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

48 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_CYCLESSQ_BUSY_CYCLESSQ_WAVESGRBM_COUNTGRBM_GUI_ACTIVECPF_CPF_STAT_BUSYCPF_CPF_STAT_STALLCPF_CPF_TCIU_BUSYCPF_CPF_TCIU_STALLCPF_CPF_STAT_IDLECPF_CPF_TCIU_IDLECPF_CMP_UTCL1_STALL_ON_TRANSLATIONDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000163645163645335544322560043241600x00x7fdfc4204280302440029361595242883780493780493780490294300378914016557764036566165606151625161656061540411416557911817657
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00216364516364532768256001224138880x00x7fdfc4223f80277736167364512347163471634716018480030542016557916956253165606202376791656062025111916557917095318
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0051636451636454194304256001224143360x7fdfc71dc3800x7fdfc4223fc013138321208091655361642281642281642280190000165602016557917131416165606203213591656062041383816557917470644
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0081636451636454194304256001624150400x7fdfc71dc2000x7fdfc422400024855922378026655363106983106983106980190800319755016557917507943165606204469581656062062663716557917882409
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00111636451636454194304256001624154880x7fdfc71dc0800x7fdfc422404024742002368582655363092743092743092740187500316622016557917916008165606206519161656062083255516557918305754
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00141636451636454194304256001224159360x7fdfc4b3bf000x7fdfc422408013213361214735655361651661651661651660191000167525016557918340213165606208571951656062095079416557918631362
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00171636451636454194304256001224163840x7fdfc4b3bd800x7fdfc42240c013122321205990655361640281640281640280188800165561016557918664741165606209763941656062106839416557918951481
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00201636451636454194304256001224170880x7fdfc4b3bc000x7fdfc422410013138801210669655361642341642341642340187800163623016557918996799165606211087131656062120055316557919268240
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00231636451636454194304256001624177920x7fdfc4b3ba800x7fdfc422414024609042354799655363076123076123076120189900314933016557919302818165606212256721656062140503116557919671125
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00261636451636454194304256001624184960x7fdfc4b3b9000x7fdfc422418024746642365207655363093323093323093320189200315623016557919703694165606214426311656062162167016557920087600
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00291636451636454194304256001624192000x7fdfc4b3b7800x7fdfc42241c013260881214581655361657601657601657600189000164683016557920119909165606216599091656062175398916557920401549
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00321636451636454194304256001624199040x7fdfc4b3b6000x7fdfc422420013147441210131655361643421643421643420188400164740016557920434648165606217821491656062187526816557920715398
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00351636451636454194304256001224206080x7fdfc71dc4800x7fdfc422424013348561223512655361668561668561668560189700168970016557920757696165606219195881656062201366716557921032766
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00381636451636454194304256001624213120x7fdfc71dc3000x7fdfc422428024848722382560655363106083106083106080184300318011016557921066995165606220461471656062222534616557921440212
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00411636451636454194304256001624220160x7fdfc71dc1800x7fdfc42242c024761202367927655363095143095143095140188100316437016557921473751165606222523851656062243302416557921844727
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00441636451636454194304256001624227200x7fdfc71dc0000x7fdfc422430013113521208115655361639181639181639180184800165027016557921878076165606224592641656062255254316557922159546
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00471636451636454194304256001224234240x7fdfc4b3be800x7fdfc422434013083921206227655361635481635481635480183700165818016557922192895165606225843831656062267718216557922494114
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00501636451636454194304256001224241280x7fdfc4b3bd000x7fdfc422438012994321198698655361624281624281624280180800165429016557922539612165606227107821656062280342116557922812893
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00531636451636454194304256001624248320x7fdfc4b3bb800x7fdfc42243c024663922356223655363082983082983082980180500316316016557922847811165606228322211656062301158016557923186919
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00561636451636454194304256001624255360x7fdfc4b3ba000x7fdfc422440024637682354024655363079703079703079700182300312789016557923220918165606230413401656062322101916557923561986
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00591636451636454194304256001224262400x7fdfc4b3b8800x7fdfc422444013201681212682655361650201650201650200181500164842016557923594894165606232461381656062334021816557923851165
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00621636451636454194304256001224269440x7fdfc4b3b7000x7fdfc422448013134801206768655361641841641841641840180000166942016557923884834165606233683781656062346133716557924138045
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00651636451636454194304256001224276480x7fdfc71dc5800x7fdfc42244c013021681198067655361627701627701627700183500164380016557924178434165606234941371656062358677616557924423495
