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

89 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_CYCLESSQ_BUSY_CYCLESSQ_WAVESSQ_BUSY_CU_CYCLESSQ_WAVE_CYCLESGRBM_COUNTGRBM_GUI_ACTIVETA_TA_BUSY_sumTA_SH_FIFO_BUSY_sumCPC_CPC_STAT_BUSYCPC_CPC_STAT_IDLETA_SH_FIFO_CMD_BUSY_sumTA_SH_FIFO_ADDR_BUSY_sumCPC_CPC_TCIU_BUSYCPC_CPC_TCIU_IDLETA_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_sumCPC_CPC_STAT_STALLCPC_UTCL1_STALL_ON_TRANSLATIONTA_SH_FIFO_DATA_TFIFO_BUSY_sumTA_SQ_TA_CMD_CYCLES_sumCPC_CPC_UTCL2IU_BUSYCPC_CPC_UTCL2IU_IDLETA_SP_TA_ADDR_CYCLES_sumTA_SP_TA_DATA_CYCLES_sumCPC_CPC_UTCL2IU_STALLCPC_ME1_BUSY_FOR_PACKET_DECODETA_SH_FIFO_ADDR_STARVED_WHILE_BUSY_CYCLES_sumTA_SH_FIFO_CMD_STARVED_WHILE_BUSY_CYCLES_sumCPC_ME1_DC0_SPI_BUSYTA_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.kd000165605165605335544322560043241600x00x7fc640604280305804829720735242883860036923954538038225538225530887826.030512995.0382255028043621.027295529.03023798380.00.019868578.0524288.00.020898975.0524288.00.0524288.00.00.029753468.028054132.0836090029389392.02097152.012343824372097152.04194304.00895364.00.03704170.01287339.00.00.00.00.00.00.016597143607745166091567496571660915698965516597287175645
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00216560516560532768256001224138880x00x7fc640623f8026520015895151213848491677609331493314936320.033364.033149031904.030544.0302335290.00.024422.04096.00.00.04096.04096.00.00.04096.00.00.01131210260.016384.013533218716384.00.00297732.00.04970.01393.00.00.00.00.00.04096.016597292632314166091618129811660916182626116597292827068
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051656051656054194304256001224143360x7fc65ed2e3800x7fc640623fc01386256125956965536162972518191663017328117328111933110.011603768.0173281011686577.011647908.03511784950.00.011705475.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01909541350.02097152.046441686672097152.00.0020836209.00.01546680.021793.00.00.00.00.00.0524288.016597293117657166091618936201660916198578016597293401058
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081656051656054194304256001624150400x7fc65ed2e2000x7fc64062400024758722367244655363067063521185371130948330948329293695.029283994.0309483029522077.029521245.03023113360.00.020625723.0524288.00.00.0524288.0524288.00.00.00.00.00.02048945230.02097152.023913075482097152.00.00241150.00.02838190.0832.00.00.00.00.00.00.016597293695827166091620203391660916219969816597294157281
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111656051656054194304256001624154880x7fc65ed2e0800x7fc64062404025075362380730655363082376021869348131344131344128763828.028740887.0313441029100191.029098879.03513154460.00.020718484.0524288.00.00.0524288.0524288.00.00.00.00.00.02055041280.02097152.036513089032097152.00.00242630.00.02842610.01811.00.00.00.00.00.00.016597294447441166091622260981660916240497716597294817508
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141656051656054194304256001224159360x7fc65c5cdf000x7fc6406240801317752121255965536156963318017225916471816471813338084.013084733.0164718011765799.011732992.03511737910.00.010693836.0524288.00.00.0524288.0524288.00.00.0524288.00.00.03245437600.02097152.047011699372097152.00.0016362154.00.01543860.033648.00.00.00.00.00.0524288.016597295108208166091624300971660916252369616597295476065
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171656051656054194304256001224163840x7fc65c5cdd800x7fc6406240c01321472121409565536157011057586880316518316518313356255.013041175.0165183012011363.011963181.03021646470.00.011263325.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0983026810.02097152.023781619972097152.00.001485785.00.01496280.034219.00.00.00.00.00.0524288.016597295762495166091625496161660916264177516597296111223
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201656051656054194304256001224170880x7fc65c5cdc000x7fc6406241001311936120955165536156486949679349016399116399113949268.013815493.0163991013649449.013632324.03021627530.00.011811563.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01007524210.02097152.029321609732097152.00.001681642.00.01459410.016875.00.00.00.00.00.0524288.016597296410172166091626811351660916277377416597296768630
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231656051656054194304256001624177920x7fc65c5cda800x7fc64062414024451042341766655363035583821034167930563730563728983875.028973454.0305637029242984.029242152.03023086890.00.020795126.0524288.00.00.0524288.0524288.00.00.00.00.00.01135024310.02097152.028973078682097152.00.00247880.00.02833940.0832.00.00.00.00.00.00.016597297055260166091628064141660916298705316597297479165
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261656051656054194304256001624184960x7fc65c5cd9000x7fc64062418024779602371269655363070241722134179230974430974429301470.029285145.0309744029477529.029473636.03023109150.00.020898909.0524288.00.00.0524288.0524288.00.00.00.00.00.01090024140.02097152.024023080622097152.00.00244950.00.02847760.03920.00.00.00.00.00.00.016597297766205166091630296121660916321105116597298195130
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291656051656054194304256001624192000x7fc65c5cd7800x7fc6406241c01420768129341065536166496079485191317759517759512706026.012573239.0177595013540882.013495559.03021658430.00.011504098.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01007228780.02097152.023891620912097152.00.0015666100.00.01476140.031936.00.00.00.00.00.0524288.016597298482830166091632436911660916333841016597298756230
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321656051656054194304256001624199040x7fc65c5cd6000x7fc6406242001319048121359065536156954428580108416488016488013475743.013292208.0164880013478906.013443560.03021644750.00.011461537.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0982024210.02097152.023751618502097152.00.001539493.00.01481980.019908.00.00.00.00.00.0524288.016597299045900166091633755301660916346848916597299417157
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351656051656054194304256001224206080x7fc65ed2e4800x7fc6406242401314224121061365536156676988931508516427716427713600217.013481242.0164277012908347.012864609.03021644010.00.011726007.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0996924330.02097152.024031607782097152.00.001562829.00.01458460.017772.00.00.00.00.00.0524288.016597299713417166091635006491660916359456916597300058115
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381656051656054194304256001624213120x7fc65ed2e3000x7fc64062428024828642377058655363077093622918426831035731035729373757.029363974.0310357029362913.029362081.03023095430.00.020858128.0524288.00.00.0524288.0524288.00.00.00.00.00.01118324240.02097152.023893069832097152.00.00247120.00.02837530.0832.00.00.00.00.00.00.016597300347115166091636275281660916380784716597300787519
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411656051656054194304256001624220160x7fc65ed2e1800x7fc6406242c024796642374228655363075038722389792930995730995729329998.029312036.0309957029239406.029235456.03023089350.00.020681783.0524288.00.00.0524288.0524288.00.00.00.00.00.01099224120.02097152.023913026412097152.00.00225590.00.02844590.03880.00.00.00.00.00.00.016597301075349166091638376071660916401808616597301559012
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441656051656054194304256001624227200x7fc65ed2e0000x7fc6406243001312296121026265536156631549759982116403616403613946790.013860822.0164036014297613.014293125.03021638850.00.011787366.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0989424300.02097152.023811623282097152.00.001565935.00.01468180.043078.00.00.00.00.00.0524288.016597301847642166091640472051660916414032516597302245298
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471656051656054194304256001224234240x7fc65c5cde800x7fc6406243401317880121313865536156980129055354116473416473413607368.013427857.0164734013715123.013689688.03021633330.00.011252547.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0986924130.02097152.023851615082097152.00.001493066.00.01473410.031785.00.00.00.00.00.0524288.016597302533468166091641790441660916427264416597302884726
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501656051656054194304256001224241280x7fc65c5cdd000x7fc6406243801302336120056665536155408419833431216279116279114089967.014017140.0162791014244136.014241699.03021637730.00.012057141.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01008924240.02097152.023931617542097152.00.0015202103.00.01459040.09980.00.00.00.00.00.0524288.016597303179726166091643059241660916439872316597303560222
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531656051656054194304256001624248320x7fc65c5cdb800x7fc6406243c024786242373308655363076564822996620630982730982729393396.029382958.0309827029417345.029416513.03023094370.00.020871691.0524288.00.00.0524288.0524288.00.00.00.00.00.01109824120.02097152.023953058462097152.00.00242370.00.02836600.0832.00.00.00.00.00.00.016597303846152166091644307231660916461136116597304293077
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561656051656054194304256001624255360x7fc65c5cda000x7fc64062440024422082334792655363025165821599514430527530527528954275.028938212.0305275028761279.028757431.03023024670.00.020575531.0524288.00.00.0524288.0524288.00.00.00.00.00.01098129660.02097152.023973071402097152.00.00232080.00.02822520.03928.00.00.00.00.00.00.016597304583057166091646390411660916482096016597305036241
