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

66 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_VALU_ADD_F16SQ_INSTS_VALU_MUL_F16SQ_INSTS_VALU_FMA_F16SQ_INSTS_VALU_TRANS_F16SQ_INSTS_VALU_ADD_F32SQ_INSTS_VALU_MUL_F32SQ_INSTS_VALU_FMA_F32SQ_INSTS_VALU_TRANS_F32TCP_TCC_READ_REQ_sumTCP_TOTAL_CACHE_ACCESSES_sumTCP_TCC_WRITE_REQ_sumTCP_TCC_ATOMIC_WITH_RET_REQ_sumTCC_EA_RDREQ_32B_sumTCC_EA_RDREQ_sumTCC_EA_WRREQ_64B_sumTCC_EA_WRREQ_sumSQ_INSTS_VALU_ADD_F64SQ_INSTS_VALU_MUL_F64SQ_INSTS_VALU_FMA_F64SQ_INSTS_VALU_TRANS_F64SQ_INSTS_VALU_MFMA_MOPS_F16SQ_INSTS_VALU_MFMA_MOPS_BF16SQ_INSTS_VALU_MFMA_MOPS_F32SQ_INSTS_VALU_MFMA_MOPS_F64TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sumSQ_LDS_IDX_ACTIVESQ_LDS_BANK_CONFLICTDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000193412193412335544322560043241600x00x7f5dc6204280000000000.00000000008388608.00000000004194304.00000000000.00000000000.0000000000311.00000000004128768.00000000004128768.0000000000000000000.00000000000017116536858082170871992789821711668389645217116683987452
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00219341219341232768256001224138880x00x7f5dc6223f80000000008192.000000000016384.00000000000.00000000000.00000000000.00000000008261.00000000000.00000000000.0000000000000000000.00000000000017116689727452171166838964521711669009327317116690095732
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051934121934124194304256001224143360x7f5dc912d3800x7f5dc6223fc000000026214402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097338.00000000000.00000000000.0000000000000000000.00000000000017116690694035171166900932731711669133663817116691338317
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081934121934124194304256001624150400x7f5dc912d2000x7f5dc622400000000026214404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194600.00000000000.00000000000.0000000000000000000.00000000000017116691937600171166913366381711669270032317116692702169
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111934121934124194304256001624154880x7f5dc912d0800x7f5dc6224040000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194607.00000000000.00000000000.000000000000262144000000.00000000000017116693296653171166927003231711669395952717116693960704
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141934121934124194304256001224159360x7f5dc69cdf000x7f5dc622408000262144000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097347.00000000000.00000000000.0000000000000000000.00000000000017116694554958171166939595271711669515201217116695153271
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171934121934124194304256001224163840x7f5dc69cdd800x7f5dc62240c0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097341.00000000000.00000000000.0000000000000000000.00000000000017116695747294171166951520121711669634817617116696349278
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201934121934124194304256001224170880x7f5dc69cdc000x7f5dc622410000000065536002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097341.00000000000.00000000000.0000000000000000000.00000000000017116696956191171166963481761711669755810017116697559254
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231934121934124194304256001624177920x7f5dc69cda800x7f5dc622414000000078643204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194596.00000000000.00000000000.0000000000000000000.00000000000017116698154327171166975581001711669888578517116698886897
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261934121934124194304256001624184960x7f5dc69cd9000x7f5dc6224180000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194598.00000000000.00000000000.000000000000786432000000.00000000000017116699481020171166988857851711670015506917116700156451
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291934121934124194304256001624192000x7f5dc69cd7800x7f5dc62241c000786432000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097338.00000000000.00000000000.0000000000000000000.00000000000017116700751615171167001550691711670137795417116701378677
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321934121934124194304256001624199040x7f5dc69cd6000x7f5dc6224200000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097344.00000000000.00000000000.0000000000000000000.00000000000017116701973680171167013779541711670258723817116702588103
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351934121934124194304256001224206080x7f5dc912d4800x7f5dc6224240000000104857602097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097337.00000000000.00000000000.0000000000000000000.00000000000017116703191546171167025872381711670380324217116703803879
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381934121934124194304256001624213120x7f5dc912d3000x7f5dc6224280000000131072004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194591.00000000000.00000000000.0000000000000000000.00000000000017116704399443171167038032421711670510596717116705106893
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411934121934124194304256001624220160x7f5dc912d1800x7f5dc62242c0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194592.00000000000.00000000000.0000000000001310720000000.00000000000017116705702346171167051059671711670641429217116706415287
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441934121934124194304256001624227200x7f5dc912d0000x7f5dc6224300001310720000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097348.00000000000.00000000000.0000000000000000000.00000000000017116707010810171167064142921711670761989617116707620723
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471934121934124194304256001224234240x7f5dc69cde800x7f5dc6224340000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097342.00000000000.00000000000.0000000000000000000.00000000000017116708215966171167076198961711670882358017116708824139
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501934121934124194304256001224241280x7f5dc69cdd000x7f5dc6224380000000144179202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097341.00000000000.00000000000.0000000000000000000.00000000000017116709426323171167088235801711671002934517116710029926
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531934121934124194304256001624248320x7f5dc69cdb800x7f5dc62243c0000000183500804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194587.00000000000.00000000000.0000000000000000000.00000000000017116710624919171167100293451711671131558917116711316670
