Files
rocm-systems/tests/workloads/SQ/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.kd000138430138430335544322560043241600x00x7f80e4204280524288541530560643954815905219297983159042740917221590536424262015905364355920
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00213843013843032768256001224138880x00x7f80e4223f80409633999381251215905369523304159053642426201590536964631115905369651142
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051384301384304194304256001224143360x7f8102aa63800x7f80e4223fc052428810729326120159096815905369686011159053696463111590537001719215905370019713
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081384301384304194304256001624150400x7f8102aa62000x7f80e422400052428811327223126863011615905370056213159053700171921590537044071315905370443104
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111384301384304194304256001624154880x7f8102aa60800x7f80e422404052428811509533128907362815905370474253159053704407131590537083303415905370835315
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141384301384304194304256001224159360x7f8100407f000x7f80e422408052428810633450119088082415905370867444159053708330341590537113319515905371135178
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171384301384304194304256001224163840x7f8100407d800x7f80e42240c052428810996336123151481215905371168318159053711331951590537143207515905371434342
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201384301384304194304256001224170880x7f8100407c000x7f80e422410052428810845856121461332415905371477421159053714320751590537173015615905371732115
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231384301384304194304256001624177920x7f8100407a800x7f80e422414052428811611708130047455215905371763584159053717301561590537211703715905372119036
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261384301384304194304256001624184960x7f81004079000x7f80e422418052428811503077128830929215905372150946159053721170371590537249959815905372501908
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291384301384304194304256001624192000x7f81004077800x7f80e42241c052428810901544122099425615905372532437159053724995981590537280983815905372811841
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321384301384304194304256001624199040x7f81004076000x7f80e422420052428810946516122599717215905372843660159053728098381590537310743915905373109714
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351384301384304194304256001224206080x7f8102aa64800x7f80e422424052428810829691121289112015905373148803159053731074391590537340376015905373406138
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381384301384304194304256001624213120x7f8102aa63000x7f80e422428052428811436021128081210015905373438497159053734037601590537378792015905373790039
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411384301384304194304256001624220160x7f8102aa61800x7f80e42242c052428811564608129521157615905373821428159053737879201590537417592115905374178350
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441384301384304194304256001624227200x7f8102aa60000x7f80e422430052428811189624125316276415905374209470159053741759211590537448264215905374484764
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471384301384304194304256001224234240x7f8100407e800x7f80e422434052428810762012120530919215905374516173159053744826421590537476552315905374767087
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501384301384304194304256001224241280x7f8100407d000x7f80e422438052428811269583126215751215905374805406159053747655231590537503560315905375037281
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531384301384304194304256001624248320x7f8100407b800x7f80e42243c052428811353289127157828815905375068831159053750356031590537539256415905375394153
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561384301384304194304256001624255360x7f8100407a000x7f80e422440052428811281912126354943615905375425783159053753925641590537575416515905375755845
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591384301384304194304256001224262400x7f81004078800x7f80e422444052428810531155117947516015905375786485159053757541651590537602440515905376026099
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621384301384304194304256001224269440x7f81004077000x7f80e422448052428810763005120544013215905376057089159053760244051590537629528615905376296763
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651384301384304194304256001224276480x7f8102aa65800x7f80e42244c052428811029121123523506415905376335782159053762952861590537656824715905376569807
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681384301384304194304256001624286080x7f8102aa64000x7f80e422450052428811404114127724493615905376601856159053765682471590537692456715905376926109
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711384301384304194304256001624293120x7f8102aa62800x7f80e422454052428811439736128127631215905376956938159053769245671590537728376815905377285311
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741384301384304194304256001224300160x7f8102aa61000x7f80e422458052428810700266119848997615905377317030159053772837681590537755256915905377554155
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077138430138430419430425600824309760x7f8100407f800x7f80e42245c052428810515261117763708415905377585544159053775525691590537781992915905377821489
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801384301384304194304256001224316800x7f8100407e000x7f80e422460052428811230690125778456415905377859618159053778199291590537808649015905378088613
