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

41 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_VMEMSQ_INST_LEVEL_VMEMSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000238129238129335544322560043241600x00x7fe2c7e04280524288549747261565648017851610507915178493189589561785175771880117851757807931
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00223812923812932768256001224138880x00x7fe2c7e23f80409655920625770817851762985423178517577188011785176311257017851763117229
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0052381292381294194304256001224143360x7fe2d67ec3800x7fe2c7e23fc052428810960198122756199217851763151509178517631125701785176348329017851763485710
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0082381292381294194304256001624150400x7fe2d67ec2000x7fe2c7e2400052428811381323127467235617851763522879178517634832901785176389033117851763892860
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00112381292381294194304256001624154880x7fe2d67ec0800x7fe2c7e2404052428811627241130221224417851763925789178517638903311785176429017217851764292530
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00142381292381294194304256001224159360x7fe2d414df000x7fe2c7e2408052428810699863119837955617851764323980178517642901721785176460585217851764608203
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00172381292381294194304256001224163840x7fe2d414dd800x7fe2c7e240c052428811118838124518586417851764640972178517646058521785176490857317851764910935
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00202381292381294194304256001224170880x7fe2d414dc000x7fe2c7e2410052428811178497125194300417851764953374178517649085731785176520905317851765211248
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00232381292381294194304256001624177920x7fe2d414da800x7fe2c7e2414052428811592460129832433617851765242887178517652090531785176559993417851765602108
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00262381292381294194304256001624184960x7fe2d414d9000x7fe2c7e2418052428811494634128736886417851765632697178517655999341785176598857417851765990788
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00292381292381294194304256001624192000x7fe2d414d7800x7fe2c7e241c052428811287982126424318817851766020358178517659885741785176633465517851766337010
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00322381292381294194304256001624199040x7fe2d414d6000x7fe2c7e2420052428811023054123464298817851766367699178517663346551785176664105617851766643422
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00352381292381294194304256001224206080x7fe2d67ec4800x7fe2c7e2424052428811244797125945584817851766682701178517666410561785176695497617851766957234
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00382381292381294194304256001624213120x7fe2d67ec3000x7fe2c7e2428052428811510571128915664017851766990564178517669549761785176733193717851767333595
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00412381292381294194304256001624220160x7fe2d67ec1800x7fe2c7e242c052428811447156128208365217851767364564178517673319371785176769049717851767692186
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00442381292381294194304256001624227200x7fe2d67ec0000x7fe2c7e2430052428811276589126301584817851767723665178517676904971785176796377817851767965349
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00472381292381294194304256001224234240x7fe2d414de800x7fe2c7e2434052428810903637122118988417851767996329178517679637781785176823705817851768238773
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00502381292381294194304256001224241280x7fe2d414dd000x7fe2c7e2438052428811051283123770673617851768276892178517682370581785176851065917851768512396
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00532381292381294194304256001624248320x7fe2d414db800x7fe2c7e243c052428811567105129551489217851768543615178517685106591785176887129917851768873267
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00562381292381294194304256001624255360x7fe2d414da000x7fe2c7e2440052428811440192128127618817851768903966178517688712991785176923754017851769239258
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00592381292381294194304256001224262400x7fe2d414d8800x7fe2c7e2444052428811218351125641315217851769269957178517692375401785176951178017851769513491
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00622381292381294194304256001224269440x7fe2d414d7000x7fe2c7e2448052428810893140122003876417851769544010178517695117801785176978698117851769788744
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00652381292381294194304256001224276480x7fe2d67ec5800x7fe2c7e244c052428811184468125265257217851769827593178517697869811785177006778117851770069447
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00682381292381294194304256001624286080x7fe2d67ec4000x7fe2c7e2450052428811405712127735918417851770101856178517700677811785177043498217851770436678
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00712381292381294194304256001624293120x7fe2d67ec2800x7fe2c7e2454052428811384947127510098417851770467807178517704349821785177079834317851770800169
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00742381292381294194304256001224300160x7fe2d67ec1000x7fe2c7e2458052428811239872125888131217851770831338178517707983431785177107322317851771074972
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077238129238129419430425600824309760x7fe2d414df800x7fe2c7e245c052428810799987120956366817851771105501178517710732231785177134474417851771346485
