파일
rocm-systems/tests/workloads/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.kd000154513154513335544322560043241600x00x7fbb0a2042803076816299146252428838460138460112307232.09403842.00.00.056.0303.00.04194696.00.04195052.00.02097594.02097458.0750.04194304.00.02064387.04128768.04128768.00.01472185.00.00.01492792.00.00.0311.00.0606.00.00.00.0200953.02064384.00.02031623.00.0141.04128768.0989215.01616374412.016299483631972163075553322281630755557127016299629181928
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00215451315451332768256001224138880x00x7fbb0a223f8026829616835051233536335361073152.0397446.00.00.00.060.00.04600.00.04659.00.0499.04160.04660.00.00.031.00.00.00.00.00.00.00.00.00.08260.00.0118.00.00.00.052775.00.00.00.00.08205.00.03274341.00.016299634449212163075603652181630756037833816299634704877
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051545131545134194304256001224143360x7fbb0cfbe3800x7fbb0a223fc013222401212884655361652791652795288928.04735777.00.00.00.0186.00.01048968.00.01049151.00.0388.01048763.01049143.00.00.031.00.00.00.00.00.00.00.00.00.02097344.00.0370.00.00.0499659.01573706.00.00.0983046.00.02097289.00.01443042619.00.016299634791785163075604468191630756053897916299635362512
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081545131545134194304256001624150400x7fbb0cfbe2000x7fbb0a22400024736962367603655363092113092119894752.09337510.00.00.00.0275.00.02364871.00.02329721.00.0232287.02097434.02346001.00.00.031.00.00.00.00.00.00.00.00.00.04194589.00.0550.00.00.0679266.02202576.00.00.02031623.00.04194532.00.02665347199.00.016299635450850163075605733791630756075402116299636052187
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111545131545134194304256001624154880x7fbb0cfbe0800x7fbb0a224040250121623915096553631265131265110004832.09412810.00.00.00.0286.00.02352793.00.02335865.00.0238423.02097442.02345685.00.00.031.00.00.00.00.00.00.00.00.00.04194604.00.0584.00.00.0756343.02521712.00.00.02031622.00.04194542.00.02632669176.00.016299636135665163075607801011630756095946216299636719382
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141545131545134194304256001224159360x7fbb0abd5f000x7fbb0a22408013260161214158655361657511657515304032.04732047.00.00.00.0183.00.01049080.00.01049260.00.0499.01048761.01049259.00.00.031.00.00.00.00.00.00.00.00.00.02097343.00.0364.00.00.0450643.01360669.00.00.0983047.00.02097287.00.01458084742.00.016299636804230163075609845821630756107802316299637287309
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171545131545134194304256001224163840x7fbb0abd5d800x7fbb0a2240c013193121212991655361649131649135277216.04751018.00.00.00.0184.00.01049024.00.01049210.00.0443.01048767.01049205.00.00.031.00.00.00.00.00.00.00.00.00.02097342.00.0364.00.00.0542005.01515556.00.00.0983047.00.02097291.00.01475520748.00.016299637370808163075611042631630756119610316299637855117
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201545131545134194304256001224170880x7fbb0abd5c000x7fbb0a22410013091281208958655361636401636405236480.04708621.00.00.00.0174.00.01049080.00.01049259.00.0499.01048760.01049264.00.00.031.00.00.00.00.00.00.00.00.00.02097339.00.0356.00.00.0459585.01500071.00.00.0983047.00.02097287.00.01436792959.00.016299637951545163075612356241630756132794416299638373625
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231545131545134194304256001624177920x7fbb0abd5a800x7fbb0a22414024875362377128655363109413109419950112.09342452.00.00.00.0277.00.02340477.00.02344518.00.0247098.02097420.02351312.00.00.031.00.00.00.00.00.00.00.00.00.04194585.00.0540.00.00.0834873.02684914.00.00.02031624.00.04194533.00.02657291165.00.016299638458083163075613671441630756154682516299638972702
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261545131545134194304256001624184960x7fbb0abd59000x7fbb0a22418024672802358908655363084093084099869088.09295907.00.00.00.0281.00.02351419.00.02357762.00.0260325.02097437.02343706.00.00.031.00.00.00.00.00.00.00.00.00.04194587.00.0546.00.00.0728732.02359515.00.00.02031623.00.04194526.00.02813070859.00.016299639057450163075615733861630756175242716299639583119
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291545131545134194304256001624192000x7fbb0abd57800x7fbb0a2241c013163681216014655361645451645455265440.04700847.00.00.00.0183.00.01049136.00.01049321.00.0555.01048766.01049318.00.00.031.00.00.00.00.00.00.00.00.00.02097339.00.0354.00.00.0345780.01045812.00.00.0983047.00.02097284.00.01417531860.00.016299639667507163075617855471630756187914716299640080178
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321545131545134194304256001624199040x7fbb0abd56000x7fbb0a22420013217281217445655361652151652155286880.04690378.00.00.00.0186.00.01049136.00.01049316.00.0555.01048761.01049321.00.00.031.00.00.00.00.00.00.00.00.00.02097345.00.0366.00.00.0544471.01687814.00.00.0983047.00.02097283.00.01416511405.00.016299640164186163075619113081630756200490816299640578827
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351545131545134194304256001224206080x7fbb0cfbe4800x7fbb0a22424013067361202743655361633411633415226912.04655894.00.00.00.0182.00.01049136.00.01049312.00.0555.01048757.01049312.00.00.031.00.00.00.00.00.00.00.00.00.02097343.00.0362.00.00.0483919.01478150.00.00.0983047.00.02097291.00.01491731786.00.016299640671575163075620370681630756213002916299641078256
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381545131545134194304256001624213120x7fbb0cfbe3000x7fbb0a22428024793922377365655363099233099239917536.09364204.00.00.00.0268.00.02329651.00.02342460.00.0245015.02097445.02324839.00.00.031.00.00.00.00.00.00.00.00.00.04194600.00.0568.00.00.0694791.02286993.00.00.02031624.00.04194546.00.02586317556.00.016299641163544163075621594691630756233851016299641664483
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411545131545134194304256001624220160x7fbb0cfbe1800x7fbb0a2242c024662002359720655363082743082749864768.09272801.00.00.00.0278.00.02364198.00.02341316.00.0243885.02097431.02360349.00.00.031.00.00.00.00.00.00.00.00.00.04194579.00.0528.00.00.0663230.02242861.00.00.02031624.00.04194530.00.02714445798.00.016299641749591163075623637901630756254331216299642258970
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441545131545134194304256001624227200x7fbb0cfbe0000x7fbb0a22430013227041211087655361653371653375290784.04698257.00.00.00.0183.00.01049192.00.01049376.00.0610.01048766.01049375.00.00.031.00.00.00.00.00.00.00.00.00.02097344.00.0362.00.00.0357008.01160192.00.00.0983048.00.02097293.00.01447906067.00.016299642345208163075625783521630756267275216299642762049
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471545131545134194304256001224234240x7fbb0abd5e800x7fbb0a22434013099841208796655361637471637475239904.04688700.00.00.00.0183.00.01049248.00.01049428.00.0666.01048762.01049429.00.00.031.00.00.00.00.00.00.00.00.00.02097345.00.0362.00.00.0544720.01652209.00.00.0983048.00.02097288.00.01435838326.00.016299642846277163075627017131630756279451316299643255818
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501545131545134194304256001224241280x7fbb0abd5d000x7fbb0a22438013135921209562655361641981641985254336.04713456.00.00.00.0178.00.01049192.00.01049371.00.0610.01048761.01049369.00.00.031.00.00.00.00.00.00.00.00.00.02097343.00.0360.00.00.0490736.01545103.00.00.0983048.00.02097289.00.01430348646.00.016299643348666163075628284331630756292219416299643755117
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531545131545134194304256001624248320x7fbb0abd5b800x7fbb0a2243c024711922366019655363088983088989884736.09314207.00.00.00.0275.00.02340950.00.02342230.00.0244795.02097435.02360699.00.00.031.00.00.00.00.00.00.00.00.00.04194581.00.0528.00.00.0729779.02382406.00.00.02031625.00.04194537.00.02761895047.00.016299643839865163075629522741630756313115516299644337014
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561545131545134194304256001624255360x7fbb0abd5a000x7fbb0a22440024637202356011655363079643079649854848.09273743.00.00.00.0279.00.02347391.00.02371210.00.0273801.02097409.02338762.00.00.031.00.00.00.00.00.00.00.00.00.04194581.00.0532.00.00.0662347.02184703.00.00.02031624.00.04194542.00.02800166439.00.016299644421462163075631620351630756334219616299644919481
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591545131545134194304256001224262400x7fbb0abd58800x7fbb0a22444013151761208187655361643961643965260672.04675140.00.00.00.0185.00.01049248.00.01049429.00.0666.01048763.01049424.00.00.031.00.00.00.00.00.00.00.00.00.02097345.00.0362.00.00.0496319.01572274.00.00.0983048.00.02097291.00.01391427562.00.016299645003959163075633687571630756346203716299645427320