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831384301384304194304256001624326400x7f8100407c800x7f80e422464052428811376641127415044015905378119932159053780864901590537845177115905378453175
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861384301384304194304256001224336000x7f8100407b000x7f80e422468052428811465081128404730415905378484394159053784517711590537881721215905378818637
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891384301384304194304256001224345600x7f81004079800x7f80e42246c052428810711739119970602815905378850366159053788172121590537908649215905379088091
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092138430138430419430425600824355200x7f81004078000x7f80e422470052428810444816116987497615905379119180159053790864921590537935545315905379356845
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951384301384304194304256001224362240x7f81004076800x7f80e422474052428810653427119314134415905379395164159053793554531590537962505315905379626699
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981384301384304194304256001224371840x7f8102aa65000x7f80e422478052428811363464127268018015905379657598159053796250531590537998137415905379982891
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011384301384304194304256001224381440x7f8102aa63800x7f80e42247c052428811429139128004994415905380014380159053799813741590538033865515905380340123
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041384301384304194304256001224391040x7f8102aa62000x7f80e422480052428810748229120376332015905380371023159053803386551590538060745615905380608957
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107138430138430419430425600824403200x7f8102aa60800x7f80e422484052428810084419112937712015905380640647159053806074561590538087785615905380879421
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101384301384304194304256001224412800x7f8100407f000x7f80e422488052428810572337118407404815905380918300159053808778561590538115289715905381154475
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131384301384304194304256001224422400x7f8100407d800x7f80e42248c052428811281654126353518415905381185394159053811528971590538151097815905381512577
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161384301384304194304256001224432000x7f8100407c000x7f80e422490052428811466965128429769215905381544257159053815109781590538186809815905381869769
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119138430138430419430425600824441600x7f8100407a800x7f80e422494052428810659108119378072415905381900519159053818680981590538214105915905382142543
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221384301384304194304256001224453760x7f81004079000x7f80e42249805242889663516108229693215905382174783159053821410591590538242026015905382421917
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251384301384304194304256001224463360x7f81004077800x7f80e42249c052428810661162119407264015905382459606159053824202601590538269018015905382691751
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281384301384304194304256001224475520x7f81004076000x7f80e4224a0052428811394873127618452815905382724200159053826901801590538304634115905383047953
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311384301384304194304256001224485120x7f8102aa64800x7f80e4224a4052428811164456125040699215905383079652159053830463411590538340682215905383408445
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134138430138430419430425600824494720x7f8102aa63000x7f80e4224a8052428810454700117093163215905383439334159053834068221590538367866215905383680209
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371384301384304194304256001224506880x7f8102aa61800x7f80e4224ac05242888948498100216673215905383712238159053836786621590538395402315905383955713
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401384301384304194304256001224516480x7f8102aa60000x7f80e4224b0052428810355777115987304815905383994762159053839540231590538422250415905384223967
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431384301384304194304256001224528640x7f8100407e800x7f80e4224b4052428811292445126471993215905384254476159053842225041590538458010415905384581639
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461384301384304194304256001224540800x7f8100407d000x7f80e4224b8052428811292143126467368015905384612998159053845801041590538493626515905384938011
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149138430138430419430425600824552960x7f8100407b800x7f80e4224bc052428810098590113095735615905384968560159053849362651590538520842615905385209995
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521384301384304194304256001224567680x7f8100407a000x7f80e4224c00524288779727787329826015905385240734159053852084261590538547818615905385479899
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551384301384304194304256001224577280x7f81004078800x7f80e4224c4052428810755352120464668415905385518058159053854781861590538575178715905385753363
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581384301384304194304256001224589440x7f81004077000x7f80e4224c8052428811374716127394759215905385785412159053857517871590538610922815905386110945
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611384301384304194304256001224601600x7f8102aa65800x7f80e4224cc052428811357877127208208815905386142804159053861092281590538647082915905386472486
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164138430138430419430425600824613760x7f8102aa64000x7f80e4224d0052428810356869115998484415905386504076159053864708291590538674602915905386747490