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00802381292381294194304256001224316800x7fe2d414de000x7fe2c7e2460052428811131170124667325217851771384385178517713447441785177161914417851771620859
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00832381292381294194304256001624326400x7fe2d414dc800x7fe2c7e2464052428811467964128437457217851771652478178517716191441785177198602517851771987720
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00862381292381294194304256001224336000x7fe2d414db000x7fe2c7e2468052428811240089125886516817851772018959178517719860251785177234938517851772351110
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00892381292381294194304256001224345600x7fe2d414d9800x7fe2c7e246c052428811111679124447340017851772381930178517723493851785177262426617851772626054
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092238129238129419430425600824355200x7fe2d414d8000x7fe2c7e2470052428810752960120423639617851772656993178517726242661785177290090617851772902707
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00952381292381294194304256001224362240x7fe2d414d6800x7fe2c7e2474052428811148981124870906817851772941226178517729009061785177317690717851773178670
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00982381292381294194304256001224371840x7fe2d67ec5000x7fe2c7e2478052428811424600127954800817851773209649178517731769071785177353962717851773541161
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001012381292381294194304256001224381440x7fe2d67ec3800x7fe2c7e247c052428811391928127585960417851773572850178517735396271785177390330817851773905072
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001042381292381294194304256001224391040x7fe2d67ec2000x7fe2c7e2480052428810688825119712112017851773936171178517739033081785177417594817851774177675
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107238129238129419430425600824403200x7fe2d67ec0800x7fe2c7e2484052428810142263113591906017851774209724178517741759481785177445578917851774457488
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001102381292381294194304256001224412800x7fe2d414df000x7fe2c7e2488052428810949440122629544417851774496357178517744557891785177474282917851774744601
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001132381292381294194304256001224422400x7fe2d414dd800x7fe2c7e248c052428811379921127454588017851774774940178517747428291785177511051017851775112212
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001162381292381294194304256001224432000x7fe2d414dc000x7fe2c7e2490052428811416790127867735217851775143441178517751105101785177547195117851775473633
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119238129238129419430425600824441600x7fe2d414da800x7fe2c7e2494052428810352192115938938417851775504362178517754719511785177574683117851775748466
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001222381292381294194304256001224453760x7fe2d414d9000x7fe2c7e249805242889913960111038653617851775779665178517757468311785177602043217851776022119
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001252381292381294194304256001224463360x7fe2d414d7800x7fe2c7e249c052428810513747117755201217851776060108178517760204321785177629691217851776298582
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001282381292381294194304256001224475520x7fe2d414d6000x7fe2c7e24a0052428811381922127475350417851776329492178517762969121785177665771317851776659383
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001312381292381294194304256001224485120x7fe2d67ec4800x7fe2c7e24a4052428811333933126938258017851776690293178517766577131785177701563317851777017335
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134238129238129419430425600824494720x7fe2d67ec3000x7fe2c7e24a8052428810580465118500271617851777048404178517770156331785177728923417851777290928
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001372381292381294194304256001224506880x7fe2d67ec1800x7fe2c7e24ac05242889199320103032978417851777322447178517772892341785177757131417851777572971
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001402381292381294194304256001224516480x7fe2d67ec0000x7fe2c7e24b0052428810586783118563718017851777611420178517775713141785177785963517851777861264
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001432381292381294194304256001224528640x7fe2d414de800x7fe2c7e24b4052428811290441126451358417851777892063178517778596351785177822875517851778230584
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001462381292381294194304256001224540800x7fe2d414dd000x7fe2c7e24b8052428811333004126928537217851778262294178517782287551785177859611617851778597795
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149238129238129419430425600824552960x7fe2d414db800x7fe2c7e24bc052428810333600115734961217851778628455178517785961161785177887291617851778874719
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001522381292381294194304256001224567680x7fe2d414da000x7fe2c7e24c00524288775886286898646817851778905648178517788729161785177914811717851779149842
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001552381292381294194304256001224577280x7fe2d414d8800x7fe2c7e24c4052428810751011120405565617851779187561178517791481171785177942491717851779426605
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001582381292381294194304256001224589440x7fe2d414d7000x7fe2c7e24c8052428811359499127225071617851779457324178517794249171785177978811817851779789916
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001612381292381294194304256001224601600x7fe2d67ec5800x7fe2c7e24cc052428811359245127220580817851779820985178517797881181785178015163917851780153257