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00681636451636454194304256001624286080x7fdfc71dc4000x7fdfc422450024676562366095655363084563084563084560187000313142016557924458794165606236229361656062380181516557924797841
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00711636451636454194304256001624293120x7fdfc71dc2800x7fdfc422454024515122347239655363064383064383064380183500313894016557924831320165606238274141656062400773316557925178718
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00741636451636454194304256001224300160x7fdfc71dc1000x7fdfc422458013007601195655655361625941625941625940189000163958016557925212187165606240563731656062414869216557925467667
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077163645163645419430425600824309760x7fdfc4b3bf800x7fdfc42245c013033841197666655361629221629221629220188500166061016557925502076165606241763721656062426837116557925757047
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00801636451636454194304256001224316800x7fdfc4b3be000x7fdfc422460013040561198565655361630061630061630060189100164948016557925797156165606243018111656062439413016557926050916
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00831636451636454194304256001624326400x7fdfc4b3bc800x7fdfc422464024383442329883655363047923047923047920184800312997016557926100265165606244330101656062461252916557926431263
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00861636451636454194304256001224336000x7fdfc4b3bb000x7fdfc422468024359282323517655363044903044903044900187900314144016557926464842165606246378091656062481908716557926808079
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00891636451636454194304256001224345600x7fdfc4b3b9800x7fdfc42246c013063441200163655361632921632921632920187700167533016557926842108165606248459671656062494068716557927095069
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092163645163645419430425600824355200x7fdfc4b3b8000x7fdfc422470013068241198942655361633521633521633520188200167237016557927128688165606249642061656062505844616557927391948
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00951636451636454194304256001224362240x7fdfc4b3b6800x7fdfc422474013036081202289655361629501629501629500182500165015016557927432917165606250909261656062518452516557927685168
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00981636451636454194304256001224371840x7fdfc71dc5000x7fdfc422478024386002332733655363048243048243048240182400312486016557927721227165606252098051656062539028316557928058694
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001011636451636454194304256001224381440x7fdfc71dc3800x7fdfc42247c024482002342186655363060243060243060240184600311635016557928091843165606254163631656062559604216557928432371
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001041636451636454194304256001224391040x7fdfc71dc2000x7fdfc422480013093841203780655361636721636721636720183600166440016557928465110165606256206821656062571348116557928717041
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107163645163645419430425600824403200x7fdfc71dc0800x7fdfc422484013171601209760655361646441646441646440182200168092016557928750730165606257390811656062583220016557929009000
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001101636451636454194304256001224412800x7fdfc4b3bf000x7fdfc422488013085361203845655361635661635661635660182700165454016557929049069165606258661201656062595955916557929304100
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001131636451636454194304256001224422400x7fdfc4b3bd800x7fdfc42248c024303922323686655363037983037983037980183200313029016557929338839165606259845191656062616467816557929674606
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001161636451636454194304256001224432000x7fdfc4b3bc000x7fdfc422490024445042329426655363055623055623055620183900307234016557929708305165606261929981656062637315716557930047553
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119163645163645419430425600824441600x7fdfc4b3ba800x7fdfc422494013091441204233655361636421636421636420181300166127016557930088002165606263984361656062649283616557930345742
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001221636451636454194304256001224453760x7fdfc4b3b9000x7fdfc422498013085041197082655361635621635621635620183400165781016557930379831165606265168361656062661139516557930633492
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001251636451636454194304256001224463360x7fdfc4b3b7800x7fdfc42249c013011921194705655361626481626481626480182100163509016557930674171165606266435551656062673683416557930919382
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001281636451636454194304256001224475520x7fdfc4b3b6000x7fdfc4224a0024305842327015655363038223038223038220185500306181016557930954761165606267619541656062694163316557931287789
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001311636451636454194304256001224485120x7fdfc71dc4800x7fdfc4224a4024230242316781655363028773028773028770182700305266016557931321637165606269669121656062714899116557931658615
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134163645163645419430425600824494720x7fdfc71dc3000x7fdfc4224a8013087521198620655361635931635931635930185400165870016557931691674165606271739511656062726675016557931947135
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001371636451636454194304256001224506880x7fdfc71dc1800x7fdfc4224ac013035681194012655361629451629451629450181900167562016557931981444165606272918701656062738515016557932236595
