02097152.01018196891.02308911312.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012068056.016255492021154162632835147681626328360660916255492417705
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131525671525674194304256001224422400x7f713c149d800x7f7117c248c024569522348407304220836553623025326230711830711830765493.029538446.00.0848775.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012837.08248682.00.08388608.0856580466.03800922874.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020680277.016255492953383162632836312491626328381173016255493438612
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161525671525674194304256001224432000x7f713c149c000x7f7117c2490024575762344959303772766553622550590730719630719630720695.029544896.00.01256534.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012641.08250643.00.08388608.0870625582.03806534865.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020650727.016255493972590162632838365301626328401781216255494514278
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119152567152567419430425600824441600x7f713c149a800x7f7117c2494013112481199978155086046553610359399416390516390515835825.014613877.022429.01405166.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06634.02030631.00.02097152.01014049292.02340908701.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012014380.016255495050667162632840440521626328413621216255495445138
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221525671525674194304256001224453760x7f713c1499000x7f7117c249801303664119366215392843655369467657916295716295715753717.014450916.023413.0985228.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06627.02039629.00.02097152.0967241326.02197694776.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012053083.016255495981916162632841618131626328425525316255496367448
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251525671525674194304256001224463360x7f713c1497800x7f7117c249c012996321192229154209416553610261574716245316245315735231.014534007.022325.01488244.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06623.02041610.00.02097152.01005580679.02346964343.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012004748.016255496909066162632842888531626328438085416255497366376
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281525671525674194304256001224475520x7f713c1496000x7f7117c24a0024354642333939302454376553622622641330443230443230577357.029385240.00.0808173.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012597.08251255.00.08388608.0869926778.03774662155.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020498252.016255497900204162632844059741626328458565516255498462431
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311525671525674194304256001224485120x7f713e3884800x7f7117c24a4024205282318889300427626553621913014030256530256530381655.029145888.00.0946183.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012580.08251667.00.08388608.0870825980.03907390722.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020238269.016255498998790162632846099751626328478917716255499497059
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134152567152567419430425600824494720x7f713e3883000x7f7117c24a801294688119035315361901655369491317916183516183515710713.014552945.023796.0911641.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06626.02029884.00.02097152.0986656802.02227218489.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012070654.016255500032127162632848130171626328490469716255500498076
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371525671525674194304256001224506880x7f713e3881800x7f7117c24ac012905201185334152623686553610027101816131416131415645635.014372807.024690.0575350.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06638.02038581.00.02097152.0894340445.02018176973.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012058195.016255501033364162632849294971626328502197816255501476235
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401525671525674194304256001224516480x7f713e3880000x7f7117c24b001301296119692315477507655369786392216266116266115796227.014625384.023030.01237232.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06643.02040876.00.02097152.01007074785.02225393840.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012075482.016255502023033162632850557381626328514677916255502504542
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431525671525674194304256001224528640x7f713c149e800x7f7117c24b4024193682315804300118886553622616792930242030242030341563.029127554.00.0925705.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012619.08250901.00.08388608.0871905693.03788775439.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020323074.016255503038810162632851717391626328535142016255503571198
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461525671525674194304256001224540800x7f713c149d000x7f7117c24b8024103762309216299121346553622009948830129630129630255841.029030346.00.0863476.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012552.08251717.00.08388608.0861939296.03923206702.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020256654.016255504104217162632853754201626328555718216255504640105
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149152567152567419430425600824552960x7f713c149b800x7f7117c24bc01294392119239815387087655369385709216179816179815737519.014479747.024264.0840290.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06627.02029086.00.02097152.0996642743.02222332183.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012110126.016255505172773162632855810221626328567462216255505617813
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521525671525674194304256001224567680x7f713c149a000x7f7117c24c0012978801195016154288676553610188628316223416223415771475.014418247.024888.0331505.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06653.02057932.00.02097152.0777230783.01937413957.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011917079.016255506151992162632857008621626328579446316255506603052
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551525671525674194304256001224577280x7f713c1498800x7f7117c24c401298560118907915377654655369544306916231916231915694359.014485219.024085.01137953.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06633.02041389.00.02097152.0996286109.02220961458.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012023478.016255507147710162632858287031626328592054416255507604279
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581525671525674194304256001224589440x7f713c1497000x7f7117c24c8024329522320553300563246553622345725730411830411830403391.029187386.00.01070769.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012638.08250920.00.08388608.0856807792.03931801475.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020392991.016255508145157162632859456641626328612454516255508681156
