Files
rocm-systems/tests/workloads/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.kd000145593145593335544322560043241600x00x7fc075e04280308660029991363894380552428824250542238582438582431218489.030844323.028229379.027478990.00.00.019970745.0524288.00.020911587.0524288.00.0524288.00.00.029781861.028088624.029252073.02097152.02097152.04194304.077.00.00.01245507.00.00.00.00.00.00.016062052903004160740444517351607404469253716062204068440
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00214559314559332768256001224138880x00x7fc075e23f8027356815861714652575121782234341953419535277.030729.037671.036325.00.00.016621.04096.00.00.04096.04096.00.00.04096.00.00.00.016384.016384.00.00.00.00.01341.00.00.00.00.00.04096.016062209486770160740494898451607404950344516062209674865
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051455931455934194304256001224143360x7fc078d533800x7fc075e23fc01410112128071216509767655368043964617626317626311638605.011329706.012043703.012011243.00.00.09081557.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0160.00.00.043360.00.00.00.00.00.0524288.016062209964069160740495693661607404966136616062210260012
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081455931455934194304256001624150400x7fc078d532000x7fc075e2400024652242356825305185386553621175579730815230815229166999.029157849.028582824.028581512.00.00.021263820.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.01256.00.00.00.00.00.00.016062210553536160740496949661607404987272716062210999186
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111455931455934194304256001624154880x7fc078d530800x7fc075e2404025046162384849308683786553622560248831307631307628806289.028786937.028707646.028706334.00.00.019628958.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.07712.00.00.00.00.00.00.016062211286950160740498991281607405007832916062211639412
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141455931455934194304256001224159360x7fc0765fbf000x7fc075e240801338232122417315830544655367471275816727816727812740734.012354003.013564072.013545845.00.00.010150071.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0144.00.00.054019.00.00.00.00.00.0524288.016062211928455160740501117691607405020568916062212268908
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171455931455934194304256001224163840x7fc0765fbd800x7fc075e240c01324736121261215688938655367631934616559116559113166412.012810973.012332249.012292540.00.00.09073137.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.022.00.00.039059.00.00.00.00.00.0524288.016062212555461160740502309701607405032345016062212891884
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201455931455934194304256001224170880x7fc0765fbc000x7fc075e241001378432125767016256501655369265469217230317230312734557.012607463.013525771.013508211.00.00.012079312.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.03.00.00.019309.00.00.00.00.00.0524288.016062213189657160740503632901607405045577116062213456421
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231455931455934194304256001624177920x7fc0765fba800x7fc075e2414024839442369767307088306553622534465131049231049229326988.029318628.029227084.029226252.00.00.020889569.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0832.00.00.00.00.00.00.016062213744515160740504874511607405066761216062214191105
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261455931455934194304256001624184960x7fc0765fb9000x7fc075e2418024786802358245305468836553621312578430983430983428485049.028450355.029227563.029223659.00.00.020936534.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.03960.00.00.00.00.00.00.016062214477419160740506994521607405088009416062214827421
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291455931455934194304256001624192000x7fc0765fb7800x7fc075e241c01459704133906617027934655368647407518246218246212246372.011941713.013244357.013187380.00.00.011016992.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.023.00.00.039858.00.00.00.00.00.0524288.016062215116095160740509240941607405101769416062215391479
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321455931455934194304256001624199040x7fc0765fb6000x7fc075e242001404632128582716573639655369480315517557817557813090393.012932412.014298703.014294187.00.00.011855344.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.078.00.00.02773.00.00.00.00.00.0524288.016062215679772160740510464951607405113945516062215959256
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351455931455934194304256001224206080x7fc078d534800x7fc075e242401412400128795416578009655369319693017654917654912380890.012191288.013526675.013506230.00.00.012205701.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.030.00.00.024321.00.00.00.00.00.0524288.016062216259429160740511720951607405126553616062216538233
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381455931455934194304256001624213120x7fc078d533000x7fc075e2428024688642360960305868106553622469146630860730860729187955.029183978.029354548.029353716.00.00.020998739.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0832.00.00.00.00.00.00.016062216828917160740512976961607405147817716062217251337
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411455931455934194304256001624220160x7fc078d531800x7fc075e242c024897762378249307867456553621750848431122131122129325828.029301211.029137604.029133636.00.00.020795123.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.03956.00.00.00.00.00.00.016062217539101160740515063371607405168889816062217972681
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441455931455934194304256001624227200x7fc078d530000x7fc075e243001324480122043515779725655369360165016555916555913952721.013769150.013437174.013391484.00.00.011384461.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.094.00.00.024402.00.00.00.00.00.0524288.016062218260325160740517178591607405181113916062218597377
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471455931455934194304256001224234240x7fc0765fbe800x7fc075e243401310096120521715574441655368527147416376116376113453501.013231524.013144720.013082105.00.00.011418175.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.084.00.00.038591.00.00.00.00.00.0524288.016062218882861160740518405791607405193434016062219240463
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501455931455934194304256001224241280x7fc0765fbd000x7fc075e2438013126001208276156433396553610191889916407416407414061610.014007311.014159621.014157141.00.00.011572720.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.02.00.00.08876.00.00.00.00.00.0524288.016062219535097160740519676201607405206074116062219843630
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531455931455934194304256001624248320x7fc0765fbb800x7fc075e243c024727762366426306485546553622747507430909630909629225657.029204498.029168588.029167756.00.00.021016124.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0832.00.00.00.00.00.00.016062220130923160740520959411607405227466216062220574694
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561455931455934194304256001624255360x7fc0765fba000x7fc075e2440024557442344759303630826553621324029830696730696729019785.029000482.029007086.029003158.00.00.020887234.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.03877.00.00.00.00.00.00.016062220860987160740523015421607405248138316062221254529
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591455931455934194304256001224262400x7fc0765fb8800x7fc075e244401317288121198215691234655369573556016466016466013813944.013717681.013419589.013378641.00.00.012029643.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.03.00.00.041444.00.00.00.00.00.0524288.016062221541112160740525085831607405260266416062221849385
