Dateien
rocm-systems/tests/workloads/LDS/mi100/SQ_IFETCH_LEVEL.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

46 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjGRBM_COUNTGRBM_GUI_ACTIVESQ_WAVESSQ_IFETCHSQ_IFETCH_LEVELSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000884232884237335544322560083264640x00x7f8d4aa04180503521503521524288629145679186710152764812075619663348244120756199115240591207561991184741712075619911960749
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00288423288423732768256002424124800x00x7f8d4aa35100280482804851281928896112538812075619926497405120756199268250171207561992683173712075619926840142
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0048842328842374194304256002424129280x7f8e566fa9000x7f8d4aa35140220203220203655369175041406831796830812075619926896707120756199271390961207561992727349512075619927276994
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0068842328842374194304256003624136320x7f8e566fa8000x7f8d4aa351803901133901136553612451841835912353779212075619927346653120756199275240541207561992777333212075619927844549
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0088842328842374194304256002824140800x7f8e566fa7000x7f8d4aa351c0399515399515655369830401371771750324812075619927877260120756199280787711207561992833252912075619928404169
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00108842328842374194304256002424145280x7f8e566fa6000x7f8d4aa352002186572186576553610485761585642025921212075619928423645120756199286333281207561992876788712075619928770710
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00128842328842374194304256002424149760x7f8e566fa5000x7f8d4aa35240221091221091655369830401495851911174412075619928824801120756199290035661207561992913844512075619929141539
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00148842328842374194304256002424154240x7f8e566fa4000x7f8d4aa352802085852085856553610485761467221879903212075619929218192120756199293933241207561992952084312075619929523689
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00168842328842374194304256002824161280x7f8e566fa3000x7f8d4aa352c03949953949956553615728642290142922225612075619929576377120756199297614821207561993001252112075619930057872
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00188842328842374194304256002824168320x7f8e566faa000x7f8d4aa353003938733938736553611796481586952027918012075619930080725120756199302838791207561993053491812075619930603316
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00208842328842374194304256002424175360x7f8e566fa9000x7f8d4aa353402162192162196553611141121611162064862412075619930629785120756199308245161207561993095651612075619930959257
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00228842328842374194304256002424182400x7f8e566fa8000x7f8d4aa353802203372203376553611141121662672123456812075619931015352120756199312003541207561993133587412075619931338933
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00248842328842374194304256002424189440x7f8e566fa7000x7f8d4aa353c02128672128676553611796481681762148448012075619931404916120756199315784321207561993170851212075619931711105
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00268842328842374194304256002824199040x7f8e566fa6000x7f8d4aa354003993613993616553618350082556753279765212075619931763021120756199319437111207561993219922912075619932269623
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00288842328842374194304256002824206080x7f8e566fa5000x7f8d4aa354403983073983076553613107201783362284513612075619932295300120756199324878681207561993274162612075619932810698
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00308842328842374194304256002424213120x7f8e566fa4000x7f8d4aa354802074252074256553612451841725072218554412075619932837548120756199330309051207561993315826412075619933161029
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00328842328842374194304256002424220160x7f8e566fa3000x7f8d4aa354c02093632093636553613107201832322351276812075619933215080120756199334030631207561993353026212075619933533091
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00348842328842374194304256002424227200x7f8e566faa000x7f8d4aa355002167692167696553613107201893062430548812075619933597701120756199337737811207561993390722012075619933909941
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00368842328842374194304256002824236800x7f8e566fa9000x7f8d4aa355404020514020516553620971522915853731632412075619933960916120756199341537791207561993441057812075619934454934
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00388842328842374194304256002824243840x7f8e566fa8000x7f8d4aa355803969773969776553614417921934862480699612075619934479179120756199346715361207561993492545512075619934993655
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00408842328842374194304256002424250880x7f8e566fa7000x7f8d4aa355c02198672198676553613762562039382607912012075619935017559120756199352185731207561993535313312075619935356389
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00428842328842374194304256002424257920x7f8e566fa6000x7f8d4aa356002716332716336553615073282093062676354412075619935408937120756199355814511207561993575201112075619935754760
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00448842328842374194304256002424264960x7f8e566fa5000x7f8d4aa356402135232135236553614417922048482625305212075619935817917120756199359931291207561993612256912075619936125849