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591656051656054194304256001224262400x7fc65c5cd8800x7fc64062444013076561206082655361560984410032484916345616345613858396.013758103.0163456013977269.013966563.03021625830.00.011613432.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01001924180.02097152.029461610032097152.00.001477378.00.01468940.032283.00.00.00.00.00.0524288.016597305322251166091648531201660916494687916597305677238
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621656051656054194304256001224269440x7fc65c5cd7000x7fc64062448013108881206271655361560237010609864516386016386014186740.014101504.0163860013566813.013483478.03021624470.00.011148887.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0973224140.02097152.024051604702097152.00.001572941.00.01459640.055715.00.00.00.00.00.0524288.016597305963748166091649774391660916507055816597306326815
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651656051656054194304256001224276480x7fc65ed2e5800x7fc6406244c01296624119331765536154503659241714016207716207713612674.013521341.0162077013881496.013868223.03021625840.00.011689616.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0998624130.02097152.037041602342097152.00.001601434.00.01448430.017546.00.00.00.00.00.0524288.016597306620995166091651047981660916519695716597306973993
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681656051656054194304256001624286080x7fc65ed2e4000x7fc64062450024769362372381655363073321422681743630961630961629307411.029293103.0309616029365755.029364923.03023090690.00.020690754.0524288.00.00.0524288.0524288.00.00.00.00.00.01125024280.02097152.023963049742097152.00.00240660.00.02814170.0837.00.00.00.00.00.00.016597307259833166091652364771660916541599616597307704247
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711656051656054194304256001624293120x7fc65ed2e2800x7fc64062454024503762338216655363026169121221136030629630629628876520.028857877.0306296029195254.029191407.03023074810.00.020863261.0524288.00.00.0524288.0524288.00.00.00.00.00.01075024190.02097152.023943016652097152.00.00229814.00.02845070.03808.00.00.00.00.00.00.016597307990498166091654436761660916562591416597308432232
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741656051656054194304256001224300160x7fc65ed2e1000x7fc6406245801296040119620665536154913319470349516200416200413591948.013431801.0162004013456898.013410017.03021620020.00.011737276.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0982424090.02097152.023931597522097152.00.001486799.00.01460780.036764.00.00.00.00.00.0524288.016597308718692166091656724741660916576463416597309083549
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077165605165605419430425600824309760x7fc65c5cdf800x7fc6406245c01301056119868965536154864688799015916263116263113218865.012739764.0162631012685881.012353835.03021624400.00.010808480.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0990424250.02097152.023941588522097152.00.0014916244.00.01456580.0263743.00.00.00.00.00.0524288.016597309370989166091657907131660916588255316597309739067
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801656051656054194304256001224316800x7fc65c5cde000x7fc64062460012964321192691655361543914410284352716205316205314056948.014024999.0162053013971859.013960516.03021622230.00.012040345.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01009629200.02097152.023681607712097152.00.001552755.00.01460060.016274.00.00.00.00.00.0524288.016597310033986166091659171121660916601087216597310354885
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831656051656054194304256001624326400x7fc65c5cdc800x7fc64062464024442482336412655363026356222010256430553030553029003954.028997010.0305530028956762.028955930.03023037900.00.020541604.0524288.00.00.0524288.0524288.00.00.00.00.00.01124528510.02097152.023993041462097152.00.00245930.00.02802400.0832.00.00.00.00.00.00.016597310642685166091660502321660916623087016597311043861
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861656051656054194304256001224336000x7fc65c5cdb000x7fc64062468024637762352158655363046060521590006630797130797129063371.029047840.0307971029135431.029132394.03023072430.00.020600349.0524288.00.00.0524288.0524288.00.00.00.00.00.01080027300.02097152.023943044142097152.00.00233273.00.02825260.03285.00.00.00.00.00.00.016597311330881166091662575901660916643966916597311732577
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891656051656054194304256001224345600x7fc65c5cd9800x7fc6406246c01309288120425565536155845789572525116366016366013685606.013517821.0163660013237496.013154917.03021633630.00.011354624.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01001528900.02097152.023771597902097152.00.0015422108.00.01455370.071460.00.00.00.00.00.0524288.016597312020807166091664643091660916655790816597312387194
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092165605165605419430425600824355200x7fc65c5cd8000x7fc6406247001308328120463065536155569558893354416354016354013026239.012415034.0163540012141777.011738748.03021624650.00.010742080.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0980029340.02097152.024281605602097152.00.0015352271.00.01454210.0296301.00.00.00.00.00.0524288.016597312676034166091665836681660916667790716597313037821
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951656051656054194304256001224362240x7fc65c5cd6800x7fc6406247401306656120228665536155417458551287816333116333113199368.012926770.0163331013611802.013554217.03021621950.00.011370622.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0980724190.02097152.023721602412097152.00.0014539183.00.01472620.070462.00.00.00.00.00.0524288.016597313332801166091667139071660916680782616597313650620
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981656051656054194304256001224371840x7fc65ed2e5000x7fc64062478024408162334823655363025724822380573030510130510128995372.028983606.0305101029149631.029148799.03023065760.00.020752866.0524288.00.00.0524288.0524288.00.00.00.00.00.01115924200.02097152.030233031072097152.00.00237450.00.02799650.0832.00.00.00.00.00.00.016597313938560166091668319861660916701230516597314404673
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011656051656054194304256001224381440x7fc65ed2e3800x7fc6406247c024408482337304655363028784020974669530510530510528909949.028894960.0305105029122912.029119912.03023067330.00.020674334.0524288.00.00.0524288.0524288.00.00.00.00.00.01084729230.02097152.023923014212097152.00.00237380.00.02820760.03021.00.00.00.00.00.00.016597314692723166091670382251660916721950316597315103629
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041656051656054194304256001224391040x7fc65ed2e2000x7fc6406248001304592119736465536154763589775963616307316307313972837.013788918.0163073013763855.013686325.03021615440.00.010377501.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0998124380.02097152.023871615632097152.00.0015499133.00.01462220.0195653.00.00.00.00.00.0524288.016597315392119166091672459031660916733950316597315758526
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107165605165605419430425600824403200x7fc65ed2e0800x7fc6406248401307744120018165536154836459114778716346716346713461308.012650060.0163467012158436.011530361.03021617870.00.010119713.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01003824200.02097152.028961608512097152.00.0015356479.00.01458120.0775163.00.00.00.00.00.0524288.016597316046136166091673654221660916745902216597316410093
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101656051656054194304256001224412800x7fc65c5cdf000x7fc6406248801304800120121065536155298769493498716309916309913583899.013354618.0163099013150835.013050956.03021623630.00.011699389.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0976524150.02097152.023921602132097152.00.0014337147.00.01456910.063354.00.00.00.00.00.0524288.016597316706463166091674913421660916758478116597317016002
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131656051656054194304256001224422400x7fc65c5cdd800x7fc6406248c024184002306178655362988031619723817230229930229928522459.028510176.0302299029009428.029008596.03023060550.00.020730422.0524288.00.00.0524288.0524288.00.00.00.00.00.01121224230.02097152.023983014232097152.00.00240210.00.02807390.0832.00.00.00.00.00.00.016597317303852166091676097411660916778894016597317708168
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161656051656054194304256001224432000x7fc65c5cdc000x7fc64062490024299682318452655363004023521116342630374530374528794367.028784344.0303745028943719.028940311.03023041330.00.020621592.0524288.00.00.0524288.0524288.00.00.00.00.00.01087829200.02097152.029303019342097152.00.00231493.00.02791700.03309.00.00.00.00.00.00.016597317995978166091678140591660916799437816597318474281
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119165605165605419430425600824441600x7fc65c5cda800x7fc6406249401297592119512165536154556158847954016219816219813352987.012937696.0162198012774321.012580264.03021621200.00.011100222.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0987724140.02097152.024041601752097152.00.0014916129.00.01467780.0134029.00.00.00.00.00.0524288.016597318761411166091680199781660916811421716597319077260
