Files
rocm-systems/tests/workloads/mixbench/mi100/SQ_INST_LEVEL_SMEM.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

43 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_SMEMSQ_INST_LEVEL_SMEMSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000747744747749335544322560083264640x00x7f064ba041804194304307617239367952812073196115389249120731963600175311207319636033928912073196360448031
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00274774474774932768256002424124800x00x7f064ba3510051222348285931212073196375206414120731963755066531207319637551273312073196375518183
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0047477447477494194304256002424129280x7f077bc5d9000x7f064ba35140655361650082103571212073196375582593120731963757935321207319637592249112073196375926542
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0067477447477494194304256003624136320x7f077bc5d8000x7f064ba35180655361751422261325612073196375998105120731963761772101207319637642808812073196376497393
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0087477447477494194304256002824140800x7f077bc5d7000x7f064ba351c0655361915342456292812073196376531356120731963767197671207319637697384612073196377042325
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00107477447477494194304256002424145280x7f077bc5d6000x7f064ba35200655361801222306795212073196377072241120731963772578441207319637738584412073196377389400
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00127477447477494194304256002424149760x7f077bc5d5000x7f064ba35240655361937722469949612073196377433833120731963776114431207319637774312212073196377746774
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00147477447477494194304256002424154240x7f077bc5d4000x7f064ba352801310722485983194348012073196377828336120731963779925611207319637812376012073196378127451
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00167477447477494194304256002824161280x7f077bc5d3000x7f064ba352c01310722303002948315212073196378178837120731963783563991207319637861367812073196378657116
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00187477447477494194304256002824168320x7f077bc5da000x7f064ba35300655361786742286440812073196378686160120731963788602361207319637911319512073196379155101
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00207477447477494194304256002424175360x7f077bc5d9000x7f064ba353401310722412603080908812073196379180278120731963793744741207319637950519312073196379508988
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00227477447477494194304256002424182400x7f077bc5d8000x7f064ba353801310722559563269800012073196379561015120731963797261521207319637986423112073196379867685
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00247477447477494194304256002424189440x7f077bc5d7000x7f064ba353c01310722439623118948812073196379931073120731963801016701207319638022743012073196380231381
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00267477447477494194304256002824199040x7f077bc5d6000x7f064ba354001310722158642756544812073196380281504120731963804455091207319638070774712073196380774340
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00287477447477494194304256002824206080x7f077bc5d5000x7f064ba35440655361744242224974412073196380802843120731963809765461207319638123014512073196381297542
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00307477447477494194304256002424213120x7f077bc5d4000x7f064ba354801310722476483183269612073196381327267120731963815040631207319638163318312073196381636882
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00327477447477494194304256002424220160x7f077bc5d3000x7f064ba354c01310722507083226652012073196381686334120731963818504621207319638198214112073196381985821
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00347477447477494194304256002424227200x7f077bc5da000x7f064ba355001310722469943155081612073196382050872120731963822152601207319638234869912073196382352512
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00367477447477494194304256002824236800x7f077bc5d9000x7f064ba355401310722130002730473612073196382405240120731963825666181207319638282789712073196382895120
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00387477447477494194304256002824243840x7f077bc5d8000x7f064ba35580655361902902431660012073196382920528120731963831122151207319638336645412073196383434362
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00407477447477494194304256002424250880x7f077bc5d7000x7f064ba355c01310722356843058228812073196383459639120731963836400531207319638377429212073196383778051
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00427477447477494194304256002424257920x7f077bc5d6000x7f064ba356001310722495203177900812073196383830759120731963839896511207319638412453012073196384128422
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00447477447477494194304256002424264960x7f077bc5d5000x7f064ba356401310722397703055103212073196384190417120731963843536491207319638448468912073196384488601
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00467477447477494194304256002824277120x7f077bc5d4000x7f064ba356801310722215822820156012073196384537472120731963846995681207319638495300612073196385022924
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00487477447477494194304256002824284160x7f077bc5d3000x7f064ba356c0655361867262401126412073196385054252120731963852352451207319638549332412073196385561254
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00507477447477494194304256002424291200x7f077bc5da000x7f064ba357001310722458363145765612073196385589847120731963857680421207319638590084212073196385904672
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00527477447477494194304256002424300800x7f077bc5d9000x7f064ba357401310722489303178312012073196385953593120731963861336401207319638627156012073196386275411