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001401636451636454194304256001224516480x7fdfc71dc0000x7fdfc4224b0013035361196046655361629411629411629410184100167371016557932278173165606274184291656062751010916557932532924
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001431636451636454194304256001224528640x7fdfc4b3be800x7fdfc4224b4024206882308849655363025853025853025850186900306576016557932566873165606275363481656062771554716557932905551
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001461636451636454194304256001224540800x7fdfc4b3bd000x7fdfc4224b8024077842301574655363009723009723009720192200302710016557932938909165606277421071656062792290616557933274867
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149163645163645419430425600824552960x7fdfc4b3bb800x7fdfc4224bc013135041203252655361641871641871641870185000166519016557933309376165606279475461656062804194516557933561337
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001521636451636454194304256001224567680x7fdfc4b3ba000x7fdfc4224c0013080561204622655361635061635061635060185300165980016557933594936165606280675451656062816258416557933850067
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001551636451636454194304256001224577280x7fdfc4b3b8800x7fdfc4224c4012978641186602655361622321622321622320184200164871016557933890475165606281944241656062828770316557934142526
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001581636451636454194304256001224589440x7fdfc4b3b7000x7fdfc4224c8024058802299539655363007343007343007340185300306752016557934179285165606283141031656062849378216557934517893
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001611636451636454194304256001224601600x7fdfc71dc5800x7fdfc4224cc024008402291254655363001043001043001040183600303598016557934551992165606285185821656062869906016557934893749
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164163645163645419430425600824613760x7fdfc71dc4000x7fdfc4224d0013028241199524655361628521628521628520185700167772016557934926758165606287243401656062881810016557935183949
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001671636451636454194304256001224628480x7fdfc71dc2800x7fdfc4224d4013589681249779655361698701698701698700183400169303016557935217488165606288449791656062894417916557935474349
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001701636451636454194304256001224638080x7fdfc71dc1000x7fdfc4224d8012939921189769655361617481617481617480183900167201016557935515687165606289771381656062907121816557935760688
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001731636451636454194304256001224650240x7fdfc4b3bf800x7fdfc4224dc023982802290982655362997842997842997840182200303610016557935794677165606291000181656062927857616557936130455
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001761636451636454194304256001224662400x7fdfc4b3be000x7fdfc4224e0023874802279333655362984342984342984340182000303532016557936163964165606293051361656062948433516557936500522
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179163645163645419430425600824674560x7fdfc4b3bc800x7fdfc4224e4013050161198182655361631261631261631260181900166189016557936533991165606295086551656062960257416557936785801
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001821636451636454194304256001224689280x7fdfc4b3bb000x7fdfc4224e8014065841294649655361758221758221758220184900174333016557936818660165606296284941656062973233316557937080731
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001851636451636454194304256001224701440x7fdfc4b3b9800x7fdfc4224ec012868401183940655361608541608541608540184300163017016557937121459165606297657731656062985889216557937366011
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001881636451636454194304256001224716160x7fdfc4b3b8000x7fdfc4224f0024283282320245655363035403035403035400187300301780016557937398610165606298825721656063006257116557937743687
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001911636451636454194304256001224728320x7fdfc4b3b6800x7fdfc4224f4023900882277875655362987602987602987600181900303948016557937776816165606301206501656063030080916557938114174
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194163645163645419430425600824740480x7fdfc71dc5000x7fdfc4224f8012932721186511655361616581616581616580183400163726016557938148613165606303259291656063041984816557938406043
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001971636451636454194304256001224757760x7fdfc71dc3800x7fdfc4224fc014722641354711655361840321840321840320181200179045016557938439662165606304452881656063055280716557938709323
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002001636451636454194304256001224769920x7fdfc71dc2000x7fdfc422500012909681186635655361613701613701613700184100165490016557938761591165606305859271656063067984716557939009372
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002031636451636454194304256001224784640x7fdfc71dc0800x7fdfc422504024031042296438655363003873003873003870184600300542016557939044001165606307040061656063088480516557939384138
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002061636451636454194304256001224799360x7fdfc4b3bf000x7fdfc422508024064242298938655363008023008023008020184700302590016557939417757165606309091251656063108960416557939757195
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209163645163645419430425600824814080x7fdfc4b3bd800x7fdfc42250c013036961200778655361629611629611629610181100168614016557939790274165606311145641656063121024316557940046195