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671384301384304194304256001224628480x7f8102aa62800x7f80e4224d40524288597835166959623215905386778770159053867460291590538702251015905387023984
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701384301384304194304256001224638080x7f8102aa61000x7f80e4224d8052428810327234115656384815905387063103159053870225101590538729675015905387298378
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731384301384304194304256001224650240x7f8100407f800x7f80e4224dc052428811137390124733164415905387329567159053872967501590538765547115905387657030
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761384301384304194304256001224662400x7f8100407e000x7f80e4224e0052428811307237126642126815905387687979159053876554711590538800955215905388011162
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179138430138430419430425600824674560x7f8100407c800x7f80e4224e405242889859491110422843215905388041571159053880095521590538827851315905388280056
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821384301384304194304256001224689280x7f8100407b000x7f80e4224e80524288609315868248266815905388311465159053882785131590538855595315905388557620
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851384301384304194304256001224701440x7f81004079800x7f80e4224ec052428810065096112728671615905388595329159053885559531590538882427415905388825894
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881384301384304194304256001224716160x7f81004078000x7f80e4224f0052428811257814126083163215905388856673159053888242741590538917835515905389179856
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911384301384304194304256001224728320x7f81004076800x7f80e4224f4052428811341378127022432815905389211115159053891783551590538953883515905389540488
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194138430138430419430425600824740480x7f8102aa65000x7f80e4224f8052428810015996112176787215905389571487159053895388351590538981115615905389812752
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971384301384304194304256001224757760x7f8102aa63800x7f80e4224fc0524288433632948565752415905389843371159053898111561590539009595715905390097636
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001384301384304194304256001224769920x7f8102aa62000x7f80e422500052428810303940115404645615905390136895159053900959571590539037499715905390376549
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031384301384304194304256001224784640x7f8102aa60800x7f80e422504052428811176530125173800815905390408489159053903749971590539073627815905390737921
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061384301384304194304256001224799360x7f8100407f000x7f80e422508052428811238827125870397615905390769300159053907362781590539109195915905391093443
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209138430138430419430425600824814080x7f8100407d800x7f80e42250c05242889703910108681056415905391124793159053910919591590539136187915905391363487
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121384301384304194304256001224831360x7f8100407c000x7f80e4225100524288373337441813710015905391394297159053913618791590539164908015905391650681
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151384301384304194304256001224843520x7f8100407a800x7f80e422514052428810179251114005174415905391700060159053916490801590539193164115905391933104
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181384301384304194304256001224858240x7f81004079000x7f80e422518052428811127583124627628815905391964824159053919316411590539229228115905392294036
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211384301384304194304256001224872960x7f81004077800x7f80e42251c052428811086678124167720815905392324866159053922922811590539265708215905392658608
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241384301384304194304256001224887680x7f81004076000x7f80e42252005242889355424104777821615905392689568159053926570821590539292828315905392929852
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271384301384304194304256001224907520x7f8102aa64800x7f80e4225240524288357945440083513215905392960542159053929282831590539322252415905393223996
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301384301384304194304256001224919680x7f8102aa63000x7f80e422528052428810000739112007964015905393262685159053932225241590539349340415905393494970
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331384301384304194304256001224934400x7f8102aa61800x7f80e42252c052428811230665125784143215905393526369159053934934041590539385372515905393855352
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361384301384304194304256001224949120x7f8102aa60000x7f80e422530052428811188439125309093615905393886501159053938537251590539420876615905394210944
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391384301384304194304256001224963840x7f8100407e800x7f80e42253405242889079339101684125215905394242163159053942087661590539448572615905394487388
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421384301384304194304256001224983680x7f8100407d000x7f80e4225380524288354409339686843215905394518167159053944857261590539478492715905394786421
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451384301384304194304256001224995840x7f8100407b800x7f80e42253c05242889894000110809655615905394824680159053947849271590539505884815905395060505
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024813843013843041943042560012241013120x7f8100407a000x7f80e422540052428811188817125311091215905395091814159053950588481590539541868815905395420247