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00547477447477494194304256002424307840x7f077bc5d8000x7f064ba357801310722492823196029612073196386338629120731963864989191207319638663011812073196386633657
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00567477447477494194304256002824320000x7f077bc5d7000x7f064ba357c01310721933982475808012073196386684481120731963868561971207319638711203612073196387180102
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00587477447477494194304256002824329600x7f077bc5d6000x7f064ba35800655361777762274844812073196387207373120731963873848341207319638764323312073196387709997
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00607477447477494194304256002424339200x7f077bc5d5000x7f064ba358401310722425983074805612073196387737408120731963879112321207319638809091112073196388094842
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00627477447477494194304256002424348800x7f077bc5d4000x7f064ba358801310722495563210958412073196388145636120731963883097901207319638844594912073196388449761
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00647477447477494194304256002424358400x7f077bc5d3000x7f064ba358c01310722425183085881612073196388511426120731963886710681207319638880210712073196388805693
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00667477447477494194304256002824373120x7f077bc5da000x7f064ba359001310722047502614928012073196388855685120731963890230661207319638928594512073196389353941
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00687477447477494194304256002824382720x7f077bc5d9000x7f064ba35940655361670862140359212073196389383085120731963895579441207319638981458212073196389882013
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00707477447477494194304256002424392320x7f077bc5d8000x7f064ba359801310722477483130900012073196389908993120731963900961811207319639022850012073196390232504
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00727477447477494194304256002424401920x7f077bc5d7000x7f064ba359c01310722431423122828812073196390276556120731963904470591207319639057937812073196390583235
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00747477447477494194304256002424411520x7f077bc5d6000x7f064ba35a001310722510003221452812073196390644900120731963908065771207319639093841712073196390942072
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00767477447477494194304256002824426240x7f077bc5d5000x7f064ba35a401310721988322550907212073196390995371120731963911636961207319639142257412073196391491172
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00787477447477494194304256002824435840x7f077bc5d4000x7f064ba35a80655361716762197860812073196391517692120731963916958531207319639194689212073196391987875
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00807477447477494194304256002424445440x7f077bc5d3000x7f064ba35ac01310722606703321723212073196392016989120731963922134501207319639234401012073196392347894
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00827477447477494194304256002424457600x7f077bc5da000x7f064ba35b001310722556423257376012073196392403197120731963925681691207319639270928812073196392713063
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00847477447477494194304256002424467200x7f077bc5d9000x7f064ba35b401310722416663090896812073196392777903120731963929380871207319639306752612073196393071639
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00867477447477494194304256002824484480x7f077bc5d8000x7f064ba35b801310722063402625075212073196393124397120731963932859251207319639355600412073196393622753
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00887477447477494194304256002824494080x7f077bc5d7000x7f064ba35bc0655361684762155737612073196393649583120731963938315221207319639408784112073196394157727
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00907477447477494194304256002424503680x7f077bc5d6000x7f064ba35c001310722493563186672812073196394186300120731963943609601207319639449375912073196394497599
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00927477447477494194304256002424515840x7f077bc5d5000x7f064ba35c401310722448223142240812073196394548373120731963947169581207319639485599712073196394859712
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00947477447477494194304256002424525440x7f077bc5d4000x7f064ba35c801310722521163242676012073196394921496120731963950859161207319639522191612073196395225972
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00967477447477494194304256002824542720x7f077bc5d3000x7f064ba35cc01310722045782621251212073196395275334120731963954465541207319639570895312073196395750587
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00987477447477494194304256002824554880x7f077bc5da000x7f064ba35d00655361856962373462412073196395779160120731963959537521207319639621135112073196396280291
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001007477447477494194304256002424567040x7f077bc5d9000x7f064ba35d401310722585623316936812073196396307942120731963964814291207319639661646912073196396620613
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001027477447477494194304256002424581760x7f077bc5d8000x7f064ba35d801310722751963518634412073196396673031120731963968323081207319639697054712073196396974311
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001047477447477494194304256002424593920x7f077bc5d7000x7f064ba35dc01310722501423195613612073196397051254120731963972123061207319639734078512073196397344749
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001067477447477494194304256002824613760x7f077bc5d6000x7f064ba35e001310722515223215386412073196397397507120731963975627041207319639782894312073196397895743
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001087477447477494194304256002824625920x7f077bc5d5000x7f064ba35e40655361688382167132012073196397924005120731963981105411207319639836510012073196398433432
