Files
rocm-systems/tests/workloads/LDS/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.kd000183214183214335544322560043241600x00x7f2f90604280524288547021961256712016923739028927169214365689011692388620642116923886320630
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00218321418321432768256001224138880x00x7f2f90623f80409635703399611616923891496516169238862064211692389162992216923891634782
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051832141832144194304256001224143360x7f2f936bd3800x7f2f90623fc052428810698602119818000016923891669571169238916299221692389200240116923892005181
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081832141832144194304256001624150400x7f2f936bd2000x7f2f9062400052428811529386129126464016923892040270169238920024011692389241263916923892415079
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111832141832144194304256001624154880x7f2f936bd0800x7f2f9062404052428811442936128156583216923892448068169238924126391692389281487816923892817157
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141832141832144194304256001224159360x7f2f9108ff000x7f2f9062408052428810934300122461670016923892851016169238928148781692389312111716923893123608
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171832141832144194304256001224163840x7f2f9108fd800x7f2f906240c052428810557223118247450816923893156947169238931211171692389342943616923893431919
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201832141832144194304256001224170880x7f2f9108fc000x7f2f9062410052428811097227124286830416923893477218169238934294361692389373935516923893741650
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231832141832144194304256001624177920x7f2f9108fa800x7f2f9062414052428811441631128147226016923893774109169238937393551692389413471416923894137648
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261832141832144194304256001624184960x7f2f9108f9000x7f2f9062418052428811499863128795694416923894170747169238941347141692389455055216923894552166
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291832141832144194304256001624192000x7f2f9108f7800x7f2f906241c052428810933021122444202816923894583345169238945505521692389483615116923894837707
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321832141832144194304256001624199040x7f2f9108f6000x7f2f9062420052428810968252122851315616923894869036169238948361511692389511167016923895113459
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351832141832144194304256001224206080x7f2f936bd4800x7f2f9062424052428810941851122543890016923895153898169238951116701692389540159016923895403320
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381832141832144194304256001624213120x7f2f936bd3000x7f2f9062428052428811367872127315150416923895436189169238954015901692389576622816923895768120
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411832141832144194304256001624220160x7f2f936bd1800x7f2f906242c052428811445712128192542016923895800209169238957662281692389613150716923896133209
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441832141832144194304256001624227200x7f2f936bd0000x7f2f9062430052428810804371121009063616923896165538169238961315071692389641006616923896411900
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471832141832144194304256001224234240x7f2f9108fe800x7f2f9062434052428810860169121634388016923896442980169238964100661692389668894516923896690672
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501832141832144194304256001224241280x7f2f9108fd000x7f2f9062438052428811104952124372962416923896730161169238966889451692389697662416923896978414
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531832141832144194304256001624248320x7f2f9108fb800x7f2f906243c052428811448157128218149616923897011663169238969766241692389734062316923897342433
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561832141832144194304256001624255360x7f2f9108fa000x7f2f9062440052428811348007127096208016923897374622169238973406231692389771342216923897715002
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591832141832144194304256001224262400x7f2f9108f8800x7f2f9062444052428810940611122536645616923897746171169238977134221692389799230116923897993863
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621832141832144194304256001224269440x7f2f9108f7000x7f2f9062448052428811047617123724354016923898026233169238979923011692389828206016923898283785
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651832141832144194304256001224276480x7f2f936bd5800x7f2f906244c052428810965745122810974016923898323824169238982820601692389856141916923898563016
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681832141832144194304256001624286080x7f2f936bd4000x7f2f9062450052428811229845125767288416923898595106169238985614191692389892733816923898929116
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711832141832144194304256001624293120x7f2f936bd2800x7f2f9062454052428811543877129291650816923898960575169238989273381692389929517716923899296905
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741832141832144194304256001224300160x7f2f936bd1000x7f2f9062458052428810848522121501574816923899328974169238992951771692389957389616923899575686
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077183214183214419430425600824309760x7f2f9108ff800x7f2f906245c052428810565199118326663216923899607195169238995738961692389984989516923899851858
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801832141832144194304256001224316800x7f2f9108fe000x7f2f9062460052428811140288124762973216923899889887169238998498951692390012813416923900129700