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621545131545134194304256001224269440x7fbb0abd57000x7fbb0a22448013060881204635655361632601632605224320.04682187.00.00.00.0186.00.01049304.00.01049487.00.0721.01048766.01049488.00.00.031.00.00.00.00.00.00.00.00.00.02097350.00.0370.00.00.0523819.01674681.00.00.0983049.00.02097288.00.01362289018.00.016299645511768163075634941971630756358795816299645933648
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651545131545134194304256001224276480x7fbb0cfbe5800x7fbb0a2244c013037921203564655361629731629735215136.04676149.00.00.00.0181.00.01049192.00.01049370.00.0610.01048760.01049374.00.00.031.00.00.00.00.00.00.00.00.00.02097349.00.0372.00.00.0553893.01698209.00.00.0983048.00.02097289.00.01385606040.00.016299646026106163075636223581630756371419916299646436537
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681545131545134194304256001624286080x7fbb0cfbe4000x7fbb0a22450024700642365548655363087573087579880224.09281799.00.00.00.0275.00.02345934.00.02352726.00.0255282.02097444.02351572.00.00.031.00.00.00.00.00.00.00.00.00.04194597.00.0558.00.00.0835368.02799063.00.00.02031625.00.04194533.00.02604854370.00.016299646521655163075637644391630756394284016299647025334
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711545131545134194304256001624293120x7fbb0cfbe2800x7fbb0a22454024536882347618655363067103067109814720.09227539.00.00.00.0251.00.02371361.00.02355335.00.0257910.02097425.02346710.00.00.031.00.00.00.00.00.00.00.00.00.04194587.00.0540.00.00.0788490.02578406.00.00.02031625.00.04194522.00.02826632402.00.016299647110302163075639692401630756414892116299647610711
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741545131545134194304256001224300160x7fbb0cfbe1000x7fbb0a22458013004721200046655361625581625585201856.04683584.00.00.00.0182.00.01049248.00.01049432.00.0665.01048767.01049427.00.00.031.00.00.00.00.00.00.00.00.00.02097342.00.0356.00.00.0412481.01212400.00.00.0983049.00.02097291.00.01388419700.00.016299647695770163075641841221630756427612216299648110120
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077154513154513419430425600824309760x7fbb0abd5f800x7fbb0a2245c013067841202151655361633471633475227104.04672926.00.00.00.0190.00.01049360.00.01049547.00.0776.01048771.01049544.00.00.031.00.00.00.00.00.00.00.00.00.02097347.00.0362.00.00.0563054.01707934.00.00.0983050.00.02097297.00.01400855381.00.016299648196208163075643095621630756440204316299648612549
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801545131545134194304256001224316800x7fbb0abd5e000x7fbb0a22460013060481201303655361632551632555224160.04674595.00.00.00.0182.00.01049304.00.01049486.00.0721.01048765.01049482.00.00.031.00.00.00.00.00.00.00.00.00.02097344.00.0358.00.00.0552302.01640431.00.00.0983049.00.02097275.00.01404319625.00.016299648704977163075644359631630756452860416299649115398
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831545131545134194304256001624326400x7fbb0abd5c800x7fbb0a22464024509842345626655363063723063729803904.09270827.00.00.00.0253.00.02349923.00.02353107.00.0255685.02097422.02366836.00.00.031.00.00.00.00.00.00.00.00.00.04194592.00.0548.00.00.0555873.01783735.00.00.02031626.00.04194524.00.02610848408.00.016299649200256163075645650841630756474572516299649702565
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861545131545134194304256001224336000x7fbb0abd5b000x7fbb0a22468024606082356123655363075753075759842400.09270435.00.00.00.0271.00.02342994.00.02352360.00.0254941.02097419.02356013.00.00.031.00.00.00.00.00.00.00.00.00.04194593.00.0550.00.00.0697015.02273161.00.00.02031625.00.04194525.00.02613043764.00.016299649787683163075647700451630756495132616299650295572
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891545131545134194304256001224345600x7fbb0abd59800x7fbb0a2246c012999041198470655361624871624875199584.04650493.00.00.00.0182.00.01049360.00.01049538.00.0777.01048761.01049546.00.00.031.00.00.00.00.00.00.00.00.00.02097350.00.0368.00.00.0540213.01533915.00.00.0983049.00.02097288.00.01458566522.00.016299650379780163075649748461630756506796716299650795501
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092154513154513419430425600824355200x7fbb0abd58000x7fbb0a22470013060321205032655361632531632535224096.04661100.00.00.00.0188.00.01049472.00.01049655.00.0888.01048767.01049657.00.00.031.00.00.00.00.00.00.00.00.00.02097355.00.0374.00.00.0607920.01843427.00.00.0983051.00.02097295.00.01422081337.00.016299650880449163075650950071630756518892816299651295810
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951545131545134194304256001224362240x7fbb0abd56800x7fbb0a22474013074081205656655361634251634255229600.04687164.00.00.00.0188.00.01049304.00.01049485.00.0721.01048764.01049487.00.00.031.00.00.00.00.00.00.00.00.00.02097348.00.0366.00.00.0532420.01580998.00.00.0983049.00.02097288.00.01435937693.00.016299651387628163075652214081630756531452916299651790649
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981545131545134194304256001224371840x7fbb0cfbe5000x7fbb0a22478024463202342043655363057893057899785248.09250265.00.00.00.0281.00.02327737.00.02365746.00.0268310.02097436.02362630.00.00.031.00.00.00.00.00.00.00.00.00.04194587.00.0536.00.00.0703763.02275861.00.00.02031626.00.04194527.00.02596613729.00.016299651875617163075653394891630756551885016299652375656
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011545131545134194304256001224381440x7fbb0cfbe3800x7fbb0a2247c024388642331921655363048573048579755424.09193848.00.00.00.0262.00.02347257.00.02344369.00.0246919.02097450.02340639.00.00.031.00.00.00.00.00.00.00.00.00.04194571.00.0504.00.00.0592039.01929197.00.00.02031626.00.04194530.00.02722919972.00.016299652460534163075655431701630756572493116299652963933
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041545131545134194304256001224391040x7fbb0cfbe2000x7fbb0a22480013060321200582655361632531632535224096.04661778.00.00.00.0187.00.01049416.00.01049599.00.0832.01048767.01049601.00.00.031.00.00.00.00.00.00.00.00.00.02097354.00.0374.00.00.0500811.01638113.00.00.0983050.00.02097294.00.01410028342.00.016299653048341163075657514911630756584509216299653460502
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107154513154513419430425600824403200x7fbb0cfbe0800x7fbb0a22484013146721202114655361643331643335258656.04663702.00.00.00.0188.00.01049584.00.01049766.00.0999.01048767.01049776.00.00.031.00.00.00.00.00.00.00.00.00.02097348.00.0356.00.00.0499824.01557803.00.00.0983051.00.02097298.00.01370345240.00.016299653545320163075658692521630756596381316299653971131
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101545131545134194304256001224412800x7fbb0abd5f000x7fbb0a22488013044321199825655361630531630535217696.04660299.00.00.00.0182.00.01049360.00.01049538.00.0777.01048761.01049547.00.00.031.00.00.00.00.00.00.00.00.00.02097347.00.0362.00.00.0561980.01763211.00.00.0983049.00.02097297.00.01389728303.00.016299654064169163075659959731630756608861316299654482130
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131545131545134194304256001224422400x7fbb0abd5d800x7fbb0a2248c024566402349791655363070793070799826528.09254730.00.00.00.0260.00.02353027.00.02339187.00.0241767.02097420.02364955.00.00.031.00.00.00.00.00.00.00.00.00.04194591.00.0540.00.00.0622185.02077224.00.00.02031627.00.04194535.00.02533295148.00.016299654566898163075661164531630756629565516299655069997
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161545131545134194304256001224432000x7fbb0abd5c000x7fbb0a22490024526242347659655363065773065779810464.09276307.00.00.00.0277.00.02336779.00.02356637.00.0259211.02097426.02344078.00.00.031.00.00.00.00.00.00.00.00.00.04194583.00.0528.00.00.0678291.02226645.00.00.02031626.00.04194522.00.02576827993.00.016299655155035163075663214151630756650237616299655656864
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119154513154513419430425600824441600x7fbb0abd5a800x7fbb0a22494013084961202302655361635611635615233952.04669876.00.00.00.0189.00.01049472.00.01049656.00.0888.01048768.01049653.00.00.031.00.00.00.00.00.00.00.00.00.02097351.00.0366.00.00.0468713.01436709.00.00.0983050.00.02097297.00.01406387039.00.016299655740942163075665282961630756662221716299656160983
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221545131545134194304256001224453760x7fbb0abd59000x7fbb0a22498013088961197510655361636111636115235552.04616242.00.00.00.0187.00.01049640.00.01049825.00.01054.01048771.01049830.00.00.031.00.00.00.00.00.00.00.00.00.02097356.00.0370.00.00.0559973.01601309.00.00.0983052.00.02097301.00.01438182099.00.016299656245061163075666455771630756674029716299656661022