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00468842328842374194304256002824277120x7f8e566fa4000x7f8d4aa356803931933931936553623592963175414079762412075619936176764120756199363614471207561993661344612075619936682494
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00488842328842374194304256002824284160x7f8e566fa3000x7f8d4aa356c03906353906356553615728642109012700218412075619936709153120756199369014441207561993714976312075619937218680
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00508842328842374194304256002424291200x7f8e566faa000x7f8d4aa357002115372115376553615073282062072641243612075619937244558120756199374427221207561993757232112075619937575233
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00528842328842374194304256002424300800x7f8e566fa9000x7f8d4aa357402138032138036553617039362377823047997212075619937628612120756199378080001207561993793903912075619937941814
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00548842328842374194304256002424307840x7f8e566fa8000x7f8d4aa357802131052131056553615728642123902720397212075619938013698120756199381868781207561993831775712075619938320909
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00568842328842374194304256002824320000x7f8e566fa7000x7f8d4aa357c04074914074916553626214403572064584620012075619938372665120756199385553561207561993881615412075619938885127
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00588842328842374194304256002824329600x7f8e566fa6000x7f8d4aa358003910013910016553617039362314012954863612075619938912268120756199391185531207561993936927212075619939439427
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00608842328842374194304256002424339200x7f8e566fa5000x7f8d4aa358402136512136516553616384002449733129088812075619939464724120756199396561501207561993978702912075619939789728
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00628842328842374194304256002424348800x7f8e566fa4000x7f8d4aa358802129612129616553619005442655843389052412075619939841434120756199400313481207561994016286712075619940166038
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00648842328842374194304256002424358400x7f8e566fa3000x7f8d4aa358c02101312101316553617039362468223152475612075619940229946120756199404054261207561994053358512075619940536496
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00668842328842374194304256002824373120x7f8e566faa000x7f8d4aa359003891773891776553628835843902774994958812075619940587912120756199407740641207561994102302312075619941092850
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00688842328842374194304256002824382720x7f8e566fa9000x7f8d4aa359403978113978116553618350082444523133487612075619941118678120756199413116611207561994156526012075619941609440
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00708842328842374194304256002424392320x7f8e566fa8000x7f8d4aa359802099372099376553617694722578623305040012075619941635909120756199418303791207561994195981812075619941962697
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00728842328842374194304256002424401920x7f8e566fa7000x7f8d4aa359c02117872117876553620971523172304066291612075619942024452120756199422002971207561994233021612075619942333085
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00748842328842374194304256002424411520x7f8e566fa6000x7f8d4aa35a002160652160656553618350082482503174487612075619942395661120756199425695751207561994270253412075619942705527
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00768842328842374194304256002824426240x7f8e566fa5000x7f8d4aa35a404044194044196553631457284357895586639212075619942757854120756199429356531207561994319421112075619943264676
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00788842328842374194304256002824435840x7f8e566fa4000x7f8d4aa35a804009294009296553619660802598363338336812075619943290605120756199434871701207561994374380912075619943813056
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00808842328842374194304256002424445440x7f8e566fa3000x7f8d4aa35ac02183472183476553619005442596893323368812075619943844113120756199440487671207561994418268612075619944185658
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00828842328842374194304256002424457600x7f8e566faa000x7f8d4aa35b002145532145536553622937603141494023008812075619944230662120756199444233251207561994455628412075619944559302
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00848842328842374194304256002424467200x7f8e566fa9000x7f8d4aa35b402146672146676553619660802981043811498412075619944622239120756199447945231207561994492588212075619944928859
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00868842328842374194304256002824484480x7f8e566fa8000x7f8d4aa35b804046734046736553634078724534765814394412075619944981086120756199451673211207561994542764012075619945473371
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00888842328842374194304256002824494080x7f8e566fa7000x7f8d4aa35bc04554754554756553620971522781053552138012075619945501063120756199456905181207561994598251712075619946052908
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00908842328842374194304256002424503680x7f8e566fa6000x7f8d4aa35c002112092112096553620316162815253611551212075619946075751120756199462709951207561994639979512075619946402668
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00928842328842374194304256002424515840x7f8e566fa5000x7f8d4aa35c402209632209636553624903683428924393046412075619946454114120756199466309931207561994676795312075619946770862
