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

79 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_CYCLESSQ_BUSY_CYCLESSQ_BUSY_CU_CYCLESSQ_WAVESSQ_WAVE_CYCLESGRBM_COUNTGRBM_GUI_ACTIVETA_TA_BUSY_sumTA_SH_FIFO_BUSY_sumTA_SH_FIFO_CMD_BUSY_sumTA_SH_FIFO_ADDR_BUSY_sumTA_BUFFER_COALESCED_READ_CYCLES_sumTA_BUFFER_COALESCED_WRITE_CYCLES_sumTA_ADDR_STALLED_BY_TC_CYCLES_sumTA_TOTAL_WAVEFRONTS_sumTA_ADDR_STALLED_BY_TD_CYCLES_sumTA_DATA_STALLED_BY_TC_CYCLES_sumTA_FLAT_WAVEFRONTS_sumTA_FLAT_READ_WAVEFRONTS_sumTA_FLAT_WRITE_WAVEFRONTS_sumTA_FLAT_ATOMIC_WAVEFRONTS_sumTA_FLAT_COALESCEABLE_WAVEFRONTS_sumTA_SH_FIFO_DATA_BUSY_sumTA_SH_FIFO_DATA_SFIFO_BUSY_sumTA_SH_FIFO_DATA_TFIFO_BUSY_sumTA_SQ_TA_CMD_CYCLES_sumTA_SP_TA_ADDR_CYCLES_sumTA_SP_TA_DATA_CYCLES_sumTA_SH_FIFO_ADDR_STARVED_WHILE_BUSY_CYCLES_sumTA_SH_FIFO_CMD_STARVED_WHILE_BUSY_CYCLES_sumTA_SH_FIFO_DATA_STARVED_WHILE_BUSY_CYCLES_sumTA_TA_SH_FIFO_STARVED_sumTA_BUFFER_WAVEFRONTS_sumTA_BUFFER_READ_WAVEFRONTS_sumTA_BUFFER_WRITE_WAVEFRONTS_sumTA_BUFFER_ATOMIC_WAVEFRONTS_sumTA_BUFFER_TOTAL_CYCLES_sumTA_BUFFER_COALESCABLE_WAVEFRONTS_sumDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000147071147071335544322560043241600x00x7f2230404280304623229596163844938152428823875332038077838077830852999.030478278.028313183.027565185.00.00.019857447.0524288.00.020515113.0524288.00.0524288.00.00.029700912.028009036.029452305.02097152.02097152.04194304.047.00.00.01254675.00.00.00.00.00.00.016101851410638161137977456401611379798740216101999674671
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00214707114707132768256001224138880x00x7f2230423f8026620816640314092535121733528332753327538325.035129.032231.030913.00.00.015119.04096.00.00.04096.04096.00.00.04096.00.00.00.016384.016384.00.00.00.00.01304.00.00.00.00.00.04096.016102005090371161138027986291611380281190916102005278617
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051470711470714194304256001224143360x7f22334cd3800x7f2230423fc01374336125289216191606655368279752317179117179112587106.012351663.011701257.011681359.00.00.011376649.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0262.00.00.045422.00.00.00.00.00.0524288.016102005568720161138028837501611380297607016102005848414
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081470711470714194304256001624150400x7f22334cd2000x7f223042400025309442400503310846816553622418542531636731636729163404.029148853.029414799.029413967.00.00.020345772.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.01328.00.00.00.00.00.00.016102006144767161138030098311611380319015216102006527969
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111470711470714194304256001624154880x7f22334cd0800x7f223042404024873362362056305963346553621266871531091631091628565559.028543210.027698054.027696046.00.00.021187799.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.01.00.00.0832.00.00.00.00.00.00.016102006817133161138032151121611380339591316102007182804
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141470711470714194304256001224159360x7f2230e2df000x7f22304240801493936136569117245858655368261217318674118674110770243.010510920.012582603.012559189.00.00.011625348.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0261.00.00.021565.00.00.00.00.00.0524288.016102007472348161138034205531611380351543416102007739252
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171470711470714194304256001224163840x7f2230e2dd800x7f22304240c01396000126718716379583655368876265317449917449912438558.012210616.011594871.011567472.00.00.010627553.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0115.00.00.039117.00.00.00.00.00.0524288.016102008025976161138035416741611380363383416102008328829
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201470711470714194304256001224170880x7f2230e2dc000x7f223042410013030001202487155789646553610178428916287416287414111258.014043776.014277164.014273775.00.00.012243175.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.043.00.00.010478.00.00.00.00.00.0524288.016102008628772161138036747941611380376711516102008942985
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231470711470714194304256001624177920x7f2230e2da800x7f223042414024787602378170308218386553622558658330984430984429409443.029391665.029437132.029436300.00.00.020868109.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0832.00.00.00.00.00.00.016102009229299161138037962351611380397559616102009642720
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261470711470714194304256001624184960x7f2230e2d9000x7f223042418024922802384358308618886553622426051431153431153429489322.029471587.029031926.029028006.00.00.020790030.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.03932.00.00.00.00.00.00.016102009929983161138040195971611380419831816102010341114
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291470711470714194304256001624192000x7f2230e2d7800x7f22304241c013080721207373156273686553610296297616350816350814241364.014221214.013716119.013679704.00.00.012151326.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0151.00.00.018176.00.00.00.00.00.0524288.016102010627338161138042261581611380431959816102010987760
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321470711470714194304256001624199040x7f2230e2d6000x7f22304242001313224120906515649507655369180210816415216415213571608.013422067.013923828.013907148.00.00.011692660.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.06.00.00.015114.00.00.00.00.00.0524288.016102011274344161138043567191611380445063916102011630846
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351470711470714194304256001224206080x7f22334cd4800x7f22304242401313320120785015639827655369731641916416416416413957484.013872510.014137234.014134573.00.00.012163723.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.044.00.00.016417.00.00.00.00.00.0524288.016102011928439161138045007191611380459432016102012282341
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381470711470714194304256001624213120x7f22334cd3000x7f223042428024771522373469307579216553622885643730964330964329360560.029351938.029235205.029234373.00.00.020860428.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0832.00.00.00.00.00.00.016102012571045161138046229601611380480184116102013021835
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411470711470714194304256001624220160x7f22334cd1800x7f22304242c024617122356479305036136553622165252230771330771329088061.029071306.029205433.029201551.00.00.020862398.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.03880.00.00.00.00.00.00.016102013309509161138048256811611380500552216102013725759
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441470711470714194304256001624227200x7f22334cd0000x7f22304243001320600121628415741214655368551211816507416507413764169.013566275.014186496.014177064.00.00.011541592.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0119.00.00.030254.00.00.00.00.00.0524288.016102014012673161138050439231611380513720316102014383415
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471470711470714194304256001224234240x7f2230e2de800x7f22304243401310424120660615604801655369037413416380216380213316085.013108102.013827492.013801188.00.00.011941351.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.046.00.00.023758.00.00.00.00.00.0524288.016102014670128161138051751231611380526920416102015032720
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501470711470714194304256001224241280x7f2230e2dd000x7f22304243801299424119666315493054655369085789116242716242713701151.013576727.014188968.014184192.00.00.012138081.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0125.00.00.03216.00.00.00.00.00.0524288.016102015327614161138053037641611380539592516102015639107
