Files
rocm-systems/tests/workloads/Axes2/mi200/SQ_INST_LEVEL_SMEM.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

41 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_SMEMSQ_INST_LEVEL_SMEMSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBufferAligned.kd000206069206069335544322560043241600x00x7fd4d72042803670016310823434835298417334968515481173299005487101733511732481917335117440069
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00220606920606932768256001224138880x00x7fd4d7223f80512951041066758417335122621942173351173248191733512275090717335122755808
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0052060692060694194304256001224143360x7fd4da1703800x7fd4d7223fc0655366252847002256817335122790767173351227509071733512311874817335123121248
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0082060692060694194304256001624150400x7fd4da1702000x7fd4d7224000655366563667368634417335123157237173351231187481733512352578817335123528378
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]00112060692060694194304256001624154880x7fd4da1700800x7fd4d7224040655366578087371303217335123561897173351235257881733512392850917335123930697
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00142060692060694194304256001224159360x7fd4d7b11f000x7fd4d7224080655366602787401896817335123964226173351239285091733512423474917335124237259
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00172060692060694194304256001224163840x7fd4d7b11d800x7fd4d72240c0655366313207058681617335124269418173351242347491733512453699017335124539271
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00202060692060694194304256001224170880x7fd4d7b11c000x7fd4d72241001310726636467431321617335124583380173351245369901733512483971017335124842093
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00232060692060694194304256001624177920x7fd4d7b11a800x7fd4d72241401310726969947791164017335124873942173351248397101733512522931117335125231602
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00262060692060694194304256001624184960x7fd4d7b119000x7fd4d7224180655366630567433233617335125263892173351252293111733512562019217335125622472
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00292060692060694194304256001624192000x7fd4d7b117800x7fd4d72241c01310726899487715347217335125654281173351256201921733512593699217335125939184
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00322060692060694194304256001624199040x7fd4d7b116000x7fd4d72242001310727161628020044017335125971113173351259369921733512626355317335126266185
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00352060692060694194304256001224206080x7fd4da1704800x7fd4d72242401310726927567775784017335126306674173351262635531733512657811317335126580407
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00382060692060694194304256001624213120x7fd4da1703000x7fd4d72242801310726969967800220017335126611616173351265781131733512697059417335126972946
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00412060692060694194304256001624220160x7fd4da1701800x7fd4d72242c0655366543307328407217335127007995173351269705941733512737107517335127372766
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00442060692060694194304256001624227200x7fd4da1700000x7fd4d72243001310727027307876540017335127404305173351273710751733512764483517335127646699
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00472060692060694194304256001224234240x7fd4d7b11e800x7fd4d72243401310727296908178163217335127677598173351276448351733512792051517335127922081
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00502060692060694194304256001224241280x7fd4d7b11d000x7fd4d72243801310726998627830172017335127960540173351279205151733512820323617335128205094
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00532060692060694194304256001624248320x7fd4d7b11b800x7fd4d72243c01310726951567802523217335128238413173351282032361733512856899617335128570724
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00562060692060694194304256001624255360x7fd4d7b11a000x7fd4d7224400655366203486951665617335128602843173351285689961733512894195717335128943624
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00592060692060694194304256001224262400x7fd4d7b118800x7fd4d72244401310726896447740312017335128976164173351289419571733512921795817335129219617
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00622060692060694194304256001224269440x7fd4d7b117000x7fd4d72244801310726924187766889617335129251076173351292179581733512949283817335129494480
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00652060692060694194304256001224276480x7fd4da1705800x7fd4d72244c01310726961827799524017335129533389173351294928381733512976915817335129770853
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00682060692060694194304256001624286080x7fd4da1704000x7fd4d72245001310726877447696288817335129803162173351297691581733513013427917335130136593
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00712060692060694194304256001624293120x7fd4da1702800x7fd4d7224540655366649867437957617335130168082173351301342791733513049988017335130501703
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00742060692060694194304256001224300160x7fd4da1701000x7fd4d72245801310726613567414524817335130534043173351304998801733513077380017335130775556
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]0077206069206069419430425600824309760x7fd4d7b11f800x7fd4d72245c01310727067567914428817335130807545173351307738001733513104884017335131050439