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00948842328842374194304256002424525440x7f8e566fa4000x7f8d4aa35c802133852133856553620971522966763794117212075619946835923120756199470085911207561994713963112075619947142904
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00968842328842374194304256002824542720x7f8e566fa3000x7f8d4aa35cc04093794093796553636700164905386283859612075619947196073120756199473799491207561994764330812075619947713474
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00988842328842374194304256002824554880x7f8e566faa000x7f8d4aa35d003983453983456553622282242986523821519212075619947741386120756199479290671207561994818442512075619948255662
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001008842328842374194304256002424567040x7f8e566fa9000x7f8d4aa35d402147872147876553621626883159744043998812075619948280759120756199484733841207561994860538312075619948608548
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001028842328842374194304256002424581760x7f8e566fa8000x7f8d4aa35d802208892208896553626869763919665008094012075619948661336120756199488413821207561994897834112075619948981321
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001048842328842374194304256002424593920x7f8e566fa7000x7f8d4aa35dc02136832136836553622282243058323911883612075619949044508120756199492175401207561994934921912075619949352430
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001068842328842374194304256002824613760x7f8e566fa6000x7f8d4aa35e003988333988336553639321605433036934910012075619949404397120756199495836181207561994984009612075619949910097
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001088842328842374194304256002824625920x7f8e566fa5000x7f8d4aa35e403903553903556553623592963133274008650012075619949934933120756199501320951207561995038233412075619950451783
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001108842328842374194304256002424638080x7f8e566fa4000x7f8d4aa35e802155452155456553622937603307924238009212075619950476359120756199506680921207561995080073112075619950803788
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001128842328842374194304256002424652800x7f8e566fa3000x7f8d4aa35ec02239952239956553628835844120555252568412075619950855173120756199510439301207561995118344912075619951186839
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001148842328842374194304256002424664960x7f8e566faa000x7f8d4aa35f002123132123136553623592963244694153506812075619951251600120756199514237681207561995155400712075619951556877
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001168842328842374194304256002824684800x7f8e566fa9000x7f8d4aa35f404021954021956553641943045643467212195212075619951600939120756199517848861207561995204408512075619952115165
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001188842328842374194304256002824696960x7f8e566fa8000x7f8d4aa35f803938973938976553624903683278014205278812075619952140932120756199523311231207561995258408212075619952653906
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001208842328842374194304256002424709120x7f8e566fa7000x7f8d4aa35fc02145472145476553624248323395284347212012075619952680686120756199528648811207561995299704012075619952999959
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001228842328842374194304256002424723840x7f8e566fa6000x7f8d4aa360002255932255936553630801925234446703166412075619953052567120756199532339991207561995337383812075619953377020
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001248842328842374194304256002424736000x7f8e566fa5000x7f8d4aa360402085392085396553624903683437954404194412075619953440287120756199536115971207561995373975612075619953742830
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001268842328842374194304256002824758400x7f8e566fa4000x7f8d4aa360804103614103616553644564485904897541742412075619953794756120756199539720751207561995423623312075619954306357
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001288842328842374194304256002824770560x7f8e566fa3000x7f8d4aa360c03931633931636553626214403419864387811212075619954331033120756199545250321207561995477767112075619954846911
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001308842328842374194304256002424782720x7f8e566faa000x7f8d4aa361002185212185216553625559043954085065837212075619954871417120756199550749491207561995520950812075619955212892
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001328842328842374194304256002424800000x7f8e566fa9000x7f8d4aa361402313312313316553632768005276976748525212075619955264588120756199554431071207561995558758612075619955590804
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001348842328842374194304256002424812160x7f8e566fa8000x7f8d4aa361802113692113696553626214403612394621343612075619955653781120756199558250251207561995595526412075619955958197
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001368842328842374194304256002824834560x7f8e566fa7000x7f8d4aa361c04089394089396553647185926361738141855212075619956015363120756199561949431207561995645926212075619956530150
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001388842328842374194304256002824849280x7f8e566fa6000x7f8d4aa362003980653980656553627525123611064611637612075619956554385120756199567434201207561995699877912075619957044666
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001408842328842374194304256002424864000x7f8e566fa5000x7f8d4aa362402107872107876553626869763864594954905612075619957067068120756199572627771207561995739221712075619957395498
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001428842328842374194304256002424881280x7f8e566fa4000x7f8d4aa362802400732400736553634734084848816207686012075619957447935120756199576194161207561995776901512075619957772158