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251545131545134194304256001224463360x7fbb0abd57800x7fbb0a2249c013005761200480655361625711625715202272.04645495.00.00.00.0184.00.01049416.00.01049601.00.0832.01048769.01049604.00.00.031.00.00.00.00.00.00.00.00.00.02097357.00.0380.00.00.0484049.01449888.00.00.0983050.00.02097301.00.01397499280.00.016299656753310163075667729381630756686605816299657166360
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281545131545134194304256001224475520x7fbb0abd56000x7fbb0a224a0024670242349110655363083773083779868064.09263334.00.00.00.0266.00.02352038.00.02378272.00.0280849.02097423.02359752.00.00.031.00.00.00.00.00.00.00.00.00.04194588.00.0532.00.00.0594617.01928466.00.00.02031627.00.04194526.00.02637049899.00.016299657250519163075668913381630756707149916299657755967
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311545131545134194304256001224485120x7fbb0cfbe4800x7fbb0a224a4024189682309752655363023703023709675840.09113202.00.00.00.0257.00.02355202.00.02355499.00.0258084.02097415.02351561.00.00.031.00.00.00.00.00.00.00.00.00.04194561.00.0480.00.00.0666031.02164559.00.00.02031627.00.04194509.00.02728705551.00.016299657840516163075670950191630756727582116299658350234
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134154513154513419430425600824494720x7fbb0cfbe3000x7fbb0a224a8012893601186214655361611691611695157408.04624854.00.00.00.0184.00.01049472.00.01049654.00.0887.01048767.01049660.00.00.031.00.00.00.00.00.00.00.00.00.02097352.00.0368.00.00.0545667.01603001.00.00.0983051.00.02097292.00.01427694366.00.016299658435712163075672990211630756739214116299658857553
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371545131545134194304256001224506880x7fbb0cfbe1800x7fbb0a224ac013077441200046655361634671634675230944.04657372.00.00.00.0190.00.01049696.00.01049884.00.01109.01048775.01049882.00.00.031.00.00.00.00.00.00.00.00.00.02097362.00.0380.00.00.0426717.01310304.00.00.0983053.00.02097302.00.01397929489.00.016299658942231163075674166211630756750958216299659356202
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401545131545134194304256001224516480x7fbb0cfbe0000x7fbb0a224b0012887841188184655361610971610975155104.04639782.00.00.00.0184.00.01049416.00.01049602.00.0832.01048770.01049598.00.00.031.00.00.00.00.00.00.00.00.00.02097353.00.0372.00.00.0536622.01554281.00.00.0983050.00.02097294.00.01419422071.00.016299659450130163075675419021630756763454316299659858471
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431545131545134194304256001224528640x7fbb0abd5e800x7fbb0a224b4024358802329274655363044843044849743488.09189007.00.00.00.0278.00.02369373.00.02351207.00.0253788.02097419.02361194.00.00.031.00.00.00.00.00.00.00.00.00.04194589.00.0532.00.00.0758073.02523226.00.00.02031628.00.04194506.00.02634921195.00.016299659942779163075676603031630756784014416299660452058
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461545131545134194304256001224540800x7fbb0abd5d000x7fbb0a224b8024142002304924655363017743017749656768.09071234.00.00.00.0248.00.02360193.00.02375421.00.0277990.02097431.02355080.00.00.031.00.00.00.00.00.00.00.00.00.04194581.00.0518.00.00.0650071.02132911.00.00.02031627.00.04194520.00.02721050564.00.016299660536496163075678644641630756804494516299661035935
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149154513154513419430425600824552960x7fbb0abd5b800x7fbb0a224bc012982001198585655361622741622745192768.04629348.00.00.00.0183.00.01049584.00.01049771.00.0999.01048772.01049771.00.00.031.00.00.00.00.00.00.00.00.00.02097357.00.0374.00.00.0576535.01618715.00.00.0983051.00.02097300.00.01403166421.00.016299661120723163075680686251630756816238616299661543614
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521545131545134194304256001224567680x7fbb0abd5a000x7fbb0a224c0013124641203264655361640571640575249824.04666329.00.00.00.0184.00.01049808.00.01049991.00.01221.01048770.01049998.00.00.031.00.00.00.00.00.00.00.00.00.02097364.00.0380.00.00.0343795.01121030.00.00.0983053.00.02097308.00.01297117453.00.016299661628822163075681865461630756828222716299662049553
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551545131545134194304256001224577280x7fbb0abd58800x7fbb0a224c4013068481196285655361633551633555227360.04640967.00.00.00.0187.00.01049528.00.01049715.00.0943.01048772.01049714.00.00.031.00.00.00.00.00.00.00.00.00.02097353.00.0368.00.00.0442169.01483574.00.00.0983051.00.02097294.00.01431487423.00.016299662142251163075683145471630756840846816299662565562
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581545131545134194304256001224589440x7fbb0abd57000x7fbb0a224c8024334482327807655363041803041809733760.09170691.00.00.00.0236.00.02355031.00.02360999.00.0263592.02097407.02370059.00.00.031.00.00.00.00.00.00.00.00.00.04194585.00.0524.00.00.0650412.02093718.00.00.02031628.00.04194511.00.02690677322.00.016299662650570163075684332681630756861246916299663158448
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611545131545134194304256001224601600x7fbb0cfbe5800x7fbb0a224cc024204882314628655363025603025609681920.09099377.00.00.00.0241.00.02365919.00.02355116.00.0257700.02097416.02339678.00.00.031.00.00.00.00.00.00.00.00.00.04194574.00.0502.00.00.0685658.02228327.00.00.02031628.00.04194516.00.02752380634.00.016299663243097163075686367891630756881743016299663762005
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164154513154513419430425600824613760x7fbb0cfbe4000x7fbb0a224d0012984881196996655361623101623105193920.04630305.00.00.00.0185.00.01049640.00.01049827.00.01054.01048773.01049828.00.00.031.00.00.00.00.00.00.00.00.00.02097355.00.0368.00.00.0445367.01348182.00.00.0983052.00.02097301.00.01367854963.00.016299663847613163075688422301630756893775116299664267374
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671545131545134194304256001224628480x7fbb0cfbe2800x7fbb0a224d4013434481238044655361679301679305373760.04791805.00.00.00.0184.00.01049920.00.01050099.00.01332.01048767.01050109.00.00.031.00.00.00.00.00.00.00.00.00.02097355.00.0358.00.00.0210209.0715035.00.00.0983054.00.02097302.00.01107728420.00.016299664351782163075689627111630756906271216299664774533
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701545131545134194304256001224638080x7fbb0cfbe1000x7fbb0a224d8013013121192989655361626631626635205216.04625878.00.00.00.0187.00.01049528.00.01049711.00.0943.01048768.01049717.00.00.031.00.00.00.00.00.00.00.00.00.02097357.00.0376.00.00.0512723.01586467.00.00.0983051.00.02097302.00.01431882214.00.016299664867300163075690959921630756918991216299665281011
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731545131545134194304256001224650240x7fbb0abd5f800x7fbb0a224dc024304162322489655363038013038019721632.09164884.00.00.00.0245.00.02349293.00.02349865.00.0252455.02097410.02374059.00.00.031.00.00.00.00.00.00.00.00.00.04194564.00.0480.00.00.0658317.02174604.00.00.02031629.00.04194518.00.02726518981.00.016299665365349163075692187131630756939775416299665875168
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761545131545134194304256001224662400x7fbb0abd5e000x7fbb0a224e0023968722290442655362996082996089587456.09061341.00.00.00.0242.00.02363140.00.02367120.00.0269727.02097393.02382147.00.00.031.00.00.00.00.00.00.00.00.00.04194580.00.0514.00.00.0720614.02372827.00.00.02031628.00.04194521.00.02813126784.00.016299665959236163075694241541630756960271516299666465465
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179154513154513419430425600824674560x7fbb0abd5c800x7fbb0a224e4013007201195846655361625891625895202848.04618726.00.00.00.0191.00.01049696.00.01049880.00.01110.01048770.01049886.00.00.031.00.00.00.00.00.00.00.00.00.02097355.00.0366.00.00.0610948.01855747.00.00.0983052.00.02097300.00.01389080936.00.016299666549343163075696286351630756972319616299666986544
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821545131545134194304256001224689280x7fbb0abd5b000x7fbb0a224e8014128561311615655361766061766065651392.05079715.00.00.00.0183.00.01049976.00.01050164.00.01387.01048777.01050159.00.00.031.00.00.00.00.00.00.00.00.00.02097356.00.0358.00.00.0287898.0897546.00.00.0983055.00.02097296.00.01076649688.00.016299667071032163075697492761630756985359616299667507182
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851545131545134194304256001224701440x7fbb0abd59800x7fbb0a224ec012885121182375655361610631610635154016.04601323.00.00.00.0188.00.01049528.00.01049713.00.0943.01048770.01049713.00.00.031.00.00.00.00.00.00.00.00.00.02097355.00.0372.00.00.0632397.01698914.00.00.0983051.00.02097296.00.01437664420.00.016299667599770163075698875171630756998047716299668033151