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025113843013843041943042560012241027840x7f81004078800x7f80e422544052428811172719125131278815905395451126159053954186881590539577804915905395779589
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025413843013843041943042560012241042560x7f81004077000x7f80e4225480524288883373398938345615905395810438159053957780491590539604765015905396049363
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025713843013843041943042560012241062400x7f8102aa65800x7f80e42254c0524288325029636394539615905396080242159053960476501590539635933115905396361126
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026013843013843041943042560012241077120x7f8102aa64000x7f80e42255005242889801829109777783615905396400805159053963593311590539662845115905396630070
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026313843013843041943042560016241094400x7f8102aa62800x7f80e422554052428811054912123810363215905396662519159053966284511590539698429215905396985892
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026613843013843041943042560016241111680x7f8102aa61000x7f80e422558052428811191459125338821215905397017461159053969842921590539734253315905397344104
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691384301384304194304256008241128960x7f8100407f800x7f80e42255c0524288814682091232811215905397375323159053973425331590539761949315905397621048
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027213843013843041943042560012241151360x7f8100407e000x7f80e4225600524288307727934467611215905397651597159053976194931590539793197415905397933471
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027513843013843041943042560012241166080x7f8100407c800x7f80e42256405242889758428109288864015905397971630159053979319741590539822189515905398223665
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027813843013843041943042560016241183360x7f8100407b000x7f80e422568052428811106411124385104815905398256264159053982218951590539858077515905398582507
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028113843013843041943042560016241200640x7f81004079800x7f80e42256c052428811012724123337639615905398613726159053985807751590539893661615905398938249
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028413843013843041943042560012241217920x7f81004078000x7f80e4225700524288693580977680855215905398968808159053989366161590539920765715905399209193
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028713843013843041943042560012241240320x7f81004076800x7f80e4225740524288294197532950745615905399239892159053992076571590539952701815905399528515
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029013843013843041943042560012241255040x7f8102aa65000x7f80e42257805242889046482101314955215905399566985159053995270181590539979709815905399798609
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029313843013843041943042560012241274880x7f8102aa63800x7f80e42257c052428810935144122471194015905399829529159053997970981590540015149915905400153242
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029613843013843041943042560012241292160x7f8102aa62000x7f80e422580052428811061106123883541215905400184871159054001514991590540050654015905400507974
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029913843013843041943042560012241309440x7f8102aa60800x7f80e4225840524288607431368032115615905400538923159054005065401590540078110015905400782707
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030213843013843041943042560012241334400x7f8100407f000x7f80e4225880524288284076331809774015905400814457159054007811001590540111678115905401118470
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030513843013843041943042560012241349120x7f8100407d800x7f80e42258c0524288818180691636558815905401158039159054011167811590540138926215905401390884
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030813843013843041943042560012241368960x7f8100407c000x7f80e422590052428811025951123488804815905401421763159054013892621590540174350215905401745176
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031113843013843041943042560012241388800x7f8100407a800x7f80e422594052428811032309123559790415905401776185159054017435021590540209870315905402100598
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031413843013843041943042560012241408640x7f81004079000x7f80e4225980524288448512750231214815905402131797159054020987031590540238526415905402386822
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031713843013843041943042560012241436160x7f81004077800x7f80e42259c0524288285120531930343215905402417991159054023852641590540272990515905402731584
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032013843013843041943042560012241453440x7f81004076000x7f80e4225a00524288751148984129599615905402770693159054027299051590540299902515905403000698
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032313843013843041943042560012241475840x7f8102aa64800x7f80e4225a4052428810910131122193671615905403031597159054029990251590540335518615905403356570
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032613843013843041943042560012241495680x7f8102aa63000x7f80e4225a8052428810810349121074460415905403388339159054033551861590540370942715905403711062
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032913843013843041943042560012241515520x7f8102aa61800x7f80e4225ac0524288363670140730591215905403743111159054037094271590540400062715905404002176
