Files
rocm-systems/tests/workloads/Axes3/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.kd000213375213375335544322560043241600x00x7f594ea04280524288545686261118746817432727256629174304162729011743287617078317432876284272
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00221337521337532768256001224138880x00x7f594ea23f80409647128527902817432881448727174328761707831743288157765717432881582104
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0052133752133754194304256001224143360x7f5951a953800x7f594ea23fc052428810541605118065736017432881616473174328815776571743288194661717432881949174
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0082133752133754194304256001624150400x7f5951a952000x7f594ea2400052428811387598127537339217432881984183174328819466171743288236437617432882366903
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00112133752133754194304256001624154880x7f5951a950800x7f594ea2404052428811520489129031767617432882398473174328823643761743288276757617432882769923
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00142133752133754194304256001224159360x7f594f2fdf000x7f594ea2408052428810659237119375766417432882802932174328827675761743288307925617432883081605
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00172133752133754194304256001224163840x7f594f2fdd800x7f594ea240c052428810752710120423090417432883113474174328830792561743288338901517432883391427
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00202133752133754194304256001224170880x7f594f2fdc000x7f594ea2410052428811018132123403046417432883435976174328833890151743288369813517432883700429
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00232133752133754194304256001624177920x7f594f2fda800x7f594ea2414052428811398963127665792017432883731158174328836981351743288409189517432884094119
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00262133752133754194304256001624184960x7f594f2fd9000x7f594ea2418052428811610126130030686017432884126528174328840918951743288448645417432884488848
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00292133752133754194304256001624192000x7f594f2fd7800x7f594ea241c052428810811476121083227217432884518578174328844864541743288480661417432884808970
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00322133752133754194304256001624199040x7f594f2fd6000x7f594ea2420052428810855377121577635217432884840999174328848066141743288511189417432885113992
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00352133752133754194304256001224206080x7f5951a954800x7f594ea2424052428811056345123829839217432885153771174328851118941743288541941417432885421554
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00382133752133754194304256001624213120x7f5951a953000x7f594ea2428052428811505558128858574017432885453023174328854194141743288581221317432885814414
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00412133752133754194304256001624220160x7f5951a951800x7f594ea242c052428811492196128708514417432885845913174328858122131743288620309317432886205684
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00442133752133754194304256001624227200x7f5951a950000x7f594ea2430052428811030682123534492417432886236923174328862030931743288652821317432886529955
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00472133752133754194304256001224234240x7f594f2fde800x7f594ea2434052428810883582121898526417432886560924174328865282131743288681013217432886811708
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00502133752133754194304256001224241280x7f594f2fdd000x7f594ea2438052428811201967125460802417432886851217174328868101321743288709189217432887093621
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00532133752133754194304256001624248320x7f594f2fdb800x7f594ea243c052428811318776126770014817432887125710174328870918921743288745829217432887459981
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00562133752133754194304256001624255360x7f594f2fda000x7f594ea2440052428811391028127577647617432887490940174328874582921743288783317217432887834991
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00592133752133754194304256001224262400x7f594f2fd8800x7f594ea2444052428810879580121849896817432887866320174328878331721743288811349117432888115244
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00622133752133754194304256001224269440x7f594f2fd7000x7f594ea2448052428810924562122352925217432888146343174328881134911743288839477117432888396387
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00652133752133754194304256001224276480x7f5951a955800x7f594ea244c052428811031744123545602417432888435586174328883947711743288867253117432888674239
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00682133752133754194304256001624286080x7f5951a954000x7f594ea2450052428811513944128952779617432888705699174328886725311743288904293117432889044740
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00712133752133754194304256001624293120x7f5951a952800x7f594ea2454052428811389738127561491217432889076099174328890429311743288940949017432889411190
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00742133752133754194304256001224300160x7f5951a951000x7f594ea2458052428811166670125065691617432889442839174328894094901743288968661017432889688373
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077213375213375419430425600824309760x7f594f2fdf800x7f594ea245c052428810325412115650502817432889720302174328896866101743288996885017432889970486
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00802133752133754194304256001224316800x7f594f2fde000x7f594ea2460052428810947614122609260817432890009025174328899688501743289026740917432890269548