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611525671525674194304256001224601600x7f713e3885800x7f7117c24cc024379442332420302171796553622027097730474230474230557519.029359186.00.0880315.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012652.08250866.00.08388608.0855636865.03918732611.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020162397.016255509215974162632861495051626328632966716255509752842
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164152567152567419430425600824613760x7f713e3884000x7f7117c24d001297360119209915400942655368970476816216916216915733411.014474019.024794.0706856.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06601.02029107.00.02097152.0946967809.02344056841.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011986238.016255510286360162632863528671626328644582716255510732240
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671525671525674194304256001224628480x7f713e3882800x7f7117c24d4013561361244812160629756553610542055116951616951616418641.014723016.023139.0256646.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06632.02038990.00.02097152.0673004796.01781067783.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012048953.016255511264958162632864712671626328656822816255511713249
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701525671525674194304256001224638080x7f713e3881000x7f7117c24d801295912119270115423483655369208627716198816198815741289.014548448.023366.01052345.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06626.02042032.00.02097152.01001290529.02288245267.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012014241.016255512254957162632866003881626328669254916255512695217
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731525671525674194304256001224650240x7f713c149f800x7f7117c24dc024315122326893301319576553622529321230393830393830485759.029265345.00.01120643.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012648.08250714.00.08388608.0865037062.03888946217.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020187507.016255513229045162632867202291626328689927016255513770083
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761525671525674194304256001224662400x7f713c149e000x7f7117c24e0024263122317079299831186553621691393430328830328830358229.029150306.00.01145854.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012618.08251163.00.08388608.0872352287.04006502727.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020212536.016255514304182162632869239101626328710263116255514859389
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179152567152567419430425600824674560x7f713c149c800x7f7117c24e401296152119226815372694655369976432416201816201815735673.014356017.024657.0678857.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06620.02027562.00.02097152.0986068858.02222386241.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011962200.016255515392527162632871269521626328721975216255515840387
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821525671525674194304256001224689280x7f713c149b000x7f7117c24e8013992001293914166615856553611605647917489917489917056967.014955174.022165.0102311.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06640.02038302.00.02097152.0627889123.01636404858.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012370202.016255516374336162632872435921626328734567316255516840035
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851525671525674194304256001224701440x7f713c1499800x7f7117c24ec01278344117524415182199655369559743415979215979215514153.014364321.024417.0628797.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06639.02041910.00.02097152.0969057966.02245677982.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011995874.016255517381433162632873789531626328747095416255517817044
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881525671525674194304256001224716160x7f713c1498000x7f7117c24f0024406242332732302043376553622368144030507730507730561705.029268182.00.01154496.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012819.08249022.00.08388608.0876233306.03794428659.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020489710.016255518350352162632874957541626328767623516255518882190
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911525671525674194304256001224728320x7f713c1496800x7f7117c24f4024285602317166300302286553622428193330356930356930359243.029087746.00.01099653.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012717.08250077.00.08388608.0858690993.03883065849.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020041767.016255519414638162632877016751626328788199716255519948167
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194152567152567419430425600824740480x7f713e3885000x7f7117c24f801291584118748715325705655369669751816144716144715673533.014420906.023079.01062709.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06643.02056409.00.02097152.0984494462.02087678491.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011972628.016255520480925162632879061571626328799847716255520921815
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971525671525674194304256001224757760x7f713e3883800x7f7117c24fc014566961350777174190406553612094559018208618208617796277.015504263.020884.0125659.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06640.02038783.00.02097152.0540176599.01446690851.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012518962.016255521454994162632880224771626328812839816255521930243
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001525671525674194304256001224769920x7f713e3882000x7f7117c2500012906001187229153445876553610355431116132416132415670205.014438942.024464.0633375.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06613.02042725.00.02097152.0999552226.02269553815.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011540090.016255522483031162632881615181626328825399916255522931721
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031525671525674194304256001224784640x7f713e3880800x7f7117c2504024226082312417299610346553622046798030282530282530297623.029020406.00.0765652.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012762.08249811.00.08388608.0868008872.03901610174.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019434574.016255523464719162632882781591626328845848016255524003617
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061525671525674194304256001224799360x7f713c149f000x7f7117c2508024123122306373298391466553622271447230153830153830218869.028917857.00.0586771.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012609.08251160.00.08388608.0873406239.03767714043.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019648587.016255524536355162632884831201626328866184216255525069394
