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

41 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_VMEMSQ_INST_LEVEL_VMEMSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000195736195736335544322560043241600x00x7f56c0404280524288543186960836875617143202999529171408996559281714335599888517143356090154
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00219573619573632768256001224138880x00x7f56c0423f80409650189562758017143361212472171433559988851714336134480017143361349528
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051957361957364194304256001224143360x7f56cec933800x7f56c0423fc052428810921699122325114017143361384817171433613448001714336170576017143361708228
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081957361957364194304256001624150400x7f56cec932000x7f56c042400052428811444204128175938817143361744437171433617057601714336210943917143362111787
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111957361957364194304256001624154880x7f56cec930800x7f56c042404052428811537223129214174817143362143726171433621094391714336251087917143362513196
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141957361957364194304256001224159360x7f56cc4fbf000x7f56c042408052428811042243123670951617143362547135171433625108791714336281663917143362818857
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171957361957364194304256001224163840x7f56cc4fbd800x7f56c04240c052428811013283123348516017143362851056171433628166391714336312303917143363125399
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201957361957364194304256001224170880x7f56cc4fbc000x7f56c042410052428811345943127073959217143363168048171433631230391714336342687817143363429170
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231957361957364194304256001624177920x7f56cc4fba800x7f56c042414052428811523901129062284017143363460920171433634268781714336381743817143363819620
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261957361957364194304256001624184960x7f56cc4fb9000x7f56c042418052428811550749129367832017143363851499171433638174381714336420655817143364208859
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291957361957364194304256001624192000x7f56cc4fb7800x7f56c04241c052428811387128127533076017143364239358171433642065581714336452287817143364524960
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321957361957364194304256001624199040x7f56cc4fb6000x7f56c042420052428810975644122929925617143364556819171433645228781714336482863817143364830912
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351957361957364194304256001224206080x7f56cec934800x7f56c042424052428811186732125284940417143364870301171433648286381714336513263717143365134863
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381957361957364194304256001624213120x7f56cec933000x7f56c042428052428811618120130120304417143365166862171433651326371714336552271717143365524832
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411957361957364194304256001624220160x7f56cec931800x7f56c04242c052428811469889128457366817143365557822171433655227171714336591487717143365916922
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441957361957364194304256001624227200x7f56cec930000x7f56c042430052428811274899126278375217143365950081171433659148771714336623535717143366237993
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471957361957364194304256001224234240x7f56cc4fbe800x7f56c042434052428811194366125375047617143366268762171433662353571714336654783617143366550434
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501957361957364194304256001224241280x7f56cc4fbd000x7f56c042438052428811319988126786054417143366589203171433665478361714336685167617143366853716
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531957361957364194304256001624248320x7f56cc4fbb800x7f56c04243c052428811451327128253308417143366885785171433668516761714336724479617143367246785
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561957361957364194304256001624255360x7f56cc4fba000x7f56c042440052428811354284127166952817143367278154171433672447961714336761711617143367618715
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591957361957364194304256001224262400x7f56cc4fb8800x7f56c042444052428811176864125178790017143367650014171433676171161714336789775517143367899397
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621957361957364194304256001224269440x7f56cc4fb7000x7f56c042448052428810807427121036869617143367930516171433678977551714336817535517143368176939
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651957361957364194304256001224276480x7f56cec935800x7f56c04244c052428811189482125322749617143368216328171433681753551714336846031517143368461952
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681957361957364194304256001624286080x7f56cec934000x7f56c042450052428811486338128647556417143368493591171433684603151714336882991517143368831571
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711957361957364194304256001624293120x7f56cec932800x7f56c042454052428811343633127047386017143368863600171433688299151714336919359517143369195291
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741957361957364194304256001224300160x7f56cec931000x7f56c042458052428811083557124135165617143369227580171433691935951714336947103417143369472714
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077195736195736419430425600824309760x7f56cc4fbf800x7f56c04245c052428810767933120601061217143369504633171433694710341714336974847417143369750086
