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

38 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_LDSSQ_INST_LEVEL_LDSSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd0002331223312335544322560043241600x00x7feaad20428000014233267445370142326422506741423341472008314233414811963
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]002233122331232768256001224138880x00x7feaad223f8000014233420005197142334147200831423342013114114233420134244
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]00523312233124194304256001224143360x7feab02cc3800x7feaad223fc000014233420170393142334201311411423342045770214233420460207
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00823312233124194304256001624150400x7feab02cc2000x7feaad22400000014233420496887142334204577021423342085642414233420858779
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]001123312233124194304256001624154880x7feab02cc0800x7feaad22404000014233420890689142334208564241423342125146514233421253831
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]001423312233124194304256001224159360x7feaadc2df000x7feaad22408000014233421286690142334212514651423342156458614233421566805
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]001723312233124194304256001224163840x7feaadc2dd800x7feaad2240c000014233421599144142334215645861423342187002714233421872388
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]002023312233124194304256001224170880x7feaadc2dc000x7feaad22410000014233421915368142334218700271423342217354814233422175942
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002323312233124194304256001624177920x7feaadc2da800x7feaad22414000014233422206112142334221735481423342257563014233422577884
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]002623312233124194304256001624184960x7feaadc2d9000x7feaad22418000014233422608323142334225756301423342296747114233422969786
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]002923312233124194304256001624192000x7feaadc2d7800x7feaad2241c000014233422999415142334229674711423342328571214233423288309
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]003223312233124194304256001624199040x7feaadc2d6000x7feaad22420000014233423319219142334232857121423342358907314233423591443
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]003523312233124194304256001224206080x7feab02cc4800x7feaad22424000014233423630112142334235890731423342389595414233423898357
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]003823312233124194304256001624213120x7feab02cc3000x7feaad22428000014233423928926142334238959541423342428523514233424287569
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]004123312233124194304256001624220160x7feab02cc1800x7feaad2242c000014233424318808142334242852351423342467515714233424677491
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]004423312233124194304256001624227200x7feab02cc0000x7feaad22430000014233424708090142334246751571423342497483814233424977245
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]004723312233124194304256001224234240x7feaadc2de800x7feaad22434000014233425007194142334249748381423342527531914233425277809
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]005023312233124194304256001224241280x7feaadc2dd000x7feaad22438000014233425314958142334252753191423342557516014233425577492
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]005323312233124194304256001624248320x7feaadc2db800x7feaad2243c000014233425607532142334255751601423342596380114233425966164
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]005623312233124194304256001624255360x7feaadc2da000x7feaad22440000014233425997074142334259638011423342638092314233426383696
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]005923312233124194304256001224262400x7feaadc2d8800x7feaad22444000014233426414205142334263809231423342669692414233426699540
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]006223312233124194304256001224269440x7feaadc2d7000x7feaad22448000014233426729259142334266969241423342700156514233427003913
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]006523312233124194304256001224276480x7feab02cc5800x7feaad2244c000014233427040503142334270015651423342728524614233427286918
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]006823312233124194304256001624286080x7feab02cc4000x7feaad22450000014233427318107142334272852461423342764828714233427650120
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]007123312233124194304256001624293120x7feab02cc2800x7feaad22454000014233427681020142334276482871423342801116814233428012883
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]007423312233124194304256001224300160x7feab02cc1000x7feaad22458000014233428043812142334280111681423342828700914233428288867
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00772331223312419430425600824309760x7feaadc2df800x7feaad2245c000014233428319397142334282870091423342856061014233428562472
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]008023312233124194304256001224316800x7feaadc2de000x7feaad22460000014233428600031142334285606101423342884205114233428843896
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]008323312233124194304256001624326400x7feaadc2dc800x7feaad22464000014233428873915142334288420511423342920301314233429204659
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]008623312233124194304256001224336000x7feaadc2db000x7feaad22468000014233429235038142334292030131423342956461414233429566341
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]008923312233124194304256001224345600x7feaadc2d9800x7feaad2246c000014233429596271142334295646141423342984557514233429847386
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00922331223312419430425600824355200x7feaadc2d8000x7feaad22470000014233429877675142334298455751423343012109614233430123470
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]009523312233124194304256001224362240x7feaadc2d6800x7feaad22474000014233430160139142334301210961423343040461714233430406334
