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

84 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_CYCLESSQ_BUSY_CYCLESSQ_WAVESGRBM_COUNTGRBM_GUI_ACTIVETCC_CYCLE_sumTCC_BUSY_sumTCC_PROBE_sumTCC_PROBE_ALL_sumTCC_NC_REQ_sumTCC_UC_REQ_sumTCC_CC_REQ_sumTCC_RW_REQ_sumTCC_EA_ATOMIC_LEVEL_sumTCC_REQ_sumTCC_STREAMING_REQ_sumTCC_HIT_sumTCC_MISS_sumTCC_READ_sumTCC_WRITE_sumTCC_ATOMIC_sumTCC_WRITEBACK_sumTCC_EA_WRREQ_sumTCC_EA_WRREQ_64B_sumTCC_EA_WR_UNCACHED_32B_sumTCC_EA_WRREQ_STALL_sumTCC_EA_WRREQ_IO_CREDIT_STALL_sumTCC_EA_WRREQ_GMI_CREDIT_STALL_sumTCC_EA_WRREQ_DRAM_CREDIT_STALL_sumTCC_TOO_MANY_EA_WRREQS_STALL_sumTCC_EA_ATOMIC_sumTCC_EA_RDREQ_sumTCC_EA_RDREQ_32B_sumTCC_EA_RD_UNCACHED_32B_sumTCC_EA_RDREQ_IO_CREDIT_STALL_sumTCC_EA_RDREQ_GMI_CREDIT_STALL_sumTCC_EA_RDREQ_DRAM_CREDIT_STALL_sumTCC_TAG_STALL_sumTCC_NORMAL_WRITEBACK_sumTCC_ALL_TC_OP_WB_WRITEBACK_sumTCC_NORMAL_EVICT_sumTCC_ALL_TC_OP_INV_EVICT_sumTCC_EA_RDREQ_DRAM_sumTCC_EA_WRREQ_DRAM_sumTCC_EA_RDREQ_LEVEL_sumTCC_EA_WRREQ_LEVEL_sumDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000155691155691335544322560043241600x00x7f018c6042803035792294834552428837947337947312143136.09351792.00.00.056.0304.00.04194696.00.04195057.00.02097594.02097463.0750.04194304.00.02064387.04128768.04128768.00.01450770.00.00.01457360.00.00.0309.00.0602.00.00.00.0190929.02064384.00.02031623.00.0142.04128768.0526448.01629445996.016335241863961163431792809501634317951871216335386682896
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00215569115569132768256001224138880x00x7f018c623f802009121027385122511325113803616.0259457.00.00.00.061.00.04600.00.04660.00.0499.04161.04660.00.00.031.00.00.00.00.00.00.00.00.00.08259.00.0116.00.00.00.053619.00.00.00.00.08205.00.03416027.00.016335392065267163431844057851634318441298516335392328611
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051556911556914194304256001224143360x7f018f6963800x7f018c623fc013130561205448655361641311641315252192.04725074.00.00.00.0184.00.01048968.00.01049133.00.0388.01048745.01049146.00.00.031.00.00.00.00.00.00.00.00.00.02097337.00.0356.00.00.0334375.0964875.00.00.0983046.00.02097265.00.01476812669.00.016335392404579163431844477061634318453986616335392983106
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081556911556914194304256001624150400x7f018f6962000x7f018c62400024722082373474655363090253090259888800.09366799.00.00.00.0295.00.02344520.00.02361513.00.0264088.02097425.02343417.00.00.031.00.00.00.00.00.00.00.00.00.04194591.00.0554.00.00.0619678.02017179.00.00.02031623.00.04194526.00.02668810769.00.016335393074594163431845741061634318475442816335393670131
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111556911556914194304256001624154880x7f018f6960800x7f018c62404024650562360817655363081313081319860192.09331900.00.00.00.0298.00.02341236.00.02358897.00.0261475.02097422.02360361.00.00.031.00.00.00.00.00.00.00.00.00.04194593.00.0562.00.00.0602853.01936888.00.00.02031622.00.04194526.00.02648486536.00.016335393755049163431847809881634318496162916335394380876
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141556911556914194304256001224159360x7f018cefdf000x7f018c62408013122641210525655361640321640325249024.04715538.00.00.00.0185.00.01049080.00.01049248.00.0499.01048749.01049260.00.00.031.00.00.00.00.00.00.00.00.00.02097345.00.0368.00.00.0421066.01241649.00.00.0983047.00.02097268.00.01399900071.00.016335394465704163431849857891634318507811016335394980152
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171556911556914194304256001224163840x7f018cefdd800x7f018c6240c013206401217725655361650791650795282528.04728212.00.00.00.0180.00.01049024.00.01049193.00.0443.01048750.01049202.00.00.031.00.00.00.00.00.00.00.00.00.02097345.00.0370.00.00.0369121.01143373.00.00.0983047.00.02097275.00.01424168357.00.016335395065190163431851048301634318519683116335395568129
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201556911556914194304256001224170880x7f018cefdc000x7f018c62410012985281195629655361623151623155194080.04666718.00.00.00.0181.00.01049080.00.01049246.00.0499.01048747.01049258.00.00.031.00.00.00.00.00.00.00.00.00.02097339.00.0356.00.00.0383509.01189651.00.00.0983047.00.02097268.00.01408346844.00.016335395667417163431852414711634318533283216335396155646
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231556911556914194304256001624177920x7f018cefda800x7f018c62414024673122365562655363084133084139869216.09338244.00.00.00.0279.00.02327934.00.02339781.00.0242348.02097433.02316398.00.00.031.00.00.00.00.00.00.00.00.00.04194604.00.0578.00.00.0639058.02082377.00.00.02031624.00.04194528.00.02599216543.00.016335396239284163431853717121634318555155316335396760703
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261556911556914194304256001624184960x7f018cefd9000x7f018c62418024762082378386655363095253095259904800.09347881.00.00.00.0294.00.02341317.00.02340874.00.0243450.02097424.02343973.00.00.031.00.00.00.00.00.00.00.00.00.04194593.00.0558.00.00.0602953.01985936.00.00.02031623.00.04194517.00.02673540888.00.016335396844581163431855977941634318577651516335397358010
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291556911556914194304256001624192000x7f018cefd7800x7f018c6241c013075441207209655361634421634425230144.04677375.00.00.00.0176.00.01049136.00.01049305.00.0555.01048750.01049313.00.00.031.00.00.00.00.00.00.00.00.00.02097344.00.0364.00.00.0407300.01268523.00.00.0983047.00.02097275.00.01361919913.00.016335397442098163431858120351634318590419616335397868528
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321556911556914194304256001624199040x7f018cefd6000x7f018c62420013132561211960655361641561641565252992.04714552.00.00.00.0176.00.01049136.00.01049302.00.0555.01048747.01049319.00.00.031.00.00.00.00.00.00.00.00.00.02097343.00.0362.00.00.0424727.01195651.00.00.0983047.00.02097277.00.01414538248.00.016335397952036163431859365161634318602883716335398401047
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351556911556914194304256001224206080x7f018f6964800x7f018c62424013042161202463655361630261630265216832.04660036.00.00.00.0185.00.01049136.00.01049300.00.0555.01048745.01049313.00.00.031.00.00.00.00.00.00.00.00.00.02097340.00.0356.00.00.0422490.01332750.00.00.0983047.00.02097266.00.01411153568.00.016335398495344163431860688371634318616099816335398917645
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381556911556914194304256001624213120x7f018f6963000x7f018c62428024662242363735655363082773082779864864.09324348.00.00.00.0288.00.02322985.00.02351190.00.0253757.02097433.02348682.00.00.031.00.00.00.00.00.00.00.00.00.04194608.00.0584.00.00.0659664.02138829.00.00.02031624.00.04194530.00.02604938519.00.016335399002723163431861981181634318637827916335399515152
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411556911556914194304256001624220160x7f018f6961800x7f018c6242c024527202343963655363065893065899810848.09275021.00.00.00.0287.00.02350140.00.02351637.00.0254221.02097416.02342086.00.00.031.00.00.00.00.00.00.00.00.00.04194606.00.0582.00.00.0734080.02399683.00.00.02031624.00.04194521.00.02657770873.00.016335399599570163431864064391634318658692116335400130628
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441556911556914194304256001624227200x7f018f6960000x7f018c62430013106241207006655361638271638275242464.04687369.00.00.00.0176.00.01049192.00.01049362.00.0610.01048752.01049376.00.00.031.00.00.00.00.00.00.00.00.00.02097345.00.0364.00.00.0349767.01099055.00.00.0983048.00.02097280.00.01425801390.00.016335400215757163431866130011634318670516216335400638407
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471556911556914194304256001224234240x7f018cefde800x7f018c62434013030561203512655361628811628815212192.04689776.00.00.00.0187.00.01049248.00.01049416.00.0666.01048750.01049421.00.00.031.00.00.00.00.00.00.00.00.00.02097344.00.0360.00.00.0475514.01440012.00.00.0983048.00.02097278.00.01422266987.00.016335400722365163431867339621634318682564216335401149506
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501556911556914194304256001224241280x7f018cefdd000x7f018c62438013054241204575655361631771631775221664.04690166.00.00.00.0184.00.01049192.00.01049361.00.0610.01048751.01049370.00.00.031.00.00.00.00.00.00.00.00.00.02097342.00.0358.00.00.0598294.01798037.00.00.0983048.00.02097277.00.01443794403.00.016335401242134163431868595631634318695124316335401675824
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531556911556914194304256001624248320x7f018cefdb800x7f018c6243c024564002358248655363070493070499825568.09305704.00.00.00.0284.00.02313973.00.02359496.00.0262073.02097423.02349915.00.00.031.00.00.00.00.00.00.00.00.00.04194593.00.0552.00.00.0727033.02362092.00.00.02031625.00.04194524.00.02654942463.00.016335401760383163431869885241634318716820516335402271841
