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

44 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjGRBM_COUNTGRBM_GUI_ACTIVESQ_WAVESSQ_IFETCHSQ_IFETCH_LEVELSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000181588181588335544322560043241600x00x7f5c3c20428038377938377952428847185926807917629818016905275892927169045637585201690542280178716905422915136
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00218158818158832768256001224138880x00x7f5c3c223f8033925339255128192764186082416905428065962169054228017871690542819761416905428202268
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051815881815884194304256001224143360x7f5c3f2773800x7f5c3c223fc0167038167038655369175041394811571482016905428239037169054281976141690542858177316905428584227
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081815881815884194304256001624150400x7f5c3f2772000x7f5c3c2240003173193173196553611141121677861879227216905428624716169054285817731690542900289216905429005184
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111815881815884194304256001624154880x7f5c3f2770800x7f5c3c224040322801322801655369175041394371561690816905429041153169054290028921690542941633116905429422032
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141815881815884194304256001224159360x7f5c3cc19f000x7f5c3c2240801667851667856553610485761586531777875616905429454011169054294163311690542973137116905429733552
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171815881815884194304256001224163840x7f5c3cc19d800x7f5c3c2240c0168987168987655369830401493221663484816905429768471169054297313711690543004593016905430048333
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201815881815884194304256001224170880x7f5c3cc19c000x7f5c3c2241001676281676286553611141121634391824345616905430115641169054300459301690543038032916905430382913
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231815881815884194304256001624177920x7f5c3cc19a800x7f5c3c2241403198673198676553613107201956522186546816905430417972169054303803291690543079408916905430796400
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261815881815884194304256001624184960x7f5c3cc199000x7f5c3c2241803142923142926553611796481766021988159616905430830479169054307940891690543121488816905431217178
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291815881815884194304256001624192000x7f5c3cc197800x7f5c3c2241c01689911689916553612451841930812164161616905431252407169054312148881690543153104716905431533388
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321815881815884194304256001624199040x7f5c3cc196000x7f5c3c2242001668621668626553612451841866752094382016905431568747169054315310471690543184496616905431847109
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351815881815884194304256001224206080x7f5c3f2774800x7f5c3c2242401681031681036553612451841882272107599616905431890898169054318449661690543216224616905432164440
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381815881815884194304256001624213120x7f5c3f2773000x7f5c3c2242803225803225806553614417922338652621060016905432201379169054321622461690543258112516905432585447
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411815881815884194304256001624220160x7f5c3f2771800x7f5c3c2242c03171653171656553613107201992952239882016905432619126169054325811251690543299536416905432997835
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441815881815884194304256001624227200x7f5c3f2770000x7f5c3c2243001679991679996553613762562134652384599616905433033564169054329953641690543331072316905433312895
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471815881815884194304256001224234240x7f5c3cc19e800x7f5c3c2243401677861677866553614417922256792516612016905433348714169054333107231690543362672216905433629186
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501815881815884194304256001224241280x7f5c3cc19d000x7f5c3c2243801668251668256553613107201962212199141216905433671385169054336267221690543395168216905433954116
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531815881815884194304256001624248320x7f5c3cc19b800x7f5c3c2243c03169413169416553615728642350172631613616905433988925169054339516821690543436928116905434371884
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561815881815884194304256001624255360x7f5c3cc19a000x7f5c3c2244003161833161836553614417922088362335868016905434405923169054343692811690543478080016905434782692
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591815881815884194304256001224262400x7f5c3cc198800x7f5c3c2244401681511681516553615073282267802527465216905434818150169054347808001690543506815916905435069753
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621815881815884194304256001224269440x7f5c3cc197000x7f5c3c2244801665911665916553616384002435992733137216905435105122169054350681591690543535583916905435357524
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651815881815884194304256001224276480x7f5c3f2775800x7f5c3c2244c01660671660676553614417922196292462032016905435399603169054353558391690543564399816905435645856
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681815881815884194304256001624286080x7f5c3f2774000x7f5c3c2245003191153191156553617039362528782820389616905435683135169054356439981690543602191716905436025784
