Files
rocm-systems/tests/workloads/kernels/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.kd000189646189646335544322560043241600x00x7f9d56804280524288549090161498374817037332490146170349650567541703748141390317037481526322
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00218964618964632768256001224138880x00x7f9d56823f80409635384396734417037486684195170374814139031703748681004917037486814861
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051896461896464194304256001224143360x7f9d5979f3800x7f9d56823fc052428810971179122873310417037486847540170374868100491703748717948817037487182511
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081896461896464194304256001624150400x7f9d5979f2000x7f9d5682400052428811407137127760341617037487217940170374871794881703748758188717037487584229
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111896461896464194304256001624154880x7f9d5979f0800x7f9d5682404052428811442722128157430017037487614988170374875818871703748797964617037487982088
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141896461896464194304256001224159360x7f9d57109f000x7f9d5682408052428810861099121651812017037488014087170374879796461703748828540517037488287829
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171896461896464194304256001224163840x7f9d57109d800x7f9d568240c052428810573574118410070417037488319478170374882854051703748858732517037488589481
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201896461896464194304256001224170880x7f9d57109c000x7f9d5682410052428810964404122797332017037488632119170374885873251703748888860417037488890902
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231896461896464194304256001624177920x7f9d57109a800x7f9d5682414052428811456963128313446417037488921571170374888886041703748927868317037489280771
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261896461896464194304256001624184960x7f9d571099000x7f9d5682418052428811550159129361910817037489311760170374892786831703748966956217037489671690
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291896461896464194304256001624192000x7f9d571097800x7f9d568241c052428810976960122941951617037489701739170374896695621703748998540117037489987631
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321896461896464194304256001624199040x7f9d571096000x7f9d5682420052428810817707121152987217037490018600170374899854011703749032780017037490330121
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351896461896464194304256001224206080x7f9d5979f4800x7f9d5682424052428810879495121848528817037490370170170374903278001703749063564017037490637862
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381896461896464194304256001624213120x7f9d5979f3000x7f9d5682428052428811539775129243526817037490668821170374906356401703749102507917037491027261
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411896461896464194304256001624220160x7f9d5979f1800x7f9d568242c052428811492854128721281617037491057960170374910250791703749141659817037491418280
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441896461896464194304256001624227200x7f9d5979f0000x7f9d5682430052428810797987120928833217037491449569170374914165981703749169275717037491694342
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471896461896464194304256001224234240x7f9d57109e800x7f9d5682434052428810702976119865897617037491724511170374916927571703749196747617037491969124
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501896461896464194304256001224241280x7f9d57109d000x7f9d5682438052428811252349126023399217037492007433170374919674761703749224347617037492245216
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531896461896464194304256001624248320x7f9d57109b800x7f9d568243c052428811383664127492650817037492277235170374922434761703749260731517037492609076
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561896461896464194304256001624255360x7f9d57109a000x7f9d5682440052428811404369127728912017037492639075170374926073151703749297403417037492975765
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591896461896464194304256001224262400x7f9d571098800x7f9d5682444052428810834224121340744017037493006025170374929740341703749324939317037493251028
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621896461896464194304256001224269440x7f9d571097000x7f9d5682448052428810976310122933081617037493281737170374932493931703749352363317037493525310
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651896461896464194304256001224276480x7f9d5979f5800x7f9d568244c052428811131698124671773217037493563829170374935236331703749379755217037493799182
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681896461896464194304256001624286080x7f9d5979f4000x7f9d5682450052428811296810126521410817037493831211170374937975521703749415883117037494161072
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711896461896464194304256001624293120x7f9d5979f2800x7f9d5682454052428811421520127918839617037494192741170374941588311703749452587017037494527641
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741896461896464194304256001224300160x7f9d5979f1000x7f9d5682458052428811027158123500868017037494558800170374945258701703749480923017037494811053
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077189646189646419430425600824309760x7f9d57109f800x7f9d568245c052428810534369117980028817037494842452170374948092301703749508458917037495086165
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801896461896464194304256001224316800x7f9d57109e000x7f9d5682460052428811094494124254687217037495124134170374950845891703749536746817037495369147
