Files
rocm-systems/tests/workloads/L2/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.kd000176783176783335544322560043241600x00x7fcb9c804280524288547800061345464816810213261190168078925111061681036445995516810364571254
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00217678317678332768256001224138880x00x7fcb9c823f80409635204394664416810369719563168103644599551681036984601116810369850749
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051767831767834194304256001224143360x7fcb9f7333800x7fcb9c823fc052428810762506120531428816810369884598168103698460111681037021257016810370214988
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081767831767834194304256001624150400x7fcb9f7332000x7fcb9c82400052428811468392128441876016810370251287168103702125701681037061736816810370619675
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111767831767834194304256001624154880x7fcb9f7330800x7fcb9c82404052428811639989130363678816810370651254168103706173681681037100760616810371010003
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141767831767834194304256001224159360x7fcb9d103f000x7fcb9c82408052428810999921123194541216810371043072168103710076061681037130792516810371310044
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171767831767834194304256001224163840x7fcb9d103d800x7fcb9c8240c052428810857908121598959216810371342443168103713079251681037160408416810371606394
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201767831767834194304256001224170880x7fcb9d103c000x7fcb9c82410052428811190241125329804416810371649693168103716040841681037190168216810371903895
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231767831767834194304256001624177920x7fcb9d103a800x7fcb9c82414052428811522430129051193616810371934844168103719016821681037228696116810372289233
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261767831767834194304256001624184960x7fcb9d1039000x7fcb9c82418052428811596726129884355616810372320652168103722869611681037268295916810372685301
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291767831767834194304256001624192000x7fcb9d1037800x7fcb9c8241c052428811018488123408437616810372715830168103726829591681037299655816810372998821
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321767831767834194304256001624199040x7fcb9d1036000x7fcb9c82420052428810837797121383063616810373030720168103729965581681037329447616810373296712
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351767831767834194304256001224206080x7fcb9f7334800x7fcb9c82424052428810917447122276263216810373335681168103732944761681037359735516810373599542
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381767831767834194304256001624213120x7fcb9f7333000x7fcb9c82428052428811533320129169817216810373631751168103735973551681037398535316810373987590
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411767831767834194304256001624220160x7fcb9f7331800x7fcb9c8242c052428811429358128006560016810374018879168103739853531681037440471216810374407077
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441767831767834194304256001624227200x7fcb9f7330000x7fcb9c82430052428811297692126526521616810374438336168103744047121681037470919016810374710698
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471767831767834194304256001224234240x7fcb9d103e800x7fcb9c82434052428811069679123976932016810374741277168103747091901681037497926916810374980809
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501767831767834194304256001224241280x7fcb9d103d000x7fcb9c82438052428811220432125671361216810375019478168103749792691681037525094816810375252671
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531767831767834194304256001624248320x7fcb9d103b800x7fcb9c8243c052428811578687129674895616810375284750168103752509481681037560918716810375610860
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561767831767834194304256001624255360x7fcb9d103a000x7fcb9c82440052428811369166127332532416810375642089168103756091871681037597302516810375974558
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591767831767834194304256001224262400x7fcb9d1038800x7fcb9c82444052428811019959123417119616810376004177168103759730251681037624566416810376247360
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621767831767834194304256001224269440x7fcb9d1037000x7fcb9c82448052428810986404123044403216810376277809168103762456641681037651734316810376518941
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651767831767834194304256001224276480x7fcb9f7335800x7fcb9c8244c052428811175223125164719616810376556770168103765173431681037679302216810376794603
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681767831767834194304256001624286080x7fcb9f7334000x7fcb9c82450052428811404897127730527216810376826622168103767930221681037715222016810377153761
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711767831767834194304256001624293120x7fcb9f7332800x7fcb9c82454052428811280928126346534416810377184771168103771522201681037751285816810377514430
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741767831767834194304256001224300160x7fcb9f7331000x7fcb9c82458052428811048439123746225616810377546219168103775128581681037778213716810377783772
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077176783176783419430425600824309760x7fcb9d103f800x7fcb9c8245c052428810575965118445138016810377815251168103777821371681037805125616810378052873
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801767831767834194304256001224316800x7fcb9d103e000x7fcb9c82460052428810593217118641694416810378097222168103780512561681037832741516810378328965