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881545131545134194304256001224716160x7fbb0abd58000x7fbb0a224f0024242082316362655363030253030259696800.09102169.00.00.00.0221.00.02376858.00.02350213.00.0252829.02097384.02325100.00.00.031.00.00.00.00.00.00.00.00.00.04194540.00.0428.00.00.0587330.01928322.00.00.02031629.00.04194491.00.02740795721.00.016299668117769163075700060771630757018479816299668624678
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911545131545134194304256001224728320x7fbb0abd56800x7fbb0a224f4024145202310163655363018143018149658048.09106529.00.00.00.0232.00.02375635.00.02361831.00.0264438.02097393.02359148.00.00.031.00.00.00.00.00.00.00.00.00.04194565.00.0480.00.00.0589068.01944240.00.00.02031629.00.04194508.00.02630582607.00.016299668708466163075702131191630757039200016299669221684
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194154513154513419430425600824740480x7fbb0cfbe5000x7fbb0a224f8012960241192863655361620021620025184064.04615597.00.00.00.0185.00.01049696.00.01049879.00.01109.01048770.01049886.00.00.031.00.00.00.00.00.00.00.00.00.02097359.00.0374.00.00.0526968.01628984.00.00.0983053.00.02097300.00.01407104501.00.016299669305723163075704156801630757050912016299669734113
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971545131545134194304256001224757760x7fbb0cfbe3800x7fbb0a224fc014676961353127655361834611834615870752.05320963.00.00.00.0180.00.01050032.00.01050204.00.01442.01048762.01050208.00.00.031.00.00.00.00.00.00.00.00.00.02097355.00.0354.00.00.042544.0172920.00.00.0983056.00.02097290.00.0901174814.00.016299669819141163075705332811630757064096116299670280171
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001545131545134194304256001224769920x7fbb0cfbe2000x7fbb0a22500013012321190953655361626531626535204896.04616910.00.00.00.0186.00.01049640.00.01049827.00.01054.01048773.01049823.00.00.031.00.00.00.00.00.00.00.00.00.02097360.00.0378.00.00.0416535.01358687.00.00.0983052.00.02097299.00.01411404529.00.016299670385349163075706731211630757076768216299670807799
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031545131545134194304256001224784640x7fbb0cfbe0800x7fbb0a22504024101762301561655363012713012719640672.09022071.00.00.00.0226.00.02364359.00.02350430.00.0253045.02097385.02363347.00.00.031.00.00.00.00.00.00.00.00.00.04194569.00.0484.00.00.0566147.01838422.00.00.02031630.00.04194516.00.02796304324.00.016299670892468163075707920021630757097120316299671427246
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061545131545134194304256001224799360x7fbb0abd5f000x7fbb0a22508024170082309222655363021253021259668000.09096636.00.00.00.0227.00.02363373.00.02368082.00.0270685.02097397.02356413.00.00.031.00.00.00.00.00.00.00.00.00.04194543.00.0434.00.00.0550912.01802857.00.00.02031629.00.04194507.00.02690521674.00.016299671511884163075709960031630757117472416299672038332
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209154513154513419430425600824814080x7fbb0abd5d800x7fbb0a2250c013001921189155655361625231625235200736.04604843.00.00.00.0189.00.01049808.00.01049993.00.01221.01048772.01049988.00.00.031.00.00.00.00.00.00.00.00.00.02097364.00.0380.00.00.0598703.01789793.00.00.0983053.00.02097303.00.01403759978.00.016299672123350163075711995251630757129392516299672559471
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121545131545134194304256001224831360x7fbb0abd5c000x7fbb0a22510015364641427128655361920571920576145824.05547972.00.00.00.0169.00.01050144.00.01050313.00.01554.01048759.01050318.00.00.031.00.00.00.00.00.00.00.00.00.02097356.00.0352.00.00.026818.0128442.00.00.0983056.00.02097300.00.0780102848.00.016299672644739163075713179251630757143328616299673091479
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151545131545134194304256001224843520x7fbb0abd5a800x7fbb0a22514012888321185822655361611031611035155296.04601418.00.00.00.0188.00.01049696.00.01049880.00.01110.01048770.01049882.00.00.031.00.00.00.00.00.00.00.00.00.02097355.00.0366.00.00.0523875.01674388.00.00.0983052.00.02097302.00.01422964216.00.016299673184177163075714801661630757157424716299673604597
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181545131545134194304256001224858240x7fbb0abd59000x7fbb0a22518024141122308917655363017633017639656416.09034732.00.00.00.0251.00.02334750.00.02349054.00.0251637.02097417.02360489.00.00.031.00.00.00.00.00.00.00.00.00.04194596.00.0536.00.00.0593967.01958061.00.00.02031630.00.04194513.00.02622860553.00.016299673690426163075715984071630757177808816299674222964
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211545131545134194304256001224872960x7fbb0abd57800x7fbb0a2251c023974562289668655362996812996819589792.09015643.00.00.00.0253.00.02357308.00.02362171.00.0264769.02097402.02349092.00.00.031.00.00.00.00.00.00.00.00.00.04194553.00.0452.00.00.0631745.02086383.00.00.02031630.00.04194509.00.02645896986.00.016299674308372163075718028881630757198304916299674833010
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241545131545134194304256001224887680x7fbb0abd56000x7fbb0a22520012967281193466655361620901620905186880.04610074.00.00.00.0184.00.01049864.00.01050047.00.01276.01048771.01050047.00.00.031.00.00.00.00.00.00.00.00.00.02097360.00.0370.00.00.0568906.01745661.00.00.0983054.00.02097303.00.01353519410.00.016299674919018163075720072101630757210177016299675351859
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271545131545134194304256001224907520x7fbb0cfbe4800x7fbb0a22524016165121507482655362020632020636466016.05858497.00.00.00.0170.00.01050256.00.01050428.00.01665.01048763.01050434.00.00.031.00.00.00.00.00.00.00.00.00.02097358.00.0352.00.00.018411.0103092.00.00.0983057.00.02097298.00.0704341117.00.016299675436957163075721264101630757224721116299675893177
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301545131545134194304256001224919680x7fbb0cfbe3000x7fbb0a22528012918561190184655361614811614815167392.04609993.00.00.00.0184.00.01049696.00.01049872.00.01110.01048762.01049878.00.00.031.00.00.00.00.00.00.00.00.00.02097357.00.0370.00.00.0472860.01484285.00.00.0983052.00.02097303.00.01420613359.00.016299675987165163075722803311630757237393216299676409506
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331545131545134194304256001224934400x7fbb0cfbe1800x7fbb0a2252c024129522305606655363016183016189651776.09052312.00.00.00.0255.00.02335777.00.02375029.00.0277612.02097417.02346718.00.00.031.00.00.00.00.00.00.00.00.00.04194581.00.0506.00.00.0827591.02772665.00.00.02031630.00.04194542.00.02781880186.00.016299676495014163075723987321630757257857316299677017962
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361545131545134194304256001224949120x7fbb0cfbe0000x7fbb0a22530024043922299533655363005483005489617536.09060991.00.00.00.0248.00.02369398.00.02372329.00.0274929.02097400.02366974.00.00.031.00.00.00.00.00.00.00.00.00.04194573.00.0490.00.00.0691306.02224822.00.00.02031630.00.04194524.00.02693637242.00.016299677103590163075726033731630757278257416299677620329
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391545131545134194304256001224963840x7fbb0abd5e800x7fbb0a22534012953761191887655361619211619215181472.04608054.00.00.00.0189.00.01049920.00.01050106.00.01332.01048774.01050108.00.00.031.00.00.00.00.00.00.00.00.00.02097362.00.0372.00.00.0499028.01634529.00.00.0983054.00.02097308.00.01409170624.00.016299677704357163075728075351630757290257516299678141677
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421545131545134194304256001224983680x7fbb0abd5d000x7fbb0a22538016984481587281655362123052123056793760.06205938.00.00.00.0164.00.01050312.00.01050475.00.01720.01048755.01050462.00.00.031.00.00.00.00.00.00.00.00.00.02097340.00.0314.00.00.041408.0160691.00.00.0983058.00.02097286.00.0680936246.00.016299678227366163075729267351630757305361616299678699185
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451545131545134194304256001224995840x7fbb0abd5b800x7fbb0a2253c012989921196591655361623731623735195936.04594673.00.00.00.0187.00.01049752.00.01049938.00.01165.01048773.01049936.00.00.031.00.00.00.00.00.00.00.00.00.02097360.00.0374.00.00.0364655.01172948.00.00.0983053.00.02097304.00.01415660813.00.016299678792343163075730868961630757318193716299679212834