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00802060692060694194304256001224316800x7fd4d7b11e000x7fd4d72246001310726900187727463217335131088848173351310488401733513132580117335131327651
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00832060692060694194304256001624326400x7fd4d7b11c800x7fd4d72246401310726549787345540817335131359081173351313258011733513168900217335131690632
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00862060692060694194304256001224336000x7fd4d7b11b000x7fd4d7224680655366696167490931217335131723231173351316890021733513205332217335132055162
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00892060692060694194304256001224345600x7fd4d7b119800x7fd4d72246c01310726808727638991217335132086621173351320533221733513232820317335132330065
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]0092206069206069419430425600824355200x7fd4d7b118000x7fd4d72247001310726922347767510417335132362694173351323282031733513260244317335132604028
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00952060692060694194304256001224362240x7fd4d7b116800x7fd4d72247401310726934787771469617335132642097173351326024431733513287828317335132879900
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00982060692060694194304256001224371840x7fd4da1705000x7fd4d72247801310726741267540164017335132910880173351328782831733513324020417335133241981
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]001012060692060694194304256001224381440x7fd4da1703800x7fd4d72247c0655366572887378980017335133274930173351332402041733513360356517335133605201
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]001042060692060694194304256001224391040x7fd4da1702000x7fd4d72248001310726989867818747217335133637320173351336035651733513388100517335133882754
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00107206069206069419430425600824403200x7fd4da1700800x7fd4d72248401310726884107712563217335133915303173351338810051733513415508617335134156756
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]001102060692060694194304256001224412800x7fd4d7b11f000x7fd4d72248801310726952547807673617335134196665173351341550861733513444628617335134448059
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001132060692060694194304256001224422400x7fd4d7b11d800x7fd4d72248c01310726821907641272017335134479148173351344462861733513481508717335134816709
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]001162060692060694194304256001224432000x7fd4d7b11c000x7fd4d7224900655366170866925441617335134848618173351348150871733513518084717335135182539
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00119206069206069419430425600824441600x7fd4d7b11a800x7fd4d72249401310726917607753109617335135214218173351351808471733513546212817335135463702
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]001222060692060694194304256001224453760x7fd4d7b119000x7fd4d72249801310726902107723900817335135495801173351354621281733513573828817335135740114
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]001252060692060694194304256001224463360x7fd4d7b117800x7fd4d72249c01310726923007745114417335135779463173351357382881733513602068917335136022247
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001282060692060694194304256001224475520x7fd4d7b116000x7fd4d7224a001310726865767684640017335136053446173351360206891733513638468917335136386467
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]001312060692060694194304256001224485120x7fd4da1704800x7fd4d7224a40655366426167192843217335136418597173351363846891733513674661017335136748298
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00134206069206069419430425600824494720x7fd4da1703000x7fd4d7224a801310726586687384411217335136779867173351367466101733513702149017335137023500
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]001372060692060694194304256001224506880x7fd4da1701800x7fd4d7224ac01310726595227383620817335137054620173351370214901733513730325117335137304933
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]001402060692060694194304256001224516480x7fd4da1700000x7fd4d7224b001310726600027387932817335137344062173351373032511733513759045117335137591975
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001432060692060694194304256001224528640x7fd4d7b11e800x7fd4d7224b401310726870107698598417335137623535173351375904511733513795365217335137955226
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]001462060692060694194304256001224540800x7fd4d7b11d000x7fd4d7224b80655366612247402777617335137987305173351379536521733513832437217335138326566
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]00149206069206069419430425600824552960x7fd4d7b11b800x7fd4d7224bc01310726896367720075217335138358035173351383243721733513860629317335138607998
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001522060692060694194304256001224567680x7fd4d7b11a000x7fd4d7224c001310726990687834060017335138640518173351386062931733513888373317335138885421
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001552060692060694194304256001224577280x7fd4d7b118800x7fd4d7224c401310726934067762585617335138924420173351388837331733513915845417335139160124
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001582060692060694194304256001224589440x7fd4d7b117000x7fd4d7224c801310726576047358569617335139192183173351391584541733513951957417335139521114
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001612060692060694194304256001224601600x7fd4da1705800x7fd4d7224cc0655366569227347870417335139552693173351395195741733513988181517335139883505