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561556911556914194304256001624255360x7f018cefda000x7f018c62440024564162349291655363070513070519825632.09275938.00.00.00.0298.00.02352537.00.02351893.00.0254469.02097424.02355668.00.00.031.00.00.00.00.00.00.00.00.00.04194596.00.0562.00.00.0640216.02087698.00.00.02031624.00.04194528.00.02653509966.00.016335402356360163431871968451634318737636616335402872848
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591556911556914194304256001224262400x7f018cefd8800x7f018c62444013060081204680655361632501632505224000.04695624.00.00.00.0181.00.01049248.00.01049419.00.0666.01048753.01049422.00.00.031.00.00.00.00.00.00.00.00.00.02097337.00.0346.00.00.0418240.01340208.00.00.0983048.00.02097275.00.01341933436.00.016335402957256163431874027661634318749588716335403384897
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621556911556914194304256001224269440x7f018cefd7000x7f018c62448012964721195526655361620581620585185856.04664175.00.00.00.0183.00.01049304.00.01049477.00.0721.01048756.01049484.00.00.031.00.00.00.00.00.00.00.00.00.02097344.00.0358.00.00.0455134.01459714.00.00.0983049.00.02097278.00.01434811299.00.016335403469045163431875246871634318761668816335403902545
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651556911556914194304256001224276480x7f018f6965800x7f018c6244c012941441192980655361617671617675176544.04661962.00.00.00.0182.00.01049192.00.01049364.00.0610.01048754.01049370.00.00.031.00.00.00.00.00.00.00.00.00.02097335.00.0344.00.00.0381161.01255020.00.00.0983048.00.02097278.00.01427158896.00.016335403995163163431876502881634318774164916335404426814
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681556911556914194304256001624286080x7f018f6964000x7f018c62450024441202346093655363055143055149776448.09243575.00.00.00.0289.00.02348579.00.02323319.00.0225886.02097433.02354176.00.00.031.00.00.00.00.00.00.00.00.00.04194608.00.0580.00.00.0616670.02050907.00.00.02031625.00.04194532.00.02627762075.00.016335404513312163431877920491634318797269016335405024381
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711556911556914194304256001624293120x7f018f6962800x7f018c62454024390082334980655363048753048759756000.09221029.00.00.00.0287.00.02334675.00.02343434.00.0246006.02097428.02349164.00.00.031.00.00.00.00.00.00.00.00.00.04194601.00.0568.00.00.0643821.02126938.00.00.02031625.00.04194532.00.02691244783.00.016335405108979163431879994111634318818181216335405622038
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741556911556914194304256001224300160x7f018f6961000x7f018c62458012960801197711655361620091620095184288.04687110.00.00.00.0182.00.01049248.00.01049414.00.0665.01048749.01049428.00.00.031.00.00.00.00.00.00.00.00.00.02097345.00.0362.00.00.0480842.01490124.00.00.0983049.00.02097284.00.01343969224.00.016335405706036163431882146121634318830645316335406128377
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077155691155691419430425600824309760x7f018cefdf800x7f018c6245c012838721185895655361604831604835135456.04634096.00.00.00.0189.00.01049360.00.01049533.00.0776.01048757.01049548.00.00.031.00.00.00.00.00.00.00.00.00.02097350.00.0368.00.00.0459170.01406448.00.00.0983050.00.02097288.00.01361118508.00.016335406213995163431883312531634318842229416335406636965
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801556911556914194304256001224316800x7f018cefde000x7f018c62460012914081192218655361614251614255165600.04639981.00.00.00.0184.00.01049304.00.01049470.00.0721.01048749.01049485.00.00.031.00.00.00.00.00.00.00.00.00.02097348.00.0366.00.00.0312267.0887596.00.00.0983049.00.02097276.00.01448508025.00.016335406729313163431884546141634318854629516335407144624
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831556911556914194304256001624326400x7f018cefdc800x7f018c62464024474402343870655363059293059299789728.09284243.00.00.00.0286.00.02316968.00.02353343.00.0255914.02097429.02344592.00.00.031.00.00.00.00.00.00.00.00.00.04194593.00.0550.00.00.0512989.01638402.00.00.02031626.00.04194524.00.02657950740.00.016335407230832163431885712551634318875077616335407739381
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861556911556914194304256001224336000x7f018cefdb000x7f018c62468024494962346787655363061863061869797952.09250870.00.00.00.0289.00.02340234.00.02353464.00.0256029.02097435.02338356.00.00.031.00.00.00.00.00.00.00.00.00.04194583.00.0530.00.00.0827694.02687277.00.00.02031625.00.04194526.00.02765194305.00.016335407823689163431887742961634318895461716335408332618
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891556911556914194304256001224345600x7f018cefd9800x7f018c6246c012976081199006655361622001622005190400.04671351.00.00.00.0185.00.01049360.00.01049527.00.0777.01048750.01049547.00.00.031.00.00.00.00.00.00.00.00.00.02097352.00.0372.00.00.0479959.01479656.00.00.0983049.00.02097277.00.01438335905.00.016335408417676163431889778181634318907029816335408847206
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092155691155691419430425600824355200x7f018cefd8000x7f018c62470013080161196253655361635011635015232032.04675136.00.00.00.0186.00.01049472.00.01049646.00.0888.01048758.01049662.00.00.031.00.00.00.00.00.00.00.00.00.02097348.00.0360.00.00.0487786.01546954.00.00.0983050.00.02097288.00.01387263100.00.016335408931294163431890942981634318918613916335409352585
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951556911556914194304256001224362240x7f018cefd6800x7f018c62474012966401196081655361620791620795186528.04658776.00.00.00.0175.00.01049304.00.01049475.00.0721.01048754.01049484.00.00.031.00.00.00.00.00.00.00.00.00.02097347.00.0364.00.00.0456131.01451658.00.00.0983049.00.02097284.00.01339758478.00.016335409445033163431892182991634318931046016335409862934
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981556911556914194304256001224371840x7f018f6965000x7f018c62478024303442331843655363037923037929721344.09222740.00.00.00.0303.00.02337810.00.02327268.00.0229840.02097428.02349231.00.00.031.00.00.00.00.00.00.00.00.00.04194599.00.0560.00.00.0655182.02162791.00.00.02031626.00.04194529.00.02587924749.00.016335409947292163431893346201634318951382116335410492570
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011556911556914194304256001224381440x7f018f6963800x7f018c6247c024337922330915655363042233042239735136.09198262.00.00.00.0290.00.02333817.00.02348259.00.0250824.02097435.02326470.00.00.031.00.00.00.00.00.00.00.00.00.04194605.00.0572.00.00.0699069.02306010.00.00.02031626.00.04194532.00.02674873906.00.016335410576968163431895381421634318971766316335411095697
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041556911556914194304256001224391040x7f018f6962000x7f018c62480012961921197458655361620231620235184736.04650810.00.00.00.0185.00.01049416.00.01049591.00.0832.01048759.01049604.00.00.031.00.00.00.00.00.00.00.00.00.02097350.00.0366.00.00.0545706.01691754.00.00.0983050.00.02097286.00.01369851276.00.016335411179665163431897421431634318983478416335411603655
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107155691155691419430425600824403200x7f018f6960800x7f018c62484012905681186526655361613201613205162240.04622764.00.00.00.0187.00.01049584.00.01049751.00.0999.01048752.01049768.00.00.031.00.00.00.00.00.00.00.00.00.02097353.00.0366.00.00.0341422.01195378.00.00.0983051.00.02097286.00.01371931598.00.016335411687424163431898589441634318995158416335412107374
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101556911556914194304256001224412800x7f018cefdf000x7f018c62488012991601197662655361623941623945196608.04652392.00.00.00.0180.00.01049360.00.01049533.00.0777.01048756.01049536.00.00.031.00.00.00.00.00.00.00.00.00.02097343.00.0354.00.00.0457482.01498445.00.00.0983049.00.02097284.00.01373806801.00.016335412199412163431899839051634319007558516335412620283
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131556911556914194304256001224422400x7f018cefdd800x7f018c6248c024435202341917655363054393054399774048.09246363.00.00.00.0290.00.02339461.00.02320102.00.0222681.02097421.02333856.00.00.031.00.00.00.00.00.00.00.00.00.04194601.00.0560.00.00.0699403.02267714.00.00.02031627.00.04194528.00.02563726485.00.016335412704131163431901043861634319028374716335413217580
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161556911556914194304256001224432000x7f018cefdc000x7f018c62490024462242343221655363057773057779784864.09264443.00.00.00.0281.00.02352715.00.02341614.00.0244193.02097421.02348891.00.00.031.00.00.00.00.00.00.00.00.00.04194594.00.0550.00.00.0619188.02042083.00.00.02031626.00.04194534.00.02724663205.00.016335413300538163431903072671634319048790816335413816097