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221656051656054194304256001224453760x7fc65c5cd9000x7fc6406249801320856121390065536156296669575929916510616510613027515.011984488.0165106011205468.010449467.03021622610.00.010065688.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0998024200.02097152.027931593832097152.00.0016074507.00.01462170.0736853.00.00.00.00.00.0524288.016597319365890166091681377371660916823261616597319732377
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251656051656054194304256001224463360x7fc65c5cd7800x7fc6406249c01298504119567865536154548769418800916231216231213319353.012990016.0162312012907028.012668709.03021619230.00.011437749.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0993429460.02097152.023851598292097152.00.0014773157.00.01462620.0242719.00.00.00.00.00.0524288.016597320025817166091682644561660916835773616597320382384
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281656051656054194304256001224475520x7fc65c5cd6000x7fc640624a0024344482328417655363015400822279038230430530430528776750.028772252.0304305028956782.028955950.03023050720.00.020525813.0524288.00.00.0524288.0524288.00.00.00.00.00.01119824140.02097152.023963029592097152.00.00249490.00.02804320.0832.00.00.00.00.00.00.016597320669844166091683836551660916856301416597321117739
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311656051656054194304256001224485120x7fc65ed2e4800x7fc640624a4024408802332944655363021521521273850730510930510928876485.028862563.0305109028634867.028631063.03023018220.00.020072988.0524288.00.00.0524288.0524288.00.00.00.00.00.01091724100.02097152.026732990882097152.00.00228420.00.02809720.03761.00.00.00.00.00.00.016597321405279166091685894141660916876893316597321863443
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134165605165605419430425600824494720x7fc65ed2e3000x7fc640624a801290040118332365536153083788853043416125416125413138959.012660886.0161254012591771.012249136.03021621060.00.010823619.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0990326890.02097152.023901595572097152.00.0014780215.00.01452440.0299934.00.00.00.00.00.0524288.016597322152692166091687945331660916888733216597322522860
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371656051656054194304256001224506880x7fc65ed2e1800x7fc640624ac01291656118475165536152755279450400016145616145611825058.09742853.016145609868681.08982045.03021611160.00.07825147.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0980824100.02097152.023951597402097152.00.0017284525.00.01435970.0866976.00.00.00.00.00.0524288.016597322810369166091689143721660916900717116597323178807
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401656051656054194304256001224516480x7fc65ed2e0000x7fc640624b001285824118208465536152842298349528516072716072712987207.012460040.0160727012665763.012407813.03021599040.00.010798213.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0980724160.02097152.028491587772097152.00.0014487275.00.01446710.0369604.00.00.00.00.00.0524288.016597323473126166091690398111660916913181016597323827254
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431656051656054194304256001224528640x7fc65c5cde800x7fc640624b4024098722302198655362982252920802170430123330123328460370.028450581.0301233028457721.028456889.03022998490.00.020509949.0524288.00.00.0524288.0524288.00.00.00.00.00.01077129380.02097152.029283004302097152.00.00251160.00.02784370.0832.00.00.00.00.00.00.016597324115014166091691585301660916933884916597324558798
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461656051656054194304256001224540800x7fc65c5cdd000x7fc640624b8024252242323824655363010532921625038630315230315228745018.028730311.0303152028513787.028510458.03023010010.00.020264203.0524288.00.00.0524288.0524288.00.00.00.00.00.01098924200.02097152.023942983632097152.00.00225660.00.02780290.03154.00.00.00.00.00.00.016597324846938166091693646091660916954476716597325296022
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149165605165605419430425600824552960x7fc65c5cdb800x7fc640624bc01306912120009165536154788798262281016336316336312676186.011857336.0163363012654120.012317014.03021625110.00.010226848.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0988225630.02097152.027151612072097152.00.0014801308.00.01460680.0405241.00.00.00.00.00.0524288.016597325582532166091695692471660916966364716597325943070
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521656051656054194304256001224567680x7fc65c5cda000x7fc640624c0012965681194790655361541013210196830016207016207010536353.08224493.016207007934073.06730989.03021616680.00.05260325.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01010328850.02097152.023721606242097152.00.0016106444.00.01448640.01170778.00.00.00.00.00.0524288.016597326230730166091696887661660916978444616597326599477
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551656051656054194304256001224577280x7fc65c5cd8800x7fc640624c401298640119580965536154585459732515516232916232913628875.013223693.0162329013236639.013061460.03021608810.00.010461930.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01001326380.02097152.024071596122097152.00.0014128204.00.01452030.0107616.00.00.00.00.00.0524288.016597326892727166091698185261660916991164516597327262074
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581656051656054194304256001224589440x7fc65c5cd7000x7fc640624c8024193362313588655362998219221693686430241630241628657866.028650171.0302416028859975.028859142.03023041270.00.020332993.0524288.00.00.0524288.0524288.00.00.00.00.00.01103630680.02097152.023932982632097152.00.00238440.00.02774080.0841.00.00.00.00.00.00.016597327549234166091699382051660917011836316597328001858
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611656051656054194304256001224601600x7fc65ed2e5800x7fc640624cc024400802331197655363017067921656365030500930500928759321.028742066.0305009028513100.028509322.03023007020.00.020074681.0524288.00.00.0524288.0524288.00.00.00.00.00.01078424090.02097152.029262973092097152.00.00229852.00.02799580.05147.00.00.00.00.00.00.016597328288908166091701426831660917032396216597328743022
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164165605165605419430425600824613760x7fc65ed2e4000x7fc640624d001304904119957565536154620899037956716311216311213114856.012501221.0163112012135932.011668257.03021632190.00.010336500.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0978024420.02097152.023891599212097152.00.0015481346.00.01464270.0456223.00.00.00.00.00.0524288.016597329030052166091703479621660917044268116597329392119
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671656051656054194304256001224628480x7fc65ed2e2800x7fc640624d40135264012483376553616104264978880441690791690798671528.06259456.016907906240404.05107178.03021691030.00.03906495.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0998825140.02097152.023971650912097152.00.0016587301.00.01507290.01114775.00.00.00.00.00.0524288.016597329678230166091704681211660917056796016597330055576
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701656051656054194304256001224638080x7fc65ed2e1000x7fc640624d801305568120317565536155409368951212516319516319513134068.012551407.0163195012845362.012585723.03021615760.00.010729190.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01001828130.02097152.023991595222097152.00.0015031288.00.01453260.0347955.00.00.00.00.00.0524288.016597330349926166091706012401660917069515916597330713723
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731656051656054194304256001224650240x7fc65c5cdf800x7fc640624dc024137442307583655362988378021053028930171730171728578429.028571650.0301717028436706.028435738.03022989040.00.020327926.0524288.00.00.0524288.0524288.00.00.00.00.00.01091524250.02097152.023742992112097152.00.00237660.00.02776360.0832.00.00.00.00.00.00.016597331001203166091707231591660917090235816597331449428
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761656051656054194304256001224662400x7fc65c5cde000x7fc640624e0023916242282988655362958782821002525229895229895228359258.028345050.0298952028559521.028556045.03023013400.00.019998927.0524288.00.00.0524288.0524288.00.00.00.00.00.01084824120.02097152.023792982892097152.00.00234812.00.02783180.03638.00.00.00.00.00.00.016597331736547166091709277981660917110683716597332192162
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179165605165605419430425600824674560x7fc65c5cdc800x7fc640624e401313208120447065536155338298955682916415016415013068894.012267375.0164150011995997.011496824.03021631870.00.010345564.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0992724010.02097152.023971604932097152.00.0015485266.00.01460410.0470476.00.00.00.00.00.0524288.016597332478761166091711308361660917122571616597332844269
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821656051656054194304256001224689280x7fc65c5cdb000x7fc640624e801416616130977065536168899621054082711770761770768482619.05964370.017707605838529.04642502.03021758110.00.02855018.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01003524100.02097152.023861731792097152.00.0017749345.00.01580270.01168622.00.00.00.00.00.0524288.016597333131249166091712495561660917135307516597333509465