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]00164206069206069419430425600824613760x7fd4da1704000x7fd4d7224d001310726922587749878417335139915044173351398818151733514015717517335140158907
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001672060692060694194304256001224628480x7fd4da1702800x7fd4d7224d401310726938767773977617335140190806173351401571751733514044325617335140444990
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001702060692060694194304256001224638080x7fd4da1701000x7fd4d7224d801310726947587788896017335140483899173351404432561733514072117617335140722812
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001732060692060694194304256001224650240x7fd4d7b11f800x7fd4d7224dc01310726522087296974417335140754642173351407211761733514108373717335141085313
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001762060692060694194304256001224662400x7fd4d7b11e000x7fd4d7224e00655366179646923644017335141116712173351410837371733514144677717335141448563
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]00179206069206069419430425600824674560x7fd4d7b11c800x7fd4d7224e401310726900967729938417335141479612173351414467771733514172469817335141726316
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001822060692060694194304256001224689280x7fd4d7b11b000x7fd4d7224e801310727003427842948817335141757905173351417246981733514201077817335142012328
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001852060692060694194304256001224701440x7fd4d7b119800x7fd4d7224ec01310726927867756930417335142051137173351420107781733514229093917335142292671
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001882060692060694194304256001224716160x7fd4d7b118000x7fd4d7224f001310726903007738163217335142323950173351422909391733514265573917335142657591
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001912060692060694194304256001224728320x7fd4d7b116800x7fd4d7224f40655366545447339052817335142689640173351426557391733514301734017335143019002
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]00194206069206069419430425600824740480x7fd4da1705000x7fd4d7224f801310726590167383073617335143050131173351430173401733514329814017335143300034
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001972060692060694194304256001224757760x7fd4da1703800x7fd4d7224fc01310727057927896684817335143331913173351432981401733514358790117335143589687
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]002002060692060694194304256001224769920x7fd4da1702000x7fd4d72250001310726866647702836817335143628176173351435879011733514386310117335143865029
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002032060692060694194304256001224784640x7fd4da1700800x7fd4d72250401310726917627753246417335143896439173351438631011733514422614217335144227800
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]002062060692060694194304256001224799360x7fd4d7b11f000x7fd4d7225080655366549447337119217335144260109173351442261421733514458886217335144590440
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]00209206069206069419430425600824814080x7fd4d7b11d800x7fd4d72250c01310726887447713049617335144622299173351445888621733514486614317335144868023
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]002122060692060694194304256001224831360x7fd4d7b11c000x7fd4d72251001310726854667676370417335144898992173351448661431733514516182317335145163605
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]002152060692060694194304256001224843520x7fd4d7b11a800x7fd4d72251401310726860227680266417335145214164173351451618231733514544134417335145443058
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002182060692060694194304256001224858240x7fd4d7b119000x7fd4d72251801310726905907741204017335145473857173351454413441733514581110417335145812738
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]002212060692060694194304256001224872960x7fd4d7b117800x7fd4d72251c0655366588147385329617335145845187173351458111041733514617702517335146178798
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]002242060692060694194304256001224887680x7fd4d7b116000x7fd4d72252001310726948847777468817335146211208173351461770251733514646230517335146464071
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]002272060692060694194304256001224907520x7fd4da1704800x7fd4d72252401310726857147684684017335146496230173351464623051733514676198617335146763693
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]002302060692060694194304256001224919680x7fd4da1703000x7fd4d72252801310726878147698990417335146802582173351467619861733514704070617335147042356
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]002332060692060694194304256001224934400x7fd4da1701800x7fd4d72252c01310726844667661447217335147074735173351470407061733514740534717335147406946
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]002362060692060694194304256001224949120x7fd4da1700000x7fd4d7225300655366551287333853617335147439255173351474053471733514776614817335147767786
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]002392060692060694194304256001224963840x7fd4d7b11e800x7fd4d72253401310726845027678599217335147799425173351477661481733514804214817335148043979
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]002422060692060694194304256001224983680x7fd4d7b11d000x7fd4d72253801310726798527617773617335148075288173351480421481733514834918817335148350831
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]002452060692060694194304256001224995840x7fd4d7b11b800x7fd4d72253c01310726905447739468017335148389170173351483491881733514862662917335148628333