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033213843013843041943042560012241543040x7f8102aa60000x7f80e4225b00524288283291031717253615905404033755159054040006271590540435598815905404357538
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033513843013843041943042560012241562880x7f8100407e800x7f80e4225b40524288576135464527493615905404396157159054043559881590540463854915905404640241
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033813843013843041943042560012241587840x7f8100407d000x7f80e4225b805242889795422109707504415905404670491159054046385491590540499599015905404997603
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034113843013843041943042560012241610240x7f8100407b800x7f80e4225bc052428810867055121714490015905405028853159054049959901590540535343015905405355085
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034413843013843041943042560012241632640x7f8100407a000x7f80e4225c00524288358388640130058815905405384995159054053534301590540565055115905405652099
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034713843013843041943042560012241665280x7f81004078800x7f80e4225c40524288282860931680199215905405682678159054056505511590540603263215905406052700
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035013843013843041943042560012241685120x7f81004077000x7f80e4225c80524288393650644082828015905406072469159054060326321590540633311315905406334783
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035313843013843041943042560012241712640x7f8102aa65800x7f80e4225cc05242889792857109676910015905406365803159054063331131590540669151315905406693136
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035613843013843041943042560012241737600x7f8102aa64000x7f80e4225d005242889712545108781474815905406724785159054066915131590540705647415905407058037
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035913843013843041943042560012241762560x7f8102aa62800x7f80e4225d40524288276105830925046415905407088727159054070564741590540736767515905407369291
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036213843013843041943042560012241797760x7f8102aa61000x7f80e4225d80524288284980931917420015905407400580159054073676751590540777503615905407821011
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036513843013843041943042560012241822720x7f8100407f800x7f80e4225dc0524288299606033554620015905407840420159054077750361590540811343715905408115034
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036813843013843041943042560012241855360x7f8100407e000x7f80e4225e00524288806737490351873215905408145183159054081134371590540847887715905408525215
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037113843013843041943042560012241885440x7f8100407c800x7f80e4225e40524288788018588258044015905408536845159054084788771590540888447815905408902667
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037413843013843041943042560012241915520x7f8100407b000x7f80e4225e80524288277206031039220015905408916966159054088844781590540922479915905409226489
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037713843013843041943042560012241958400x7f81004079800x7f80e4225ec0524288279759031328984415905409257109159054092247991590540968496015905409703329
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038013843013843041943042560012241985920x7f81004078000x7f80e4225f00524288295990433147568815905409726038159054096849601590541001680115905410018472
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038313843013843041943042560012242023680x7f81004076800x7f80e4225f40524288678745276015643215905410048831159054100168011590541042560215905410453822
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038613843013843041943042560012242058880x7f8102aa65000x7f80e4225f80524288575175364417941215905410465252159054104256021590541082448315905410866973
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038913843013843041943042560012242094080x7f8102aa63800x7f80e4225fc0524288280907731451362415905410877873159054108244831590541121712315905411218705
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039213843013843041943042560012242144640x7f8102aa62000x7f80e4226000524288291812732677145215905411250064159054112171231590541172864515905411771913
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039513843013843041943042560012242177280x7f8102aa60800x7f80e4226040524288273966730678628815905411790932159054117286451590541210848515905412110165
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039813843013843041943042560012242220160x7f8100407f000x7f80e4226080524288558717462578030415905412140814159054121084851590541251120615905412553605
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040113843013843041943042560012242260480x7f8100407d800x7f80e42260c0524288499667155958218815905412566475159054125112061590541294768715905412990485
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040413843013843041943042560012242300800x7f8100407c000x7f80e4226100524288271838930438995615905413001315159054129476871590541336560815905413408046
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040713843013843041943042560012242359040x7f8100407a800x7f80e4226140524288286701332111761215905413419316159054133656081590541396017015905413978143
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041013843013843041943042560012242394240x7f81004079000x7f80e4226180524288275238530820562815905414000803159054139601701590541434113015905414342945
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041313843013843041943042560012242442240x7f81004077800x7f80e42261c0524288496603355620976815905414373894159054143411301590541477201115905414820605