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]009823312233124194304256001224371840x7feab02cc5000x7feaad22478000014233430436303142334304046171423343076621814233430768047
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]0010123312233124194304256001224381440x7feab02cc3800x7feaad2247c000014233430798606142334307662181423343113133914233431133039
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]0010423312233124194304256001224391040x7feab02cc2000x7feaad22480000014233431163269142334311313391423343140638014233431408094
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]001072331223312419430425600824403200x7feab02cc0800x7feaad22484000014233431438753142334314063801423343168270114233431684448
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]0011023312233124194304256001224412800x7feaadc2df000x7feaad22488000014233431722517142334316827011423343196382214233431965572
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0011323312233124194304256001224422400x7feaadc2dd800x7feaad2248c000014233431995522142334319638221423343232654314233432328225
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]0011623312233124194304256001224432000x7feaadc2dc000x7feaad22490000014233432358114142334323265431423343269278514233432694617
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]001192331223312419430425600824441600x7feaadc2da800x7feaad22494000014233432724767142334326927851423343296942614233432971242
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]0012223312233124194304256001224453760x7feaadc2d9000x7feaad22498000014233433001511142334329694261423343325214714233433253926
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]0012523312233124194304256001224463360x7feaadc2d7800x7feaad2249c000014233433290845142334332521471423343352926814233433530860
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0012823312233124194304256001224475520x7feaadc2d6000x7feaad224a0000014233433561019142334335292681423343389294914233433894783
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]0013123312233124194304256001224485120x7feab02cc4800x7feaad224a4000014233433925722142334338929491423343425407014233434256265
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]001342331223312419430425600824494720x7feab02cc3000x7feaad224a8000014233434289094142334342540701423343453551114233434537299
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]0013723312233124194304256001224506880x7feab02cc1800x7feaad224ac000014233434569329142334345355111423343481327214233434815114
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]0014023312233124194304256001224516480x7feab02cc0000x7feaad224b0000014233434852653142334348132721423343509551314233435097278
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0014323312233124194304256001224528640x7feaadc2de800x7feaad224b4000014233435128857142334350955131423343546271414233435464310
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]0014623312233124194304256001224540800x7feaadc2dd000x7feaad224b8000014233435495090142334354627141423343583279614233435834573
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001492331223312419430425600824552960x7feaadc2db800x7feaad224bc000014233435865052142334358327961423343611055714233436112327
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]0015223312233124194304256001224567680x7feaadc2da000x7feaad224c0000014233436143696142334361105571423343638943814233436391251
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]0015523312233124194304256001224577280x7feaadc2d8800x7feaad224c4000014233436428661142334363894381423343666927914233436671076
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015823312233124194304256001224589440x7feaadc2d7000x7feaad224c8000014233436700925142334366692791423343703136014233437033268
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]0016123312233124194304256001224601600x7feab02cc5800x7feaad224cc000014233437064018142334370313601423343739136114233437393101
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001642331223312419430425600824613760x7feab02cc4000x7feaad224d0000014233437423310142334373913611423343766528214233437667055
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]0016723312233124194304256001224628480x7feab02cc2800x7feaad224d4000014233437697565142334376652821423343794592314233437947589
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]0017023312233124194304256001224638080x7feab02cc1000x7feaad224d8000014233437986729142334379459231423343823184414233438233684
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017323312233124194304256001224650240x7feaadc2df800x7feaad224dc000014233438265143142334382318441423343859360514233438595416
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]0017623312233124194304256001224662400x7feaadc2de000x7feaad224e0000014233438625786142334385936051423343895776714233438959409
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001792331223312419430425600824674560x7feaadc2dc800x7feaad224e4000014233438990108142334389577671423343923232814233439234113
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]0018223312233124194304256001224689280x7feaadc2db000x7feaad224e8000014233439264822142334392323281423343951840914233439520147
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]0018523312233124194304256001224701440x7feaadc2d9800x7feaad224ec000014233439558486142334395184091423343979776914233439799622
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018823312233124194304256001224716160x7feaadc2d8000x7feaad224f0000014233439830891142334397977691423344015969114233440161344
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]0019123312233124194304256001224728320x7feaadc2d6800x7feaad224f4000014233440191803142334401596911423344052001214233440521747
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001942331223312419430425600824740480x7feab02cc5000x7feaad224f8000014233440551436142334405200121423344079601314233440797631
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]0019723312233124194304256001224757760x7feab02cc3800x7feaad224fc000014233440828030142334407960131423344108641414233441088135