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001107477447477494194304256002424638080x7f077bc5d4000x7f064ba35e801310722889503715871212073196398458649120731963986377391207319639877741812073196398781338
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001127477447477494194304256002424652800x7f077bc5d3000x7f064ba35ec01310722411943110623212073196398834006120731963989921371207319639913181612073196399135667
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001147477447477494194304256002424664960x7f077bc5da000x7f064ba35f001310722444363129088012073196399199555120731963993601351207319639949149412073196399495375
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001167477447477494194304256002824684800x7f077bc5d9000x7f064ba35f401310722444663118828812073196399543865120731963997049331207319639997629212073196400043433
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001187477447477494194304256002824696960x7f077bc5d8000x7f064ba35f80655361660502132972012073196400068901120731964002476511207319640050716912073196400574731
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001207477447477494194304256002424709120x7f077bc5d7000x7f064ba35fc01310722536863243444012073196400602632120731964007748481207319640095708712073196400960908
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001227477447477494194304256002424723840x7f077bc5d6000x7f064ba360001310722427123127740012073196401015750120731964011796461207319640131852512073196401322450
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001247477447477494194304256002424736000x7f077bc5d5000x7f064ba360401310722562103267476012073196401385707120731964015444441207319640168428412073196401688220
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001267477447477494194304256002824758400x7f077bc5d4000x7f064ba360801310722357763014140812073196401738934120731964019036421207319640217228112073196402224386
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001287477447477494194304256002824770560x7f077bc5d3000x7f064ba360c0655361914582447070412073196402251236120731964024340401207319640268907912073196402738251
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001307477447477494194304256002424782720x7f077bc5da000x7f064ba361001310722430083096945612073196402764730120731964029377171207319640307003712073196403074085
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001327477447477494194304256002424800000x7f077bc5d9000x7f064ba361401310722129522725359212073196403125039120731964032866761207319640343035512073196403434144
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001347477447477494194304256002424812160x7f077bc5d8000x7f064ba361801310722488963189831212073196403496329120731964036551541207319640378875312073196403792469
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001367477447477494194304256002824834560x7f077bc5d7000x7f064ba361c01310722154702752890412073196403841360120731964040095521207319640428059112073196404329477
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001387477447477494194304256002824849280x7f077bc5d6000x7f064ba36200655361721542200697612073196404357650120731964045337091207319640478650812073196404835327
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001407477447477494194304256002424864000x7f077bc5d5000x7f064ba362401310722488943197878412073196404861897120731964050423471207319640518282612073196405186720
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001427477447477494194304256002424881280x7f077bc5d4000x7f064ba362801310722229622839845612073196405241071120731964053980251207319640554778412073196405551448
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001447477447477494194304256002424896000x7f077bc5d3000x7f064ba362c01310722556963288323212073196405632168120731964057897031207319640591914312073196405922958
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001467477447477494194304256002824920960x7f077bc5da000x7f064ba363001310722057542632308812073196405972981120731964061476221207319640641306012073196406463963
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001487477447477494194304256002824935680x7f077bc5d9000x7f064ba36340655361772302260160012073196406490923120731964066655391207319640692041812073196406969202
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001507477447477494194304256002424950400x7f077bc5d8000x7f064ba363801310722462663157510412073196406995401120731964071756161207319640731433612073196407318291
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001527477447477494194304256002424967680x7f077bc5d7000x7f064ba363c01310722563403286586412073196407366741120731964075349751207319640769161412073196407695451
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001547477447477494194304256002424982400x7f077bc5d6000x7f064ba364001310722682683424861612073196407757276120731964079159331207319640805305212073196408057124
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015674774474774941943042560028241007360x7f077bc5d5000x7f064ba364401310722140022743265612073196408109811120731964082919311207319640856297012073196408609269
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015874774474774941943042560028241022080x7f077bc5d4000x7f064ba36480655361843422360540812073196408636590120731964088077681207319640906584712073196409115059
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016074774474774941943042560024241036800x7f077bc5d3000x7f064ba364c01310722690703454952812073196409139004120731964093215261207319640945608512073196409459980
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016274774474774941943042560024241056640x7f077bc5da000x7f064ba365001310722611063346896812073196409510414120731964096884041207319640985576312073196409859693
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016474774474774941943042560024241071360x7f077bc5d9000x7f064ba365401310722474223153204012073196409921187120731964100871221207319641021944112073196410223128