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00832133752133754194304256001624326400x7f594f2fdc800x7f594ea2464052428811279640126331714817432890300567174328902674091743289064196917432890643668
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00862133752133754194304256001224336000x7f594f2fdb000x7f594ea2468052428811526060129084553217432890675237174328906419691743289100964917432891011269
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00892133752133754194304256001224345600x7f594f2fd9800x7f594ea246c052428810933276122452156017432891042388174328910096491743289128868917432891290391
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092213375213375419430425600824355200x7f594f2fd8000x7f594ea2470052428810360817116045020817432891321551174328912886891743289157412817432891575824
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00952133752133754194304256001224362240x7f594f2fd6800x7f594ea2474052428810840297121415829217432891613573174328915741281743289186212817432891863836
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00982133752133754194304256001224371840x7f5951a955000x7f594ea2478052428811297665126530012017432891895006174328918621281743289222804817432892229817
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001012133752133754194304256001224381440x7f5951a953800x7f594ea247c052428811392052127588628817432892261566174328922280481743289260004717432892601667
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001042133752133754194304256001224391040x7f5951a952000x7f594ea2480052428810469951117259469217432892632566174328926000471743289287908717432892880670
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107213375213375419430425600824403200x7f5951a950800x7f594ea2484052428810006153112067578017432892912809174328928790871743289315828717432893159973
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001102133752133754194304256001224412800x7f594f2fdf000x7f594ea2488052428810633657119101161217432893198512174328931582871743289344260717432893444205
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001132133752133754194304256001224422400x7f594f2fdd800x7f594ea248c052428811406920127753455617432893475145174328934426071743289380740617432893809126
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001162133752133754194304256001224432000x7f594f2fdc000x7f594ea2490052428811214289125596259617432893841085174328938074061743289417572617432894177446
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119213375213375419430425600824441600x7f594f2fda800x7f594ea2494052428810433050116849170817432894209115174328941757261743289446100617432894462749
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001222133752133754194304256001224453760x7f594f2fd9000x7f594ea249805242889773702109457656817432894494668174328944610061743289474500617432894746691
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001252133752133754194304256001224463360x7f594f2fd7800x7f594ea249c052428810437907116913904417432894784900174328947450061743289503108517432895032774
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001282133752133754194304256001224475520x7f594f2fd6000x7f594ea24a0052428811387258127534588017432895064323174328950310851743289539860517432895400364
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001312133752133754194304256001224485120x7f5951a954800x7f594ea24a4052428811286861126413423617432895432814174328953986051743289576644517432895768145
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134213375213375419430425600824494720x7f5951a953000x7f594ea24a8052428810394076116411041217432895799444174328957664451743289604612417432896047798
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001372133752133754194304256001224506880x7f5951a951800x7f594ea24ac0524288887513699401225617432896079927174328960461241743289633108417432896332840
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001402133752133754194304256001224516480x7f5951a950000x7f594ea24b0052428810234618114621390417432896371879174328963310841743289661172417432896613423
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001432133752133754194304256001224528640x7f594f2fde800x7f594ea24b4052428811305473126620470417432896644262174328966117241743289697812417432896979833
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001462133752133754194304256001224540800x7f594f2fdd000x7f594ea24b8052428811216500125617925617432897011303174328969781241743289734180317432897343464
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149213375213375419430425600824552960x7f594f2fdb800x7f594ea24bc052428810341437115827133617432897373893174328973418031743289762356317432897625247
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001522133752133754194304256001224567680x7f594f2fda000x7f594ea24c00524288771782586432824817432897656296174328976235631743289790372317432897905569
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001552133752133754194304256001224577280x7f594f2fd8800x7f594ea24c4052428810528886117917812417432897943248174328979037231743289819172317432898193612
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001582133752133754194304256001224589440x7f594f2fd7000x7f594ea24c8052428811346497127075433617432898225571174328981917231743289856212217432898563712
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001612133752133754194304256001224601600x7f5951a955800x7f594ea24cc052428811277845126312639617432898595801174328985621221743289892852217432898930353
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164213375213375419430425600824613760x7f5951a954000x7f594ea24d0052428810076281112844687617432898962022174328989285221743289922052217432899222135
