Files
rocm-systems/tests/workloads/Axes4/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.kd000915943915948335544322560083264640x00x7f5764c041804194304311731439885348012076227848839156120762280928329301207622809315676912076228093271172
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00291594391594832768256002424124800x00x7f5764c3510051220536261644812076228108114247120762281084075011207622810841406112076228108419344
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0049159439159484194304256002424129280x7f587084d9000x7f5764c35140655361693962171172012076228108485006120762281087020601207622810883918012076228108842811
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0069159439159484194304256003624136320x7f587084d8000x7f5764c35180655361535461965652812076228108911920120762281090913381207622810934205712076228109409635
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0089159439159484194304256002824140800x7f587084d7000x7f5764c351c0655361657762114615212076228109442025120762281096252561207622810988077512076228109945480
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00109159439159484194304256002424145280x7f587084d6000x7f5764c35200655361673802132854412076228109972731120762281101687741207622811030861312076228110312312
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00129159439159484194304256002424149760x7f587084d5000x7f5764c35240655361411441811563212076228110363878120762281105377321207622811067469212076228110678092
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00149159439159484194304256002424154240x7f587084d4000x7f5764c352801310722541843247946412076228110758071120762281109292501207622811106125012076228111065442
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00169159439159484194304256002824161280x7f587084d3000x7f5764c352c01310721805422314180012076228111117729120762281112828491207622811153772812076228111576802
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00189159439159484194304256002824168320x7f587084da000x7f5764c35300655361682842156860812076228111602991120762281117854071207622811203964612076228112085097
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00209159439159484194304256002424175360x7f587084d9000x7f5764c353401310722219402829975212076228112109101120762281123038041207622811243724412076228112440698
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00229159439159484194304256002424182400x7f587084d8000x7f5764c353801310722522043222898412076228112490610120762281126599631207622811279484212076228112798242
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00249159439159484194304256002424189440x7f587084d7000x7f5764c353c01310722199262815828812076228112861139120762281130326011207622811316156112076228113165214
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00269159439159484194304256002824199040x7f587084d6000x7f5764c354001310721954782503159212076228113217772120762281133844401207622811363803912076228113702573
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00289159439159484194304256002824206080x7f587084d5000x7f5764c35440655361416641816640012076228113728261120762281139081171207622811415835612076228114222639
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00309159439159484194304256002424213120x7f587084d4000x7f5764c354801310722585403294619212076228114251733120762281144282751207622811456043512076228114563793
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00329159439159484194304256002424220160x7f587084d3000x7f5764c354c01310722345703004022412076228114615039120762281147900341207622811492347312076228114927018
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00349159439159484194304256002424227200x7f587084da000x7f5764c355001310722296162939175212076228114988002120762281151577121207622811528939112076228115293439
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00369159439159484194304256002824236800x7f587084d9000x7f5764c355401310721733882220907212076228115342010120762281155130701207622811576602912076228115805711
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00389159439159484194304256002824243840x7f587084d8000x7f5764c35580655361515541935511212076228115829125120762281160149881207622811627434712076228116339343
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00409159439159484194304256002424250880x7f587084d7000x7f5764c355c01310722273002930890412076228116366684120762281165489061207622811668090512076228116684314
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00429159439159484194304256002424257920x7f587084d6000x7f5764c356001310722383443035422412076228116733856120762281169033041207622811703594412076228117039725
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00449159439159484194304256002424264960x7f587084d5000x7f5764c356401310722228162848380012076228117101780120762281172673031207622811739946212076228117403020
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00469159439159484194304256002824277120x7f587084d4000x7f5764c356801310721763262264377612076228117454025120762281176271411207622811787754012076228117942262
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00489159439159484194304256002824284160x7f587084d3000x7f5764c356c0655361582682030072812076228117968872120762281181528991207622811840633812076228118471185
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00509159439159484194304256002424291200x7f587084da000x7f5764c357001310722144862747892812076228118497744120762281186783371207622811880841612076228118811788