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024820606920606941943042560012241013120x7fd4d7b11a000x7fd4d72254001310726511547291187217335148659673173351486266291733514899334917335148995044
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0025120606920606941943042560012241027840x7fd4d7b118800x7fd4d7225440655366525767308204817335149026453173351489933491733514935543017335149357044
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0025420606920606941943042560012241042560x7fd4d7b117000x7fd4d72254801310726624047418343217335149388633173351493554301733514963143117335149633137
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0025720606920606941943042560012241062400x7fd4da1705800x7fd4d72254c01310726742267545460817335149664686173351496314311733514994615117335149947668
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0026020606920606941943042560012241077120x7fd4da1704000x7fd4d72255001310726673807466838417335149987217173351499461511733515023735117335150239301
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026320606920606941943042560016241094400x7fd4da1702800x7fd4d72255401310726910867751960017335150271140173351502373511733515061079217335150612591
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0026620606920606941943042560016241111680x7fd4da1701000x7fd4d7225580655366884387719527217335150645020173351506107921733515097319317335150974841
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]002692060692060694194304256008241128960x7fd4d7b11f800x7fd4d72255c01310726928427762356817335151006680173351509731931733515125255317335151254334
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0027220606920606941943042560012241151360x7fd4d7b11e000x7fd4d72256001310726968807807312817335151286153173351512525531733515157255417335151574215
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0027520606920606941943042560012241166080x7fd4d7b11c800x7fd4d72256401310726988327831984017335151613794173351515725541733515185607417335151857658
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027820606920606941943042560016241183360x7fd4d7b11b000x7fd4d72256801310726848707668781617335151890017173351518560741733515222631517335152228178
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0028120606920606941943042560016241200640x7fd4d7b119800x7fd4d72256c0655366513967297075217335152259617173351522263151733515258999517335152591578
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0028420606920606941943042560012241217920x7fd4d7b118000x7fd4d72257001310726862407689540817335152622968173351525899951733515286631617335152868051
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0028720606920606941943042560012241240320x7fd4d7b116800x7fd4d72257401310726951127791680017335152899570173351528663161733515319239617335153194232
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0029020606920606941943042560012241255040x7fd4da1705000x7fd4d72257801310726984927828154417335153233591173351531923961733515346919717335153470875
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029320606920606941943042560012241274880x7fd4da1703800x7fd4d72257c01310726876887700975217335153502654173351534691971733515383223717335153834115
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0029620606920606941943042560012241292160x7fd4da1702000x7fd4d7225800655366533007310457617335153865805173351538322371733515419655817335154198176
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0029920606920606941943042560012241309440x7fd4da1700800x7fd4d72258401310726651327446796017335154231555173351541965581733515448375817335154485368
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0030220606920606941943042560012241334400x7fd4d7b11f000x7fd4d72258801310726670227462984017335154517417173351544837581733515482519917335154826859
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0030520606920606941943042560012241349120x7fd4d7b11d800x7fd4d72258c0131072102030611437405617335154866588173351548251991733515511751917335155119081
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030820606920606941943042560012241368960x7fd4d7b11c000x7fd4d72259001310726602827399203217335155150481173351551175191733515547864017335155480242
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0031120606920606941943042560012241388800x7fd4d7b11a800x7fd4d7225940655366534587311657617335155511941173351554786401733515584152117335155843302
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0031420606920606941943042560012241408640x7fd4d7b119000x7fd4d72259801310726881467708437617335155874651173351558415211733515612712117335156128665
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0031720606920606941943042560012241436160x7fd4d7b117800x7fd4d72259c01310726879567698891217335156160794173351561271211733515647656217335156478295
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0032020606920606941943042560012241453440x7fd4d7b116000x7fd4d7225a00131072102254611447206417335156518304173351564765621733515675512217335156756758
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032320606920606941943042560012241475840x7fd4da1704800x7fd4d7225a401310727025687867144017335156788747173351567551221733515712936317335157130938
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0032620606920606941943042560012241495680x7fd4da1703000x7fd4d7225a80655366522847304980817335157162927173351571293631733515749512317335157496848
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0032920606920606941943042560012241515520x7fd4da1701800x7fd4d7225ac01310726576247364788017335157528697173351574951231733515778776417335157789491
