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

48 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjGRBM_COUNTGRBM_GUI_ACTIVECPC_ME1_BUSY_FOR_PACKET_DECODESQ_CYCLESSQ_WAVESSQ_WAVE_CYCLESSQ_BUSY_CYCLESSQ_LEVEL_WAVESSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000188242188242335544322560043241600x00x7fd4a6804280388284388284877831062805242882449678043019488099617140417019739890511170190364281161701988502768217019885140781
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00218824218824232768256001224138880x00x7fd4a6823f8033728337283023026983251216930191640260678538417019890314053170198850276821701989045326817019890458139
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051882421882424194304256001224143360x7fd4a98823800x7fd4a6823fc016460716460714285131686465536826224291217167033221890017019890502057170198904532681701989084814717019890850967
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081882421882424194304256001624150400x7fd4a98822000x7fd4a6824000309658309658240762477272655362190121582366437087777512017019890896976170198908481471701989127726617019891279845
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111882421882424194304256001624154880x7fd4a98820800x7fd4a6824040310040310040243632480328655362250777052376809090203899617019891321304170198912772661701989169934517019891701683
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141882421882424194304256001224159360x7fd4a7223f000x7fd4a682408016562216562213528132498465536860261251218875034583084417019891743592170198916993451701989202910417019892031313
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171882421882424194304256001224163840x7fd4a7223d800x7fd4a68240c016575016575013270132600865536804755421220716032363349617019892072222170198920291041701989235710317019892359374
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201882421882424194304256001224170880x7fd4a7223c000x7fd4a682410016343216343214791130746465536935850401205188037607190417019892412603170198923571031701989268190217019892684125
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231882421882424194304256001624177920x7fd4a7223a800x7fd4a6824140309075309075242052472608655362259973742372366090571878017019892724894170198926819021701989311422117019893116502
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261882421882424194304256001624184960x7fd4a72239000x7fd4a6824180308706308706221582469656655362206293822366323088424682017019893156931170198931142211701989353118017019893533490
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291882421882424194304256001624192000x7fd4a72237800x7fd4a68241c016415316415313740131323265536858613221212366034518267217019893573259170198935311801701989385678017019893858951
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321882421882424194304256001624199040x7fd4a72236000x7fd4a6824200164678164678147701317432655361034332711217099041545803617019893899070170198938567801701989418989917019894192201
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351882421882424194304256001224206080x7fd4a98824800x7fd4a6824240164178164178155921313432655361014409471208305040748705217019894244890170198941898991701989452877817019894530732
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381882421882424194304256001624213120x7fd4a98823000x7fd4a6824280308446308446241812467576655362323789602368086093124428417019894573300170198945287781701989491517717019894916821
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411882421882424194304256001624220160x7fd4a98821800x7fd4a68242c0311585311585225002492688655362144898172384988085968895617019894960409170198949151771701989530397617019895305769
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441882421882424194304256001624227200x7fd4a98820000x7fd4a682430016390016390014490131120865536996227751212799040021908417019895349028170198953039761701989560653517019895608381
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471882421882424194304256001224234240x7fd4a7223e800x7fd4a682434016418916418914508131352065536922439761212687037070787217019895650189170198956065351701989590333517019895905092
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501882421882424194304256001224241280x7fd4a7223d000x7fd4a6824380162516162516149021300136655361057242391201244042461433617019895954481170198959033351701989620157417019896203283
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531882421882424194304256001624248320x7fd4a7223b800x7fd4a68243c0311124311124242942489000655362257846862377134090487057617019896248312170198962015741701989660301317019896604732
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561882421882424194304256001624255360x7fd4a7223a000x7fd4a6824400304448304448206232435592655362141207562334150085821399217019896647051170198966030131701989698733217019896989151
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591882421882424194304256001224262400x7fd4a72238800x7fd4a682444016421516421515996131372865536911569321206010036636102417019897030770170198969873321701989728621117019897287952
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621882421882424194304256001224269440x7fd4a72237000x7fd4a6824480162962162962145891303704655361003282171202971040303584017019897331531170198972862111701989758637117019897587983
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651882421882424194304256001224276480x7fd4a98825800x7fd4a68244c016296116296114487130369665536900551591201273036196332817019897637642170198975863711701989789917017019897900994