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]0020023312233124194304256001224769920x7feab02cc2000x7feaad22500000014233441126174142334410864141423344136081514233441362879
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020323312233124194304256001224784640x7feab02cc0800x7feaad22504000014233441393179142334413608151423344172929614233441731092
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]0020623312233124194304256001224799360x7feaadc2df000x7feaad22508000014233441762021142334417292961423344209217714233442094074
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]002092331223312419430425600824814080x7feaadc2dd800x7feaad2250c000014233442125424142334420921771423344237361814233442375189
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]0021223312233124194304256001224831360x7feaadc2dc000x7feaad22510000014233442405728142334423736181423344267473914233442676383
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]0021523312233124194304256001224843520x7feaadc2da800x7feaad22514000014233442726481142334426747391423344295346014233442955367
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021823312233124194304256001224858240x7feaadc2d9000x7feaad22518000014233442984776142334429534601423344333282214233443334669
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]0022123312233124194304256001224872960x7feaadc2d7800x7feaad2251c000014233443364808142334433328221423344369554314233443697302
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]0022423312233124194304256001224887680x7feaadc2d6000x7feaad22520000014233443727311142334436955431423344397250414233443974196
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]0022723312233124194304256001224907520x7feab02cc4800x7feaad22524000014233444004855142334439725041423344427634514233444278130
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]0023023312233124194304256001224919680x7feab02cc3000x7feaad22528000014233444315879142334442763451423344455810614233444559894
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023323312233124194304256001224934400x7feab02cc1800x7feaad2252c000014233444589663142334445581061423344492898714233444930706
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0023623312233124194304256001224949120x7feab02cc0000x7feaad22530000014233444961856142334449289871423344529170914233445293369
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0023923312233124194304256001224963840x7feaadc2de800x7feaad22534000014233445323508142334452917091423344556835014233445570033
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0024223312233124194304256001224983680x7feaadc2dd000x7feaad22538000014233445600663142334455683501423344587843114233445880167
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0024523312233124194304256001224995840x7feaadc2db800x7feaad2253c000014233445917346142334458784311423344615427214233446156111
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00248233122331241943042560012241013120x7feaadc2da000x7feaad22540000014233446187151142334461542721423344652451314233446526294
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]00251233122331241943042560012241027840x7feaadc2d8800x7feaad22544000014233446557063142334465245131423344689011414233446891806
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]00254233122331241943042560012241042560x7feaadc2d7000x7feaad22548000014233446921856142334468901141423344716835514233447170031
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]00257233122331241943042560012241062400x7feab02cc5800x7feaad2254c000014233447201160142334471683551423344748387614233447485654
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]00260233122331241943042560012241077120x7feab02cc4000x7feaad22550000014233447523703142334474838761423344776707714233447768788
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00263233122331241943042560016241094400x7feab02cc2800x7feaad22554000014233447799068142334477670771423344812931814233448131041
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]00266233122331241943042560016241111680x7feab02cc1000x7feaad22558000014233448162510142334481293181423344849284014233448494564
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0026923312233124194304256008241128960x7feaadc2df800x7feaad2255c000014233448525723142334484928401423344877076114233448772508
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]00272233122331241943042560012241151360x7feaadc2de000x7feaad22560000014233448802977142334487707611423344909412214233449095861
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]00275233122331241943042560012241166080x7feaadc2dc800x7feaad22564000014233449134021142334490941221423344937140314233449373236
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00278233122331241943042560016241183360x7feaadc2db000x7feaad22568000014233449403215142334493714031423344973492414233449736448
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]00281233122331241943042560016241200640x7feaadc2d9800x7feaad2256c000014233449766678142334497349241423345009748514233450099711
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]00284233122331241943042560012241217920x7feaadc2d8000x7feaad22570000014233450130280142334500974851423345038052614233450382345
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]00287233122331241943042560012241240320x7feaadc2d6800x7feaad22574000014233450412745142334503805261423345070564714233450707309
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]00290233122331241943042560012241255040x7feab02cc5000x7feaad22578000014233450745438142334507056471423345099412814233450995963
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00293233122331241943042560012241274880x7feab02cc3800x7feaad2257c000014233451026382142334509941281423345135845014233451360065
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]00296233122331241943042560012241292160x7feab02cc2000x7feaad22580000014233451391134142334513584501423345172085114233451722708