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041613843013843041943042560012242487680x7f81004076000x7f80e4226200524288317478035558831615905414831764159054147720111590541523057215905415275494
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041913843013843041943042560012242533120x7f8102aa64800x7f80e4226240524288274209030706257615905415286784159054152305721590541567713315905415719424
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221384301384304194304256008242555520x7f8102aa63000x7f80e4226280524288236477326485074015905415730264159054156771331590541633585515905416377710
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042513843013843041943042560012242598400x7f8102aa61800x7f80e42262c0524288273402930626445615905416396959159054163358551590541676785615905416810190
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042813843013843041943042560012242656640x7f8102aa60000x7f80e4226300524288321071235959068815905416821300159054167678561590541727761715905417319959
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043113843013843041943042560012242712320x7f8100407e800x7f80e4226340524288368531841277785215905417331078159054172776171590541778257815905417802618
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341384301384304194304256008242732160x7f8100407d000x7f80e4226380524288239278326801798415905417814508159054177825781590541826305915905418309987
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371384301384304194304256008242757120x7f8100407b800x7f80e42263c0524288238178126668998415905418321176159054182630591590541903842115905419087429
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044013843013843041943042560012242807680x7f8100407a000x7f80e4226400524288266383429842052815905419106829159054190384211590541951762215905419560799
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044313843013843041943042560012242876160x7f81004078800x7f80e4226440524288338300937887234815905419571228159054195176221590542007506315905420118456
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044613843013843041943042560012242942080x7f81004077000x7f80e4226480524288353539339602255615905420130046159054200750631590542063058415905420673294
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491384301384304194304256008242969600x7f8102aa65800x7f80e42264c0524288238420826708653615905420683724159054206305841590542118386615905421227181
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521384301384304194304256008242999680x7f8102aa64000x7f80e4226500524288240129726892137215905421238381159054211838661590542204978715905422099672
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551384301384304194304256008243027200x7f8102aa62800x7f80e4226540524288238793526738175215905422118911159054220497871590542271874915905422764747
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045813843013843041943042560012243054720x7f8102aa61000x7f80e4226580524288259785029098987615905422776017159054227187491590542339187015905423437282
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046113843013843041943042560012243082240x7f8100407f800x7f80e42265c0524288259203329031243615905423449092159054233918701590542406099215905424103827
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641384301384304194304256008243109760x7f8100407e000x7f80e4226600524288238194726677833215905424114077159054240609921590542472323315905424765853
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671384301384304194304256008243132160x7f8100407c800x7f80e4226640524288239267926797172415905424776693159054247232331590542579699615905425839989
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701384301384304194304256008243159680x7f8100407b000x7f80e4226680524288244291127356814015905425859479159054257968731590542685495515905426924955
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047313843013843041943042560012243187200x7f81004079800x7f80e42266c0524288258846728989290815905426935865159054268549551590542797863715905428049120
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047613843013843041943042560012243214720x7f81004078000x7f80e4226700524288258955829004381615905428059779159054279786371590542909159915905429158415
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791384301384304194304256008243242240x7f81004076800x7f80e4226740524288242536327165444015905429169245159054290915991590543019624115905430264020
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821384301384304194304256008243264640x7f8102aa65000x7f80e4226780524288246465327604882015905430276790159054301962411590543214504515905432212647
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851384301384304194304256008243292160x7f8102aa63800x7f80e42267c0524288245093327443734015905432232506159054321450451590543405608915905434126974
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048813843013843041943042560012243319680x7f8102aa62000x7f80e4226800524288264117129581948815905434138864159054340560891590543603737315905436110990
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049113843013843041943042560012243347200x7f8102aa60800x7f80e4226840524288262643629413748015905436122070159054360373731590543801817615905438091636
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941384301384304194304256008243374720x7f8100407f000x7f80e4226880524288243650527292648815905438103896159054380181761590543994922015905440017913
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049713843013843041943042560082400x7f8100407d800x7f80e42268c0524288246189627567161615905440029503159054399492201590544355738715905443627392