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681882421882424194304256001624286080x7fd4a98824000x7fd4a6824500308294308294240202466360655362290142962370344091778822817019897947633170198978991701701989830956917019898311363
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711882421882424194304256001624293120x7fd4a98822800x7fd4a6824540306400306400206402451208655362200457372352752088191133217019898354911170198983095691701989869900817019898700691
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741882421882424194304256001224300160x7fd4a98821000x7fd4a682458016208116208115031129665665536976799531198562039245406817019898743080170198986990081701989899628717019898997983
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077188242188242419430425600824309760x7fd4a7223f800x7fd4a68245c016285016285015183130280865536863852211197567034727472017019899040172170198989962871701989929468717019899296444
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801882421882424194304256001224316800x7fd4a7223e000x7fd4a6824600162497162497150281299984655361043940211200433041929647217019899344993170198992946871701989959020617019899592086
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831882421882424194304256001624326400x7fd4a7223c800x7fd4a6824640307540307540237422460328655362253761912355673090323968817019899634165170198995902061701989997964517019899981385
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861882421882424194304256001224336000x7fd4a7223b000x7fd4a6824680307633307633231472461072655362165178022350793086779974417019900023674170198999796451701990036524417019900366854
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891882421882424194304256001224345600x7fd4a72239800x7fd4a68246c016309416309414194130476065536938138261204080037698785217019900410352170199003652441701990066508317019900667035
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092188242188242419430425600824355200x7fd4a72238000x7fd4a682470016262716262713806130102465536882908091202985035488955217019900709134170199006650831701990096108317019900962717
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951882421882424194304256001224362240x7fd4a72236800x7fd4a682474016198916198914427129592065536970562181198379038995454417019901011405170199009610831701990125740217019901259068
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981882421882424194304256001224371840x7fd4a98825000x7fd4a6824780308085308085251142464688655362296814312358272092045598017019901305687170199012574021701990165276117019901654387
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011882421882424194304256001224381440x7fd4a98823800x7fd4a68247c0307826307826230052462616655362238729072363147089722012417019901696946170199016527611701990204028017019902042006
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041882421882424194304256001224391040x7fd4a98822000x7fd4a682480016246516246514822129972865536946699071199458038040380017019902095604170199020402801701990235131917019902353147
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107188242188242419430425600824403200x7fd4a98820800x7fd4a682484016238416238414944129908065536917459751197851036870772417019902395426170199023513191701990265355917019902655258
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101882421882424194304256001224412800x7fd4a7223f000x7fd4a682488016239316239314204129915265536852305951196219034265373217019902704137170199026535591701990295067817019902952390
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131882421882424194304256001224422400x7fd4a7223d800x7fd4a68248c0305058305058235502440472655362167278522336323086864093617019902999248170199029506781701990334491717019903346598
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161882421882424194304256001224432000x7fd4a7223c000x7fd4a6824900306000306000221542448008655362203027692339223088294258417019903389427170199033449171701990373755617019903739237
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119188242188242419430425600824441600x7fd4a7223a800x7fd4a682494016288416288414925130308065536924194611197223037141072017019903780286170199037375561701990403435517019904036028
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221882421882424194304256001224453760x7fd4a72239000x7fd4a682498016292516292514138130340865536895793751201507036004644417019904077757170199040343551701990433275417019904334480
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251882421882424194304256001224463360x7fd4a72237800x7fd4a68249c016142416142413639129140065536956252321193766038422307617019904383438170199043327541701990463691417019904638581
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281882421882424194304256001224475520x7fd4a72236000x7fd4a6824a00306826306826243072454616655362275454252349969091191078417019904679340170199046369141701990502267317019905024380
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311882421882424194304256001224485120x7fd4a98824800x7fd4a6824a40303566303566211922428536655362088963182325717083731477217019905067229170199050226731701990540763217019905409509
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134188242188242419430425600824494720x7fd4a98823000x7fd4a6824a8016184116184114773129473665536896735331194627036043208817019905451138170199054076321701990570939117019905710990
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371882421882424194304256001224506880x7fd4a98821800x7fd4a6824ac016150416150415314129204065536961477741192435038632829217019905753439170199057093911701990600923017019906010992
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401882421882424194304256001224516480x7fd4a98820000x7fd4a6824b0016092716092714319128742465536884430271184781035550447617019906060020170199060092301701990631643017019906318233