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119155691155691419430425600824441600x7f018cefda800x7f018c62494012974161195003655361621761621765189632.04660874.00.00.00.0184.00.01049472.00.01049648.00.0888.01048760.01049659.00.00.031.00.00.00.00.00.00.00.00.00.02097357.00.0378.00.00.0446337.01357632.00.00.0983051.00.02097286.00.01301848535.00.016335413898935163431905127081634319060518916335414334885
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221556911556914194304256001224453760x7f018cefd9000x7f018c62498012887041188254655361610871610875154784.04600768.00.00.00.0187.00.01049640.00.01049812.00.01054.01048758.01049815.00.00.031.00.00.00.00.00.00.00.00.00.02097353.00.0364.00.00.0409172.01168871.00.00.0983052.00.02097288.00.01311017523.00.016335414421983163431906288691634319072167016335414860144
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251556911556914194304256001224463360x7f018cefd7800x7f018c6249c012914561193327655361614311614315165792.04652654.00.00.00.0184.00.01049416.00.01049590.00.0832.01048758.01049594.00.00.031.00.00.00.00.00.00.00.00.00.02097342.00.0350.00.00.0416522.01249629.00.00.0983050.00.02097284.00.01339510388.00.016335414956062163431907539901634319084599116335415383532
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281556911556914194304256001224475520x7f018cefd6000x7f018c624a0024224242319503655363028023028029689664.09166759.00.00.00.0269.00.02344002.00.02353952.00.0256519.02097433.02346715.00.00.031.00.00.00.00.00.00.00.00.00.04194585.00.0526.00.00.0769519.02485616.00.00.02031627.00.04194533.00.02871118241.00.016335415473600163431908709511634319105063216335415988409
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311556911556914194304256001224485120x7f018f6964800x7f018c624a4024062322302700655363007783007789624896.09096920.00.00.00.0243.00.02348028.00.02355672.00.0258239.02097433.02338798.00.00.031.00.00.00.00.00.00.00.00.00.04194577.00.0512.00.00.0772113.02573421.00.00.02031627.00.04194538.00.02776020321.00.016335416073627163431910741521634319125511416335416582656
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134155691155691419430425600824494720x7f018f6963000x7f018c624a8012856161183891655361607011607015142432.04631459.00.00.00.0191.00.01049472.00.01049643.00.0887.01048756.01049654.00.00.031.00.00.00.00.00.00.00.00.00.02097357.00.0378.00.00.0520842.01476430.00.00.0983051.00.02097279.00.01358119080.00.016335416665914163431912791141634319137143516335417104264
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371556911556914194304256001224506880x7f018f6961800x7f018c624ac012814241177533655361601771601775125664.04587724.00.00.00.0190.00.01049696.00.01049872.00.01109.01048763.01049884.00.00.031.00.00.00.00.00.00.00.00.00.02097357.00.0370.00.00.0391964.01169373.00.00.0983053.00.02097290.00.01359557042.00.016335417189162163431913971951634319148935516335417617743
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401556911556914194304256001224516480x7f018f6960000x7f018c624b0012914721193237655361614331614335165856.04651472.00.00.00.0189.00.01049416.00.01049592.00.0832.01048760.01049601.00.00.031.00.00.00.00.00.00.00.00.00.02097351.00.0368.00.00.0603953.01652181.00.00.0983050.00.02097283.00.01338509148.00.016335417709741163431915216761634319161287616335418133892
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431556911556914194304256001224528640x7f018cefde800x7f018c624b4024222562316447655363027813027819688992.09130432.00.00.00.0262.00.02352783.00.02342558.00.0245136.02097422.02343935.00.00.031.00.00.00.00.00.00.00.00.00.04194583.00.0520.00.00.0769516.02608080.00.00.02031628.00.04194544.00.02697417120.00.016335418218060163431916386361634319181735816335418745468
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461556911556914194304256001224540800x7f018cefdd000x7f018c624b8024149122315360655363018633018639659616.09128654.00.00.00.0261.00.02355958.00.02359305.00.0261877.02097428.02349991.00.00.031.00.00.00.00.00.00.00.00.00.04194577.00.0510.00.00.0654812.02168942.00.00.02031627.00.04194531.00.02719236515.00.016335418829326163431918421581634319202311916335419362874
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149155691155691419430425600824552960x7f018cefdb800x7f018c624bc012895841188887655361611971611975158304.04604660.00.00.00.0184.00.01049584.00.01049758.00.0999.01048759.01049771.00.00.031.00.00.00.00.00.00.00.00.00.02097354.00.0368.00.00.0457911.01437847.00.00.0983051.00.02097290.00.01338848683.00.016335419446023163431920471191634319214056016335419872453
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521556911556914194304256001224567680x7f018cefda000x7f018c624c0012893601189445655361611691611695157408.04605177.00.00.00.0187.00.01049808.00.01049984.00.01221.01048763.01049999.00.00.031.00.00.00.00.00.00.00.00.00.02097362.00.0376.00.00.0349786.01064472.00.00.0983053.00.02097299.00.01370734670.00.016335419956431163431921642401634319225704116335420385102
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551556911556914194304256001224577280x7f018cefd8800x7f018c624c4012844321185338655361605531605535137696.04621145.00.00.00.0185.00.01049528.00.01049704.00.0943.01048761.01049709.00.00.031.00.00.00.00.00.00.00.00.00.02097349.00.0360.00.00.0627621.01937427.00.00.0983051.00.02097288.00.01331677435.00.016335420476900163431922893611634319238120216335420897720
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581556911556914194304256001224589440x7f018cefd7000x7f018c624c8024119522308573655363014933014939647776.09134804.00.00.00.0256.00.02348640.00.02350376.00.0252946.02097430.02348731.00.00.031.00.00.00.00.00.00.00.00.00.04194576.00.0506.00.00.0558584.01834272.00.00.02031628.00.04194533.00.02806386392.00.016335420982888163431924055221634319258456316335421513137
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611556911556914194304256001224601600x7f018f6965800x7f018c624cc024034802304902655363004343004349613888.09102912.00.00.00.0241.00.02361629.00.02360022.00.0262594.02097428.02367266.00.00.031.00.00.00.00.00.00.00.00.00.04194580.00.0514.00.00.0686772.02309952.00.00.02031628.00.04194531.00.02747112950.00.016335421597805163431926090431634319279032516335422130133
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164155691155691419430425600824613760x7f018f6964000x7f018c624d0012941201195381655361617641617645176448.04621401.00.00.00.0192.00.01049640.00.01049810.00.01054.01048756.01049826.00.00.031.00.00.00.00.00.00.00.00.00.02097353.00.0364.00.00.0403612.01398799.00.00.0983052.00.02097288.00.01390457247.00.016335422215281163431928144851634319290728516335422655051
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671556911556914194304256001224628480x7f018f6962800x7f018c624d4013365361232646655361670661670665346112.04786270.00.00.00.0187.00.01049920.00.01050096.00.01332.01048764.01050101.00.00.031.00.00.00.00.00.00.00.00.00.02097360.00.0368.00.00.0387480.01062465.00.00.0983054.00.02097301.00.01210449144.00.016335422740490163431929324061634319302968616335423194060
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701556911556914194304256001224638080x7f018f6961000x7f018c624d8012892161187729655361611511611515156832.04635536.00.00.00.0190.00.01049528.00.01049708.00.0943.01048765.01049712.00.00.031.00.00.00.00.00.00.00.00.00.02097350.00.0362.00.00.0446967.01429288.00.00.0983051.00.02097288.00.01379991018.00.016335423287188163431930620061634319315400716335423720338
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731556911556914194304256001224650240x7f018cefdf800x7f018c624dc023910722292985655362988832988839564256.09073419.00.00.00.0267.00.02355504.00.02342469.00.0245038.02097431.02350470.00.00.031.00.00.00.00.00.00.00.00.00.04194593.00.0538.00.00.0664244.02180623.00.00.02031629.00.04194534.00.02772665580.00.016335423805566163431931810471634319336104916335424336114
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761556911556914194304256001224662400x7f018cefde000x7f018c624e0024082962304092655363010363010369633152.09134168.00.00.00.0259.00.02369162.00.02355700.00.0258287.02097413.02373848.00.00.031.00.00.00.00.00.00.00.00.00.04194556.00.0466.00.00.0699382.02298599.00.00.02031628.00.04194532.00.02772422303.00.016335424420853163431933847291634319356233016335424957271
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179155691155691419430425600824674560x7f018cefdc800x7f018c624e4012876481185713655361609551609555150560.04594260.00.00.00.0189.00.01049696.00.01049867.00.01110.01048757.01049882.00.00.031.00.00.00.00.00.00.00.00.00.02097354.00.0364.00.00.0452315.01378047.00.00.0983052.00.02097289.00.01377024122.00.016335425041639163431935890501634319368217116335425485609