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561934121934124194304256001624255360x7f5dc69cda000x7f5dc6224400000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194594.00000000000.00000000000.0000000000001835008000000.00000000000017116711911414171167113155891711671261287417116712613544
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591934121934124194304256001224262400x7f5dc69cd8800x7f5dc6224440001835008000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097347.00000000000.00000000000.0000000000000000000.00000000000017116713208677171167126128741711671383063817116713830950
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621934121934124194304256001224269440x7f5dc69cd7000x7f5dc6224480000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097348.00000000000.00000000000.0000000000000000000.00000000000017116714426223171167138306381711671502648317116715027167
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651934121934124194304256001224276480x7f5dc912d5800x7f5dc62244c0000000183500802097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097345.00000000000.00000000000.0000000000000000000.00000000000017116715629520171167150264831711671625704717116716257492
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681934121934124194304256001624286080x7f5dc912d4000x7f5dc6224500000000235929604194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194585.00000000000.00000000000.0000000000000000000.00000000000017116716852446171167162570471711671755033217116717551086
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711934121934124194304256001624293120x7f5dc912d2800x7f5dc6224540000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194588.00000000000.00000000000.0000000000002359296000000.00000000000017116718146680171167175503321711671883145617116718831891
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741934121934124194304256001224300160x7f5dc912d1000x7f5dc6224580002359296000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097347.00000000000.00000000000.0000000000000000000.00000000000017116719427444171167188314561711672004042117116720040987
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077193412193412419430425600824309760x7f5dc69cdf800x7f5dc62245c0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097347.00000000000.00000000000.0000000000000000000.00000000000017116720636181171167200404211711672125674517116721257263
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801934121934124194304256001224316800x7f5dc69cde000x7f5dc6224600000000222822402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097347.00000000000.00000000000.0000000000000000000.00000000000017116721858926171167212567451711672248986917116722490529
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831934121934124194304256001624326400x7f5dc69cdc800x7f5dc6224640000000288358404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194583.00000000000.00000000000.0000000000000000000.00000000000017116723087072171167224898691711672379643417116723797093
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861934121934124194304256001224336000x7f5dc69cdb000x7f5dc6224680000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194591.00000000000.00000000000.0000000000002883584000000.00000000000017116724392376171167237964341711672509147917116725092306
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891934121934124194304256001224345600x7f5dc69cd9800x7f5dc62246c0002883584000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097352.00000000000.00000000000.0000000000000000000.00000000000017116725686620171167250914791711672630268317116726303053
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092193412193412419430425600824355200x7f5dc69cd8000x7f5dc6224700000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097353.00000000000.00000000000.0000000000000000000.00000000000017116726898096171167263026831711672749788717116727497989
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951934121934124194304256001224362240x7f5dc69cd6800x7f5dc6224740000000262144002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097346.00000000000.00000000000.0000000000000000000.00000000000017116728100772171167274978871711672877693217116728777023
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981934121934124194304256001224371840x7f5dc912d5000x7f5dc6224780000000340787204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194585.00000000000.00000000000.0000000000000000000.00000000000017116729371957171167287769321711673005293717116730052928
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011934121934124194304256001224381440x7f5dc912d3800x7f5dc62247c0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194604.00000000000.00000000000.0000000000003407872000000.00000000000017116730649561171167300529371711673137534117116731375381
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041934121934124194304256001224391040x7f5dc912d2000x7f5dc6224800003407872000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097353.00000000000.00000000000.0000000000000000000.00000000000017116731970874171167313753411711673261710617116732617046
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107193412193412419430425600824403200x7f5dc912d0800x7f5dc6224840000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097355.00000000000.00000000000.0000000000000000000.00000000000017116733211930171167326171061711673385631017116733856472
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101934121934124194304256001224412800x7f5dc69cdf000x7f5dc6224880000000301465602097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097350.00000000000.00000000000.0000000000000000000.00000000000017116734459875171167338563101711673511391517116735114007
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131934121934124194304256001224422400x7f5dc69cdd800x7f5dc62248c0000000393216004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194588.00000000000.00000000000.0000000000000000000.00000000000017116735708080171167351139151711673636655917116736367152
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161934121934124194304256001224432000x7f5dc69cdc000x7f5dc6224900000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194582.00000000000.00000000000.0000000000003932160000000.00000000000017116736961705171167363665591711673765792417116737658396