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024815451315451341943042560012241013120x7fbb0abd5a000x7fbb0a22540023853122271675655362981632981639541216.08975526.00.00.00.0253.00.02341126.00.02368459.00.0271043.02097416.02364987.00.00.031.00.00.00.00.00.00.00.00.00.04194573.00.0488.00.00.0810238.02727752.00.00.02031631.00.04194521.00.02683612806.00.016299679297612163075732075371630757338785816299679817490
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025115451315451341943042560012241027840x7fbb0abd58800x7fbb0a22544023898882282210655362987352987359559520.08992039.00.00.00.0260.00.02357398.00.02369441.00.0272003.02097438.02341254.00.00.031.00.00.00.00.00.00.00.00.00.04194578.00.0498.00.00.0666872.02214884.00.00.02031631.00.04194523.00.02631251355.00.016299679901788163075734124981630757359169916299680418707
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025415451315451341943042560012241042560x7fbb0abd57000x7fbb0a22548012838721182931655361604831604835135456.04598185.00.00.00.0188.00.01049920.00.01050105.00.01331.01048774.01050108.00.00.031.00.00.00.00.00.00.00.00.00.02097363.00.0374.00.00.0468092.01554868.00.00.0983055.00.02097309.00.01311601374.00.016299680502665163075736160191630757370978016299680950305
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025715451315451341943042560012241062400x7fbb0cfbe5800x7fbb0a2254c017557761647542655362194712194717023072.06474549.00.00.00.0153.00.01050368.00.01050517.00.01775.01048742.01050528.00.00.031.00.00.00.00.00.00.00.00.00.02097350.00.0332.00.00.01252.058318.00.00.0983059.00.02097279.00.0648070363.00.016299681035383163075737334601630757386386116299681500753
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026015451315451341943042560012241077120x7fbb0cfbe4000x7fbb0a22550012817921180166655361602231602235127136.04580726.00.00.00.0185.00.01049752.00.01049935.00.01165.01048770.01049938.00.00.031.00.00.00.00.00.00.00.00.00.02097358.00.0370.00.00.0523465.01652952.00.00.0983053.00.02097299.00.01431637384.00.016299681593111163075738960211630757398914216299682019102
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026315451315451341943042560016241094400x7fbb0cfbe2800x7fbb0a22554023984002288327655362997992997999593568.09007437.00.00.00.0244.00.02365762.00.02353897.00.0256507.02097390.02349405.00.00.031.00.00.00.00.00.00.00.00.00.04194569.00.0476.00.00.0696601.02306065.00.00.02031632.00.04194510.00.02703756947.00.016299682105310163075740147421630757419570316299682629928
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026615451315451341943042560016241111680x7fbb0cfbe1000x7fbb0a22558023855682273098655362981952981959542240.08955628.00.00.00.0263.00.02352263.00.02361522.00.0264128.02097394.02366616.00.00.031.00.00.00.00.00.00.00.00.00.04194563.00.0466.00.00.0770087.02567284.00.00.02031631.00.04194528.00.02765487166.00.016299682715336163075742208231630757440066416299683242185
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691545131545134194304256008241128960x7fbb0abd5f800x7fbb0a2255c013136161212487655361642011642015254432.04662134.00.00.00.0190.00.01050032.00.01050218.00.01443.01048775.01050217.00.00.031.00.00.00.00.00.00.00.00.00.02097364.00.0372.00.00.0347222.01146412.00.00.0983055.00.02097309.00.01325989398.00.016299683327963163075744248241630757452066516299683758683
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027215451315451341943042560012241151360x7fbb0abd5e000x7fbb0a22560018394721725526655362299332299337357856.06784314.00.00.00.0157.00.01050480.00.01050637.00.01887.01048750.01050626.00.00.031.00.00.00.00.00.00.00.00.00.02097339.00.0306.00.00.00.057258.00.00.0983059.00.02097285.00.0612548111.00.016299683843161163075745457851630757468450616299684323681
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027515451315451341943042560012241166080x7fbb0abd5c800x7fbb0a22564012877601186345655361609691609695151008.04571413.00.00.00.0189.00.01049808.00.01049993.00.01221.01048772.01049989.00.00.031.00.00.00.00.00.00.00.00.00.02097360.00.0372.00.00.0505551.01655887.00.00.0983054.00.02097303.00.01451576724.00.016299684416299163075747169861630757481218716299684837669
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027815451315451341943042560016241183360x7fbb0abd5b000x7fbb0a22568024004402291387655363000543000549601728.09023268.00.00.00.0240.00.02366861.00.02370852.00.0273443.02097409.02346223.00.00.031.00.00.00.00.00.00.00.00.00.04194573.00.0482.00.00.0703892.02336594.00.00.02031632.00.04194515.00.02728107357.00.016299684922608163075748369871630757501554816299685440266
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028115451315451341943042560016241200640x7fbb0abd59800x7fbb0a2256c023937762286860655362992212992219575072.09006297.00.00.00.0242.00.02381071.00.02371006.00.0273598.02097408.02345975.00.00.031.00.00.00.00.00.00.00.00.00.04194586.00.0510.00.00.0750526.02528682.00.00.02031632.00.04194534.00.02679211054.00.016299685524934163075750406681630757522034916299686047343
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028415451315451341943042560012241217920x7fbb0abd58000x7fbb0a22570013128561212622655361641061641065251392.04688682.00.00.00.0183.00.01050088.00.01050272.00.01498.01048774.01050273.00.00.031.00.00.00.00.00.00.00.00.00.02097366.00.0374.00.00.0285586.0941246.00.00.0983056.00.02097310.00.01254939037.00.016299686132371163075752438691630757534147016299686579541
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028715451315451341943042560012241240320x7fbb0abd56800x7fbb0a22574019255681811317655362406952406957702240.07106782.00.00.00.0148.00.01050592.00.01050732.00.01998.01048734.01050735.00.00.031.00.00.00.00.00.00.00.00.00.02097340.00.0304.00.00.00.054465.00.00.0983060.00.02097287.00.0592523956.00.016299686663819163075753659501630757551203116299687148128
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029015451315451341943042560012241255040x7fbb0cfbe5000x7fbb0a22578013018001197248655361627241627245207168.04581414.00.00.00.0186.00.01049920.00.01050103.00.01332.01048771.01050111.00.00.031.00.00.00.00.00.00.00.00.00.02097363.00.0374.00.00.0425604.01416760.00.00.0983054.00.02097301.00.01421757798.00.016299687241386163075755440311630757563891216299687688296
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029315451315451341943042560012241274880x7fbb0cfbe3800x7fbb0a2257c023753442268943655362969172969179501344.08911414.00.00.00.0269.00.02376232.00.02380717.00.0283297.02097420.02359102.00.00.031.00.00.00.00.00.00.00.00.00.04194592.00.0516.00.00.0619057.02024230.00.00.02031633.00.04194550.00.02748247028.00.016299687773955163075756633921630757584371316299688295163
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029615451315451341943042560012241292160x7fbb0cfbe2000x7fbb0a22580023836322275458655362979532979539534496.08943552.00.00.00.0261.00.02354192.00.02359482.00.0262069.02097413.02357849.00.00.031.00.00.00.00.00.00.00.00.00.04194589.00.0512.00.00.0637746.02094927.00.00.02031633.00.04194518.00.02734170552.00.016299688380951163075758680331630757604915416299688903000
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029915451315451341943042560012241309440x7fbb0cfbe0800x7fbb0a22584013676641259686655361709571709575470624.04922237.00.00.00.0181.00.01050144.00.01050326.00.01553.01048773.01050327.00.00.031.00.00.00.00.00.00.00.00.00.02097360.00.0360.00.00.0254536.0842724.00.00.0983057.00.02097296.00.01121532093.00.016299688987588163075760725151630757617267516299689435998
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030215451315451341943042560012241334400x7fbb0abd5f000x7fbb0a22588020726561963434655362590812590818290592.07726028.00.00.00.0149.00.01050704.00.01050842.00.02108.01048734.01050851.00.00.031.00.00.00.00.00.00.00.00.00.02097333.00.0286.00.00.06.053938.00.00.0983062.00.02097276.00.0577560554.00.016299689520536163075761966751630757635203616299690031365
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030515451315451341943042560012241349120x7fbb0abd5d800x7fbb0a2258c012867281182910655361608401608405146880.04573959.00.00.00.0188.00.01049976.00.01050159.00.01387.01048772.01050164.00.00.031.00.00.00.00.00.00.00.00.00.02097365.00.0376.00.00.0426241.01313379.00.00.0983055.00.02097307.00.01379514367.00.016299690124792163075763846761630757647987716299690565593
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030815451315451341943042560012241368960x7fbb0abd5c000x7fbb0a22590023729762267034655362966212966219491872.08929700.00.00.00.0264.00.02367532.00.02361913.00.0264472.02097441.02337875.00.00.031.00.00.00.00.00.00.00.00.00.04194602.00.0534.00.00.0768920.02575023.00.00.02031634.00.04194547.00.02757380996.00.016299690649721163075765069171630757668595816299691174379