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831767831767834194304256001624326400x7fcb9d103c800x7fcb9c82464052428811384425127502790016810378360304168103783274151681037869301316810378694533
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861767831767834194304256001224336000x7fcb9d103b000x7fcb9c82468052428811493448128722212416810378725782168103786930131681037905269216810379054132
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891767831767834194304256001224345600x7fcb9d1039800x7fcb9c8246c052428810671051119508106016810379084801168103790526921681037932325116810379324864
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092176783176783419430425600824355200x7fcb9d1038000x7fcb9c82470052428810229460114569786016810379355293168103793232511681037959349016810379594925
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951767831767834194304256001224362240x7fcb9d1036800x7fcb9c82474052428810835170121345503616810379632074168103795934901681037986548816810379867007
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981767831767834194304256001224371840x7fcb9f7335000x7fcb9c82478052428811398735127657204016810379897996168103798654881681038022308716810380224756
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011767831767834194304256001224381440x7fcb9f7333800x7fcb9c8247c052428811511327128923331216810380255355168103802230871681038058132516810380582845
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041767831767834194304256001224391040x7fcb9f7332000x7fcb9c82480052428811037480123617724816810380613934168103805813251681038085220416810380853896
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107176783176783419430425600824403200x7fcb9f7330800x7fcb9c82484052428810015205112165396816810380884655168103808522041681038112356316810381125168
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101767831767834194304256001224412800x7fcb9d103f000x7fcb9c82488052428810814790121126962016810381163676168103811235631681038140084216810381402409
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131767831767834194304256001224422400x7fcb9d103d800x7fcb9c8248c052428811372046127367175216810381432768168103814008421681038175812016810381759828
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161767831767834194304256001224432000x7fcb9d103c000x7fcb9c82490052428811414763127845636816810381790907168103817581201681038211731916810382119077
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119176783176783419430425600824441600x7fcb9d103a800x7fcb9c82494052428810552386118189246416810382150876168103821173191681038239331816810382395078
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221767831767834194304256001224453760x7fcb9d1039000x7fcb9c8249805242889694113108568544016810382426077168103823933181681038266595716810382667490
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251767831767834194304256001224463360x7fcb9d1037800x7fcb9c8249c052428811071658123995378416810382705468168103826659571681038294067516810382942341
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281767831767834194304256001224475520x7fcb9d1036000x7fcb9c824a0052428811491288128699562816810382972530168103829406751681038330547416810383306980
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311767831767834194304256001224485120x7fcb9f7334800x7fcb9c824a4052428811362552127255701616810383338339168103833054741681038366371216810383665238
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134176783176783419430425600824494720x7fcb9f7333000x7fcb9c824a8052428810207822114318433216810383696747168103836637121681038393475116810383936260
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371767831767834194304256001224506880x7fcb9f7331800x7fcb9c824ac05242889134023102296385616810383967849168103839347511681038421283016810384214411
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401767831767834194304256001224516480x7fcb9f7330000x7fcb9c824b0052428810386704116326465616810384253010168103842128301681038448434916810384486033
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431767831767834194304256001224528640x7fcb9d103e800x7fcb9c824b4052428811481076128586470016810384516732168103844843491681038484594716810384847502
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461767831767834194304256001224540800x7fcb9d103d000x7fcb9c824b8052428811260362126113564816810384878921168103848459471681038520354616810385205020
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149176783176783419430425600824552960x7fcb9d103b800x7fcb9c824bc052428810469175117244861616810385235379168103852035461681038548242516810385484112
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521767831767834194304256001224567680x7fcb9d103a000x7fcb9c824c00524288773159986589140016810385515411168103854824251681038575602316810385757503
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551767831767834194304256001224577280x7fcb9d1038800x7fcb9c824c4052428810667882119475892416810385794882168103857560231681038602994216810386031475
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581767831767834194304256001224589440x7fcb9d1037000x7fcb9c824c8052428811281111126344920416810386061684168103860299421681038639138116810386392983
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611767831767834194304256001224601600x7fcb9f7335800x7fcb9c824cc052428811270846126234580816810386424122168103863913811681038674785916810386749322
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164176783176783419430425600824613760x7fcb9f7334000x7fcb9c824d0052428810342299115826321216810386780831168103867478591681038702497816810387026564