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00529159439159484194304256002424300800x7f587084d9000x7f5764c357401310722484983183628812076228118862252120762281190383351207622811917241412076228119176145
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00549159439159484194304256002424307840x7f587084d8000x7f5764c357801310722432203098624812076228119237620120762281193994531207622811953001312076228119533329
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00569159439159484194304256002824320000x7f587084d7000x7f5764c357c01310722015562576949612076228119582791120762281197572121207622812001593112076228120083672
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00589159439159484194304256002824329600x7f587084d6000x7f5764c35800655361542521965099212076228120108608120762281202930501207622812055128812076228120615901
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00609159439159484194304256002424339200x7f587084d5000x7f5764c358401310722200122835992012076228120642861120762281208303271207622812096120712076228120965070
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00629159439159484194304256002424348800x7f587084d4000x7f5764c358801310722236682868733612076228121022507120762281211860061207622812132184512076228121325540
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00649159439159484194304256002424358400x7f587084d3000x7f5764c358c01310722324262972810412076228121388437120762281215540041207622812168600312076228121689456
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00669159439159484194304256002824373120x7f587084da000x7f5764c359001310721749302246832812076228121737836120762281219068021207622812220856112076228122276227
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00689159439159484194304256002824382720x7f587084d9000x7f5764c35940655361409981789285612076228122302385120762281224837601207622812274103912076228122779602
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00709159439159484194304256002424392320x7f587084d8000x7f5764c359801310722222162827988012076228122803897120762281229829581207622812311815712076228123122059
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00729159439159484194304256002424401920x7f587084d7000x7f5764c359c01310722199282815718412076228123173564120762281233447161207622812348135612076228123484993
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00749159439159484194304256002424411520x7f587084d6000x7f5764c35a001310722191062792819212076228123547449120762281237099951207622812388743412076228123891198
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00769159439159484194304256002824426240x7f587084d5000x7f5764c35a401310722032022594668812076228123939157120762281241167131207622812437175212076228124435239
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00789159439159484194304256002824435840x7f587084d4000x7f5764c35a80655361546541983701612076228124461488120762281246395911207622812489574912076228124934607
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00809159439159484194304256002424445440x7f587084d3000x7f5764c35ac01310722195242812199212076228124960235120762281251434281207622812527526812076228125279147
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00829159439159484194304256002424457600x7f587084da000x7f5764c35b001310722257102900605612076228125329511120762281254931871207622812563014612076228125633716
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00849159439159484194304256002424467200x7f587084d9000x7f5764c35b401310722589123306908812076228125693718120762281258541451207622812598966512076228125993465
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00869159439159484194304256002824484480x7f587084d8000x7f5764c35b801310721863522377220812076228126041294120762281262133441207622812648310212076228126520665
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00889159439159484194304256002824494080x7f587084d7000x7f5764c35bc0655361689722167425612076228126545461120762281267242211207622812698198012076228127046452
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00909159439159484194304256002424503680x7f587084d6000x7f5764c35c001310722157162783521612076228127076197120762281272558991207622812738965912076228127392976
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00929159439159484194304256002424515840x7f587084d5000x7f5764c35c401310722494563205241612076228127443109120762281276155781207622812775589712076228127759477
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00949159439159484194304256002424525440x7f587084d4000x7f5764c35c801310722098322677882412076228127819839120762281279853361207622812811813512076228128121991
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00969159439159484194304256002824542720x7f587084d3000x7f5764c35cc01310721735702228761612076228128170551120762281283467741207622812861717312076228128681250
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00989159439159484194304256002824554880x7f587084da000x7f5764c35d00655361541841974177612076228128707018120762281288834121207622812913669112076228129206526
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001009159439159484194304256002424567040x7f587084d9000x7f5764c35d401310722537903251230412076228129231533120762281294082101207622812954020912076228129543503