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801957361957364194304256001224316800x7f56cc4fbe000x7f56c042460052428811104559124376446817143369788265171433697484741714337002783417143370029488
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831957361957364194304256001624326400x7f56cc4fbc800x7f56c042464052428811457123128318550817143370061558171433700278341714337040607417143370407908
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861957361957364194304256001224336000x7f56cc4fbb000x7f56c042468052428811468034128438565617143370439807171433704060741714337077007317143370771818
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891957361957364194304256001224345600x7f56cc4fb9800x7f56c04246c052428811050033123757167217143370803347171433707700731714337104511317143371046790
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092195736195736419430425600824355200x7f56cc4fb8000x7f56c042470052428810825854121245036017143371078059171433710451131714337132031317143371321813
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951957361957364194304256001224362240x7f56cc4fb6800x7f56c042474052428811182173125240225217143371360172171433713203131714337159583317143371597445
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981957361957364194304256001224371840x7f56cec935000x7f56c042478052428811487573128655051217143371629334171433715958331714337197151317143371973195
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011957361957364194304256001224381440x7f56cec933800x7f56c04247c052428811361332127247935617143372005744171433719715131714337233551217143372337165
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041957361957364194304256001224391040x7f56cec932000x7f56c042480052428810875192121803360817143372368814171433723355121714337261327217143372614787
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107195736195736419430425600824403200x7f56cec930800x7f56c042484052428810067091112747318417143372646986171433726132721714337289135217143372892979
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101957361957364194304256001224412800x7f56cc4fbf000x7f56c042488052428810825919121243474817143372932108171433728913521714337318015217143373181921
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131957361957364194304256001224422400x7f56cc4fbd800x7f56c04248c052428811406676127752555217143373213660171433731801521714337354799217143373549641
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161957361957364194304256001224432000x7f56cc4fbc000x7f56c042490052428811520279129021586417143373581720171433735479921714337391983117143373921791
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119195736195736419430425600824441600x7f56cc4fba800x7f56c042494052428810582064118514334417143373952640171433739198311714337420303117143374204843
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221957361957364194304256001224453760x7f56cc4fb9000x7f56c04249805242889742985109127226017143374237432171433742030311714337448303117143374484775
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251957361957364194304256001224463360x7f56cc4fb7800x7f56c04249c052428810707176119916774417143374524474171433744830311714337476127117143374762937
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281957361957364194304256001224475520x7f56cc4fb6000x7f56c0424a0052428811315708126733309617143374794457171433747612711714337512431017143375125917
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311957361957364194304256001224485120x7f56cec934800x7f56c0424a4052428811297233126528451617143375158116171433751243101714337549327017143375494957
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134195736195736419430425600824494720x7f56cec933000x7f56c0424a8052428810654939119334460817143375526506171433754932701714337576975017143375771459
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371957361957364194304256001224506880x7f56cec931800x7f56c0424ac05242889250118103604191217143375803879171433757697501714337606191017143376063401
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401957361957364194304256001224516480x7f56cec930000x7f56c0424b0052428810613536118864736817143376102590171433760619101714337633727017143376338784
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431957361957364194304256001224528640x7f56cc4fbe800x7f56c0424b4052428811203364125474146017143376370123171433763372701714337670190917143376703664
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461957361957364194304256001224540800x7f56cc4fbd000x7f56c0424b8052428811418839127888824017143376735003171433767019091714337706702917143377068664
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149195736195736419430425600824552960x7f56cc4fbb800x7f56c0424bc052428810191291114137979617143377099743171433770670291714337734430917143377345906
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521957361957364194304256001224567680x7f56cc4fba000x7f56c0424c00524288769226886167132817143377377185171433773443091714337762302917143377624738
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551957361957364194304256001224577280x7f56cc4fb8800x7f56c0424c4052428810390129116367917617143377663397171433776230291714337789934917143377900761
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581957361957364194304256001224589440x7f56cc4fb7000x7f56c0424c8052428811375336127399706017143377931710171433778993491714337826318817143378264950
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611957361957364194304256001224601600x7f56cec935800x7f56c0424cc052428811300801126569272417143378297720171433782631881714337863086817143378632430