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711815881815884194304256001624293120x7f5c3f2772800x7f5c3c2245403154553154556553615728642338082616533216905436058753169054360219171690543640319616905436404853
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741815881815884194304256001224300160x7f5c3f2771000x7f5c3c2245801666791666796553616384002468022761791616905436440162169054364031961690543669983616905436701714
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077181588181588419430425600824309760x7f5c3cc19f800x7f5c3c2245c01688231688236553618350082703723027219616905436737483169054366998361690543699199516905436993786
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801815881815884194304256001224316800x7f5c3cc19e000x7f5c3c2246001677291677296553615073282252012525205216905437035444169054369919951690543727999516905437281697
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831815881815884194304256001624326400x7f5c3cc19c800x7f5c3c2246403146353146356553618350082728883048506416905437318136169054372799951690543765887416905437660776
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861815881815884194304256001224336000x7f5c3cc19b000x7f5c3c2246803137153137156553617039362488712781216416905437695985169054376588741690543803823316905438039814
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891815881815884194304256001224345600x7f5c3cc199800x7f5c3c2246c01703251703256553617694722649792968718816905438074363169054380382331690543833231216905438334065
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092181588181588419430425600824355200x7f5c3cc198000x7f5c3c2247001685871685876553620316163046333409868816905438370594169054383323121690543862191216905438623537
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951815881815884194304256001224362240x7f5c3cc196800x7f5c3c2247401677971677976553616384002474452765398416905438665466169054386219121690543891119116905438912988
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981815881815884194304256001224371840x7f5c3f2775000x7f5c3c2247803125813125816553619660802881243237790416905438948097169054389111911690543928815016905439289817
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011815881815884194304256001224381440x7f5c3f2773800x7f5c3c2247c03144433144436553618350082722833044551216905439326096169054392881501690543966670916905439668405
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041815881815884194304256001224391040x7f5c3f2772000x7f5c3c2248001689971689976553619005442826063168021216905439703134169054396667091690543995630916905439957937
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107181588181588419430425600824403200x7f5c3f2770800x7f5c3c2248401695511695516553622282243282523677891216905439993586169054399563091690544024414816905440246068
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101815881815884194304256001224412800x7f5c3cc19f000x7f5c3c2248801669911669916553617039362547692858275216905440288537169054402441481690544053822716905440539979
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131815881815884194304256001224422400x7f5c3cc19d800x7f5c3c2248c03139833139836553620971523104073480399216905440577538169054405382271690544091742716905440919188
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161815881815884194304256001224432000x7f5c3cc19c000x7f5c3c2249003118453118456553619660802845153187552816905440954197169054409174271690544129406616905441295637
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119181588181588419430425600824441600x7f5c3cc19a800x7f5c3c2249401675371675376553620316163022293385299216905441329936169054412940661690544158334516905441584918
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221815881815884194304256001224453760x7f5c3cc199000x7f5c3c2249801691111691116553624248323618694045922016905441619777169054415833451690544187726516905441878979
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251815881815884194304256001224463360x7f5c3cc197800x7f5c3c2249c01676991676996553618350082715383044919216905441921018169054418772651690544217454416905442176420
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281815881815884194304256001224475520x7f5c3cc196000x7f5c3c224a003099533099536553622282243313153719105616905442212829169054421745441690544255726316905442558999
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311815881815884194304256001224485120x7f5c3f2774800x7f5c3c224a403075213075216553620971523092973461935216905442594538169054425572631690544293134216905442932958
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134181588181588419430425600824494720x7f5c3f2773000x7f5c3c224a801675931675936553621626883185473561983616905442968946169054429313421690544321998216905443221709
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371815881815884194304256001224506880x7f5c3f2771800x7f5c3c224ac01661391661396553626214403866164334220416905443257148169054432199821690544350942116905443511300
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401815881815884194304256001224516480x7f5c3f2770000x7f5c3c224b001669671669676553619660802955183312823616905443554489169054435094211690544379742016905443799122