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119193412193412419430425600824441600x7f5dc69cda800x7f5dc6224940003932160000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097352.00000000000.00000000000.0000000000000000000.00000000000017116738253889171167376579241711673886688817116738867432
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221934121934124194304256001224453760x7f5dc69cd9000x7f5dc6224980000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097356.00000000000.00000000000.0000000000000000000.00000000000017116739461646171167388668881711674008321217116740083668
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251934121934124194304256001224463360x7f5dc69cd7800x7f5dc62249c0000000340787202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097353.00000000000.00000000000.0000000000000000000.00000000000017116740686072171167400832121711674128785717116741288635
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281934121934124194304256001224475520x7f5dc69cd6000x7f5dc6224a00000000445644804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194587.00000000000.00000000000.0000000000000000000.00000000000017116741883608171167412878571711674259346117116742594018
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311934121934124194304256001224485120x7f5dc912d4800x7f5dc6224a40000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194580.00000000000.00000000000.0000000000004456448000000.00000000000017116743190522171167425934611711674387074617116743871233
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134193412193412419430425600824494720x7f5dc912d3000x7f5dc6224a80004456448000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097353.00000000000.00000000000.0000000000000000000.00000000000017116744465556171167438707461711674505539017116745055960
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371934121934124194304256001224506880x7f5dc912d1800x7f5dc6224ac0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097354.00000000000.00000000000.0000000000000000000.00000000000017116745651763171167450553901711674628003517116746280396
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401934121934124194304256001224516480x7f5dc912d0000x7f5dc6224b00000000380108802097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097354.00000000000.00000000000.0000000000000000000.00000000000017116746884819171167462780411711674751195917116747514601
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431934121934124194304256001224528640x7f5dc69cde800x7f5dc6224b40000000498073604194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194571.00000000000.00000000000.0000000000000000000.00000000000017116748109635171167475119591711674879835917116748800776
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461934121934124194304256001224540800x7f5dc69cdd000x7f5dc6224b80000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194562.00000000000.00000000000.0000000000004980736000000.00000000000017116749395389171167487983591711675009051917116750093190
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149193412193412419430425600824552960x7f5dc69cdb800x7f5dc6224bc0004980736000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097354.00000000000.00000000000.0000000000000000000.00000000000017116750687653171167500905191711675132507817116751327935
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521934121934124194304256001224567680x7f5dc69cda000x7f5dc6224c00000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097363.00000000000.00000000000.0000000000000000000.00000000000017116751924349171167513250781711675254219817116752544361
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551934121934124194304256001224577280x7f5dc69cd8800x7f5dc6224c40000000419430402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097358.00000000000.00000000000.0000000000000000000.00000000000017116753147085171167525421981711675374443717116753747118
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581934121934124194304256001224589440x7f5dc69cd7000x7f5dc6224c80000000550502404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194579.00000000000.00000000000.0000000000000000000.00000000000017116754341881171167537444371711675502811717116755030922
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611934121934124194304256001224601600x7f5dc912d5800x7f5dc6224cc0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194576.00000000000.00000000000.0000000000005505024000000.00000000000017116755625315171167550281171711675630763717116756310126
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164193412193412419430425600824613760x7f5dc912d4000x7f5dc6224d00005505024000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097352.00000000000.00000000000.0000000000000000000.00000000000017116756905239171167563076371711675749947617116757502333
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671934121934124194304256001224628480x7f5dc912d2800x7f5dc6224d40000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097362.00000000000.00000000000.0000000000000000000.00000000000017116758098266171167574994761711675871067617116758713139
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701934121934124194304256001224638080x7f5dc912d1000x7f5dc6224d80000000458752002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097353.00000000000.00000000000.0000000000000000000.00000000000017116759316952171167587106761711675991547617116759918195
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731934121934124194304256001224650240x7f5dc69cdf800x7f5dc6224dc0000000602931204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194567.00000000000.00000000000.0000000000000000000.00000000000017116760513009171167599154761711676119899517116761201760
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761934121934124194304256001224662400x7f5dc69cde000x7f5dc6224e00000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194585.00000000000.00000000000.0000000000006029312000000.00000000000017116761795973171167611989951711676247243517116762474754
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179193412193412419430425600824674560x7f5dc69cdc800x7f5dc6224e40006029312000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097356.00000000000.00000000000.0000000000000000000.00000000000017116763069628171167624724351711676367163417116763674231