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209152567152567419430425600824814080x7f713c149d800x7f7117c250c01300616119172715361567655369175081516257616257615728497.014424256.024399.0777247.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06619.02039260.00.02097152.0943385619.02267587735.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011923171.016255525608042162632886888821626328878216216255526063861
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121525671525674194304256001224831360x7f713c149c000x7f7117c2510015332081425469183837106553612497828819165019165018767091.015521397.020916.095018.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06636.02040335.00.02097152.0454264252.01228436906.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012131925.016255526596510162632888072821626328891896316255527071369
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151525671525674194304256001224843520x7f713c149a800x7f7117c2514012872321187247153314586553610446797216090316090315670413.014433992.023432.0929230.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06622.02042311.00.02097152.0993665081.02265632528.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011949378.016255527612797162632889690441626328906200416255528049878
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181525671525674194304256001224858240x7f713c1499000x7f7117c2518024181842317494300034316553622338143130227230227230363533.029062371.00.01020094.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012745.08249915.00.08388608.0872198121.03791509472.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020049279.016255528582736162632890874441626328926792516255529139104
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211525671525674194304256001224872960x7f713c1497800x7f7117c251c024212082315546299676966553622006491830265030265030338235.029066384.00.0960231.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012636.08251013.00.08388608.0871228173.03763784690.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020200551.016255529672312162632892927261626328947256716255530208520
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241525671525674194304256001224887680x7f713c1496000x7f7117c252001297560118988915330592655369520718216219416219415704759.014375445.025002.0641893.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06622.02038689.00.02097152.0959829197.02204778656.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011894552.016255530741978162632894972071626328959064816255531217528
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271525671525674194304256001224907520x7f713e3884800x7f7117c2524016000161495050192673576553613228781820000120000119671891.015806935.019868.056965.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06635.02041581.00.02097152.0435325125.01145194636.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012526629.016255531753086162632896159281626328973400816255532232025
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301525671525674194304256001224919680x7f713e3883000x7f7117c252801290216118530015299780655369806909316127616127615645167.014399980.023325.0962791.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06597.02042986.00.02097152.0968748473.02302710515.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011890390.016255532774843162632897669691626328985912916255533218253
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331525671525674194304256001224934400x7f713e3881800x7f7117c252c024193202317900300304896553622380474130241430241430368759.028985747.00.0841674.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012741.08250184.00.08388608.0863926533.03837600654.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020073337.016255533752432162632898832891626329006313116255534295940
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361525671525674194304256001224949120x7f713e3880000x7f7117c2530023989202294936297212736553621646391729986429986430070461.028765209.00.0825556.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012607.08251187.00.08388608.0864398217.03842588202.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019878014.016255534829118162632901029711626329028313216255535360086
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391525671525674194304256001224963840x7f713c149e800x7f7117c2534013001201189085153274336553610163682516251416251415694229.014356928.024055.0805193.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06607.02039459.00.02097152.0923620921.02156214745.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011906659.016255535892134162632903093721626329040345316255536360784
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421525671525674194304256001224983680x7f713c149d000x7f7117c2538016725441566683202001986553614126847420906720906720602977.016525691.018914.031683.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06656.02041085.00.02097152.0403221582.01086200329.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012979406.016255536894732162632904282531626329055177416255537384451
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451525671525674194304256001224995840x7f713c149b800x7f7117c253c01296232118749115313157655369475397516202816202815673611.014399097.023996.0884984.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06623.02040017.00.02097152.0980621516.02185377232.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012004635.016255537924789162632905845741626329067737516255538395639
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024815256715256741943042560012241013120x7f713c149a000x7f7117c2540023981602294145297233876553622119671229976929976930060009.028890657.00.0880120.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012622.08250886.00.08388608.0860617197.03880744662.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019889375.016255538930427162632907029751626329088041616255539473525
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025115256715256741943042560012241027840x7f713c1498800x7f7117c2544023926802288300296150356553621593366829908429908429983959.028732732.00.0867746.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012557.08251601.00.08388608.0859107793.03839398956.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020047338.016255540006483162632909053761626329108377716255540542791
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025415256715256741943042560012241042560x7f713c1497000x7f7117c2548012947601185080152864866553610260106316184416184415642281.014300033.024919.0351728.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06633.02039071.00.02097152.0888682569.02166574658.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011907215.016255541073780162632911082571626329120121816255541527710
