Files
rocm-systems/tests/workloads/dev0/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.kd000224923224923335544322560043241600x00x7f6676804280524288543309960852812417616429017287176141623296481761657824418017616578354430
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00222492322492332768256001224138880x00x7f6676823f80409642285473687217616583510399176165782441801761658363714317616583641776
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0052249232249234194304256001224143360x7f66798a93800x7f6676823fc052428810680424119619336817616583675735176165836371431761658400722317616584009546
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0082249232249234194304256001624150400x7f66798a92000x7f667682400052428811460754128357055217616584045545176165840072231761658440610317616584408176
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00112249232249234194304256001624154880x7f66798a90800x7f667682404052428811434216128058796017616584439935176165844061031761658480066317616584802576
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00142249232249234194304256001224159360x7f6677207f000x7f667682408052428810725172120118858417616584835485176165848006631761658510130317616585103359
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00172249232249234194304256001224163840x7f6677207d800x7f66768240c052428810820892121188265617616585134888176165851013031761658540050417616585402521
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00202249232249234194304256001224170880x7f6677207c000x7f667682410052428811264600126160267617616585446060176165854005041761658570562417616585707533
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00232249232249234194304256001624177920x7f6677207a800x7f667682414052428811459579128345314017616585738492176165857056241761658608994417616586105043
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00262249232249234194304256001624184960x7f66772079000x7f667682418052428811636886130331051217616586123853176165860899441761658649426417616586496113
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00292249232249234194304256001624192000x7f66772077800x7f66768241c052428811006422123269602417616586526353176165864942641761658678882417616586790096
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00322249232249234194304256001624199040x7f66772076000x7f667682420052428811011983123329156417616586820495176165867888241761658706434517616587066029
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00352249232249234194304256001224206080x7f66798a94800x7f667682424052428810884992121906564417616587105378176165870643451761658733858517616587340112
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00382249232249234194304256001624213120x7f66798a93000x7f667682428052428811486594128649474417616587371061176165873385851761658769778517616587699073
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00412249232249234194304256001624220160x7f66798a91800x7f66768242c052428811447281128210756817616587730422176165876977851761658805730517616588058734
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00442249232249234194304256001624227200x7f66798a90000x7f667682430052428811340196127004753217616588090153176165880573051761658832866517616588330047
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00472249232249234194304256001224234240x7f6677207e800x7f667682434052428811235643125836619617616588361016176165883286651761658859890517616588600380
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00502249232249234194304256001224241280x7f6677207d000x7f667682438052428811212984125586352017616588638479176165885989051761658887202617616588873363
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00532249232249234194304256001624248320x7f6677207b800x7f66768243c052428811475817128527732417616588905152176165888720261761658922994617616589231314
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00562249232249234194304256001624255360x7f6677207a000x7f667682440052428811565969129536375617616589261653176165892299461761658959426617616589595715
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00592249232249234194304256001224262400x7f66772078800x7f667682444052428811124985124591636017616589626254176165895942661761658986674617616589868168
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00622249232249234194304256001224269440x7f66772077000x7f667682448052428810914456122238886417616589898867176165898667461761659014034617616590141681
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00652249232249234194304256001224276480x7f66798a95800x7f66768244c052428811122668124569659617616590181100176165901403461761659041810717616590419434
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00682249232249234194304256001624286080x7f66798a94000x7f667682450052428811374860127394415617616590449703176165904181071761659077618717616590777725
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00712249232249234194304256001624293120x7f66798a92800x7f667682454052428811410133127792764017616590808744176165907761871761659113490717616591136306
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00742249232249234194304256001224300160x7f66798a91000x7f667682458052428810954631122694654017616591168025176165911349071761659140690717616591408309
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077224923224923419430425600824309760x7f6677207f800x7f66768245c052428810617058118911087217616591439468176165914069071761659168194717616591683512
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00802249232249234194304256001224316800x7f6677207e000x7f667682460052428811108853124424028417616591720561176165916819471761659195570717616591957015