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164238129238129419430425600824613760x7fe2d67ec4000x7fe2c7e24d0052428810233865114620868017851780183876178517801516391785178043227917851780434060
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001672381292381294194304256001224628480x7fe2d67ec2800x7fe2c7e24d40524288679091576063895617851780466599178517804322791785178071516017851780716753
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001702381292381294194304256001224638080x7fe2d67ec1000x7fe2c7e24d8052428810722907120089019617851780755482178517807151601785178099340017851780994976
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001732381292381294194304256001224650240x7fe2d414df800x7fe2c7e24dc052428811235953125838950817851781026845178517809934001785178135436117851781356027
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001762381292381294194304256001224662400x7fe2d414de000x7fe2c7e24e0052428811251763126019696817851781387597178517813543611785178171660117851781718348
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179238129238129419430425600824674560x7fe2d414dc800x7fe2c7e24e4052428810603428118761453217851781749108178517817166011785178199356217851781995242
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001822381292381294194304256001224689280x7fe2d414db000x7fe2c7e24e80524288573617164247992017851782026071178517819935621785178228460217851782286414
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001852381292381294194304256001224701440x7fe2d414d9800x7fe2c7e24ec052428810761174120515982417851782324253178517822846021785178256252317851782564147
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001882381292381294194304256001224716160x7fe2d414d8000x7fe2c7e24f0052428811277622126310434817851782596237178517825625231785178292492317851782926658
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001912381292381294194304256001224728320x7fe2d414d6800x7fe2c7e24f4052428811403554127717701217851782958358178517829249231785178329404417851783295759
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194238129238129419430425600824740480x7fe2d67ec5000x7fe2c7e24f805242889971998111683952817851783326518178517832940441785178357260517851783574332
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001972381292381294194304256001224757760x7fe2d67ec3800x7fe2c7e24fc0524288478867653632388817851783605412178517835726051785178386252517851783864245
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002002381292381294194304256001224769920x7fe2d67ec2000x7fe2c7e2500052428810496241117554899217851783902714178517838625251785178413836517851784140138
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002032381292381294194304256001224784640x7fe2d67ec0800x7fe2c7e2504052428811254474126045973617851784171147178517841383651785178450044617851784502099
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002062381292381294194304256001224799360x7fe2d414df000x7fe2c7e2508052428811308943126656423217851784534368178517845004461785178486524717851784866980
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209238129238129419430425600824814080x7fe2d414dd800x7fe2c7e250c05242889969059111653171617851784897639178517848652471785178513964717851785141433
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002122381292381294194304256001224831360x7fe2d414dc000x7fe2c7e25100524288410124945929257217851785172763178517851396471785178543516817851785436936
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002152381292381294194304256001224843520x7fe2d414da800x7fe2c7e2514052428810552160118182958017851785487385178517854351681785178571692817851785718719
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002182381292381294194304256001224858240x7fe2d414d9000x7fe2c7e2518052428811311011126680653617851785749208178517857169281785178608412917851786085730
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002212381292381294194304256001224872960x7fe2d414d7800x7fe2c7e251c052428811219564125656892017851786117729178517860841291785178645788917851786459631
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002242381292381294194304256001224887680x7fe2d414d6000x7fe2c7e252005242889820308109974856417851786490400178517864578891785178673549017851786737154
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002272381292381294194304256001224907520x7fe2d67ec4800x7fe2c7e25240524288367164841118786417851786768093178517867354901785178703789017851787039626
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002302381292381294194304256001224919680x7fe2d67ec3000x7fe2c7e2528052428810077664112870636417851787077675178517870378901785178731533117851787316989
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002332381292381294194304256001224934400x7fe2d67ec1800x7fe2c7e252c052428811126647124615948417851787348009178517873153311785178767469217851787676360
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002362381292381294194304256001224949120x7fe2d67ec0000x7fe2c7e2530052428811153488124917038817851787708170178517876746921785178803229217851788034032
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002392381292381294194304256001224963840x7fe2d414de800x7fe2c7e253405242888941596100144938417851788064441178517880322921785178830685317851788308635
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002422381292381294194304256001224983680x7fe2d414dd000x7fe2c7e25380524288349724339170869217851788339414178517883068531785178861341317851788614977
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002452381292381294194304256001224995840x7fe2d414db800x7fe2c7e253c05242889670492108310800417851788652536178517886134131785178889693417851788898650