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531470711470714194304256001624248320x7f2230e2db800x7f22304243c024813042377935307775686553623116126631016231016229403751.029391390.029270771.029269939.00.00.021125417.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0832.00.00.00.00.00.00.016102015926271161138054263251611380560520616102016377321
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561470711470714194304256001624255360x7f2230e2da000x7f223042440024830802372230307349466553622161357931038431038429442232.029425245.029128614.029124683.00.00.020790862.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.01.00.00.03790.00.00.00.00.00.00.016102016663684161138056314461611380580968716102017059415
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591470711470714194304256001224262400x7f2230e2d8800x7f22304244401307400120310615576425655369988177416342416342413799031.013697506.013533938.013502018.00.00.011812997.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.079.00.00.053482.00.00.00.00.00.0524288.016102017346249161138058360871611380593016816102017655212
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621470711470714194304256001224269440x7f2230e2d7000x7f22304244801306152120414015561943655368826057516326816326813317909.013001434.013878816.013807474.00.00.010992169.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.083.00.00.0125064.00.00.00.00.00.0524288.016102017942476161138059684081611380606184916102018320547
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651470711470714194304256001224276480x7f22334cd5800x7f22304244c013201521214855157285896553610262410216501816501814172690.014089000.014060980.014052715.00.00.012103383.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.055.00.00.046170.00.00.00.00.00.0524288.016102018614871161138061024891611380619480916102018930854
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681470711470714194304256001624286080x7f22334cd4000x7f223042450024567682354384305000986553622371333130709530709529135190.029125818.029193315.029192483.00.00.020829431.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0832.00.00.00.00.00.00.016102019218298161138062205701611380639897116102019667948
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711470711470714194304256001624293120x7f22334cd2800x7f223042454024512002347234304221476553621037898930639930639929066406.029046484.028901629.028897735.00.00.020706561.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.03896.00.00.00.00.00.00.016102019955851161138064255311611380660569216102020397761
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741470711470714194304256001224300160x7f22334cd1000x7f22304245801297736119730815502545655369963922816221616221614060209.013978432.013528493.013494415.00.00.011913721.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.087.00.00.040471.00.00.00.00.00.0524288.016102020686235161138066344921611380672681316102021037037
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077147071147071419430425600824309760x7f2230e2df800x7f22304245c01302488120030815501324655369693123716281016281013781327.013478708.013046452.012795072.00.00.011129757.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0199.00.00.0207875.00.00.00.00.00.0524288.016102021323761161138067530531611380684505316102021677783
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801470711470714194304256001224316800x7f2230e2de000x7f22304246001301192119714915487375655369134702916264816264813626754.013510644.014197589.014193927.00.00.011465000.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0169.00.00.02631.00.00.00.00.00.0524288.016102021970297161138068781731611380697209416102022325079
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831470711470714194304256001624326400x7f2230e2dc800x7f223042464024486002343973303774626553622206824530607430607429117113.029108003.029231885.029231053.00.00.020716980.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0832.00.00.00.00.00.00.016102022611992161138069992941611380717977516102023063502
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861470711470714194304256001224336000x7f2230e2db000x7f223042468024501762345080303736786553621996242730627130627129049037.029036454.029049867.029046541.00.00.020904653.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.02989.00.00.00.00.00.00.016102023350246161138072029751611380738329616102023794296
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891470711470714194304256001224345600x7f2230e2d9800x7f22304246c01302240119819715495737655368923168216277916277913384103.013115663.013453359.013387066.00.00.011870755.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.051.00.00.076940.00.00.00.00.00.0524288.016102024082620161138074074571611380750153716102024435642
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092147071147071419430425600824355200x7f2230e2d8000x7f22304247001306432120169415518303655369062692116330316330313216648.012660280.012469421.012098122.00.00.010862112.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0225.00.00.0345271.00.00.00.00.00.0524288.016102024721876161138075258571611380762009816102025076928
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951470711470714194304256001224362240x7f2230e2d6800x7f22304247401314584121132115671092655369556718716432216432214048098.013877343.013443104.013380384.00.00.011404351.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0135.00.00.077086.00.00.00.00.00.0524288.016102025369351161138076525781611380774585916102025718613
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981470711470714194304256001224371840x7f22334cd5000x7f223042478024378962329784301947416553622180194830473630473628938573.028926321.029163588.029162756.00.00.020693911.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0832.00.00.00.00.00.00.016102026006377161138077700191611380794970016102026457397
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011470711470714194304256001224381440x7f22334cd3800x7f22304247c024340162330918302089296553621371788630425130425128855131.028840877.029041745.029038809.00.00.020639398.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.01.00.00.03061.00.00.00.00.00.00.016102026744451161138079756201611380815690116102027191911
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041470711470714194304256001224391040x7f22334cd2000x7f22304248001302072119689815466876655368377329316275816275813158007.012774051.013310860.013149672.00.00.010844204.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0189.00.00.0133891.00.00.00.00.00.0524288.016102027478814161138081821811611380827610216102027833637
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107147071147071419430425600824403200x7f22334cd0800x7f22304248401311160119981915471964655369115896216389416389413062383.012269863.012712370.012223847.00.00.09947004.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0572.00.00.0759926.00.00.00.00.00.0524288.016102028122130161138083004221611380839450216102028479622
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101470711470714194304256001224412800x7f2230e2df000x7f22304248801304088120157515541792655369442656716301016301013962888.013803335.013663573.013619051.00.00.011825385.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.071.00.00.046993.00.00.00.00.00.0524288.016102028772356161138084271431611380852138316102029123868
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131470711470714194304256001224422400x7f2230e2dd800x7f22304248c024518322346465303914876553622876042230647830647829022998.029013472.028981151.028980319.00.00.020671799.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0832.00.00.00.00.00.00.016102029410632161138085468231611380872650416102029854042
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161470711470714194304256001224432000x7f2230e2dc000x7f223042490024319362324711301132326553621272662530399130399128851626.028836725.028825132.028821719.00.00.020723909.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.03269.00.00.00.00.00.00.016102030141075161138087517851611380893098616102030593605