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00832249232249234194304256001624326400x7f6677207c800x7f667682464052428811568683129566416417616591987614176165919557071761659231970817616592321145
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00862249232249234194304256001224336000x7f6677207b000x7f667682468052428811530782129141829217616592351345176165923197081761659267730817616592678706
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00892249232249234194304256001224345600x7f66772079800x7f66768246c052428810659903119384788017616592709545176165926773081761659294866817616592949999
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092224923224923419430425600824355200x7f66772078000x7f667682470052428810442292116950147617616592980148176165929486681761659323010817616593231572
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00952249232249234194304256001224362240x7f66772076800x7f667682474052428810884366121895802417616593269151176165932301081761659350210817616593503775
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00982249232249234194304256001224371840x7f66798a95000x7f667682478052428811449817128233492417616593534774176165935021081761659386146917616593862736
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001012249232249234194304256001224381440x7f66798a93800x7f66768247c052428811342802127036098417616593893635176165938614691761659421762917616594219287
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001042249232249234194304256001224391040x7f66798a92000x7f667682480052428810697145119814855217616594251286176165942176291761659449362917616594495230
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107224923224923419430425600824403200x7f66798a90800x7f66768248405242889998816111984805217616594525979176165944936291761659476482917616594766313
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001102249232249234194304256001224412800x7f6677207f000x7f667682488052428810622469118964561617616594804622176165947648291761659504562917616595046936
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001132249232249234194304256001224422400x7f6677207d800x7f66768248c052428811504704128852795217616595077105176165950456291761659540466917616595406117
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001162249232249234194304256001224432000x7f6677207c000x7f667682490052428811459692128340678817616595437476176165954046691761659576019017616595761558
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119224923224923419430425600824441600x7f6677207a800x7f667682494052428810636268119127678417616595791687176165957601901761659602931017616596030861
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001222249232249234194304256001224453760x7f66772079000x7f66768249805242889540413106848714817616596061170176165960293101761659629891017616596300374
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001252249232249234194304256001224463360x7f66772077800x7f66768249c052428811005247123254725217616596338123176165962989101761659656915017616596570477
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001282249232249234194304256001224475520x7f66772076000x7f6676824a0052428811291528126466440817616596601337176165965691501761659692467017616596925898
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001312249232249234194304256001224485120x7f66798a94800x7f6676824a4052428811464293128397693617616596957847176165969246701761659728355117616597285029
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134224923224923419430425600824494720x7f66798a93000x7f6676824a8052428810351349115931073617616597315118176165972835511761659755203117616597553652
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001372249232249234194304256001224506880x7f66798a91800x7f6676824ac05242889189592102927005617616597584822176165975520311761659782947117616597830875
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001402249232249234194304256001224516480x7f66798a90000x7f6676824b0052428810490920117504417217616597869014176165978294711761659809859117616598100079
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001432249232249234194304256001224528640x7f6677207e800x7f6676824b4052428811243719125928806817616598130938176165980985911761659845987117616598461469
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001462249232249234194304256001224540800x7f6677207d000x7f6676824b8052428811333427126935478417616598491949176165984598711761659881875117616598820110
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149224923224923419430425600824552960x7f6677207b800x7f6676824bc052428810311900115488191617616598850270176165988187511761659908835217616599089833
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001522249232249234194304256001224567680x7f6677207a000x7f6676824c00524288766096285803341617616599121143176165990883521761659935747217616599358907
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001552249232249234194304256001224577280x7f66772078800x7f6676824c4052428810668081119480579217616599396086176165993574721761659962963217616599631100
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001582249232249234194304256001224589440x7f66772077000x7f6676824c8052428811332260126920850817616599661319176165996296321761659998931217616599990621
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001612249232249234194304256001224601600x7f66798a95800x7f6676824cc052428811364999127287085217616600022310176165999893121761660034451217616600345982
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164224923224923419430425600824613760x7f66798a94000x7f6676824d0052428810103502113153819617616600376871176166003445121761660061955317616600620975