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821556911556914194304256001224689280x7f018cefdb000x7f018c624e8013956721294277655361744581744585582656.05031243.00.00.00.0183.00.01049976.00.01050155.00.01387.01048768.01050155.00.00.031.00.00.00.00.00.00.00.00.00.02097357.00.0360.00.00.0323645.01015438.00.00.0983055.00.02097299.00.01085017918.00.016335425570627163431937080911634319381049216335426043957
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851556911556914194304256001224701440x7f018cefd9800x7f018c624ec012852481183464655361606551606555140960.04627736.00.00.00.0185.00.01049528.00.01049698.00.0943.01048755.01049709.00.00.031.00.00.00.00.00.00.00.00.00.02097353.00.0368.00.00.0510251.01419818.00.00.0983051.00.02097287.00.01343812580.00.016335426137125163431938428121634319393497316335426579695
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881556911556914194304256001224716160x7f018cefd8000x7f018c624f0024168322315590655363021033021039667296.09113650.00.00.00.0226.00.02327197.00.02341002.00.0243583.02097419.02355097.00.00.031.00.00.00.00.00.00.00.00.00.04194544.00.0436.00.00.0635540.02103097.00.00.02031629.00.04194519.00.02767884569.00.016335426664403163431939588131634319413945416335427187782
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911556911556914194304256001224728320x7f018cefd6800x7f018c624f4024043682296403655363005453005459617440.09062123.00.00.00.0244.00.02360227.00.02355598.00.0258185.02097413.02362594.00.00.031.00.00.00.00.00.00.00.00.00.04194565.00.0480.00.00.0607461.01975742.00.00.02031629.00.04194530.00.02786265737.00.016335427271760163431941668141634319434681616335427825588
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194155691155691419430425600824740480x7f018f6965000x7f018c624f8012817121177228655361602131602135126816.04593081.00.00.00.0190.00.01049696.00.01049862.00.01109.01048753.01049880.00.00.031.00.00.00.00.00.00.00.00.00.02097361.00.0378.00.00.0460347.01348517.00.00.0983053.00.02097284.00.01400679362.00.016335427909406163431943700161634319446297616335428358296
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971556911556914194304256001224757760x7f018f6963800x7f018c624fc014349281337757655361793651793655739680.05215168.00.00.00.0174.00.01050032.00.01050210.00.01442.01048768.01050205.00.00.031.00.00.00.00.00.00.00.00.00.02097349.00.0342.00.00.098775.0341104.00.00.0983056.00.02097297.00.01011766312.00.016335428445504163431944869771634319459241716335428900364
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001556911556914194304256001224769920x7f018f6962000x7f018c62500012831281183710655361603901603905132480.04593804.00.00.00.0190.00.01049640.00.01049816.00.01054.01048762.01049827.00.00.031.00.00.00.00.00.00.00.00.00.02097348.00.0354.00.00.0469964.01439522.00.00.0983052.00.02097287.00.01336690459.00.016335429005882163431946247381634319471721816335429429642
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031556911556914194304256001224784640x7f018f6960800x7f018c62504024049762304273655363006213006219619872.09060467.00.00.00.0225.00.02359138.00.02343880.00.0246471.02097409.02343282.00.00.031.00.00.00.00.00.00.00.00.00.04194558.00.0462.00.00.0515550.01698297.00.00.02031630.00.04194535.00.02731143008.00.016335429514331163431947410581634319492170016335430047709
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061556911556914194304256001224799360x7f018cefdf000x7f018c62508024075682305432655363009453009459630240.09105118.00.00.00.0251.00.02366473.00.02343198.00.0245767.02097431.02330911.00.00.031.00.00.00.00.00.00.00.00.00.04194564.00.0476.00.00.0676945.02224648.00.00.02031629.00.04194530.00.02747649586.00.016335430132737163431949450601634319512634116335430673325
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209155691155691419430425600824814080x7f018cefdd800x7f018c6250c012935281184942655361616901616905174080.04596507.00.00.00.0187.00.01049808.00.01049985.00.01221.01048764.01049992.00.00.031.00.00.00.00.00.00.00.00.00.02097355.00.0362.00.00.0619396.01900286.00.00.0983053.00.02097288.00.01381159155.00.016335430757853163431951501811634319524410216335431201953
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121556911556914194304256001224831360x7f018cefdc000x7f018c62510015165281418187655361895651895656066080.05487910.00.00.00.0163.00.01050144.00.01050304.00.01554.01048750.01050310.00.00.031.00.00.00.00.00.00.00.00.00.02097334.00.0308.00.00.092509.0298965.00.00.0983056.00.02097290.00.0818301928.00.016335431286701163431952673021634319537946316335431748461
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151556911556914194304256001224843520x7f018cefda800x7f018c62514012851361185155655361606411606415140512.04603425.00.00.00.0191.00.01049696.00.01049871.00.01110.01048761.01049882.00.00.031.00.00.00.00.00.00.00.00.00.02097355.00.0366.00.00.0508449.01569400.00.00.0983052.00.02097285.00.01386540951.00.016335431840619163431954255431634319551786416335432279329
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181556911556914194304256001224858240x7f018cefd9000x7f018c62518024114082312681655363014253014259645600.09100486.00.00.00.0264.00.02346234.00.02337733.00.0240301.02097432.02348585.00.00.031.00.00.00.00.00.00.00.00.00.04194574.00.0492.00.00.0549113.01824501.00.00.02031630.00.04194543.00.02794472265.00.016335432363797163431955431441634319572314516335432888476
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211556911556914194304256001224872960x7f018cefd7800x7f018c6251c023856162283149655362982012982019542432.08993265.00.00.00.0253.00.02363775.00.02344567.00.0247147.02097420.02345945.00.00.031.00.00.00.00.00.00.00.00.00.04194564.00.0474.00.00.0610537.02001289.00.00.02031630.00.04194533.00.02759324936.00.016335432972334163431957497051634319593050716335433523032
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241556911556914194304256001224887680x7f018cefd6000x7f018c62520012838881179766655361604851604855135520.04570747.00.00.00.0189.00.01049864.00.01050036.00.01276.01048760.01050050.00.00.031.00.00.00.00.00.00.00.00.00.02097358.00.0366.00.00.0580798.01861172.00.00.0983054.00.02097300.00.01308756689.00.016335433607440163431959541871634319604794816335434057470
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271556911556914194304256001224907520x7f018f6964800x7f018c62524016034561496625655362004312004316413792.05819141.00.00.00.0163.00.01050256.00.01050422.00.01665.01048757.01050413.00.00.031.00.00.00.00.00.00.00.00.00.02097335.00.0306.00.00.092567.0302746.00.00.0983057.00.02097291.00.0750792552.00.016335434148258163431960740281634319619274916335434627137
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301556911556914194304256001224919680x7f018f6963000x7f018c62528012809601178051655361601191601195123808.04581147.00.00.00.0186.00.01049696.00.01049865.00.01110.01048755.01049880.00.00.031.00.00.00.00.00.00.00.00.00.02097356.00.0368.00.00.0370349.01101456.00.00.0983052.00.02097290.00.01314117181.00.016335434720245163431962249091634319631690916335435167765
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331556911556914194304256001224934400x7f018f6961800x7f018c6252c024048322307127655363006033006039619296.09062333.00.00.00.0264.00.02351198.00.02352122.00.0254691.02097431.02365203.00.00.031.00.00.00.00.00.00.00.00.00.04194589.00.0522.00.00.0655424.02160002.00.00.02031630.00.04194534.00.02711106639.00.016335435253704163431963410701634319652123116335435785442
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361556911556914194304256001224949120x7f018f6960000x7f018c62530023801842277908655362975222975229520704.08998152.00.00.00.0258.00.02340489.00.02357995.00.0260570.02097425.02344248.00.00.031.00.00.00.00.00.00.00.00.00.04194565.00.0474.00.00.0724905.02420383.00.00.02031630.00.04194533.00.02741511643.00.016335435875400163431965460311634319672507216335436397098
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391556911556914194304256001224963840x7f018cefde800x7f018c62534012897441182132655361612171612175158944.04588807.00.00.00.0192.00.01049920.00.01050093.00.01332.01048761.01050103.00.00.031.00.00.00.00.00.00.00.00.00.02097356.00.0360.00.00.0597380.01918874.00.00.0983054.00.02097299.00.01331620880.00.016335436481257163431967497131634319684315316335436940246
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421556911556914194304256001224983680x7f018cefdd000x7f018c62538016624881562453655362078102078106649920.06104575.00.00.00.0160.00.01050312.00.01050466.00.01720.01048746.01050475.00.00.031.00.00.00.00.00.00.00.00.00.02097340.00.0314.00.00.057176.0207195.00.00.0983058.00.02097283.00.0718181742.00.016335437024765163431968677931634319699163416335437508644