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431815881815884194304256001224528640x7f5c3cc19e800x7f5c3c224b403108293108296553623592963480253907733616905443834111169054437974201690544417582016905444177570
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461815881815884194304256001224540800x7f5c3cc19d000x7f5c3c224b803066803066806553622282243342593741582816905444212489169054441758201690544455405916905444555809
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149181588181588419430425600824552960x7f5c3cc19b800x7f5c3c224bc01707561707566553622937603429963838473616905444590728169054445540591690544484541816905444847100
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521815881815884194304256001224567680x7f5c3cc19a000x7f5c3c224c001701981701986553627525124129014627624016905444883039169054448454181690544514269816905445144302
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551815881815884194304256001224577280x7f5c3cc198800x7f5c3c224c401691551691556553620316163215253606899216905445186160169054451426981690544543997716905445441703
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581815881815884194304256001224589440x7f5c3cc197000x7f5c3c224c803049943049946553624903683751204195636016905445476902169054454399771690544581741616905445819091
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611815881815884194304256001224601600x7f5c3f2775800x7f5c3c224cc03065153065156553623592963773144231914416905445854780169054458174161690544619357516905446195530
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164181588181588419430425600824613760x7f5c3f2774000x7f5c3c224d001675161675166553624248323708364156357616905446231599169054461935751690544649165516905446493271
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671815881815884194304256001224628480x7f5c3f2772800x7f5c3c224d401727761727766553629491204385474919276416905446528310169054464916551690544678557416905446787332
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701815881815884194304256001224638080x7f5c3f2771000x7f5c3c224d801659481659486553621626883202643595356016905446830301169054467855741690544708221316905447083963
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731815881815884194304256001224650240x7f5c3cc19f800x7f5c3c224dc03047963047966553626214403866734333166416905447121072169054470822131690544745517316905447456772
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761815881815884194304256001224662400x7f5c3cc19e000x7f5c3c224e003045863045866553624903683604644035182416905447492321169054474551731690544783037216905447832001
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179181588181588419430425600824674560x7f5c3cc19c800x7f5c3c224e401700111700116553625559043862544329414016905447866410169054478303721690544812205116905448123672
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821815881815884194304256001224689280x7f5c3cc19b000x7f5c3c224e801764991764996553631457284705435274465216905448158811169054481220511690544841997016905448421723
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851815881815884194304256001224701440x7f5c3cc199800x7f5c3c224ec01666061666066553622282243271103667151216905448463642169054484199701690544871309016905448714705
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881815881815884194304256001224716160x7f5c3cc198000x7f5c3c224f003038803038806553627525124055304543855216905448751623169054487130901690544908620916905449087823
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911815881815884194304256001224728320x7f5c3cc196800x7f5c3c224f403044813044816553626214403879474343800816905449122722169054490862091690544946316816905449464852
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194181588181588419430425600824740480x7f5c3f2775000x7f5c3c224f801683071683076553626869763956154430234016905449499461169054494631681690544975708816905449758793
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971815881815884194304256001224757760x7f5c3f2773800x7f5c3c224fc01838931838936553633423364994905584173616905449794252169054497570881690545006076716905450062354
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001815881815884194304256001224769920x7f5c3f2772000x7f5c3c2250001658491658496553623592963500793919172416905450117402169054500607671690545036316616905450364855
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031815881815884194304256001224784640x7f5c3f2770800x7f5c3c2250403020713020716553628835844286354805176016905450400734169054503631661690545074172516905450743484
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061815881815884194304256001224799360x7f5c3cc19f000x7f5c3c2250803025493025496553626869764031264505694416905450778723169054507417251690545111628516905451117973
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209181588181588419430425600824814080x7f5c3cc19d800x7f5c3c2250c01696251696256553628180484204114701957216905451153951169054511162851690545141084416905451412614
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121815881815884194304256001224831360x7f5c3cc19c000x7f5c3c2251001921951921956553635389445324125970011216905451448363169054514108441690545171724316905451718865