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851656051656054194304256001224701440x7fc65c5cd9800x7fc640624ec01293712118276465536152774588745451816171316171312914971.012240105.0161713012600135.012293596.03021615690.00.010516886.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0997724220.02097152.023971586002097152.00.0015680222.00.01440900.0324583.00.00.00.00.00.0524288.016597333802615166091713852351660917147819416597334163792
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881656051656054194304256001224716160x7fc65c5cd8000x7fc640624f0024057282295463655362974473220953638230071530071528320319.028312076.0300715028550645.028549571.03023020570.00.020206346.0524288.00.00.0524288.0524288.00.00.00.00.00.01113727260.02097152.023892974242097152.00.00237640.00.02775580.01438.00.00.00.00.00.00.016597334450802166091715029941660917168411316597334907297
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911656051656054194304256001224728320x7fc65c5cd6800x7fc640624f4024008882291383655362968303120859685530011030011028331482.028323480.0300110028603831.028602975.03023026410.00.020145811.0524288.00.00.0524288.0524288.00.00.00.00.00.01094129140.02097152.023932993282097152.00.00245160.00.02774630.0832.00.00.00.00.00.00.016597335193677166091717098721660917189019116597335651231
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194165605165605419430425600824740480x7fc65ed2e5000x7fc640624f801296336119040465536153414898518650616204116204112701914.011604573.0162041012556353.012000725.03021608780.00.09002244.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01005224200.02097152.031321579712097152.00.0015024544.00.01444610.01186682.00.00.00.00.00.0524288.016597335937741166091719132311660917200667016597336317697
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971656051656054194304256001224757760x7fc65ed2e3800x7fc640624fc01470712135923365536175394071083654881838381838387754807.05158544.018383804702996.03347278.03021809340.00.01759278.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01001224130.02097152.023921800542097152.00.0017309351.00.01640900.01342833.00.00.00.00.00.0524288.016597336606197166091720325901660917213930916597336990244
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001656051656054194304256001224769920x7fc65ed2e2000x7fc6406250001296496119226865536153872909110848416206116206112870745.012259923.0162061012641837.012355048.03021608020.00.010558090.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0999627970.02097152.023941596562097152.00.0015520241.00.01436410.0296095.00.00.00.00.00.0524288.016597337295503166091721724291660917226634916597337655141
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031656051656054194304256001224784640x7fc65ed2e0800x7fc64062504024024722293067655362970184521129195130030830030828291251.028273331.0300308028229962.028228962.03022984830.00.019904386.0524288.00.00.0524288.0524288.00.00.00.00.00.01110024180.02097152.023672992802097152.00.00218300.00.02747160.01032.00.00.00.00.00.00.016597337943131166091722909881660917247018716597338406055
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061656051656054194304256001224799360x7fc65c5cdf000x7fc64062508024317442313865655362996903021597825330396730396728609876.028600366.0303967028231641.028230809.03022991190.00.020404868.0524288.00.00.0524288.0524288.00.00.00.00.00.01098224120.02097152.031193003622097152.00.00222491.00.02770190.0889.00.00.00.00.00.00.016597338693634166091724964271660917267594616597339154058
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209165605165605419430425600824814080x7fc65c5cdd800x7fc6406250c01299016119608765536154238318928490116237616237612576555.011127815.0162376011324773.010599889.03021622880.00.09737677.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0998229030.02097152.023811595342097152.00.0015900546.00.01458620.0727058.00.00.00.00.00.0524288.016597339440678166091727023461660917279738516597339817525
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121656051656054194304256001224831360x7fc65c5cdc000x7fc6406251001545184143120265536184595791065068321931471931476606615.04401285.019314704164384.03010750.03021917220.00.01514469.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01029024160.02097152.023491885102097152.00.0017916264.00.01717570.01134336.00.00.00.00.00.0524288.016597340104515166091728233051660917293834416597340495521
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151656051656054194304256001224843520x7fc65c5cda800x7fc64062514012885361188301655361534740710341950716106616106613654477.013272294.0161066012418706.012051988.03021608250.00.011260790.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0981526560.02097152.023911587422097152.00.0015195237.00.01440860.0246965.00.00.00.00.00.0524288.016597340788761166091729847441660917307882316597341150838
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181656051656054194304256001224858240x7fc65c5cd9000x7fc64062518024295602323684655363008362422013236630369430369428648578.028638096.0303694028183757.028182573.03022983380.00.020033783.0524288.00.00.0524288.0524288.00.00.00.00.00.01062330120.02097152.023902997882097152.00.00244880.00.02771210.0840.00.00.00.00.00.00.016597341436848166091731042631660917328458216597341886973
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211656051656054194304256001224872960x7fc65c5cd7800x7fc6406251c024117202305126655362983640821365000730146430146428483398.028471008.0301464028131939.028131075.03022974670.00.019912156.0524288.00.00.0524288.0524288.00.00.00.00.00.01083626740.02097152.023762961672097152.00.00175290.00.02764570.01005.00.00.00.00.00.00.016597342176173166091733108211660917348986016597342645146
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241656051656054194304256001224887680x7fc65c5cd6000x7fc6406252001303648119230065536153663129575256416295516295512731114.011294259.0162955011139966.010384192.03021610250.00.08608533.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01003324300.02097152.023691606242097152.00.0015551550.00.01450480.0938035.00.00.00.00.00.0524288.016597342932536166091735153001660917361049916597343298283
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271656051656054194304256001224907520x7fc65ed2e4800x7fc6406252401613472150441065536193888011301222432016832016836731468.04473442.020168303992936.02864581.03022007800.00.01486938.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01031324140.02097152.023941989652097152.00.0017658319.00.01822440.01140934.00.00.00.00.00.0524288.016597343585253166091736354591660917375737816597343990029
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301656051656054194304256001224919680x7fc65ed2e3000x7fc6406252801289544118456165536152963058810376516119216119212799314.012007497.0161192011693197.011206680.03021614770.00.010097054.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0985424300.02097152.023891583292097152.00.0015352312.00.01444210.0259596.00.00.00.00.00.0524288.016597344283279166091737898581660917388473716597344650246
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331656051656054194304256001224934400x7fc65ed2e1800x7fc6406252c024272562319595655363002477322164917030340630340628566329.028555234.0303406028447609.028446749.03023009350.00.020018971.0524288.00.00.0524288.0524288.00.00.00.00.00.01121528470.02097152.023872989682097152.00.00241180.00.02763010.0861.00.00.00.00.00.00.016597344936716166091739095371660917408889616597345396030
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361656051656054194304256001224949120x7fc65ed2e0000x7fc64062530023852322283471655362959063020593724629815329815328235814.028223253.0298153028427016.028425283.03023004980.00.019893433.0524288.00.00.0524288.0524288.00.00.00.00.00.01063829650.02097152.028562952312097152.00.00220320.00.02756300.03016.00.00.00.00.00.00.016597345681640166091741143361660917429385516597346134755
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391656051656054194304256001224963840x7fc65c5cde800x7fc6406253401296824119325665536153874819843557816210216210212268476.010463815.0162102010310624.09413616.03021614990.00.08579615.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01001230060.02097152.024061594332097152.00.0015875544.00.01451200.0868531.00.00.00.00.00.0524288.016597346421514166091743194541660917441417416597346800071
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421656051656054194304256001224983680x7fc65c5cdd000x7fc6406253801695440158439465536204248721263702962119292119296272079.04155234.021192903875878.02694400.03022111670.00.0933627.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01050024080.02097152.023972084952097152.00.0018163277.00.01893710.01169682.00.00.00.00.00.0524288.016597347086631166091744416941660917456809316597347491627
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451656051656054194304256001224995840x7fc65c5cdb800x7fc6406253c01293936119058665536153643929279319216174116174112940095.012130786.0161741010758072.010025773.03021606080.00.09467480.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0990824160.02097152.024061576912097152.00.0015076333.00.01451930.0447324.00.00.00.00.00.0524288.016597347784467166091746020121660917469657216597348149704