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002121636451636454194304256001224831360x7fdfc4b3bc000x7fdfc422510015395681425678655361924451924451924450181400189268016557940078723165606312348831656063135072216557940357223
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002151636451636454194304256001224843520x7fdfc4b3ba800x7fdfc422514012925281186148655361615651615651615650178600166417016557940397992165606313976021656063149216116557940645333
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002181636451636454194304256001224858240x7fdfc4b3b9000x7fdfc422518024049682293005655363006203006203006200179400304038016557940678132165606315177611656063169871916557941026369
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002211636451636454194304256001224872960x7fdfc4b3b7800x7fdfc42251c023984482285224655362998052998052998050185900299257016557941060438165606317255991656063190655816557941406826
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002241636451636454194304256001224887680x7fdfc4b3b6000x7fdfc422520012918161188715655361614761614761614760183500168740016557941439525165606319318381656063202783716557941695575
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002271636451636454194304256001224907520x7fdfc71dc4800x7fdfc422524016238961507154655362029862029862029860184400199376016557941728924165606320537571656063217535616557942006904
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002301636451636454194304256001224919680x7fdfc71dc3000x7fdfc422528013024481190152655361628051628051628050180200165972016557942047263165606322073561656063230111516557942314903
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002331636451636454194304256001224934400x7fdfc71dc1800x7fdfc42252c024239762311705655363029963029963029960183000306413016557942348832165606323249551656063250367416557942697449
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002361636451636454194304256001224949120x7fdfc71dc0000x7fdfc422530023873682282907655362984202984202984200187300299888016557942732318165606325271941656063270719216557943070226
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002391636451636454194304256001224963840x7fdfc4b3be800x7fdfc422534013047761197539655361630961630961630960183800166985016557943103495165606327316721656063282767216557943355236
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002421636451636454194304256001224983680x7fdfc4b3bd000x7fdfc422538016854801573652655362106842106842106840189500209786016557943388115165606328531111656063297919116557943672685
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002451636451636454194304256001224995840x7fdfc4b3bb800x7fdfc42253c012915441186493655361614421614421614420183800165360016557943713403165606330116701656063310575016557943959664
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024816364516364541943042560012241013120x7fdfc4b3ba000x7fdfc422540023976722281597655362997082997082997080183600299847016557943993033165606331385491656063331742816557944330401
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025116364516364541943042560012241027840x7fdfc4b3b8800x7fdfc422544023966322288043655362995782995782995780183500300805016557944364350165606333431881656063352222716557944703428
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025416364516364541943042560012241042560x7fdfc4b3b7000x7fdfc422548012986961191044655361623361623361623360189500166136016557944736186165606335471871656063364174616557944991057
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025716364516364541943042560012241062400x7fdfc71dc5800x7fdfc42254c017551121640902655362193882193882193880180300217002016557945022856165606336659061656063379646516557945315536
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026016364516364541943042560012241077120x7fdfc71dc4000x7fdfc422550012920081187846655361615001615001615000180600167459016557945356724165606338300651656063392350416557945609175
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026316364516364541943042560016241094400x7fdfc71dc2800x7fdfc422554023754322269585655362969282969282969280181200297050016557945642124165606339510241656063413054216557945981592
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026616364516364541943042560016241111680x7fdfc71dc1000x7fdfc422558023793682275899655362974202974202974200180800302296016557946015521165606341550221656063433422116557946363618
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002691636451636454194304256008241128960x7fdfc4b3bf800x7fdfc42255c012975681194920655361621951621951621950179200167353016557946396767165606343595011656063445534016557946650658
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027216364516364541943042560012241151360x7fdfc4b3be000x7fdfc422560018446321724682655362305782305782305780181000228701016557946683527165606344814201656063462013916557946980106
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027516364516364541943042560012241166080x7fdfc4b3bc800x7fdfc422564012934641184243655361616821616821616820178700165557016557947020624165606346522991656063474733816557947272915
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027816364516364541943042560016241183360x7fdfc4b3bb000x7fdfc422568023790962262836655362973862973862973860182500298400016557947304834165606347716581656063495245716557947644752
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028116364516364541943042560016241200640x7fdfc4b3b9800x7fdfc42256c023884322283145655362985532985532985530182600301176016557947676901165606349767771656063515581516557948024368
