Dosyalar
rocm-systems/tests/workloads/Axes4/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.kd000218061218061335544322560043241600x00x7fba6d404280385123385123898130809925242882423861812992283098578168417521113721029175204026323171752126350762117521263620361
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00221806121806132768256001224138880x00x7fba6d423f8033238332382933726591251217045201651630683157617521268762179175212635076211752126890346717521268908505
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0052180612180614194304256001224143360x7fba704e83800x7fba6d423fc016570916570914915132568065536822474181216131033071973617521268951944175212689034671752126929514817521269297865
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0082180612180614194304256001624150400x7fba704e82000x7fba6d424000310419310419249612483360655362271291192374562091024565217521269342894175212692951481752126972202817521269724914
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00112180612180614194304256001624154880x7fba704e80800x7fba6d424040309979309979241112479840655362187766762368617087683757617521269767213175212697220281752127014154917521270144193
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00142180612180614194304256001224159360x7fba6de47f000x7fba6d42408016652416652413931133220065536793745321220376031922938417521270185722175212701415491752127047914917521270481495
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00172180612180614194304256001224163840x7fba6de47d800x7fba6d4240c016467416467414475131740065536842323091207022033865920417521270522214175212704791491752127081002917521270812586
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00202180612180614194304256001224170880x7fba6de47c000x7fba6d424100163337163337159501306704655361019094171200914040936874417521270866475175212708100291752127113931017521271141758
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00232180612180614194304256001624177920x7fba6de47a800x7fba6d424140308209308209251292465680655362239380622357619089748304017521271181517175212711393101752127156571017521271568167
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00262180612180614194304256001624184960x7fba6de479000x7fba6d424180308743308743218492469952655362144097682361657085936749217521271608526175212715657101752127198379117521271986156
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00292180612180614194304256001624192000x7fba6de477800x7fba6d4241c016533116533115356132265665536895578951213986035996096417521272026555175212719837911752127231019117521272312558
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00322180612180614194304256001624199040x7fba6de476000x7fba6d42420016581916581915216132656065536962551181219137038674853617521272353757175212723101911752127263579217521272638119
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00352180612180614194304256001224206080x7fba704e84800x7fba6d424240164555164555158991316448655361114834151210740044765793217521272689288175212726357921752127296299217521272965341
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00382180612180614194304256001624213120x7fba704e83000x7fba6d424280308819308819251612470560655362228284702362157089304469617521273007410175212729629921752127337611317521273378620
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00412180612180614194304256001624220160x7fba704e81800x7fba6d4242c0310259310259227112482080655362262640642376609090678493617521273419619175212733761131752127379051317521273793020
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00442180612180614194304256001624227200x7fba704e80000x7fba6d42430016533716533714684132270465536872248071218036035062920417521273834429175212737905131752127412539317521274127961
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00472180612180614194304256001224234240x7fba6de47e800x7fba6d42434016354816354815134130839265536970586851204941038996160817521274169540175212741253931752127445787417521274460343
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00502180612180614194304256001224241280x7fba6de47d000x7fba6d42438016295716295715214130366465536933573611199858037515396817521274510151175212744578741752127478235417521274784864
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00532180612180614194304256001624248320x7fba6de47b800x7fba6d4243c0311128311128252932489032655362302723062378341092281883217521274825323175212747823541752127519691517521275198684
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00562180612180614194304256001624255360x7fba6de47a000x7fba6d424400308701308701234072469616655362218205292358276088901550017521275240683175212751969151752127558299517521275584754
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00592180612180614194304256001224262400x7fba6de478800x7fba6d424440163506163506155561308056655361020766421205638041003627217521275625293175212755829951752127588955617521275891376
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00622180612180614194304256001224269440x7fba6de477000x7fba6d42448016370616370614548130965665536905148781199256036378672417521275931975175212758895561752127618715617521276189048
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00652180612180614194304256001224276480x7fba704e85800x7fba6d4244c0162565162565156991300528655361011732201198542040642807217521276238117175212761871561752127648987617521276491730
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00682180612180614194304256001624286080x7fba704e84000x7fba6d424500308281308281242142466256655362287641082362969091678668017521276532789175212764898761752127688011717521276881950