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001448842328842374194304256002424896000x7f8e566fa3000x7f8d4aa362c02148272148276553627525124015425138316812075619957856324120756199580350931207561995816789312075619958171370
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001468842328842374194304256002824920960x7f8e566faa000x7f8d4aa363004004014004016553649807366569398431855212075619958223877120756199584083711207561995866709012075619958716192
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001488842328842374194304256002824935680x7f8e566fa9000x7f8d4aa363403948673948676553628835843833524892541612075619958741279120756199589288491207561995918324712075619959235588
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001508842328842374194304256002424950400x7f8e566fa8000x7f8d4aa363802215772215776553628180484317495532022812075619959260835120756199594496461207561995958468512075619959587732
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001528842328842374194304256002424967680x7f8e566fa7000x7f8d4aa363c02505712505716553636700165166116600451212075619959641482120756199598208441207561995997828312075619959981474
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001548842328842374194304256002424982400x7f8e566fa6000x7f8d4aa364002153452153456553628835843946095056848012075619960047907120756199602200421207561996035220112075619960355559
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015688423288423741943042560028241007360x7f8e566fa5000x7f8d4aa364404100914100916553651773446827578761850812075619960406985120756199605845201207561996085011912075619960873482
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015888423288423741943042560028241022080x7f8e566fa4000x7f8d4aa364803880333880336553630146564181255348813612075619960918896120756199610949171207561996134515612075619961395672
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016088423288423741943042560024241036800x7f8e566fa3000x7f8d4aa364c02166032166036553629491204173085343561212075619961419386120756199616137951207561996174803412075619961750942
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016288423288423741943042560024241056640x7f8e566faa000x7f8d4aa365002651932651936553638666245952817583639612075619961804782120756199619845131207561996215107212075619962154863
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016488423288423741943042560024241071360x7f8e566fa9000x7f8d4aa365402112192112196553630146563974735084745212075619962220204120756199623958711207561996252611012075619962529329
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016688423288423741943042560028241098880x7f8e566fa8000x7f8d4aa365804105854105856553654394887450819516698412075619962581165120756199627633891207561996302882712075619963080102
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016888423288423741943042560028241113600x7f8e566fa7000x7f8d4aa365c03909553909556553631457284162865333105612075619963100420120756199632937861207561996354578412075619963595691
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017088423288423741943042560024241128320x7f8e566fa6000x7f8d4aa366002211612211616553630801924875986245086012075619963620347120756199638176231207561996395426212075619963957203
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017288423288423741943042560024241148160x7f8e566fa5000x7f8d4aa366402757392757396553640632325520437024212412075619964014449120756199641869011207561996436050012075619964364009
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017488423288423741943042560024241162880x7f8e566fa4000x7f8d4aa366802210732210736553631457284555595827960412075619964430111120756199645993791207561996473585812075619964738835
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017688423288423741943042560028241190400x7f8e566fa3000x7f8d4aa366c03962273962276553657016327813159961798012075619964791263120756199649708971207561996522721612075619965278648
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017888423288423741943042560028241207680x7f8e566faa000x7f8d4aa367003931933931936553632768004357415578833212075619965306781120756199654955341207561996574913312075619965798715
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018088423288423741943042560024241224960x7f8e566fa9000x7f8d4aa367402252992252996553632112644703896017173212075619965822439120756199660110521207561996615073112075619966154216
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018288423288423741943042560024241247360x7f8e566fa8000x7f8d4aa367802892572892576553642598406071827728570812075619966208517120756199663848101207561996656752912075619966570469
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018488423288423741943042560024241264640x7f8e566fa7000x7f8d4aa367c02203152203156553632768004765216093701612075619966635380120756199668056071207561996694224712075619966945206
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018688423288423741943042560020241279360x7f8e566fa6000x7f8d4aa3680040895340895365536773324897883512502080812075619966997493120756199671844851207561996745008412075619967474219
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018888423288423741943042560028241296640x7f8e566fa5000x7f8d4aa368403986913986916553634078724519805760104412075619967519373120756199676864031207561996794384112075619967992161
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019088423288423741943042560024241313920x7f8e566fa4000x7f8d4aa368802110652110656553633423364876256243019612075619968016046120756199682190401207561996834927912075619968352601