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821934121934124194304256001224689280x7f5dc69cdb000x7f5dc6224e80000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097361.00000000000.00000000000.0000000000000000000.00000000000017116764269034171167636716341711676489083417116764893637
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851934121934124194304256001224701440x7f5dc69cd9800x7f5dc6224ec0000000498073602097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097349.00000000000.00000000000.0000000000000000000.00000000000017116765507880171167648908341711676624171417116766244299
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881934121934124194304256001224716160x7f5dc69cd8000x7f5dc6224f00000000655360004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194538.00000000000.00000000000.0000000000000000000.00000000000017116766840033171167662417141711676749915317116767501644
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911934121934124194304256001224728320x7f5dc69cd6800x7f5dc6224f40000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194562.00000000000.00000000000.0000000000006553600000000.00000000000017116768095798171167674991531711676878635317116768789118
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194193412193412419430425600824740480x7f5dc912d5000x7f5dc6224f80006553600000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097353.00000000000.00000000000.0000000000000000000.00000000000017116769383312171167687863531711676997387217116769976645
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971934121934124194304256001224757760x7f5dc912d3800x7f5dc6224fc0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097357.00000000000.00000000000.0000000000000000000.00000000000017116770572089171167699738721711677120059217116771203391
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001934121934124194304256001224769920x7f5dc912d2000x7f5dc6225000000000537395202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097356.00000000000.00000000000.0000000000000000000.00000000000017116771805994171167712005921711677241771217116772420277
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031934121934124194304256001224784640x7f5dc912d0800x7f5dc6225040000000707788804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194560.00000000000.00000000000.0000000000000000000.00000000000017116773015071171167724177121711677371323117116773715771
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061934121934124194304256001224799360x7f5dc69cdf000x7f5dc6225080000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194569.00000000000.00000000000.0000000000007077888000000.00000000000017116774311124171167737132311711677499691117116774999455
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209193412193412419430425600824814080x7f5dc69cdd800x7f5dc62250c0007077888000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097361.00000000000.00000000000.0000000000000000000.00000000000017116775594699171167749969111711677621387117116776216571
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121934121934124194304256001224831360x7f5dc69cdc000x7f5dc6225100000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097351.00000000000.00000000000.0000000000000000000.00000000000017116776812235171167762138711711677746587017116777468057
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151934121934124194304256001224843520x7f5dc69cda800x7f5dc6225140000000576716802097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097350.00000000000.00000000000.0000000000000000000.00000000000017116778070820171167774658701711677869787017116778700512
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181934121934124194304256001224858240x7f5dc69cd9000x7f5dc6225180000000760217604194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194566.00000000000.00000000000.0000000000000000000.00000000000017116779295916171167786978701711677997050917116779973347
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211934121934124194304256001224872960x7f5dc69cd7800x7f5dc62251c0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194566.00000000000.00000000000.0000000000007602176000000.00000000000017116780568040171167799705091711678124298917116781245551
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241934121934124194304256001224887680x7f5dc69cd6000x7f5dc6225200007602176000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097355.00000000000.00000000000.0000000000000000000.00000000000017116781839355171167812429891711678246410917116782466587
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271934121934124194304256001224907520x7f5dc912d4800x7f5dc6225240000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097360.00000000000.00000000000.0000000000000000000.00000000000017116783062031171167824641091711678369914817116783701563
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301934121934124194304256001224919680x7f5dc912d3000x7f5dc6225280000000616038402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097350.00000000000.00000000000.0000000000000000000.00000000000017116784303346171167836991481711678490074817116784903269
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331934121934124194304256001224934400x7f5dc912d1800x7f5dc62252c0000000812646404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194577.00000000000.00000000000.0000000000000000000.00000000000017116785498373171167849007481711678619514817116786197643
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361934121934124194304256001224949120x7f5dc912d0000x7f5dc6225300000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194574.00000000000.00000000000.0000000000008126464000000.00000000000017116786792717171167861951481711678749386717116787496257
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391934121934124194304256001224963840x7f5dc69cde800x7f5dc6225340008126464000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097363.00000000000.00000000000.0000000000000000000.00000000000017116788091720171167874938671711678869738717116788700153
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421934121934124194304256001224983680x7f5dc69cdd000x7f5dc6225380000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097344.00000000000.00000000000.0000000000000000000.00000000000017116789294877171167886973871711678993562617116789938189
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451934121934124194304256001224995840x7f5dc69cdb800x7f5dc62253c0000000655360002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097354.00000000000.00000000000.0000000000000000000.00000000000017116790541042171167899356261711679114842617116791150975