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151815881815884194304256001224843520x7f5c3cc19a800x7f5c3c2251401672191672196553624248323655424094386416905451761203169054517172431690545201612316905452017866
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181815881815884194304256001224858240x7f5c3cc199000x7f5c3c2251803072013072016553630146564547115092608016905452052525169054520161231690545240060216905452402344
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211815881815884194304256001224872960x7f5c3cc197800x7f5c3c2251c03022533022536553628180484161464666264016905452438103169054524006021690545277788116905452779653
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241815881815884194304256001224887680x7f5c3cc196000x7f5c3c2252001702331702336553629491204481375020299616905452814962169054527778811690545306908016905453070894
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271815881815884194304256001224907520x7f5c3f2774800x7f5c3c2252402021832021836553637355525597786275816416905453105353169054530690801690545338284016905453384385
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301815881815884194304256001224919680x7f5c3f2773000x7f5c3c2252801686311686316553625559043940214411250016905453426514169054533828401690545367883916905453680596
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331815881815884194304256001224934400x7f5c3f2771800x7f5c3c2252c03055693055696553631457284629285195941616905453717325169054536788391690545405339816905454055045
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361815881815884194304256001224949120x7f5c3f2770000x7f5c3c2253003043193043196553629491204320764839122816905454096074169054540533981690545444603716905454447753
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391815881815884194304256001224963840x7f5c3cc19e800x7f5c3c2253401694801694806553630801924631925180214816905454481672169054544460371690545474043716905454742064
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421815881815884194304256001224983680x7f5c3cc19d000x7f5c3c2253802105632105636553639321605822676523213616905454776693169054547404371690545506331616905455064885
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451815881815884194304256001224995840x7f5c3cc19b800x7f5c3c2253c01661621661626553626214403953934421735616905455107023169054550633161690545535387616905455355586
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024818158818158841943042560012241013120x7f5c3cc19a000x7f5c3c2254002997552997556553632768004881565464768016905455390295169054553538761690545572635516905455727965
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025118158818158841943042560012241027840x7f5c3cc198800x7f5c3c2254403060863060866553630801924575205118688416905455763304169054557263551690545610443416905456106043
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025418158818158841943042560012241042560x7f5c3cc197000x7f5c3c2254801680131680136553632112644747795309376816905456140792169054561044341690545639563316905456397365
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025718158818158841943042560012241062400x7f5c3f2775800x7f5c3c2254c02187922187926553641287686143926879759616905456432234169054563956331690545671899316905456720825
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026018158818158841943042560012241077120x7f5c3f2774000x7f5c3c2255001665011665016553627525124115124614088016905456763794169054567189931690545701195216905457013626
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026318158818158841943042560016241094400x7f5c3f2772800x7f5c3c2255402993882993886553634078725098005715331616905457049795169054570119521690545738667116905457388415
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026618158818158841943042560016241111680x7f5c3f2771000x7f5c3c2255803012373012376553632112644759065334927616905457423364169054573866711690545776411016905457765803
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691815881815884194304256008241128960x7f5c3cc19f800x7f5c3c2255c01680811680816553632768004923205516644416905457800942169054577641101690545805627016905458057975
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027218158818158841943042560012241151360x7f5c3cc19e000x7f5c3c2256002293762293766553643253766452867218896816905458094524169054580562701690545840074916905458402404
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027518158818158841943042560012241166080x7f5c3cc19c800x7f5c3c2256401678631678636553628180484315894832168816905458444633169054584007491690545869418816905458695986
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027818158818158841943042560016241183360x7f5c3cc19b000x7f5c3c2256802998822998826553635389445249175878818016905458731605169054586941881690545906634816905459067925
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028118158818158841943042560016241200640x7f5c3cc199800x7f5c3c2256c03035053035056553634078725055335663870016905459102684169054590663481690545944026716905459441983
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028418158818158841943042560012241217920x7f5c3cc198000x7f5c3c2257001714561714566553634078725066935678481616905459476612169054594402671690545973578616905459737405