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621455931455934194304256001224269440x7fc0765fb7000x7fc075e244801307024120226815564041655369416624516337716337713944045.013740024.013878039.013826544.00.00.011368977.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0103.00.00.022830.00.00.00.00.00.0524288.016062222136469160740526305041607405272394516062222447082
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651455931455934194304256001224276480x7fc078d535800x7fc075e244c01303056119649315490810655369412613716288116288113794584.013698311.013710339.013688090.00.00.011908710.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.031.00.00.041082.00.00.00.00.00.0524288.016062222741446160740527573851607405284970616062223096488
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681455931455934194304256001624286080x7fc078d534000x7fc075e2450024385682336983302860586553621900259830482030482028901883.028890224.029137192.029136360.00.00.020914314.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0832.00.00.00.00.00.00.016062223383221160740528821861607405306138716062223820942
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711455931455934194304256001624293120x7fc078d532800x7fc075e2454024523522347865304051266553621475452430654330654328935804.028916481.029325947.029322069.00.00.020619853.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.03893.00.00.00.00.00.00.016062224107575160740530855471607405326778816062224546786
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741455931455934194304256001224300160x7fc078d531000x7fc075e245801295424119241215421107655368225617916192716192713300466.012954325.013386466.013340053.00.00.011895275.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.028.00.00.037287.00.00.00.00.00.0524288.016062224834439160740533156281607405340778916062225187441
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077145593145593419430425600824309760x7fc0765fbf800x7fc075e245c01308856120202015512619655367950822416360616360612846849.012222113.013110026.012891115.00.00.011325471.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0158.00.00.0208331.00.00.00.00.00.0524288.016062225473735160740534351491607405352699016062225824227
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801455931455934194304256001224316800x7fc0765fbe000x7fc075e2460012985041195739154876956553610462031916231216231214110750.014089456.014030549.014026680.00.00.011867895.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0131.00.00.024248.00.00.00.00.00.0524288.016062226116871160740535597901607405365275016062226464613
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831455931455934194304256001624326400x7fc0765fbc800x7fc075e2464024409282329782301904806553622091820730511530511528884441.028875916.028785475.028784643.00.00.020526678.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0840.00.00.00.00.00.00.016062226749667160740536812311607405386123216062227191287
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861455931455934194304256001224336000x7fc0765fbb000x7fc075e2468024527362347982304237426553621939883230659130659129078342.029065081.029270081.029267042.00.00.020696480.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.03151.00.00.00.00.00.00.016062227477211160740538881121607405406891316062227916501
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891455931455934194304256001224345600x7fc0765fb9800x7fc075e246c01304024120005015522000655369149060116300216300213601764.013404293.013600264.013550885.00.00.011945831.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.026.00.00.081653.00.00.00.00.00.0524288.016062228202854160740541111531607405420555416062228554407
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092145593145593419430425600824355200x7fc0765fb8000x7fc075e247001312504120629715576144655368928762616406216406213251389.012673053.012762248.012488739.00.00.010491508.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0297.00.00.0312768.00.00.00.00.00.0524288.016062228840860160740542337141607405432779516062229197382
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951455931455934194304256001224362240x7fc0765fb6800x7fc075e247401311064120449115591864655369548070816388216388213623866.013454386.013247780.013175788.00.00.011783855.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.040.00.00.047774.00.00.00.00.00.0524288.016062229488486160740543615551607405445547516062229836348
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981455931455934194304256001224371840x7fc078d535000x7fc075e2478024527122347867304330026553622360469430658830658829138934.029120728.028987577.028986745.00.00.020721932.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0832.00.00.00.00.00.00.016062230123602160740544853961607405466459716062230586462
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011455931455934194304256001224381440x7fc078d533800x7fc075e247c024700802363357306246926553621965444930875930875929234265.029221095.028713600.028710392.00.00.020496417.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.03096.00.00.00.00.00.00.016062230872655160740546897171607405487003816062231323615
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041455931455934194304256001224391040x7fc078d532000x7fc075e248001300224119402515446006655369367535316252716252713416354.013147859.013645643.013546091.00.00.011622648.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0230.00.00.0136295.00.00.00.00.00.0524288.016062231612489160740548940381607405498699916062231976611
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107145593145593419430425600824403200x7fc078d530800x7fc075e248401304400119791415458610655368634532216304916304912818750.011696813.011993200.011274828.00.00.010110386.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0652.00.00.0563149.00.00.00.00.00.0524288.016062232262724160740550108391607405510507916062232615947
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101455931455934194304256001224412800x7fc0765fbf000x7fc075e248801310640120730015609406655369915969616382916382913636119.013524458.013327585.013248834.00.00.011998889.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.035.00.00.0190781.00.00.00.00.00.0524288.016062232907580160740551375601607405523132016062233257492
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131455931455934194304256001224422400x7fc0765fbd800x7fc075e248c024488802344373303713276553622966405430610930610929004198.028997426.028639375.028638543.00.00.020683921.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0832.00.00.00.00.00.00.016062233543946160740552558001607405543532116062233981886
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161455931455934194304256001224432000x7fc0765fbc000x7fc075e2490024586562346882304107556553621959502530733130733129125889.029109731.028854903.028851671.00.00.020442742.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.03254.00.00.00.00.00.00.016062234269020160740554593211607405564092316062234715090
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119145593145593419430425600824441600x7fc0765fba800x7fc075e249401306952120235715535375655369385391616336816336813503963.013188942.013327999.013216448.00.00.011429648.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0117.00.00.0128480.00.00.00.00.00.0524288.016062235000424160740556658831607405575932316062235361806
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221455931455934194304256001224453760x7fc0765fb9000x7fc075e249801298408119635115423616655369446925816230016230012923321.011798380.011798800.011178796.00.00.010029593.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0542.00.00.0638086.00.00.00.00.00.0524288.016062235647349160740557905231607405588556416062236013211