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119147071147071419430425600824441600x7f2230e2da800x7f22304249401309328120228215547538655368151881616366516366512674684.012041102.013343687.013225607.00.00.011431259.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0146.00.00.0184550.00.00.00.00.00.0524288.016102030880229161138089564261611380905066616102031248471
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221470711470714194304256001224453760x7f2230e2d9000x7f22304249801312480120476715533225655369361697316405916405912932286.011739034.011530692.010826906.00.00.010108383.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0517.00.00.0650816.00.00.00.00.00.0524288.016102031535634161138090754661611380917066716102031896916
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251470711470714194304256001224463360x7f2230e2d7800x7f22304249c01305744120374815566019655369018218716321716321713370308.012965364.013732391.013612656.00.00.011179870.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0259.00.00.0188165.00.00.00.00.00.0524288.016102032190120161138092031471611380929658816102032541442
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281470711470714194304256001224475520x7f2230e2d6000x7f2230424a0024284882323576301096906553622085856730356030356028786286.028775303.028902371.028901531.00.00.020397028.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0832.00.00.00.00.00.00.016102032827916161138093205881611380949930916102033269906
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311470711470714194304256001224485120x7f22334cd4800x7f2230424a4024242322308041298906266553619257260430302830302828545900.028519350.028512692.028508725.00.00.020281169.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.03868.00.00.00.00.00.00.016102033555910161138095258691611380970491016102033992140
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134147071147071419430425600824494720x7f22334cd3000x7f2230424a801290976118731015344797655369270007516137116137113320836.012926136.012692360.012394534.00.00.010507374.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0170.00.00.0445907.00.00.00.00.00.0524288.016102034280314161138097308301611380982331116102034643786
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371470711470714194304256001224506880x7f22334cd1800x7f2230424ac01310528120001415458525655369859023716381516381512109168.010184462.09975003.09093257.00.00.08250205.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0518.00.00.0920768.00.00.00.00.00.0524288.016102034931429161138098481111611380994155216102035244462
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401470711470714194304256001224516480x7f22334cd0000x7f2230424b001291816118975315383747655368932328216147616147613315548.012813233.013125837.012906320.00.00.010772013.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0264.00.00.0211306.00.00.00.00.00.0524288.016102035537166161138099741921611381006571216102035883918
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431470711470714194304256001224528640x7f2230e2de800x7f2230424b4024282802321398300750586553622309357730353430353428722543.028713444.028658318.028657478.00.00.020115364.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0832.00.00.00.00.00.00.016102036170272161138101066731611381028539416102036620582
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461470711470714194304256001224540800x7f2230e2dd000x7f2230424b8024357842330679301930506553621625741530447230447228826321.028812153.028491165.028487740.00.00.020178350.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.03.00.00.03601.00.00.00.00.00.00.016102036907065161138103109941611381049019516102037359195
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149147071147071419430425600824552960x7f2230e2db800x7f2230424bc01316680120903515603577655368743210416458416458412888572.012150037.012683150.012368893.00.00.010529727.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0270.00.00.0321481.00.00.00.00.00.0524288.016102037644389161138105153151611381061035616102038002231
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521470711470714194304256001224567680x7f2230e2da000x7f2230424c001297472119302915382008655369755630316218316218310156674.07754958.08059191.06870254.00.00.05474754.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0423.00.00.01230897.00.00.00.00.00.0524288.016102038289275161138106359561611381073179616102038651337
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551470711470714194304256001224577280x7f2230e2d8800x7f2230424c401300688119761215474832655369421384516258516258513469345.013034301.013066355.012837861.00.00.010512014.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0108.00.00.0240703.00.00.00.00.00.0524288.016102038943510161138107661961611381085947716102039298352
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581470711470714194304256001224589440x7f2230e2d7000x7f2230424c8024329522325239301180036553622104406030411830411828767843.028755290.028627405.028626521.00.00.020373797.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0905.00.00.00.00.00.00.016102039585046161138108849171611381106395816102040042566
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611470711470714194304256001224601600x7f22334cd5800x7f2230424cc024069362298653297788246553621416258830086630086628452090.028438302.028733580.028730479.00.00.020197894.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.02.00.00.03528.00.00.00.00.00.00.016102040330770161138110887581611381127163916102040783960
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164147071147071419430425600824613760x7f22334cd4000x7f2230424d001320032120442315527662655369398373316500316500313306057.012731038.011611579.011083975.00.00.010172109.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0264.00.00.0560735.00.00.00.00.00.0524288.016102041071403161138112962801611381139068016102041384217
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671470711470714194304256001224628480x7f22334cd2800x7f2230424d401348424124107215985426655361050851261685521685529136396.06748228.06121005.04992175.00.00.03694708.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0364.00.00.01162426.00.00.00.00.00.0524288.016102041670300161138114170801611381151644116102042029372
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701470711470714194304256001224638080x7f22334cd1000x7f2230424d801304296119988615496596655368561721416303616303612915784.012154181.012539088.012264415.00.00.011120099.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0234.00.00.0240745.00.00.00.00.00.0524288.016102042324436161138115490811611381164284216102042679038
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731470711470714194304256001224650240x7f2230e2df800x7f2230424dc024056562298231297447296553621752249730070630070628478401.028464868.028638789.028637951.00.00.020198456.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.01.00.00.0866.00.00.00.00.00.00.016102042966722161138116705221611381185100316102043407712
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761470711470714194304256001224662400x7f2230e2de000x7f2230424e0024005362290420296788176553621279954530006630006628408100.028394464.028599169.028595671.00.00.020012243.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.02.00.00.03469.00.00.00.00.00.00.016102043693506161138118751631611381205564416102044139556
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179147071147071419430425600824674560x7f2230e2dc800x7f2230424e401305544120160415488422655368841984416319216319213162237.012340153.012249194.011806824.00.00.010237041.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0355.00.00.0432492.00.00.00.00.00.0524288.016102044425919161138120802841611381217532516102044781791