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019288423288423741943042560024241336320x7f8e566fa3000x7f8d4aa368c03028433028436553644564486641568497516012075619968406020120756199685839981207561996877647712075619968825179
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019488423288423741943042560024241353600x7f8e566faa000x7f8d4aa369002190492190496553635389445323906811314412075619968862338120756199690401561207561996917519512075619969178546
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019688423288423741943042560020241368320x7f8e566fa9000x7f8d4aa36940436163436163655368978432112856414453465612075619969232456120756199694052741207561996968943212075619969738377
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019888423288423741943042560028241385600x7f8e566fa8000x7f8d4aa369803966733966736553636700164951346335681212075619969764665120756199699499111207561997020623012075619970256359
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020088423288423741943042560024241402880x7f8e566fa7000x7f8d4aa369c02130912130916553636044805557987110202812075619970283359120756199704710281207561997060270712075619970605799
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020288423288423741943042560024241427840x7f8e566fa6000x7f8d4aa36a003293213293216553648496647216119268709212075619970658527120756199708385461207561997104814512075619971097923
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020488423288423741943042560024241447680x7f8e566fa5000x7f8d4aa36a402211072211076553638010885601537183768412075619971139601120756199713108641207561997144830312075619971451370
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020688423288423741943042560020241457280x7f8e566fa4000x7f8d4aa36a804730814730816553614548992182603623385579612075619971503297120756199716855821207561997199470012075619972046596
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020888423288423741943042560028241477120x7f8e566fa3000x7f8d4aa36ac03983873983876553639321605109646526322412075619972073436120756199722626991207561997252061712075619972570079
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021088423288423741943042560024241496960x7f8e566faa000x7f8d4aa36b002225292225296553638666245422226939274412075619972593833120756199727831761207561997292109512075619972924177
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021288423288423741943042560024241521920x7f8e566fa9000x7f8d4aa36b403566193566196553652428807677689866467212075619972975823120756199731610941207561997338925312075619973440817
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021488423288423741943042560024241541760x7f8e566fa8000x7f8d4aa36b802255452255456553640632326375578160192812075619973481162120756199736506911207561997379053112075619973794224
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021688423288423741943042560020241556480x7f8e566fa7000x7f8d4aa36bc05034995034996553610027008125619616124910412075619973845950120756199740297291207561997435948812075619974409538
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021888423288423741943042560028241576320x7f8e566fa6000x7f8d4aa36c004064654064656553641943045565317105069212075619974433432120756199746256881207561997488920712075619974915318
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022088423288423741943042560024241596160x7f8e566fa5000x7f8d4aa36c402153072153076553641287685892597533540412075619974956254120756199751335251207561997526696412075619975269205
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022288423288423741943042560024241623680x7f8e566fa4000x7f8d4aa36c8038244938244965536563609680157910274175612075619975322805120756199755074431207561997575288212075619975801224
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022488423288423741943042560024241646080x7f8e566fa3000x7f8d4aa36cc02242272242276553645875206496778314051612075619975839215120756199760098411207561997614952112075619976152186
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022688423288423741943042560020241663360x7f8e566faa000x7f8d4aa36d005760095760096553611075584139388617857872412075619976204213120756199763876001207561997676551812075619976813806
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022888423288423741943042560028241685760x7f8e566fa9000x7f8d4aa36d404039714039716553647185926564468388444412075619976837450120756199770338371207561997729639612075619977346927
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023088423288423741943042560024241708160x7f8e566fa8000x7f8d4aa36d802227692227696553646530566889808815518012075619977370701120756199775640751207561997770247512075619977704431
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023288423288423741943042560024241740800x7f8e566fa7000x7f8d4aa36dc043408343408365536642252891117611732382812075619977755847120756199779330341207561997821351312075619978263650
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023488423288423741943042560024241765760x7f8e566fa6000x7f8d4aa36e002234892234896553651118087766369932762012075619978303484120756199784776721207561997861719112075619978619211
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023688423288423741943042560020241777920x7f8e566fa5000x7f8d4aa36e406425076425076553615007744188825524151504412075619978670697120756199788477501207561997927142812075619979319994
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023888423288423741943042560028241802880x7f8e566fa4000x7f8d4aa36e804063214063216553652428807733449909453612075619979346212120756199795418271207561997980550612075619979828408