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028416364516364541943042560012241217920x7fdfc4b3b8000x7fdfc422570013052881203504655361631601631601631600182700167823016557948056207165606351798151656063527693416557948314928
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028716364516364541943042560012241240320x7fdfc4b3b6800x7fdfc422574019128481803402655362391052391052391050184100238055016557948347527165606353015741656063544701316557948652106
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029016364516364541943042560012241255040x7fdfc71dc5000x7fdfc422578012901361185864655361612661612661612660184300164662016557948691955165606354791731656063557533216557948946355
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029316364516364541943042560012241274880x7fdfc71dc3800x7fdfc42257c023870242274788655362983772983772983770182500300581016557948978814165606356009321656063578477116557949318482
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029616364516364541943042560012241292160x7fdfc71dc2000x7fdfc422580023945122280211655362993132993132993130186900300888016557949351761165606358087711656063598893016557949691689
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029916364516364541943042560012241309440x7fdfc71dc0800x7fdfc422584013708001258969655361713491713491713490186400170162016557949724538165606360138891656063611356916557949984618
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030216364516364541943042560012241334400x7fdfc4b3bf000x7fdfc422588020772161962868655362596512596512596510183400256849016557950016947165606361369291656063629212716557950350165
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030516364516364541943042560012241349120x7fdfc4b3bd800x7fdfc42258c012935521186688655361616931616931616930190200166930016557950390044165606363242871656063641948716557950644055
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030816364516364541943042560012241368960x7fdfc4b3bc000x7fdfc422590023801762271579655362975212975212975210189000298410016557950679633165606364436461656063662252516557951018201
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031116364516364541943042560012241388800x7fdfc4b3ba800x7fdfc422594023663602260596655362957942957942957940184400299994016557951051020165606366470051656063682764416557951392028
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031416364516364541943042560012241408640x7fdfc4b3b9000x7fdfc422598014336001321819655361791991791991791990181300176554016557951424307165606368506841656063695788316557951697947
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031716364516364541943042560012241436160x7fdfc4b3b7800x7fdfc42259c022479362127438655362809912809912809910184100277493016557951731156165606369830031656063715340116557952060194
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032016364516364541943042560012241453440x7fdfc4b3b6000x7fdfc4225a0012938641188406655361617321617321617320184400165279016557952100392165606371860411656063728124116557952347233
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032316364516364541943042560012241475840x7fdfc71dc4800x7fdfc4225a4023688642256775655362961072961072961070285700296908016557952379472165606373074801656063748763916557952719740
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032616364516364541943042560012241495680x7fdfc71dc3000x7fdfc4225a8023632402261049655362954042954042954040180300297425016557952752229165606375125991656063769243816557953096797
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032916364516364541943042560012241515520x7fdfc71dc1800x7fdfc4225ac015021441388634655361877671877671877670181400184121016557953129445165606377162771656063782667716557953400916
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033216364516364541943042560012241543040x7fdfc71dc0000x7fdfc4225b0024068082292099655363008503008503008500188700297687016557953433145165606378506771656063803163516557953775962
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033516364516364541943042560012241562880x7fdfc4b3be800x7fdfc4225b4013786881271697655361723351723351723350179100169408016557953815931165606380634751656063816507416557954082651
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033816364516364541943042560012241587840x7fdfc4b3bd000x7fdfc4225b8023890562258939655362986312986312986310180900302238016557954108900165606381906741656063837643316557954455508
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034116364516364541943042560012241610240x7fdfc4b3bb800x7fdfc4225bc023766402263604655362970792970792970790183100300847016557954489047165606384001131656063858603116557954833144
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034416364516364541943042560012241632640x7fdfc4b3ba000x7fdfc4225c0016623281542290655362077902077902077900182300203676016557954865453165606386105111656063873323016557955159423
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034716364516364541943042560012241665280x7fdfc4b3b8800x7fdfc4225c4027337922617965655363417233417233417230181000337109016557955192391165606387572301656063896378916557955582437
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035016364516364541943042560012241685120x7fdfc4b3b7000x7fdfc4225c8014699681361580655361837451837451837450186900183321016557955602457165606390351481656063914602816557955881057
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035316364516364541943042560012241712640x7fdfc71dc5800x7fdfc4225cc023686162239587655362960762960762960760182700298824016557955914316165606391732271656063935626616557956257123