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821470711470714194304256001224689280x7f2230e2db000x7f2230424e801410320130450016794297655361054072421762891762898300722.05727060.06126929.04964139.00.00.03321969.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0340.00.00.01208828.00.00.00.00.00.0524288.016102045069965161138121994851611381230316616102045439247
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851470711470714194304256001224701440x7f2230e2d9800x7f2230424ec01301160119003415366958655369057512716264416264413313540.012638901.012601066.012301556.00.00.011011102.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0240.00.00.0294104.00.00.00.00.00.0524288.016102045731620161138123366061611381242924616102046081013
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881470711470714194304256001224716160x7f2230e2d8000x7f2230424f0023945042291824297006636553621330916529931229931228327521.028320118.028220842.028219782.00.00.020245395.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.01.00.00.02083.00.00.00.00.00.00.016102046367936161138124548461611381263548816102046763837
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911470711470714194304256001224728320x7f2230e2d6800x7f2230424f4024085282307871298959656553622094608930106530106528532609.028526388.028566376.028565544.00.00.020310722.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0832.00.00.00.00.00.00.016102047051121161138126620481611381284380916102047496101
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194147071147071419430425600824740480x7f22334cd5000x7f2230424f801292216118975615343239655369457403516152616152613401689.012658871.011023613.09984148.00.00.09517033.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0624.00.00.0919273.00.00.00.00.00.0524288.016102047782165161138128673291611381296076916102048147027
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971470711470714194304256001224757760x7f22334cd3800x7f2230424fc01458280135349617458877655361138065001822841822847923548.05378224.04869101.03523605.00.00.01918981.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0340.00.00.01316824.00.00.00.00.00.0524288.016102048434420161138129850901611381309245016102048820212
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001470711470714194304256001224769920x7f22334cd2000x7f22304250001305320119355515413632655369532109116316416316413237985.012776221.012404197.012097592.00.00.010646927.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0215.00.00.0322275.00.00.00.00.00.0524288.016102049124775161138131270101611381322061116102049485267
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031470711470714194304256001224784640x7f22334cd0800x7f223042504024281842323319300611436553621973334230352230352228649713.028642255.028490111.028489091.00.00.020257040.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.01004.00.00.00.00.00.00.016102049771591161138132463711611381342541216102050222251
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061470711470714194304256001224799360x7f2230e2df000x7f223042508024052962298604297592046553622102259230066130066128424124.028414319.028273687.028272855.00.00.020257250.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0850.00.00.00.00.00.00.016102050511114161138134500521611381362957316102050961344
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209147071147071419430425600824814080x7f2230e2dd800x7f22304250c01300408119211415377962655369268530016255016255012967006.011647389.011626367.010955949.00.00.09343383.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0518.00.00.0821274.00.00.00.00.00.0524288.016102051248718161138136562941611381375133416102051608200
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121470711470714194304256001224831360x7f2230e2dc000x7f22304251001541752142686418403235655361217709051927181927186793252.04595432.04346928.03218768.00.00.01434382.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0311.00.00.01135909.00.00.00.00.00.0524288.016102051894434161138137769341611381389309516102052276695
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151470711470714194304256001224843520x7f2230e2da800x7f22304251401288488118856915355040655369149338416106016106013146222.012484028.013110743.012891495.00.00.010461095.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0230.00.00.0386213.00.00.00.00.00.0524288.016102052569119161138139383751611381403229616102052925441
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181470711470714194304256001224858240x7f2230e2d9000x7f223042518024133682307798298769326553622149154730167030167028459882.028453356.028538594.028537690.00.00.020068461.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0890.00.00.00.00.00.00.016102053212374161138140583761611381423949716102053662284
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211470711470714194304256001224872960x7f2230e2d7800x7f22304251c023826722276773295066796553620316690029783329783328163304.028142032.028279755.028278855.00.00.020027236.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.01306.00.00.00.00.00.00.016102053948158161138142655771611381444429816102054404958
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241470711470714194304256001224887680x7f2230e2d6000x7f22304252001310120119571215434883655369423243516376416376412719722.011058763.010634585.09708850.00.00.09468868.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0521.00.00.0846865.00.00.00.00.00.0524288.016102054691872161138144695781611381456525916102055059713
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271470711470714194304256001224907520x7f22334cd4800x7f22304252401612832150358319375773655361258763342016032016036615170.04356279.03991277.02835825.00.00.01183648.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0332.00.00.01138858.00.00.00.00.00.0524288.016102055347587161138145908591611381471246016102055738438
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301470711470714194304256001224919680x7f22334cd3000x7f22304252801294792119007915360601655368958395516184816184812790871.011996176.011741759.011265182.00.00.010262906.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0278.00.00.0341474.00.00.00.00.00.0524288.016102056031722161138147447801611381483950116102056401324
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331470711470714194304256001224934400x7f22334cd1800x7f22304252c024281202321235300592666553622072578030351430351428652667.028639042.028648273.028647425.00.00.020250878.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0840.00.00.00.00.00.00.016102056688957161138148641411611381504382216102057139067
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361470711470714194304256001224949120x7f22334cd0000x7f223042530023913362285858296314416553619326147429891629891628252530.028214616.028434111.028431974.00.00.019878503.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.02360.00.00.00.00.00.00.016102057427571161138150675021611381524718316102057882991
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391470711470714194304256001224963840x7f2230e2de800x7f22304253401291088118748815292378655369659738816138516138512247918.010536547.010908261.010109080.00.00.07880832.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0520.00.00.0877221.00.00.00.00.00.0524288.016102058171264161138152721431611381536750416102058545296
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421470711470714194304256001224983680x7f2230e2dd000x7f22304253801689680157860820338834655361262228122112092112096180948.04128187.04063104.02908465.00.00.0924982.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0290.00.00.01174075.00.00.00.00.00.0524288.016102058831230161138153921441611381551822516102059179652