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024816560516560541943042560012241013120x7fc65c5cda000x7fc64062540024034242297203655362974194920794472730042730042728404173.028392527.0300427028239748.028238868.03022984320.00.019828703.0524288.00.00.0524288.0524288.00.00.00.00.00.01095130180.02097152.023942976872097152.00.00240060.00.02735500.0856.00.00.00.00.00.00.016597348437144166091747216921660917490169016597348897418
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025116560516560541943042560012241027840x7fc65c5cd8800x7fc64062544023868802284320655362957552721141043729835929835928192129.028175736.0298359028207052.028204458.03022983800.00.019958305.0524288.00.00.0524288.0524288.00.00.00.00.00.01093424150.02097152.023772958862097152.00.00229911.00.02761030.02429.00.00.00.00.00.00.016597349184208166091749269701660917510808916597349637482
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025416560516560541943042560012241042560x7fc65c5cd7000x7fc6406254801294192119143065536153731169693448416177316177311741611.09577500.016177309199616.08180539.03021598400.00.07076521.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01005124270.02097152.031281595272097152.00.0016646503.00.01434400.01021733.00.00.00.00.00.0524288.016597349923182166091751333691660917522696816597350296809
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025716560516560541943042560012241062400x7fc65ed2e5800x7fc6406254c01755760164012565536211849161296034262194692194695881012.03895864.021946903694750.02546102.03022185420.00.0801126.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01053624290.02097152.023942170412097152.00.0018854300.00.01981090.01164244.00.00.00.00.00.0524288.016597350584349166091752516081660917538280716597350993754
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026016560516560541943042560012241077120x7fc65ed2e4000x7fc6406255001286536118294365536152446589118693316081616081612709039.011814329.0160816011508960.010913113.03021607750.00.09543282.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0984924180.02097152.031721569402097152.00.0014811416.00.01434820.0544283.00.00.00.00.00.0524288.016597351286534166091754154471660917550888616597351653022
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026316560516560541943042560016241094400x7fc65ed2e2800x7fc64062554023805762278960655362951765521302025529757129757128140068.028132431.0297571028131987.028131075.03022982590.00.019977974.0524288.00.00.0524288.0524288.00.00.00.00.00.01083129300.02097152.023932944542097152.00.00232770.00.02748260.0888.00.00.00.00.00.00.016597351940801166091755356061660917571416516597352391316
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026616560516560541943042560016241111680x7fc65ed2e1000x7fc64062558023869522286758655362958380021516509829836829836828190363.028177799.0298368028115689.028113608.03022967960.00.019796209.0524288.00.00.0524288.0524288.00.00.00.00.00.01108624070.02097152.023922951772097152.00.00227572.00.02756290.02025.00.00.00.00.00.00.016597352679026166091757396051660917592024316597353134330
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691656051656054194304256008241128960x7fc65c5cdf800x7fc6406255c012945601193813655361539405710024162316181916181910967600.08484547.016181908376944.07207055.03021625690.00.06273717.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0996724260.02097152.031351598662097152.00.0015969575.00.01451340.01152689.00.00.00.00.00.0524288.016597353421230166091759460031660917604216316597353786017
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027216560516560541943042560012241151360x7fc65c5cde000x7fc6406256001832080172216965536222550141524684902290092290095676919.03790892.022900903676229.02580886.03022279250.00.0818255.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01066029920.02097152.030012255872097152.00.0019447290.00.02079660.01116574.00.00.00.00.00.0524288.016597354074337166091760660021660917620456116597354503752
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027516560516560541943042560012241166080x7fc65c5cdc800x7fc6406256401289920118347665536152751459053929116123916123912602838.011546682.0161239011890386.011391442.03021608730.00.010544033.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01012424130.02097152.023881588112097152.00.0016161383.00.01440890.0604721.00.00.00.00.00.0524288.016597354796462166091762372011660917633144116597355162409
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027816560516560541943042560016241183360x7fc65c5cdb000x7fc64062568023967362286915655362961972820272826229959129959128152808.028141309.0299591028120285.028119345.03022976950.00.019876320.0524288.00.00.0524288.0524288.00.00.00.00.00.01062029960.02097152.028732954002097152.00.00221650.00.02746980.01040.00.00.00.00.00.00.016597355449779166091763568801660917653895916597355913493
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028116560516560541943042560016241200640x7fc65c5cd9800x7fc6406256c023977922293257655362970809121349035329972329972328288937.028275238.0299723028188472.028185387.03022982870.00.019934515.0524288.00.00.0524288.0524288.00.00.00.00.00.01077123640.02097152.023972949632097152.00.00218890.00.02754560.02992.00.00.00.00.00.00.016597356199733166091765645591660917674407816597356650777
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028416560516560541943042560012241217920x7fc65c5cd8000x7fc64062570013106481208554655361560485710090375316383016383010285773.07747764.016383007430403.06121787.03021635110.00.04527583.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0999924230.02097152.024121609692097152.00.0015962417.00.01465310.01327870.00.00.00.00.00.0524288.016597356937427166091767683981660917686631716597357301884
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028716560516560541943042560012241240320x7fc65c5cd6800x7fc6406257401924608181302265536234324251605601202405752405755894442.03900064.024057503592662.02503242.03022385230.00.0685240.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01060324190.02097152.023962363762097152.00.0020054351.00.02164060.01099868.00.00.00.00.00.0524288.016597357587834166091768919171660917703735616597358003070
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029016560516560541943042560012241255040x7fc65ed2e5000x7fc6406257801297896119120265536153300619591279316223616223612219363.010735545.0162236010578590.09825742.03021609760.00.08739414.0524288.00.00.0524288.0524288.00.00.0524288.00.00.0988129020.02097152.024041578552097152.00.0015550488.00.01431830.0659466.00.00.00.00.00.0524288.016597358296759166091770707951660917716615516597358664676
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029316560516560541943042560012241274880x7fc65ed2e3800x7fc6406257c023875682280285655362950451718536711629844529844528086965.028059779.0298445028137462.028130685.03022986010.00.019664356.0524288.00.00.0524288.0524288.00.00.00.00.00.01058024070.02097152.023922947472097152.00.00227194.00.02755920.07362.00.00.00.00.00.00.016597358952186166091771911151660917737335316597359405470
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029616560516560541943042560012241292160x7fc65ed2e2000x7fc64062580023963202286241655362960194220175319229953929953928188319.028172411.0299539028036603.028031399.03022977350.00.019668212.0524288.00.00.0524288.0524288.00.00.00.00.00.01063224110.02097152.023922960422097152.00.00224330.00.02747840.07115.00.00.00.00.00.00.016597359693050166091773979931660917758119216597360153294
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029916560516560541943042560012241309440x7fc65ed2e0800x7fc6406258401372560126628465536163415981038015121715691715699394852.06840280.017156906254018.05049245.03021706110.00.04205185.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01013524950.02097152.023981672812097152.00.0016091323.00.01521760.01251243.00.00.00.00.00.0524288.016597360439604166091776064721660917770647116597360813501
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030216560516560541943042560012241334400x7fc65c5cdf000x7fc6406258802077152196628265536254034521698976762596432596434574681.03285493.025964303235443.02547792.03022592930.00.0553465.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01068624100.02097152.023882573962097152.00.0020867450.00.02352680.0701830.00.00.00.00.00.0524288.016597361100651166091777327111660917788839016597361537746
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030516560516560541943042560012241349120x7fc65c5cdd800x7fc6406258c01303200119515565536153870509736170116289916289911392594.09440570.016289908879679.07795483.03021602280.00.06888916.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01013628480.02097152.023971599482097152.00.0015892455.00.01437920.01078145.00.00.00.00.00.0524288.016597361831225166091779208701660917801574916597362192673
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030816560516560541943042560012241368960x7fc65c5cdc000x7fc64062590023681362261474655362926754019565825329601629601627870889.027840759.0296016027877859.027869979.03022958100.00.019535297.0524288.00.00.0524288.0524288.00.00.00.00.00.01065530980.02097152.023502938102097152.00.00224822.00.02745900.09274.00.00.00.00.00.00.016597362479423166091780421491660917822182716597362941067