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831896461896464194304256001624326400x7f9d57109c800x7f9d5682464052428811338745126992042417037495399966170374953674681703749573514717037495736826
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861896461896464194304256001224336000x7f9d57109b000x7f9d5682468052428811364054127277684417037495767916170374957351471703749609578617037496097496
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891896461896464194304256001224345600x7f9d571099800x7f9d568246c052428810788217120817291217037496128215170374960957861703749637130617037496372998
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092189646189646419430425600824355200x7f9d571098000x7f9d5682470052428810463351117177472417037496402847170374963713061703749664634517037496648000
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951896461896464194304256001224362240x7f9d571096800x7f9d5682474052428810719100120053732017037496685419170374966463451703749693258417037496934162
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981896461896464194304256001224371840x7f9d5979f5000x7f9d5682478052428811383194127487396017037496964191170374969325841703749729578417037497297482
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011896461896464194304256001224381440x7f9d5979f3800x7f9d568247c052428811416012127856183217037497328741170374972957841703749765706317037497658651
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041896461896464194304256001224391040x7f9d5979f2000x7f9d5682480052428810435879116880370017037497689290170374976570631703749793066217037497932333
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107189646189646419430425600824403200x7f9d5979f0800x7f9d568248405242889750321109197182417037497962743170374979306621703749822538117037498227235
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101896461896464194304256001224412800x7f9d57109f000x7f9d5682488052428810851588121539193217037498265894170374982253811703749851098117037498512887
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131896461896464194304256001224422400x7f9d57109d800x7f9d568248c052428811135730124719794817037498542436170374985109811703749887370017037498875357
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161896461896464194304256001224432000x7f9d57109c000x7f9d5682490052428811347230127085786417037498906356170374988737001703749923449917037499236156
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119189646189646419430425600824441600x7f9d57109a800x7f9d5682494052428810583880118538984017037499266285170374992344991703749951161817037499513148
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221896461896464194304256001224453760x7f9d571099000x7f9d568249805242889522638106648574817037499543797170374995116181703749978633817037499788031
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251896461896464194304256001224463360x7f9d571097800x7f9d568249c052428810838868121385559217037499824979170374997863381703750006377717037500065483
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281896461896464194304256001224475520x7f9d571096000x7f9d56824a0052428811339542127003163617037500095622170375000637771703750042921617037500430912
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311896461896464194304256001224485120x7f9d5979f4800x7f9d56824a4052428811240101125885264017037500462141170375004292161703750079257517037500794332
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134189646189646419430425600824494720x7f9d5979f3000x7f9d56824a8052428810253442114827788417037500824611170375007925751703750106841417037501070154
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371896461896464194304256001224506880x7f9d5979f1800x7f9d56824ac05242889098454101901688817037501100363170375010684141703750135225417037501354126
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401896461896464194304256001224516480x7f9d5979f0000x7f9d56824b0052428810228381114559982417037501392235170375013522541703750163033317037501632018
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431896461896464194304256001224528640x7f9d57109e800x7f9d56824b4052428811282291126360462817037501661757170375016303331703750199513217037501996698
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461896461896464194304256001224540800x7f9d57109d000x7f9d56824b8052428811428412127994402017037502026647170375019951321703750236489117037502366827
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149189646189646419430425600824552960x7f9d57109b800x7f9d56824bc052428810278122115111934017037502396666170375023648911703750264409117037502645879
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521896461896464194304256001224567680x7f9d57109a000x7f9d56824c00524288788054988251334817037502675768170375026440911703750292153017037502923411
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551896461896464194304256001224577280x7f9d571098800x7f9d56824c4052428810605760118774548417037502960810170375029215301703750320392917037503205643
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581896461896464194304256001224589440x7f9d571097000x7f9d56824c8052428811272090126248020817037503238062170375032039291703750356664817037503568303
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611896461896464194304256001224601600x7f9d5979f5800x7f9d56824cc052428811260785126116341217037503598842170375035666481703750392984817037503931612
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164189646189646419430425600824613760x7f9d5979f4000x7f9d56824d0052428810266940114992126017037503962851170375039298481703750421112717037504212754