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016674774474774941943042560028241098880x7f077bc5d8000x7f064ba365801310722128762721799212073196410275516120731964104378401207319641070503912073196410751750
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016874774474774941943042560028241113600x7f077bc5d7000x7f064ba365c0655361756682257932812073196410779392120731964109541581207319641121095612073196411259003
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017074774474774941943042560024241128320x7f077bc5d6000x7f064ba366001310722494963174072012073196411283909120731964114661551207319641159975512073196411603844
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017274774474774941943042560024241148160x7f077bc5d5000x7f064ba366401310722437563128221612073196411656862120731964118119131207319641198567312073196411989490
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017474774474774941943042560024241162880x7f077bc5d4000x7f064ba366801310722606443360148812073196412054211120731964122171911207319641235223112073196412356071
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017674774474774941943042560028241190400x7f077bc5d3000x7f064ba366c01310722144482735536012073196412404692120731964125661501207319641282870812073196412875827
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017874774474774941943042560028241207680x7f077bc5da000x7f064ba36700655361714682185524012073196412899892120731964130866271207319641333798612073196413388540
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018074774474774941943042560024241224960x7f077bc5d9000x7f064ba367401310722603663337932012073196413412494120731964136007051207319641374310412073196413747086
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018274774474774941943042560024241247360x7f077bc5d8000x7f064ba367801310722411423086825612073196413798101120731964139658231207319641414982212073196414156266
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018474774474774941943042560024241264640x7f077bc5d7000x7f064ba367c01310722389043068467212073196414216919120731964143760611207319641451766012073196414521846
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018674774474774941943042560020241279360x7f077bc5d6000x7f064ba368001310722395143077256812073196414571087120731964147366991207319641500197812073196415051019
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018874774474774941943042560028241296640x7f077bc5d5000x7f064ba36840655361709322199403212073196415080864120731964152586161207319641555189512073196415598907
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019074774474774941943042560024241313920x7f077bc5d4000x7f064ba368801310722442203123108812073196415622200120731964157994141207319641593509312073196415939069
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019274774474774941943042560024241336320x7f077bc5d3000x7f064ba368c01310722675203416276812073196415991506120731964161589321207319641635093112073196416401498
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019474774474774941943042560024241353600x7f077bc5da000x7f064ba369001310722410983094359212073196416441452120731964166018101207319641674356912073196416747812
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019674774474774941943042560020241368320x7f077bc5d9000x7f064ba369401310722580683295080812073196416794458120731964169595681207319641724388712073196417293486
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019874774474774941943042560028241385600x7f077bc5d8000x7f064ba36980655361792642284032812073196417319865120731964175027651207319641776228412073196417810196
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020074774474774941943042560024241402880x7f077bc5d7000x7f064ba369c01310722480003166756812073196417834020120731964180104431207319641815156212073196418155708
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020274774474774941943042560024241427840x7f077bc5d6000x7f064ba36a001310722520643223082412073196418211902120731964183738011207319641858388012073196418632694
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020474774474774941943042560024241447680x7f077bc5d5000x7f064ba36a401310722583923302088812073196418671145120731964188294791207319641896899812073196418973157
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020674774474774941943042560020241457280x7f077bc5d4000x7f064ba36a801310722695003454476012073196419031625120731964191950771207319641953283512073196419581647
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020874774474774941943042560028241477120x7f077bc5d3000x7f064ba36ac0655361867202397633612073196419604790120731964197835541207319642004355312073196420092867
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021074774474774941943042560024241496960x7f077bc5da000x7f064ba36b001310722694003437493612073196420117763120731964202966721207319642043699112073196420440964
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021274774474774941943042560024241521920x7f077bc5d9000x7f064ba36b401310722458623148582412073196420489955120731964206539501207319642088178912073196420929061
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021474774474774941943042560024241541760x7f077bc5d8000x7f064ba36b801310722422703103620012073196420968043120731964211336271207319642127186712073196421276096
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021674774474774941943042560020241556480x7f077bc5d7000x7f064ba36bc01310722495003196238412073196421327541120731964214945861207319642182578412073196421873055
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021874774474774941943042560028241576320x7f077bc5d6000x7f064ba36c00655361735062220245612073196421900586120731964220790631207319642232834112073196422378724
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022074774474774941943042560024241596160x7f077bc5d5000x7f064ba36c401310722693283439053612073196422403601120731964225816201207319642271810012073196422722102