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671767831767834194304256001224628480x7fcb9f7332800x7fcb9c824d40524288647212572488708416810387057963168103870249781681038730081716810387302445
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701767831767834194304256001224638080x7fcb9f7331000x7fcb9c824d8052428810489081117483576416810387341354168103873008171681038757377616810387575237
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731767831767834194304256001224650240x7fcb9d103f800x7fcb9c824dc052428811308460126654263616810387606906168103875737761681038793009416810387931776
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761767831767834194304256001224662400x7fcb9d103e000x7fcb9c824e0052428811256619126069679216810387962195168103879300941681038828289316810388284385
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179176783176783419430425600824674560x7fcb9d103c800x7fcb9c824e4052428810102970113151003616810388315294168103882828931681038855505216810388556486
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821767831767834194304256001224689280x7fcb9d103b000x7fcb9c824e80524288535566459978972416810388587685168103885550521681038883617016810388837678
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851767831767834194304256001224701440x7fcb9d1039800x7fcb9c824ec052428810171333113908738816810388876526168103888361701681038910560916810389107199
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881767831767834194304256001224716160x7fcb9d1038000x7fcb9c824f0052428811261573126126909616810389137788168103891056091681038946176816810389463328
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911767831767834194304256001224728320x7fcb9d1036800x7fcb9c824f4052428811232760125804875616810389493487168103894617681681038982336616810389824937
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194176783176783419430425600824740480x7fcb9f7335000x7fcb9c824f805242889746927109162826816810389855126168103898233661681039009312516810390094769
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971767831767834194304256001224757760x7fcb9f7333800x7fcb9c824fc0524288452407750671963616810390125888168103900931251681039038256416810390384280
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001767831767834194304256001224769920x7fcb9f7332000x7fcb9c82500052428810547615118132723216810390422648168103903825641681039065552316810390657181
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031767831767834194304256001224784640x7fcb9f7330800x7fcb9c82504052428811301537126572291216810390687550168103906555231681039101760116810391019260
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061767831767834194304256001224799360x7fcb9d103f000x7fcb9c82508052428811288613126430172816810391050739168103910176011681039137344016810391375059
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209176783176783419430425600824814080x7fcb9d103d800x7fcb9c8250c05242889845367110267979616810391405258168103913734401681039164367816810391645290
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121767831767834194304256001224831360x7fcb9d103c000x7fcb9c825100524288382251042808807216810391676709168103916436781681039193695716810391938641
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151767831767834194304256001224843520x7fcb9d103a800x7fcb9c82514052428810223863114504337616810391986500168103919369571681039221471616810392216642
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181767831767834194304256001224858240x7fcb9d1039000x7fcb9c82518052428811202768125468692016810392247601168103922147161681039257503416810392576741
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211767831767834194304256001224872960x7fcb9d1037800x7fcb9c8251c052428811197754125411284816810392608220168103925750341681039294223316810392943850
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241767831767834194304256001224887680x7fcb9d1036000x7fcb9c8252005242889289372104036805216810392974159168103929422331681039321551216810393217141
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271767831767834194304256001224907520x7fcb9f7334800x7fcb9c825240524288381511042731727216810393248850168103932155121681039351327016810393514802
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301767831767834194304256001224919680x7fcb9f7333000x7fcb9c82528052428810231223114581500416810393553191168103935132701681039380094916810393802453
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331767831767834194304256001224934400x7fcb9f7331800x7fcb9c8252c052428811194482125374892816810393833812168103938009491681039416254816810394164252
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361767831767834194304256001224949120x7fcb9f7330000x7fcb9c82530052428811288834126437314016810394196481168103941625481681039452686616810394528460
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391767831767834194304256001224963840x7fcb9d103e800x7fcb9c8253405242889184963102861031216810394558889168103945268661681039479742516810394798962
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421767831767834194304256001224983680x7fcb9d103d000x7fcb9c825380524288356926339973426816810394830271168103947974251681039510094416810395102602
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451767831767834194304256001224995840x7fcb9d103b800x7fcb9c8253c052428810198487114214010016810395141041168103951009441681039537102316810395372644
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024817678317678341943042560012241013120x7fcb9d103a000x7fcb9c82540052428811219972125655991216810395403893168103953710231681039573198116810395733513