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251455931455934194304256001224463360x7fc0765fb7800x7fc075e249c01306880119894515508545655369362344316335916335913736551.013393856.013055152.012829285.00.00.011676767.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0173.00.00.0149642.00.00.00.00.00.0524288.016062236303945160740559180441607405601100516062236654657
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281455931455934194304256001224475520x7fc0765fb6000x7fc075e24a0024473762341715303302056553621839059430592130592128956455.028947493.028953711.028952879.00.00.020273764.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0832.00.00.00.00.00.00.016062236940561160740560374051607405621596616062237388001
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311455931455934194304256001224485120x7fc078d534800x7fc075e24a4024335922325500300880836553621570687230419830419828707874.028691498.028526795.028522956.00.00.020177836.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.02.00.00.03415.00.00.00.00.00.00.016062237673124160740562406061607405642188716062238108775
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134145593145593419430425600824494720x7fc078d533000x7fc075e24a801309128119344015401343655368466289816364016364013063037.012440728.012300113.011938524.00.00.010956752.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0215.00.00.0239789.00.00.00.00.00.0524288.016062238396108160740564466871607405653932816062238754450
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371455931455934194304256001224506880x7fc078d531800x7fc075e24ac01292288118798515301349655369789762916153516153512104332.010219338.09804289.08906985.00.00.08055096.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0453.00.00.0893387.00.00.00.00.00.0524288.016062239040034160740565647681607405665804916062239400416
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401455931455934194304256001224516480x7fc078d530000x7fc075e24b001290616118815415364208655368792503616132616132613072107.012567884.012749451.012485593.00.00.011126063.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0212.00.00.0228628.00.00.00.00.00.0524288.016062239693380160740566913291607405678349016062240048832
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431455931455934194304256001224528640x7fc0765fbe800x7fc075e24b4024171362309987299326986553620765652430214130214128565605.028557104.028705551.028704711.00.00.020390639.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0865.00.00.00.00.00.00.016062240335185160740568095701607405698957116062240779816
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461455931455934194304256001224540800x7fc0765fbd000x7fc075e24b8024114242307415298818216553620898961830142730142728472216.028458837.028448975.028445315.00.00.020107407.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.03956.00.00.00.00.00.00.016062241065619160740570132511607405719469216062241510469
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149145593145593419430425600824552960x7fc0765fbb800x7fc075e24bc01299584119473315422550655368930270616244716244713183254.012681457.013005830.012765537.00.00.011045082.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0369.00.00.0218762.00.00.00.00.00.0524288.016062241795603160740572198121607405731437316062242152485
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521455931455934194304256001224567680x7fc0765fba000x7fc075e24c0013202481211411156286746553610159483616503016503010560405.08233254.07783213.06542477.00.00.05451114.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0470.00.00.01202524.00.00.00.00.00.0524288.016062242438969160740573399731607405743517416062242804681
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551455931455934194304256001224577280x7fc0765fb8800x7fc075e24c401294808118895615376404655369410097916185016185013731373.013370644.013095493.012887114.00.00.011080419.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0198.00.00.0208598.00.00.00.00.00.0524288.016062243097014160740574674941607405756029416062243444386
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581455931455934194304256001224589440x7fc0765fb7000x7fc075e24c8024216962304908298516606553620856922230271130271128442448.028421706.028605506.028604613.00.00.020331351.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0864.00.00.00.00.00.00.016062243731120160740575847741607405776509616062244168070
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611455931455934194304256001224601600x7fc078d535800x7fc075e24cc024150162308415299213886553621462423530187630187628536941.028520947.028616419.028612817.00.00.020060559.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.03584.00.00.00.00.00.00.016062244454164160740577890961607405797053716062244898774
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164145593145593419430425600824613760x7fc078d534000x7fc075e24d001301088119550115421799655368194096416263516263512522203.011684207.012387142.011978666.00.00.010390758.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0325.00.00.0384395.00.00.00.00.00.0524288.016062245186898160740579932571607405808701716062245538670
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671455931455934194304256001224628480x7fc078d532800x7fc075e24d401350200124361916027330655361034580681687741687748910324.06491674.06144999.05004836.00.00.04341318.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0372.00.00.01128561.00.00.00.00.00.0524288.016062245823634160740581231781607405822301816062246194885
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701455931455934194304256001224638080x7fc078d531000x7fc075e24d801296160119520615441467655369075795716201916201913297029.012799375.012163468.011799885.00.00.011166488.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0253.00.00.0348487.00.00.00.00.00.0524288.016062246488069160740582551791607405834973916062246844071
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731455931455934194304256001224650240x7fc0765fbf800x7fc075e24dc024104882302332298287446553622130314030131030131028510438.028499614.028671249.028670377.00.00.020036703.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0956.00.00.00.00.00.00.016062247131965160740583788591607405855806016062247575625
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761455931455934194304256001224662400x7fc0765fbe000x7fc075e24e0023990002292113296950506553620923839229987429987428405760.028391273.028415173.028411207.00.00.020020519.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.03012.00.00.00.00.00.00.016062247861339160740585819011607405876286216062248303379
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179145593145593419430425600824674560x7fc0765fbc800x7fc075e24e401301600119832815438743655368782474216269916269912844778.011983556.012307784.011904401.00.00.010594758.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0408.00.00.0484650.00.00.00.00.00.0524288.016062248589022160740587879821607405888238216062248959664
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821455931455934194304256001224689280x7fc0765fbb000x7fc075e24e80141889613100681691527265536970285731773611773618197508.05593471.05297827.04048631.00.00.03010604.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0377.00.00.01186281.00.00.00.00.00.0524288.016062249247938160740589078221607405901166316062249618090
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851455931455934194304256001224701440x7fc0765fb9800x7fc075e24ec01281608117929515232926655368083524016020016020012473991.011606963.012435529.012113800.00.00.010653181.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0327.00.00.0494596.00.00.00.00.00.0524288.016062249910903160740590447831607405913710416062250261685