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022274774474774941943042560024241623680x7f077bc5d4000x7f064ba36c801310722446023139372012073196422771534120731964229332071207319642317848612073196423230046
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022474774474774941943042560024241646080x7f077bc5d3000x7f064ba36cc01310722745183514542412073196423267085120731964234293641207319642357000312073196423573294
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022674774474774941943042560020241663360x7f077bc5da000x7f064ba36d001310722643963371121612073196423622095120731964237863221207319642416376112073196424213113
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022874774474774941943042560028241685760x7f077bc5d9000x7f064ba36d40655361874562393970412073196424237288120731964244194391207319642468807812073196424736085
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023074774474774941943042560024241708160x7f077bc5d8000x7f064ba36d801310722448983129432812073196424759448120731964249376771207319642508103712073196425084592
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023274774474774941943042560024241740800x7f077bc5d7000x7f064ba36dc01310722491563198567212073196425138663120731964252986361207319642557879412073196425626249
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023474774474774941943042560024241765760x7f077bc5d6000x7f064ba36e001310722564803275155212073196425663067120731964258352731207319642597303312073196425976489
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023674774474774941943042560020241777920x7f077bc5d5000x7f064ba36e401310722513203212852812073196426036160120731964262101521207319642663383012073196426682211
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023874774474774941943042560028241802880x7f077bc5d4000x7f064ba36e80655361776982273945612073196426711926120731964268885491207319642715478812073196427201926
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024074774474774941943042560024241827840x7f077bc5d3000x7f064ba36ec01310722375863046256812073196427228967120731964274080671207319642754694612073196427550374
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024274774474774941943042560024241863040x7f077bc5da000x7f064ba36f001310722616743330565612073196427600778120731964277679051207319642808390412073196428134149
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024474774474774941943042560024241893120x7f077bc5d9000x7f064ba36f401310722460763153676012073196428181226120731964283447031207319642849718212073196428500690
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024674774474774941943042560020241907840x7f077bc5d8000x7f064ba36f801310722466123161083212073196428552776120731964287122211207319642922965912073196429277333
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024874774474774941943042560028241937920x7f077bc5d7000x7f064ba36fc0655361737942212308812073196429310705120731964294848581207319642978005712073196429828086
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025074774474774941943042560024241968000x7f077bc5d6000x7f064ba370001310722417543107947212073196429861979120731964300291761207319643018485512073196430188386
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025274774474774941943042560024242010880x7f077bc5d5000x7f064ba370401310722422783107917612073196430240542120731964304208541207319643080645212073196430828545
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025474774474774941943042560024242046080x7f077bc5d4000x7f064ba370801310722498463217435212073196430885050120731964310507711207319643122693012073196431230181
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025674774474774941943042560020242060800x7f077bc5d3000x7f064ba370c01310722616763350348012073196431282759120731964314448501207319643205492712073196432103424
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025874774474774941943042560028242096000x7f077bc5da000x7f064ba37100655361881282411279212073196432132237120731964323134861207319643264404412073196432690986
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026074774474774941943042560024242131200x7f077bc5d9000x7f064ba371401310722640783364228812073196432718176120731964328958831207319643307556312073196433079327
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026274774474774941943042560024242181760x7f077bc5d8000x7f064ba371801310722459383157080012073196433130652120731964332926821207319643374916012073196433796209
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026474774474774941943042560024242222080x7f077bc5d7000x7f064ba371c01310722691523458764812073196433837526120731964340001991207319643420115812073196434249962
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026674774474774941943042560020242239360x7f077bc5d6000x7f064ba372001310722629683355458412073196434277273120731964344550771207319643515939412073196435206379
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026874774474774941943042560028242279680x7f077bc5d5000x7f064ba37240655361814062320501612073196435231206120731964354249931207319643582307112073196435869482
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027074774474774941943042560024242320000x7f077bc5d4000x7f064ba372801310722649463388105612073196435896712120731964360849901207319643628770912073196436337161
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027274774474774941943042560024242378240x7f077bc5d3000x7f064ba372c01310722599743320028012073196436368980120731964365401881207319643706690612073196437118582
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027474774474774941943042560024242423680x7f077bc5da000x7f064ba373001310722414563079337612073196437163917120731964373363441207319643756082312073196437607621
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027674774474774941943042560020242435840x7f077bc5d9000x7f064ba373401310722554863279611212073196437633820120731964378062621207319643860577912073196438658123