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024088423288423741943042560024241827840x7f8e566fa3000x7f8d4aa36ec022546722546765536517734481972510494446412075619979877660120756199800563851207561998019670512075619980199458
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024288423288423741943042560024241863040x7f8e566faa000x7f8d4aa36f00488241488241655367208960105613213464197612075619980251925120756199804357441207561998075126312075619980800014
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024488423288423741943042560024241893120x7f8e566fa9000x7f8d4aa36f4024240324240365536616038488596611340947612075619980836833120756199810082221207561998116006112075619981162628
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024688423288423741943042560020241907840x7f8e566fa8000x7f8d4aa36f807847057847056553617104896214574227467628412075619981220476120756199813970201207561998191461812075619981963697
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024888423288423741943042560028241937920x7f8e566fa7000x7f8d4aa36fc045294745294765536629145682843810636883212075619981988052120756199821877371207561998248357612075619982533536
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025088423288423741943042560024241968000x7f8e566fa6000x7f8d4aa3700024612124612165536622592089645711471001612075619982564042120756199827565351207561998291077412075619982913011
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025288423288423741943042560024242010880x7f8e566fa5000x7f8d4aa37040592211592211655368781824126535316235869612075619982965679120756199831616531207561998354757212075619983596231
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025488423288423741943042560024242046080x7f8e566fa4000x7f8d4aa37080278257278257655367208960108424413882248412075619983634672120756199838070911207561998398341012075619983985785
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025688423288423741943042560020242060800x7f8e566fa3000x7f8d4aa370c09250999250996553619202048239824030820883612075619984038533120756199842194091207561998483060712075619984880287
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025888423288423741943042560028242096000x7f8e566faa000x7f8d4aa3710049760149760165536734003297600212551164412075619984902929120756199851024461207561998542820412075619985479351
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026088423288423741943042560024242131200x7f8e566fa9000x7f8d4aa37140282243282243655367274496108320113856356412075619985503465120756199856930031207561998587268312075619985874795
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026288423288423741943042560024242181760x7f8e566fa8000x7f8d4aa371806986336986336553610354688147981218847439212075619985926451120756199861170021207561998657300012075619986622305
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026488423288423741943042560024242222080x7f8e566fa7000x7f8d4aa371c0313707313707655368257536123798115841350012075619986663070120756199868352391207561998703587812075619987084954
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026688423288423741943042560020242239360x7f8e566fa6000x7f8d4aa37200106582510658256553621299200266945234152870412075619987109991120756199873056371207561998800867412075619988062992
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026888423288423741943042560028242279680x7f8e566fa5000x7f8d4aa37240567147567147655368388608110996614188339612075619988089151120756199882840331207561998865811212075619988708011
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027088423288423741943042560024242320000x7f8e566fa4000x7f8d4aa37280317753317753655368323072126335416176798412075619988731775120756199889214711207561998912451012075619989175970
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027288423288423741943042560024242378240x7f8e566fa3000x7f8d4aa372c08028438028436553611927552166968621533840012075619989200656120756199893912291207561998991778712075619989968203
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027488423288423741943042560024242423680x7f8e566faa000x7f8d4aa37300348489348489655369306112138341417717518412075619990012375120756199901859461207561999040946512075619990459275
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027688423288423741943042560020242435840x7f8e566fa9000x7f8d4aa37340120618712061876553629163520365863646801668012075619990484743120756199906745841207561999147346112075619991542418
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027888423288423741943042560028242481280x7f8e566fa8000x7f8d4aa37380638353638353655369437184135887417292697212075619991567475120756199917584201207561999217969812075619992249653
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028088423288423741943042560024242526720x7f8e566fa7000x7f8d4aa373c0352843352843655369371648137496617607023212075619992281081120756199924782571207561999270545612075619992774729
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028288423288423741943042560024242592640x7f8e566fa6000x7f8d4aa374009076259076256553613500416190641924271877612075619992803101120756199929968151207561999359297312075619993663981
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028488423288423741943042560024242648320x7f8e566fa5000x7f8d4aa374404177314177316553611403264172991522137744412075619993700820120756199938832111207561999415329012075619994222690