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831832141832144194304256001624326400x7f2f9108fc800x7f2f9062464052428811404324127720674016923900161229169239001281341692390049645316923900498279
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861832141832144194304256001224336000x7f2f9108fb000x7f2f9062468052428811334422126943824816923900529968169239004964531692390085933216923900861138
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891832141832144194304256001224345600x7f2f9108f9800x7f2f906246c052428810664204119437088416923900892447169239008593321692390113373116923901135320
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092183214183214419430425600824355200x7f2f9108f8000x7f2f9062470052428810390289116366799216923901167609169239011337311692390141069016923901412431
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951832141832144194304256001224362240x7f2f9108f6800x7f2f9062474052428810899535122073172816923901450750169239014106901692390169068916923901692343
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981832141832144194304256001224371840x7f2f936bd5000x7f2f9062478052428811460318128352193216923901724062169239016906891692390205820816923902059902
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011832141832144194304256001224381440x7f2f936bd3800x7f2f906247c052428811366458127302308416923902094841169239020582081692390243436616923902436341
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041832141832144194304256001224391040x7f2f936bd2000x7f2f9062480052428810607712118804992416923902467950169239024343661692390271068516923902712403
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107183214183214419430425600824403200x7f2f936bd0800x7f2f906248405242889845378110265280816923902743672169239027106851692390298972516923902991534
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101832141832144194304256001224412800x7f2f9108ff000x7f2f9062488052428810737438120254442416923903030523169239029897251692390327804416923903279756
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131832141832144194304256001224422400x7f2f9108fd800x7f2f906248c052428811313154126707533216923903311125169239032780441692390364252216923903644245
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161832141832144194304256001224432000x7f2f9108fc000x7f2f9062490052428811282300126361807216923903675274169239036425221692390400556116923904007254
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119183214183214419430425600824441600x7f2f9108fa800x7f2f9062494052428810612846118858938816923904038783169239040055611692390428460016923904286316
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221832141832144194304256001224453760x7f2f9108f9000x7f2f906249805242889629482107842355616923904317505169239042846001692390456411916923904565868
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251832141832144194304256001224463360x7f2f9108f7800x7f2f906249c052428810768594120603111216923904604977169239045641191692390485099816923904852659
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281832141832144194304256001224475520x7f2f9108f6000x7f2f90624a0052428811440995128134730816923904884388169239048509981692390521483716923905216598
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311832141832144194304256001224485120x7f2f936bd4800x7f2f90624a4052428811297452126530273216923905248427169239052148371692390557595616923905577758
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134183214183214419430425600824494720x7f2f936bd3000x7f2f90624a8052428810246218114748062816923905610257169239055759561692390585195516923905853589
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371832141832144194304256001224506880x7f2f936bd1800x7f2f90624ac05242889154629102530638416923905885829169239058519551692390613547416923906137471
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401832141832144194304256001224516480x7f2f936bd0000x7f2f90624b0052428810500827117599096816923906176850169239061354741692390641883316923906420393
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431832141832144194304256001224528640x7f2f9108fe800x7f2f90624b4052428811299614126554580816923906451582169239064188331692390678539216923906787022
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461832141832144194304256001224540800x7f2f9108fd000x7f2f90624b8052428811309041126662309616923906819841169239067853921692390715195116923907153691
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149183214183214419430425600824552960x7f2f9108fb800x7f2f90624bc052428810106766113192430416923907184870169239071519511692390743163016923907433413
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521832141832144194304256001224567680x7f2f9108fa000x7f2f90624c00524288778059487141835216923907464222169239074316301692390771258916923907714334
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551832141832144194304256001224577280x7f2f9108f8800x7f2f90624c4052428810669848119505191616923907752293169239077125891692390799306816923907994886
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581832141832144194304256001224589440x7f2f9108f7000x7f2f90624c8052428811326619126855022816923908026555169239079930681692390835866716923908360335
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611832141832144194304256001224601600x7f2f936bd5800x7f2f90624cc052428811267449126190535616923908392784169239083586671692390872362616923908725454
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164183214183214419430425600824613760x7f2f936bd4000x7f2f90624d0052428810247179114772948016923908756913169239087236261692390900794516923909009656