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00712180612180614194304256001624293120x7fba704e82800x7fba6d424540306821306821217582454576655362113148242345285084698814817521276923299175212768801171752127727435717521277276180
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00742180612180614194304256001224300160x7fba704e81000x7fba6d424580162313162313154651298512655361041623991197009041838170417521277317509175212772743571752127757099817521277572833
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077218061218061419430425600824309760x7fba6de47f800x7fba6d4245c016348516348515988130788865536911263911195999036624350417521277614762175212775709981752127786875817521277870615
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00802180612180614194304256001224316800x7fba6de47e000x7fba6d424600162751162751161141302016655361049829551197875042165268417521277918304175212778687581752127816731817521278169477
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00832180612180614194304256001624326400x7fba6de47c800x7fba6d424640306981306981242852455856655362271855612348550091047477617521278210776175212781673181752127855995917521278561807
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00862180612180614194304256001224336000x7fba6de47b000x7fba6d424680307395307395239902459168655362190056582341936087775308417521278602726175212785599591752127894715917521278949097
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00892180612180614194304256001224345600x7fba6de479800x7fba6d4246c0164347164347151971314784655361088317951209952043705076017521278988766175212789471591752127924572017521279247700
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092218061218061419430425600824355200x7fba6de478000x7fba6d42470016364316364315336130915265536917646201202722036878041617521279288749175212792457201752127954540017521279547262
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00952180612180614194304256001224362240x7fba6de476800x7fba6d424740163357163357150151306864655361052816091204981042284898017521279594781175212795454001752127984348117521279845224
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00982180612180614194304256001224371840x7fba704e85000x7fba6d424780305953305953241652447632655362281431242343948091430694817521279885743175212798434811752128022860117521280230344
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001012180612180614194304256001224381440x7fba704e83800x7fba6d4247c0308817308817236152470544655362227815122364250089285619217521280271203175212802286011752128061628217521280618454
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001042180612180614194304256001224391040x7fba704e82000x7fba6d42480016335516335514949130684865536940713991201966037801614417521280658493175212806162821752128091868217521280920517
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107218061218061419430425600824403200x7fba704e80800x7fba6d42484016341116341115385130729665536862660051198921034679636417521280960976175212809186821752128121836217521281220299
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001102180612180614194304256001224412800x7fba6de47f000x7fba6d424880163211163211156211305696655361072775531198517043083300017521281268758175212812183621752128151564317521281517551
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001132180612180614194304256001224422400x7fba6de47d800x7fba6d4248c0306455306455234572451648655362288580322349773091716051217521281558190175212815156431752128190716317521281908991
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001162180612180614194304256001224432000x7fba6de47c000x7fba6d424900306214306214230612449720655362194940282334860087970649217521281950170175212819071631752128230492417521282306881
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119218061218061419430425600824441600x7fba6de47a800x7fba6d42494016452416452414701131620065536973249861209833039102421217521282347920175212823049241752128260812417521282609863
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001222180612180614194304256001224453760x7fba6de479000x7fba6d42498016365616365615901130925665536929571381199106037355843217521282650452175212826081241752128290764417521282909346
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001252180612180614194304256001224463360x7fba6de477800x7fba6d4249c016426616426614551131413665536940205971207344037781272817521282957124175212829076441752128321292517521283214808
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001282180612180614194304256001224475520x7fba6de476000x7fba6d424a00305518305518245712444152655362235205242332457089581198017521283256077175212832129251752128359884517521283600738
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001312180612180614194304256001224485120x7fba704e84800x7fba6d424a40301314301314205072410520655361976836232298177079246391617521283642207175212835988451752128398316617521283985048
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134218061218061419430425600824494720x7fba704e83000x7fba6d424a8016341116341116172130729665536955747931194149038403330017521284025977175212839831661752128428236617521284284170
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001372180612180614194304256001224506880x7fba704e81800x7fba6d424ac016240216240216527129922465536981478401190943039432439217521284325549175212842823661752128457868617521284580483
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001402180612180614194304256001224516480x7fba704e80000x7fba6d424b0016068616068614757128549665536926663451181043037240439217521284629391175212845786861752128488044717521284882325