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025715256715256741943042560012241062400x7f713e3885800x7f7117c254c017557361644868212149386553614910723021946621946621619317.016717195.018569.036115.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06654.02041412.00.02097152.0370478390.01041294179.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012943440.016255542061118162632912258581626329135481916255542569937
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026015256715256741943042560012241077120x7f713e3884000x7f7117c2550012823921176898151663196553610010388716029816029815535889.014212343.024789.0640308.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06606.02041810.00.02097152.0928376543.02246325852.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011936702.016255543113755162632913872991626329147946016255543545175
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026315256715256741943042560016241094400x7f713e3882800x7f7117c2554023926162285551295795326553621817613229907629907629948417.028681397.00.0683312.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012620.08250882.00.08388608.0853123460.03986138167.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019805386.016255544080633162632915052201626329168426116255544551633
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026615256715256741943042560016241111680x7f713e3881000x7f7117c2558023748002273076294512896553621653291329684929684929786151.028563337.00.0687902.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012346.08253956.00.08388608.0836726519.03843706968.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020059801.016255545087791162632917085811626329188874216255545595480
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691525671525674194304256008241128960x7f713c149f800x7f7117c255c012957201194966154064476553610610132716196416196415770643.014250693.024801.0241509.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06673.02056329.00.02097152.0844324128.01935768367.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011990404.016255546128608162632919130621626329200698316255546596398
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027215256715256741943042560012241151360x7f713c149e000x7f7117c2560018179921713572221395966553615885468922724822724822512469.016829509.018176.031819.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06658.02041456.00.02097152.0357754948.01018313254.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012627159.016255547132776162632920313031626329216746416255547567846
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027515256715256741943042560012241166080x7f713c149c800x7f7117c256401298864119031315351794655369884446216235716235715710219.014366091.023762.0822648.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06596.02042479.00.02097152.0961443464.02226069217.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011849684.016255548110024162632922004241626329229402516255548471246
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027815256715256741943042560016241183360x7f713c149b000x7f7117c2568023772562274821294692846553621785060329715629715629808771.028549842.00.0751638.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012563.08251564.00.08388608.0856942841.03874625742.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019595916.016255549006255162632923181851626329249754616255549461495
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028115256715256741943042560016241200640x7f713c1499800x7f7117c256c024101442297500297347366553621842062030126730126730103767.028847883.00.01010725.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012631.08250849.00.08388608.0855539355.03917669653.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019814632.016255549996513162632925221861626329270250816255550464452
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028415256715256741943042560012241217920x7f713c1498000x7f7117c2570012988481192651153936666553610637442616235516235515740509.014343006.024315.0234251.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06658.02059288.00.02097152.0751056380.01849868481.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011999095.016255550999211162632927269881626329282218816255551356493
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028715256715256741943042560012241240320x7f713c1496800x7f7117c2574019008881799537232485906553616854474923761023761023630183.017365458.017813.030216.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06674.02041461.00.02097152.0327591784.0936572930.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.013103749.016255551890681162632928476281626329298970916255552298052
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029015256715256741943042560012241255040x7f713e3885000x7f7117c2578012823121179708152139296553610109237616028816028815572471.014217858.024313.0636847.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06605.02040371.00.02097152.0919310100.02035007281.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011792339.016255552840550162632930241101626329311739016255553201092
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029315256715256741943042560012241274880x7f713e3883800x7f7117c257c023968562287654295937126553620462644629960629960629975769.028600361.00.01185457.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012157.08256061.00.08388608.0841370353.03951637905.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019643228.016255553736090162632931423501626329332027216255554205889
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029615256715256741943042560012241292160x7f713e3882000x7f7117c2580023917042287457296120446553621489885929896229896229973013.028674203.00.01150069.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012397.08253645.00.08388608.0857050786.03870643095.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019738097.016255554741948162632933447521626329352379316255555203288
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029915256715256741943042560012241309440x7f713e3880800x7f7117c2584013597601253933161858956553611156296516996916996916537175.015094767.022622.0173128.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06651.02038971.00.02097152.0677604479.01767242814.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012589620.016255555738476162632935497131626329364875416255556106708
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030215256715256741943042560012241334400x7f713c149f000x7f7117c2588020631441960676253284876553618795176025789225789225724899.017184747.019022.039261.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06672.02040936.00.02097152.0337077703.0966689500.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012347126.016255556642576162632936740341626329382715516255557131975