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671832141832144194304256001224628480x7f2f936bd2800x7f2f90624d40524288628926070435510016923909041155169239090079451692390929098416923909292787
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701832141832144194304256001224638080x7f2f936bd1000x7f2f90624d8052428810383982116308697616923909331986169239092909841692390957018316923909571969
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731832141832144194304256001224650240x7f2f9108ff800x7f2f90624dc052428811195283125383158816923909605028169239095701831692390993802216923909939778
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761832141832144194304256001224662400x7f2f9108fe000x7f2f90624e0052428811269221126210694016923909970907169239099380221692391030794016923910309797
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179183214183214419430425600824674560x7f2f9108fc800x7f2f90624e4052428810031547112351717616923910341266169239103079401692391059145916923910593099
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821832141832144194304256001224689280x7f2f9108fb000x7f2f90624e80524288563515163110456416923910624538169239105914591692391087865816923910880220
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851832141832144194304256001224701440x7f2f9108f9800x7f2f90624ec052428810151446113693533616923910919239169239108786581692391115529816923911157092
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881832141832144194304256001224716160x7f2f9108f8000x7f2f90624f0052428811190899125336432816923911189231169239111552981692391151577616923911517451
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911832141832144194304256001224728320x7f2f9108f6800x7f2f90624f4052428811237673125859909616923911548740169239115157761692391188457516923911886320
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194183214183214419430425600824740480x7f2f936bd5000x7f2f90624f805242889847209110289767216923911917160169239118845751692391216201416923912163662
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971832141832144194304256001224757760x7f2f936bd3800x7f2f90624fc0524288446337449986279616923912195851169239121620141692391245145316923912453214
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001832141832144194304256001224769920x7f2f936bd2000x7f2f9062500052428810245626114750689616923912491522169239124514531692391273001216923912731845
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031832141832144194304256001224784640x7f2f936bd0800x7f2f9062504052428811227052125742550416923912763224169239127300121692391309529116923913097274
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061832141832144194304256001224799360x7f2f9108ff000x7f2f9062508052428811144682124821396416923913129504169239130952911692391345817016923913460034
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209183214183214419430425600824814080x7f2f9108fd800x7f2f906250c05242889381009105057855616923913490983169239134581701692391373512916923913736955
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121832141832144194304256001224831360x7f2f9108fc000x7f2f90625100524288395924444342048416923913767995169239137351291692391403160816923914033367
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151832141832144194304256001224843520x7f2f9108fa800x7f2f9062514052428810572479118411702816923914091165169239140316081692391432040716923914322458
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181832141832144194304256001224858240x7f2f9108f9000x7f2f9062518052428811133722124694801216923914352837169239143204071692391469288616923914694827
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211832141832144194304256001224872960x7f2f9108f7800x7f2f906251c052428811308838126657029616923914726686169239146928861692391506280516923915064526
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241832141832144194304256001224887680x7f2f9108f6000x7f2f906252005242889390068105163512016923915095575169239150628051692391533976416923915341418
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271832141832144194304256001224907520x7f2f936bd4800x7f2f90625240524288359129040223798416923915373107169239153397641692391564328316923915645019
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301832141832144194304256001224919680x7f2f936bd3000x7f2f9062528052428810072425112805546016923915683128169239156432831692391592008216923915921951
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331832141832144194304256001224934400x7f2f936bd1800x7f2f906252c052428811163849125029964016923915953250169239159200821692391628184116923916283560
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361832141832144194304256001224949120x7f2f936bd0000x7f2f9062530052428811196891125404906816923916315029169239162818411692391664743916923916649199
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391832141832144194304256001224963840x7f2f9108fe800x7f2f906253405242889374310104986645216923916680408169239166474391692391692695916923916928661
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421832141832144194304256001224983680x7f2f9108fd000x7f2f90625380524288361845540529244416923916960340169239169269591692391723415816923917235862
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451832141832144194304256001224995840x7f2f9108fb800x7f2f906253c05242889977671111746366016923917274970169239172341581692391750999716923917511823
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024818321418321441943042560012241013120x7f2f9108fa000x7f2f9062540052428811131345124671285616923917542453169239175099971692391787799516923917879823