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001432180612180614194304256001224528640x7fba6de47e800x7fba6d424b40302633302633239222421072655362209657182309066088559190017521284922874175212848804471752128526940717521285271175
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001462180612180614194304256001224540800x7fba6de47d000x7fba6d424b80304311304311229852434496655362141770442320424085843838817521285310784175212852694071752128565820817521285659945
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149218061218061419430425600824552960x7fba6de47b800x7fba6d424bc016312816312815212130503265536930755251195759037402827217521285700344175212856582081752128595740817521285959267
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001522180612180614194304256001224567680x7fba6de47a000x7fba6d424c00162646162646162331301176655361007605481197663040477733217521285999626175212859574081752128626716917521286269149
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001552180612180614194304256001224577280x7fba6de478800x7fba6d424c4016166716166715012129334465536975800861189644039204803217521286317168175212862671691752128657740917521286579271
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001582180612180614194304256001224589440x7fba6de477000x7fba6d424c80303566303566239062428536655362197909182317182088089618017521286619050175212865774091752128696252917521286964572
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001612180612180614194304256001224601600x7fba704e85800x7fba6d424cc0302390302390224112419128655362121126872303956085017977217521287006840175212869625291752128734781017521287349742
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164218061218061419430425600824613760x7fba704e84000x7fba6d424d0016316116316115458130529665536919479101198303036952616417521287390551175212873478101752128764509017521287647204
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001672180612180614194304256001224628480x7fba704e82800x7fba6d424d40169975169975165361359808655361006766651251368040444614017521287687133175212876450901752128795869117521287960416
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001702180612180614194304256001224638080x7fba704e81000x7fba6d424d8016219516219515050129756865536889455331193907035750645217521288009965175212879586911752128826509117521288266858
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001732180612180614194304256001224650240x7fba6de47f800x7fba6d424dc0300726300726226942405816655362184060872297586087535656817521288308467175212882650911752128864765117521288649558
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001762180612180614194304256001224662400x7fba6de47e000x7fba6d424e00299197299197215992393584655362114450062286864084751446017521288690537175212886476511752128903037217521289032228
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179218061218061419430425600824674560x7fba6de47c800x7fba6d424e4016489216489214977131914465536913766291213259036723448417521289073057175212890303721752128932973217521289331481
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001822180612180614194304256001224689280x7fba6de47b000x7fba6d424e80176045176045166271408368655361011554481298720040636604017521289371650175212893297321752128963965317521289641503
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001852180612180614194304256001224701440x7fba6de479800x7fba6d424ec016141816141815221129135265536923035871185180037094500017521289689292175212896396531752128994957317521289951335
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001882180612180614194304256001224716160x7fba6de478000x7fba6d424f00306174306174238932449400655362275501192342804091193643617521289992274175212899495731752129034813417521290350055
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001912180612180614194304256001224728320x7fba6de476800x7fba6d424f40300120300120225862400968655362201715062293645088241614817521290390344175212903481341752129073773417521290739575
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194218061218061419430425600824740480x7fba704e85000x7fba6d424f8016026116026115179128209665536899290591177636036145080817521290780404175212907377341752129103613417521291037977
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001972180612180614194304256001224757760x7fba704e83800x7fba6d424fc0182238182238177201457912655361139263761348206045745337617521291078816175212910361341752129135053517521291352359
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002002180612180614194304256001224769920x7fba704e82000x7fba6d42500016233516233515586129868865536968581101191513038916626017521291412737175212913505351752129165789517521291660001
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002032180612180614194304256001224784640x7fba704e80800x7fba6d425040299276299276224982394216655362182728392289100087482342417521291700980175212916578951752129204269617521292044741
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002062180612180614194304256001224799360x7fba6de47f000x7fba6d425080300163300163230402401312655362195418622292767087989408417521292085560175212920426961752129243101617521292432951
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209218061218061419430425600824814080x7fba6de47d800x7fba6d4250c016232116232115511129857665536925044721191644037174492017521292472820175212924310161752129273213617521292733883
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002122180612180614194304256001224831360x7fba6de47c000x7fba6d425100191131191131182011529056655361275124401422980051179569617521292774312175212927321361752129305213717521293053895