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001029159439159484194304256002424581760x7f587084d8000x7f5764c35d801310722235522866336812076228129592003120762281297547681207622812989556812076228129899164
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001049159439159484194304256002424593920x7f587084d7000x7f5764c35dc01310722485783182668812076228129960988120762281301293271207622813025956612076228130263601
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001069159439159484194304256002824613760x7f587084d6000x7f5764c35e001310722403683073105612076228130312081120762281304832451207622813074820412076228130811960
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001089159439159484194304256002824625920x7f587084d5000x7f5764c35e40655361691342159347212076228130837407120762281310149231207622813126916212076228131335022
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001109159439159484194304256002424638080x7f587084d4000x7f5764c35e801310722236702873933612076228131361251120762281315451601207622813168564012076228131688900
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001129159439159484194304256002424652800x7f587084d3000x7f5764c35ec01310722457523139265612076228131738241120762281319086791207622813204835812076228132052195
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001149159439159484194304256002424664960x7f587084da000x7f5764c35f001310722236902850533612076228132114911120762281322801971207622813241475712076228132418285
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001169159439159484194304256002824684800x7f587084d9000x7f5764c35f401310722543323259980012076228132467907120762281326337961207622813289459412076228132913896
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001189159439159484194304256002824696960x7f587084d8000x7f5764c35f80655361430281825687212076228132956756120762281331211531207622813337427212076228133422161
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001209159439159484194304256002424709120x7f587084d7000x7f5764c35fc01310722221562834062412076228133450353120762281336253111207622813375427112076228133757674
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001229159439159484194304256002424723840x7f587084d6000x7f5764c360001310722269342916679212076228133807246120762281339734701207622813411106912076228134115109
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001249159439159484194304256002424736000x7f587084d5000x7f5764c360401310722205322825476812076228134177465120762281343424281207622813447634812076228134479947
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001269159439159484194304256002824758400x7f587084d4000x7f5764c360801310721855422383775212076228134526984120762281346985871207622813496514512076228135018968
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001289159439159484194304256002824770560x7f587084d3000x7f5764c360c0655361382581773357612076228135042893120762281352299441207622813548338312076228135531551
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001309159439159484194304256002424782720x7f587084da000x7f5764c361001310722455803128727212076228135556828120762281357345821207622813586818212076228135871733
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001329159439159484194304256002424800000x7f587084d9000x7f5764c361401310721729622219072812076228135921766120762281360926611207622813623618012076228136240218
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001349159439159484194304256002424812160x7f587084d8000x7f5764c361801310722576623281785612076228136302514120762281364622591207622813659393812076228136597532
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001369159439159484194304256002824834560x7f587084d7000x7f5764c361c01310721918182462204012076228136646142120762281368174571207622813708433612076228137132677
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001389159439159484194304256002824849280x7f587084d6000x7f5764c36200655361721642185978412076228137159466120762281373393751207622813759377412076228137639649
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001409159439159484194304256002424864000x7f587084d5000x7f5764c362401310722518483217748812076228137664455120762281378414531207622813798209212076228137985772
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001429159439159484194304256002424881280x7f587084d4000x7f5764c362801310721991182548439212076228138035414120762281382107311207622813836161112076228138365227
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001449159439159484194304256002424896000x7f587084d3000x7f5764c362c01310722208042818033612076228138447901120762281386086501207622813874480912076228138748439
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001469159439159484194304256002824920960x7f587084da000x7f5764c363001310721987802538067212076228138796619120762281389649681207622813923488712076228139285107
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001489159439159484194304256002824935680x7f587084d9000x7f5764c36340655361542081974696012076228139309793120762281395091261207622813976736412076228139786108
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001509159439159484194304256002424950400x7f587084d8000x7f5764c363801310722765443541989612076228139832013120762281399918431207622814012912312076228140132922
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001529159439159484194304256002424967680x7f587084d7000x7f5764c363c01310722231182850049612076228140183867120762281403555221207622814051360112076228140517197