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035616364516364541943042560012241737600x7fdfc71dc4000x7fdfc4225d0023896642267138655362987072987072987070190700301933016557956290152165606393810661656063956874516557956632400
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035916364516364541943042560012241762560x7fdfc71dc2800x7fdfc4225d4018023761690930655362252962252962252960180500222495016557956665349165606395924241656063972698316557956961158
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036216364516364541943042560012241797760x7fdfc71dc1000x7fdfc4225d8030514802935125655363814343814343814340178600378944016557956994667165606397521031656063998410216557957401492
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036516364516364541943042560012241822720x7fdfc4b3bf800x7fdfc4225dc016977681584015655362122202122202122200180500208497016557957427761165606400533811656064018010016557957709951
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036816364516364541943042560012241855360x7fdfc4b3be000x7fdfc4225e0024731602344482655363091443091443091440185800303071016557957741800165606402045801656064039545916557958116277
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037116364516364541943042560012241885440x7fdfc4b3bc800x7fdfc4225e4024963282351789655363120403120403120400188100308777016557958129806165606404202591656064061385716557958517582
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037416364516364541943042560012241915520x7fdfc4b3bb000x7fdfc4225e8021419282022898655362677402677402677400185800263769016557958531082165606406378571656064079785616557958858440
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037716364516364541943042560012241958400x7fdfc4b3b9800x7fdfc4225ec036976643580494655364622074622074622070191100458761016557958891209165606408218561656064110601416557959356412
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038016364516364541943042560012241985920x7fdfc4b3b8000x7fdfc4225f0019470801834880655362433842433842433840182000242357016557959381501165606411540141656064130361216557959686220
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038316364516364541943042560012242023680x7fdfc4b3b6800x7fdfc4225f4026825442564145655363353173353173353170184200332458016557959718539165606413308121656064154089116557960103485
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038616364516364541943042560012242058880x7fdfc71dc5000x7fdfc4225f8026536882508761655363317103317103317100183100326638016557960122445165606415781711656064178728916557960505581
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038916364516364541943042560012242094080x7fdfc71dc3800x7fdfc4225fc024556882346162655363069603069603069600181600304574016557960523420165606418247291656064201096816557960873728
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039216364516364541943042560012242144640x7fdfc71dc2000x7fdfc422600043467764227642655365433465433465433460181200540019016557960906507165606420356071656064237016516557961416748
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039516364516364541943042560012242177280x7fdfc71dc0800x7fdfc422604021746162067807655362718262718262718260183800271929016557961442307165606424402451656064260776316557961776195
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039816364516364541943042560012242220160x7fdfc4b3bf000x7fdfc422608029245362809757655363655663655663655660184200364766016557961808674165606426319231656064286232216557962213240
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040116364516364541943042560012242260480x7fdfc4b3bd800x7fdfc42260c029277042803874655363659623659623659620182300363875016557962231839165606429202411656064315016016557962672453
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040416364516364541943042560012242300800x7fdfc4b3bc000x7fdfc422610027852562670139655363481563481563481560191100344749016557962683233165606432112791656064342247816557963108108
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040716364516364541943042560012242359040x7fdfc4b3ba800x7fdfc422614049990644879339655366248826248826248820183600621835016557963118627165606434807171656064386663516557963715806
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041016364516364541943042560012242394240x7fdfc4b3b9000x7fdfc422618024314162313442655363039263039263039260184800301156016557963734765165606439331941656064412071316557964081463
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041316364516364541943042560012242442240x7fdfc4b3b7800x7fdfc42261c031876963078826655363984613984613984610186000394546016557964114421165606441453531656064439575116557964569325
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041616364516364541943042560012242487680x7fdfc4b3b6000x7fdfc422620031349683019138655363918703918703918700184800387867016557964579355165606444573501656064470582916557965039208
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041916364516364541943042560012242533120x7fdfc71dc4800x7fdfc422624031071042988329655363883873883873883870183000385324016557965049988165606447679081656064500534716557965504102
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004221636451636454194304256008242555520x7fdfc71dc3000x7fdfc422628057552405632356655367194047194047194040180000716623016557965514631165606450419861656064549654316557966175768
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042516364516364541943042560012242598400x7fdfc71dc1800x7fdfc42262c029191522807899655363648933648933648930183900362918016557966195347165606455394231656064576502116557966629521