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002152180612180614194304256001224843520x7fba6de47a800x7fba6d42514016244116244114858129953665536886537701194650035635264417521293102504175212930521371752129335245717521293354277
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002182180612180614194304256001224858240x7fba6de479000x7fba6d425180301233301233236292409872655362179992602303577087373961217521293395036175212933524571752129373597817521293737798
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002212180612180614194304256001224872960x7fba6de477800x7fba6d4251c0302347302347237582418784655362198792832304994088124630817521293778937175212937359781752129412109817521294122938
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002242180612180614194304256001224887680x7fba6de476000x7fba6d42520016238716238715762129910465536952700201194428038280952817521294163677175212941210981752129442829917521294430140
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002272180612180614194304256001224907520x7fba704e84800x7fba6d425240202540202540195261620328655361256507381506037050434490417521294469799175212944282991752129476253917521294764581
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002302180612180614194304256001224919680x7fba704e83000x7fba6d42528016122316122315127128979265536906541251184760036434737617521294813240175212947625391752129506573917521295067643
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002332180612180614194304256001224934400x7fba704e81800x7fba6d4252c0302585302585232912420688655362207770162313793088484014817521295113312175212950657391752129545934017521295461143
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002362180612180614194304256001224949120x7fba704e80000x7fba6d425300299022299022209422392184655362061576102284109082636390417521295503042175212954593401752129584638017521295848263
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002392180612180614194304256001224963840x7fba6de47e800x7fba6d42534016224916224915528129800065536961565681194807038635710417521295889002175212958463801752129615102117521296152846
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002422180612180614194304256001224983680x7fba6de47d000x7fba6d425380211007211007188141688064655361380646401579686055399792417521296192935175212961510211752129648270117521296484447
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002452180612180614194304256001224995840x7fba6de47b800x7fba6d4253c016076816076815357128615265536887507781183417035673500817521296532636175212964827011752129678414217521296785999
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024821806121806141943042560012241013120x7fba6de47a000x7fba6d425400299966299966239642399736655362173881142288231087128987617521296826378175212967841421752129717710217521297178979
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025121806121806141943042560012241027840x7fba6de478800x7fba6d425440299500299500220282396008655362010061162285417080575741217521297221468175212971771021752129756446217521297566179
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025421806121806141943042560012241042560x7fba6de477000x7fba6d42548016067016067015706128536865536976376171181865039228626417521297607058175212975644621752129786190317521297863772
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025721806121806141943042560012241062400x7fba704e85800x7fba6d4254c0218837218837196131750704655361466895791643344058850704017521297903761175212978619031752129820302317521298204923
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026021806121806141943042560012241077120x7fba704e84000x7fba6d42550016085616085615200128685665536873413801178803035110672417521298254172175212982030231752129850670417521298508505
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026321806121806141943042560016241094400x7fba704e82800x7fba6d425540300688300688230152405512655362146486862291776086033196817521298550954175212985067041752129889294417521298894755
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026621806121806141943042560016241111680x7fba704e81000x7fba6d425580302097302097225302416784655362121421382302036085030220417521298936484175212988929441752129928350517521299285265
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002692180612180614194304256008241128960x7fba6de47f800x7fba6d4255c0162606162606156081300856655361030885681195231041408786017521299333854175212992835051752129959086517521299592777
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027221806121806141943042560012241151360x7fba6de47e000x7fba6d425600231137231137199201849104655361330957101728478053412880417521299633486175212995908651752129993486517521299936668
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027521806121806141943042560012241166080x7fba6de47c800x7fba6d42564016124516124515096128996865536948293111181230038105030417521299984247175212999348651752130023838617521300240161
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027821806121806141943042560016241183360x7fba6de47b000x7fba6d425680297595297595212632380768655362135218952272126085582632417521300281550175213002383861752130062414617521300626061
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028121806121806141943042560016241200640x7fba6de479800x7fba6d4256c0297810297810213822382488655362049920392275575082170228417521300668780175213006241461752130101070717521301012551
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028421806121806141943042560012241217920x7fba6de478000x7fba6d425700163068163068159571304552655361041981951200763041852608017521301053130175213010107071752130131294717521301314893