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030515256715256741943042560012241349120x7f713c149d800x7f7117c258c01284960117997115218038655369866841416061916061915575643.014280253.023978.0519803.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06617.02039851.00.02097152.0875767331.02055459500.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011857378.016255557676073162632938618751626329395499616255558063675
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030815256715256741943042560012241368960x7f713c149c000x7f7117c2590023602962254191291600396553621061808129503629503629540555.028317157.00.0823384.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012229.08255149.00.08388608.0838443313.03881034498.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019752591.016255558599283162632939809161626329415899716255559094742
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031115256715256741943042560012241388800x7f713c149a800x7f7117c2594023657362263707293109856553621661935329571629571629664445.028372336.00.0974933.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012604.08251263.00.08388608.0841468260.03944579850.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019617822.016255559630840162632941844371626329436315816255560122829
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031415256715256741943042560012241408640x7f713c1499000x7f7117c2598014412881335889172454436553612230956918016018016017602733.015739281.020158.0195539.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06629.02039195.00.02097152.0539137549.01425708839.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.013156350.016255560656677162632943868381626329449067916255561090077
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031715256715256741943042560012241436160x7f713c1497800x7f7117c259c022273202117515273655216553620115990427841427841427763819.017407645.018984.032776.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06678.02041208.00.02097152.0311754234.0923362275.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012160803.016255561630455162632945143591626329468188016255562088855
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032015256715256741943042560012241453440x7f713c1496000x7f7117c25a0012985841195564154235166553610432422116232216232215778521.014407802.023047.0375882.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06630.02041053.00.02097152.0770787395.01899661782.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.011877882.016255562633273162632947145211626329480860116255563040774
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032315256715256741943042560012241475840x7f713e3884800x7f7117c25a4023674482259761292342846553620942107229593029593029613121.028222534.00.0514535.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012557.08251398.00.08388608.0821545153.03998795276.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019375145.016255563577863162632948327611626329501180216255564076632
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032615256715256741943042560012241495680x7f713e3883000x7f7117c25a8023655682259199291721096553621026630829569529569529605841.028224018.00.01133603.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012490.08252364.00.08388608.0826660110.03918501568.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019460388.016255564611990162632950354831626329521516416255565083999
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032915256715256741943042560012241515520x7f713e3881800x7f7117c25ac014894401386898178691296553612517090918617918617918265811.016657831.016421.0155889.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06645.02040180.00.02097152.0451238099.01192132932.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.014023731.016255565619978162632952393241626329534796516255566052338
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033215256715256741943042560012241543040x7f713e3880000x7f7117c25b0023882642278695294315226553621534159429853229853229859081.017921232.018435.048845.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06665.02041083.00.02097152.0305250461.0879453456.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012323646.016255566588846162632953722851626329555116616255567067616
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033515256715256741943042560012241562880x7f713c149e800x7f7117c25b4013832641281137165112276553611245962517290717290716890983.015127920.022217.0228895.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06629.02038638.00.02097152.0621558807.01627724410.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012458255.016255567610794162632955834861626329568364716255568029444
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033815256715256741943042560012241587840x7f713c149d000x7f7117c25b8023883842260548292058826553618721464429854729854729623261.028283933.00.0699312.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.011727.08260827.00.08388608.0839358743.03846610150.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019329525.016255568564372162632957098871626329589196816255569035122
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034115256715256741943042560012241610240x7f713c149b800x7f7117c25bc023634802254387291452756553619658069629543429543429543207.028193465.00.0633691.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012181.08255677.00.08388608.0837697073.03835522714.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019709776.016255569570480162632959159681626329609948916255570059759
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034415256715256741943042560012241632640x7f713c149a000x7f7117c25c0016426961536244198285386553614363281520533620533620207231.018167395.015880.055377.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06626.02039615.00.02097152.0416103063.01129930029.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.015410810.016255570594957162632961236501626329624461016255571055627
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034715256715256741943042560012241665280x7f713c1498800x7f7117c25c4026999282600014336220936553625087940833749033749034036267.017978004.018854.048175.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06737.02041857.00.02097152.0309292166.0904709859.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012655285.016255571591036162632962690911626329647293216255572149913
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035015256715256741943042560012241685120x7f713c1497000x7f7117c25c8014664641361790175726476553612307547118330718330717939355.016035873.019638.048637.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06654.02037005.00.02097152.0481770767.01218419076.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.013375501.016255572628063162632965428521626329665101316255573046694
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035315256715256741943042560012241712640x7f713e3885800x7f7117c25cc023860642275213293493106553620215923429825729825729813893.028242145.00.0501094.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012171.08255703.00.08388608.0810711678.03935260275.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019222791.016255573580822162632966772531626329685981416255574090461