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451470711470714194304256001224995840x7f2230e2db800x7f22304253c01291784118999515344493655369140208416147216147212913954.012087353.011997657.011542248.00.00.010055212.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0272.00.00.0615845.00.00.00.00.00.0524288.016102059472686161138155510251611381564542516102059828548
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024814707114707141943042560012241013120x7f2230e2da000x7f223042540024060242300988297980186553622022122130075230075228506431.028494850.028546164.028545308.00.00.019753277.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.01008.00.00.00.00.00.00.016102060117141161138156779061611381585614716102060572241
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025114707114707141943042560012241027840x7f2230e2d8800x7f223042544023864722280940295605576553621036774629830829830828235737.028225062.028381366.028378677.00.00.019937236.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.01.00.00.02387.00.00.00.00.00.00.016102060858575161138158806271611381605934816102061305775
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025414707114707141943042560012241042560x7f2230e2d7000x7f22304254801293120118852715330121655369876764916163916163911725464.09530281.09400342.08404271.00.00.06946172.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0459.00.00.01033264.00.00.00.00.00.0524288.016102061590729161138160836681611381617726916102061947391
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025714707114707141943042560012241062400x7f22334cd5800x7f22304254c01745168163964421178211655361443252192181452181456065740.04008494.03830865.02659994.00.00.0872239.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0269.00.00.01182404.00.00.00.00.00.0524288.016102062235164161138162017491611381633246916102062636885
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026014707114707141943042560012241077120x7f22334cd4000x7f22304255001278496117795815207754655368880688715981115981112691775.011677880.011560714.010964269.00.00.09579352.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0448.00.00.0524744.00.00.00.00.00.0524288.016102062930239161138163670301611381646015016102063294221
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026314707114707141943042560016241094400x7f22334cd2800x7f223042554023987842290909296645736553621217647829984729984728287235.028278429.028027278.028026398.00.00.019715544.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0858.00.00.00.00.00.00.016102063582395161138164863901611381666447116102064033454
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026614707114707141943042560016241111680x7f22334cd1000x7f223042558023839122274683294583506553620708692329798829798828111893.028101449.028117907.028116061.00.00.019724487.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.02.00.00.01810.00.00.00.00.00.00.016102064319968161138166887921611381686783316102064770858
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691470711470714194304256008241128960x7f2230e2df800x7f22304255c01296016119037715361510655369996851716200116200110876217.08315464.08403217.07224365.00.00.06824997.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0473.00.00.01174587.00.00.00.00.00.0524288.016102065057592161138168924731611381698847316102065425704
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027214707114707141943042560012241151360x7f2230e2de000x7f22304256001839440172827522305954655361476588742299292299295971794.03943024.03711406.02577410.00.00.0747559.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0297.00.00.01121630.00.00.00.00.00.0524288.016102065710797161138170142331611381715295416102066110728
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027514707114707141943042560012241166080x7f2230e2dc800x7f22304256401282592117816415203307655369719072016032316032312972862.012058139.011440698.010799836.00.00.010324428.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0361.00.00.0544601.00.00.00.00.00.0524288.016102066403342161138171867151611381728159516102066771554
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027814707114707141943042560016241183360x7f2230e2db000x7f223042568023921522289114296370126553621391277829901829901828197115.028184470.027993876.027992396.00.00.019708308.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0872.00.00.00.00.00.00.016102067057737161138173078351611381748767616102067509777
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028114707114707141943042560016241200640x7f2230e2d9800x7f22304256c023865362271193294183996553620346981929831629831628074131.028064544.028239912.028237016.00.00.019802633.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.02996.00.00.00.00.00.00.016102067796581161138175126361611381769423816102068254611
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028414707114707141943042560012241217920x7f2230e2d8000x7f223042570013080961206510155643606553610124782516351116351110263186.07625382.07476761.06178146.00.00.05292233.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0445.00.00.01343326.00.00.00.00.00.0524288.016102068540725161138177203181611381781727816102068910626
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028714707114707141943042560012241240320x7f2230e2d6800x7f22304257401925592180892823350951655361496801092406982406985687331.03799157.03611213.02491371.00.00.0626550.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0315.00.00.01119615.00.00.00.00.00.0524288.016102069197060161138178427181611381798719916102069559382
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029014707114707141943042560012241255040x7f22334cd5000x7f22304257801291272118671715305116655369766115916140816140812527177.011163526.010638972.09897208.00.00.08914944.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0463.00.00.0734918.00.00.00.00.00.0524288.016102069851665161138180211191611381811728016102070209878
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029314707114707141943042560012241274880x7f22334cd3800x7f22304257c023864882276096294544926553619656561929831029831028048260.028020710.027971720.027965827.00.00.019650059.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.03.00.00.07784.00.00.00.00.00.00.016102070496801161138181428801611381832368116102070955021
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029614707114707141943042560012241292160x7f22334cd2000x7f223042580023871922277174294871936553619838288429839829839828042936.028003442.027882668.027871447.00.00.019779754.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.01.00.00.08189.00.00.00.00.00.00.016102071241405161138183473611611381852800216102071695115
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029914707114707141943042560012241309440x7f22334cd0800x7f2230425840136168012497331613181765536987972441702091702098792796.06181968.06028241.04803692.00.00.04106274.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0265.00.00.01215213.00.00.00.00.00.0524288.016102071983068161138185520031611381865104316102072358860
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030214707114707141943042560012241334400x7f2230e2df000x7f22304258802076488196891725426350655361719324972595602595604633990.03350395.03207709.02507544.00.00.0545883.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0460.00.00.0709492.00.00.00.00.00.0524288.016102072644814161138186742431611381883024416102073072204
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030514707114707141943042560012241349120x7f2230e2dd800x7f22304258c01294656118821015322880655369808860716183116183111463668.09479600.09480286.08479165.00.00.07276965.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0501.00.00.01049207.00.00.00.00.00.0524288.016102073364568161138188628841611381895872516102073725140
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030814707114707141943042560012241368960x7f2230e2dc000x7f223042590023644082260374292417416553620274837129555029555027901763.027880928.027906160.027896824.00.00.019614019.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.07.00.00.07339.00.00.00.00.00.00.016102074010273161138189860851611381916464616102074458783