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025118321418321441943042560012241027840x7f2f9108f8800x7f2f9062544052428811072313124009592816923917910672169239178779951692391824711416923918248772
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025418321418321441943042560012241042560x7f2f9108f7000x7f2f90625480524288876374898146799216923918280751169239182471141692391852951316923918531213
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025718321418321441943042560012241062400x7f2f936bd5800x7f2f906254c0524288313908635149705216923918563102169239185295131692391884359216923918845184
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026018321418321441943042560012241077120x7f2f936bd4000x7f2f906255005242889674164108349861616923918884683169239188435921692391912231116923919124025
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026318321418321441943042560016241094400x7f2f936bd2800x7f2f9062554052428811106945124391238416923919155464169239191223111692391948599016923919487785
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026618321418321441943042560016241111680x7f2f936bd1000x7f2f9062558052428811141262124781327216923919520124169239194859901692391984790916923919849564
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691832141832144194304256008241128960x7f2f9108ff800x7f2f906255c0524288823840392266868016923919882263169239198479091692392012678816923920128295
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027218321418321441943042560012241151360x7f2f9108fe000x7f2f90625600524288301237233734192416923920159964169239201267881692392044742716923920449296
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027518321418321441943042560012241166080x7f2f9108fc800x7f2f906256405242889930498111222234416923920487985169239204474271692392073270616923920734347
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027818321418321441943042560016241183360x7f2f9108fb000x7f2f9062568052428811131971124674694016923920764996169239207327061692392109702516923921098946
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028118321418321441943042560016241200640x7f2f9108f9800x7f2f906256c052428811038121123624924816923921129976169239210970251692392146006416923921461696
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028418321418321441943042560012241217920x7f2f9108f8000x7f2f90625700524288697477478111118816923921492795169239214600641692392173942316923921741237
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028718321418321441943042560012241240320x7f2f9108f6800x7f2f90625740524288299847533580213216923921772466169239217394231692392206614216923922067868
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029018321418321441943042560012241255040x7f2f936bd5000x7f2f906257805242889093250101839407616923922107336169239220661421692392235494116923922356779
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029318321418321441943042560012241274880x7f2f936bd3800x7f2f906257c052428810981701122995916816923922387038169239223549411692392271861916923922720408
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029618321418321441943042560012241292160x7f2f936bd2000x7f2f9062580052428811108635124414122016923922751417169239227186191692392308245816923923084167
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029918321418321441943042560012241309440x7f2f936bd0800x7f2f90625840524288655218173383934016923923116106169239230824581692392337125716923923373049
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030218321418321441943042560012241334400x7f2f9108ff000x7f2f90625880524288289501432423027216923923404598169239233712571692392371845616923923720578
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030518321418321441943042560012241349120x7f2f9108fd800x7f2f906258c0524288856807795948637216923923759097169239237184561692392400357516923924005170
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030818321418321441943042560012241368960x7f2f9108fc000x7f2f9062590052428810997414123169354416923924036139169239240035751692392436709416923924369059
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031118321418321441943042560012241388800x7f2f9108fa800x7f2f9062594052428811003905123242961616923924399848169239243670941692392473333316923924734978
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031418321418321441943042560012241408640x7f2f9108f9000x7f2f90625980524288473203952992860016923924765917169239247333331692392502405216923925025750
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031718321418321441943042560012241436160x7f2f9108f7800x7f2f906259c0524288283702431771170016923925056729169239250240521692392537845116923925380339
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032018321418321441943042560012241453440x7f2f9108f6000x7f2f90625a00524288741030783003586416923925418678169239253784511692392565893016923925660561
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032318321418321441943042560012241475840x7f2f936bd4800x7f2f90625a4052428810949222122634250016923925692300169239256589301692392602468916923926026300
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032618321418321441943042560012241495680x7f2f936bd3000x7f2f90625a8052428810938559122510587616923926057929169239260246891692392639572716923926397599
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032918321418321441943042560012241515520x7f2f936bd1800x7f2f90625ac0524288371518041610562416923926429638169239263957271692392669604616923926697670