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001672249232249234194304256001224628480x7f66798a92800x7f6676824d40524288611217768458083217616600652174176166006195531761660089587317616600897318
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001702249232249234194304256001224638080x7f66798a91000x7f6676824d8052428810015600112174125217616600935627176166008958731761660117011317616601171441
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001732249232249234194304256001224650240x7f6677207f800x7f6676824dc052428811187710125300102417616601203690176166011701131761660152627317616601527682
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001762249232249234194304256001224662400x7f6677207e000x7f6676824e0052428811315916126734876017616601558741176166015262731761660188163317616601882923
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179224923224923419430425600824674560x7f6677207c800x7f6676824e4052428810029985112328569617616601912862176166018816331761660215091317616602152566
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001822249232249234194304256001224689280x7f6677207b000x7f6676824e80524288558324662532488817616602184665176166021509131761660244147417616602442938
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001852249232249234194304256001224701440x7f66772079800x7f6676824ec052428810215409114409689217616602480957176166024414741761660271603417616602717501
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001882249232249234194304256001224716160x7f66772078000x7f6676824f0052428811359905127228185217616602748221176166027160341761660307571417616603077082
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001912249232249234194304256001224728320x7f66772076800x7f6676824f4052428811350178127115724417616603107072176166030757141761660343811417616603439493
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194224923224923419430425600824740480x7f66798a95000x7f6676824f805242889917994111080899217616603470322176166034381141761660370723417616603708736
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001972249232249234194304256001224757760x7f66798a93800x7f6676824fc0524288486311254468883617616603739946176166037072341761660398963417616603991009
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002002249232249234194304256001224769920x7f66798a92000x7f667682500052428810380466116256188017616604029308176166039896341761660426211517616604263672
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002032249232249234194304256001224784640x7f66798a90800x7f667682504052428811179716125209918417616604295032176166042621151761660461939517616604620833
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002062249232249234194304256001224799360x7f6677207f000x7f667682508052428811305869126626893617616604652082176166046193951761660497475517616604976134
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209224923224923419430425600824814080x7f6677207d800x7f66768250c05242889799511109750592417616605006363176166049747551761660524419517616605245757
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002122249232249234194304256001224831360x7f6677207c000x7f6676825100524288411981146135463617616605276557176166052441951761660553251517616605534080
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002152249232249234194304256001224843520x7f6677207a800x7f667682514052428810632933119089801217616605584079176166055325151761660581651617616605818093
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002182249232249234194304256001224858240x7f66772079000x7f667682518052428811260095126110836017616605848142176166058165161761660617971617616606181284
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002212249232249234194304256001224872960x7f66772077800x7f66768251c052428811284094126378339217616606213333176166061797161761660654883617616606550334
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002242249232249234194304256001224887680x7f66772076000x7f66768252005242889414519105435179217616606580284176166065488361761660681875617616606820058
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002272249232249234194304256001224907520x7f66798a94800x7f6676825240524288384427043057073217616606850577176166068187561761660711347617616607114940
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002302249232249234194304256001224919680x7f66798a93000x7f66768252805242889868269110524052817616607153569176166071134761761660738451617616607385923
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002332249232249234194304256001224934400x7f66798a91800x7f66768252c052428810983926123018904417616607416802176166073845161761660773859717616607739874
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002362249232249234194304256001224949120x7f66798a90000x7f667682530052428811307938126643569617616607771423176166077385971761660809347717616608094815
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002392249232249234194304256001224963840x7f6677207e800x7f66768253405242889182374102840776817616608125164176166080934771761660836467717616608366088
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002422249232249234194304256001224983680x7f6677207d000x7f6676825380524288358211740123542417616608396868176166083646771761660866547717616608666791
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002452249232249234194304256001224995840x7f6677207b800x7f66768253c05242889846286110265807217616608704860176166086654771761660893427717616608935814