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001672133752133754194304256001224628480x7f5951a952800x7f594ea24d40524288598053466974746817432899254804174328992205221743289950420217432899505928
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001702133752133754194304256001224638080x7f5951a951000x7f594ea24d8052428810517587117790890817432899545547174328995042021743289978852117432899790230
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001732133752133754194304256001224650240x7f594f2fdf800x7f594ea24dc052428811324204126831270817432899822239174328997885211743290015572117432900157381
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001762133752133754194304256001224662400x7f594f2fde000x7f594ea24e0052428811323825126825420417432900189010174329001557211743290052372117432900525411
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179213375213375419430425600824674560x7f594f2fdc800x7f594ea24e4052428810010826112113792417432900557160174329005237211743290080644017432900808104
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001822133752133754194304256001224689280x7f594f2fdb000x7f594ea24e80524288565456563325745617432900839953174329008064401743290109700017432901098576
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001852133752133754194304256001224701440x7f594f2fd9800x7f594ea24ec052428810212843114381972817432901137055174329010970001743290138356017432901385299
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001882133752133754194304256001224716160x7f594f2fd8000x7f594ea24f0052428811280678126342150417432901416078174329013835601743290175092017432901752619
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001912133752133754194304256001224728320x7f594f2fd6800x7f594ea24f4052428811387169127537821617432901783458174329017509201743290212323917432902125140
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194213375213375419430425600824740480x7f5951a955000x7f594ea24f805242889880876110670218817432902157559174329021232391743290241091917432902412492
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001972133752133754194304256001224757760x7f5951a953800x7f594ea24fc0524288470560852698211217432902443851174329024109191743290270643917432902708164
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002002133752133754194304256001224769920x7f5951a952000x7f594ea250005242889829043110078593617432902747283174329027064391743290298547917432902987167
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002032133752133754194304256001224784640x7f5951a950800x7f594ea2504052428811203792125480430817432903019576174329029854791743290335075817432903352418
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002062133752133754194304256001224799360x7f594f2fdf000x7f594ea2508052428811035225123592180017432903384797174329033507581743290372003817432903721758
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209213375213375419430425600824814080x7f594f2fdd800x7f594ea250c05242889672068108321101217432903753227174329037200381743290400243817432904004181
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002122133752133754194304256001224831360x7f594f2fdc000x7f594ea25100524288419100346936224417432904035670174329040024381743290430131717432904303023
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002152133752133754194304256001224843520x7f594f2fda800x7f594ea251405242889981262111785581217432904352302174329043013171743290458163717432904583466
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002182133752133754194304256001224858240x7f594f2fd9000x7f594ea2518052428811318289126761782817432904614625174329045816371743290495299717432904954636
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002212133752133754194304256001224872960x7f594f2fd7800x7f594ea251c052428811093521124241948417432904985845174329049529971743290532355617432905325516
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002242133752133754194304256001224887680x7f594f2fd6000x7f594ea252005242889382578105077858817432905356135174329053235561743290560291617432905604549
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002272133752133754194304256001224907520x7f5951a954800x7f594ea25240524288348928239069862017432905635488174329056029161743290591235617432905914061
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002302133752133754194304256001224919680x7f5951a953000x7f594ea252805242889929248111203050417432905953130174329059123561743290620451617432906206663
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002332133752133754194304256001224934400x7f5951a951800x7f594ea252c052428811152494124905026817432906238193174329062045161743290657651517432906578254
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002362133752133754194304256001224949120x7f5951a950000x7f594ea2530052428811171249125113842417432906609933174329065765151743290694195517432906943704
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002392133752133754194304256001224963840x7f594f2fde800x7f594ea253405242889472195106089802417432906975163174329069419551743290722115517432907222907
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002422133752133754194304256001224983680x7f594f2fdd000x7f594ea25380524288357927840076458817432907254406174329072211551743290753091517432907532559
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002452133752133754194304256001224995840x7f594f2fdb800x7f594ea253c052428810005778112063826417432907570508174329075309151743290781523417432907817141