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033218321418321441943042560012241543040x7f2f936bd0000x7f2f90625b00524288284638731876615216923926729439169239266960461692392705988516923927061649
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033518321418321441943042560012241562880x7f2f9108fe800x7f2f90625b40524288571207463974257216923927100758169239270598851692392734596416923927347951
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033818321418321441943042560012241587840x7f2f9108fd000x7f2f90625b805242889849219110309465616923927379160169239273459641692392771172316923927713320
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034118321418321441943042560012241610240x7f2f9108fb800x7f2f90625bc052428810642757119197944016923927745319169239277117231692392807716216923928078959
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034418321418321441943042560012241632640x7f2f9108fa000x7f2f90625c00524288375431942048014016923928110838169239280771621692392838500116923928386590
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034718321418321441943042560012241665280x7f2f9108f8800x7f2f90625c40524288281746631545746416923928417769169239283850011692392877811916923928824247
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035018321418321441943042560012241685120x7f2f9108f7000x7f2f90625c80524288397976544568297616923928844456169239287781191692392911043816923929112268
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035318321418321441943042560012241712640x7f2f936bd5800x7f2f90625cc05242889683318108451604016923929142868169239291104381692392948067716923929482467
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035618321418321441943042560012241737600x7f2f936bd4000x7f2f90625d0052428810015535112175336816923929515786169239294806771692392985507616923929856826
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035918321418321441943042560012241762560x7f2f936bd2800x7f2f90625d40524288280874631448953216923929888245169239298550761692393017603516923930177917
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036218321418321441943042560012241797760x7f2f936bd1000x7f2f90625d80524288285648331997876416923930210646169239301760351692393059795316923930645543
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036518321418321441943042560012241822720x7f2f9108ff800x7f2f90625dc0524288302945533923328816923930665272169239305979531692393094547216923930947134
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036818321418321441943042560012241855360x7f2f9108fe000x7f2f90625e00524288822996592171415216923930977903169239309454721692393132259116923931324013
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037118321418321441943042560012241885440x7f2f9108fc800x7f2f90625e40524288799434689536096016923931356582169239313225911692393170179016923931748080
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037418321418321441943042560012241915520x7f2f9108fb000x7f2f90625e80524288278892631238422016923931760060169239317017901692393208194916923932083840
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037718321418321441943042560012241958400x7f2f9108f9800x7f2f90625ec0524288284071631816168416923932115559169239320819491692393254914716923932593985
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038018321418321441943042560012241985920x7f2f9108f8000x7f2f90625f00524288275145930799969216923932613334169239325491471692393291554616923932917195
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038318321418321441943042560012242023680x7f2f9108f6800x7f2f90625f40524288667715074780478416923932948205169239329155461692393331506416923933334983
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038618321418321441943042560012242058880x7f2f936bd5000x7f2f90625f80524288617719469178901616923933349263169239333150641692393371394316923933731541
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038918321418321441943042560012242094080x7f2f936bd3800x7f2f90625fc0524288278439931186120416923933746401169239337139431692393408786216923934089671
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039218321418321441943042560012242144640x7f2f936bd2000x7f2f90626000524288289937532470214416923934121580169239340878621692393461170016923934629575
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039518321418321441943042560012242177280x7f2f936bd0800x7f2f90626040524288279317831280246416923934652984169239346117001692393497553916923934977294
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039818321418321441943042560012242220160x7f2f9108ff000x7f2f90626080524288598815067064464416923935008883169239349755391692393539073816923935409421
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040118321418321441943042560012242260480x7f2f9108fd800x7f2f906260c0524288503997856441963216923935424401169239353907381692393581057616923935827819
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040418321418321441943042560012242300800x7f2f9108fc000x7f2f90626100524288272615530530287616923935843399169239358105761692393621601516923936233077
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040718321418321441943042560012242359040x7f2f9108fa800x7f2f90626140524288289014632369961616923936249297169239362160151692393679361316923936811790
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041018321418321441943042560012242394240x7f2f9108f9000x7f2f90626180524288283949431799694816923936833729169239367936131692393717617216923937177929
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041318321418321441943042560012242442240x7f2f9108f7800x7f2f906261c0524288507235256803004016923937209288169239371761721692393761201016923937630796