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0033220606920606941943042560012241543040x7fd4da1700000x7fd4d7225b001310726614227407895217335157823000173351577877641733515815800417335158160081
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0033520606920606941943042560012241562880x7fd4d7b11e800x7fd4d7225b4013107297475210919436817335158200300173351581580041733515844648517335158448363
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0033820606920606941943042560012241587840x7fd4d7b11d000x7fd4d7225b801310726869727697566417335158480032173351584464851733515880888517335158810504
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0034120606920606941943042560012241610240x7fd4d7b11b800x7fd4d7225bc0655366483327267608817335158841643173351588088851733515917176617335159173414
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0034420606920606941943042560012241632640x7fd4d7b11a000x7fd4d7225c001310726626487418405617335159204613173351591717661733515947800617335159479526
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0034720606920606941943042560012241665280x7fd4d7b118800x7fd4d7225c401310726619987416500817335159510925173351594780061733515986616717335159913085
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0035020606920606941943042560012241685120x7fd4d7b117000x7fd4d7225c80131072101820811395585617335159933144173351598661671733516019768817335160199427
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0035320606920606941943042560012241712640x7fd4da1705800x7fd4d7225cc01310726642747442991217335160231036173351601976881733516056360817335160565197
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0035620606920606941943042560012241737600x7fd4da1704000x7fd4d7225d00655366562647344818417335160598257173351605636081733516092872917335160930448
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0035920606920606941943042560012241762560x7fd4da1702800x7fd4d7225d401310726564047342317617335160962017173351609287291733516125176917335161253639
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0036220606920606941943042560012241797760x7fd4da1701000x7fd4d7225d801310726548827331656817335161285178173351612517691733516166617017335161685688
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0036520606920606941943042560012241822720x7fd4d7b11f800x7fd4d7225dc0131072102001411411610417335161706987173351616661701733516197977017335161981430
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0036820606920606941943042560012241855360x7fd4d7b11e000x7fd4d7225e001310727021907866028017335162012659173351619797701733516236217117335162384149
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0037120606920606941943042560012241885440x7fd4d7b11c800x7fd4d7225e40655366476687260801617335162397909173351623621711733516275113217335162795819
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0037420606920606941943042560012241915520x7fd4d7b11b000x7fd4d7225e801310726542847329980017335162807688173351627511321733516312569217335163127450
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0037720606920606941943042560012241958400x7fd4d7b119800x7fd4d7225ec01310726607027400885617335163159109173351631256921733516359289317335163637606
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0038020606920606941943042560012241985920x7fd4d7b118000x7fd4d7225f00131072102893611538364817335163657926173351635928931733516395625417335163957848
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0038320606920606941943042560012242023680x7fd4d7b116800x7fd4d7225f40131072102008411448179217335163989777173351639562541733516434873417335164390876
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0038620606920606941943042560012242058880x7fd4da1705000x7fd4d7225f80655366569847352799217335164402346173351643487341733516477785517335164819625
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0038920606920606941943042560012242094080x7fd4da1703800x7fd4d7225fc01310726611307408608817335164831565173351647778551733516517561617335165177475
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0039220606920606941943042560012242144640x7fd4da1702000x7fd4d72260001310726601227401621617335165209065173351651756161733516569225617335165711341
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0039520606920606941943042560012242177280x7fd4da1700800x7fd4d7226040131072104929411759296817335165734151173351656922561733516605225717335166053742
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0039820606920606941943042560012242220160x7fd4d7b11f000x7fd4d7226080131072102100611442956817335166092931173351660522571733516648745817335166505440
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0040120606920606941943042560012242260480x7fd4d7b11d800x7fd4d72260c0655366584647401132817335166521740173351664874581733516690585817335166923309
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0040420606920606941943042560012242300800x7fd4d7b11c000x7fd4d72261001310727125667977741617335166939549173351669058581733516730745917335167324448
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0040720606920606941943042560012242359040x7fd4d7b11a800x7fd4d72261401310726558487347189617335167341288173351673074591733516788122017335167901233
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0041020606920606941943042560012242394240x7fd4d7b119000x7fd4d7226180131072103715611636160817335167922453173351678812201733516826394117335168265703
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0041320606920606941943042560012242442240x7fd4d7b117800x7fd4d72261c0131072106628211943272017335168297583173351682639411733516870458117335168721931