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024822492322492341943042560012241013120x7f6677207a000x7f667682540052428811230912125786602417616608966603176166089342771761660929475817616609296185
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025122492322492341943042560012241027840x7f66772078800x7f667682544052428811195118125381641217616609325994176166092947581761660964963817616609651126
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025422492322492341943042560012241042560x7f66772077000x7f6676825480524288884691199089370017616609680985176166096496381761660991795817616609919339
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025722492322492341943042560012241062400x7f66798a95800x7f66768254c0524288322646836134194817616609950348176166099179581761661023027817616610231731
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026022492322492341943042560012241077120x7f66798a94000x7f66768255005242889896332110833741617616610270730176166102302781761661050307817616610504414
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026322492322492341943042560016241094400x7f66798a92800x7f667682554052428811267814126193352017616610535683176166105030781761661085955917616610860995
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026622492322492341943042560016241111680x7f66798a91000x7f667682558052428811205376125497168417616610891814176166108595591761661121571917616611217136
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002692249232249234194304256008241128960x7f6677207f800x7f66768255c0524288811250890855169217616611248415176166112157191761661148563917616611487089
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027222492322492341943042560012241151360x7f6677207e000x7f6676825600524288298936333476763217616611519188176166114856391761661179811917616611799431
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027522492322492341943042560012241166080x7f6677207c800x7f66768256405242889377872105029692417616611837240176166117981191761661207987917616612081324
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027822492322492341943042560016241183360x7f6677207b000x7f667682568052428811095753124272520017616612112023176166120798791761661243539917616612436885
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028122492322492341943042560016241200640x7f66772079800x7f66768256c052428811132157124673733217616612467294176166124353991761661279076017616612792196
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028422492322492341943042560012241217920x7f66772078000x7f6676825700524288690813877363524017616612822435176166127907601761661306404017616613065519
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028722492322492341943042560012241240320x7f66772076800x7f6676825740524288298703333452178417616613095598176166130640401761661338292017616613384501
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029022492322492341943042560012241255040x7f66798a95000x7f66768257805242889068751101580415617616613422400176166133829201761661365572017616613657144
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029322492322492341943042560012241274880x7f66798a93800x7f66768257c052428811119819124538215617616613687593176166136557201761661401652017616614017935
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029622492322492341943042560012241292160x7f66798a92000x7f667682580052428810959202122740020417616614048924176166140165201761661438068117616614382106
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029922492322492341943042560012241309440x7f66798a90800x7f6676825840524288622307869697825217616614413155176166143806811761661466148117616614662849
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030222492322492341943042560012241334400x7f6677207f000x7f6676825880524288299188733505993617616614694488176166146614811761661499908117616615000450
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030522492322492341943042560012241349120x7f6677207d800x7f66768258c0524288847755794940557617616615039199176166149990811761661527668117616615278123
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030822492322492341943042560012241368960x7f6677207c000x7f667682590052428810943848122567854017616615308762176166152766811761661563108117616615632404
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031122492322492341943042560012241388800x7f6677207a800x7f667682594052428810998557123181015617616615662823176166156310811761661598692217616615988555
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031422492322492341943042560012241408640x7f66772079000x7f6676825980524288472555052920815617616616018834176166159869221761661626788217616616269328
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031722492322492341943042560012241436160x7f66772077800x7f66768259c0524288290280832498783617616616300067176166162678821761661661124217616616612659
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032022492322492341943042560012241453440x7f66772076000x7f6676825a00524288747720883738458817616616650638176166166112421761661688196217616616883472
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032322492322492341943042560012241475840x7f66798a94800x7f6676825a4052428810829654121290450417616616913502176166168819621761661723652217616617237883
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032622492322492341943042560012241495680x7f66798a93000x7f6676825a8052428810920320122303438417616617268913176166172365221761661759060217616617592085
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032922492322492341943042560012241515520x7f66798a91800x7f6676825ac0524288402169145038704817616617623654176166175906021761661788100317616617882447