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027874774474774941943042560028242481280x7f077bc5d8000x7f064ba37380655361726562207760012073196438686456120731964388616181207319643928305612073196439334710
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028074774474774941943042560024242526720x7f077bc5d7000x7f064ba373c01310722632243376349612073196439363133120731964395387351207319643976481412073196439812037
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028274774474774941943042560024242592640x7f077bc5d6000x7f064ba374001310722431483129359212073196439839578120731964400137731207319644061073112073196440659332
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028474774474774941943042560024242648320x7f077bc5d5000x7f064ba374401310722390663075096012073196440698975120731964408593691207319644112864812073196441179147
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028674774474774941943042560020242663040x7f077bc5d4000x7f064ba374801310722527903209092012073196441203643120731964413868871207319644237184312073196442440311
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028874774474774941943042560028242718720x7f077bc5d3000x7f064ba374c0655361697842167744812073196442472000120731964426520021207319644316608012073196443234106
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029074774474774941943042560024242774400x7f077bc5da000x7f064ba375001310722444723125778412073196443266877120731964434399981207319644371247712073196443780351
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029274774474774941943042560012242799360x7f077bc5d9000x7f064ba375401310722451563120137612073196443811919120731964439788761207319644471775312073196444787793
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029474774474774941943042560024242865280x7f077bc5d8000x7f064ba375801310722489003164682412073196444831434120731964449934321207319644530943112073196445376316
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029674774474774941943042560020242880000x7f077bc5d7000x7f064ba375c01310722680103395248012073196445403897120731964455833491207319644675518412073196446824036
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029874774474774941943042560032242945920x7f077bc5d6000x7f064ba37600655361893742419122412073196446855625120731964470403031207319644765038112073196447719610
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030074774474774941943042560024243011840x7f077bc5d5000x7f064ba376401310722417543112349612073196447744126120731964479284591207319644824733812073196448317431
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030274774474774941943042560012243049600x7f077bc5d4000x7f064ba376801310722447823132778412073196448342708120731964485226971207319644940077312073196449468229
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030474774474774941943042560024243136000x7f077bc5d3000x7f064ba376c01310722452323127540012073196449505559120731964496737321207319645008365012073196450152651
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030674774474774941943042560020243148160x7f077bc5da000x7f064ba377001310722691763458219212073196450183158120731964503598091207319645190892212073196451977341
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030874774474774941943042560020243175680x7f077bc5d9000x7f064ba37740655361625722080565612073196452016384120731964521887611207319645298379812073196453054433
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031074774474774941943042560012243203200x7f077bc5d8000x7f064ba377801310722521883217695212073196453085350120731964532570771207319645367163512073196453738664
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031274774474774941943042560012243240960x7f077bc5d7000x7f064ba377c01310722460143116696812073196453765514120731964539367541207319645509610912073196455165275
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031474774474774941943042560012243288960x7f077bc5d6000x7f064ba378001310722510243204812012073196455210910120731964553754681207319645616250412073196456230194
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031674774474774941943042560020243301120x7f077bc5d5000x7f064ba378401310722469983178911212073196456262454120731964564388231207319645948985012073196459558388
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031874774474774941943042560020243328640x7f077bc5d4000x7f064ba37880655361621562083510412073196459592030120731964597626491207319646130552212073196461374112
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032074774474774941943042560012243356160x7f077bc5d3000x7f064ba378c01310722647163340940012073196461407263120731964615813611207319646237175812073196462439351
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032274774474774941943042560012243393920x7f077bc5da000x7f064ba379001310722346442974992812073196462473083120731964626509571207319646493270712073196465004327
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032474774474774941943042560012243441920x7f077bc5d9000x7f064ba379401310722311002961892012073196465046956120731964652063061207319646674085912073196466808850
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032674774474774941943042560020243454080x7f077bc5d8000x7f064ba379801310722431823099605612073196466840789120731964670246981207319647308211212073196473151896
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032874774474774941943042560020243481600x7f077bc5d7000x7f064ba379c0655361703322184592012073196473184456120731964733625911207319647640529812073196476476884
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033074774474774941943042560012243509120x7f077bc5d6000x7f064ba37a001310722533583255122412073196476505227120731964766868971207319647822641012073196478294341
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332747744747749419430425600122400x7f077bc5d5000x7f064ba37a401310722288982953925612073196478327022120731964784987291207319648302687012073196483098017