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671896461896464194304256001224628480x7f9d5979f2800x7f9d56824d40524288590913166179026817037504243713170375042111271703750449016617037504491876
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701896461896464194304256001224638080x7f9d5979f1000x7f9d56824d8052428810245818114755364817037504529855170375044901661703750476600617037504767709
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731896461896464194304256001224650240x7f9d57109f800x7f9d56824dc052428811228481125755035617037504798318170375047660061703750512584517037505127468
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761896461896464194304256001224662400x7f9d57109e000x7f9d56824e0052428811230888125788200417037505157807170375051258451703750548648417037505488088
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179189646189646419430425600824674560x7f9d57109c800x7f9d56824e405242889842545110231079617037505518227170375054864841703750576376317037505765480
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821896461896464194304256001224689280x7f9d57109b000x7f9d56824e80524288615847668966174817037505795289170375057637631703750604904317037506050572
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851896461896464194304256001224701440x7f9d571099800x7f9d56824ec052428810277191115100102817037506093211170375060490431703750633208217037506334014
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881896461896464194304256001224716160x7f9d571098000x7f9d56824f0052428811243870125930848017037506364053170375063320821703750669480117037506696524
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911896461896464194304256001224728320x7f9d571096800x7f9d56824f4052428811285433126395106817037506726883170375066948011703750706008017037507061893
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194189646189646419430425600824740480x7f9d5979f5000x7f9d56824f805242889701805108655170017037507091922170375070600801703750733703917037507338685
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971896461896464194304256001224757760x7f9d5979f3800x7f9d56824fc0524288426895447813160417037507368554170375073370391703750762695917037507628697
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001896461896464194304256001224769920x7f9d5979f2000x7f9d5682500052428810338822115800229217037507667036170375076269591703750791575817037507917439
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031896461896464194304256001224784640x7f9d5979f0800x7f9d5682504052428811090300124209651217037507947338170375079157581703750828055717037508282258
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061896461896464194304256001224799360x7f9d57109f000x7f9d5682508052428811124402124592484817037508313087170375082805571703750864231617037508643928
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209189646189646419430425600824814080x7f9d57109d800x7f9d568250c05242889453460105871776417037508673917170375086423161703750891863617037508920250
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121896461896464194304256001224831360x7f9d57109c000x7f9d56825100524288385229643141087217037508950419170375089186361703750921735517037509219032
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151896461896464194304256001224843520x7f9d57109a800x7f9d5682514052428810148860113673472417037509267000170375092173551703750949831417037509500134
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181896461896464194304256001224858240x7f9d571099000x7f9d5682518052428811066063123940928417037509530593170375094983141703750986599317037509867603
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211896461896464194304256001224872960x7f9d571097800x7f9d568251c052428811120493124548047617037509898612170375098659931703751023287217037510234973
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241896461896464194304256001224887680x7f9d571096000x7f9d568252005242889348607104695123617037510265862170375102328721703751051687217037510518435
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271896461896464194304256001224907520x7f9d5979f4800x7f9d56825240524288377641242296545217037510548764170375105168721703751081943117037510821066
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301896461896464194304256001224919680x7f9d5979f3000x7f9d5682528052428810064288112707306417037510858665170375108194311703751110311017037511104778
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331896461896464194304256001224934400x7f9d5979f1800x7f9d568252c052428811102827124346762017037511135337170375111031101703751146918917037511470767
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361896461896464194304256001224949120x7f9d5979f0000x7f9d5682530052428811054604123810337217037511502476170375114691891703751182998917037511831737
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391896461896464194304256001224963840x7f9d57109e800x7f9d568253405242889317636104354649617037511862066170375118299891703751210886817037512110579
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421896461896464194304256001224983680x7f9d57109d000x7f9d56825380524288347123838874502017037512141448170375121088681703751241926717037512420850
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451896461896464194304256001224995840x7f9d57109b800x7f9d568253c05242889885466110712301617037512458059170375124192671703751269638717037512698052
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024818964618964641943042560012241013120x7f9d57109a000x7f9d5682540052428811100507124320130417037512727852170375126963871703751306134617037513063042