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024823812923812941943042560012241013120x7fe2d414da000x7fe2c7e2540052428811021697123441433217851788930049178517888969341785178926173417851789263381
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025123812923812941943042560012241027840x7fe2d414d8800x7fe2c7e2544052428811132126124679801217851789294310178517892617341785178962189517851789623662
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025423812923812941943042560012241042560x7fe2d414d7000x7fe2c7e25480524288868926197319892417851789653931178517896218951785178989837517851789900145
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025723812923812941943042560012241062400x7fe2d67ec5800x7fe2c7e254c0524288329635936916910017851789930734178517898983751785179021181617851790213657
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026023812923812941943042560012241077120x7fe2d67ec4000x7fe2c7e2550052428810037455112419528417851790252606178517902118161785179048925617851790491010
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026323812923812941943042560016241094400x7fe2d67ec2800x7fe2c7e2554052428811174234125147107217851790521940178517904892561785179084845717851790850182
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026623812923812941943042560016241111680x7fe2d67ec1000x7fe2c7e2558052428811156391124949457217851790881871178517908484571785179121389817851791215562
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002692381292381294194304256008241128960x7fe2d414df800x7fe2c7e255c0524288845339594674972417851791246402178517912138981785179149165817851791493396
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027223812923812941943042560012241151360x7fe2d414de000x7fe2c7e25600524288302499633879614817851791524785178517914916581785179181661917851791818288
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027523812923812941943042560012241166080x7fe2d414dc800x7fe2c7e256405242889898403110857838017851791856967178517918166191785179209853917851792100221
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027823812923812941943042560016241183360x7fe2d414db000x7fe2c7e2568052428811104075124364251217851792131210178517920985391785179245742017851792459142
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028123812923812941943042560016241200640x7fe2d414d9800x7fe2c7e256c052428811097123124287950417851792489141178517924574201785179281790017851792819553
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028423812923812941943042560012241217920x7fe2d414d8000x7fe2c7e25700524288731037881862458817851792849692178517928179001785179309614117851793097826
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028723812923812941943042560012241240320x7fe2d414d6800x7fe2c7e25740524288294123732942562417851793128535178517930961411785179342142117851793423188
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029023812923812941943042560012241255040x7fe2d67ec5000x7fe2c7e257805242889559653107072550017851793461137178517934214211785179369566217851793697541
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029323812923812941943042560012241274880x7fe2d67ec3800x7fe2c7e257c052428811023374123461596817851793727930178517936956621785179405326217851794055012
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029623812923812941943042560012241292160x7fe2d67ec2000x7fe2c7e2580052428811082656124125856417851794092211178517940532621785179443182317851794433593
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029923812923812941943042560012241309440x7fe2d67ec0800x7fe2c7e25840524288635325571159398817851794464132178517944318231785179471230417851794713966
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030223812923812941943042560012241334400x7fe2d414df000x7fe2c7e25880524288293908832919193217851794744745178517947123041785179505566417851795057367
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030523812923812941943042560012241349120x7fe2d414dd800x7fe2c7e258c0524288867432897149117217851795096216178517950556641785179533310517851795334710
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030823812923812941943042560012241368960x7fe2d414dc000x7fe2c7e2590052428810772675120651220417851795365530178517953331051785179569518517851795696821
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031123812923812941943042560012241388800x7fe2d414da800x7fe2c7e2594052428810815365121124423617851795728621178517956951851785179605662617851796058483
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031423812923812941943042560012241408640x7fe2d414d9000x7fe2c7e25980524288500841156093477217851796088352178517960566261785179634046617851796342176
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031723812923812941943042560012241436160x7fe2d414d7800x7fe2c7e259c0524288286002332034698017851796373065178517963404661785179669102717851796692677
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032023812923812941943042560012241453440x7fe2d414d6000x7fe2c7e25a00524288697500278117054017851796731096178517966910271785179696878717851796970440
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032323812923812941943042560012241475840x7fe2d67ec4800x7fe2c7e25a4052428810836988121371638417851797001379178517969687871785179733086817851797332751
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032623812923812941943042560012241495680x7fe2d67ec3000x7fe2c7e25a8052428810812264121098188417851797363950178517973308681785179769934917851797701022
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032923812923812941943042560012241515520x7fe2d67ec1800x7fe2c7e25ac0524288393286944044624817851797731601178517976993491785179799646917851797998205