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]00299233122331241943042560012241309440x7feab02cc0800x7feaad22584000014233451753607142334517208511423345200293214233452004642
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]00302233122331241943042560012241334400x7feaadc2df000x7feaad22588000014233452035761142334520029321423345234277314233452344565
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]00305233122331241943042560012241349120x7feaadc2dd800x7feaad2258c000014233452382714142334523427731423345262021414233452621959
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00308233122331241943042560012241368960x7feaadc2dc000x7feaad22590000014233452652439142334526202141423345297925514233452980992
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]00311233122331241943042560012241388800x7feaadc2da800x7feaad22594000014233453012381142334529792551423345334357714233453345344
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]00314233122331241943042560012241408640x7feaadc2d9000x7feaad22598000014233453375354142334533435771423345363237814233453634069
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]00317233122331241943042560012241436160x7feaadc2d7800x7feaad2259c000014233453664188142334536323781423345398837914233453990181
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]00320233122331241943042560012241453440x7feaadc2d6000x7feaad225a0000014233454028830142334539883791423345428662014233454288385
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00323233122331241943042560012241475840x7feab02cc4800x7feaad225a4000014233454319164142334542866201423345465174114233454653528
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]00326233122331241943042560012241495680x7feab02cc3000x7feaad225a8000014233454684917142334546517411423345501286214233455014770
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]00329233122331241943042560012241515520x7feab02cc1800x7feaad225ac000014233455044840142334550128621423345530518314233455306924
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]00332233122331241943042560012241543040x7feab02cc0000x7feaad225b0000014233455337854142334553051831423345566918514233455670897
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]00335233122331241943042560012241562880x7feaadc2de800x7feaad225b4000014233455709236142334556691851423345595558614233455957361
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00338233122331241943042560012241587840x7feaadc2dd000x7feaad225b8000014233455987750142334559555861423345632230714233456323913
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]00341233122331241943042560012241610240x7feaadc2db800x7feaad225bc000014233456354343142334563223071423345668918814233456690896
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]00344233122331241943042560012241632640x7feaadc2da000x7feaad225c0000014233456721275142334566891881423345699366914233456995330
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]00347233122331241943042560012241665280x7feaadc2d8800x7feaad225c4000014233457026159142334569936691423345739031114233457410191
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]00350233122331241943042560012241685120x7feaadc2d7000x7feaad225c8000014233457430501142334573903111423345769815214233457699785
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00353233122331241943042560012241712640x7feab02cc5800x7feaad225cc000014233457729945142334576981521423345806183314233458063448
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]00356233122331241943042560012241737600x7feab02cc4000x7feaad225d0000014233458098077142334580618331423345843575414233458437450
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]00359233122331241943042560012241762560x7feab02cc2800x7feaad225d4000014233458468409142334584357541423345875335514233458755023
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]00362233122331241943042560012241797760x7feab02cc1000x7feaad225d8000014233458786103142334587533551423345916711714233459213014
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]00365233122331241943042560012241822720x7feaadc2df800x7feaad225dc000014233459232034142334591671171423345951623814233459517918
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00368233122331241943042560012241855360x7feaadc2de000x7feaad225e0000014233459548847142334595162381423345988663914233459908790
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]00371233122331241943042560012241885440x7feaadc2dc800x7feaad225e4000014233459921330142334598866391423346027576114233460295962
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]00374233122331241943042560012241915520x7feaadc2db000x7feaad225e8000014233460308662142334602757611423346062552214233460627245
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]00377233122331241943042560012241958400x7feaadc2d9800x7feaad225ec000014233460657304142334606255221423346109496414233461114115
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]00380233122331241943042560012241985920x7feaadc2d8000x7feaad225f0000014233461134755142334610949641423346143144514233461433119
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00383233122331241943042560012242023680x7feaadc2d6800x7feaad225f4000014233461463298142334614314451423346182200614233461839190
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]00386233122331241943042560012242058880x7feab02cc5000x7feaad225f8000014233461855290142334618220061423346221608814233462233472
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]00389233122331241943042560012242094080x7feab02cc3800x7feaad225fc000014233462249712142334622160881423346259400914233462595915
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]00392233122331241943042560012242144640x7feab02cc2000x7feaad22600000014233462627054142334625940091423346311049114233463152243
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]00395233122331241943042560012242177280x7feab02cc0800x7feaad22604000014233463170953142334631104911423346349145214233463493146