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031115451315451341943042560012241388800x7fbb0abd5a800x7fbb0a22594023887522277702655362985932985939554976.08939851.00.00.00.0258.00.02362817.00.02355326.00.0257901.02097425.02361737.00.00.031.00.00.00.00.00.00.00.00.00.04194594.00.0518.00.00.0685600.02261468.00.00.02031634.00.04194531.00.02691857855.00.016299691258438163075767117181630757689236016299691796136
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031415451315451341943042560012241408640x7fbb0abd59000x7fbb0a22598014197441314368655361774671774675678944.05122636.00.00.00.0179.00.01050312.00.01050486.00.01720.01048766.01050487.00.00.031.00.00.00.00.00.00.00.00.00.02097352.00.0338.00.00.094862.0330334.00.00.0983058.00.02097296.00.0936994438.00.016299691876114163075769158801630757702356016299692339264
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031715451315451341943042560012241436160x7fbb0abd57800x7fbb0a2259c022335922129475655362791982791988934336.08352709.00.00.00.0155.00.01050928.00.01051067.00.02331.01048736.01051075.00.00.031.00.00.00.00.00.00.00.00.00.02097335.00.0282.00.00.00.054019.00.00.0983063.00.02097285.00.0568977667.00.016299692422302163075770477211630757721780216299692953640
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032015451315451341943042560012241453440x7fbb0abd56000x7fbb0a225a0012964961194469655361620611620615185952.04629207.00.00.00.0187.00.01050088.00.01050276.00.01498.01048778.01050275.00.00.031.00.00.00.00.00.00.00.00.00.02097367.00.0376.00.00.0310622.01032639.00.00.0983056.00.02097313.00.01261539179.00.016299693044768163075772509221630757734692216299693481049
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032315451315451341943042560012241475840x7fbb0cfbe4800x7fbb0a225a4023662242257192655362957772957779464864.08873998.00.00.00.0270.00.02367867.00.02368847.00.0271419.02097428.02344359.00.00.031.00.00.00.00.00.00.00.00.00.04194609.00.0542.00.00.0633122.02070719.00.00.02031635.00.04194564.00.02719511113.00.016299693565027163075773717221630757755316416299694086145
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032615451315451341943042560012241495680x7fbb0cfbe3000x7fbb0a225a8023691602254212655362961442961449476608.08888556.00.00.00.0279.00.02367028.00.02356583.00.0259161.02097422.02356535.00.00.031.00.00.00.00.00.00.00.00.00.04194602.00.0530.00.00.0611867.02022043.00.00.02031635.00.04194538.00.02792003151.00.016299694170333163075775771641630757775748516299694700442
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032915451315451341943042560012241515520x7fbb0cfbe1800x7fbb0a225ac014978401383602655361872291872295991328.05415759.00.00.00.0162.00.01050368.00.01050532.00.01775.01048757.01050533.00.00.031.00.00.00.00.00.00.00.00.00.02097347.00.0326.00.00.047409.0187068.00.00.0983059.00.02097288.00.0705615180.00.016299694784280163075777814851630757789220616299695249200
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033215451315451341943042560012241543040x7fbb0cfbe0000x7fbb0a225b0023996562290432655362999562999569598592.09011537.00.00.00.0139.00.01051040.00.01051178.00.02441.01048737.01051180.00.00.031.00.00.00.00.00.00.00.00.00.02097332.00.0272.00.00.00.054833.00.00.0983065.00.02097275.00.0562333356.00.016299695333358163075779163661630757809764716299695862846
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033515451315451341943042560012241562880x7fbb0abd5e800x7fbb0a225b4013731521268701655361716431716435492576.04942772.00.00.00.0182.00.01050200.00.01050384.00.01609.01048775.01050381.00.00.031.00.00.00.00.00.00.00.00.00.02097365.00.0368.00.00.0199833.0622709.00.00.0983057.00.02097303.00.01088922802.00.016299695955074163075781304471630757823108816299696393515
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033815451315451341943042560012241587840x7fbb0abd5d000x7fbb0a225b8023930402266254655362991292991299572128.08932938.00.00.00.0298.00.02322950.00.02304278.00.0206816.02097462.02326812.00.00.031.00.00.00.00.00.00.00.00.00.04194635.00.0586.00.00.0678888.02286263.00.00.02031637.00.04194587.00.02754035786.00.016299696477643163075782557281630757844164916299697006421
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034115451315451341943042560012241610240x7fbb0abd5b800x7fbb0a225bc023827922259927655362978482978489531136.08938749.00.00.00.0288.00.02339531.00.02342782.00.0245324.02097458.02360115.00.00.031.00.00.00.00.00.00.00.00.00.04194621.00.0560.00.00.0700318.02360929.00.00.02031637.00.04194573.00.02691967681.00.016299697089699163075784651691630757864773016299697623067
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034415451315451341943042560012241632640x7fbb0abd5a000x7fbb0a225c0016505681536761655362063202063206602240.06031791.00.00.00.0156.00.01050592.00.01050744.00.01997.01048747.01050740.00.00.031.00.00.00.00.00.00.00.00.00.02097345.00.0314.00.00.025446.0119966.00.00.0983061.00.02097282.00.0737739022.00.016299697705836163075786728501630757879541116299698172865
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034715451315451341943042560012241665280x7fbb0abd58800x7fbb0a225c40272366426114106553634045734045710894624.010267249.00.00.00.0132.00.01051376.00.01051507.00.02774.01048733.01051513.00.00.031.00.00.00.00.00.00.00.00.00.02097338.00.0272.00.00.00.057788.00.00.0983068.00.02097283.00.0558733809.00.016299698256803163075788194111630757902661316299698880200
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035015451315451341943042560012241685120x7fbb0abd57000x7fbb0a225c8014804961364980655361850611850615921952.05317939.00.00.00.0169.00.01050424.00.01050582.00.01831.01048751.01050590.00.00.031.00.00.00.00.00.00.00.00.00.02097354.00.0338.00.00.049988.0194114.00.00.0983059.00.02097297.00.0786160250.00.016299698909029163075790973331630757920901416299699356359
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035315451315451341943042560012241712640x7fbb0cfbe5800x7fbb0a225cc023852322254829655362981532981539540896.08945535.00.00.00.0290.00.02323559.00.02352074.00.0254607.02097467.02350873.00.00.031.00.00.00.00.00.00.00.00.00.04194639.00.0588.00.00.0559733.01852583.00.00.02031639.00.04194592.00.02717193019.00.016299699440757163075792339741630757941781516299699970495
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035615451315451341943042560012241737600x7fbb0cfbe4000x7fbb0a225d0023613442247522655362951672951679445344.08820979.00.00.00.0294.00.02343804.00.02349348.00.0251882.02097466.02335703.00.00.031.00.00.00.00.00.00.00.00.00.04194645.00.0600.00.00.0719357.02396996.00.00.02031639.00.04194588.00.02703198674.00.016299700054554163075794421351630757962613616299700578952
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035915451315451341943042560012241762560x7fbb0cfbe2800x7fbb0a225d4018076641690986655362259572259577230624.06667309.00.00.00.0148.00.01050816.00.01050965.00.02219.01048746.01050962.00.00.031.00.00.00.00.00.00.00.00.00.02097331.00.0278.00.00.04601.066335.00.00.0983063.00.02097279.00.0584135389.00.016299700662750163075796520561630757978677716299701146559
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036215451315451341943042560012241797760x7fbb0cfbe1000x7fbb0a225d80304382429311946553638047738047712175264.011572547.00.00.00.0136.00.01051712.00.01051849.00.03107.01048742.01051844.00.00.031.00.00.00.00.00.00.00.00.00.02097340.00.0264.00.00.00.054223.00.00.0983071.00.02097290.00.0560254297.00.016299701229938163075798104571630758004293916299701848344
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036515451315451341943042560012241822720x7fbb0abd5f800x7fbb0a225dc016874241577225655362109272109276749664.06206386.00.00.00.0157.00.01050704.00.01050852.00.02108.01048744.01050860.00.00.031.00.00.00.00.00.00.00.00.00.02097347.00.0314.00.00.0833.055826.00.00.0983062.00.02097286.00.0610299850.00.016299701900433163075801130191630758024006016299702367942
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036815451315451341943042560012241855360x7fbb0abd5e000x7fbb0a225e0024494722326974655363061833061839797856.09133095.00.00.00.0281.00.02285451.00.02289507.00.0192042.02097465.02287199.00.00.031.00.00.00.00.00.00.00.00.00.04194647.00.0586.00.00.0519688.01747783.00.00.02031643.00.04194589.00.02450748466.00.016299702451751163075802658201630758045670116299703051457
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037115451315451341943042560012241885440x7fbb0abd5c800x7fbb0a225e4024634242327218655363079273079279853664.09232381.00.00.00.0289.00.02272527.00.02272833.00.0175370.02097463.02269203.00.00.031.00.00.00.00.00.00.00.00.00.04194624.00.0542.00.00.0498979.01716103.00.00.02031643.00.04194577.00.02374081504.00.016299703070747163075804821421630758067622316299703671694