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031116560516560541943042560012241388800x7fc65c5cda800x7fc64062594023876722276087655362944042419891589129845829845828013551.028001777.0298458027878284.027875306.03022964430.00.019617022.0524288.00.00.0524288.0524288.00.00.00.00.00.01090529510.02097152.023922929942097152.00.00218610.00.02735040.02654.00.00.00.00.00.00.016597363227807166091782469471660917843014616597363682741
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031416560516560541943042560012241408640x7fc65c5cd9000x7fc6406259801429264132109765536170531341057517651786571786578276086.05421977.017865704973396.03569445.03021787250.00.01936471.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01020629470.02097152.023981773732097152.00.0016342203.00.01592220.01390973.00.00.00.00.00.0524288.016597363969141166091784539861660917856150516597364347068
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031716560516560541943042560012241436160x7fc65c5cd7800x7fc6406259c02255568214163165536276783461869912692819452819454639021.03339550.028194503168717.02479096.03022799900.00.0549223.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01087524320.02097152.024072772222097152.00.0021983520.00.02555440.0687555.00.00.00.00.00.0524288.016597364633538166091785867851660917875734416597365073142
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032016560516560541943042560012241453440x7fc65c5cd6000x7fc640625a001299888119326865536153844729797540516248516248510061722.07713627.016248507851337.06585207.03021609360.00.05280029.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01007624060.02097152.023951591782097152.00.0016294313.00.01438710.01291913.00.00.00.00.00.0524288.016597365366372166091787901441660917888646316597365726870
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032316560516560541943042560012241475840x7fc65ed2e4800x7fc640625a4023721442261009655362923520319804420029651729651727637469.027619870.0296517027631749.027626594.03022939020.00.019360575.0524288.00.00.0524288.0524288.00.00.00.00.00.01078826000.02097152.023772941222097152.00.00222362.00.02745610.03715.00.00.00.00.00.00.016597366015330166091789115831660917909366116597366428615
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032616560516560541943042560012241495680x7fc65ed2e3000x7fc640625a8023753042266151655362932509919113242229691229691227803920.027757259.0296912024310509.024144548.04023077540.00.019517280.0524288.00.00.0524288.0524288.00.00.00.00.00.01066624120.02097152.023912961462097152.00.00224371.00.02734310.02800.00.00.00.00.00.00.016597366714665166091791186211660917930182016597367169299
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032916560516560541943042560012241515520x7fc65ed2e1800x7fc640625ac01500296138641965536178669731045872611875361875367998291.04935335.018753604575952.03048003.03021861690.00.01386558.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01023724130.02097152.023871842072097152.00.0017047163.00.01665200.01534553.00.00.00.00.00.0524288.016597367456049166091793266201660917943653916597367847655
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033216560516560541943042560012241543040x7fc65ed2e0000x7fc640625b002397632228635965536295446932032163282997032997034558664.03293250.029970303437044.02736427.04023323280.00.0543555.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01097924180.02097152.023902974732097152.00.0023456406.00.02745480.0691752.00.00.00.00.00.0524288.016597368133715166091794606991660917964165816597368594499
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033516560516560541943042560012241562880x7fc65c5cde800x7fc640625b401367240126386365536163058711051979861709041709048537252.05867609.017090405638449.04441785.03021723220.00.03418444.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01002424140.02097152.023871694812097152.00.0016405304.00.01523610.01247440.00.00.00.00.00.0524288.016597368887799166091796742971660917977525716597369262316
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033816560516560541943042560012241587840x7fc65c5cdd000x7fc640625b8023969842274235655362939415217775291629962229962226805584.026457392.0299622022550417.022154566.04023208870.00.016727596.0524288.00.00.0524288.0524288.00.00.00.00.00.01068927420.02097152.026572953572097152.00.0021918113.00.02781240.0159411.00.00.00.00.00.00.016597369548936166091797998971660917998629516597370005340
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034116560516560541943042560012241610240x7fc65c5cdb800x7fc640625bc023779122258359655362913877118026882129723829723827540632.027465212.0297238025272327.025099404.03513057120.00.019165047.0524288.00.00.0524288.0524288.00.00.00.00.00.01056624140.02097152.023352926032097152.00.002269169.00.02778670.055816.00.00.00.00.00.00.016597370292850166091800104551660918019589416597370707465
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034416560516560541943042560012241632640x7fc65c5cda000x7fc640625c001650728153764465536198401281292214452063402063407256720.04605042.020634004332877.02978495.03022058240.00.01051276.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01045724180.02097152.023882030372097152.00.0017947219.00.01865320.01358646.00.00.00.00.00.0524288.016597370993985166091802203741660918034325316597371338143
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034716560516560541943042560012241665280x7fc65c5cd8800x7fc640625c402732864261656165536337735132297515103416073416074569285.03244425.034160703095631.02439238.03023395430.00.0526784.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01125424160.02097152.023953369022097152.00.0025269290.00.03121740.0661882.00.00.00.00.00.0524288.016597371625693166091803691731660918057621116597372101637
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035016560516560541943042560012241685120x7fc65c5cd7000x7fc640625c801474296136380765536176000011121784231842861842867684666.04821374.018428604505345.03110730.03021838430.00.01571354.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01016626800.02097152.026571812562097152.00.0017253178.00.01644960.01401906.00.00.00.00.00.0524288.016597372357148166091806269311660918073701016597372703336
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035316560516560541943042560012241712640x7fc65ed2e5800x7fc640625cc023855282242619655362897269315047435729819029819024961918.024066074.0298190024096754.023759588.03022987550.00.017424074.0524288.00.00.0524288.0524288.00.00.00.00.00.01074624140.02097152.023912960022097152.00.002239198.00.02738030.0446896.00.00.00.00.00.00.016597372991576166091807629301660918094500916597373403151
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035616560516560541943042560012241737600x7fc65ed2e4000x7fc640625d0023881522265361655362925837116927160229851829851825934060.025298522.0298518024556531.024228974.03022979730.00.016089196.0524288.00.00.0524288.0524288.00.00.00.00.00.01063324150.02097152.023672950802097152.00.0021641218.00.02762450.0274424.00.00.00.00.00.00.016597373691051166091809710891660918115812716597374150975
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035916560516560541943042560012241762560x7fc65ed2e2800x7fc640625d401804696169494465536218925461463918892255862255866710505.04107757.022558603800653.02398646.03022240530.00.0491142.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01046429030.02097152.024002227232097152.00.0019070152.00.02039410.01387021.00.00.00.00.00.0524288.016597374438675166091811837271660918131796616597374860860
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036216560516560541943042560012241797760x7fc65ed2e1000x7fc640625d803050880293437465536379181282654236443813593813594500176.03200971.038135903070403.02423893.03023807590.00.0472445.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01176024140.02097152.023913768212097152.00.0027276370.00.03518070.0649643.00.00.00.00.00.0524288.016597375147940166091813438861660918157604416597375644723
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036516560516560541943042560012241822720x7fc65c5cdf800x7fc640625dc01698208158620365536204507011202501922122752122756705447.04333976.021227504025071.02473231.03022103580.00.0543470.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01041224270.02097152.024052079212097152.00.0018226141.00.01905910.01530924.00.00.00.00.00.0524288.016597375900824166091816213241660918174788316597376253842
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036816560516560541943042560012241855360x7fc65c5cde000x7fc640625e0024634242337754655363008946119423120730792730792722021636.021198529.0307927020404006.019749097.03023076570.00.012476964.0524288.00.00.0524288.0524288.00.00.00.00.00.01124127630.02097152.023913017122097152.00.0022520175.00.02834500.0729291.00.00.00.00.00.00.016597376541022166091817730031660918196500216597376977406
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037116560516560541943042560012241885440x7fc65c5cdc800x7fc640625e4024881842358451655363035269618279928731102231102221951513.020359280.0311022019548761.018793052.03023097870.00.011193020.0524288.00.00.0524288.0524288.00.00.00.00.00.01079129790.02097152.023913063032097152.00.0022206290.00.02881490.0907245.00.00.00.00.00.00.016597377245487166091819925211660918218804016597377731920