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035615256715256741943042560012241737600x7f713e3884000x7f7117c25d0023764322267370292554966553620263644429705329705329712077.028290892.00.0720779.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012146.08255903.00.08388608.0823019278.03879739964.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019203161.016255574624129162632968844541626329706989616255575107178
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035915256715256741943042560012241762560x7f713e3882800x7f7117c25d4017876001685173217945796553616111187522344922344922143425.020203417.014198.082488.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06637.02036948.00.02097152.0318787943.0939524810.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.016432076.016255575641826162632970966161626329722909716255576077166
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036215256715256741943042560012241797760x7f713e3881000x7f7117c25d8030278962924883378052076553628263586037848637848638259681.018524222.018854.060046.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06725.02041918.00.02097152.0318055860.0917713495.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.012496525.016255576612245162632972530971626329748413816255577224831
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036515256715256741943042560012241822720x7f713c149f800x7f7117c25dc016911521582270204296486553614524731721139321139320805569.018394253.017425.0135312.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06635.02050113.00.02097152.0345611706.0996781250.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.014420642.016255577700271162632975287791626329765405916255578156560
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036815256715256741943042560012241855360x7f713c149e000x7f7117c25e0024871122363503304559036553619663752631088831088830961741.028609563.00.0480144.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012502.08251603.00.08388608.0686150028.03368018271.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019141067.016255578691769162632976790201626329787070116255579247536
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037115256715256741943042560012241885440x7f713c149c800x7f7117c25e4025236802386740307746316553619404373331545931545931263965.029435024.00.0536680.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012759.08248841.00.08388608.0688784584.03462872011.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.019955880.016255579720266162632978963011626329809086216255580275493
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037415256715256741943042560012241915520x7f713c149b000x7f7117c25e8021140402011522260319256553619444238726425426425426385871.023081986.015671.063177.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06640.02030917.00.02097152.0322377474.0932561909.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.016173304.016255580751033162632981275021626329828558416255581204803
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037715256715256741943042560012241958400x7f713c1499800x7f7117c25ec036713523562285461182376553634856831445891845891846545959.018645517.018879.049623.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06706.02040777.00.02097152.0315964416.0889869034.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.013348241.016255581739671162632983102241626329859134516255582378997
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038015256715256741943042560012241985920x7f713c1498000x7f7117c25f0019227281822688235748856553617509221924034024034023931159.021778724.013493.010084.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06650.02048819.00.02097152.0314328380.0933175434.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.019339588.016255582858476162632986366261626329878222716255583310046
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038315256715256741943042560012242023680x7f713c1496800x7f7117c25f4026805522566417330630706553621316225933506833506833599467.029637236.00.0173678.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012614.08250294.00.08388608.0636247245.03087043766.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020124165.016255583844975162632988092671626329902126816255584409572
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038615256715256741943042560012242058880x7f713e3885000x7f7117c25f8026535682539940326954416553622408877933169533169533255409.030855224.00.0286460.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012600.08250386.00.08388608.0546899727.02896333661.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.021678067.016255584879442162632990599891626329927055016255585484348
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038915256715256741943042560012242094080x7f713e3883800x7f7117c25fc024417762335151302318046553622799059330522130522130593269.023218128.016161.079656.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06620.02029527.00.02097152.0302921113.0885942045.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.016710712.016255585957568162632993315101626329951551116255586468287
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039215256715256741943042560012242144640x7f713e3882000x7f7117c2600043205844210645545401266553641421510654007254007254974587.017812061.019960.026335.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06704.02041516.00.02097152.0319642958.0907510184.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.013302734.016255587004575162632995404721626329987327416255587733419
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039515256715256741943042560012242177280x7f713e3880800x7f7117c2604021662242063948266945566553619957524227077727077727067565.020923431.015652.044507.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06624.02047408.00.02097152.0316233029.0921796817.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.015349294.016255588218148162632999166341626330008063516255588700577
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039815256715256741943042560012242220160x7f713c149f000x7f7117c2608029599362844314365863166553624988976136999136999137212297.030566761.00.0178162.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012630.08249911.00.08388608.0540009298.02693693397.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020518306.016255589237695162633001065551626330033839716255589800753
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040115256715256741943042560012242260480x7f713c149d800x7f7117c260c029424162829519364282246553626039477636780136780137019845.033931572.00.0175475.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012951.08246461.00.08388608.0470521969.02388822031.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.024194656.016255590298482162633003731171626330060207816255590890999