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025117678317678341943042560012241027840x7fcb9d1038800x7fcb9c82544052428811212214125573240416810395764802168103957319811681039608893916810396090512
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025417678317678341943042560012241042560x7fcb9d1037000x7fcb9c825480524288863095596663001616810396121721168103960889391681039635933816810396361093
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025717678317678341943042560012241062400x7fcb9f7335800x7fcb9c8254c0524288309379434653538816810396391402168103963593381681039666541716810396666964
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026017678317678341943042560012241077120x7fcb9f7334000x7fcb9c82550052428810048649112550428016810396705502168103966654171681039694125616810396942905
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026317678317678341943042560016241094400x7fcb9f7332800x7fcb9c82554052428811297694126531231616810396973624168103969412561681039730125416810397302834
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026617678317678341943042560016241111680x7fcb9f7331000x7fcb9c82558052428811120650124553312016810397334703168103973012541681039765693316810397658613
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691767831767834194304256008241128960x7fcb9d103f800x7fcb9c8255c0524288809411190656788016810397689592168103976569331681039792797216810397929664
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027217678317678341943042560012241151360x7fcb9d103e000x7fcb9c825600524288303977434039192416810397960573168103979279721681039824861016810398250254
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027517678317678341943042560012241166080x7fcb9d103c800x7fcb9c8256405242889949162111437922816810398288773168103982486101681039853404916810398535575
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027817678317678341943042560016241183360x7fcb9d103b000x7fcb9c82568052428811093202124244141216810398566954168103985340491681039888988816810398891484
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028117678317678341943042560016241200640x7fcb9d1039800x7fcb9c8256c052428811199343125431885616810398922523168103988898881681039924732616810399248903
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028417678317678341943042560012241217920x7fcb9d1038000x7fcb9c825700524288695777477919043216810399279222168103992473261681039952140516810399523135
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028717678317678341943042560012241240320x7fcb9d1036800x7fcb9c825740524288297127733280088816810399553844168103995214051681039984124416810399842995
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029017678317678341943042560012241255040x7fcb9f7335000x7fcb9c8257805242889241587103510789616810399880993168103998412441681040011516216810400116756
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029317678317678341943042560012241274880x7fcb9f7333800x7fcb9c8257c052428811018658123407581216810400147805168104001151621681040047116116810400472705
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029617678317678341943042560012241292160x7fcb9f7332000x7fcb9c82580052428811060868123880448016810400504234168104004711611681040082811916810400829714
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029917678317678341943042560012241309440x7fcb9f7330800x7fcb9c825840524288594867366622692416810400860913168104008281191681040110635816810401107935
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030217678317678341943042560012241334400x7fcb9d103f000x7fcb9c825880524288292228832721118816810401138914168104011063581681040144555716810401447055
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030517678317678341943042560012241349120x7fcb9d103d800x7fcb9c8258c0524288842396894344162816810401485733168104014455571681040171803616810401719536
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030817678317678341943042560012241368960x7fcb9d103c000x7fcb9c82590052428810978273122952928816810401749915168104017180361681040207595416810402085765
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031117678317678341943042560012241388800x7fcb9d103a800x7fcb9c82594052428811013467123349232816810402109214168104020759541681040243867216810402440284
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031417678317678341943042560012241408640x7fcb9d1039000x7fcb9c825980524288485344754357578816810402470923168104024386721681040272459116810402726075
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031717678317678341943042560012241436160x7fcb9d1037800x7fcb9c8259c0524288285107931933651216810402757014168104027245911681040306987016810403071674
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032017678317678341943042560012241453440x7fcb9d1036000x7fcb9c825a00524288753422284370589216810403110343168104030698701681040334554916810403347155
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032317678317678341943042560012241475840x7fcb9f7334800x7fcb9c825a4052428810687903119705807616810403378414168104033455491681040370170716810403703324
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032617678317678341943042560012241495680x7fcb9f7333000x7fcb9c825a8052428810933349122450964016810403734713168104037017071681040405914616810404060803
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032917678317678341943042560012241515520x7fcb9f7331800x7fcb9c825ac0524288395757844324869616810404091502168104040591461681040435338416810404354894