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451556911556914194304256001224995840x7f018cefdb800x7f018c6253c012799361179958655361599911599915119712.04580514.00.00.00.0188.00.01049752.00.01049929.00.01165.01048764.01049939.00.00.031.00.00.00.00.00.00.00.00.00.02097352.00.0358.00.00.0670186.02003460.00.00.0983053.00.02097290.00.01383047139.00.016335437600452163431970236341634319711691516335438037742
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024815569115569141943042560012241013120x7f018cefda000x7f018c62540023839042282763655362979872979879535584.09033726.00.00.00.0246.00.02346834.00.02363084.00.0265655.02097429.02355359.00.00.031.00.00.00.00.00.00.00.00.00.04194574.00.0490.00.00.0601192.01974472.00.00.02031631.00.04194551.00.02755775772.00.016335438122690163431971409151634319731931716335438658839
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025115569115569141943042560012241027840x7f018cefd8800x7f018c62544023719522274505655362964932964939487776.08955939.00.00.00.0264.00.02340403.00.02332940.00.0235503.02097437.02360257.00.00.031.00.00.00.00.00.00.00.00.00.04194602.00.0546.00.00.0633313.02058221.00.00.02031631.00.04194547.00.02741519636.00.016335438743017163431973434771634319752363816335439274105
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025415569115569141943042560012241042560x7f018cefd7000x7f018c62548012763201177676655361595391595395105248.04592422.00.00.00.0186.00.01049920.00.01050095.00.01331.01048764.01050101.00.00.031.00.00.00.00.00.00.00.00.00.02097361.00.0370.00.00.0372899.01129986.00.00.0983055.00.02097299.00.01338219528.00.016335439358643163431975474781634319763995916335439807683
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025715569115569141943042560012241062400x7f018f6965800x7f018c6254c017341201632987655362167642167646936448.06400900.00.00.00.0151.00.01050368.00.01050525.00.01775.01048750.01050512.00.00.031.00.00.00.00.00.00.00.00.00.02097334.00.0300.00.00.041259.0163735.00.00.0983059.00.02097283.00.0711045886.00.016335439894841163431976636391634319779212016335440382300
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026015569115569141943042560012241077120x7f018f6964000x7f018c62550012744721173362655361593081593085097856.04562450.00.00.00.0186.00.01049752.00.01049924.00.01165.01048759.01049944.00.00.031.00.00.00.00.00.00.00.00.00.02097355.00.0364.00.00.0546103.01758259.00.00.0983053.00.02097288.00.01385792495.00.016335440475948163431978244401634319791692116335440913729
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026315569115569141943042560016241094400x7f018f6962800x7f018c62554023882802289373655362985342985349553088.09007212.00.00.00.0240.00.02353672.00.02354131.00.0256712.02097419.02370257.00.00.031.00.00.00.00.00.00.00.00.00.04194562.00.0462.00.00.0712839.02386849.00.00.02031632.00.04194528.00.02736324158.00.016335440999327163431979431611634319812108216335441529745
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026615569115569141943042560016241111680x7f018f6961000x7f018c62558023783362278937655362972912972919513312.08975432.00.00.00.0253.00.02355963.00.02343139.00.0245705.02097434.02355903.00.00.031.00.00.00.00.00.00.00.00.00.04194566.00.0472.00.00.0740504.02488130.00.00.02031631.00.04194531.00.02793995890.00.016335441613583163431981466821634319832572416335442145271
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691556911556914194304256008241128960x7f018cefdf800x7f018c6255c012881361189599655361610161610165152512.04597236.00.00.00.0185.00.01050032.00.01050207.00.01443.01048764.01050218.00.00.031.00.00.00.00.00.00.00.00.00.02097363.00.0370.00.00.0276399.0878295.00.00.0983055.00.02097299.00.01363558675.00.016335442232139163431983497241634319844300416335442678809
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027215569115569141943042560012241151360x7f018cefde000x7f018c62560018205041719549655362275622275627281984.06673200.00.00.00.0153.00.01050480.00.01050633.00.01887.01048746.01050628.00.00.031.00.00.00.00.00.00.00.00.00.02097332.00.0292.00.00.020592.0117125.00.00.0983059.00.02097283.00.0669064079.00.016335442762608163431984666851634319860236616335443242257
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027515569115569141943042560012241166080x7f018cefdc800x7f018c62564012763681177029655361595451595455105440.04552079.00.00.00.0190.00.01049808.00.01049986.00.01221.01048765.01049989.00.00.031.00.00.00.00.00.00.00.00.00.02097360.00.0372.00.00.0451540.01432630.00.00.0983053.00.02097292.00.01304540426.00.016335443334245163431986353261634319872860616335443776405
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027815569115569141943042560016241183360x7f018cefdb000x7f018c62568023639042264491655362954872954879455584.08910246.00.00.00.0249.00.02364511.00.02349300.00.0251869.02097431.02364643.00.00.031.00.00.00.00.00.00.00.00.00.04194571.00.0478.00.00.0747726.02490708.00.00.02031632.00.04194528.00.02765568118.00.016335443861133163431987534071634319893228816335444406901
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028115569115569141943042560016241200640x7f018cefd9800x7f018c6256c023616402262044655362952042952049446528.08926969.00.00.00.0265.00.02360459.00.02362420.00.0264997.02097423.02346673.00.00.031.00.00.00.00.00.00.00.00.00.04194583.00.0504.00.00.0910243.02984294.00.00.02031632.00.04194544.00.02781989557.00.016335444490810163431989561281634319913596916335445026678
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028415569115569141943042560012241217920x7f018cefd8000x7f018c62570013035601194724655361629441629445214208.04653219.00.00.00.0185.00.01050088.00.01050266.00.01498.01048768.01050273.00.00.031.00.00.00.00.00.00.00.00.00.02097359.00.0360.00.00.0346983.01108231.00.00.0983056.00.02097305.00.01354352893.00.016335445111556163431991586901634319925405016335445566716
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028715569115569141943042560012241240320x7f018cefd6800x7f018c62574018835841785664655362354472354477534304.06985467.00.00.00.0151.00.01050592.00.01050739.00.01998.01048741.01050741.00.00.031.00.00.00.00.00.00.00.00.00.02097336.00.0296.00.00.047257.0186818.00.00.0983060.00.02097287.00.0624466956.00.016335445651274163431992785301634319942061116335446153103
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029015569115569141943042560012241255040x7f018f6965000x7f018c62578012782881172871655361597851597855113120.04546019.00.00.00.0193.00.01049920.00.01050094.00.01332.01048762.01050110.00.00.031.00.00.00.00.00.00.00.00.00.02097363.00.0374.00.00.0491386.01485651.00.00.0983054.00.02097295.00.01350130151.00.016335446246031163431994529321634319954621216335446692931
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029315569115569141943042560012241274880x7f018f6963800x7f018c6257c023811122272933655362976382976389524416.08954714.00.00.00.0274.00.02357111.00.02343447.00.0246013.02097434.02357820.00.00.031.00.00.00.00.00.00.00.00.00.04194610.00.0552.00.00.0562852.01906479.00.00.02031633.00.04194554.00.02685025674.00.016335446778019163431995700521634319974765416335447308848
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029615569115569141943042560012241292160x7f018f6962000x7f018c62580023705442268223655362963172963179482144.08926877.00.00.00.0250.00.02379998.00.02341096.00.0243656.02097440.02363123.00.00.031.00.00.00.00.00.00.00.00.00.04194585.00.0504.00.00.0646860.02159304.00.00.02031633.00.04194536.00.02692964419.00.016335447393896163431997718141634319995133516335447926524
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029915569115569141943042560012241309440x7f018f6960800x7f018c62584013550241252014655361693771693775420064.04883327.00.00.00.0187.00.01050144.00.01050321.00.01553.01048768.01050317.00.00.031.00.00.00.00.00.00.00.00.00.02097357.00.0354.00.00.0375433.01198854.00.00.0983057.00.02097299.00.01143518809.00.016335448011692163431999761351634320007549616335448464422
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030215569115569141943042560012241334400x7f018cefdf000x7f018c62588020438721944972655362554832554838175456.07610277.00.00.00.0149.00.01050704.00.01050847.00.02108.01048739.01050847.00.00.031.00.00.00.00.00.00.00.00.00.02097333.00.0286.00.00.036965.0152148.00.00.0983062.00.02097281.00.0630902061.00.016335448548870163432000991761634320025309716335449058099
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030515569115569141943042560012241349120x7f018cefdd800x7f018c6258c012683841166661655361585471585475073504.04532226.00.00.00.0192.00.01049976.00.01050155.00.01387.01048768.01050163.00.00.031.00.00.00.00.00.00.00.00.00.02097365.00.0376.00.00.0581595.01900696.00.00.0983055.00.02097296.00.01299343808.00.016335449151047163432002852571634320037805816335449593517
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030815569115569141943042560012241368960x7f018cefdc000x7f018c62590023569442256465655362946172946179427744.08891313.00.00.00.0283.00.02347743.00.02333605.00.0236164.02097441.02364735.00.00.031.00.00.00.00.00.00.00.00.00.04194611.00.0552.00.00.0707474.02403391.00.00.02031634.00.04194548.00.02754518590.00.016335449668306163432004034981634320058222016335450198804