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040415256715256741943042560012242300800x7f713c149c000x7f7117c2610027619442656797344060136553625919847734524234524234774563.023855858.015564.036229.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06613.02031843.00.02097152.0307528789.0913444553.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.016834933.016255591360968162633006388791626330084864016255591943846
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040715256715256741943042560012242359040x7f713c149a800x7f7117c2614049653044861392629853646553647950938762066262066263434259.018676401.019602.075954.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06721.02041074.00.02097152.0314206598.0902268763.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.013368460.016255592414635162633008817601626330126448316255593162719
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041015256715256741943042560012242394240x7f713c1499000x7f7117c2618024234082315728299819276553622524618330292530292530340757.021694346.015552.029883.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06643.02046778.00.02097152.0313470347.0911902182.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.016304134.016255593644488162633013057631626330148992416255594155097
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041315256715256741943042560012242442240x7f713c1497800x7f7117c261c032146403105506400485266553627421104140182940182940607819.031444715.00.090367.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012847.08247560.00.08388608.0463909659.02400525117.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.021404877.016255594691265162633015153641626330176736616255595337041
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041615256715256741943042560012242487680x7f713c1496000x7f7117c2620031244963021820391263016553629799304139056139056139519771.035026344.00.0107647.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.013142.08244086.00.08388608.0315452876.01800505020.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.023819257.016255595807740162633018022461626330204784816255596410907
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041915256715256741943042560012242533120x7f713e3884800x7f7117c2624030938242990604387684746553629773097338672738672739113989.023938588.016785.031006.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06628.02029571.00.02097152.0354728513.01023273976.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.017080468.016255596880917162633020875281626330232289016255597470413
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221525671525674194304256008242555520x7f713e3883000x7f7117c2628057085045601301725797366553655327469471356271356273053115.068566664.0897.00.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.07126.02065332.00.02097152.0232617145.0802443452.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.063273653.016255597943433162633023820901626330283201316255598803214
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042515256715256741943042560012242598400x7f713e3881800x7f7117c262c028967682793184361711356553627252437036209536209536547321.024330646.013930.030958.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06632.02045983.00.02097152.0301960098.0907784017.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.018409614.016255599281714162633029022531626330312465516255599868731
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042815256715256741943042560012242656640x7f713e3880000x7f7117c2630037608083658543474055146553636117249847010047010047797105.033741527.00.044317.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.013078.08244802.00.08388608.0305096668.01723478098.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.022688174.016255600343110162633031864151626330348529716255601045905
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043115256715256741943042560012242712320x7f713c149e800x7f7117c2634038100563702092478388186553634989452147625647625648363333.033362066.00.042049.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.012873.08247097.00.08388608.0355702033.01957995201.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.020627571.016255601517264162633035443371626330384177916255602185680
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341525671525674194304256008242732160x7f713c149d000x7f7117c2638038355923727847482137556553636409680347944847944848698265.047118559.01433.00.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.07662.02063703.00.02097152.0235487319.0806413171.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.044415517.016255602680249162633039056201626330419922216255603346754
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371525671525674194304256008242757120x7f713c149b800x7f7117c263c070103126900284894108076553668805157687628887628889939985.076177492.0949.00.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06833.02063976.00.02097152.0231842692.0799688158.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.067676676.016255603814863162633042606621626330481410616255604719813
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044015256715256741943042560012242807680x7f713c149a000x7f7117c2640034051843299843427547656553632404030642564742564743134005.030253145.011846.069206.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06644.02028447.00.02097152.0310868537.0941311951.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.021997767.016255605198293162633048795461626330514114816255605852218
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044315256715256741943042560012242876160x7f713c1498800x7f7117c2644044107444307895557197686553641284361855134255134256238889.035689981.00.056491.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.013007.08245601.00.08388608.0331601105.01876940464.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.021855452.016255606326268162633052041881626330555539016255607054162
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044615256715256741943042560012242942080x7f713c1497000x7f7117c2648044132484308340557421936553641697225055165555165556244557.034874806.00.0120505.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.013119.08244391.00.08388608.0332172506.01866319133.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.017257303.016255607525761162633056003511626330595011316255608233866
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491525671525674194304256008242969600x7f713e3885800x7f7117c264c044775284365806565336046553642791571655969055969056991823.055039825.01228.00.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.07715.02063573.00.02097152.0236186302.0808258419.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.051861581.016255608704805162633059891531626330633331516255609452279