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033217678317678341943042560012241543040x7fcb9f7330000x7fcb9c825b00524288288098232268116416810404385873168104043533841681040471130316810404713023
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033517678317678341943042560012241562880x7fcb9d103e800x7fcb9c825b40524288554930162140922416810404751141168104047113031681040499034216810404991994
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033817678317678341943042560012241587840x7fcb9d103d000x7fcb9c825b8052428810605241118779080816810405023653168104049903421681040534938016810405350903
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034117678317678341943042560012241610240x7fcb9d103b800x7fcb9c825bc052428810781605120750252416810405381672168104053493801681040570585916810405707502
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034417678317678341943042560012241632640x7fcb9d103a000x7fcb9c825c00524288359412940250043616810405737661168104057058591681040600729716810406008792
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034717678317678341943042560012241665280x7fcb9d1038800x7fcb9c825c40524288285503031970856816810406039251168104060072971681040639673616810406419619
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035017678317678341943042560012241685120x7fcb9d1037000x7fcb9c825c80524288415884046576832816810406439389168104063967361681040669737416810406699121
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035317678317678341943042560012241712640x7fcb9f7335800x7fcb9c825cc052428810198238114218812016810406729650168104066973741681040705689316810407058530
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035617678317678341943042560012241737600x7fcb9f7334000x7fcb9c825d005242889858726110414087616810407089949168104070568931681040742265116810407424118
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035917678317678341943042560012241762560x7fcb9f7332800x7fcb9c825d40524288279982031351234416810407454767168104074226511681040774137016810407743058
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036217678317678341943042560012241797760x7fcb9f7331000x7fcb9c825d80524288280314631389102016810407775077168104077413701681040815096816810408196934
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036517678317678341943042560012241822720x7fcb9d103f800x7fcb9c825dc0524288306587034333342016810408215333168104081509681681040848728716810408488895
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036817678317678341943042560012241855360x7fcb9d103e000x7fcb9c825e00524288812266990977608416810408519354168104084872871681040885432516810408896582
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037117678317678341943042560012241885440x7fcb9d103c800x7fcb9c825e40524288769298386156585616810408907862168104088543251681040925304416810409295310
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037417678317678341943042560012241915520x7fcb9d103b000x7fcb9c825e80524288282772531666434416810409305989168104092530441681040962248216810409624130
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037717678317678341943042560012241958400x7fcb9d1039800x7fcb9c825ec0524288279991631357249616810409654749168104096224821681041008584016810410107164
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038017678317678341943042560012241985920x7fcb9d1038000x7fcb9c825f00524288275381130839984416810410126194168104100858401681041042391916810410425335
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038317678317678341943042560012242023680x7fcb9d1036800x7fcb9c825f40524288665098474486226816810410456054168104104239191681041081639716810410834232
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038617678317678341943042560012242058880x7fcb9f7335000x7fcb9c825f80524288661849974124906816810410849251168104108163971681041120711516810411224210
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038917678317678341943042560012242094080x7fcb9f7333800x7fcb9c825fc0524288278668331209692416810411240719168104112071151681041157527416810411577029
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039217678317678341943042560012242144640x7fcb9f7332000x7fcb9c826000524288292394932753208416810411607718168104115752741681041208807116810412105592
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039517678317678341943042560012242177280x7fcb9f7330800x7fcb9c826040524288277832631113778016810412128241168104120880711681041244135016810412442922
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039817678317678341943042560012242220160x7fcb9d103f000x7fcb9c826080524288582360465222401616810412474171168104124413501681041284966816810412868798
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040117678317678341943042560012242260480x7fcb9d103d800x7fcb9c8260c0524288495096155449869616810412882458168104128496681681041326470616810413282255
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040417678317678341943042560012242300800x7fcb9d103c000x7fcb9c826100524288280657631437533616810413297875168104132647061681041366614516810413683843
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040717678317678341943042560012242359040x7fcb9d103a800x7fcb9c826140524288291131432602779616810413698492168104136661451681041423654216810414258945
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041017678317678341943042560012242394240x7fcb9d1039000x7fcb9c826180524288275814130889094016810414278924168104142365421681041461942116810414621074
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041317678317678341943042560012242442240x7fcb9d1037800x7fcb9c8261c0524288497558855720703216810414651923168104146194211681041504853916810415091799