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037416560516560541943042560012241915520x7fc65c5cdb000x7fc640625e802133120201586965536260229351788128572666392666395097070.03369569.026663903149342.02300473.03022657470.00.0528822.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01065424270.02097152.023672630172097152.00.0021555161.00.02423290.0856823.00.00.00.00.00.0524288.016597377999470166091822131601660918237331916597378444965
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037716560516560541943042560012241958400x7fc65c5cd9800x7fc640625ec03704624357977165536463094483399193994630774630774728008.03224827.046307703084931.02440584.03024610670.00.0657587.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01226024170.02097152.023914585282097152.00.0030927240.00.04276620.0638477.00.00.00.00.00.0524288.016597378732745166091823985991660918268243716597379266096
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038016560516560541943042560012241985920x7fc65c5cd8000x7fc640625f001951288184200765536237418151558739572439102439107297845.04516831.024391004144795.02336331.03022423740.00.0420297.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01066524220.02097152.023802419262097152.00.002011376.00.02207270.01787844.00.00.00.00.00.0524288.016597379541107166091827565161660918290563516597379946003
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038316560516560541943042560012242023680x7fc65c5cd6800x7fc640625f4026773842563677655363300553621035722633467233467219196623.018047375.0334672017239508.016303955.03023344900.00.09585624.0524288.00.00.0524288.0524288.00.00.00.00.00.01117924080.02097152.023943319432097152.00.0024219101.00.03089550.01030706.00.00.00.00.00.00.016597380232513166091829320351660918314019416597380744135
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038616560516560541943042560012242058880x7fc65ed2e5000x7fc640625f8026682162534361655363268716120056158933352633352619611161.016911817.0333526014610812.013314585.03023285710.00.08120848.0524288.00.00.0524288.0524288.00.00.00.00.00.01134824230.02097152.023923290372097152.00.0022844355.00.03061250.01366089.00.00.00.00.00.00.016597381012295166091832029131660918341059216597381524858
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038916560516560541943042560012242094080x7fc65ed2e3800x7fc640625fc02464120235336865536302763481879077593080143080145047537.03327172.030801403179139.02302320.03023065570.00.0537155.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01113629590.02097152.030003037102097152.00.0023148110.00.02811520.0880432.00.00.00.00.00.0524288.016597381792298166091834729911660918365875016597382260982
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039216560516560541943042560012242144640x7fc65ed2e2000x7fc6406260004333728422739465536547167474059996635417155417154573932.03194373.054171503058417.02461421.03025420010.00.0617376.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01279724280.02097152.024015398372097152.00.0035263270.00.05047020.0592623.00.00.00.00.00.0524288.016597382546702166091836838701660918401874716597383179890
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039516560516560541943042560012242177280x7fc65ed2e0800x7fc6406260402176848207055865536267537921899084302721052721056790420.04421967.027210504035954.02366659.03022720830.00.0484031.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01097428070.02097152.030402701592097152.00.0021606171.00.02479390.01670109.00.00.00.00.00.0524288.016597383453010166091840859471660918425282616597383888125
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039816560516560541943042560012242220160x7fc65c5cdf000x7fc64062608029212002800853655363607114724219642736514936514916738971.015289561.0365149014373354.013180298.03023630950.00.07235690.0524288.00.00.0524288.0524288.00.00.00.00.00.01158126800.02097152.023963656052097152.00.0027589132.00.03369720.01146712.00.00.00.00.00.00.016597384175705166091842781061660918450674416597384697257
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040116560516560541943042560012242260480x7fc65c5cdd800x7fc6406260c029301602819301655363627519025164337836626936626919249030.015925055.0366269013848185.012276074.03023673190.00.06616245.0524288.00.00.0524288.0524288.00.00.00.00.00.01190723650.02097152.031393641242097152.00.0027491218.00.03333950.01621550.00.00.00.00.00.00.016597384965137166091845661041660918479522216597385490869
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040416560516560541943042560012242300800x7fc65c5cdc000x7fc6406261002774432266435665536344469292440574203468033468035158516.03385356.034680303167665.02275332.03023471730.00.0445273.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01127830270.02097152.024033439112097152.00.002527678.00.03198450.0925488.00.00.00.00.00.0524288.016597385757229166091848541021660918506530016597386267392
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040716560516560541943042560012242359040x7fc65c5cda800x7fc6406261405000680487887865536631252564664173276250846250844570446.03193723.062508403035458.02437322.03026229360.00.0635569.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01325229240.02097152.023936209302097152.00.0039589275.00.05820900.0595425.00.00.00.00.00.0524288.016597386534992166091851019401660918548785716597387221868
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041016560516560541943042560012242394240x7fc65c5cd9000x7fc6406261802438448232147465536299400001960478823048053048056876525.04445977.030480504073648.02368156.03023028130.00.0518719.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01113724090.02097152.023913000722097152.00.0023078161.00.02783290.01693847.00.00.00.00.00.0524288.016597387496379166091855296171660918571745616597387953552
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041316560516560541943042560012242442240x7fc65c5cd7800x7fc6406261c031797763071266655363959121027570459439747139747116195469.014623168.0397471013112623.011761884.03023961830.00.05637718.0524288.00.00.0524288.0524288.00.00.00.00.00.01157124210.02097152.030223961622097152.00.0027069117.00.03701820.01375701.00.00.00.00.00.00.016597388241492166091857433761660918599281416597388786133
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041616560516560541943042560012242487680x7fc65c5cd6000x7fc64062620031309923020482655363908997528252786839137339137315506762.011893008.039137309487074.07589259.03023914550.00.02278962.0524288.00.00.0524288.0524288.00.00.00.00.00.01175129740.02097152.023893881342097152.00.0027383289.00.03613350.01831017.00.00.00.00.00.00.016597389054514166091860291341660918627713216597389604205
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041916560516560541943042560012242533120x7fc65ed2e4800x7fc6406262403108144299574365536387052802759781113885173885175168880.03416271.038851703215938.02298335.03023871370.00.0445821.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01178224170.02097152.024033858192097152.00.0027474106.00.03590440.0902582.00.00.00.00.00.0524288.016597389871935166091863417711660918657905016597390356558
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221656051656054194304256008242555520x7fc65ed2e3000x7fc64062628057504805630636655367291269053892482971880971880915215013.06852992.071880905947727.02137931.03027186750.00.051070.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01394324160.02097152.023987158202097152.00.00446580.00.06724430.03814307.00.00.00.00.00.0524288.016597390621749166091866435291660918709792616597391375663
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042516560516560541943042560012242598400x7fc65ed2e1800x7fc6406262c02912040280379465536362070922497398793640043640047142861.04482705.036400404112358.02356314.03023627120.00.0421490.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01142624240.02097152.026903616892097152.00.0026382167.00.03346060.01754836.00.00.00.00.00.0524288.016597391651193166091871657661660918739136416597392163335
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042816560516560541943042560012242656640x7fc65ed2e0000x7fc64062630037445123640562655364711439735205314146806346806314394453.011686114.046806309344760.07718075.03024677430.00.01821956.0524288.00.00.0524288.0524288.00.00.00.00.00.01209624300.02097152.030114670382097152.00.0031276386.00.04356840.01660881.00.00.00.00.00.00.016597392431786166091874516841660918774944216597393030735
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043116560516560541943042560012242712320x7fc65c5cde800x7fc64062634037787283669109655364743152634558357947234047234014141849.012200442.0472340010008329.08778738.03024696990.00.02676129.0524288.00.00.0524288.0524288.00.00.00.00.00.01215329130.02097152.023934689092097152.00.0031555236.00.04381280.01244998.00.00.00.00.00.00.016597393299496166091878102411660918810847916597393896205
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341656051656054194304256008242732160x7fc65c5cdd000x7fc64062638038695923752062655364853642335018320648369848369814718182.06818878.048369805934273.02145188.03024825200.00.078200.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01239925880.02097152.023964811682097152.00.00329994.00.04482730.03793849.00.00.00.00.00.0524288.016597394168835166091881731191660918847007716597394770324