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164195736195736419430425600824613760x7f56cec934000x7f56c0424d0052428810005077112059151617143378664879171433786308681714337891422817143378915782
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671957361957364194304256001224628480x7f56cec932800x7f56c0424d40524288621088169559005617143378948012171433789142281714337919566817143379197345
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701957361957364194304256001224638080x7f56cec931000x7f56c0424d8052428810717864120039564017143379236994171433791956681714337947230717143379473867
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731957361957364194304256001224650240x7f56cc4fbf800x7f56c0424dc052428811338654126994450017143379505756171433794723071714337983582717143379837457
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761957361957364194304256001224662400x7f56cc4fbe000x7f56c0424e0052428811243507125923828817143379869166171433798358271714338019774717143380199407
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179195736195736419430425600824674560x7f56cc4fbc800x7f56c0424e405242889895612110826028417143380231156171433801977471714338047662717143380478309
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821957361957364194304256001224689280x7f56cc4fbb000x7f56c0424e80524288577124764642054017143380509858171433804766271714338076206717143380763611
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851957361957364194304256001224701440x7f56cc4fb9800x7f56c0424ec052428810040331112457552017143380802730171433807620671714338103838617143381040064
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881957361957364194304256001224716160x7f56cc4fb8000x7f56c0424f0052428811338849126992561217143381071683171433810383861714338139950617143381401184
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911957361957364194304256001224728320x7f56cc4fb6800x7f56c0424f4052428811258977126098791617143381432863171433813995061714338176718617143381768903
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194195736195736419430425600824740480x7f56cec935000x7f56c0424f8052428810041146112458002017143381800503171433817671861714338204638617143382047906
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971957361957364194304256001224757760x7f56cec933800x7f56c0424fc0524288491276655037224817143382087145171433820463861714338235294517143382354557
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001957361957364194304256001224769920x7f56cec932000x7f56c042500052428810260792114920627217143382393986171433823529451714338263102517143382632670
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031957361957364194304256001224784640x7f56cec930800x7f56c042504052428811243996125932168417143382663749171433826310251714338299678517143382998269
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061957361957364194304256001224799360x7f56cc4fbf000x7f56c042508052428811271850126241095217143383030229171433829967851714338336014517143383361789
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209195736195736419430425600824814080x7f56cc4fbd800x7f56c04250c05242889750090109198210417143383393178171433833601451714338363838517143383640022
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121957361957364194304256001224831360x7f56cc4fbc000x7f56c0425100524288411260246053406817143383672371171433836383851714338393326417143383935003
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151957361957364194304256001224843520x7f56cc4fba800x7f56c042514052428810316270115540835217143383983502171433839332641714338421102417143384212556
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181957361957364194304256001224858240x7f56cc4fb9000x7f56c042518052428811354906127172932817143384246505171433842110241714338457502417143384576476
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211957361957364194304256001224872960x7f56cc4fb7800x7f56c04251c052428811220914125670520417143384607925171433845750241714338494366417143384945176
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241957361957364194304256001224887680x7f56cc4fb6000x7f56c04252005242889348373104695456017143384975915171433849436641714338522542417143385227158
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271957361957364194304256001224907520x7f56cec934800x7f56c0425240524288393183744039600017143385258757171433852254241714338553294317143385534399
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301957361957364194304256001224919680x7f56cec933000x7f56c042528052428810049342112546384817143385573308171433855329431714338581214317143385813801
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331957361957364194304256001224934400x7f56cec931800x7f56c04252c052428811247014125963306817143385845441171433858121431714338617646317143386178331
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361957361957364194304256001224949120x7f56cec930000x7f56c042530052428811262766126139186017143386210570171433861764631714338654430317143386546051
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391957361957364194304256001224963840x7f56cc4fbe800x7f56c04253405242889315297104331741617143386577480171433865443031714338682126217143386822784
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421957361957364194304256001224983680x7f56cc4fbd000x7f56c0425380524288346708338826737217143386853693171433868212621714338713662217143387138285
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451957361957364194304256001224995840x7f56cc4fbb800x7f56c04253c05242889618224107710902817143387176784171433871366221714338742094217143387422617