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031114707114707141943042560012241388800x7f2230e2da800x7f223042594023719922268089293676986553620760098729649829649827964624.027955446.027932845.027930088.00.00.019352996.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.03.00.00.01945.00.00.00.00.00.00.016102074743817161138191896061611381936960716102075146608
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031414707114707141943042560012241408640x7f2230e2d9000x7f22304259801437176132573917091817655361057347811796461796468330682.05539102.05129227.03764403.00.00.02401066.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0199.00.00.01366739.00.00.00.00.00.0524288.016102075431862161138193931281611381950080816102075761824
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031714707114707141943042560012241436160x7f2230e2d7800x7f22304259c02234376212822827507685655361941159842792962792964586730.03290144.03160946.02461192.00.00.0553454.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0453.00.00.0712565.00.00.00.00.00.0524288.016102076047998161138195262481611381969744916102076491208
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032014707114707141943042560012241453440x7f2230e2d6000x7f2230425a001293552119265115364307655369886936916169316169310076638.07748886.07501346.06141696.00.00.04932433.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0372.00.00.01295878.00.00.00.00.00.0524288.016102076783712161138197313701611381982689016102077148374
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032314707114707141943042560012241475840x7f22334cd4800x7f2230425a4023674642257276291775736553619901400129593229593227712847.027699455.027685899.027681128.00.00.019271657.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.05273.00.00.00.00.00.00.016102077436447161138198515301611382003585116102077882657
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032614707114707141943042560012241495680x7f22334cd3000x7f2230425a8023696722266993293398676553620884108829620829620827942585.027931766.027681531.027677681.00.00.019459432.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.02.00.00.04840.00.00.00.00.00.00.016102078170891161138200595321611382024081316102078626331
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032914707114707141943042560012241515520x7f22334cd1800x7f2230425ac01496016138513817861131655361130996691870011870018203768.05136265.04762091.03230323.00.00.01364557.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0185.00.00.01534900.00.00.00.00.00.0524288.016102078912675161138202656131611382037697316102079292436
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033214707114707141943042560012241543040x7f22334cd0000x7f2230425b002405608229093029561128655362024468753007003007004591951.03321033.03142841.02441455.00.00.0519982.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0407.00.00.0697078.00.00.00.00.00.0524288.016102079578960161138204008141611382058209516102080030330
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033514707114707141943042560012241562880x7f2230e2de800x7f2230425b401363000126255916284629655361071585281703741703748586798.05921336.05677933.04493142.00.00.02906003.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0307.00.00.01225453.00.00.00.00.00.0524288.016102080322203161138206142551611382071537516102080682975
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033814707114707141943042560012241587840x7f2230e2dd000x7f2230425b8023857842252923291304056553615745624629822229822225198749.024514077.027328395.027281627.00.00.017864709.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.050.00.00.0170102.00.00.00.00.00.00.016102080969639161138207396961611382092641716102081420199
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034114707114707141943042560012241610240x7f2230e2db800x7f2230425bc023649442255846291373606553619192030029561729561727480176.027430824.027530202.027507955.00.00.019114211.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.026.00.00.0119490.00.00.00.00.00.00.016102081704923161138209500971611382113473816102082159893
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034414707114707141943042560012241632640x7f2230e2da000x7f2230425c001648808153913319844856655361327036432061002061007183956.04557904.04283109.02936201.00.00.0930769.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0192.00.00.01370451.00.00.00.00.00.0524288.016102082446216161138211580981611382128081916102082848707
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034714707114707141943042560012241665280x7f2230e2d8800x7f2230425c402719656260929533717829655362415915053399563399564526816.03213368.03069097.02403766.00.00.0479124.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0371.00.00.0666493.00.00.00.00.00.0524288.016102083134091161138213059391611382151282016102083626820
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035014707114707141943042560012241685120x7f2230e2d7000x7f2230425c80149399213749231774017665536995725221867481867487561106.04741700.04445642.03038937.00.00.01421672.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0203.00.00.01412963.00.00.00.00.00.0524288.016102083898344161138215617801611382167250116102084274366
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035314707114707141943042560012241712640x7f22334cd5800x7f2230425cc023593682245050289532996553618236850129492029492026873803.026701673.025209117.024981103.00.00.018651136.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.0204.00.00.0295966.00.00.00.00.00.00.016102084559439161138216998611611382188306216102084959111
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035614707114707141943042560012241737600x7f22334cd4000x7f2230425d0023794642268338292538526553619478229729743229743227177837.027008126.025500069.025275478.00.00.018503298.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.0225.00.00.0336661.00.00.00.00.00.00.016102085244924161138219077021611382209490416102085693764
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035914707114707141943042560012241762560x7f22334cd2800x7f2230425d401802464169194921851145655361431362552253072253076633530.04049794.03810407.02398988.00.00.0534055.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0134.00.00.01388618.00.00.00.00.00.0524288.016102085979538161138221208241611382225538516102086398449
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036214707114707141943042560012241797760x7f22334cd1000x7f2230425d803039880293128037897803655362784958783799843799844519076.03213895.03101890.02440413.00.00.0506058.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0398.00.00.0651121.00.00.00.00.00.0524288.016102086685712161138222792251611382251122616102087211941
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036514707114707141943042560012241822720x7f2230e2df800x7f2230425dc01680960157531120351023655361423505202101192101196722898.04352134.04027532.02487445.00.00.0676518.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0199.00.00.01515055.00.00.00.00.00.0524288.016102087485444161138225817861611382270866716102087878096
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036814707114707141943042560012241855360x7f2230e2de000x7f2230425e0024466482326711299323556553618934769130583030583021615094.020738774.020749357.020134356.00.00.011850580.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.0129.00.00.0734015.00.00.00.00.00.00.016102088163939161138227347471611382292882916102088631409
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037114707114707141943042560012241885440x7f2230e2dc800x7f2230425e4024848642344809302116676553617429208931060731060721459414.019777707.018980564.018190568.00.00.09964078.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.0306.00.00.0792043.00.00.00.00.00.00.016102088917203161138229542691611382314675016102089405072