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0041620606920606941943042560012242487680x7fd4d7b116000x7fd4d7226200655366477507260858417335168740511173351687045811733516914058217335169158850
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0041920606920606941943042560012242533120x7fd4da1704800x7fd4d72262401310726861927686807217335169175589173351691405821733516956746317335169584729
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]004222060692060694194304256008242555520x7fd4da1703000x7fd4d7226280131072102171611424853617335169601588173351695674631733517020826417335170226651
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0042520606920606941943042560012242598400x7fd4da1701800x7fd4d72262c0131072102490411487935217335170250171173351702082641733517062538417335170666760
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0042820606920606941943042560012242656640x7fd4da1700000x7fd4d722630013107299153011088420017335170678100173351706253841733517113626517335171178436
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0043120606920606941943042560012242712320x7fd4d7b11e800x7fd4d7226340655366613527399374417335171190296173351711362651733517164682617335171688833
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]004342060692060694194304256008242732160x7fd4d7b11d000x7fd4d722638013107298872411095262417335171700122173351716468261733517215562717335172197609
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]004372060692060694194304256008242757120x7fd4d7b11b800x7fd4d72263c0131072102255211456617617335172209209173351721556271733517292282817335172965189
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0044020606920606941943042560012242807680x7fd4d7b11a000x7fd4d7226400131072103074211551071217335172988518173351729228281733517340506917335173448876
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0044320606920606941943042560012242876160x7fd4d7b118800x7fd4d7226440131072102581611469164817335173461216173351734050691733517396715017335173985002
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0044620606920606941943042560012242942080x7fd4d7b117000x7fd4d7226480655366512067304408017335174000471173351739671501733517451355117335174559227
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]004492060692060694194304256008242969600x7fd4da1705800x7fd4d72264c0131072101366611369916017335174571436173351745135511733517507627217335175119942
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]004522060692060694194304256008242999680x7fd4da1704000x7fd4d7226500131072102731011513232017335175131472173351750762721733517594907317335175991999
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]004552060692060694194304256008243027200x7fd4da1702800x7fd4d7226540131072103328811578824817335176011748173351759490731733517660859417335176650672
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0045820606920606941943042560012243054720x7fd4da1701000x7fd4d7226580131072103078411549137617335176662321173351766085941733517728523517335177327034
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0046120606920606941943042560012243082240x7fd4d7b11f800x7fd4d72265c0655366470107250232017335177338673173351772852351733517795627617335177975007
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]004642060692060694194304256008243109760x7fd4d7b11e000x7fd4d7226600131072103531211590664817335177989366173351779562761733517860587717335178650149
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]004672060692060694194304256008243132160x7fd4d7b11c800x7fd4d7226640131072102184011458464817335178662359173351786058771733517969483917335179742410
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]004702060692060694194304256008243159680x7fd4d7b11b000x7fd4d7226680131072102604011482452817335179762359173351796946101733518076597117335180835341
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0047320606920606941943042560012243187200x7fd4d7b119800x7fd4d72266c0131072103485011610704817335180847751173351807659711733518190421217335181968431
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0047620606920606941943042560012243214720x7fd4d7b118000x7fd4d7226700655366531547299391217335181979851173351819042121733518304373317335183110331
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]004792060692060694194304256008243242240x7fd4d7b116800x7fd4d7226740131072102555411473646417335183122980173351830437331733518415557417335184219741
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]004822060692060694194304256008243264640x7fd4da1705000x7fd4d7226780131072102260411447852817335184232281173351841555741733518610149717335186153230
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]004852060692060694194304256008243292160x7fd4da1703800x7fd4d72267c0131072105962011859928817335186174799173351861014971733518801029917335188085559
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0048820606920606941943042560012243319680x7fd4da1702000x7fd4d7226800131072101696211419344017335188097438173351880102991733519000710117335190072356
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0049120606920606941943042560012243347200x7fd4da1700800x7fd4d7226840655366513127292800017335190092115173351900071011733519198198417335192052273
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]004942060692060694194304256008243374720x7fd4d7b11f000x7fd4d7226880131072103194211557336017335192064363173351919819841733519391974617335193984222
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]0049720606920606941943042560082400x7fd4d7b11d800x7fd4d72268c0131072101162811326168017335193996402173351939197461733519753927017335197613877