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521525671525674194304256008242999680x7f713e3884000x7f7117c26500830521681956081061681106553681006068910381511038151106779275.084850934.0848.00.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06837.02064118.00.02097152.0235363339.0810733391.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.073579448.016255609924079162633063942761626330705124016255610948776
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551525671525674194304256008243027200x7f713e3882800x7f7117c2654057374325630379729542986553655545613571717871717873430999.068447194.01004.00.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.07647.02063179.00.02097152.0235447415.0811271581.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.062348048.016255611428675162633071269201626330756996316255612237447
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045815256715256741943042560012243054720x7f713e3881000x7f7117c2658057508645646073731400436553655736342571885771885773635099.069123389.00.00.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.013220.08243188.00.08388608.0239051359.01595482571.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.057710835.016255612708667162633076358841626330809668716255613522719
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046115256715256741943042560012243082240x7f713c149f800x7f7117c265c057467525638604730247886553656098911471834371834373538015.069039485.00.00.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.013204.08243364.00.08388608.0240889711.01609361348.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.057750810.016255613993938162633081637271626330862133016255614816840
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641525671525674194304256008243109760x7f713c149e000x7f7117c2660057666245664763734066776553656223007672082772082773878069.068645924.01019.00.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.07647.02063320.00.02097152.0232829451.0805157462.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.062951679.016255615284880162633086853301626330913397316255616125971
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671525671525674194304256008243132160x7f713c149c800x7f7117c26640109064881079089413980333665536107976676813633101363310140517759.095383202.0853.00.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06835.02065379.00.02097152.0235304970.0810929336.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.082978088.016255616598021162633091978141626331006261916255617830574
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701525671525674194304256008243159680x7f713c149b000x7f7117c26680109244241082374514024386565536108405294813655521365552140944861.094956898.0998.00.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.07537.02063301.00.02097152.0237378753.0818400841.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.080102439.016255618310203162633101453401626331099430516255619564106
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047315256715256741943042560012243187200x7f713c1499800x7f7117c266c0109575681083761414040141165536107919316813696951369695141125041.097672308.00.00.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.013273.08242605.00.08388608.0237197157.01587099462.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.078585800.016255620040215162633110607061626331194167116255621296567
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047615256715256741943042560012243214720x7f713c1498000x7f7117c26700109369441082570014025010965536108226519213671171367117140970315.098057218.00.00.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.013168.08243760.00.08388608.0235565270.01585538120.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.078351342.016255621771027162633120077521626331288295816255623012839
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791525671525674194304256008243242240x7f713c1496800x7f7117c26740109707761086194614074992465536108682952913713461371346141441539.092845851.0864.00.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.07523.02063374.00.02097152.0237439586.0819270887.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.082304668.016255623482199162633129536781626331380840316255624717602
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821525671525674194304256008243264640x7f713e3885000x7f7117c26780212765202116356427427559765536213160696626595642659564275362599.0116834804.0538.00.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06793.02065151.00.02097152.0241864455.0833728798.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.096033261.016255625186811162633138733641626331556649516255627276495
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851525671525674194304256008243292160x7f713e3883800x7f7117c267c0213124962120458827475957565536213345429726640612664061275895807.0130961548.0555.00.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.07916.02061986.00.02097152.0242028555.0838837868.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.0108299586.016255627752795162633156687351626331732970616255629777740
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048815256715256741943042560012243319680x7f713e3882000x7f7117c26800213240802121263827494177465536213556152626655092665509276000405.0134592988.00.00.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.013255.08242803.00.08388608.0234277669.01595795102.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.0107600960.016255630251989162633174169071626331913643816255632379042
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049115256715256741943042560012243347200x7f713e3880800x7f7117c26840213199122121059527482953865536212809009926649882664988275973885.0137588191.00.00.00.00.00.0524288.033554432.033554432.033554432.00.00.00.0104.08388608.013141.08244057.00.08388608.0234601779.01599584988.00.04194304.00.00.00.00.00.00.00.00.00.00.00.00.04194304.00.00.0111131695.016255632847792162633192266781626332093788916255634924676
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941525671525674194304256008243374720x7f713c149f000x7f7117c26880213472402123946727527758265536213877169626684042668404276349247.0129343979.0625.00.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.08000.02061984.00.02097152.0241863765.0838629466.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.0109943191.016255635398025162633210233301626332269230116255637425861
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049715256715256741943042560082400x7f713c149d800x7f7117c268c0420156644190293954311197965536423637811652519575251957544974357.0113838432.0451.00.00.00.00.0524288.08388608.08388608.08388608.00.00.00.0104.02097152.06748.02066081.00.02097152.0244282680.0845748474.00.02097152.00.00.00.00.00.00.00.00.00.00.00.00.02097152.00.00.092086761.016255637900450162633227811011626332613392316255641643247