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024821337521337541943042560012241013120x7f594f2fda000x7f594ea2540052428811135437124717221217432907848591174329078152341743290818339417432908185072
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025121337521337541943042560012241027840x7f594f2fd8800x7f594ea2544052428811038525123630732817432908216671174329081833941743290854899417432908550602
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025421337521337541943042560012241042560x7f594f2fd7000x7f594ea25480524288869634497396016417432908581682174329085489941743290883043317432908832045
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025721337521337541943042560012241062400x7f5951a955800x7f594ea254c0524288322316236099644417432908863644174329088304331743290914867317432909150417
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026021337521337541943042560012241077120x7f5951a954000x7f594ea255005242889832818110127779617432909189036174329091486731743290942707317432909428910
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026321337521337541943042560016241094400x7f5951a952800x7f594ea2554052428811081643124113899217432909460359174329094270731743290979283317432909794580
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026621337521337541943042560016241111680x7f5951a951000x7f594ea2558052428811120776124548680417432909826249174329097928331743291015619217432910158211
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002692133752133754194304256008241128960x7f594f2fdf800x7f594ea255c0524288816442291439499217432910190440174329101561921743291044083217432910442613
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027221337521337541943042560012241151360x7f594f2fde000x7f594ea25600524288297586133326903217432910473992174329104408321743291076547217432910767085
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027521337521337541943042560012241166080x7f594f2fdc800x7f594ea256405242889738524109062945617432910805664174329107654721743291105075217432911052347
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027821337521337541943042560016241183360x7f594f2fdb000x7f594ea2568052428811046326123712652417432911083307174329110507521743291142131117432911422978
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028121337521337541943042560016241200640x7f594f2fd9800x7f594ea256c052428811012158123333968817432911454777174329114213111743291178627117432911787998
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028421337521337541943042560012241217920x7f594f2fd8000x7f594ea25700524288672531375326260017432911818487174329117862711743291206803117432912069821
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028721337521337541943042560012241240320x7f594f2fd6800x7f594ea25740524288293459532858349617432912101490174329120680311743291239651017432912398342
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029021337521337541943042560012241255040x7f5951a955000x7f594ea257805242889371021104952699617432912436921174329123965101743291268307017432912684775
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029321337521337541943042560012241274880x7f5951a953800x7f594ea257c052428811116263124499117617432912716104174329126830701743291305395017432913055695
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029621337521337541943042560012241292160x7f5951a952000x7f594ea2580052428811083291124132439217432913086984174329130539501743291342803017432913429705
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029921337521337541943042560012241309440x7f5951a950800x7f594ea25840524288603187367554744417432913460945174329134280301743291371714917432913718998
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030221337521337541943042560012241334400x7f594f2fdf000x7f594ea25880524288291760832669567217432913750407174329137171491743291406562917432914067339
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030521337521337541943042560012241349120x7f594f2fdd800x7f594ea258c0524288833812893398143617432914106758174329140656291743291435842917432914360351
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030821337521337541943042560012241368960x7f594f2fdc000x7f594ea2590052428811045896123714739617432914390810174329143584291743291472738817432914729142
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031121337521337541943042560012241388800x7f594f2fda800x7f594ea2594052428810960218122750778417432914760481174329147273881743291509458817432915096362
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031421337521337541943042560012241408640x7f594f2fd9000x7f594ea25980524288444282449751899217432915127611174329150945881743291538338817432915385205
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031721337521337541943042560012241436160x7f594f2fd7800x7f594ea259c0524288283726731771924417432915417734174329153833881743291574018817432915741925
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032021337521337541943042560012241453440x7f594f2fd6000x7f594ea25a00524288724321581119789217432915781574174329157401881743291602258717432916024278
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032321337521337541943042560012241475840x7f5951a954800x7f594ea25a4052428810754575120449486817432916055567174329160225871743291639058717432916392248
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032621337521337541943042560012241495680x7f5951a953000x7f594ea25a8052428810963089122784826017432916423718174329163905871743291675714717432916758839
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032921337521337541943042560012241515520x7f5951a951800x7f594ea25ac0524288369230341348818017432916789768174329167571471743291706018617432917061901