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025118964618964641943042560012241027840x7f9d571098800x7f9d5682544052428811145493124827828817037513093541170375130613461703751342518517037513426822
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025418964618964641943042560012241042560x7f9d571097000x7f9d56825480524288866528597051950017037513456781170375134251851703751370102417037513702724
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025718964618964641943042560012241062400x7f9d5979f5800x7f9d568254c0524288316265135404846817037513733033170375137010241703751401382317037514015505
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026018964618964641943042560012241077120x7f9d5979f4000x7f9d568255005242889736959109050050017037514053374170375140138231703751430662317037514308376
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026318964618964641943042560016241094400x7f9d5979f2800x7f9d5682554052428811090727124216501617037514339436170375143066231703751466822217037514669906
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026618964618964641943042560016241111680x7f9d5979f1000x7f9d5682558052428811059555123866522417037514701025170375146682221703751503174117037515033376
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691896461896464194304256008241128960x7f9d57109f800x7f9d568255c0524288799588689548949617037515063815170375150317411703751531478017037515316658
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027218964618964641943042560012241151360x7f9d57109e000x7f9d56825600524288303863634036830417037515347297170375153147801703751563429917037515636149
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027518964618964641943042560012241166080x7f9d57109c800x7f9d568256405242889765361109367183617037515673998170375156342991703751592181917037515923420
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027818964618964641943042560016241183360x7f9d57109b000x7f9d5682568052428811037961123622945217037515953450170375159218191703751628245817037516284210
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028118964618964641943042560016241200640x7f9d571099800x7f9d568256c052428810935224122473804017037516314509170375162824581703751664853717037516650170
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028418964618964641943042560012241217920x7f9d571098000x7f9d56825700524288685690376794508817037516680269170375166485371703751692501617037516926672
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028718964618964641943042560012241240320x7f9d571096800x7f9d56825740524288294747433002372817037516957261170375169250161703751725141617037517253072
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029018964618964641943042560012241255040x7f9d5979f5000x7f9d568257805242889107859102001868417037517291171170375172514161703751752965517037517531195
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029318964618964641943042560012241274880x7f9d5979f3800x7f9d568257c052428811075189124037379617037517561794170375175296551703751789253417037517894274
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029618964618964641943042560012241292160x7f9d5979f2000x7f9d5682580052428811059355123862662017037517925633170375178925341703751825333317037518255444
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029918964618964641943042560012241309440x7f9d5979f0800x7f9d56825840524288595709066721622017037518286183170375182533331703751854181217037518543406
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030218964618964641943042560012241334400x7f9d57109f000x7f9d56825880524288287887332235669617037518574095170375185418121703751888677217037518888506
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030518964618964641943042560012241349120x7f9d57109d800x7f9d568258c0524288814247491187739617037518927285170375188867721703751916357117037519165198
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030818964618964641943042560012241368960x7f9d57109c000x7f9d5682590052428810926582122378820417037519195287170375191635711703751952581017037519527447
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031118964618964641943042560012241388800x7f9d57109a800x7f9d5682594052428810952539122669544417037519558427170375195258101703751988676917037519888407
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031418964618964641943042560012241408640x7f9d571099000x7f9d56825980524288473852753078231617037519918186170375198867691703752017444917037520176039
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031718964618964641943042560012241436160x7f9d571097800x7f9d568259c0524288284380131852275217037520205498170375201744491703752052500817037520526719
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032018964618964641943042560012241453440x7f9d571096000x7f9d56825a00524288707129379194141617037520565308170375205250081703752080516717037520806761
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032318964618964641943042560012241475840x7f9d5979f4800x7f9d56825a4052428810883308121889226017037520837760170375208051671703752117796617037521179620
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032618964618964641943042560012241495680x7f9d5979f3000x7f9d56825a8052428810883841121895404817037521210179170375211779661703752154068517037521542410
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032918964618964641943042560012241515520x7f9d5979f1800x7f9d56825ac0524288396657444429684417037521572559170375215406851703752184084517037521842601