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033222492322492341943042560012241543040x7f66798a90000x7f6676825b00524288287441232196014017616617912676176166178810031761661824052317616618242108
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033522492322492341943042560012241562880x7f6677207e800x7f6676825b40524288553945162039873617616618280487176166182405231761661852516317616618526791
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033822492322492341943042560012241587840x7f6677207d000x7f6676825b805242889956863111515668017616618557630176166185251631761661888452317616618885892
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034122492322492341943042560012241610240x7f6677207b800x7f6676825bc052428810933613122458685217616618916561176166188845231761661925252317616619253912
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034422492322492341943042560012241632640x7f6677207a000x7f6676825c00524288356721039961422817616619284452176166192525231761661955124417616619552705
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034722492322492341943042560012241665280x7f66772078800x7f6676825c40524288287620132213546817616619583364176166195512441761661993284417616619978274
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035022492322492341943042560012241685120x7f66772077000x7f6676825c80524288405132145371460417616619997054176166199328441761662025652417616620258007
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035322492322492341943042560012241712640x7f66798a95800x7f6676825cc05242889834752110149535217616620288956176166202565241761662061492417616620616318
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035622492322492341943042560012241737600x7f66798a94000x7f6676825d0052428810166230113859131617616620648857176166206149241761662098052417616620981909
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035922492322492341943042560012241762560x7f66798a92800x7f6676825d40524288283906531784006017616621012708176166209805241761662129124517616621292721
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036222492322492341943042560012241797760x7f66798a91000x7f6676825d80524288286854232131027217616621323460176166212912451761662169796517616621716970
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036522492322492341943042560012241822720x7f6677207f800x7f6676825dc0524288314229335189254417616621737729176166216979651761662200804517616622009613
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036822492322492341943042560012241855360x7f6677207e000x7f6676825e00524288790170288491570817616622039702176166220080451761662237924517616622426112
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037122492322492341943042560012241885440x7f6677207c800x7f6676825e40524288765833085767584817616622437902176166223792451761662278612517616622832242
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037422492322492341943042560012241915520x7f6677207b000x7f6676825e80524288289224632384861617616622843621176166227861251761662315764617616623159153
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037722492322492341943042560012241958400x7f66772079800x7f6676825ec0524288287493232198331217616623189973176166231576461761662361620617616623662361
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038022492322492341943042560012241985920x7f66772078000x7f6676825f00524288276041230911160417616623681380176166236162061761662397428617616623975763
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038322492322492341943042560012242023680x7f66772076800x7f6676825f40524288681854076365677217616624006222176166239742861761662436308617616624405312
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038622492322492341943042560012242058880x7f66798a95000x7f6676825f80524288647915372563793217616624416932176166243630861761662478116717616624822921
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038922492322492341943042560012242094080x7f66798a93800x7f6676825fc0524288283035231689442817616624833051176166247811671761662517220717616625173662
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039222492322492341943042560012242144640x7f66798a92000x7f6676826000524288292218932719646017616625204752176166251722071761662568212717616625700439
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039522492322492341943042560012242177280x7f66798a90800x7f6676826040524288277275731043504817616625722508176166256821271761662603428717616626035721
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039822492322492341943042560012242220160x7f6677207f000x7f6676826080524288592746566386133617616626067170176166260342871761662647204817616626515438
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040122492322492341943042560012242260480x7f6677207d800x7f66768260c0524288519504758177405617616626526338176166264720481761662691108817616626954027
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040422492322492341943042560012242300800x7f6677207c000x7f6676826100524288277553931082465617616626965047176166269110881761662733092817616627372237
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040722492322492341943042560012242359040x7f6677207a800x7f6676826140524288290740332562393617616627383526176166273309281761662792372817616627965152
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041022492322492341943042560012242394240x7f66772079000x7f6676826180524288282485131635662017616627983991176166279237281761662832372917616628325262
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041322492322492341943042560012242442240x7f66772077800x7f66768261c0524288525494758858067217616628355832176166283237291761662875348917616628796461