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028721806121806141943042560012241240320x7fba6de476800x7fba6d425740239968239968212131919752655361579745641802589063364900017521301354982175213013129471752130166606817521301667944
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029021806121806141943042560012241255040x7fba704e85000x7fba6d425780161372161372156081290984655361000391031184524040189114017521301715913175213016660681752130196862817521301970456
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029321806121806141943042560012241274880x7fba704e83800x7fba6d4257c0297826297826219772382616655362072951922270039083091900417521302016025175213019686281752130237342817521302375196
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029621806121806141943042560012241292160x7fba704e82000x7fba6d425800299136299136216272393096655362086614842283794083638532417521302416815175213023734281752130276606917521302767926
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029921806121806141943042560012241309440x7fba704e80800x7fba6d425840170290170290164811362328655361076595101256838043237669617521302809365175213027660691752130306974917521303071618
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030221806121806141943042560012241334400x7fba6de47f000x7fba6d425880259898259898220052079192655361768516371963392070916213617521303112597175213030697491752130344175017521303443548
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030521806121806141943042560012241349120x7fba6de47d800x7fba6d4258c016159616159616233129277665536986298181182260039624888017521303491947175213034417501752130374399017521303745741
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030821806121806141943042560012241368960x7fba6de47c000x7fba6d425900296135296135216222369088655362036080092254506081616743617521303786950175213037439901752130413391117521304135761
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031121806121806141943042560012241388800x7fba6de47a800x7fba6d425940295362295362211652362904655362038716592253598081722998417521304177110175213041339111752130452495117521304526811
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031421806121806141943042560012241408640x7fba6de479000x7fba6d425980178773178773173001430192655361145125801321961045979720417521304567219175213045249511752130483663117521304838383
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031721806121806141943042560012241436160x7fba6de477800x7fba6d4259c0279060279060225992232488655361968398912126071078910736817521304878951175213048366311752130521007217521305211883
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032021806121806141943042560012241453440x7fba6de476000x7fba6d425a0016180216180215842129442465536997842061186942040087158817521305260752175213052100721752130551135217521305513205
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032321806121806141943042560012241475840x7fba704e84800x7fba6d425a40296429296429221312371440655362060443752258824082591932017521305555134175213055113521752130589999317521305901725
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032621806121806141943042560012241495680x7fba704e83000x7fba6d425a80296871296871216482374976655362090207472263669083782298817521305943984175213058999931752130629135317521306293325
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032921806121806141943042560012241515520x7fba704e81800x7fba6d425ac0187751187751181911502016655361115720801383242044803650817521306334334175213062913531752130661647417521306618357
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033221806121806141943042560012241543040x7fba704e80000x7fba6d425b00300457300457244012403664655362098021892285975084096614417521306659896175213066164741752130700223417521307004097
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033521806121806141943042560012241562880x7fba6de47e800x7fba6d425b40172887172887167401383104655361016550651270368040837485217521307052526175213070022341752130730879517521307310659
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033821806121806141943042560012241587840x7fba6de47d000x7fba6d425b80298713298713196522389712655361777225612255513071264276417521307351508175213073087951752130769551517521307697349
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034121806121806141943042560012241610240x7fba6de47b800x7fba6d425bc0298259298259198442386080655361839054242264289073737320017521307737878175213076955151752130808367517521308085489
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034421806121806141943042560012241632640x7fba6de47a000x7fba6d425c00207407207407196161659264655361285401711540206051591332017521308126058175213080836751752130841503617521308416921
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034721806121806141943042560012241665280x7fba6de478800x7fba6d425c40339863339863261972718912655362465872712608513098810420417521308457270175213084150361752130882719617521308873229
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035021806121806141943042560012241685120x7fba6de477000x7fba6d425c80185307185307179331482464655361047958521365317042093050817521308892448175213088271961752130917551717521309177331
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035321806121806141943042560012241712640x7fba704e85800x7fba6d425cc0297402297402207452379224655361915983162253116076815984817521309218450175213091755171752130956543717521309567231
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035621806121806141943042560012241737600x7fba704e84000x7fba6d425d00297510297510210232380088655361974478242262474079154030417521309608490175213095654371752130995599817521309957791