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024819341219341241943042560012241013120x7f5dc69cda000x7f5dc6225400000000865075204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194579.00000000000.00000000000.0000000000000000000.00000000000017116791746618171167911484261711679242682617116792429239
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025119341219341241943042560012241027840x7f5dc69cd8800x7f5dc6225440000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194603.00000000000.00000000000.0000000000008650752000000.00000000000017116793023813171167924268261711679371674517116793719233
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025419341219341241943042560012241042560x7f5dc69cd7000x7f5dc6225480008650752000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097359.00000000000.00000000000.0000000000000000000.00000000000017116794312977171167937167451711679492922517116794932010
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025719341219341241943042560012241062400x7f5dc912d5800x7f5dc62254c0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097335.00000000000.00000000000.0000000000000000000.00000000000017116795525753171167949292251711679616330417116796166005
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026019341219341241943042560012241077120x7f5dc912d4000x7f5dc6225500000000694681602097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097358.00000000000.00000000000.0000000000000000000.00000000000017116796769028171167961633041711679736970417116797372432
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026319341219341241943042560016241094400x7f5dc912d2800x7f5dc6225540000000917504004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194554.00000000000.00000000000.0000000000000000000.00000000000017116797967995171167973697041711679867258417116798675065
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026619341219341241943042560016241111680x7f5dc912d1000x7f5dc6225580000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194576.00000000000.00000000000.0000000000009175040000000.00000000000017116799270609171167986725841711680010026317116800102516
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691934121934124194304256008241128960x7f5dc69cdf800x7f5dc62255c0009175040000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097364.00000000000.00000000000.0000000000000000000.00000000000017116800698479171168001002631711680127530317116801277713
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027219341219341241943042560012241151360x7f5dc69cde000x7f5dc6225600000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097343.00000000000.00000000000.0000000000000000000.00000000000017116801872696171168012753031711680249594217116802498529
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027519341219341241943042560012241166080x7f5dc69cdc800x7f5dc6225640000000734003202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097354.00000000000.00000000000.0000000000000000000.00000000000017116803102182171168024959421711680372106217116803723735
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027819341219341241943042560016241183360x7f5dc69cdb000x7f5dc6225680000000969932804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194582.00000000000.00000000000.0000000000000000000.00000000000017116804319698171168037210621711680497370217116804976540
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028119341219341241943042560016241200640x7f5dc69cd9800x7f5dc62256c0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194580.00000000000.00000000000.0000000000009699328000000.00000000000017116805570953171168049737021711680625834117116806261414
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028419341219341241943042560012241217920x7f5dc69cd8000x7f5dc6225700009699328000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097361.00000000000.00000000000.0000000000000000000.00000000000017116806857757171168062583411711680759738117116807599707
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028719341219341241943042560012241240320x7f5dc69cd6800x7f5dc6225740000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097328.00000000000.00000000000.0000000000000000000.00000000000017116808194600171168075973811711680881290117116808815473
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029019341219341241943042560012241255040x7f5dc912d5000x7f5dc6225780000000812646402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097362.00000000000.00000000000.0000000000000000000.00000000000017116809417936171168088131001711681000446017116810010730
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029319341219341241943042560012241274880x7f5dc912d3800x7f5dc62257c00000001074790404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194605.00000000000.00000000000.0000000000000000000.00000000000017116810602573171168100044601711681127822017116811280414
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029619341219341241943042560012241292160x7f5dc912d2000x7f5dc6225800000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194588.00000000000.00000000000.00000000000010747904000000.00000000000017116811876998171168112782201711681256126017116812563639
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029919341219341241943042560012241309440x7f5dc912d0800x7f5dc62258400010747904000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097358.00000000000.00000000000.0000000000000000000.00000000000017116813159482171168125612601711681376462017116813766805
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030219341219341241943042560012241334400x7f5dc69cdf000x7f5dc6225880000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097327.00000000000.00000000000.0000000000000000000.00000000000017116814363158171168137646201711681502670017116815029000
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030519341219341241943042560012241349120x7f5dc69cdd800x7f5dc62258c0000000891289602097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097360.00000000000.00000000000.0000000000000000000.00000000000017116815631553171168150267001711681622702017116816229356
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030819341219341241943042560012241368960x7f5dc69cdc000x7f5dc62259000000001179648004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194606.00000000000.00000000000.0000000000000000000.00000000000017116816824579171168162270201711681751886017116817521480