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031115569115569141943042560012241388800x7f018cefda800x7f018c62594023616082259153655362952002952009446400.08904165.00.00.00.0252.00.02346828.00.02345631.00.0248191.02097440.02358375.00.00.031.00.00.00.00.00.00.00.00.00.04194604.00.0538.00.00.0746594.02486081.00.00.02031634.00.04194538.00.02733692953.00.016335450284332163432006067001634320078766116335450819200
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031415569115569141943042560012241408640x7f018cefd9000x7f018c62598014137361310449655361767161767165654912.05103056.00.00.00.0173.00.01050312.00.01050481.00.01720.01048761.01050478.00.00.031.00.00.00.00.00.00.00.00.00.02097358.00.0350.00.00.0172732.0546883.00.00.0983058.00.02097303.00.0984096753.00.016335450903518163432008108611634320091454216335451361908
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031715569115569141943042560012241436160x7f018cefd7800x7f018c6259c022103682105262655362762952762958841440.08264072.00.00.00.0143.00.01050928.00.01051070.00.02331.01048739.01051075.00.00.031.00.00.00.00.00.00.00.00.00.02097335.00.0282.00.00.08733.076804.00.00.0983063.00.02097284.00.0580059050.00.016335451445666163432009393421634320110670316335451988514
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032015569115569141943042560012241453440x7f018cefd6000x7f018c625a0012768801177184655361596091596095107488.04572256.00.00.00.0184.00.01050088.00.01050268.00.01498.01048770.01050274.00.00.031.00.00.00.00.00.00.00.00.00.02097364.00.0370.00.00.0347493.01162751.00.00.0983056.00.02097305.00.01261376487.00.016335452081202163432011390241634320123278416335452523102
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032315569115569141943042560012241475840x7f018f6964800x7f018c625a4023513202250210655362939142939149405248.08820999.00.00.00.0275.00.02355847.00.02346394.00.0248962.02097432.02353443.00.00.031.00.00.00.00.00.00.00.00.00.04194615.00.0554.00.00.0630888.02126399.00.00.02031635.00.04194545.00.02660329949.00.016335452610970163432012564641634320143518616335453157428
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032615569115569141943042560012241495680x7f018f6963000x7f018c625a8023679682267746655362959952959959471840.08874553.00.00.00.0258.00.02351458.00.02346435.00.0249003.02097432.02375111.00.00.031.00.00.00.00.00.00.00.00.00.04194590.00.0506.00.00.0578306.01956250.00.00.02031635.00.04194536.00.02777557942.00.016335453242037163432014612661634320164030716335453774045
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032915569115569141943042560012241515520x7f018f6961800x7f018c625ac014662721365395655361832831832835865056.05351679.00.00.00.0155.00.01050368.00.01050527.00.01775.01048752.01050526.00.00.031.00.00.00.00.00.00.00.00.00.02097337.00.0306.00.00.073844.0269280.00.00.0983059.00.02097286.00.0794612826.00.016335453859103163432016644671634320177278816335454328372
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033215569115569141943042560012241543040x7f018f6960000x7f018c625b0023795362278361655362974412974419518112.08838217.00.00.00.0139.00.01051040.00.01051180.00.02441.01048739.01051188.00.00.031.00.00.00.00.00.00.00.00.00.02097338.00.0284.00.00.035998.0148356.00.00.0983065.00.02097277.00.0593006806.00.016335454414711163432017974281634320197662916335454942259
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033515569115569141943042560012241562880x7f018cefde800x7f018c625b4013527201255682655361690891690895410848.04893593.00.00.00.0180.00.01050200.00.01050372.00.01609.01048763.01050375.00.00.031.00.00.00.00.00.00.00.00.00.02097359.00.0356.00.00.0319270.01020236.00.00.0983057.00.02097302.00.01086930983.00.016335455034467163432020092701634320210959016335455486487
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033815569115569141943042560012241587840x7f018cefdd000x7f018c625b8023579522255710655362947432947439431776.08895051.00.00.00.0306.00.02339628.00.02352181.00.0254736.02097445.02337520.00.00.031.00.00.00.00.00.00.00.00.00.04194636.00.0588.00.00.0631818.02144591.00.00.02031637.00.04194568.00.02657833881.00.016335455571055163432021358311634320231727216335456105133
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034115569115569141943042560012241610240x7f018cefdb800x7f018c625bc023803682268567655362975452975459521440.08953998.00.00.00.0285.00.02353571.00.02347603.00.0250157.02097446.02354845.00.00.031.00.00.00.00.00.00.00.00.00.04194617.00.0552.00.00.0839369.02765571.00.00.02031637.00.04194556.00.02732959599.00.016335456188622163432023407921634320252447316335456729360
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034415569115569141943042560012241632640x7f018cefda000x7f018c625c0016299841530765655362037472037476519904.05986909.00.00.00.0152.00.01050592.00.01050750.00.01997.01048753.01050752.00.00.031.00.00.00.00.00.00.00.00.00.02097343.00.0310.00.00.0105866.0346048.00.00.0983061.00.02097284.00.0767037810.00.016335456812808163432025491131634320266991416335457285137
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034715569115569141943042560012241665280x7f018cefd8800x7f018c625c40269788825970706553633723533723510791520.010029324.00.00.00.0141.00.01051376.00.01051512.00.02774.01048738.01051520.00.00.031.00.00.00.00.00.00.00.00.00.02097338.00.0272.00.00.022608.0130169.00.00.0983068.00.02097280.00.0611721893.00.016335457368876163432026935951634320289759616335457933833
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035015569115569141943042560012241685120x7f018cefd7000x7f018c625c8014579041355383655361822371822375831584.05281815.00.00.00.0162.00.01050424.00.01050582.00.01831.01048751.01050587.00.00.031.00.00.00.00.00.00.00.00.00.02097349.00.0328.00.00.0114132.0375590.00.00.0983059.00.02097294.00.0857503887.00.016335458014541163432029425561634320305119716335458484801
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035315569115569141943042560012241712640x7f018f6965800x7f018c625cc023529122246428655362941132941139411616.08869216.00.00.00.0299.00.02359903.00.02338414.00.0240958.02097456.02354968.00.00.031.00.00.00.00.00.00.00.00.00.04194639.00.0588.00.00.0926515.03103520.00.00.02031639.00.04194571.00.02712580586.00.016335458569779163432030766371634320325983916335459109377
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035615569115569141943042560012241737600x7f018f6964000x7f018c625d0023559362253675655362944912944919423712.08871074.00.00.00.0304.00.02365952.00.02334523.00.0237070.02097453.02349671.00.00.031.00.00.00.00.00.00.00.00.00.04194648.00.0606.00.00.0874156.02987806.00.00.02031639.00.04194567.00.02717762020.00.016335459194555163432032839991634320346640016335459735683
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035915569115569141943042560012241762560x7f018f6962800x7f018c625d4017722321673094655362215282215287088896.06555747.00.00.00.0148.00.01050816.00.01050970.00.02219.01048751.01050956.00.00.031.00.00.00.00.00.00.00.00.00.02097335.00.0286.00.00.067591.0243949.00.00.0983063.00.02097291.00.0610741944.00.016335459820542163432034913601634320362384116335460322991
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036215569115569141943042560012241797760x7f018f6961000x7f018c625d80301140829132436553637642537642512045600.011300099.00.00.00.0143.00.01051712.00.01051850.00.03107.01048743.01051850.00.00.031.00.00.00.00.00.00.00.00.00.02097347.00.0278.00.00.019514.0116548.00.00.0983071.00.02097294.00.0602255841.00.016335460407639163432036472011634320387776316335461007135
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036515569115569141943042560012241822720x7f018cefdf800x7f018c625dc016781121577333655362097632097636712416.06163908.00.00.00.0154.00.01050704.00.01050853.00.02108.01048745.01050861.00.00.031.00.00.00.00.00.00.00.00.00.02097335.00.0290.00.00.030573.0141158.00.00.0983062.00.02097281.00.0665520323.00.016335461089804163432039227231634320404768416335461563603
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036815569115569141943042560012241855360x7f018cefde000x7f018c625e0024796962363758655363099613099619918752.09316657.00.00.00.0296.00.02286876.00.02282647.00.0185180.02097467.02290024.00.00.031.00.00.00.00.00.00.00.00.00.04194635.00.0562.00.00.0503931.01679154.00.00.02031643.00.04194585.00.02421278669.00.016335461647851163432040716841634320426240616335462210069
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037115569115569141943042560012241885440x7f018cefdc800x7f018c625e4024948002348422655363118493118499979168.09325174.00.00.00.0287.00.02258503.00.02276572.00.0179116.02097456.02263130.00.00.031.00.00.00.00.00.00.00.00.00.04194625.00.0544.00.00.0681581.02244763.00.00.02031643.00.04194579.00.02435752980.00.016335462282687163432042867261634320447824716335462855045