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035921806121806141943042560012241762560x7fba704e82800x7fba6d425d40225804225804196721806440655361435673031695172057603010417521309998080175213099559981752131031135817521310313342
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036221806121806141943042560012241797760x7fba704e81000x7fba6d425d803811283811282857230490326553627834620829283570111514134017521310353971175213103113581752131075327917521310799669
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036521806121806141943042560012241822720x7fba6de47f800x7fba6d425dc0210293210293189361682352655361425191631573538057182017617521310818599175213107532791752131111247917521311114241
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036821806121806141943042560012241855360x7fba6de47e000x7fba6d425e00309036309036257702472296655361746006832342270070015524817521311154840175213111124791752131151200017521311557740
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037121806121806141943042560012241885440x7fba6de47c800x7fba6d425e40310063310063227322480512655361817864652343267072891444017521311568290175213115120001752131193872017521311985019
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037421806121806141943042560012241915520x7fba6de47b000x7fba6d425e80266551266551223112132416655361805364872017876072390552817521311996419175213119387201752131233264117521312334460
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037721806121806141943042560012241958400x7fba6de479800x7fba6d425ec04618674618673204236949446553634422638535798990137867002817521312375499175213123326411752131282448117521312867406
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038021806121806141943042560012241985920x7fba6de478000x7fba6d425f00244209244209208311953680655361526358681836977061229784017521312887876175213128244811752131320336217521313205128
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038321806121806141943042560012242023680x7fba6de476800x7fba6d425f40335828335828233192686632655362124085002569576085140864817521313245887175213132033621752131361760217521313637307
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038621806121806141943042560012242058880x7fba704e85000x7fba6d425f80332859332859235652662880655362101223952538908084226868817521313662076175213136176021752131403920317521314057376
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038921806121806141943042560012242094080x7fba704e83800x7fba6d425fc0306010306010237082448088655362164092112337030086740205617521314088275175213140392031752131444512317521314446996
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039221806121806141943042560012242144640x7fba704e82000x7fba6d4260005429675429673618043437446553640603086242230950162589147217521314488655175213144451231752131499120417521315035311
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039521806121806141943042560012242177280x7fba704e80800x7fba6d426040274840274840223972198728655361710967452081915068615476817521315055080175213149912041752131538800517521315389802
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039821806121806141943042560012242220160x7fba6de47f000x7fba6d426080369321369321277332954576655362379508582827433095358399217521315430871175213153880051752131582320517521315866039
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040121806121806141943042560012242260480x7fba6de47d800x7fba6d4260c03669843669842867629358806553625241684528211140101144348817521315876729175213158232051752131627968617521316321888
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040421806121806141943042560012242300800x7fba6de47c000x7fba6d4261003461533461532577727692326553625334695526605840101515294417521316332867175213162796861752131671616617521316758456
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040721806121806141943042560012242359040x7fba6de47a800x7fba6d4261406243406243404067349947286553647461573048750710190023083617521316769026175213167161661752131733264717521317375171
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041021806121806141943042560012242394240x7fba6de479000x7fba6d426180302447302447234712419584655362205397522315732088392675617521317393970175213173326471752131775168717521317753631
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041321806121806141943042560012242442240x7fba6de477800x7fba6d4261c03984423984422795831875446553627482104130759660110106235617521317793490175213177516871752131821056817521318260968
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041621806121806141943042560012242487680x7fba6de476000x7fba6d4262003908073908072794031264646553628762559530153950115227601617521318272538175213182105681752131869664917521318740766
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041921806121806141943042560012242533120x7fba704e84800x7fba6d4262403876363876362808331010966553628848023529882210115569362017521318751945175213186966491752131916240917521319204824
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004222180612180614194304256008242555520x7fba704e83000x7fba6d4262807197837197834552657582726553653926178656331000215878744817521319215544175213191624091752131984305017521319885876
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042521806121806141943042560012242598400x7fba704e81800x7fba6d4262c03640733640732687629125926553626285485327972440105318186817521319906116175213198430501752132029825117521320340335