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031119341219341241943042560012241388800x7f5dc69cda800x7f5dc6225940000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194592.00000000000.00000000000.00000000000011796480000000.00000000000017116818116783171168175188601711681881502017116818817324
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031419341219341241943042560012241408640x7f5dc69cd9000x7f5dc62259800011796480000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097355.00000000000.00000000000.0000000000000000000.00000000000017116819412147171168188150201711682004046017116820042640
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031719341219341241943042560012241436160x7f5dc69cd7800x7f5dc62259c0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097337.00000000000.00000000000.0000000000000000000.00000000000017116820638013171168200404601711682134606017116821348603
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032019341219341241943042560012241453440x7f5dc69cd6000x7f5dc6225a00000000969932802097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097366.00000000000.00000000000.0000000000000000000.00000000000017116821953226171168213460601711682257054017116822572769
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032319341219341241943042560012241475840x7f5dc912d4800x7f5dc6225a400000001284505604194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194613.00000000000.00000000000.0000000000000000000.00000000000017116823169573171168225705401711682382286017116823825014
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032619341219341241943042560012241495680x7f5dc912d3000x7f5dc6225a80000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194598.00000000000.00000000000.00000000000012845056000000.00000000000017116824420618171168238228601711682512686017116825129378
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032919341219341241943042560012241515520x7f5dc912d1800x7f5dc6225ac00012845056000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097339.00000000000.00000000000.0000000000000000000.00000000000017116825724751171168251268601711682632894017116826331454
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033219341219341241943042560012241543040x7f5dc912d0000x7f5dc6225b00000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097333.00000000000.00000000000.0000000000000000000.00000000000017116826926998171168263289401711682760910017116827611609
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033519341219341241943042560012241562880x7f5dc69cde800x7f5dc6225b400000001127219202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097366.00000000000.00000000000.0000000000000000000.00000000000017116828214102171168276091001711682882654017116828828605
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033819341219341241943042560012241587840x7f5dc69cdd000x7f5dc6225b800000001494220804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194633.00000000000.00000000000.0000000000000000000.00000000000017116829424388171168288265401711683010398017116830109049
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034119341219341241943042560012241610240x7f5dc69cdb800x7f5dc6225bc0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194624.00000000000.00000000000.00000000000014942208000000.00000000000017116830701253171168301039801711683141006017116831413653
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034419341219341241943042560012241632640x7f5dc69cda000x7f5dc6225c000014942208000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097337.00000000000.00000000000.0000000000000000000.00000000000017116832007546171168314100601711683264014017116832642729
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034719341219341241943042560012241665280x7f5dc69cd8800x7f5dc6225c40000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097339.00000000000.00000000000.0000000000000000000.00000000000017116833237752171168326401401711683392814017116833969362
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035019341219341241943042560012241685120x7f5dc69cd7000x7f5dc6225c800000001284505602097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097348.00000000000.00000000000.0000000000000000000.00000000000017116834533676171168339281401711683512990017116835132079
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035319341219341241943042560012241712640x7f5dc912d5800x7f5dc6225cc00000001703936004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194633.00000000000.00000000000.0000000000000000000.00000000000017116835726983171168351299001711683638750117116836389984
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035619341219341241943042560012241737600x7f5dc912d4000x7f5dc6225d00000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194640.00000000000.00000000000.00000000000017039360000000.00000000000017116836985378171168363875011711683768142117116837685078
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035919341219341241943042560012241762560x7f5dc912d2800x7f5dc6225d400017039360000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097331.00000000000.00000000000.0000000000000000000.00000000000017116838280192171168376814211711683891262117116838915204
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036219341219341241943042560012241797760x7f5dc912d1000x7f5dc6225d80000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097341.00000000000.00000000000.0000000000000000000.00000000000017116839510297171168389126211711684025678117116840321165
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036519341219341241943042560012241822720x7f5dc69cdf800x7f5dc6225dc00000001599078402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097337.00000000000.00000000000.0000000000000000000.00000000000017116840864580171168402567811711684150782117116841510512
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036819341219341241943042560012241855360x7f5dc69cde000x7f5dc6225e000000002123366404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194640.00000000000.00000000000.0000000000000000000.00000000000017116842106495171168415078211711684281166117116842876444
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037119341219341241943042560012241885440x7f5dc69cdc800x7f5dc6225e40000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194628.00000000000.00000000000.00000000000021233664000000.00000000000017116843408669171168428116611711684409726117116844137808