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00398233122331241943042560012242220160x7feaadc2df000x7feaad22608000014233463524596142334634914521423346390825314233463926637
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]00401233122331241943042560012242260480x7feaadc2dd800x7feaad2260c000014233463941087142334639082531423346433129514233464349839
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]00404233122331241943042560012242300800x7feaadc2dc000x7feaad22610000014233464363598142334643312951423346473913614233464756360
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]00407233122331241943042560012242359040x7feaadc2da800x7feaad22614000014233464771430142334647391361423346531257814233465331119
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]00410233122331241943042560012242394240x7feaadc2d9000x7feaad22618000014233465353198142334653125781423346569434014233465696101
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00413233122331241943042560012242442240x7feaadc2d7800x7feaad2261c000014233465726231142334656943401423346613146114233466177341
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]00416233122331241943042560012242487680x7feaadc2d6000x7feaad22620000014233466189441142334661314611423346659962314233466618062
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]00419233122331241943042560012242533120x7feab02cc4800x7feaad22624000014233466632202142334665996231423346702474414233467042344
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0042223312233124194304256008242555520x7feab02cc3000x7feaad22628000014233467057943142334670247441423346766362614233467682271
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]00425233122331241943042560012242598400x7feab02cc1800x7feaad2262c000014233467704010142334676636261423346807914814233468096662
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00428233122331241943042560012242656640x7feab02cc0000x7feaad22630000014233468111662142334680791481423346857531014233468593292
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]00431233122331241943042560012242712320x7feaadc2de800x7feaad22634000014233468608182142334685753101423346906987114233469087242
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0043423312233124194304256008242732160x7feaadc2dd000x7feaad22638000014233469101202142334690698711423346956075314233469579252
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0043723312233124194304256008242757120x7feaadc2db800x7feaad2263c000014233469593052142334695607531423347030779614233470327147
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]00440233122331241943042560012242807680x7feaadc2da000x7feaad22640000014233470347876142334703077961423347076635714233470808957
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00443233122331241943042560012242876160x7feaadc2d8800x7feaad22644000014233470819737142334707663571423347133339914233471350926
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]00446233122331241943042560012242942080x7feaadc2d7000x7feaad22648000014233471365416142334713333991423347186892114233471887845
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0044923312233124194304256008242969600x7feab02cc5800x7feaad2264c000014233471901225142334718689211423347240428314233472422084
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0045223312233124194304256008242999680x7feab02cc4000x7feaad22650000014233472437394142334724042831423347324924614233473267807
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0045523312233124194304256008243027200x7feab02cc2800x7feaad22654000014233473289196142334732492461423347388348814233473902464
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00458233122331241943042560012243054720x7feab02cc1000x7feaad22658000014233473916863142334738834881423347453437014233474552820
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]00461233122331241943042560012243082240x7feaadc2df800x7feaad2265c000014233474567160142334745343701423347519325314233475211887
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0046423312233124194304256008243109760x7feaadc2de000x7feaad22660000014233475225526142334751932531423347583229514233475849944
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0046723312233124194304256008243132160x7feaadc2dc800x7feaad22664000014233475865193142334758322951423347688941914233476907822
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0047023312233124194304256008243159680x7feaadc2db000x7feaad22668000014233476929252142334768891381423347793154114233477952551
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00473233122331241943042560012243187200x7feaadc2d9800x7feaad2266c000014233477964060142334779315411423347901890414233479058748
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]00476233122331241943042560012243214720x7feaadc2d8000x7feaad22670000014233479070998142334790189041423348013394714233480153395
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0047923312233124194304256008243242240x7feaadc2d6800x7feaad22674000014233480166975142334801339471423348119603014233481214424
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0048223312233124194304256008243264640x7feab02cc5000x7feaad22678000014233481228723142334811960301423348309555614233483117895
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0048523312233124194304256008243292160x7feab02cc3800x7feaad2267c000014233483137164142334830955561423348497476114233485044285
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00488233122331241943042560012243319680x7feab02cc2000x7feaad22680000014233485055575142334849747611423348695956714233487032815
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]00491233122331241943042560012243347200x7feab02cc0800x7feaad22684000014233487044904142334869595671423348895173314233488996525
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0049423312233124194304256008243374720x7feaadc2df000x7feaad22688000014233489007984142334889517331423349085781814233490929365
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00497233122331241943042560082400x7feaadc2dd800x7feaad2268c000014233490941095142334908578181423349447942914233494551231