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028718158818158841943042560012241240320x7f5c3cc196800x7f5c3c2257402391542391546553645219846775587590560816905459772484169054597357861690546007338516905460074975
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029018158818158841943042560012241255040x7f5c3f2775000x7f5c3c2257801690081690086553630146564536315076630816905460118013169054600733851690546037146516905460373066
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029318158818158841943042560012241274880x7f5c3f2773800x7f5c3c2257c03015203015206553638010885736206421219616905460408425169054603714651690546075114416905460752844
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029618158818158841943042560012241292160x7f5c3f2772000x7f5c3c2258003029843029846553636700165596386258306816905460788033169054607511441690546112554316905461127253
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029918158818158841943042560012241309440x7f5c3f2770800x7f5c3c2258401724841724846553636700165622496306152016905461162542169054611255431690546142250216905461424144
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030218158818158841943042560012241334400x7f5c3cc19f000x7f5c3c2258802595222595226553649152007408648299670816905461459653169054614225021690546177386216905461775484
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030518158818158841943042560012241349120x7f5c3cc19d800x7f5c3c2258c01697141697146553631457284708155270356016905461818822169054617738621690546207162116905462073195
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030818158818158841943042560012241368960x7f5c3cc19c000x7f5c3c2259003031753031756553640632326051316775343216905462109694169054620716211690546245450016905462456153
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031118158818158841943042560012241388800x7f5c3cc19a800x7f5c3c2259403027393027396553639321605930956637219616905462491312169054624545001690546283001916905462831642
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031418158818158841943042560012241408640x7f5c3cc199000x7f5c3c2259801793691793696553639321605983616702630016905462865501169054628300191690546313369916905463135493
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031718158818158841943042560012241436160x7f5c3cc197800x7f5c3c2259c02803872803876553653084167982298936688016905463170802169054631336991690546349689816905463498562
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032018158818158841943042560012241453440x7f5c3cc196000x7f5c3c225a001683651683656553633423365045885654894416905463540961169054634968981690546379225716905463793973
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032318158818158841943042560012241475840x7f5c3f2774800x7f5c3c225a403019853019856553643253766828477655459216905463830302169054637922571690546417081716905464172462
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032618158818158841943042560012241495680x7f5c3f2773000x7f5c3c225a803021733021736553641943046271527015786016905464208421169054641708171690546454681616905464548441
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032918158818158841943042560012241515520x7f5c3f2771800x7f5c3c225ac01869331869336553641943046263007016569216905464583560169054645468161690546485097516905464852621
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033218158818158841943042560012241543040x7f5c3f2770000x7f5c3c225b002998302998306553657016328524799545245616905464888270169054648509751690546522537416905465226980
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033518158818158841943042560012241562880x7f5c3cc19e800x7f5c3c225b401735021735026553637355525640856319340416905465269219169054652253741690546553273416905465534361
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033818158818158841943042560012241587840x7f5c3cc19d000x7f5c3c225b803038143038146553648496647340568226458816905465568020169054655327341690546591241316905465914040
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034118158818158841943042560012241610240x7f5c3cc19b800x7f5c3c225bc03039203039206553647185927259608129347216905465948239169054659124131690546630649216905466308218
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034418158818158841943042560012241632640x7f5c3cc19a000x7f5c3c225c002071762071766553647185927086917939829616905466343797169054663064921690546662633116905466627898
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034718158818158841943042560012241665280x7f5c3cc198800x7f5c3c225c4034064834064865536648806497112510873006816905466663367169054666263311690546702921016905467052936
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035018158818158841943042560012241685120x7f5c3cc197000x7f5c3c225c801832241832246553641287686197256942456016905467073075169054670292101690546734393016905467345607
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035318158818158841943042560012241712640x7f5c3f2775800x7f5c3c225cc03030363030366553653739528528329556522016905467380786169054673439301690546772456916905467726165
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035618158818158841943042560012241737600x7f5c3f2774000x7f5c3c225d003041043041046553652428808311819306288416905467762284169054677245691690546810312816905468104734