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881455931455934194304256001224716160x7fc0765fb8000x7fc075e24f0024138162302526298260536553620743171230172630172628376250.028371510.028384202.028383158.00.00.020323502.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.01044.00.00.00.00.00.00.016062250547219160740591628641607405934190516062250990429
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911455931455934194304256001224728320x7fc0765fb6800x7fc075e24f4024052082292949297101836553621272746530065030065028328982.028320648.028432790.028431942.00.00.020111241.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0840.00.00.00.00.00.00.016062251277153160740593689451607405954910616062251719683
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194145593145593419430425600824740480x7fc078d535000x7fc075e24f801291472118810415326124655369065107216143316143312939778.011982917.011920423.011196778.00.00.010128438.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0565.00.00.0514127.00.00.00.00.00.0524288.016062252006236160740595732671607405966686716062252360318
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971455931455934194304256001224757760x7fc078d533800x7fc075e24fc01467160135563917509545655361030759121833941833947595497.05027554.04663953.03309636.00.00.01956303.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0363.00.00.01338642.00.00.00.00.00.0524288.016062252647982160740596942271607405980078816062253015964
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001455931455934194304256001224769920x7fc078d532000x7fc075e2500012923201187422153403006553610092911516153916153913476908.013116638.012686877.012388988.00.00.010505932.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0229.00.00.0254349.00.00.00.00.00.0524288.016062253320037160740598345481607405992766916062253669449
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031455931455934194304256001224784640x7fc078d530800x7fc075e2504024098402304128298476806553621030716930122930122928406112.028398145.028404482.028403373.00.00.020255391.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.01088.00.00.00.00.00.00.016062253956603160740599532691607406013359016062254409113
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061455931455934194304256001224799360x7fc0765fbf000x7fc075e2508024112642299352297918186553621125778030140730140728392885.028382873.028192579.028191716.00.00.020048761.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0896.00.00.00.00.00.00.016062254694836160740601588701607406033887116062255140876
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209145593145593419430425600824814080x7fc0765fbd800x7fc075e250c01303864119869615473329655368888258216298216298212524116.011093759.011446406.010766551.00.00.09404827.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0523.00.00.0755317.00.00.00.00.00.0524288.016062255426510160740603649511607406046031216062255786812
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121455931455934194304256001224831360x7fc0765fbc000x7fc075e251001540208142994618421472655361138484941925251925256690065.04459354.04028918.02891316.00.00.01505048.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0273.00.00.01138288.00.00.00.00.00.0524288.016062256072446160740604857521607406060159316062256448937
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151455931455934194304256001224843520x7fc0765fba800x7fc075e251401291856118899115364519655369673549916148116148113535007.013030632.011728151.011278706.00.00.010799407.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0294.00.00.0400881.00.00.00.00.00.0524288.016062256741401160740606487931607406074239416062257091593
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181455931455934194304256001224858240x7fc0765fb9000x7fc075e2518024064082301659298028876553621492830630080030080028371454.028360263.028429818.028428950.00.00.020117997.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0864.00.00.00.00.00.00.016062257377157160740607659141607406094543516062257827647
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211455931455934194304256001224872960x7fc0765fb7800x7fc075e251c023955762290070296541816553621117481729944629944628240164.028229126.028505290.028504418.00.00.019830342.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0889.00.00.00.00.00.00.016062258114811160740609691151607406115007616062258568650
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241455931455934194304256001224887680x7fc0765fb6000x7fc075e252001309792120075615474716655368990516316372316372312318007.010570286.011009182.010178570.00.00.09356858.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0516.00.00.0861107.00.00.00.00.00.0524288.016062258854924160740611767961607406127343716062259215396
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271455931455934194304256001224907520x7fc078d534800x7fc075e252401629296151094019503314655361156284492036612036616612157.04321375.04173477.03042354.00.00.01467847.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0309.00.00.01145126.00.00.00.00.00.0524288.016062259501850160740612995171607406141999816062259883561
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301455931455934194304256001224919680x7fc078d533000x7fc075e252801297272119058115365417655369387656116215816215812845139.012250827.012559270.012254131.00.00.010511104.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0285.00.00.0379442.00.00.00.00.00.0524288.016062260175525160740614524781607406154623916062260528067
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331455931455934194304256001224934400x7fc078d531800x7fc075e252c024116802305997298617666553621630440730145930145928421969.028413955.028621664.028620824.00.00.020026732.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0852.00.00.00.00.00.00.016062260814611160740615721591607406175232016062261258981
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361455931455934194304256001224949120x7fc078d530000x7fc075e2530023830802281876295708506553620247665229788429788428175658.028159157.028301859.028299953.00.00.019991759.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.02373.00.00.00.00.00.00.016062261546674160740617785601607406195712116062261985175
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391455931455934194304256001224963840x7fc0765fbe800x7fc075e253401298032119418415414886655369421580316225316225312009798.010133803.010589541.09741363.00.00.08744482.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0498.00.00.0838259.00.00.00.00.00.0524288.016062262270888160740619849611607406208048216062262632280
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421455931455934194304256001224983680x7fc0765fbd000x7fc075e253801689768157767220358212655361350663382112202112206503124.04323491.03926604.02765705.00.00.0909179.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0291.00.00.01155848.00.00.00.00.00.0524288.016062262917434160740621052821607406223216316062263317165
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451455931455934194304256001224995840x7fc0765fbb800x7fc075e253c01294976119244815388126655368625640216187116187112671593.011587955.011635875.011071499.00.00.09829719.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0332.00.00.0545007.00.00.00.00.00.0524288.016062263611279160740622656031607406236000416062263961131
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024814559314559341943042560012241013120x7fc0765fba000x7fc075e2540023850802280621295401426553621293197929813429813428185759.028175984.028047227.028046046.00.00.020048265.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0856.00.00.00.00.00.00.016062264247185160740623859241607406256624516062264687635