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024819573619573641943042560012241013120x7f56cc4fba000x7f56c042540052428811148988124865526817143387453656171433874209421714338778766217143387789147
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025119573619573641943042560012241027840x7f56cc4fb8800x7f56c042544052428811253366126033722417143387820426171433877876621714338815326217143388154797
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025419573619573641943042560012241042560x7f56cc4fb7000x7f56c04254805242889025237101074916817143388186186171433881532621714338843182117143388433429
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025719573619573641943042560012241062400x7f56cec935800x7f56c04254c0524288328648836805990817143388465218171433884318211714338874638117143388747970
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026019573619573641943042560012241077120x7f56cec934000x7f56c04255005242889976536111743384417143388787909171433887463811714338902430117143389025903
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026319573619573641943042560016241094400x7f56cec932800x7f56c042554052428811121672124558749217143389057832171433890243011714338938654117143389388203
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026619573619573641943042560016241111680x7f56cec931000x7f56c042558052428811197953125416518817143389419302171433893865411714338975150017143389753002
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691957361957364194304256008241128960x7f56cc4fbf800x7f56c04255c0524288802568589892846417143389784772171433897515001714339002878017143390030555
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027219573619573641943042560012241151360x7f56cc4fbe000x7f56c0425600524288307769834469453217143390061434171433900287801714339035502017143390356846
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027519573619573641943042560012241166080x7f56cc4fbc800x7f56c04256405242889923467111145057217143390395965171433903550201714339063902017143390640648
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027819573619573641943042560016241183360x7f56cc4fbb000x7f56c042568052428811080032124094681217143390671787171433906390201714339100110017143391002728
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028119573619573641943042560016241200640x7f56cc4fb9800x7f56c04256c052428811154227124920930017143391034107171433910011001714339136221917143391363878
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028419573619573641943042560012241217920x7f56cc4fb8000x7f56c0425700524288713840479953882817143391394217171433913622191714339164189917143391643530
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028719573619573641943042560012241240320x7f56cc4fb6800x7f56c0425740524288289204932383801617143391675049171433916418991714339196749917143391969021
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029019573619573641943042560012241255040x7f56cec935000x7f56c04257805242889612605107659568417143392007490171433919674991714339224653917143392248013
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029319573619573641943042560012241274880x7f56cec933800x7f56c04257c052428811049345123751161617143392278893171433922465391714339260893817143392610663
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029619573619573641943042560012241292160x7f56cec932000x7f56c042580052428811073783124026646017143392642932171433926089381714339297133817143392972763
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029919573619573641943042560012241309440x7f56cec930800x7f56c0425840524288652739373105141217143393004912171433929713381714339325437817143393256095
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030219573619573641943042560012241334400x7f56cc4fbf000x7f56c0425880524288289538832425028817143393288275171433932543781714339359661817143393598256
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030519573619573641943042560012241349120x7f56cc4fbd800x7f56c04258c0524288863254696681196017143393638185171433935966181714339387437817143393876098
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030819573619573641943042560012241368960x7f56cc4fbc000x7f56c042590052428810989271123076611617143393907357171433938743781714339424461717143394246628
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031119573619573641943042560012241388800x7f56cc4fba800x7f56c042594052428811030330123535158417143394278977171433942446171714339461277717143394614438
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031419573619573641943042560012241408640x7f56cc4fb9000x7f56c0425980524288462392551792032417143394645247171433946127771714339489965717143394901170
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031719573619573641943042560012241436160x7f56cc4fb7800x7f56c04259c0524288286037332031508817143394932419171433948996571714339525133717143395252980
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032019573619573641943042560012241453440x7f56cc4fb6000x7f56c0425a00524288757407484832205617143395292339171433952513371714339552781617143395529343
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032319573619573641943042560012241475840x7f56cec934800x7f56c0425a4052428810837587121382905217143395560812171433955278161714339588909617143395890603
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032619573619573641943042560012241495680x7f56cec933000x7f56c0425a8052428810923312122340118817143395922932171433958890961714339626333617143396264982
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032919573619573641943042560012241515520x7f56cec931800x7f56c0425ac0524288374517341942828817143396296771171433962633361714339656349617143396565244