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033218964618964641943042560012241543040x7f9d5979f0000x7f9d56825b00524288282659131658074017037521873260170375218408451703752220612417037522208081
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033518964618964641943042560012241562880x7f9d57109e800x7f9d56825b40524288562274162973508817037522246429170375222061241703752250644317037522508172
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033818964618964641943042560012241587840x7f9d57109d000x7f9d56825b805242889648765108064428417037522538731170375225064431703752287236217037522873922
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034118964618964641943042560012241610240x7f9d57109b800x7f9d56825bc052428810856353121590486017037522904211170375228723621703752323668117037523238461
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034418964618964641943042560012241632640x7f9d57109a000x7f9d56825c00524288366128441010338817037523268600170375232366811703752354084017037523542472
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034718964618964641943042560012241665280x7f9d571098800x7f9d56825c40524288289344332403404017037523572912170375235408401703752393284017037523954761
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035018964618964641943042560012241685120x7f9d571097000x7f9d56825c80524288413149146267887617037523973480170375239328401703752423619917037524237813
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035318964618964641943042560012241712640x7f9d5979f5800x7f9d56825cc052428810385018116309656817037524268172170375242361991703752460179817037524603552
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035618964618964641943042560012241737600x7f9d5979f4000x7f9d56825d005242889585961107359092417037524634541170375246017981703752497299717037524974602
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035918964618964641943042560012241762560x7f9d5979f2800x7f9d56825d40524288280803831453778017037525005111170375249729971703752529203617037525293633
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036218964618964641943042560012241797760x7f9d5979f1000x7f9d56825d80524288282203431605010017037525324732170375252920361703752570835517037525726200
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036518964618964641943042560012241822720x7f9d57109f800x7f9d56825dc0524288309095534611318817037525748430170375257083551703752602579417037526027392
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036818964618964641943042560012241855360x7f9d57109e000x7f9d56825e00524288798753089457258817037526057431170375260257941703752641395417037526415461
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037118964618964641943042560012241885440x7f9d57109c800x7f9d56825e40524288792460588752624417037526447350170375264139541703752679123317037526838438
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037418964618964641943042560012241915520x7f9d57109b000x7f9d56825e80524288277567831085186017037526848858170375267912331703752717139217037527173039
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037718964618964641943042560012241958400x7f9d571099800x7f9d56825ec0524288286455932081784017037527203388170375271713921703752763747117037527681904
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038018964618964641943042560012241985920x7f9d571098000x7f9d56825f00524288275842730899431617037527700984170375276374711703752800515017037528006695
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038318964618964641943042560012242023680x7f9d571096800x7f9d56825f40524288686680176903116817037528036364170375280051501703752840978917037528453952
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038618964618964641943042560012242058880x7f9d5979f5000x7f9d56825f80524288639466971618293217037528464762170375284097891703752882818817037528869371
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038918964618964641943042560012242094080x7f9d5979f3800x7f9d56825fc0524288279712231322090817037528879940170375288281881703752922434717037529226010
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039218964618964641943042560012242144640x7f9d5979f2000x7f9d56826000524288289103532390111617037529257130170375292243471703752974114617037529759905
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039518964618964641943042560012242177280x7f9d5979f0800x7f9d56826040524288275350930838701217037529781545170375297411461703753009826517037530100315
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039818964618964641943042560012242220160x7f9d57109f000x7f9d56826080524288584403665459288417037530130815170375300982651703753051618417037530533823
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040118964618964641943042560012242260480x7f9d57109d800x7f9d568260c0524288516204157817921617037530549173170375305161841703753093362317037530951151
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040418964618964641943042560012242300800x7f9d57109c000x7f9d56826100524288272251130492788017037530964991170375309336231703753133154217037531348310
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040718964618964641943042560012242359040x7f9d57109a800x7f9d56826140524288287577332202330417037531363569170375313315421703753190306017037531920024
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041018964618964641943042560012242394240x7f9d571099000x7f9d56826180524288274164330698749617037531942883170375319030601703753228449917037532286213
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041318964618964641943042560012242442240x7f9d571097800x7f9d568261c0524288502638356297302017037532315802170375322844991703753272097817037532738060