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025114559314559341943042560012241027840x7fc0765fb8800x7fc075e2544023928082282866295605376553621045832129910029910028181391.028169833.028379204.028376731.00.00.019814534.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.02110.00.00.00.00.00.00.016062264973628160740625908851607406277056616062265409679
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025414559314559341943042560012241042560x7fc0765fb7000x7fc075e254801298288119324715385209655369716844516228516228511709936.09393046.09164071.08132496.00.00.07866368.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0474.00.00.01007037.00.00.00.00.00.0524288.016062265694562160740627952061607406288992716062266045335
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025714559314559341943042560012241062400x7fc078d535800x7fc075e254c01758712164187021196105655361303359732198382198385958709.03916600.03815788.02667664.00.00.0785082.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0304.00.00.01154673.00.00.00.00.00.0524288.016062266331788160740629148871607406304528816062266738929
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026014559314559341943042560012241077120x7fc078d534000x7fc075e255001291808118530915281443655368839631716147516147512636069.011518784.011585719.010993708.00.00.09514848.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0419.00.00.0562567.00.00.00.00.00.0524288.016062267027533160740630777681607406317072816062267382225
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026314559314559341943042560016241094400x7fc078d532800x7fc075e2554023969442292751296663516553621590688029961729961728184659.028174760.028181295.028180423.00.00.019856698.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.0848.00.00.00.00.00.00.016062267669839160740631969691607406337713016062268110159
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026614559314559341943042560016241111680x7fc078d531000x7fc075e2558024004642288659296296176553621338079630005730005728234327.028223690.028068548.028066732.00.00.019841901.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.01.00.00.02204.00.00.00.00.00.00.016062268395623160740634016101607406358129116062268844193
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691455931455934194304256008241128960x7fc0765fbf800x7fc075e255c01303968120069815493319655369804956316299516299511026576.08537726.08550682.07423058.00.00.06404608.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0540.00.00.01164972.00.00.00.00.00.0524288.016062269130366160740636064111607406370209216062269489448
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027214559314559341943042560012241151360x7fc0765fbe000x7fc075e256001842968173216322387466655361473605932303702303705778294.03841417.03596710.02502426.00.00.0863884.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0203.00.00.01107702.00.00.00.00.00.0524288.016062269776332160740637270521607406386545316062270177133
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027514559314559341943042560012241166080x7fc0765fbc800x7fc075e256401297328118795015309922655368724145216216516216512375085.011049110.011439268.010832406.00.00.010463544.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0351.00.00.0652638.00.00.00.00.00.0524288.016062270469487160740638985731607406399297316062270827319
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027814559314559341943042560016241183360x7fc0765fbb000x7fc075e2568023880802282004295629016553619996272429850929850928090564.028083526.027913004.027911976.00.00.019735521.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.01592.00.00.00.00.00.00.016062271114052160740640169741607406419617516062271562212
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028114559314559341943042560016241200640x7fc0765fb9800x7fc075e256c023872642283422295621356553620905330829840729840728087934.028075074.027992681.027989511.00.00.019817235.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.01.00.00.02981.00.00.00.00.00.00.016062271848486160740642198551607406440017616062272295126
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028414559314559341943042560012241217920x7fc0765fb8000x7fc075e257001305936120277415523372655369727040916324116324110009229.07349641.06959202.05570524.00.00.05065959.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0355.00.00.01264891.00.00.00.00.00.0524288.016062272581310160740644236961607406452049716062272944172
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028714559314559341943042560012241240320x7fc0765fb6800x7fc075e257401919312181136723417126655361592437182399132399135661097.03763950.03589980.02503661.00.00.0620386.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0323.00.00.01108650.00.00.00.00.00.0524288.016062273230445160740645483371607406469345816062273636066
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029014559314559341943042560012241255040x7fc078d535000x7fc075e257801292952119054415355419655369750846416161816161812457170.010921186.010690287.09991690.00.00.09004002.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0492.00.00.0722216.00.00.00.00.00.0524288.016062273927900160740647270581607406482257916062274279152
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029314559314559341943042560012241274880x7fc078d533800x7fc075e257c023970482283912295418176553619414738329963029963028123827.028108648.028050943.028044887.00.00.019714047.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.02.00.00.05686.00.00.00.00.00.00.016062274568146160740648484991607406502930016062275013326
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029614559314559341943042560012241292160x7fc078d532000x7fc075e2580023870882278510295010196553618883287929838529838527940763.027876114.027940265.027935133.00.00.019620907.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.02.00.00.09002.00.00.00.00.00.00.016062275299179160740650545801607406523490116062275743150
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029914559314559341943042560012241309440x7fc078d530800x7fc075e258401366816126450016317186655361050973831708511708519221584.06715364.06150253.04941597.00.00.03830521.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0375.00.00.01210606.00.00.00.00.00.0524288.016062276029263160740652584211607406535810216062276397855
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030214559314559341943042560012241334400x7fc0765fbf000x7fc075e258802074944196598925371301655361708057142593672593674586769.03295628.03131579.02432813.00.00.0595428.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0440.00.00.0697532.00.00.00.00.00.0524288.016062276685539160740653856221607406554178316062277102849
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030514559314559341943042560012241349120x7fc0765fbd800x7fc075e258c01289568118759615302122655369788249116119516119511288497.09286856.09084124.08031059.00.00.07207790.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0475.00.00.01016003.00.00.00.00.00.0524288.016062277396263160740655769831607406567202416062277748095
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030814559314559341943042560012241368960x7fc0765fbc000x7fc075e2590023660722257109292036016553619535167029575829575827810924.027775616.027808255.027800305.00.00.019458902.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.06.00.00.07740.00.00.00.00.00.00.016062278033499160740656979441607406587810516062278492419
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031114559314559341943042560012241388800x7fc0765fba800x7fc075e2594023652562258448292473456553620271150929565629565627821495.027808859.027879002.027876213.00.00.019635300.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.06.00.00.03720.00.00.00.00.00.00.016062278779162160740659053051607406608562616062279225542