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033219573619573641943042560012241543040x7f56cec930000x7f56c0425b00524288284301631839156017143396596253171433965634961714339692653617143396928144
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033519573619573641943042560012241562880x7f56cc4fbe800x7f56c0425b40524288565304463312714817143396966993171433969265361714339720941517143397210976
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033819573619573641943042560012241587840x7f56cc4fbd000x7f56c0425b8052428810643167119201868817143397243135171433972094151714339757165517143397573316
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034119573619573641943042560012241610240x7f56cc4fbb800x7f56c0425bc052428810774177120669850417143397604555171433975716551714339793501517143397936706
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034419573619573641943042560012241632640x7f56cc4fba000x7f56c0425c00524288369090741333532417143397967045171433979350151714339824781517143398249877
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034719573619573641943042560012241665280x7f56cc4fb8800x7f56c0425c40524288286932732125612017143398281216171433982478151714339864045417143398662436
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035019573619573641943042560012241685120x7f56cc4fb7000x7f56c0425c80524288382287642809932417143398681385171433986404541714339895005417143398951638
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035319573619573641943042560012241712640x7f56cec935800x7f56c0425cc052428810402399116504247617143398983537171433989500541714339931581417143399317358
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035619573619573641943042560012241737600x7f56cec934000x7f56c0425d005242889902545110906950817143399349577171433993158141714339969021417143399691897
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035919573619573641943042560012241762560x7f56cec932800x7f56c0425d40524288278483531189132817143399723526171433996902141714340000765317143400009449
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036219573619573641943042560012241797760x7f56cec931000x7f56c0425d80524288286482432078380817143400041198171434000076531714340042157317143400442567
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036519573619573641943042560012241822720x7f56cc4fbf800x7f56c0425dc0524288308405634539826817143400463156171434004215731714340074125317143400742918
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036819573619573641943042560012241855360x7f56cc4fbe000x7f56c0425e00524288794285588954696417143400773557171434007412531714340111613317143401134127
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037119573619573641943042560012241885440x7f56cc4fbc800x7f56c0425e40524288771228186376368017143401149677171434011161331714340149613217143401513227
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037419573619573641943042560012241915520x7f56cc4fbb000x7f56c0425e80524288277137831026508017143401528636171434014961321714340184301217143401844538
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037719573619573641943042560012241958400x7f56cc4fb9800x7f56c0425ec0524288285007931910792017143401876067171434018430121714340231037217143402355184
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038019573619573641943042560012241985920x7f56cc4fb8000x7f56c0425f00524288270939230347963617143402375653171434023103721714340268093217143402682615
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038319573619573641943042560012242023680x7f56cc4fb6800x7f56c0425f40524288670410675084916017143402714084171434026809321714340307725117143403119773
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038619573619573641943042560012242058880x7f56cec935000x7f56c0425f80524288567921263602129617143403132342171434030772511714340349917117143403543871
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038919573619573641943042560012242094080x7f56cec933800x7f56c0425fc0524288276820031005500817143403555911171434034991711714340390093117143403902571
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039219573619573641943042560012242144640x7f56cec932000x7f56c0426000524288293056032824789217143403934670171434039009311714340441869017143404461026
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039519573619573641943042560012242177280x7f56cec930800x7f56c0426040524288281129531479990017143404480005171434044186901714340480029017143404802026
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039819573619573641943042560012242220160x7f56cc4fbf000x7f56c0426080524288586214365652312017143404833475171434048002901714340521261017143405254704
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040119573619573641943042560012242260480x7f56cc4fbd800x7f56c04260c0524288531206759496784017143405267114171434052126101714340565677017143405675032
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040419573619573641943042560012242300800x7f56cc4fbc000x7f56c0426100524288274806130773779217143405690022171434056567701714340605532917143406072681
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040719573619573641943042560012242359040x7f56cc4fba800x7f56c0426140524288291623632654926017143406095211171434060553291714340663900917143406686694
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041019573619573641943042560012242394240x7f56cc4fb9000x7f56c0426180524288278379131177814817143406706894171434066390091714340704908917143407050734
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041319573619573641943042560012242442240x7f56cc4fb7800x7f56c04261c0524288526219158933553617143407082333171434070490891714340748412817143407529071