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042821806121806141943042560012242656640x7fba704e80000x7fba6d4263004703974703973188537631846553635544626636560960142357448017521320351415175213202982511752132082705117521320870021
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043121806121806141943042560012242712320x7fba6de47e800x7fba6d4263404736414736413316237891366553635105449136748540140600346017521320880651175213208270511752132136001217521321404028
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004342180612180614194304256008242732160x7fba6de47d000x7fba6d4263804829994829993291438640006553635667101337500070142842560017521321415367175213213600121752132188417317521321902955
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004372180612180614194304256008242757120x7fba6de47b800x7fba6d4263c08820438820435428070563526553668144794169229110272753377217521321926354175213218841731752132265905317521322705634
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044021806121806141943042560012242807680x7fba6de47a000x7fba6d4264004259194259192991434073606553631847670733014670127567298417521322726084175213226590531752132316849417521323212401
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044321806121806141943042560012242876160x7fba6de478800x7fba6d4264405508755508753606444070086553641224630242935090165077272417521323223281175213231684941752132375025517521323792976
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044621806121806141943042560012242942080x7fba6de477000x7fba6d4264805531425531423616244251446553641073185443137210164471296017521323804486175213237502551752132433329617521324375982
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004492180612180614194304256008242969600x7fba704e85800x7fba6d4264c05637285637283663645098326553642542639643927450170344987217521324387451175213243332961752132491009617521324952907
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004522180612180614194304256008242999680x7fba704e84000x7fba6d426500104422510442256270983538086553680573675182146720322469010417521324963376175213249100961752132580929717521325852154
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004552180612180614194304256008243027200x7fba704e82800x7fba6d4265407221967221964492257775766553654661363356575230218819675617521325871683175213258091861752132648726617521326535506
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045821806121806141943042560012243054720x7fba704e81000x7fba6d4265807243977243974471557951846553655922316456686810223863420817521326547126175213264872661752132718854617521327234298
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046121806121806141943042560012243082240x7fba6de47f800x7fba6d4265c07210407210404477157683286553655902799556604300223785298417521327245448175213271885461752132789510717521327940620
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004642180612180614194304256008243109760x7fba6de47e000x7fba6d4266007283657283654527058269286553655458158357003230222006930017521327951640175213278951071752132859206817521328637042
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004672180612180614194304256008243132160x7fba6de47c800x7fba6d426640136643013664307660610931448655361064724019108147240426063766817521328647882175213285920681752132970518917521329749444
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004702180612180614194304256008243159680x7fba6de47b000x7fba6d426680137247513724757844210979808655361073310860108459970429498523617521329768683175213297051891752133080967017521330877295
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047321806121806141943042560012243187200x7fba6de479800x7fba6d4266c0137172613717267794710973816655361081396385108570190432732693617521330889774175213308096701752133196615117521332032675
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047621806121806141943042560012243214720x7fba6de478000x7fba6d426700137176813717687755110974152655361079230490108441110431866310817521332044245175213319661511752133311543217521333181585
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004792180612180614194304256008243242240x7fba6de476800x7fba6d426740137524013752407714311001928655361077929989108857420431346216417521333192545175213331154321752133424295317521334313636
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004822180612180614194304256008243264640x7fba704e85000x7fba6d4267802665741266574114293721325936655362127702038211917570851255035617521334325066175213342429531752133622135517521336287706
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004852180612180614194304256008243292160x7fba704e83800x7fba6d4267c02668769266876914316521350160655362129538586212344660851989516417521336306495175213362213551752133815863717521338229356
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048821806121806141943042560012243319680x7fba704e82000x7fba6d4268002670605267060514309221364848655362131721793212398130852862786417521338241545175213381586371752134016551917521340233894
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049121806121806141943042560012243347200x7fba704e80800x7fba6d4268402668724266872414356421349800655362124285309212254210849888193617521340245254175213401655191752134216056117521342230613
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004942180612180614194304256008243374720x7fba6de47f000x7fba6d4268802673313267331314292021386512655362128188990212624380851449874017521342242533175213421605611752134411720317521344188383
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049721806121806141943042560082400x7fba6de47d800x7fba6d4268c052571845257184274650420574806553642290925394192631401691811193617521344199362175213441172031752134774696717521347820000