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031414559314559341943042560012241408640x7fc0765fb9000x7fc075e259801439128132550817096595655361020451651798901798908078387.05252680.04912302.03524791.00.00.02218619.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0205.00.00.01374569.00.00.00.00.00.0524288.016062279512006160740661126661607406622002716062279884548
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031714559314559341943042560012241436160x7fc0765fb7800x7fc075e259c02243160212950827530462655361866173942803942803944545190.03271586.03129136.02436059.00.00.0564633.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0519.00.00.0700457.00.00.00.00.00.0524288.016062280170681160740662448271607406641586816062280606172
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032014559314559341943042560012241453440x7fc0765fb6000x7fc075e25a0013133361211145156173606553610068408616416616416610209635.07893938.07508352.06171443.00.00.04441307.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0339.00.00.01322063.00.00.00.00.00.0524288.016062280898935160740664502681607406654626916062281261077
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032314559314559341943042560012241475840x7fc078d534800x7fc075e25a4023724562262264292707756553620616767629655629655627640278.027624345.027678930.027674976.00.00.019334060.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.00.00.00.03789.00.00.00.00.00.00.016062281548551160740665701091607406675027016062281989071
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032614559314559341943042560012241495680x7fc078d533000x7fc075e25a8023733282264112292899766553620153390029666529666527802833.027780700.027698358.027693487.00.00.019419943.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.05.00.00.04303.00.00.00.00.00.00.016062282276865160740667744301607406695715216062282724075
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032914559314559341943042560012241515520x7fc078d531800x7fc075e25ac01493592138609117873201655361109778631866981866988153191.05135069.04636981.03122686.00.00.01298829.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0174.00.00.01534938.00.00.00.00.00.0524288.016062283010698160740669821121607406709411216062283383230
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033214559314559341943042560012241543040x7fc078d530000x7fc075e25b002403704228998529558936655362058892193004623004624525207.03264356.03136017.02433487.00.00.0531585.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0482.00.00.0682285.00.00.00.00.00.0524288.016062283669494160740671185931607406729971416062284112044
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033514559314559341943042560012241562880x7fc0765fbe800x7fc075e25b401370744126678016330254655361037868591713421713428508036.05794989.05585074.04409160.00.00.02838780.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0337.00.00.01200122.00.00.00.00.00.0524288.016062284403858160740673321941607406743395416062284764560
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033814559314559341943042560012241587840x7fc0765fbd000x7fc075e25b8024226882285133294826576553614890452330283530283525055134.024219385.025800658.025618208.00.00.019201399.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.075.00.00.0174964.00.00.00.00.00.00.016062285049903160740674592351607406764483616062285499913
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034114559314559341943042560012241610240x7fc0765fbb800x7fc075e25bc023849922263488292304496553617641068029812329812327621218.027549102.027065966.026995586.00.00.019372525.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.03.00.00.021410.00.00.00.00.00.00.016062285785987160740676686761607406785507716062286190098
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034414559314559341943042560012241632640x7fc0765fba000x7fc075e25c001660192154189619883839655361111798302075232075237010019.04369272.04189683.02818037.00.00.01434877.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0213.00.00.01363645.00.00.00.00.00.0524288.016062286476462160740678787571607406800131816062286873193
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034714559314559341943042560012241665280x7fc0765fb8800x7fc075e25c402726128261092633780239655362411470073407653407654555476.03230310.03084012.02419935.00.00.0495131.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0359.00.00.0663410.00.00.00.00.00.0524288.016062287158567160740680265981607406823331916062287649946
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035014559314559341943042560012241685120x7fc0765fb7000x7fc075e25c801479888137247217692864655361163469021849851849857825249.04983734.04540688.03147252.00.00.01382149.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0268.00.00.01411095.00.00.00.00.00.0524288.016062287923390160740682794001607406839028016062288292371
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035314559314559341943042560012241712640x7fc078d535800x7fc075e25cc023791202245711289867266553617343391629738929738926503063.026125324.023390649.023011286.00.00.018877117.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.028.00.00.0223085.00.00.00.00.00.00.016062288577655160740684165201607406860052216062289041325
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035614559314559341943042560012241737600x7fc078d534000x7fc075e25d0024022962273397293528096553615511279030028630028625235366.024398486.022690889.022171085.00.00.018146607.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.088.00.00.0215594.00.00.00.00.00.00.016062289327318160740686246821607406881348316062289781548
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035914559314559341943042560012241762560x7fc078d532800x7fc075e25d401807560169801821890679655361368103972259442259446760320.04132757.03750306.02344587.00.00.0481895.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0132.00.00.01404783.00.00.00.00.00.0524288.016062290068452160740688374831607406897156416062290434454
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036214559314559341943042560012241797760x7fc078d531000x7fc075e25d803052600293763137917259655362578177423815743815744538470.03201955.03051884.02399165.00.00.0545502.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0333.00.00.0655211.00.00.00.00.00.0524288.016062290720538160740689970041607406922932516062291241296
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036514559314559341943042560012241822720x7fc0765fbf800x7fc075e25dc01691560157940620399511655361283141542114442114446723038.04312098.03916024.02407008.00.00.0624793.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0177.00.00.01549325.00.00.00.00.00.0524288.016062291515050160740692754061607406940180616062291901561
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036814559314559341943042560012241855360x7fc0765fbe000x7fc075e25e0024536002334428300592836553618975487130669930669921705344.020841464.019667575.018957322.00.00.012294128.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.0181.00.00.0718482.00.00.00.00.00.00.016062292187145160740694264471607406961652816062292662894
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037114559314559341943042560012241885440x7fc0765fbc800x7fc075e25e4024827682351077302478806553618453474231034531034522402763.020919247.019424326.018660378.00.00.010485588.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.0323.00.00.0755474.00.00.00.00.00.00.016062292930319160740696435681607406983700916062293408158
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037414559314559341943042560012241915520x7fc0765fbb000x7fc075e25e802139000201854926060362655361771032452673742673745081737.03357559.03137589.02288796.00.00.0549815.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.099.00.00.0890214.00.00.00.00.00.0524288.016062293671082160740698626091607407002293016062294101503