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037415569115569141943042560012241915520x7f018cefdb000x7f018c625e8021035522002944655362629432629438414176.07772103.00.00.00.0155.00.01051264.00.01051422.00.02663.01048759.01051399.00.00.031.00.00.00.00.00.00.00.00.00.02097357.00.0314.00.00.014230.096299.00.00.0983067.00.02097285.00.0604310455.00.016335462928553163432045014471634320465920816335463434342
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037715569115569141943042560012241958400x7f018cefd9800x7f018c625ec0367172835633816553645896545896514686880.013726578.00.00.00.0139.00.01052328.00.01052468.00.03718.01048750.01052466.00.00.031.00.00.00.00.00.00.00.00.00.02097359.00.0280.00.00.019078.0103225.00.00.0983076.00.02097299.00.0584868095.00.016335463517950163432046833691634320496497116335464161496
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038015569115569141943042560012241985920x7f018cefd8000x7f018c625f0019303361834372655362412912412917721312.07083682.00.00.00.0147.00.01051096.00.01051241.00.02497.01048744.01051250.00.00.031.00.00.00.00.00.00.00.00.00.02097352.00.0310.00.00.061221.0229019.00.00.0983065.00.02097290.00.0625191932.00.016335464243774163432050088111634320515505216335464744453
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038315569115569141943042560012242023680x7f018cefd6800x7f018c625f40267568825624696553633446033446010702720.010064280.00.00.00.0272.00.02253881.00.02250095.00.0152650.02097445.02254422.00.00.031.00.00.00.00.00.00.00.00.00.04194632.00.0542.00.00.0402845.01360057.00.00.02031647.00.04194585.00.02254708891.00.016335464828191163432051808121634320539041416335465402578
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038615569115569141943042560012242058880x7f018f6965000x7f018c625f80264778425239476553633097233097210591104.09964686.00.00.00.0268.00.02206580.00.02228388.00.0130944.02097444.02228194.00.00.031.00.00.00.00.00.00.00.00.00.04194619.00.0516.00.00.0403695.01331922.00.00.02031647.00.04194574.00.02085977074.00.016335465477157163432054275341634320563873516335466051664
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038915569115569141943042560012242094080x7f018f6963800x7f018c625fc024275042325567655363034373034379709984.09025450.00.00.00.0151.00.01051712.00.01051876.00.03107.01048769.01051870.00.00.031.00.00.00.00.00.00.00.00.00.02097364.00.0312.00.00.018271.0102787.00.00.0983071.00.02097298.00.0597126308.00.016335466127382163432056745761634320585825716335466666860
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039215569115569141943042560012242144640x7f018f6962000x7f018c626000431040842080486553653880053880017241600.016047169.00.00.00.0132.00.01053000.00.01053141.00.04384.01048757.01053137.00.00.031.00.00.00.00.00.00.00.00.00.02097366.00.0270.00.00.010840.085214.00.00.0983082.00.02097311.00.0595344737.00.016335466751508163432058833771634320621649916335467445233
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039515569115569141943042560012242177280x7f018f6960800x7f018c62604021431842043013655362678972678978572704.08005168.00.00.00.0149.00.01051432.00.01051578.00.02830.01048748.01051587.00.00.031.00.00.00.00.00.00.00.00.00.02097344.00.0282.00.00.021221.0123948.00.00.0983068.00.02097294.00.0592333582.00.016335467527651163432062889801634320645314116335468031790
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039815569115569141943042560012242220160x7f018cefdf000x7f018c626080292871228116566553636608836608811714816.011036253.00.00.00.0268.00.02207062.00.02203090.00.0105652.02097438.02210462.00.00.031.00.00.00.00.00.00.00.00.00.04194615.00.0490.00.00.0197254.0644760.00.00.02031651.00.04194568.00.01999411729.00.016335468116158163432064785811634320670914316335468708615
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040115569115569141943042560012242260480x7f018cefdd800x7f018c6260c0293341628227776553636667636667611733632.011102535.00.00.00.0234.00.02180935.00.02168781.00.071370.02097411.02185028.00.00.031.00.00.00.00.00.00.00.00.00.04194601.00.0464.00.00.0346357.01110499.00.00.02031651.00.04194543.00.01579289907.00.016335468783724163432067685031634320699698516335469384550
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040415569115569141943042560012242300800x7f018cefdc000x7f018c626100275323226537806553634415334415311012896.010233468.00.00.00.0166.00.01052160.00.01052316.00.03551.01048765.01052322.00.00.031.00.00.00.00.00.00.00.00.00.02097371.00.0310.00.00.024187.0124944.00.00.0983075.00.02097291.00.0571918389.00.016335469458849163432070574651634320726738716335470031186
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040715569115569141943042560012242359040x7f018cefda800x7f018c626140495012848470696553661876561876519800480.018636877.00.00.00.0135.00.01053672.00.01053812.00.05050.01048762.01053802.00.00.031.00.00.00.00.00.00.00.00.00.02097380.00.0274.00.00.045388.0176927.00.00.0983088.00.02097318.00.0583829686.00.016335470105405163432073265871634320770931016335470857458
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041015569115569141943042560012242394240x7f018cefd9000x7f018c62618024002162302211655363000263000269600832.08951115.00.00.00.0146.00.01051768.00.01051911.00.03163.01048748.01051904.00.00.031.00.00.00.00.00.00.00.00.00.02097352.00.0286.00.00.029332.0146596.00.00.0983071.00.02097301.00.0598496753.00.016335470938826163432077739501634320795859216335471469184
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041315569115569141943042560012242442240x7f018cefd7800x7f018c6261c0320521630884136553640065140065112820832.012044811.00.00.00.0238.00.02184323.00.02181713.00.084297.02097416.02192961.00.00.031.00.00.00.00.00.00.00.00.00.04194609.00.0464.00.00.0244062.0806146.00.00.02031655.00.04194562.00.01714570046.00.016335471554062163432079830721634320823571416335472190768
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041615569115569141943042560012242487680x7f018cefd6000x7f018c626200310761630044006553638845138845112430432.011834374.00.00.00.0237.00.02116842.00.02114195.00.016790.02097405.02114907.00.00.031.00.00.00.00.00.00.00.00.00.04194600.00.0446.00.00.026130.0130433.00.00.02031655.00.04194542.00.01268335523.00.016335472243047163432082947541634320854083616335472852174
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041915569115569141943042560012242533120x7f018f6964800x7f018c626240307592029754896553638448938448912303648.011473901.00.00.00.0169.00.01052552.00.01052712.00.03940.01048772.01052708.00.00.031.00.00.00.00.00.00.00.00.00.02097378.00.0310.00.00.022525.0123606.00.00.0983078.00.02097316.00.0681809532.00.016335472925532163432086035561634320883907816335473542618
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221556911556914194304256008242555520x7f018f6963000x7f018c626280570864055988866553671357971357922834528.020998694.00.00.00.0133.00.01050536.00.01050669.00.01942.01048727.01050666.00.00.031.00.00.00.00.00.00.00.00.00.02097316.00.0258.00.00.00.056957.00.00.0983060.00.02097263.00.0540998528.00.016335473617287163432088777981634320932740116335474457118
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042515569115569141943042560012242598400x7f018f6961800x7f018c6262c0288320027800596553636039936039911532768.010849050.00.00.00.0138.00.01052440.00.01052581.00.03829.01048752.01052581.00.00.031.00.00.00.00.00.00.00.00.00.02097365.00.0288.00.00.033005.0148726.00.00.0983077.00.02097312.00.0583580990.00.016335474518217163432093714021634320959460316335475096194
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042815569115569141943042560012242656640x7f018f6960000x7f018c626300374852836482196553646856546856514994080.014284334.00.00.00.0253.00.02114071.00.02114149.00.016715.02097434.02114292.00.00.031.00.00.00.00.00.00.00.00.00.04194620.00.0454.00.00.019616.0112160.00.00.02031663.00.04194581.00.01191833321.00.016335475171162163432096282041634320992660616335475841328
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043115569115569141943042560012242712320x7f018cefde800x7f018c626340377232836712126553647154047154015089280.014320594.00.00.00.0217.00.02135063.00.02143669.00.046257.02097412.02141955.00.00.031.00.00.00.00.00.00.00.00.00.04194608.00.0430.00.00.055134.0221617.00.00.02031663.00.04194558.00.01405720458.00.016335475915526163432099619661634321025892816335476574082
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341556911556914194304256008242732160x7f018cefdd000x7f018c626380382524837214526553647815547815515300960.014569687.00.00.00.0144.00.01050312.00.01050459.00.01720.01048739.01050461.00.00.031.00.00.00.00.00.00.00.00.00.02097327.00.0288.00.00.00.059062.00.00.0983058.00.02097274.00.0546229919.00.016335476648300163432103222881634321061605016335477303476