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431882421882424194304256001224528640x7fd4a7223e800x7fd4a6824b40303278303278215052426232655362164855462325192086767457617019906359782170199063164301701990670042917019906702022
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461882421882424194304256001224540800x7fd4a7223d000x7fd4a6824b80302207302207219032417664655362152515972313509086273464017019906745211170199067004291701990709642817019907098201
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149188242188242419430425600824552960x7fd4a7223b800x7fd4a6824bc016237416237414591129900065536871506861196659035033614417019907139759170199070964281701990739338717019907395222
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521882421882424194304256001224567680x7fd4a7223a000x7fd4a6824c0016250216250215914130002465536999212861199466040141890017019907436201170199073933871701990769690617019907698663
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551882421882424194304256001224577280x7fd4a72238800x7fd4a6824c4016270616270613818130165665536827623511196598033277598017019907747712170199076969061701990799802617019907999705
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581882421882424194304256001224589440x7fd4a72237000x7fd4a6824c80304267304267231452434144655362224789962327122089165145617019908046543170199079980261701990838890517019908390764
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611882421882424194304256001224601600x7fd4a98825800x7fd4a6824cc0303952303952214782431624655362055060972321658082375488017019908432852170199083889051701990878010417019908782002
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164188242188242419430425600824613760x7fd4a98824000x7fd4a6824d0016353916353914605130832065536912739301208643036682604417019908824281170199087801041701990907850317019909080104
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671882421882424194304256001224628480x7fd4a98822800x7fd4a6824d40168437168437159201347504655361040317381247420041787624017019909122133170199090785031701990938474217019909386605
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701882421882424194304256001224638080x7fd4a98821000x7fd4a6824d8016226716226714211129814465536867025421196100034854328417019909435804170199093847421701990969578217019909697586
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731882421882424194304256001224650240x7fd4a7223f800x7fd4a6824dc0301846301846235842414776655362205778112309798088404503217019909744465170199096957821701991008634117019910088055
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761882421882424194304256001224662400x7fd4a7223e000x7fd4a6824e00300915300915202992407328655362072996662300930083093384017019910131624170199100863411701991047722017019910479174
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179188242188242419430425600824674560x7fd4a7223c800x7fd4a6824e4016314016314014627130512865536854025841203745034335042417019910520492170199104772201701991077705917019910779015
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821882421882424194304256001224689280x7fd4a7223b000x7fd4a6824e80176787176787167161414304655361127375671311115045268844417019910821164170199107770591701991108633817019911088016
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851882421882424194304256001224701440x7fd4a72239800x7fd4a6824ec016102016102014372128816865536924877961189123037168528417019911136975170199110863381701991139417817019911395877
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881882421882424194304256001224716160x7fd4a72238000x7fd4a6824f00301434301434224492411480655362180296632304365087385341617019911436996170199113941781701991178777717019911789416
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911882421882424194304256001224728320x7fd4a72236800x7fd4a6824f40302838302838227962422712655362176535242319895087234550817019911830465170199117877771701991217513617019912176875
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194188242188242419430425600824740480x7fd4a98825000x7fd4a6824f8016194616194614277129557665536818986901189989032933184817019912218774170199121751361701991247337517019912475106
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971882421882424194304256001224757760x7fd4a98823800x7fd4a6824fc0183802183802178381470424655361086753911356103043644111217019912517555170199124733751701991278857417019912790317
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001882421882424194304256001224769920x7fd4a98822000x7fd4a682500016304816304814920130439265536887054201199342035654929617019912853326170199127885741701991308793417019913089659
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031882421882424194304256001224784640x7fd4a98820800x7fd4a6825040303024303024235872424200655362200570612315133088195994817019913131548170199130879341701991347913317019913480818
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061882421882424194304256001224799360x7fd4a7223f000x7fd4a6825080299786299786214432398296655362027286272290698081264789217019913522156170199134791331701991387241217019913874136
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209188242188242419430425600824814080x7fd4a7223d800x7fd4a68250c016263716263714888130110465536936038781200522037615311617019913915665170199138724121701991417177117019914173788
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121882421882424194304256001224831360x7fd4a7223c000x7fd4a6825100191869191869173861534960655361161394101429153046630288017019914215096170199141717711701991449273017019914494408