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037419341219341241943042560012241915520x7f5dc69cdb000x7f5dc6225e800021233664000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097347.00000000000.00000000000.0000000000000000000.00000000000017116844694113171168440972611711684536110117116845363414
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037719341219341241943042560012241958400x7f5dc69cd9800x7f5dc6225ec0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097351.00000000000.00000000000.0000000000000000000.00000000000017116845957717171168453611011711684675870117116846799064
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038019341219341241943042560012241985920x7f5dc69cd8000x7f5dc6225f000000001913651202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097329.00000000000.00000000000.0000000000000000000.00000000000017116847364848171168467587011711684801326117116848015800
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038319341219341241943042560012242023680x7f5dc69cd6800x7f5dc6225f400000002542796804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194632.00000000000.00000000000.0000000000000000000.00000000000017116848610973171168480132611711684932382117116849388362
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038619341219341241943042560012242058880x7f5dc912d5000x7f5dc6225f80000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194610.00000000000.00000000000.00000000000025427968000000.00000000000017116849921877171168493238211711685066574117116850730214
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038919341219341241943042560012242094080x7f5dc912d3800x7f5dc6225fc00025427968000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097334.00000000000.00000000000.0000000000000000000.00000000000017116851263269171168506657411711685194494117116852008859
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039219341219341241943042560012242144640x7f5dc912d2000x7f5dc6226000000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097363.00000000000.00000000000.0000000000000000000.00000000000017116852543214171168519449411711685339118117116853434319
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039519341219341241943042560012242177280x7f5dc912d0800x7f5dc62260400000002228224002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097342.00000000000.00000000000.0000000000000000000.00000000000017116853997423171168533911811711685467838117116854680664
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039819341219341241943042560012242220160x7f5dc69cdf000x7f5dc62260800000002962227204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194628.00000000000.00000000000.0000000000000000000.00000000000017116855276208171168546783811711685601390117116856054456
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040119341219341241943042560012242260480x7f5dc69cdd800x7f5dc62260c0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194596.00000000000.00000000000.00000000000029622272000000.00000000000017116856611071171168560139011711685736494117116857404368
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040419341219341241943042560012242300800x7f5dc69cdc000x7f5dc62261000029622272000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097370.00000000000.00000000000.0000000000000000000.00000000000017116857962583171168573649411711685872974117116858770190
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040719341219341241943042560012242359040x7f5dc69cda800x7f5dc6226140000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097377.00000000000.00000000000.0000000000000000000.00000000000017116859327725171168587297411711686023646117116860276578
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041019341219341241943042560012242394240x7f5dc69cd9000x7f5dc62261800000002542796802097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097345.00000000000.00000000000.0000000000000000000.00000000000017116860842063171168602364611711686153150117116861570572
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041319341219341241943042560012242442240x7f5dc69cd7800x7f5dc62261c00000003381657604194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194616.00000000000.00000000000.0000000000000000000.00000000000017116862129287171168615315011711686290046217116862940694
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041619341219341241943042560012242487680x7f5dc69cd6000x7f5dc6226200000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194603.00000000000.00000000000.00000000000033816576000000.00000000000017116863497449171168629004621711686425870217116864298376
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041919341219341241943042560012242533120x7f5dc912d4800x7f5dc62262400033816576000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097364.00000000000.00000000000.0000000000000000000.00000000000017116864856891171168642587021711686560638217116865670018
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221934121934124194304256008242555520x7f5dc912d3000x7f5dc6226280000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097324.00000000000.00000000000.0000000000000000000.00000000000017116866204523171168656063821711686715982217116867224725
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042519341219341241943042560012242598400x7f5dc912d1800x7f5dc62262c00000003171942402097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097352.00000000000.00000000000.0000000000000000000.00000000000017116867765990171168671598221711686849182217116868556218
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042819341219341241943042560012242656640x7f5dc912d0000x7f5dc62263000000004220518404194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194588.00000000000.00000000000.0000000000000000000.00000000000017116869089013171168684918221711686992110217116869962959
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043119341219341241943042560012242712320x7f5dc69cde800x7f5dc6226340000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194609.00000000000.00000000000.00000000000042205184000000.00000000000017116870519223171168699211021711687131694217116871359580
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341934121934124194304256008242732160x7f5dc69cdd000x7f5dc62263800042205184000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097326.00000000000.00000000000.0000000000000000000.00000000000017116871913444171168713192751711687273384017116872777990