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033223812923812941943042560012241543040x7fe2d67ec0000x7fe2c7e25b00524288284656531881804017851798029344178517979964691785179836671017851798368385
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033523812923812941943042560012241562880x7fe2d414de800x7fe2c7e25b40524288583451565344893217851798406914178517983667101785179865807017851798659808
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033823812923812941943042560012241587840x7fe2d414dd000x7fe2c7e25b8052428810823083121214125617851798690347178517986580701785179902031117851799022009
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034123812923812941943042560012241610240x7fe2d414db800x7fe2c7e25bc052428810796310120918981617851799053408178517990203111785179938351217851799385260
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034423812923812941943042560012241632640x7fe2d414da000x7fe2c7e25c00524288380714942637812417851799416469178517993835121785179968719217851799688903
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034723812923812941943042560012241665280x7fe2d414d8800x7fe2c7e25c40524288287656832220386417851799719172178517996871921785180007615317851800121672
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035023812923812941943042560012241685120x7fe2d414d7000x7fe2c7e25c80524288440055949285525617851800141391178518000761531785180040399317851800405705
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035323812923812941943042560012241712640x7fe2d67ec5800x7fe2c7e25cc052428810574190118427948017851800437434178518004039931785180076943417851800771206
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035623812923812941943042560012241737600x7fe2d67ec4000x7fe2c7e25d005242889756056109260907217851800803335178518007694341785180114127517851801142977
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035923812923812941943042560012241762560x7fe2d67ec2800x7fe2c7e25d40524288293715132896980817851801174356178518011412751785180146063517851801462349
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036223812923812941943042560012241797760x7fe2d67ec1000x7fe2c7e25d80524288288578332316551617851801493368178518014606351785180187759617851801898488
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036523812923812941943042560012241822720x7fe2d414df800x7fe2c7e25dc0524288306237034301568817851801918537178518018775961785180220719617851802209040
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036823812923812941943042560012241855360x7fe2d414de000x7fe2c7e25e00524288796585189215097217851802241089178518022071961785180258687717851802634739
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037123812923812941943042560012241885440x7fe2d414dc800x7fe2c7e25e40524288729538581716512017851802647099178518025868771785180300047817851803045659
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037423812923812941943042560012241915520x7fe2d414db000x7fe2c7e25e80524288280850131456268017851803057569178518030004781785180337871817851803380351
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037723812923812941943042560012241958400x7fe2d414d9800x7fe2c7e25ec0524288283442931741385217851803410380178518033787181785180384463917851803889878
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038023812923812941943042560012241985920x7fe2d414d8000x7fe2c7e25f00524288282936431681614817851803909458178518038446391785180421104017851804212750
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038323812923812941943042560012242023680x7fe2d414d6800x7fe2c7e25f40524288715625280141267617851804244429178518042110401785180460640017851804648529
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038623812923812941943042560012242058880x7fe2d67ec5000x7fe2c7e25f80524288654654373316931617851804661659178518046064001785180502432117851805066159
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038923812923812941943042560012242094080x7fe2d67ec3800x7fe2c7e25fc0524288278240031162230017851805077389178518050243211785180541936217851805421170
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039223812923812941943042560012242144640x7fe2d67ec2000x7fe2c7e26000524288289754232450773217851805452989178518054193621785180593792317851805958267
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039523812923812941943042560012242177280x7fe2d67ec0800x7fe2c7e26040524288275870930900892817851805978236178518059379231785180630224317851806304268
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039823812923812941943042560012242220160x7fe2d414df000x7fe2c7e26080524288536150260045110017851806335168178518063022431785180671568417851806759087
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040123812923812941943042560012242260480x7fe2d414dd800x7fe2c7e260c0524288524156058704003217851806772477178518067156841785180716240517851807206206
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040423812923812941943042560012242300800x7fe2d414dc000x7fe2c7e26100524288271957830463259617851807218236178518071624051785180758624617851807627715
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040723812923812941943042560012242359040x7fe2d414da800x7fe2c7e26140524288292935332806090817851807640425178518075862461785180818320717851808224711
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041023812923812941943042560012242394240x7fe2d414d9000x7fe2c7e26180524288279844331344364417851808244280178518081832071785180858672717851808588512
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041323812923812941943042560012242442240x7fe2d414d7800x7fe2c7e261c0524288519868858225631217851808619471178518085867271785180902048817851809062250