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041618321418321441943042560012242487680x7f2f9108f6000x7f2f90626200524288316281735420888816923937644805169239376120101692393805184916923938069233
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041918321418321441943042560012242533120x7f2f936bd4800x7f2f90626240524288270406630274986816923938091912169239380518491692393849552716923938514419
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221832141832144194304256008242555520x7f2f936bd3000x7f2f90626280524288236258826457170816923938528949169239384955271692393914000516923939157110
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042518321418321441943042560012242598400x7f2f936bd1800x7f2f906262c0524288271682830420200016923939181349169239391400051692393956144416923939578827
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042818321418321441943042560012242656640x7f2f936bd0000x7f2f90626300524288317887335602770016923939594687169239395614441692394005024216923940067583
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043118321418321441943042560012242712320x7f2f9108fe800x7f2f90626340524288348376739021482816923940085732169239400502421692394053952116923940557088
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341832141832144194304256008242732160x7f2f9108fd000x7f2f90626380524288239251226798325616923940572378169239405395211692394102751916923941044654
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371832141832144194304256008242757120x7f2f9108fb800x7f2f906263c0524288237975726649914416923941061263169239410275191692394177679716923941794611
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044018321418321441943042560012242807680x7f2f9108fa000x7f2f90626400524288263994329560049616923941817601169239417767971692394223247516923942254298
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044318321418321441943042560012242876160x7f2f9108f8800x7f2f90626440524288354272939677132016923942265767169239422324751692394278623316923942830001
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044618321418321441943042560012242942080x7f2f9108f7000x7f2f90626480524288355264739781290816923942842630169239427862331692394335311116923943394704
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491832141832144194304256008242969600x7f2f936bd5800x7f2f906264c0524288238261726684894816923943406903169239433531111692394391711016923943959587
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521832141832144194304256008242999680x7f2f936bd4000x7f2f90626500524288239375126811560416923943972347169239439171101692394479502716923944837001
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551832141832144194304256008243027200x7f2f936bd2800x7f2f90626540524288238547726717234416923944856660169239447950271692394546782416923945509861
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045818321418321441943042560012243054720x7f2f936bd1000x7f2f90626580524288258960728993268816923945522051169239454678241692394615182216923946196081
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046118321418321441943042560012243082240x7f2f9108ff800x7f2f906265c0524288259128029016542816923946208200169239461518221692394683902016923946882450
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641832141832144194304256008243109760x7f2f9108fe000x7f2f90626600524288238887126761658016923946894340169239468390201692394751245816923947556330
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671832141832144194304256008243132160x7f2f9108fc800x7f2f90626640524288239488526822926016923947568820169239475124581692394861341416923948657278
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701832141832144194304256008243159680x7f2f9108fb000x7f2f90626680524288243686527290080016923948678817169239486133001692394969777616923949766365
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047318321418321441943042560012243187200x7f2f9108f9800x7f2f906266c0524288259143429019750016923949777874169239496977761692395083809116923950907691
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047618321418321441943042560012243214720x7f2f9108f8000x7f2f90626700524288259957929110573616923950920020169239508380911692395197776716923952043447
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791832141832144194304256008243242240x7f2f9108f6800x7f2f90626740524288243032627217629616923952055857169239519777671692395309120316923953157344
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821832141832144194304256008243264640x7f2f936bd5000x7f2f90626780524288245635227512356416923953169254169239530912031692395504223616923955118356
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851832141832144194304256008243292160x7f2f936bd3800x7f2f906267c0524288245563527497547216923955138515169239550422361692395697934916923957045889
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048818321418321441943042560012243319680x7f2f936bd2000x7f2f90626800524288262697129423450016923957057708169239569793491692395895646216923959027290
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049118321418321441943042560012243347200x7f2f936bd0800x7f2f90626840524288262138229357814416923959039459169239589564621692396094541516923961012260
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941832141832144194304256008243374720x7f2f9108ff000x7f2f90626880524288245813727530046416923961025250169239609454151692396287228816923962939053
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049718321418321441943042560082400x7f2f9108fd800x7f2f906268c0524288246176327572677616923962951763169239628722881692396649483616923966573005