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371934121934124194304256008242757120x7f5dc69cdb800x7f5dc62263c0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097323.00000000000.00000000000.0000000000000000000.00000000000017116873329405171168727338401711687437672517116874416715
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044019341219341241943042560012242807680x7f5dc69cda000x7f5dc62264000000003801088002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097362.00000000000.00000000000.0000000000000000000.00000000000017116874980119171168743767251711687579977117116875837785
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044319341219341241943042560012242876160x7f5dc69cd8800x7f5dc62264400000005059379204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194629.00000000000.00000000000.0000000000000000000.00000000000017116876395789171168757997711711687726217617116877324323
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044619341219341241943042560012242942080x7f5dc69cd7000x7f5dc6226480000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194616.00000000000.00000000000.00000000000050593792000000.00000000000017116877856738171168772621761711687871834117116878780813
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491934121934124194304256008242969600x7f5dc912d5800x7f5dc62264c00050593792000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097337.00000000000.00000000000.0000000000000000000.00000000000017116879313128171168787183411711688016906717116880231272
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521934121934124194304256008242999680x7f5dc912d4000x7f5dc6226500000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097330.00000000000.00000000000.0000000000000000000.00000000000017116880764887171168801690671711688192251317116881985233
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551934121934124194304256008243027200x7f5dc912d2800x7f5dc62265400000006737100802097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097328.00000000000.00000000000.0000000000000000000.00000000000017116882525538171168819225131711688349547917116883556740
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045819341219341241943042560012243054720x7f5dc912d1000x7f5dc62265800000006737100804194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194555.00000000000.00000000000.0000000000000000000.00000000000017116884091095171168834954791711688508332517116885121286
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046119341219341241943042560012243082240x7f5dc69cdf800x7f5dc62265c0000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194552.00000000000.00000000000.00000000000067371008000000.00000000000017116885679850171168850833251711688665501117116886693212
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641934121934124194304256008243109760x7f5dc69cde000x7f5dc62266000067371008000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097327.00000000000.00000000000.0000000000000000000.00000000000017116887250397171168866550111711688835181717116888388675
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671934121934124194304256008243132160x7f5dc69cdc800x7f5dc6226640000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097318.00000000000.00000000000.0000000000000000000.00000000000017116888946649171168883518171711689030318417116890366610
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701934121934124194304256008243159680x7f5dc69cdb000x7f5dc622668000000013447987202097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097324.00000000000.00000000000.0000000000000000000.00000000000017116890906135171168903031841711689225471117116892320635
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047319341219341241943042560012243187200x7f5dc69cd9800x7f5dc62266c000000013447987204194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194543.00000000000.00000000000.0000000000000000000.00000000000017116892849351171168922547111711689425087917116894295050
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047619341219341241943042560012243214720x7f5dc69cd8000x7f5dc6226700000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194549.00000000000.00000000000.000000000000134479872000000.00000000000017116894846275171168942508791711689621776617116896256036
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791934121934124194304256008243242240x7f5dc69cd6800x7f5dc622674000134479872000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097323.00000000000.00000000000.0000000000000000000.00000000000017116896811670171168962177661711689818977317116898251310
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821934121934124194304256008243264640x7f5dc912d5000x7f5dc6226780000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097314.00000000000.00000000000.0000000000000000000.00000000000017116898784895171168981897731711690099634417116901058492
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851934121934124194304256008243292160x7f5dc912d3800x7f5dc62267c000000026869760002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097324.00000000000.00000000000.0000000000000000000.00000000000017116901606327171169009963441711690380627417116903874623
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048819341219341241943042560012243319680x7f5dc912d2000x7f5dc622680000000026869760004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194542.00000000000.00000000000.0000000000000000000.00000000000017116904403119171169038062741711690664516517116906709474
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049119341219341241943042560012243347200x7f5dc912d0800x7f5dc6226840000000004194304.00000000008388608.00000000000.00000000000.00000000000.00000000004194549.00000000000.00000000000.000000000000268697600000000.00000000000017116907240449171169066451651711690948005517116909544335
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941934121934124194304256008243374720x7f5dc69cdf000x7f5dc622688000268697600000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097326.00000000000.00000000000.0000000000000000000.00000000000017116910073830171169094800551711691229478617116912365227
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049719341219341241943042560082400x7f5dc69cdd800x7f5dc62268c0000000002097152.00000000002097152.00000000000.00000000000.00000000000.00000000002097315.00000000000.00000000000.0000000000000000000.00000000000017116912889272171169122947861711691674200217116916788423