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037415451315451341943042560012241915520x7fbb0abd5b000x7fbb0a225e8021258402015674655362657292657298503328.07934039.00.00.00.0134.00.01051264.00.01051393.00.02663.01048730.01051411.00.00.031.00.00.00.00.00.00.00.00.00.02097341.00.0282.00.00.00.051681.00.00.0983067.00.02097287.00.0566692652.00.016299703693283163075807035831630758086406416299704205442
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037715451315451341943042560012241958400x7fbb0abd59800x7fbb0a225ec0369773635899666553646221646221614790912.014105392.00.00.00.0145.00.01052328.00.01052467.00.03718.01048749.01052464.00.00.031.00.00.00.00.00.00.00.00.00.02097351.00.0264.00.00.00.054524.00.00.0983076.00.02097302.00.0555146368.00.016299704288360163075808899841630758117382616299704960545
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038015451315451341943042560012241985920x7fbb0abd58000x7fbb0a225f0019513281839825655362439152439157805280.07209630.00.00.00.0133.00.01051096.00.01051239.00.02497.01048742.01051233.00.00.031.00.00.00.00.00.00.00.00.00.02097332.00.0270.00.00.0158.056263.00.00.0983065.00.02097281.00.0563949467.00.016299705009234163075812203861630758136950716299705502333
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038315451315451341943042560012242023680x7fbb0abd56800x7fbb0a225f40267379225563216553633422333422310695136.010098678.00.00.00.0268.00.02247897.00.02259695.00.0162246.02097449.02256888.00.00.031.00.00.00.00.00.00.00.00.00.04194635.00.0548.00.00.0312422.01052037.00.00.02031647.00.04194576.00.02167982544.00.016299705585212163075813947871630758160390816299706203978
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038615451315451341943042560012242058880x7fbb0cfbe5000x7fbb0a225f80265633625293126553633204133204110625312.010018511.00.00.00.0271.00.02206132.00.02201753.00.0104306.02097447.02224556.00.00.031.00.00.00.00.00.00.00.00.00.04194620.00.0518.00.00.0295180.0975974.00.00.02031647.00.04194563.00.02080353935.00.016299706223467163075816440691630758185495016299706848084
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038915451315451341943042560012242094080x7fbb0cfbe3800x7fbb0a225fc024568002344040655363070993070999827168.09235273.00.00.00.0128.00.01051712.00.01051849.00.03107.01048742.01051839.00.00.031.00.00.00.00.00.00.00.00.00.02097355.00.0294.00.00.0176.054648.00.00.0983071.00.02097283.00.0556189253.00.016299706868653163075818936701630758207975116299707413641
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039215451315451341943042560012242144640x7fbb0cfbe2000x7fbb0a226000434161642267716553654270154270117366432.016638904.00.00.00.0138.00.01053000.00.01053140.00.04384.01048756.01053141.00.00.031.00.00.00.00.00.00.00.00.00.02097363.00.0264.00.00.00.054316.00.00.0983082.00.02097307.00.0557384900.00.016299707497319163075821064721630758244135416299708219933
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039515451315451341943042560012242177280x7fbb0cfbe0800x7fbb0a22604021827442071050655362728422728428730944.08145465.00.00.00.0143.00.01051432.00.01051570.00.02830.01048740.01051563.00.00.031.00.00.00.00.00.00.00.00.00.02097339.00.0272.00.00.020.056823.00.00.0983068.00.02097289.00.0561146422.00.016299708271512163075825107941630758267879516299708774061
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039815451315451341943042560012242220160x7fbb0abd5f000x7fbb0a226080291902428007076553636487736487711676064.010970250.00.00.00.0253.00.02206124.00.02219825.00.0122390.02097435.02224711.00.00.031.00.00.00.00.00.00.00.00.00.04194617.00.0494.00.00.0214187.0726659.00.00.02031651.00.04194572.00.01882579496.00.016299708857739163075827050351630758293479716299709470805
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040115451315451341943042560012242260480x7fbb0abd5d800x7fbb0a2260c0292919228139586553636614836614811716736.011063295.00.00.00.0236.00.02175160.00.02169878.00.072464.02097414.02172368.00.00.031.00.00.00.00.00.00.00.00.00.04194599.00.0460.00.00.0285088.0919903.00.00.02031651.00.04194551.00.01704952624.00.016299709516244163075829944771630758322423816299710165200
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040415451315451341943042560012242300800x7fbb0abd5c000x7fbb0a226100277333626623816553634666634666611093312.010506164.00.00.00.0126.00.01052160.00.01052289.00.03551.01048738.01052315.00.00.031.00.00.00.00.00.00.00.00.00.02097342.00.0252.00.00.00.054639.00.00.0983075.00.02097315.00.0552995878.00.016299710183430163075832840791630758349592016299710814136
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040715451315451341943042560012242359040x7fbb0abd5a800x7fbb0a226140500040048769346553662504962504920001568.019003227.00.00.00.0136.00.01053672.00.01053811.00.05050.01048761.01053807.00.00.031.00.00.00.00.00.00.00.00.00.02097380.00.0274.00.00.00.054752.00.00.0983088.00.02097321.00.0559109864.00.016299710833125163075835564001630758394232316299711622028
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041015451315451341943042560012242394240x7fbb0abd59000x7fbb0a22618024276322318401655363034533034539710496.09095219.00.00.00.0143.00.01051768.00.01051905.00.03163.01048742.01051905.00.00.031.00.00.00.00.00.00.00.00.00.02097342.00.0266.00.00.00.054165.00.00.0983071.00.02097292.00.0557068746.00.016299711669587163075840088831630758419592416299712195465
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041315451315451341943042560012242442240x7fbb0abd57800x7fbb0a2261c0318398430719636553639799739799712735904.012096568.00.00.00.0235.00.02180864.00.02188194.00.090775.02097419.02178724.00.00.031.00.00.00.00.00.00.00.00.00.04194619.00.0484.00.00.0180700.0588718.00.00.02031655.00.04194556.00.01616448488.00.016299712279224163075842202441630758447032616299712940519
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041615451315451341943042560012242487680x7fbb0abd56000x7fbb0a226200312244830146956553639030539030512489760.011860188.00.00.00.0230.00.02119069.00.02115398.00.017991.02097407.02116067.00.00.031.00.00.00.00.00.00.00.00.00.04194597.00.0440.00.00.017579.0106845.00.00.02031655.00.04194533.00.01226394448.00.016299712962179163075845332061630758478056816299713616714
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041915451315451341943042560012242533120x7fbb0cfbe4800x7fbb0a226240310377629899766553638797138797112415072.011780307.00.00.00.0134.00.01052552.00.01052683.00.03940.01048743.01052708.00.00.031.00.00.00.00.00.00.00.00.00.02097350.00.0254.00.00.00.054337.00.00.0983078.00.02097310.00.0545650304.00.016299713639194163075848196081630758505673016299714289299
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221545131545134194304256008242555520x7fbb0cfbe3000x7fbb0a226280574662456334826553671832771832722986464.020878961.00.00.00.0132.00.01050536.00.01050667.00.01942.01048725.01050670.00.00.031.00.00.00.00.00.00.00.00.00.02097322.00.0270.00.00.00.055750.00.00.0983060.00.02097259.00.0539493570.00.016299714309369163075850928901630758554649316299715179410
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042515451315451341943042560012242598400x7fbb0cfbe1800x7fbb0a2262c0291938428025336553636492236492211677504.011021471.00.00.00.0136.00.01052440.00.01052575.00.03829.01048746.01052577.00.00.031.00.00.00.00.00.00.00.00.00.02097354.00.0266.00.00.00.054248.00.00.0983077.00.02097304.00.0549795909.00.016299715208789163075855876131630758581353416299715834845
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042815451315451341943042560012242656640x7fbb0cfbe0000x7fbb0a226300376363236480436553647045347045315054496.014343460.00.00.00.0200.00.02112574.00.02114973.00.017552.02097421.02113015.00.00.031.00.00.00.00.00.00.00.00.00.04194594.00.0402.00.00.09405.081312.00.00.02031663.00.04194546.00.01140732483.00.016299715857455163075858506541630758614873616299716547189
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043115451315451341943042560012242712320x7fbb0abd5e800x7fbb0a226340378440036808886553647304947304915137568.014464055.00.00.00.0219.00.02135364.00.02137476.00.040062.02097414.02133964.00.00.031.00.00.00.00.00.00.00.00.00.04194608.00.0430.00.00.013371.093698.00.00.02031663.00.04194551.00.01285461798.00.016299716589978163075862148171630758651369916299717277993
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341545131545134194304256008242732160x7fbb0abd5d000x7fbb0a226380386430437507716553648303748303715457184.014792970.00.00.00.0144.00.01050312.00.01050457.00.01720.01048737.01050456.00.00.031.00.00.00.00.00.00.00.00.00.02097329.00.0292.00.00.00.059748.00.00.0983058.00.02097273.00.0542608416.00.016299717317382163075865546591630758685146116299718004907