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041622492322492341943042560012242487680x7f66772076000x7f6676826200524288332787437270856017616628807600176166287534891761662921300917616629234139
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041922492322492341943042560012242533120x7f66798a94800x7f6676826240524288274643030747016417616629245669176166292130091761662963476917616629654779
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004222249232249234194304256008242555520x7f66798a93000x7f6676826280524288236500626488766417616629667448176166296347691761663027317017616630295683
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042522492322492341943042560012242598400x7f66798a91800x7f66768262c0524288275604530860755217616630314482176166302731701761663069029017616630711832
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042822492322492341943042560012242656640x7f66798a90000x7f6676826300524288330257136984634017616630722592176166306902901761663117733017616631197970
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043122492322492341943042560012242712320x7f6677207e800x7f6676826340524288373577741834480017616631209439176166311773301761663166421117616631681227
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004342249232249234194304256008242732160x7f6677207d000x7f6676826380524288240229926901914817616631696597176166316642111761663214085117616632157905
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004372249232249234194304256008242757120x7f6677207b800x7f66768263c0524288238570026723215617616632172865176166321408511761663288245117616632899677
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044022492322492341943042560012242807680x7f6677207a000x7f6676826400524288264098529576460817616632922216176166328824511761663333397217616633350265
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044322492322492341943042560012242876160x7f66772078800x7f6676826440524288349910039188965617616633365955176166333339721761663386565217616633882802
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044622492322492341943042560012242942080x7f66772077000x7f6676826480524288336404737671928017616633900411176166338656521761663439749217616634416018
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004492249232249234194304256008242969600x7f66798a95800x7f66768264c0524288239292326800511217616634429828176166343974921761663493205317616634975704
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004522249232249234194304256008242999680x7f66798a94000x7f6676826500524288240229526899296017616634987064176166349320531761663580005317616635841962
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004552249232249234194304256008243027200x7f66798a92800x7f6676826540524288238724326734368017616635860891176166358000531761663645909317616636500825
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045822492322492341943042560012243054720x7f66798a91000x7f6676826580524288258772928976224417616636512105176166364590931761663713173417616637173178
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046122492322492341943042560012243082240x7f6677207f800x7f66768265c0524288259904529115654817616637185288176166371317341761663779861417616637840301
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004642249232249234194304256008243109760x7f6677207e000x7f6676826600524288239727126848971617616637850871176166377986141761663845781517616638503664
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004672249232249234194304256008243132160x7f6677207c800x7f6676826640524288241810727077694417616638515954176166384578151761663955957517616639605156
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004702249232249234194304256008243159680x7f6677207b000x7f6676826680524288244355427373572817616639625056176166395595751761664063813617616640683119
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047322492322492341943042560012243187200x7f66772079800x7f66768266c0524288258633028962239217616640694219176166406379601761664174420017616641813000
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047622492322492341943042560012243214720x7f66772078000x7f6676826700524288261380229268424817616641824460176166417442001761664287156017616642942701
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004792249232249234194304256008243242240x7f66772076800x7f6676826740524288243596627280485217616642953751176166428715601761664398548017616644051093
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004822249232249234194304256008243264640x7f66798a95000x7f6676826780524288246656127619044817616644062383176166439854801761664593044117616645996534
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004852249232249234194304256008243292160x7f66798a93800x7f66768267c0524288245303127469181617616646015123176166459304411761664785604117616647925465
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048822492322492341943042560012243319680x7f66798a92000x7f6676826800524288261775529315978017616647936565176166478560411761664984388117616649907945
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049122492322492341943042560012243347200x7f66798a90800x7f6676826840524288262917729447322417616649918805176166498438811761665182292217616651893654
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004942249232249234194304256008243374720x7f6677207f000x7f6676826880524288245664227518373217616651905794176166518229221761665375460217616653820396
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049722492322492341943042560082400x7f6677207d800x7f66768268c0524288246616327622304017616653831885176166537546021761665735748317616657478993