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028688423288423741943042560020242663040x7f8e566fa4000x7f8d4aa37480149026514902656553633357824417792553499333612075619994248357120756199944401691207561999542608512075619995496827
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028888423288423741943042560028242718720x7f8e566fa3000x7f8d4aa374c07789237789236553611534336165092321083317612075619995525190120756199957187241207561999623552212075619996305240
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029088423288423741943042560024242774400x7f8e566faa000x7f8d4aa375004201294201296553611534336170615721839389612075619996336097120756199965310411207561999680320012075619996872414
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029288423288423741943042560012242799360x7f8e566fa9000x7f8d4aa37540112583511258356553619267584241950231004888812075619996898803120756199970996791207561999783839612075619997909221
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029488423288423741943042560024242865280x7f8e566fa8000x7f8d4aa375804878094878096553613500416205866726337982412075619997945238120756199981287951207561999844511412075619998514646
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029688423288423741943042560020242880000x7f8e566fa7000x7f8d4aa375c0176725117672516553637552128469006260171082812075619998539001120756199987307121207561999990046812075619999970351
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029888423288423741943042560032242945920x7f8e566fa6000x7f8d4aa376009179299179296553613631488189204524300382412075620000008091120756200002015871207562000081070412075620000880543
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030088423288423741943042560024243011840x7f8e566fa5000x7f8d4aa376404913794913796553613631488207089626501218012075620000904918120756200011199831207562000143982212075620001510834
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030288423288423741943042560012243049600x7f8e566fa4000x7f8d4aa37680133548913354896553621692416273714335036537212075620001542954120756200017275011207562000260589712075620002675829
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030488423288423741943042560024243136000x7f8e566fa3000x7f8d4aa376c06356356356356553617694720286339336641922812075620002721685120756200028990161207562000331277512075620003381791
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030688423288423741943042560020243148160x7f8e566faa000x7f8d4aa37700233086523308656553657475072719553592088295612075620003412619120756200036066931207562000515548712075620005224356
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030888423288423741943042560020243175680x7f8e566fa9000x7f8d4aa37740119986711998676553619660800246476931575026412075620005256335120756200054426861207562000623724312075620006305795
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031088423288423741943042560012243203200x7f8e566fa8000x7f8d4aa377806383376383376553620381696257707632995359212075620006329620120756200065287621207562000694348012075620007021115
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031288423288423741943042560012243240960x7f8e566fa7000x7f8d4aa377c0175753117575316553628704768361327046211015612075620007054327120756200072401191207562000839851512075620008466471
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031488423288423741943042560012243288960x7f8e566fa6000x7f8d4aa37800119663311966336553636634624463777859349054012075620008505223120756200086777141207562000946347112075620009531641
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031688423288423741943042560020243301120x7f8e566fa5000x7f8d4aa37840458364345836436553610584064013243266169495511212075620009565053120756200097559491207562001280393712075620012878160
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031888423288423741943042560020243328640x7f8e566fa4000x7f8d4aa37880232248123224816553638535168484718561951327212075620012904870120756200131266561207562001466841012075620014739429
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032088423288423741943042560012243356160x7f8e566fa3000x7f8d4aa378c0120318712031876553639124992491628362930150012075620014769836120756200149644091207562001575400612075620015824516
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032288423288423741943042560012243393920x7f8e566faa000x7f8d4aa37900344173734417376553655771136700248589619063212075620015856144120756200160554451207562001833719612075620018407786
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032488423288423741943042560012243441920x7f8e566fa9000x7f8d4aa379402323091232309165536725483529111196116650351212075620018453131120756200186293551207562002016486912075620020233439
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032688423288423741943042560020243454080x7f8e566fa8000x7f8d4aa37980908659390865936553621069824026354033337263357612075620020265008120756200204571881207562002650996412075620026579734
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032888423288423741943042560020243481600x7f8e566fa7000x7f8d4aa379c04573299457329965536762839049545049122278386412075620026612715120756200268013231207562002984307112075620029919330
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033088423288423741943042560012243509120x7f8e566fa6000x7f8d4aa37a002326745232674565536773980169697038124120998012075620029944036120756200301712301207562003170994412075620031783845
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332884232884237419430425600122400x7f8e566fa5000x7f8d4aa37a40681344368134436553611082137613886160177768898012075620031811907120756200320325021207562003655936512075620036631164