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041619573619573641943042560012242487680x7f56cc4fb6000x7f56c0426200524288318288235649569217143407541301171434074841281714340794524817143407986828
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041919573619573641943042560012242533120x7f56cec934800x7f56c0426240524288274457930734025617143407998728171434079452481714340839324817143408434806
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221957361957364194304256008242555520x7f56cec933000x7f56c0426280524288238228726679956017143408445536171434083932481714340905660717143409099038
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042519573619573641943042560012242598400x7f56cec931800x7f56c04262c0524288274689730758689217143409118717171434090566071714340949276717143409534596
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042819573619573641943042560012242656640x7f56cec930000x7f56c0426300524288326647936583100017143409546805171434094927671714341001388717143410034132
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043119573619573641943042560012242712320x7f56cc4fbe800x7f56c0426340524288379420242493797217143410047121171434100138871714341052092617143410568507
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341957361957364194304256008242732160x7f56cc4fbd000x7f56c0426380524288241089026996543617143410580657171434105209261714341103980617143411083533
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371957361957364194304256008242757120x7f56cc4fbb800x7f56c04263c0524288238693126732372417143411095202171434110398061714341182044517143411863301
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044019573619573641943042560012242807680x7f56cc4fba000x7f56c0426400524288264397529612953217143411882631171434118204451714341230044517143412342728
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044319573619573641943042560012242876160x7f56cc4fb8800x7f56c0426440524288336765937709867617143412354077171434123004451714341286380517143412906232
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044619573619573641943042560012242942080x7f56cc4fb7000x7f56c0426480524288351243739336764017143412918732171434128638051714341342908417143413473227
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491957361957364194304256008242969600x7f56cec935800x7f56c04264c0524288239580026830256017143413485276171434134290841714341399468417143414012372
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521957361957364194304256008242999680x7f56cec934000x7f56c0426500524288239738826844184017143414028861171434139946841714341484812317143414892217
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551957361957364194304256008243027200x7f56cec932800x7f56c0426540524288239190326790828017143414912147171434148481231714341551132317143415553799
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045819573619573641943042560012243054720x7f56cec931000x7f56c0426580524288259148329034067217143415566089171434155113231714341618892217143416230450
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046119573619573641943042560012243082240x7f56cc4fbf800x7f56c04265c0524288259563229070268417143416243360171434161889221714341686252217143416904302
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641957361957364194304256008243109760x7f56cc4fbe000x7f56c0426600524288239501326823280417143416915321171434168625221714341753100117143417573583
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671957361957364194304256008243132160x7f56cc4fbc800x7f56c0426640524288240700726959045217143417585293171434175307351714341861217417143418666153
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701957361957364194304256008243159680x7f56cc4fbb000x7f56c0426680524288243348627258934017143418686672171434186121741714341969809117143419764822
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047319573619573641943042560012243187200x7f56cc4fb9800x7f56c04266c0524288258760428979794017143419777222171434196980911714342084033017143420904951
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047619573619573641943042560012243214720x7f56cc4fb8000x7f56c0426700524288259683929080744817143420917000171434208403301714342197216917143422037509
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791957361957364194304256008243242240x7f56cc4fb6800x7f56c0426740524288243352927253712817143422049809171434219721691714342309792717143423164828
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821957361957364194304256008243264640x7f56cec935000x7f56c0426780524288247446827712648017143423177438171434230979271714342504992517143425115434
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851957361957364194304256008243292160x7f56cec933800x7f56c04267c0524288245701827518658017143425136214171434250499251714342696480317143427040671
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048819573619573641943042560012243319680x7f56cec932000x7f56c0426800524288262382329386608817143427053361171434269648031714342895856017143429025696
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049119573619573641943042560012243347200x7f56cec930800x7f56c0426840524288262020429344788417143429037866171434289585601714343093599817143431003591
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941957361957364194304256008243374720x7f56cc4fbf000x7f56c0426880524288244884327422720817143431017051171434309359981714343286927517143432934278
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049719573619573641943042560082400x7f56cc4fbd800x7f56c04268c0524288250063828006291217143432946687171434328692751714343647695117143436553868