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371556911556914194304256008242757120x7f018cefdb800x7f018c6263c0699257668923456553687407187407127970272.023743395.00.00.00.0132.00.01050872.00.01051004.00.02275.01048729.01051008.00.00.031.00.00.00.00.00.00.00.00.00.02097321.00.0256.00.00.00.056819.00.00.0983063.00.02097276.00.0544584404.00.016335477381074163432106800511634321123349516335478298334
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044015569115569141943042560012242807680x7f018cefda000x7f018c626400338614432825266553642326742326713544544.012755696.00.00.00.0167.00.01053000.00.01053162.00.04384.01048778.01053151.00.00.031.00.00.00.00.00.00.00.00.00.02097376.00.0290.00.00.028740.0135799.00.00.0983082.00.02097315.00.0574018067.00.016335478386152163432113013351634321156309716335479015688
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044315569115569141943042560012242876160x7f018cefd8800x7f018c626440440893643093676553655111655111617635712.016754694.00.00.00.0209.00.02133768.00.02128831.00.031417.02097414.02127435.00.00.031.00.00.00.00.00.00.00.00.00.04194616.00.0412.00.00.060910.0238301.00.00.02031671.00.04194557.00.01267091388.00.016335479090036163432116232581634321197398016335479807430
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044615569115569141943042560012242942080x7f018cefd7000x7f018c626480441369643104956553655171155171117654752.016853907.00.00.00.0217.00.02126153.00.02132145.00.034726.02097419.02123436.00.00.031.00.00.00.00.00.00.00.00.00.04194622.00.0426.00.00.019171.0108471.00.00.02031671.00.04194562.00.01214145549.00.016335479879229163432120347811634321238502316335480591313
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491556911556914194304256008242969600x7f018f6965800x7f018c6264c0447238443640366553655904755904717889504.016894584.00.00.00.0149.00.01050984.00.01051131.00.02386.01048745.01051126.00.00.031.00.00.00.00.00.00.00.00.00.02097337.00.0284.00.00.00.046232.00.00.0983064.00.02097280.00.0547134066.00.016335480665872163432124456631634321279046616335481374546
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521556911556914194304256008242999680x7f018f6964000x7f018c62650082925528187808655361036568103656833170176.027704762.00.00.00.0135.00.01051208.00.01051343.00.02608.01048735.01051342.00.00.031.00.00.00.00.00.00.00.00.00.02097329.00.0260.00.00.00.056332.00.00.0983066.00.02097276.00.0551120229.00.016335481449084163432128530261634321350983116335482473492
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551556911556914194304256008243027200x7f018f6962800x7f018c626540572320856241376553671540071540022892800.020352242.00.00.00.0141.00.01050984.00.01051120.00.02386.01048734.01051121.00.00.031.00.00.00.00.00.00.00.00.00.02097331.00.0272.00.00.00.057546.00.00.0983064.00.02097275.00.0551637959.00.016335482551970163432135759111634321401911516335483379022
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045815569115569141943042560012243054720x7f018f6961000x7f018c626580573929656374606553671741171741122957152.022331469.00.00.00.0218.00.02099728.00.02099883.00.02497.02097386.02099841.00.00.031.00.00.00.00.00.00.00.00.00.04194561.00.0426.00.00.0101.058514.00.00.02031640.00.04194508.00.01072898615.00.016335483428581163432140527151634321451335816335484275882
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046115569115569141943042560012243082240x7f018cefdf800x7f018c6265c0574152056303136553671768971768922966048.022327511.00.00.00.0201.00.02099813.00.02099901.00.02514.02097387.02099855.00.00.031.00.00.00.00.00.00.00.00.00.04194546.00.0398.00.00.00.053618.00.00.02031640.00.04194501.00.01078955744.00.016335484324741163432145754381634321503288216335485174342
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641556911556914194304256008243109760x7f018cefde000x7f018c626600575888056568466553671985971985923035488.020298031.00.00.00.0138.00.01051040.00.01051177.00.02442.01048735.01051181.00.00.031.00.00.00.00.00.00.00.00.00.02097331.00.0270.00.00.00.055121.00.00.0983064.00.02097277.00.0551271977.00.016335485225131163432150938421634321554264516335486039483
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671556911556914194304256008243132160x7f018cefdc800x7f018c6266401089383210782915655361361728136172843575296.034954056.00.00.00.0131.00.01050536.00.01050667.00.01942.01048725.01050666.00.00.031.00.00.00.00.00.00.00.00.00.02097317.00.0260.00.00.00.057346.00.00.0983060.00.02097262.00.0552426509.00.016335486113851163432156013661634321646585216335487386553
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701556911556914194304256008243159680x7f018cefdb000x7f018c6266801092593610818975655361365741136574143703712.031612301.00.00.00.0129.00.01050984.00.01051114.00.02386.01048728.01051113.00.00.031.00.00.00.00.00.00.00.00.00.02097327.00.0264.00.00.00.057353.00.00.0983064.00.02097270.00.0564768947.00.016335487442492163432165328921634321738249816335488673745
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047315569115569141943042560012243187200x7f018cefd9800x7f018c6266c01093895210829774655361367368136736843755776.041944228.00.00.00.0203.00.02099616.00.02099884.00.02509.02097375.02099826.00.00.031.00.00.00.00.00.00.00.00.00.04194549.00.0402.00.00.00.054672.00.00.02031640.00.04194490.00.01068994226.00.016335488724564163432174420191634321832282516335489968656
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047615569115569141943042560012243214720x7f018cefd8000x7f018c6267001091993610813901655361364991136499143679712.041539879.00.00.00.0202.00.02099563.00.02099882.00.02512.02097370.02099797.00.00.031.00.00.00.00.00.00.00.00.00.04194549.00.0404.00.00.00.056479.00.00.02031640.00.04194499.00.01076339238.00.016335490042885163432184111461634321928715216335491330706
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791556911556914194304256008243242240x7f018cefd6800x7f018c6267401095922410853241655361369902136990243836864.033246890.00.00.00.0136.00.01051040.00.01051173.00.02442.01048731.01051171.00.00.031.00.00.00.00.00.00.00.00.00.02097325.00.0258.00.00.00.055706.00.00.0983064.00.02097273.00.0560286189.00.016335491376025163432193602721634322021563816335492705066
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821556911556914194304256008243264640x7f018f6965000x7f018c6267802125267221153651655362656583265658385010656.043019490.00.00.00.0132.00.01050536.00.01050667.00.01942.01048725.01050666.00.00.031.00.00.00.00.00.00.00.00.00.02097313.00.0252.00.00.00.057196.00.00.0983060.00.02097260.00.0573803565.00.016335492748745163432202809191634322197597116335494870818
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851556911556914194304256008243292160x7f018f6963800x7f018c6267c02131292821199322655362664115266411585251680.050086710.00.00.00.0136.00.01050984.00.01051119.00.02386.01048733.01051121.00.00.031.00.00.00.00.00.00.00.00.00.02097327.00.0264.00.00.00.057829.00.00.0983064.00.02097277.00.0579973622.00.016335494924027163432220689311634322373054316335497015231
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048815569115569141943042560012243319680x7f018f6962000x7f018c6268002131692021208144655362664614266461485267648.074237825.00.00.00.0211.00.02099666.00.02099866.00.02484.02097382.02099875.00.00.031.00.00.00.00.00.00.00.00.00.04194549.00.0402.00.00.0137.050844.00.00.02031640.00.04194497.00.01086295391.00.016335497061120163432238510241634322557151616335499218852
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049115569115569141943042560012243347200x7f018f6960800x7f018c6268402131040821195639655362663800266380085241600.076556583.00.00.00.0218.00.02099560.00.02099921.00.02539.02097382.02099778.00.00.031.00.00.00.00.00.00.00.00.00.04194551.00.0408.00.00.00.052865.00.00.02031640.00.04194505.00.01090860108.00.016335499264821163432256598371634322737136916335501413974
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941556911556914194304256008243374720x7f018cefdf000x7f018c6268802133744821228961655362667180266718085349760.047910185.00.00.00.0136.00.01051040.00.01051178.00.02442.01048736.01051174.00.00.031.00.00.00.00.00.00.00.00.00.02097327.00.0262.00.00.00.056766.00.00.0983064.00.02097274.00.0579819417.00.016335501458583163432274737701634322914290116335503561746
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049715569115569141943042560082400x7f018cefdd800x7f018c6268c042011104418986746553652513875251387168044384.067346023.00.00.00.0133.00.01050536.00.01050667.00.01942.01048725.01050668.00.00.031.00.00.00.00.00.00.00.00.00.02097314.00.0254.00.00.00.057065.00.00.0983060.00.02097263.00.0586053045.00.016335503606755163432292277021634323258196616335507392682