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035918158818158841943042560012241762560x7f5c3f2772800x7f5c3c225d402259262259266553652428807940358899708816905468139283169054681031281690546843240716905468434014
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036218158818158841943042560012241797760x7f5c3f2771000x7f5c3c225d80381982381982655367274496109714212292885616905468469943169054684324071690546886616616905468885251
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036518158818158841943042560012241822720x7f5c3cc19f800x7f5c3c225dc02112422112426553649152007306238175668416905468910890169054688661661690546919768616905469199321
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036818158818158841943042560012241855360x7f5c3cc19e000x7f5c3c225e00306284306284655366422528101926111414030816905469234730169054691976861690546958040516905469581810
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037118158818158841943042560012241885440x7f5c3cc19c800x7f5c3c225e40311163311163655366291456100632111265318016905469617639169054695804051690546996984416905469971668
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037418158818158841943042560012241915520x7f5c3cc19b000x7f5c3c225e8026632426632465536629145694973510626953216905470005877169054699698441690547033128316905470332828
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037718158818158841943042560012241958400x7f5c3cc199800x7f5c3c225ec0461310461310655368847360133914514992465216905470367417169054703312831690547080840216905470829103
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038018158818158841943042560012241985920x7f5c3cc198000x7f5c3c225f002424902424906553657016328836809898620816905470853172169054708084021690547115480116905471156363
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038318158818158841943042560012242023680x7f5c3cc196800x7f5c3c225f40333799333799655367471104119331213376766416905471190892169054711548011690547155800116905471578470
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038618158818158841943042560012242058880x7f5c3f2775000x7f5c3c225f80331646331646655367340032115257112905238416905471593780169054715580011690547196632016905471986418
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038918158818158841943042560012242094080x7f5c3f2773800x7f5c3c225fc0307151307151655367340032111150912443404416905472003057169054719663201690547234903916905472350567
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039218158818158841943042560012242144640x7f5c3f2772000x7f5c3c2260005430485430486553610420224159508217864980016905472386006169054723490391690547287991816905472897131
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039518158818158841943042560012242177280x7f5c3f2770800x7f5c3c22604027266327266365536648806497072910877680416905472924210169054728799181690547324503716905473246650
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039818158818158841943042560012242220160x7f5c3cc19f000x7f5c3c226080365606365606655368519680134339315045457216905473281819169054732450371690547368039616905473697847
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040118158818158841943042560012242260480x7f5c3cc19d800x7f5c3c2260c0364553364553655368388608130442814607277216905473717316169054736803961690547410423516905474122814
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040418158818158841943042560012242300800x7f5c3cc19c000x7f5c3c226100346260346260655368388608129111614460434416905474141633169054741042351690547451303416905474530322
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040718158818158841943042560012242359040x7f5c3cc19a800x7f5c3c2261406243186243186553611993088183147120498368416905474549251169054745130341690547509591316905475114344
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041018158818158841943042560012242394240x7f5c3cc199000x7f5c3c226180304510304510655367274496113676012739258416905475139753169054750959131690547548455216905475486433
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041318158818158841943042560012242442240x7f5c3cc197800x7f5c3c2261c0397574397574655369568256152643017098430416905475520162169054754845521690547592951116905475946969
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041618158818158841943042560012242487680x7f5c3cc196000x7f5c3c226200392020392020655369437184151540316981351216905475966439169054759295111690547637751016905476394986
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041918158818158841943042560012242533120x7f5c3f2774800x7f5c3c226240388032388032655369437184145594916317214416905476415025169054763775101690547681414916905476831233
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221815881815884194304256008242555520x7f5c3f2773000x7f5c3c2262807198437198436553616056320230315425801129216905476850702169054768141491690547746214816905477479174
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042518158818158841943042560012242598400x7f5c3f2771800x7f5c3c2262c0363817363817655368847360135430415171369616905477507013169054774621481690547788630716905477903681