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371656051656054194304256008242757120x7fc65c5cdb800x7fc6406263c070405846930382655368971954967435781188007288007214865675.06721531.088007205823404.02140962.03028783900.00.075978.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01496330240.02097152.023878783902097152.00.00521822.00.08250560.03696484.00.00.00.00.00.0524288.016597395038025166091885361561660918909327216597395892535
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044016560516560541943042560012242807680x7fc65c5cda000x7fc6406264003418096330467765536427380103067915834272614272616094064.03805503.042726103523570.02308599.03024260910.00.0321527.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01206624120.02097152.024064246152097152.00.002932693.00.03955780.01259763.00.00.00.00.00.0524288.016597396165826166091891641521660918942831016597396731016
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044316560516560541943042560012242876160x7fc65c5cd8800x7fc64062644043942644291854655365550262841221476054928254928214159303.011756629.0549282010790398.09299707.03025531830.00.02367939.0524288.00.00.0524288.0524288.00.00.00.00.00.01276524060.02097152.024005458392097152.00.0034991116.00.05118310.01336475.00.00.00.00.00.00.016597396998046166091894671901660918981790716597397638304
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044616560516560541943042560012242942080x7fc65c5cd7000x7fc64062648044069284295671655365559077440756110255086555086513891242.011483767.0550865010069818.08793443.03025507630.00.02293229.0524288.00.00.0524288.0524288.00.00.00.00.00.01263524140.02097152.023915499302097152.00.0035375166.00.05128730.01200868.00.00.00.00.00.00.016597397908105166091898559871660919020686516597398558752
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491656051656054194304256008242969600x7fc65ed2e5800x7fc6406264c045073124390819655365682772742010232556341356341315053153.06860829.056341305964710.02144413.03025631360.00.072697.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01295929160.02097152.023945606872097152.00.00368384.00.05244020.03821889.00.00.00.00.00.0524288.016597398827002166091902767841660919062446216597399471590
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521656051656054194304256008242999680x7fc65ed2e4000x7fc64062650083486568229718655361065193438024714591043581104358114844439.06691484.0104358105794075.02144842.030210406810.00.066788.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01614624260.02097152.0240210394142097152.00.00602400.00.09786300.03639293.00.00.00.00.00.0524288.016597399738201166091906871811660919134941716597400687558
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551656051656054194304256008243027200x7fc65ed2e2800x7fc64062654057786165654667655367324376154021931772232672232615134161.06849285.072232605950390.02151112.03027204490.00.060023.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01384727760.02097152.030207190902097152.00.00439040.00.06752990.03803605.00.00.00.00.00.0524288.016597400962928166091914262161660919187325316597401700142
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045816560516560541943042560012243054720x7fc65ed2e1000x7fc64062658057835605671091655367343243755043415872294472294420889185.013078373.072294406859586.02989569.03027219200.00.0833200.0524288.00.00.0524288.0524288.00.00.00.00.00.01417624270.02097152.024057210702097152.00.0044420105.00.06757160.03863921.00.00.00.00.00.00.016597401967893166091919385331660919240317016597402732156
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046116560516560541943042560012243082240x7fc65c5cdf800x7fc6406265c057715605661761655367326470355653855072144472144420784765.013006801.072144406827503.02960202.03027212530.00.0744215.0524288.00.00.0524288.0524288.00.00.00.00.00.01372924080.02097152.023987178872097152.00.0044354122.00.06745930.03855978.00.00.00.00.00.00.016597403000417166091924676491660919293020616597403722742
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641656051656054194304256008243109760x7fc65c5cde000x7fc64062660058022325691169655367370391356093066072527872527815161934.06860554.072527805946380.02143394.03027269220.00.065862.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01416724210.02097152.031487251472097152.00.00443960.00.06789320.03803990.00.00.00.00.00.0524288.016597403988272166091929954851660919344796216597404757815
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671656051656054194304256008243132160x7fc65c5cdc800x7fc64062664010943784108181206553614008120110670124941367972136797215023844.06738366.0136797205825806.02135280.030213672980.00.058348.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01825624080.02097152.0299913640372097152.00.00764750.00.012886780.03708229.00.00.00.00.00.0524288.016597405024356166091935130821660919438363616597406162296
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701656051656054194304256008243159680x7fc65c5cdb000x7fc64062668010975368108480626553614058960610804082971371920137192015290457.06856411.0137192005882552.02143234.030213701380.00.061122.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01832224130.02097152.0238713679432097152.00.00774140.00.012919860.03769714.00.00.00.00.00.0524288.016597406435457166091944604351660919531354916597407600476
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047316560516560541943042560012243187200x7fc65c5cd9800x7fc6406266c010984952108626566553614071584410724563191373118137311821362976.013161663.0137311806763053.02853254.030213741840.00.0725560.0524288.00.00.0524288.0524288.00.00.00.00.00.01830129830.02097152.0318213702312097152.00.0077632110.00.012936810.03900563.00.00.00.00.00.00.016597407866947166091953778691660919626442316597409075205
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047616560516560541943042560012243214720x7fc65c5cd8000x7fc64062670010979608108552156553614057083510711802511372450137245021278655.013115963.0137245006864167.02976929.030213710900.00.0656017.0524288.00.00.0524288.0524288.00.00.00.00.00.01831024140.02097152.0234313707562097152.00.007671986.00.012922350.03878315.00.00.00.00.00.00.016597409341035166091963402621660919721929616597410492535
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791656051656054194304256008243242240x7fc65c5cd6800x7fc64062674011016520108798746553614099654810804849821377064137706415189958.06813274.0137706405937211.02152262.030213759890.00.065995.0524288.00.00.0524288.0524288.00.00.0524288.00.00.01832027040.02097152.0237213734112097152.00.00774760.00.012969630.03762700.00.00.00.00.00.0524288.016597410759616166091972924161660919815273016597411940934
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821656051656054194304256008243264640x7fc65ed2e5000x7fc64062678021298520211816186553627452138821239936582662314266231414791691.06626793.0266231405724376.02149224.030226616690.00.089745.0524288.00.00.0524288.0524288.00.00.0524288.00.00.02706924200.02097152.0239326598462097152.00.001432492.00.025185180.03593390.00.00.00.00.00.0524288.016597412202475166091982216891660919992071816597414280062
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851656051656054194304256008243292160x7fc65ed2e3800x7fc6406267c021359112212250326553627506613521288717732669888266988815873503.06940638.0266988805966180.02131777.030226691970.00.079938.0524288.00.00.0524288.0524288.00.00.0524288.00.00.02702624280.02097152.0239326651282097152.00.001419902.00.025254790.03847781.00.00.00.00.00.0524288.016597414500005166092000261571660920169222516597416516714
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048816560516560541943042560012243319680x7fc65ed2e2000x7fc64062680021370520212391036553627525650121306251142671314267131422105579.013340157.0267131406733858.02788340.030226706190.00.0716112.0524288.00.00.0524288.0524288.00.00.00.00.00.02727529440.02097152.0239826673762097152.00.0014281464.00.025246350.03946708.00.00.00.00.00.00.016597416741686166092017869451660920351157316597418787145
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049116560516560541943042560012243347200x7fc65ed2e0800x7fc64062684021354968212284056553627510636621268269832669370266937022115922.013314581.0266937006740696.02794573.030226694210.00.0766826.0524288.00.00.0524288.0524288.00.00.00.00.00.02719929920.02097152.0240326643762097152.00.0014243386.00.025255260.03937367.00.00.00.00.00.00.016597419007547166092036003721660920531716016597421053416
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941656051656054194304256008243374720x7fc65c5cdf000x7fc64062688021392536212692466553627559350121273730532674066267406615801747.06923684.0267406606013051.02158959.030226738070.00.057773.0524288.00.00.0524288.0524288.00.00.0524288.00.00.02711624190.02097152.0238626717492097152.00.001422100.00.025268670.03841101.00.00.00.00.00.0524288.016597421297797166092054066001660920708018816597423295327
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049716560516560541943042560082400x7fc65c5cdd800x7fc6406268c042065176419359146553654348501342240910955258146525814614811260.06654349.0525814605743467.02155328.030252554770.00.062065.0524288.00.00.0524288.0524288.00.00.0524288.00.00.04488028820.02097152.0239752531872097152.00.002731322.00.049810100.03580778.00.00.00.00.00.0524288.016597423514630166092071710681660921052880416597427204631