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037414707114707141943042560012241915520x7f2230e2db000x7f2230425e802127312202020726094778655361824924522659132659135016248.03333316.03127539.02305490.00.00.0518363.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0124.00.00.0845906.00.00.00.00.00.0524288.016102089671406161138231710701611382333107116102090094407
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037714707114707141943042560012241958400x7f2230e2d9800x7f2230425ec03695440357695146294606655363379343504619294619294716893.03227385.03102863.02466693.00.00.0560976.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0239.00.00.0636994.00.00.00.00.00.0524288.016102090382600161138233550711611382363875316102090960887
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038014707114707141943042560012241985920x7f2230e2d8000x7f2230425f001959888184311423725978655361447613272449852449857214250.04486937.04159938.02371224.00.00.0390258.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0102.00.00.01806679.00.00.00.00.00.0524288.016102091232901161138237078731611382385699416102091653842
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038314707114707141943042560012242023680x7f2230e2d6800x7f2230425f4026807842565835330680766553621191405833509733509719370501.018228117.017128126.016178371.00.00.09339916.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.0117.00.00.0871861.00.00.00.00.00.00.016102091939316161138238832341611382409251516102092436245
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038614707114707141943042560012242058880x7f22334cd5000x7f2230425f8026550242517903324877706553619528100533187733187719187494.016433522.015184738.013934835.00.00.07703739.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.0334.00.00.01327437.00.00.00.00.00.00.016102092704909161138241542761611382436051716102093198388
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038914707114707141943042560012242094080x7f22334cd3800x7f2230425fc02447064234071230296013655362245337373058823058825190672.03436329.03214062.02317915.00.00.0469667.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0105.00.00.0866526.00.00.00.00.00.0524288.016102093465922161138244254771611382461139816102093918062
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039214707114707141943042560012242144640x7f22334cd2000x7f22304260004338248422211654681539655364055819955422805422804521884.03156804.03057710.02467455.00.00.0614352.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0290.00.00.0597707.00.00.00.00.00.0524288.016102094204266161138246371591611382497172116102094840251
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039514707114707141943042560012242177280x7f22334cd0800x7f22304260402184080207010226723721655361811997102730092730096668778.04357676.04058996.02389799.00.00.0455690.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0208.00.00.01674680.00.00.00.00.00.0524288.016102095113835161138250149211611382518260216102095537696
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039814707114707141943042560012242220160x7f2230e2df000x7f223042608029504722838283364615726553624705252436880836880818005738.016663727.013665999.012452444.00.00.07015814.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.0138.00.00.01181945.00.00.00.00.00.00.016102095825810161138252075621611382543716316102096347318
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040114707114707141943042560012242260480x7f2230e2dd800x7f22304260c029279922817368362863826553625123585936599836599819277161.015964038.013515117.011938537.00.00.06493823.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.0214.00.00.01596823.00.00.00.00.00.00.016102096613042161138254712441611382570020516102097129581
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040414707114707141943042560012242300800x7f2230e2dc000x7f22304261002778888266723034429322655362412355213473603473605190772.03402391.03164531.02277538.00.00.0442164.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.082.00.00.0922065.00.00.00.00.00.0524288.016102097395085161138257395651611382595108616102097889744
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040714707114707141943042560012242359040x7f2230e2da800x7f22304261404991984487293763098004655364709103286239976239974549542.03177268.03095473.02497185.00.00.0671943.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0254.00.00.0597306.00.00.00.00.00.0524288.016102098160888161138259851671611382637076916102098845033
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041014707114707141943042560012242394240x7f2230e2d9000x7f22304261802428544231664029961817655362154084543035673035676880662.04481170.04094412.02383974.00.00.0464935.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0186.00.00.01705235.00.00.00.00.00.0524288.016102099117027161138264416491611382662981016102099567747
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041314707114707141943042560012242442240x7f2230e2d7800x7f22304261c031990963085137398015486553627016319839988639988616480592.014938554.013118996.011726898.00.00.06100628.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.098.00.00.01388146.00.00.00.00.00.00.016102099853680161138266539711611382690405216102100343559
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041614707114707141943042560012242487680x7f2230e2d6000x7f223042620031295843021318391113326553629138907439119739119715178333.011766900.09102821.07274694.00.00.02852371.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.0265.00.00.01836877.00.00.00.00.00.00.016102100608743161138269659721611382721445416102101146692
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041914707114707141943042560012242533120x7f22334cd4800x7f22304262403103056298932838666745655362788002793878813878815144430.03378352.03253413.02320653.00.00.0513966.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0105.00.00.0882325.00.00.00.00.00.0524288.016102101412436161138272803741611382751749616102101953384
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221470711470714194304256008242555520x7f22334cd3000x7f223042628057583765638070729332146553653704361771979671979615201964.06848726.05957500.02155826.00.00.053277.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.00.00.00.03817415.00.00.00.00.00.0524288.016102102225178161138275811761611382803525916102102972561
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042514707114707141943042560012242598400x7f22334cd1800x7f22304262c02911408280160436209978655362586526633639253639257234003.04510790.04178168.02389631.00.00.0445127.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0192.00.00.01773228.00.00.00.00.00.0524288.016102103245605161138281038991611382833030116102103746994
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042814707114707141943042560012242656640x7f22334cd0000x7f223042630037646563653475472740706553635112347547058147058114409489.011754171.09389113.07745326.00.00.01863249.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.0380.00.00.01635572.00.00.00.00.00.00.016102104015568161138283944611611382869254316102104601745
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043114707114707141943042560012242712320x7f2230e2de800x7f223042634037915043680063475638836553634910278747393747393714126368.012102790.010064002.08843608.00.00.02831121.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.0215.00.00.01231152.00.00.00.00.00.00.016102104868509161138287557431611382905462516102105462326
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341470711470714194304256008242732160x7f2230e2dd000x7f223042638038572883746624484998536553635692791948216048216014711071.06815132.05931303.02139461.00.00.079666.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.02.00.00.03791648.00.00.00.00.00.0524288.016102105727400161138291191051611382941574716102106310357