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151882421882424194304256001224843520x7fd4a7223a800x7fd4a682514016184216184214539129474465536969891941192942038968536817019914543777170199144927301701991479336917019914795070
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181882421882424194304256001224858240x7fd4a72239000x7fd4a6825180299986299986213902399896655362146012662296357086014421217019914836609170199147933691701991517864817019915180419
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211882421882424194304256001224872960x7fd4a72237800x7fd4a68251c0298612298612218302388904655362162396862288185086668883217019915222447170199151786481701991556072817019915562458
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241882421882424194304256001224887680x7fd4a72236000x7fd4a682520016208516208515188129668865536920278401195005036984358417019915603646170199155607281701991585960717019915861369
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271882421882424194304256001224907520x7fd4a98824800x7fd4a6825240201297201297176611610384655361203297901502863048307449217019915903528170199158596071701991618856617019916190339
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301882421882424194304256001224919680x7fd4a98823000x7fd4a682528016117816117815171128943265536904011431189957036333466417019916239898170199161885661701991648808517019916489881
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331882421882424194304256001224934400x7fd4a98821800x7fd4a68252c0300550300550227092404408655362206937412305668088450994017019916532090170199164880851701991687512417019916876810
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361882421882424194304256001224949120x7fd4a98820000x7fd4a6825300300454300454217812403640655362103035452301283084294819217019916919968170199168751241701991726184317019917263559
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391882421882424194304256001224963840x7fd4a7223e800x7fd4a682534016221216221215338129770465536990537661196518039794681617019917305037170199172618431701991756216317019917563950
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421882421882424194304256001224983680x7fd4a7223d000x7fd4a6825380209361209361180831674896655361405556911574100056396460817019917604909170199175621631701991789304217019917894760
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451882421882424194304256001224995840x7fd4a7223b800x7fd4a68253c016041616041614229128333665536861774941183982034644070417019917943099170199178930421701991819768117019918199452
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024818824218824241943042560012241013120x7fd4a7223a000x7fd4a6825400303291303291245752426336655362202310462316246088265895617019918240940170199181976811701991859208017019918593790
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025118824218824241943042560012241027840x7fd4a72238800x7fd4a6825440298452298452209332387624655362123286762287737085104628417019918636129170199185920801701991897735917019918978939
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025418824218824241943042560012241042560x7fd4a72237000x7fd4a682548016264016264016033130112865536984296471197944039545682017019919020628170199189773591701991927591917019919277581
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025718824218824241943042560012241062400x7fd4a98825800x7fd4a68254c0218895218895190881751168655361349165091640669054141278017019919319649170199192759191701991960903817019919610721
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026018824218824241943042560012241077120x7fd4a98824000x7fd4a682550016086016086014714128688865536887937681182386035691227217019919659370170199196090381701991990871717019919910502
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026318824218824241943042560016241094400x7fd4a98822800x7fd4a6825540297703297703225072381632655362160687872280285086600478817019919957431170199199087171701992030263617019920304321
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026618824218824241943042560016241111680x7fd4a98821000x7fd4a6825580299560299560219412396488655362164804262292872086765448017019920347060170199203026361701992068807517019920689830
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691882421882424194304256008241128960x7fd4a7223f800x7fd4a68255c0162441162441162051299536655361003612581192677040318630017019920731679170199206880751701992099191517019920993631
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027218824218824241943042560012241151360x7fd4a7223e000x7fd4a6825600228520228520194961828168655361559428981721727062551412017019921034580170199209919151701992133175417019921333412
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027518824218824241943042560012241166080x7fd4a7223c800x7fd4a682564016172316172315118129379265536965008041192708038774506017019921382040170199213317541701992163079317019921632563
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027818824218824241943042560016241183360x7fd4a7223b000x7fd4a6825680298307298307215652386464655362097644582280926084079769617019921674392170199216307931701992201559217019922017392
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028118824218824241943042560016241200640x7fd4a72239800x7fd4a68256c0298191298191214392385536655362159049892285082086535638417019922059011170199220155921701992241175117019922413661
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028418824218824241943042560012241217920x7fd4a72238000x7fd4a6825700164533164533165241316272655361000425911217850040191012417019922454709170199224117511701992271319017019922715032