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041617678317678341943042560012242487680x7fcb9d1036000x7fcb9c826200524288328548936794906416810415104289168104150485391681041550261716810415545445
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041917678317678341943042560012242533120x7fcb9f7334800x7fcb9c826240524288279934531353990816810415556075168104155026171681041595045516810415992641
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221767831767834194304256008242555520x7fcb9f7333000x7fcb9c826280524288235823626411254016810416004421168104159504551681041661077216810416652940
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042517678317678341943042560012242598400x7fcb9f7331800x7fcb9c8262c0524288270057430257294416810416671790168104166107721681041704213016810417084127
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042817678317678341943042560012242656640x7fcb9f7330000x7fcb9c826300524288325865136492099616810417095037168104170421301681041754868816810417590591
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043117678317678341943042560012242712320x7fcb9d103e800x7fcb9c826340524288365675140954911216810417602131168104175486881681041805396616810418071816
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341767831767834194304256008242732160x7fcb9d103d000x7fcb9c826380524288239737926851127216810418094395168104180539661681041854852416810418592100
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371767831767834194304256008242757120x7fcb9d103b800x7fcb9c8263c0524288238081426658393216810418602999168104185485241681041931860116810419362586
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044017678317678341943042560012242807680x7fcb9d103a000x7fcb9c826400524288267105429908476416810419382075168104193186011681041979267916810419834431
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044317678317678341943042560012242876160x7fcb9d1038800x7fcb9c826440524288337377537785078416810419845301168104197926791681042035955616810420401743
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044617678317678341943042560012242942080x7fcb9d1037000x7fcb9c826480524288343932338525644416810420412863168104203595561681042091587416810420958186
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491767831767834194304256008242969600x7fcb9f7335800x7fcb9c8264c0524288238580626717651216810420968826168104209158741681042147139216810421513709
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521767831767834194304256008242999680x7fcb9f7334000x7fcb9c826500524288238706126738108816810421524788168104214713921681042233794816810422382012
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551767831767834194304256008243027200x7fcb9f7332800x7fcb9c826540524288239101726774772816810422401241168104223379481681042299810516810423042591
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045817678317678341943042560012243054720x7fcb9f7331000x7fcb9c826580524288260097829124861216810423053901168104229981051681042367170216810423715560
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046117678317678341943042560012243082240x7fcb9d103f800x7fcb9c8265c0524288260996929229340416810423728680168104236717021681042434241916810424385150
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641767831767834194304256008243109760x7fcb9d103e000x7fcb9c826600524288239100726781985616810424395979168104243424191681042500545716810425048359
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671767831767834194304256008243132160x7fcb9d103c800x7fcb9c826640524288240067926886044016810425059599168104250054571681042608289216810426114306
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701767831767834194304256008243159680x7fcb9d103b000x7fcb9c826680524288243351127260816416810426133835168104260827381681042713569316810427204452
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047317678317678341943042560012243187200x7fcb9d1039800x7fcb9c8266c0524288258665428966370816810427215172168104271356931681042825600716810428322457
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047617678317678341943042560012243214720x7fcb9d1038000x7fcb9c826700524288258867728990172016810428333997168104282560071681042938128216810429445782
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791767831767834194304256008243242240x7fcb9d1036800x7fcb9c826740524288242027827109556016810429457572168104293812821681043048479716810430551268
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821767831767834194304256008243264640x7fcb9f7335000x7fcb9c826780524288246931527648552816810430564017168104304847971681043243582816810432502297
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851767831767834194304256008243292160x7fcb9f7333800x7fcb9c8267c0524288245061227447259216810432522276168104324358281681043435053916810434422157
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048817678317678341943042560012243319680x7fcb9f7332000x7fcb9c826800524288261895529327004416810434434556168104343505391681043633357016810436401605
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049117678317678341943042560012243347200x7fcb9f7330800x7fcb9c826840524288262237429367846416810436413165168104363335701681043831356116810438382763
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941767831767834194304256008243374720x7fcb9d103f000x7fcb9c826880524288244335927363310416810438395453168104383135611681044024011216810440310193
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049717678317678341943042560082400x7fcb9d103d800x7fcb9c8268c0524288246264527576054816810440322233168104402401121681044384969616810443926870