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037714559314559341943042560012241958400x7fc0765fb9800x7fc075e25ec03692016357852446312065655363408322834615014615014707899.03201680.03034197.02392502.00.00.0581973.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0263.00.00.0636005.00.00.00.00.00.0524288.016062294389676160740700491701607407033285216062294964853
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038014559314559341943042560012241985920x7fc0765fb8000x7fc075e25f001953336184081923756158655361616797582441662441667273033.04515253.04105775.02308896.00.00.0441440.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.064.00.00.01778360.00.00.00.00.00.0524288.016062295236667160740704096531607407055925416062295649748
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038314559314559341943042560012242023680x7fc0765fb6800x7fc075e25f4026799682565013330480746553621037074133499533499519171305.018019159.016688048.015712266.00.00.010076968.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.0102.00.00.0998542.00.00.00.00.00.00.016062295935112160740705842141607407079285516062296425311
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038614559314559341943042560012242058880x7fc078d535000x7fc075e25f8026480402530812326228966553622186121133100433100420714547.018301386.014194230.012835439.00.00.07517456.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.0375.00.00.01279893.00.00.00.00.00.00.016062296691835160740708565351607407106501716062297185604
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038914559314559341943042560012242094080x7fc078d533800x7fc075e25fc02459608234665930273219655361964148113074503074505130991.03384074.03183717.02272479.00.00.0480682.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0128.00.00.0854035.00.00.00.00.00.0524288.016062297453428160740711266171607407131253816062297904368
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039214559314559341943042560012242144640x7fc078d532000x7fc075e260004346064422693954727364655364066556155432575432574586166.03223001.03008019.02408860.00.00.0614159.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0224.00.00.0593116.00.00.00.00.00.0524288.016062298192761160740713368581607407167142016062298768158
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039514559314559341943042560012242177280x7fc078d530800x7fc075e260402182456207343726764405655361852200622728062728066735476.04410392.04043830.02369973.00.00.0498008.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0185.00.00.01667668.00.00.00.00.00.0524288.016062299044982160740717375011607407190518216062299463753
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039814559314559341943042560012242220160x7fc0765fbf000x7fc075e2608029439362816753362665316553623786732236799136799117208921.015807715.014559286.013371205.00.00.07165912.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.0132.00.00.01184260.00.00.00.00.00.00.016062299748327160740719296621607407215798316062300267305
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040114559314559341943042560012242260480x7fc0765fbd800x7fc075e260c029357842820994362901376553625382802536697236697219279749.015994844.013177685.011559728.00.00.06468850.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.0218.00.00.01599651.00.00.00.00.00.00.016062300536889160740722165441607407244566516062301050798
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040414559314559341943042560012242300800x7fc0765fbc000x7fc075e261002778376266926934503938655362467403413472963472965242753.03461098.03171743.02270769.00.00.0458416.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0112.00.00.0898593.00.00.00.00.00.0524288.016062301320582160740725058251607407271718716062301817731
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040714559314559341943042560012242359040x7fc0765fba800x7fc075e261405251640510150165541697655363862136856564546564544817317.03335744.03032420.02436882.00.00.0652536.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0222.00.00.0595186.00.00.00.00.00.0524288.016062302093565160740727762271607407316198916062302686482
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041014559314559341943042560012242394240x7fc0765fb9000x7fc075e261802433144231837229928326655362030106943041423041426809355.04415319.04064760.02354013.00.00.0492823.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0202.00.00.01716925.00.00.00.00.00.0524288.016062302932926160740732040701607407339111116062303472154
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041314559314559341943042560012242442240x7fc0765fb7800x7fc075e261c034579363324197427836996553626720004643224143224115480159.013921885.012973702.011607249.00.00.05346425.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.0117.00.00.01369462.00.00.00.00.00.00.016062303756588160740734165511607407366583216062304164399
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041614559314559341943042560012242487680x7fc0765fb6000x7fc075e2620032433203077611397134456553622598105140541440541416190810.012420143.08939421.07122115.00.00.02043121.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.0271.00.00.01822383.00.00.00.00.00.00.016062304452302160740737007131607407394983416062304884933
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041914559314559341943042560012242533120x7fc078d534800x7fc075e262403395752323467541552929655362461112004244684244684953063.03384732.03229743.02319191.00.00.0447370.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0109.00.00.0895682.00.00.00.00.00.0524288.016062305173496160740739847141607407422167616062305589787
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221455931455934194304256008242555520x7fc078d533000x7fc075e2628057593525639840729463966553653422059571991871991815203739.06849840.05940179.02131829.00.00.0106004.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.04.00.00.03815923.00.00.00.00.00.0524288.016062305879371160740742575161607407471239916062306622674
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042514559314559341943042560012242598400x7fc078d531800x7fc075e262c02913704280239636218458655362552492613642123642127140036.04465077.04111146.02355318.00.00.0448388.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.0162.00.00.01781065.00.00.00.00.00.0524288.016062306896658160740747813591607407500696116062307436676
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042814559314559341943042560012242656640x7fc078d530000x7fc075e2630037477923640079471274256553634972086546847346847314498059.011721237.09215039.07616303.00.00.01912125.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.0361.00.00.01657163.00.00.00.00.00.00.016062307704880160740750655211607407536504316062308326336
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043114559314559341943042560012242712320x7fc0765fbe800x7fc075e2634037709123663271473631936553634758606647136347136313836964.011940376.09867619.08628268.00.00.02591567.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.0214.00.00.01225996.00.00.00.00.00.00.016062308592941160740754236031607407572200516062309215027
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341455931455934194304256008242732160x7fc0765fbd000x7fc075e2638038628563754082485638136553635941779148285648285614714593.06815297.05929637.02139164.00.00.084862.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.00.00.00.03791241.00.00.00.00.00.0524288.016062309481801160740757828051607407607960716062310116447