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042818158818158841943042560012242656640x7f5c3f2770000x7f5c3c2263004688684688686553611665408179062120039720416905477923010169054778863071690547837718616905478397106
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043118158818158841943042560012242712320x7f5c3cc19e800x7f5c3c2263404730174730176553611468800185043420723875616905478414816169054783771861690547888358516905478927830
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341815881815884194304256008242732160x7f5c3cc19d000x7f5c3c2263804825784825786553614090240201834022619434416905478939130169054788835851690547940870416905479452595
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371815881815884194304256008242757120x7f5c3cc19b800x7f5c3c2263c08801138801136553619202048275993130910769216905479464074169054794087041690548018678216905480231011
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044018158818158841943042560012242807680x7f5c3cc19a000x7f5c3c2264004269684269686553610420224159448717866109216905480251641169054801867821690548067574116905480719577
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044318158818158841943042560012242876160x7f5c3cc198800x7f5c3c2264405499135499136553613762560224087925111066416905480730847169054806757411690548125446016905481298660
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044618158818158841943042560012242942080x7f5c3cc197000x7f5c3c2264805521005521006553613565952214876624067853216905481310779169054812544601690548182629816905481870493
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491815881815884194304256008242969600x7f5c3f2775800x7f5c3c2264c05633745633746553615466496223450925025651616905481881692169054818262981690548239637716905482440275
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521815881815884194304256008242999680x7f5c3f2774000x7f5c3c226500104026410402646553622347776320937235949250416905482452405169054823963771690548327957516905483323759
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551815881815884194304256008243027200x7f5c3f2772800x7f5c3c2265407234267234266553620250624290888932563658816905483344428169054832795751690548394917416905483992519
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045818158818158841943042560012243054720x7f5c3f2771000x7f5c3c2265807232807232806553620447232295321033082225216905484003829169054839491741690548463781216905484680018
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046118158818158841943042560012243082240x7f5c3cc19f800x7f5c3c2265c07227967227966553619595264281879731573486816905484691708169054846378121690548533957116905485384477
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641815881815884194304256008243109760x7f5c3cc19e000x7f5c3c2266007265627265626553620381696293285232837816416905485396297169054853393891690548602690816905486050987
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671815881815884194304256008243132160x7f5c3cc19c800x7f5c3c226640136892013689206553631522816451491050558151216905486063197169054860269081690548712242416905487166614
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701815881815884194304256008243159680x7f5c3cc19b000x7f5c3c226680137065213706526553638993920558402062553073616905487187353169054871224241690548821906116905488284090
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047318158818158841943042560012243187200x7f5c3cc199800x7f5c3c2266c0137477713747776553639124992560800362809195216905488296130169054882190611690548936321816905489404767
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047618158818158841943042560012243214720x7f5c3cc198000x7f5c3c226700137042013704206553638469632550845461700820816905489416597169054893632181690549047569516905490542243
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791815881815884194304256008243242240x7f5c3cc196800x7f5c3c226740137609513760956553639059456559807062719940016905490554463169054904756951690549160257316905491669389
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821815881815884194304256008243264640x7f5c3f2775000x7f5c3c226780266465426646546553660489728865303196894915616905491680829169054916025731690549356912816905493639850
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851815881815884194304256008243292160x7f5c3f2773800x7f5c3c2267c026697172669717655367726694411057902123850019216905493660299169054935691281690549550592316905495576792
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048818158818158841943042560012243319680x7f5c3f2772000x7f5c3c22680026693282669328655367739801611075445124031734016905495589682169054955059231690549749903816905497565973
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049118158818158841943042560012243347200x7f5c3f2770800x7f5c3c22684026707832670783655367621836810904796122155655216905497578162169054974990381690549947823316905499548523
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941815881815884194304256008243374720x7f5c3cc19f000x7f5c3c22688026741602674160655367733248011074598123975384416905499561443169054994782331690550142222816905501488975
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049718158818158841943042560082400x7f5c3cc19d800x7f5c3c2268c0525842052584206553612025856017194289192578734416905501501295169055014222281690550504077916905505120577