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033221337521337541943042560012241543040x7f5951a950000x7f594ea25b00524288283916431800588817432917093570174329170601861743291742962617432917431281
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033521337521337541943042560012241562880x7f594f2fde800x7f594ea25b40524288558907162593485617432917470070174329174296261743291771794617432917719684
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033821337521337541943042560012241587840x7f594f2fdd000x7f594ea25b805242889657699108161546017432917750703174329177179461743291808978517432918091584
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034121337521337541943042560012241610240x7f594f2fdb800x7f594ea25bc052428810469482117256344417432918123133174329180897851743291847634517432918478114
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034421337521337541943042560012241632640x7f594f2fda000x7f594ea25c00524288372940541765482817432918509873174329184763451743291878578517432918787556
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034721337521337541943042560012241665280x7f594f2fd8800x7f594ea25c40524288283388831741658817432918818425174329187857851743291917970517432919203475
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035021337521337541943042560012241685120x7f594f2fd7000x7f594ea25c80524288398174944595774017432919223055174329191797051743291949202417432919494028
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035321337521337541943042560012241712640x7f5951a955800x7f594ea25cc05242889470537106066570017432919525177174329194920241743291986258417432919864318
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035621337521337541943042560012241737600x7f5951a954000x7f594ea25d0052428810562222118299454817432919895707174329198625841743292023938417432920241128
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035921337521337541943042560012241762560x7f5951a952800x7f594ea25d40524288286556732095490417432920271957174329202393841743292056578317432920567520
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036221337521337541943042560012241797760x7f5951a951000x7f594ea25d80524288282009331587406817432920599399174329205657831743292098402317432921001769
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036521337521337541943042560012241822720x7f594f2fdf800x7f594ea25dc0524288303188233956148417432921025558174329209840231743292130354317432921305161
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036821337521337541943042560012241855360x7f594f2fde000x7f594ea25e00524288770907586339185217432921336040174329213035431743292168322217432921685051
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037121337521337541943042560012241885440x7f594f2fdc800x7f594ea25e40524288778163587153570817432921716500174329216832221743292206498217432922067441
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037421337521337541943042560012241915520x7f594f2fdb000x7f594ea25e80524288282210631598734017432922098420174329220649821743292243298217432922434641
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037721337521337541943042560012241958400x7f594f2fd9800x7f594ea25ec0524288283267431718485217432922465920174329224329821743292290578117432922926878
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038021337521337541943042560012241985920x7f594f2fd8000x7f594ea25f00524288273558830635635617432922946638174329229057811743292325122117432923252870
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038321337521337541943042560012242023680x7f594f2fd6800x7f594ea25f40524288671061775154231617432923283319174329232512211743292365218117432923672619
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038621337521337541943042560012242058880x7f5951a955000x7f594ea25f80524288646483972402662017432923685679174329236521811743292405650017432924074189
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038921337521337541943042560012242094080x7f5951a953800x7f594ea25fc0524288280083231363620817432924088878174329240565001743292444370017432924445589
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039221337521337541943042560012242144640x7f5951a952000x7f594ea26000524288287935632247880417432924476938174329244437001743292496530017432924983225
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039521337521337541943042560012242177280x7f5951a950800x7f594ea26040524288282144731597529617432925005974174329249653001743292532369917432925325456
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039821337521337541943042560012242220160x7f594f2fdf000x7f594ea26080524288604147467658153617432925357025174329253236991743292574417917432925761545
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040121337521337541943042560012242260480x7f594f2fdd800x7f594ea260c0524288518175158034295217432925779224174329257441791743292616689917432926184404
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040421337521337541943042560012242300800x7f594f2fdc000x7f594ea26100524288285459931973498417432926199403174329261668991743292657697817432926618512
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040721337521337541943042560012242359040x7f594f2fda800x7f594ea26140524288287739332230639617432926629722174329265769781743292718097817432927222967
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041021337521337541943042560012242394240x7f594f2fd9000x7f594ea26180524288277429131070050817432927241886174329271809781743292758737717432927589157
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041321337521337541943042560012242442240x7f594f2fd7800x7f594ea261c0524288500246856022181217432927619956174329275873771743292802321717432928064655