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028718824218824241943042560012241240320x7fd4a72236800x7fd4a6825740237923237923199391903392655361670351441801814066988872017019922755431170199227131901701992306455017019923066602
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029018824218824241943042560012241255040x7fd4a98825000x7fd4a682578016144916144915348129160065536935918731189343037610325617019923115861170199230645501701992336742917019923369183
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029318824218824241943042560012241274880x7fd4a98823800x7fd4a68257c0298067298067204872384544655362053173052280812082300344017019923410852170199233674291701992375078817019923752522
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029618824218824241943042560012241292160x7fd4a98822000x7fd4a6825800300351300351207392402816655362028605912289812081317598817019923796111170199237507881701992413654717019924138231
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029918824218824241943042560012241309440x7fd4a98820800x7fd4a6825840169039169039155121352320655361032702771254107041482988817019924180680170199241365471701992444102617019924442752
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030218824218824241943042560012241334400x7fd4a7223f000x7fd4a6825880258821258821210592070576655361805422661963442072393617617019924484891170199244410261701992480102517019924802772
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030518824218824241943042560012241349120x7fd4a7223d800x7fd4a68258c016137716137715076129102465536981334571192008039426716417019924851861170199248010251701992510502517019925106673
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030818824218824241943042560012241368960x7fd4a7223c000x7fd4a6825900296691296691205162373536655361989363112264724079748503217019925147732170199251050251701992549366417019925495622
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031118824218824241943042560012241388800x7fd4a7223a800x7fd4a6825940297183297183213232377472655362136988392272864085653928417019925537061170199254936641701992587878317019925880601
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031418824218824241943042560012241408640x7fd4a72239000x7fd4a6825980178355178355164711426848655361054390061323191042350514817019925922350170199258787831701992620070217019926202732
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031718824218824241943042560012241436160x7fd4a72237800x7fd4a68259c0280283280283224872242272655361942114482130790077859792017019926244501170199262007021701992658678117019926588551
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032018824218824241943042560012241453440x7fd4a72236000x7fd4a6825a00161161161161151111289296655361038281081191034041704562417019926636930170199265867811701992689254017019926894152
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032318824218824241943042560012241475840x7fd4a98824800x7fd4a6825a40296477296477207382371824655362006440642263878080434515217019926940221170199268925401701992728517917019927286931
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032618824218824241943042560012241495680x7fd4a98823000x7fd4a6825a80295792295792208432366344655362055432102263088082391344817019927329410170199272851791701992767061917019927672430
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032918824218824241943042560012241515520x7fd4a98821800x7fd4a6825ac0187161187161177591497296655361135356571387980045589563217019927713099170199276706191701992799157817019927993341
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033218824218824241943042560012241543040x7fd4a98820000x7fd4a6825b00301126301126235602409016655361956839952297517078448746417019928035589170199279915781701992837989717019928381529
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033518824218824241943042560012241562880x7fd4a7223e800x7fd4a6825b4017283817283816831138271265536998775591272699040125560017019928430808170199283798971701992869269617019928694451
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033818824218824241943042560012241587840x7fd4a7223d000x7fd4a6825b80301854301854196912414840655361421697152276076057043144817019928735269170199286926961701992908325517019929085049
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034118824218824241943042560012241610240x7fd4a7223b800x7fd4a6825bc0298791298791206752390336655361893782552269517075925600017019929126528170199290832551701992947349417019929475318
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034418824218824241943042560012241632640x7fd4a7223a000x7fd4a6825c00204332204332182131634664655361313756711527534052725872817019929516117170199294734941701992979877317019929800689
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034718824218824241943042560012241665280x7fd4a72238800x7fd4a6825c40340143340143257462721152655362412322952610996096668688417019929841158170199297987731701993021205217019930260406
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035018824218824241943042560012241685120x7fd4a72237000x7fd4a6825c80184388184388174561475112655361123877191363915045129580417019930279635170199302120521701993056469217019930566547
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035318824218824241943042560012241712640x7fd4a98825800x7fd4a6825cc0294137294137201382353104655361931058292247784077417863617019930608576170199305646921701993094885117019930950496
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035618824218824241943042560012241737600x7fd4a98824000x7fd4a6825d00296040296040199462368328655361764521782260936070756158017019930993075170199309488511701993133525017019931337025