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371455931455934194304256008242757120x7fc0765fbb800x7fc075e263c070501686929271896919066553667585595488127088127014824130.06715913.05820546.02144102.00.00.093951.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.02.00.00.03685350.00.00.00.00.00.0524288.016062310370211160740761384881607407669641116062311214302
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044014559314559341943042560012242807680x7fc0765fba000x7fc075e264003423624330923842766965655363068493474279524279526096381.03827708.03476413.02265019.00.00.0309060.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.094.00.00.01225152.00.00.00.00.00.0524288.016062311476547160740767629711607407702713316062312017715
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044314559314559341943042560012242876160x7fc0765fb8800x7fc075e2644043984404289443555152456553640861735654980454980414071336.011741197.09755978.08396203.00.00.02197714.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.0166.00.00.01342967.00.00.00.00.00.00.016062312272009160740770871331607407743801516062312888015
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044614559314559341943042560012242942080x7fc0765fb7000x7fc075e2648044079284300809556663616553641402275355099055099013687519.011394080.09891600.08714155.00.00.02482442.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.0139.00.00.01135516.00.00.00.00.00.00.016062313159849160740774980161607407784857816062313780046
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491455931455934194304256008242969600x7fc078d535800x7fc075e264c045094804393891568520826553641162426156368456368415032838.06857246.05960278.02136812.00.00.074428.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.02.00.00.03820167.00.00.00.00.00.0524288.016062314051240160740778853781607407823242016062314704905
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521455931455934194304256008242999680x7fc078d534000x7fc075e2650083401048226145106540703655368030330251042512104251214723012.06658731.05796156.02142772.00.00.072259.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.02.00.00.03635235.00.00.00.00.00.0524288.016062314971939160740782985011607407895882516062315913538
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551455931455934194304256008243027200x7fc078d532800x7fc075e2654057694325658598732687676553655095507472117872117815143177.06853537.05936149.02138223.00.00.084547.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.02.00.00.03810649.00.00.00.00.00.0524288.016062316191942160740790332251607407947962816062316901546
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045814559314559341943042560012243054720x7fc078d531000x7fc075e2658057900325674375734594336553654073798972375372375320866568.013109639.06822377.02952491.00.00.0868390.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.0103.00.00.03866101.00.00.00.00.00.00.016062317169200160740795444281607408000907116062317929384
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046114559314559341943042560012243082240x7fc0765fbf800x7fc075e265c057822005663434733118786553654514283072277472277420808019.013013260.06800880.02940219.00.00.0783396.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.096.00.00.03856855.00.00.00.00.00.00.016062318197908160740800741921607408053691416062318952351
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641455931455934194304256008243109760x7fc0765fbe000x7fc075e2660058041445693671737212486553655364545772551772551715147944.06856691.05934484.02138830.00.00.074795.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.00.00.00.03808732.00.00.00.00.00.0524288.016062319219995160740806121151607408106395816062319963488
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671455931455934194304256008243132160x7fc0765fbc800x7fc075e2664010939272108160621401268346553610636219761367408136740814832823.06703186.05839659.02142023.00.00.0104593.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.00.00.00.03698552.00.00.00.00.00.0524288.016062320231783160740811284381607408199804316062321386957
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701455931455934194304256008243159680x7fc0765fbb000x7fc075e2668010966264108478421405451126553610766625401370782137078215227797.06825233.05884605.02135516.00.00.085448.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.00.00.00.03767874.00.00.00.00.00.0524288.016062321661291160740820668441607408291980916062322793916
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047314559314559341943042560012243187200x7fc0765fb9800x7fc075e266c011002344108621481407514346553610747626561375292137529221340963.013157044.06813690.02907729.00.00.0701756.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.090.00.00.03901670.00.00.00.00.00.00.016062323057040160740829935691607408387837516062324222804
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047614559314559341943042560012243214720x7fc0765fb8000x7fc075e2670010981256108588461405908626553610592505301372656137265621210036.013057841.06772328.02887646.00.00.0670880.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.074.00.00.03881853.00.00.00.00.00.00.016062324491768160740839449351607408482462116062325650192
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791455931455934194304256008243242240x7fc0765fb6800x7fc075e2674011010504108868351410223216553610761097901376312137631215223473.06814236.05901577.02146253.00.00.069124.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.00.00.00.03756797.00.00.00.00.00.0524288.016062325918476160740848975811607408575790616062327072951
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821455931455934194304256008243264640x7fc078d535000x7fc075e2678021302032211858282745518636553621220724402662753266275314632844.06580338.05725169.02137888.00.00.097531.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.00.00.00.03582456.00.00.00.00.00.0524288.016062327334055160740858236671607408752095716062329340401
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851455931455934194304256008243292160x7fc078d533800x7fc075e267c021356928212271212750734806553621289804572669615266961515820293.06928556.05992572.02140244.00.00.079034.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.00.00.00.03826011.00.00.00.00.00.0524288.016062329593135160740876243181607408928960816062331574551
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048814559314559341943042560012243319680x7fc078d532000x7fc075e2680021361384212416102752493966553621196770782670172267017222060503.013320733.06719084.02777787.00.00.0679505.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.075.00.00.03939982.00.00.00.00.00.00.016062331791486160740893891281607409111409916062333853680
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049114559314559341943042560012243347200x7fc078d530800x7fc075e2684021382912212381942751881636553621176740602672863267286322081011.013307722.06725493.02789999.00.00.0688617.0524288.00.00.0524288.0524288.00.00.00.00.00.00.02097152.02097152.00.0106.00.00.03937880.00.00.00.00.00.00.016062334085785160740912040191607409291939016062336181189
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941455931455934194304256008243374720x7fc0765fbf000x7fc075e2688021401512212679652755394036553621155336462675188267518815893170.06954678.05959077.02132744.00.00.073317.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.00.00.00.03835899.00.00.00.00.00.0524288.016062336391514160740930069101607409468100116062338410849
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049714559314559341943042560082400x7fc0765fbd800x7fc075e268c042062464419285685433970426553642233912035257807525780714553106.06578315.05729123.02148818.00.00.0101825.0524288.00.00.0524288.0524288.00.00.0524288.00.00.00.02097152.02097152.00.00.00.00.03576754.00.00.00.00.00.0524288.016062338626925160740947699611607409812710216062342339862