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371470711470714194304256008242757120x7f2230e2db800x7f22304263c070528966927462896884386553667699807088161188161114834324.06712428.05851082.02166951.00.00.094014.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.02.00.00.03669959.00.00.00.00.00.0524288.016102106576891161138294834271611383004039116102107429242
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044014707114707141943042560012242807680x7f2230e2da000x7f22304264003410208330082142710911655363130051404262754262756120846.03819180.03516126.02308640.00.00.0318246.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.092.00.00.01222123.00.00.00.00.00.0524288.016102107699656161138300947911611383035847316102108250444
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044314707114707141943042560012242876160x7f2230e2d8800x7f223042644044042164297773555513186553640798798555052655052614142045.011801815.09863039.08437093.00.00.02065303.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.0139.00.00.01331404.00.00.00.00.00.00.016102108516508161138304234331611383077383516102109160994
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044614707114707141943042560012242942080x7f2230e2d7000x7f223042648044206084303495556491066553640576836555257555257514093693.011651318.09818569.08631080.00.00.02312877.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.0201.00.00.01129215.00.00.00.00.00.00.016102109423688161138308383151611383118823716102110065364
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491470711470714194304256008242969600x7f22334cd5800x7f22304264c045011444390838568180976553641957417656264256264215019429.06849294.05977011.02162389.00.00.072316.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.02.00.00.03819446.00.00.00.00.00.0524288.016102110337468161138312560781611383160360016102110979034
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521470711470714194304256008242999680x7f22334cd4000x7f223042650083373528216591106443594655368051830571042168104216814905026.06705770.05788101.02155644.00.00.061769.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.00.00.00.03662439.00.00.00.00.00.0524288.016102111245978161138316652001611383232696416102112199836
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551470711470714194304256008243027200x7f22334cd2800x7f223042654057858325658914732352926553655162728872322872322815183678.06876573.05940770.02135698.00.00.063608.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.00.00.00.03808538.00.00.00.00.00.0524288.016102112473500161138323989651611383284600716102113209884
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045814707114707141943042560012243054720x7f22334cd1000x7f223042658057999845683410735460356553654293257472499772499720858843.013078547.06843395.02971866.00.00.0788608.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.097.00.00.03865140.00.00.00.00.00.00.016102113478478161138329103281611383337561016102114184102
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046114707114707141943042560012243082240x7f2230e2df800x7f22304265c057757365666680733521516553655569828172196672196620772732.013003937.06862969.02999382.00.00.0765702.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.098.00.00.03860855.00.00.00.00.00.00.016102114451077161138334477711611383391049416102115156311
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641470711470714194304256008243109760x7f2230e2de000x7f223042660058303525702485737073496553654783670572879372879315223618.06886173.05976618.02170013.00.00.061317.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.00.00.00.03819438.00.00.00.00.00.0524288.016102115420665161138339509741611383440297616102116110740
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671470711470714194304256008243132160x7f2230e2dc800x7f223042664010936424108154971401459806553610613638751367052136705215025390.06771661.05838773.02139267.00.00.056763.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.01.00.00.03696313.00.00.00.00.00.0524288.016102116376624161138344724171611383534218216102117532418
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701470711470714194304256008243159680x7f2230e2db000x7f223042668010980832108548061406140476553610813288261372603137260315293823.06831566.05900453.02164263.00.00.093041.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.00.00.00.03761274.00.00.00.00.00.0524288.016102117805372161138354181821611383627194816102118955497
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047314707114707141943042560012243187200x7f2230e2d9800x7f22304266c010981560108598511407027416553610752396351372694137269421307310.013128643.06798976.02897254.00.00.0755928.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.084.00.00.03896617.00.00.00.00.00.00.016102119217791161138363365881611383722155316102120415904
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047614707114707141943042560012243214720x7f2230e2d8000x7f223042670010984328108488551405161256553610658244001373040137304021203858.013083153.06797920.02914880.00.00.0725258.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.0101.00.00.03881744.00.00.00.00.00.00.016102120682758161138372861941611383816475916102121873452
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791470711470714194304256008243242240x7f2230e2d6800x7f223042674010998456108833671410201666553610828785561374806137480615370389.06866930.05963961.02188217.00.00.082876.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.02.00.00.03766433.00.00.00.00.00.0524288.016102122139226161138382421991611383910236416102123267211
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821470711470714194304256008243264640x7f22334cd5000x7f223042678021308096211821032745352926553621232428442663511266351114682233.06603277.05756170.02163628.00.00.078709.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.00.00.00.03585347.00.00.00.00.00.0524288.016102123531955161138391726051611384087117516102125581870
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851470711470714194304256008243292160x7f22334cd3800x7f22304267c021336672212258212750972546553621236855992667083266708315837561.06929526.06005965.02165470.00.00.085563.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.00.00.00.03844710.00.00.00.00.00.0524288.016102125806745161138409737351611384263918516102127793851
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048814707114707141943042560012243319680x7f22334cd2000x7f223042680021368912212376472751990556553621319413792671113267111322013749.013294360.06744912.02805138.00.00.0666935.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.080.00.00.03942275.00.00.00.00.00.00.016102128012996161138427295861611384445487616102130082190
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049114707114707141943042560012243347200x7f22334cd0800x7f223042684021350976212253612750961426553621207541532668871266887122063919.013333501.06706558.02767258.00.00.0776635.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.074.00.00.03936428.00.00.00.00.00.00.016102130298885161138445438371611384625856716102132366799
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941470711470714194304256008243374720x7f2230e2df000x7f223042688021398024212636512755073426553621303212692674752267475215806576.06930924.05983925.02150280.00.00.076932.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.00.00.00.03833330.00.00.00.00.00.0524288.016102132581965161138463508871611384802513716102134611070
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049714707114707141943042560082400x7f2230e2dd800x7f22304268c042049168419279925434006216553642300047835256145525614514588176.06583880.05745892.02156940.00.00.097921.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.00.00.00.03563136.00.00.00.00.00.0524288.016102134828195161138481129781611385147059816102138535143