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041621337521337541943042560012242487680x7f594f2fd6000x7f594ea26200524288319683735811388017432928075135174329280232171743292848113717432928523143
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041921337521337541943042560012242533120x7f5951a954800x7f594ea26240524288274245730725564817432928534233174329284811371743292893953617432928981561
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004222133752133754194304256008242555520x7f5951a953000x7f594ea26280524288236511926487823617432928992641174329289395361743292960993617432929656823
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042521337521337541943042560012242598400x7f5951a951800x7f594ea262c0524288272701030552240817432929676543174329296099361743293005905517432930083962
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042821337521337541943042560012242656640x7f5951a950000x7f594ea26300524288318393535657303217432930095032174329300590551743293056337517432930607549
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043121337521337541943042560012242712320x7f594f2fde800x7f594ea26340524288373868941873829217432930618218174329305633751743293108113417432931124015
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004342133752133754194304256008242732160x7f594f2fdd000x7f594ea26380524288239326226804065217432931134815174329310811341743293159537417432931637852
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004372133752133754194304256008242757120x7f594f2fdb800x7f594ea263c0524288238434426702423217432931648402174329315953741743293237281317432932414262
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044021337521337541943042560012242807680x7f594f2fda000x7f594ea26400524288266609129859042417432932433501174329323728131743293285297317432932894329
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044321337521337541943042560012242876160x7f594f2fd8800x7f594ea26440524288345027938634214417432932904969174329328529731743293341665217432933458544
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044621337521337541943042560012242942080x7f594f2fd7000x7f594ea26480524288336089337638709217432933469904174329334166521743293398225217432934000080
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004492133752133754194304256008242969600x7f5951a955800x7f594ea264c0524288238788326740463617432934015450174329339822521743293452977117432934573435
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004522133752133754194304256008242999680x7f5951a954000x7f594ea26500524288239198826788647217432934585165174329345297711743293540833117432935452523
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004552133752133754194304256008243027200x7f5951a952800x7f594ea26540524288238213326677294017432935471352174329354083311743293607281017432936114755
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045821337521337541943042560012243054720x7f5951a951000x7f594ea26580524288260262729150922017432936125455174329360728101743293674976917432936792338
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046121337521337541943042560012243082240x7f594f2fdf800x7f594ea265c0524288259438929061339617432936803447174329367497691743293743392917432937475780
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004642133752133754194304256008243109760x7f594f2fde000x7f594ea26600524288238351926690428017432937487040174329374339291743293810800817432938133143
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004672133752133754194304256008243132160x7f594f2fdc800x7f594ea26640524288240172426899904817432938145153174329381079361743293918297517432939233654
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004702133752133754194304256008243159680x7f594f2fdb000x7f594ea26680524288243370027258383217432939252924174329391829751743294027801217432940343485
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047321337521337541943042560012243187200x7f594f2fd9800x7f594ea266c0524288257984128897636817432940355425174329402780121743294141769117432941482476
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047621337521337541943042560012243214720x7f594f2fd8000x7f594ea26700524288258789128983833217432941493515174329414176911743294255113017432942622556
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004792133752133754194304256008243242240x7f594f2fd6800x7f594ea26740524288242210227125684017432942633846174329425511301743294367528917432943741817
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004822133752133754194304256008243264640x7f5951a955000x7f594ea26780524288246370327590235217432943752767174329436752891743294562568717432945692176
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004852133752133754194304256008243292160x7f5951a953800x7f594ea267c0524288246026027555688817432945711206174329456256871743294754984517432947621356
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048821337521337541943042560012243319680x7f5951a952000x7f594ea26800524288261971929341766017432947632496174329475498451743294954024317432949607104
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049121337521337541943042560012243347200x7f5951a950800x7f594ea26840524288262250929369393617432949618224174329495402431743295151704117432951588243
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004942133752133754194304256008243374720x7f594f2fdf000x7f594ea26880524288244526127387437617432951600583174329515170411743295345639917432953524143
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049721337521337541943042560082400x7f594f2fdd800x7f594ea268c0524288246337427592575617432953536112174329534563991743295706871617432957147758