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042816364516364541943042560012242656640x7fdfc71dc0000x7fdfc422630037600883651110655364700104700104700100185400468080016557966640291165606457999011656064609781916557967150673
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043116364516364541943042560012242712320x7fdfc4b3be800x7fdfc422634037723843664051655364715474715474715470183600468550016557967161532165606461416591656064644005716557967668254
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004341636451636454194304256008242732160x7fdfc4b3bd000x7fdfc422638038702243753711655364837774837774837770179800479924016557967678974165606464806961656064677797416557968184446
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004371636451636454194304256008242757120x7fdfc4b3bb800x7fdfc42263c070520246938837655368815028815028815020184800877915016557968195215165606468363741656064739333016557968959068
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044016364516364541943042560012242807680x7fdfc4b3ba000x7fdfc422640034210803301594655364276344276344276340187800423506016557968978257165606474654891656064772948816557969441080
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044316364516364541943042560012242876160x7fdfc4b3b8800x7fdfc422644043966164291747655365495765495765495760182900547275016557969451850165606477912471656064814116516557969989071
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044616364516364541943042560012242942080x7fdfc4b3b7000x7fdfc422648044071044293206655365508875508875508870183700548408016557970008840165606482102841656064856180216557970569160
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004491636451636454194304256008242969600x7fdfc71dc5800x7fdfc42264c045264404401352655365658045658045658040184100561126016557970580540165606486245211656064897203916557971142379
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004521636451636454194304256008242999680x7fdfc71dc4000x7fdfc4226500833505682190056553610418811041881104188101809001040051016557971153219165606490336391656064969411416557972020038
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004551636451636454194304256008243027200x7fdfc71dc2800x7fdfc422654057824725656876655367228087228087228080188800721071016557972039157165606497643531656065021123016557972685854
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045816364516364541943042560012243054720x7fdfc71dc1000x7fdfc422658057869765674803655367233717233717233710183900721618016557972696574165606502582701656065072274716557973366510
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046116364516364541943042560012243082240x7fdfc4b3bf800x7fdfc42265c057784805660509655367223097223097223090182400718090016557973377619165606507635461656065122642316557974021526
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004641636451636454194304256008243109760x7fdfc4b3be000x7fdfc422660058222405699418655367277797277797277790181600725104016557974039726165606512670631656065171874016557974715911
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004671636451636454194304256008243132160x7fdfc4b3bc800x7fdfc422664010952032108143876553613690031369003136900301911001366232016557974727161165606517622601656065263249316557975827451
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004701636451636454194304256008243159680x7fdfc4b3bb000x7fdfc422668010960320108473566553613700391370039137003901804001370316016557975846601165606527052931656065355968716557976922922
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047316364516364541943042560012243187200x7fdfc4b3b9800x7fdfc42266c011004432108625046553613755531375553137555301861001371341016557976935452165606536288071656065451456016557978044562
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047616364516364541943042560012243214720x7fdfc4b3b8000x7fdfc422670010960256108451996553613700311370031137003101840001369595016557978055092165606545809601656065546111416557979169672
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004791636451636454194304256008243242240x7fdfc4b3b6800x7fdfc422674011016648108997196553613770801377080137708001908001372396016557979180631165606555350331656065639550716557980269992
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004821636451636454194304256008243264640x7fdfc71dc5000x7fdfc422678021303928211901936553626629902662990266299001833002662812016557980280912165606564623871656065816125516557982210173
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004851636451636454194304256008243292160x7fdfc71dc3800x7fdfc42267c021354816212250886553626693512669351266935101910002665646016557982229542165606582598141656065992588316557984148353
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048816364516364541943042560012243319680x7fdfc71dc2000x7fdfc422680021362520212414496553626703142670314267031401878002669217016557984159783165606600380421656066176427016557986126542
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049116364516364541943042560012243347200x7fdfc71dc0800x7fdfc422684021365472212343676553626706832670683267068301898002666968016557986138222165606618609091656066357753716557988113561
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004941636451636454194304256008243374720x7fdfc4b3bf000x7fdfc422688021393808212646426553626742252674225267422501869002671350016557988124371165606636776961656066535192516557990052321
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049716364516364541943042560082400x7fdfc4b3bd800x7fdfc42268c042049344419331956553652561675256167525616702183005253196016557990063291165606654391241656066879782116557993672762