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371545131545134194304256008242757120x7fbb0abd5b800x7fbb0a2263c0705267269313916553688158388158328210656.026261350.00.00.00.0129.00.01050872.00.01051002.00.02275.01048727.01051003.00.00.031.00.00.00.00.00.00.00.00.00.02097329.00.0272.00.00.00.056862.00.00.0983063.00.02097270.00.0540377584.00.016299718048446163075868861811630758744426416299719052104
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044015451315451341943042560012242807680x7fbb0abd5a000x7fbb0a226400341904833048126553642738042738013676160.013011346.00.00.00.0130.00.01053000.00.01053137.00.04384.01048753.01053136.00.00.031.00.00.00.00.00.00.00.00.00.02097384.00.0306.00.00.00.053886.00.00.0983082.00.02097307.00.0544696111.00.016299719078503163075875113051630758777498616299719754888
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044315451315451341943042560012242876160x7fbb0abd58800x7fbb0a226440438734442840466553654841754841717549344.016874754.00.00.00.0217.00.02130529.00.02129019.00.031600.02097419.02131806.00.00.031.00.00.00.00.00.00.00.00.00.04194618.00.0416.00.00.022444.0120918.00.00.02031671.00.04194564.00.01249644826.00.016299719775048163075878349871630758818586916299720536251
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044615451315451341943042560012242942080x7fbb0abd57000x7fbb0a226480440834443008466553655104255104217633344.016954065.00.00.00.0215.00.02127385.00.02130514.00.033098.02097416.02129402.00.00.031.00.00.00.00.00.00.00.00.00.04194615.00.0412.00.00.023476.0123843.00.00.02031671.00.04194564.00.01181165853.00.016299720557741163075882445891630758859467116299721294935
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491545131545134194304256008242969600x7fbb0cfbe5800x7fbb0a2264c0451793643992976553656474156474118071712.017254107.00.00.00.0136.00.01050984.00.01051124.00.02386.01048738.01051121.00.00.031.00.00.00.00.00.00.00.00.00.02097333.00.0276.00.00.00.056767.00.00.0983064.00.02097275.00.0543850846.00.016299721336924163075886562721630758900379416299722083517
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521545131545134194304256008242999680x7fbb0cfbe4000x7fbb0a22650083306568221207655361041331104133133322592.030226002.00.00.00.0136.00.01051208.00.01051337.00.02608.01048729.01051338.00.00.031.00.00.00.00.00.00.00.00.00.02097329.00.0260.00.00.00.056389.00.00.0983066.00.02097273.00.0546387278.00.016299722122996163075890405941630758970283816299723171733
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551545131545134194304256008243027200x7fbb0cfbe2800x7fbb0a226540578187256603656553672273372273323127456.022115902.00.00.00.0136.00.01050984.00.01051117.00.02386.01048731.01051123.00.00.031.00.00.00.00.00.00.00.00.00.02097331.00.0272.00.00.00.049750.00.00.0983064.00.02097280.00.0547918727.00.016299723225402163075897455581630759019452116299724078403
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045815451315451341943042560012243054720x7fbb0cfbe1000x7fbb0a226580578972856742046553672371572371523158880.022529846.00.00.00.0217.00.02099622.00.02099919.00.02537.02097382.02099871.00.00.031.00.00.00.00.00.00.00.00.00.04194554.00.0412.00.00.00.053062.00.00.02031640.00.04194501.00.01065673156.00.016299724098892163075902582021630759072428416299724966633
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046115451315451341943042560012243082240x7fbb0abd5f800x7fbb0a2265c0577168856638216553672146072146023086720.022416546.00.00.00.0204.00.02099639.00.02099818.00.02440.02097378.02099771.00.00.031.00.00.00.00.00.00.00.00.00.04194547.00.0400.00.00.00.057133.00.00.02031640.00.04194488.00.01069240090.00.016299724987623163075907919651630759125340816299725869003
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641545131545134194304256008243109760x7fbb0abd5e000x7fbb0a226600582585656983026553672823172823123303392.022410612.00.00.00.0134.00.01051040.00.01051172.00.02442.01048730.01051175.00.00.031.00.00.00.00.00.00.00.00.00.02097328.00.0264.00.00.00.054292.00.00.0983064.00.02097277.00.0546880221.00.016299725890253163075913170881630759176957116299726755764
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671545131545134194304256008243132160x7fbb0abd5c800x7fbb0a2266401093910410810074655361367387136738743756384.035839232.00.00.00.0131.00.01050536.00.01050666.00.01942.01048724.01050666.00.00.031.00.00.00.00.00.00.00.00.00.02097320.00.0266.00.00.00.045159.00.00.0983060.00.02097266.00.0549664161.00.016299726775533163075918346911630759270477716299728059575
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701545131545134194304256008243159680x7fbb0abd5b000x7fbb0a2266801096843210849364655361371053137105343873696.034898231.00.00.00.0131.00.01050984.00.01051115.00.02386.01048729.01051117.00.00.031.00.00.00.00.00.00.00.00.00.02097324.00.0258.00.00.00.053469.00.00.0983064.00.02097271.00.0561107942.00.016299728087564163075927761371630759362974216299729351787
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047315451315451341943042560012243187200x7fbb0abd59800x7fbb0a2266c01097980010859836655361372474137247443919168.042238188.00.00.00.0198.00.02099630.00.02099843.00.02470.02097373.02099842.00.00.031.00.00.00.00.00.00.00.00.00.04194547.00.0398.00.00.00.048580.00.00.02031640.00.04194487.00.01066416692.00.016299729371936163075936935831630759457870816299730715117
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047615451315451341943042560012243214720x7fbb0abd58000x7fbb0a2267001097907210855859655361372383137238343916256.042891509.00.00.00.0197.00.02099584.00.02099848.00.02471.02097377.02099820.00.00.031.00.00.00.00.00.00.00.00.00.04194546.00.0398.00.00.00.040695.00.00.02031640.00.04194494.00.01072306360.00.016299730731926163075946574281630759553839416299732071087
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791545131545134194304256008243242240x7fbb0abd56800x7fbb0a2267401100924010884392655361376154137615444036928.034293570.00.00.00.0133.00.01051040.00.01051169.00.02442.01048727.01051172.00.00.031.00.00.00.00.00.00.00.00.00.02097326.00.0260.00.00.00.055355.00.00.0983064.00.02097270.00.0557364541.00.016299732088146163075956100741630759646976016299733404177
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821545131545134194304256008243264640x7fbb0cfbe5000x7fbb0a2267802131897621189563655362664871266487185275872.056067432.00.00.00.0130.00.01050536.00.01050662.00.01942.01048720.01050666.00.00.031.00.00.00.00.00.00.00.00.00.02097313.00.0252.00.00.00.053331.00.00.0983060.00.02097258.00.0571133608.00.016299733423357163075965353601630759823489016299735574959
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851545131545134194304256008243292160x7fbb0cfbe3800x7fbb0a2267c02134739221226576655362668423266842385389536.051992813.00.00.00.0132.00.01050984.00.01051113.00.02386.01048727.01051117.00.00.031.00.00.00.00.00.00.00.00.00.02097322.00.0254.00.00.00.049753.00.00.0983064.00.02097270.00.0575933624.00.016299735600879163075983289711630759999506116299737722932
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048815451315451341943042560012243319680x7fbb0cfbe2000x7fbb0a2268002137631221240434655362672038267203885505216.076142718.00.00.00.0202.00.02099638.00.02099843.00.02477.02097366.02099857.00.00.031.00.00.00.00.00.00.00.00.00.04194547.00.0398.00.00.00.048657.00.00.02031640.00.04194490.00.01088743075.00.016299737736641163076000824221630760180851216299739927913
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049115451315451341943042560012243347200x7fbb0cfbe0800x7fbb0a2268402134716021229724655362668394266839485388608.073416382.00.00.00.0203.00.02099560.00.02099786.00.02420.02097366.02099791.00.00.031.00.00.00.00.00.00.00.00.00.04194542.00.0390.00.00.00.043538.00.00.02031640.00.04194487.00.01092467963.00.016299739941813163076019131531630760362916416299742127435
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941545131545134194304256008243374720x7fbb0abd5f000x7fbb0a2268802140401621274659655362675501267550185616032.055248427.00.00.00.0131.00.01051040.00.01051169.00.02442.01048727.01051172.00.00.031.00.00.00.00.00.00.00.00.00.02097326.00.0260.00.00.00.052254.00.00.0983064.00.02097273.00.0574058520.00.016299742149834163076037166841630760539189416299744279527
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049715451315451341943042560082400x7fbb0abd5d800x7fbb0a2268c042048896419315026553652561115256111168195552.068798963.00.00.00.0126.00.01050536.00.01050664.00.01942.01048722.01050663.00.00.031.00.00.00.00.00.00.00.00.00.02097314.00.0254.00.00.00.049141.00.00.0983060.00.02097259.00.0576551943.00.016299744297687163076054811751630760884007516299748126322