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041618964618964641943042560012242487680x7f9d571096000x7f9d56826200524288324968336396442017037532752990170375327209781703753315841717037533175748
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041918964618964641943042560012242533120x7f9d5979f4800x7f9d56826240524288276055130924612417037533190737170375331584171703753358401617037533601636
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221896461896464194304256008242555520x7f9d5979f3000x7f9d56826280524288236175326444352017037533616585170375335840161703753422577517037534243817
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042518964618964641943042560012242598400x7f9d5979f1800x7f9d568262c0524288273281730600148017037534265847170375342257751703753464321417037534686555
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042818964618964641943042560012242656640x7f9d5979f0000x7f9d56826300524288321383935985446417037534697104170375346432141703753516081317037535201960
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043118964618964641943042560012242712320x7f9d57109e800x7f9d56826340524288364690040840669617037535215170170375351608131703753567201117037535713295
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341896461896464194304256008242732160x7f9d57109d000x7f9d56826380524288239300826800469217037535723805170375356720111703753618033017037536222481
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371896461896464194304256008242757120x7f9d57109b800x7f9d568263c0524288238379026696307617037536233001170375361803301703753695200817037536993769
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044018964618964641943042560012242807680x7f9d57109a000x7f9d56826400524288264759029654176817037537012308170375369520081703753742880717037537471205
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044318964618964641943042560012242876160x7f9d571098800x7f9d56826440524288338906837952216017037537482155170375374288071703753799152617037538009130
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044618964618964641943042560012242942080x7f9d571097000x7f9d56826480524288355616039824014017037538023940170375379915261703753853632417037538580424
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491896461896464194304256008242969600x7f9d5979f5800x7f9d568264c0524288239029626762568417037538591223170375385363241703753910528317037539150077
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521896461896464194304256008242999680x7f9d5979f4000x7f9d56826500524288239752426854944017037539161337170375391052831703753998320117037540024972
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551896461896464194304256008243027200x7f9d5979f2800x7f9d56826540524288239094026772284017037540043272170375399832011703754064239917037540683534
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045818964618964641943042560012243054720x7f9d5979f1000x7f9d56826580524288259738029088060017037540694203170375406423991703754131823817037541361704
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046118964618964641943042560012243082240x7f9d57109f800x7f9d568265c0524288259501929068906817037541372614170375413182381703754199247617037542010576
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641896461896464194304256008243109760x7f9d57109e000x7f9d56826600524288238799026742744017037542023895170375419924761703754264351517037542688516
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671896461896464194304256008243132160x7f9d57109c800x7f9d56826640524288240070726888807217037542699836170375426435151703754373359217037543777835
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701896461896464194304256008243159680x7f9d57109b000x7f9d56826680524288242316127142858817037543797405170375437335871703754479966517037544869514
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047318964618964641943042560012243187200x7f9d571099800x7f9d568266c0524288258194128912893617037544880894170375447996651703754593902117037546002821
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047618964618964641943042560012243214720x7f9d571098000x7f9d56826700524288259663929082814417037546013761170375459390211703754711293817037547180668
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791896461896464194304256008243242240x7f9d571096800x7f9d56826740524288241055926997176417037547192397170375471129381703754822957517037548276517
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821896461896464194304256008243264640x7f9d5979f5000x7f9d56826780524288245744927524580817037548287796170375482295751703755016477117037550234681
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851896461896464194304256008243292160x7f9d5979f3800x7f9d568267c0524288245523827491059617037550254720170375501647711703755209548617037552168666
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048818964618964641943042560012243319680x7f9d5979f2000x7f9d56826800524288262615329410838417037552180105170375520954861703755407964117037554122830
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049118964618964641943042560012243347200x7f9d5979f0800x7f9d56826840524288262436229392627217037554133649170375540796411703755604347717037556090894
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941896461896464194304256008243374720x7f9d57109f000x7f9d56826880524288245534227496558817037556101903170375560434771703755794699217037557991319
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049718964618964641943042560082400x7f9d57109d800x7f9d568268c0524288245935127549408817037558002429170375579469921703756154106317037561619016