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035918824218824241943042560012241762560x7fd4a98822800x7fd4a6825d40225869225869197771806960655361426636161693625057241344017019931379484170199313352501701993167732917019931679115
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036218824218824241943042560012241797760x7fd4a98821000x7fd4a6825d803816883816882750530535126553627122101929395070108664009217019931721464170199316773291701993212084817019932166401
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036518824218824241943042560012241822720x7fd4a7223f800x7fd4a6825dc0210977210977184181687824655361298037801581665052096215617019932186530170199321208481701993247668717019932478582
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036818824218824241943042560012241855360x7fd4a7223e000x7fd4a6825e00309112309112236402472904655361846407612346017074033027617019932520181170199324766871701993287236617019932914309
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037118824218824241943042560012241885440x7fd4a7223c800x7fd4a6825e40310819310819215892486560655361861834292361326074650653617019932925889170199328723661701993329636517019933298288
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037418824218824241943042560012241915520x7fd4a7223b000x7fd4a6825e80266224266224212582129800655361696704902021152068044027617019933339257170199332963651701993366340417019933665208
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037718824218824241943042560012241958400x7fd4a72239800x7fd4a6825ec04625094625093129737000806553633197818135830260132967454017019933707527170199336634041701993415284317019934174633
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038018824218824241943042560012241985920x7fd4a72238000x7fd4a6825f00243308243308203401946472655361689637741843389067760950417019934205242170199341528431701993451924217019934520873
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038318824218824241943042560012242023680x7fd4a72236800x7fd4a6825f40335477335477235482683824655362163030142569221086698732417019934564502170199345192421701993493828117019934980730
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038618824218824241943042560012242058880x7fd4a98825000x7fd4a6825f80328686328686229702629496655362071132702513175083021844417019934992470170199349382811701993536964017019935411328
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038918824218824241943042560012242094080x7fd4a98823800x7fd4a6825fc0307135307135239812457088655362143189202344555085903486417019935422998170199353696401701993578483917019935786587
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039218824218824241943042560012242144640x7fd4a98822000x7fd4a68260005423845423843543143390806553640697251342257890162965426817019935828886170199357848391701993633171817019936373700
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039518824218824241943042560012242177280x7fd4a98820800x7fd4a6826040271653271653216182173232655361899266272066340076146205217019936394060170199363317181701993672355717019936725430
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039818824218824241943042560012242220160x7fd4a7223f000x7fd4a6826080365656365656264002925256655362395446022802159095996302417019936767519170199367235571701993715811617019937200167
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040118824218824241943042560012242260480x7fd4a7223d800x7fd4a68260c03671823671822918529374646553625369865528195890101656682817019937211696170199371581161701993761491517019937633424
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040418824218824241943042560012242300800x7fd4a7223c000x7fd4a6826100347284347284253742778280655362431279182665619097427791217019937658233170199376149151701993803699417019938055602
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040718824218824241943042560012242359040x7fd4a7223a800x7fd4a68261406238486238483954549907926553647697278448762020190966119617019938087101170199380369941701993864371217019938663674
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041018824218824241943042560012242394240x7fd4a72239000x7fd4a6826180303270303270228442426168655362063514382319175082717266817019938695814170199386437121701993904915117019939050853
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041318824218824241943042560012242442240x7fd4a72237800x7fd4a68261c03970243970242727531762006553627689705430679800110937450417019939092252170199390491511701993950467017019939522360
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041618824218824241943042560012242487680x7fd4a72236000x7fd4a68262003913223913222732431305846553629340883730270570117541738017019939550119170199395046701701993996402917019939980666
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041918824218824241943042560012242533120x7fd4a98824800x7fd4a68262403872163872162714930977366553627645393929897030110758640817019940007466170199399640291701994040850817019940427314
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221882421882424194304256008242555520x7fd4a98823000x7fd4a68262807188937188934489257511526553654090914456311570216537716017019940451463170199404085081701994106946617019941087035
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042518824218824241943042560012242598400x7fd4a98821800x7fd4a68262c03626923626922641029015446553626998897927970780108171847617019941121724170199410694661701994150818517019941524652