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041623812923812941943042560012242487680x7fe2d414d6000x7fe2c7e26200524288322794636149339217851809075529178518090204881785180947984917851809522538
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041923812923812941943042560012242533120x7fe2d67ec4800x7fe2c7e26240524288276586930971969217851809534718178518094798491785180992865017851809947908
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004222381292381294194304256008242555520x7fe2d67ec3000x7fe2c7e26280524288237203026558350017851809961547178518099286501785181057905117851810623291
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042523812923812941943042560012242598400x7fe2d67ec1800x7fe2c7e262c0524288278068831139838417851810643791178518105790511785181102321117851811067380
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042823812923812941943042560012242656640x7fe2d67ec0000x7fe2c7e26300524288327319036658852417851811079870178518110232111785181153953217851811581427
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043123812923812941943042560012242712320x7fe2d414de800x7fe2c7e26340524288370643641510062017851811593917178518115395321785181205169317851812094375
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004342381292381294194304256008242732160x7fe2d414dd000x7fe2c7e26380524288239257026798817217851812106724178518120516931785181256401417851812605892
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004372381292381294194304256008242757120x7fe2d414db800x7fe2c7e263c0524288238015526652893217851812617972178518125640141785181333681517851813378153
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044023812923812941943042560012242807680x7fe2d414da000x7fe2c7e26400524288265124129686949617851813398483178518133368151785181381393617851813832062
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044323812923812941943042560012242876160x7fe2d414d8800x7fe2c7e26440524288335852737613044817851813847012178518138139361785181434913717851814394698
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044623812923812941943042560012242942080x7fe2d414d7000x7fe2c7e26480524288359508340257783217851814407058178518143491371785181492657817851814972024
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004492381292381294194304256008242969600x7fe2d67ec5800x7fe2c7e264c0524288239830626863306817851814983683178518149265781785181549681917851815538310
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004522381292381294194304256008242999680x7fe2d67ec4000x7fe2c7e26500524288238996226766617217851815550579178518154968191785181636754117851816409418
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004552381292381294194304256008243027200x7fe2d67ec2800x7fe2c7e26540524288238820526747536417851816429357178518163675411785181702834217851817069932
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045823812923812941943042560012243054720x7fe2d67ec1000x7fe2c7e26580524288257902128884341617851817081861178518170283421785181771042317851817752365
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046123812923812941943042560012243082240x7fe2d414df800x7fe2c7e265c0524288259230229029266017851817764284178518177104231785181838658417851818432168
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004642381292381294194304256008243109760x7fe2d414de000x7fe2c7e26600524288239225226794820817851818443947178518183865841785181906562517851819114581
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004672381292381294194304256008243132160x7fe2d414dc800x7fe2c7e26640524288241110626999450017851819127690178518190656251785182015442717851820200824
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004702381292381294194304256008243159680x7fe2d414db000x7fe2c7e26680524288243820127308634417851820221473178518201540851785182123952617851821308076
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047323812923812941943042560012243187200x7fe2d414d9800x7fe2c7e266c0524288259598429071954017851821320076178518212395261785182237840717851822445038
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047623812923812941943042560012243214720x7fe2d414d8000x7fe2c7e26700524288259713729086300417851822458078178518223784071785182351632817851823583740
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004792381292381294194304256008243242240x7fe2d414d6800x7fe2c7e26740524288242884427206509217851823596109178518235163281785182462768917851824694792
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004822381292381294194304256008243264640x7fe2d67ec5000x7fe2c7e26780524288246615627613240817851824706782178518246276891785182657825117851826648574
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004852381292381294194304256008243292160x7fe2d67ec3800x7fe2c7e267c0524288246419127599349217851826670493178518265782511785182850433317851828576246
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048823812923812941943042560012243319680x7fe2d67ec2000x7fe2c7e26800524288262165129362462817851828588236178518285043331785183048993517851830560797
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049123812923812941943042560012243347200x7fe2d67ec0800x7fe2c7e26840524288262664529416451617851830573217178518304899351785183247473717851832543988
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004942381292381294194304256008243374720x7fe2d414df000x7fe2c7e26880524288245575027501038417851832555917178518324747371785183440385917851834473550
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049723812923812941943042560082400x7fe2d414dd800x7fe2c7e268c0524288249644827955507217851834487209178518344038591785183802706317851838150278