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042818824218824241943042560012242656640x7fd4a98820000x7fd4a68263004689254689253133937514086553635320668336463920141461057217019941558011170199415081851701994201922417019942036587
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043118824218824241943042560012242712320x7fd4a7223e800x7fd4a68263404719454719453166737755686553635306481636749540141403850017019942061736170199420192241701994255666317019942583791
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341882421882424194304256008242732160x7fd4a7223d000x7fd4a68263804826464826463249438611766553635091600237482790140540498017019942599371170199425566631701994306482217019943106176
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371882421882424194304256008242757120x7fd4a7223b800x7fd4a68263c08798608798605253170388886553667326687869256630269480870817019943117766170199430648221701994384290017019943884464
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044018824218824241943042560012242807680x7fd4a7223a000x7fd4a68264004268104268102938934144886553631836027133025210127520834417019943905024170199438429001701994433729917019944379180
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044318824218824241943042560012242876160x7fd4a72238800x7fd4a68264405486515486513519043892166553641161109942911960164823150817019944390770170199443372991701994491537717019944957113
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044618824218824241943042560012242942080x7fd4a72237000x7fd4a68264805507965507963588844063766553641829881743024850167497770017019944969823170199449153771701994548833617019945530227
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491882421882424194304256008242969600x7fd4a98825800x7fd4a68264c05642635642633643245141126553641368877343954850165649899217019945541717170199454883361701994606129417019946082871
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521882421882424194304256008242999680x7fd4a98824000x7fd4a6826500104166810416686115783333526553680863162182213910323626802817019946105760170199460612941701994693313217019946977205
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551882421882424194304256008243027200x7fd4a98822800x7fd4a68265407219777219774421257758246553654272444056589550217263842817019946996855170199469331321701994760577117019947654306
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045818824218824241943042560012243054720x7fd4a98821000x7fd4a68265807231727231724434057853846553655225307356718860221075447617019947666266170199476057851701994830034217019948342346
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046118824218824241943042560012243082240x7fd4a7223f800x7fd4a68265c07225137225134434057801126553654417412556593570217843768817019948353756170199483003421701994898578117019949028687
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641882421882424194304256008243109760x7fd4a7223e000x7fd4a68266007249007249004466557992086553655687169456912080222922755617019949040096170199489857811701994967521917019949719167
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671882421882424194304256008243132160x7fd4a7223c800x7fd4a6826640136665213666527686610933224655361073587196108141380429609052817019949730776170199496752191701995078657617019950832925
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701882421882424194304256008243159680x7fd4a7223b000x7fd4a6826680137060513706057740010964848655361079096524108498850431812790017019950853444170199507865761701995188817417019951954703
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047318824218824241943042560012243187200x7fd4a72239800x7fd4a68266c0137398313739837821510991872655361081142446108586130432631149617019951966762170199518881741701995304449117019953111700
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047618824218824241943042560012243214720x7fd4a72238000x7fd4a6826700137021913702197693210961760655361079430818108527900431946428417019953124029170199530444911701995419040817019954260837
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791882421882424194304256008243242240x7fd4a72236800x7fd4a6826740137594013759407735211007528655361087603614108921510435215702017019954273096170199541904081701995532224617019955389134
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821882421882424194304256008243264640x7fd4a98825000x7fd4a68267802661862266186214255521294904655362128760507211831290851678362017019955400884170199553222461701995728544117019957357258
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851882421882424194304256008243292160x7fd4a98823800x7fd4a68267c02669925266992514200421359408655362133316233212344630853500594817019957376547170199572854411701995922495617019959294972
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048818824218824241943042560012243319680x7fd4a98822000x7fd4a68268002668610266861014274021348888655362133378969212362910853525628417019959308242170199592249561701996122623217019961292545
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049118824218824241943042560012243347200x7fd4a98820800x7fd4a68268402668083266808314315921344672655362125348844212244170850313634017019961304345170199612262321701996321614717019963288077
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941882421882424194304256008243374720x7fd4a7223f000x7fd4a68268802672360267236014352221378888655362126093067212591790850611438017019963299897170199632161471701996516798217019965235301
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049718824218824241943042560082400x7fd4a7223d800x7fd4a68268c052579895257989273624420639206553642307583304192356301692477510017019965246801170199651679821701996879645417019968867607