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001549159439159484194304256002424982400x7f587084d6000x7f5764c364001310722529303244827212076228140578220120762281407363201207622814087328012076228140877025
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015691594391594841943042560028241007360x7f587084d5000x7f5764c364401310721732382218640012076228140924864120762281410956791207622814136639712076228141388476
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015891594391594841943042560028241022080x7f587084d4000x7f5764c36480655361645442117712812076228141430594120762281415923171207622814184767512076228141865272
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016091594391594841943042560024241036800x7f587084d3000x7f5764c364c01310722179302799295212076228141911027120762281420719941207622814221071412076228142214291
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016291594391594841943042560024241056640x7f587084da000x7f5764c365001310722796423582764012076228142263362120762281424377531207622814260367212076228142607291
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016491594391594841943042560024241071360x7f587084d9000x7f5764c365401310722345223018491212076228142670689120762281428311911207622814297023012076228142973682
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016691594391594841943042560028241098880x7f587084d8000x7f5764c365801310721715082193004012076228143026410120762281431996691207622814346350812076228143511331
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016891594391594841943042560028241113600x7f587084d7000x7f5764c365c0655361414421814621612076228143536378120762281437142271207622814396446612076228144016209
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017091594391594841943042560024241128320x7f587084d6000x7f5764c366001310722186562811719212076228144041246120762281442211051207622814435950412076228144363154
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017291594391594841943042560024241148160x7f587084d5000x7f5764c366401310722198722804520812076228144412656120762281445791831207622814475262312076228144756235
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017491594391594841943042560024241162880x7f587084d4000x7f5764c366801310722549783271836012076228144818020120762281449763021207622814511134112076228145115362
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017691594391594841943042560028241190400x7f587084d3000x7f5764c366c01310721735642221945612076228145164584120762281453398201207622814560285912076228145649014
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017891594391594841943042560028241207680x7f587084da000x7f5764c36700655361859562378874412076228145676064120762281458508581207622814611261712076228146157950
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018091594391594841943042560024241224960x7f587084d9000x7f5764c367401310722187242789288812076228146184389120762281463706961207622814650365512076228146507359
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018291594391594841943042560024241247360x7f587084d8000x7f5764c367801310722442463117573612076228146557793120762281467218941207622814690477312076228146908404
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018491594391594841943042560024241264640x7f587084d7000x7f5764c367c01310722493603182144812076228146971973120762281471418921207622814728173212076228147285415
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018691594391594841943042560020241279360x7f587084d6000x7f5764c368001310722492523203342412076228147336390120762281475034911207622814776925012076228147814188
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018891594391594841943042560028241296640x7f587084d5000x7f5764c36840655361431541829378412076228147839996120762281480223681207622814827452712076228148321661
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019091594391594841943042560024241313920x7f587084d4000x7f5764c368801310722781143540451212076228148345295120762281485268461207622814866796612076228148671601
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019291594391594841943042560024241336320x7f587084d3000x7f5764c368c01310722208962817093612076228148722005120762281488895651207622814908108412076228149129031
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019491594391594841943042560024241353600x7f587084da000x7f5764c369001310722234782851553612076228149170899120762281493310031207622814947068212076228149474353
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019691594391594841943042560020241368320x7f587084d9000x7f5764c369401310722173282784275212076228149524426120762281496930811207622814997644012076228150022111
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019891594391594841943042560028241385600x7f587084d8000x7f5764c36980655361359121741606412076228150045204120762281502321191207622815048571812076228150530476
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020091594391594841943042560024241402880x7f587084d7000x7f5764c369c01310722178042787243212076228150556254120762281507317971207622815087243612076228150876329
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020291594391594841943042560024241427840x7f587084d6000x7f5764c36a001310722268202880288012076228150928005120762281510935551207622815130347412076228151350921
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020491594391594841943042560024241447680x7f587084d5000x7f5764c36a401310722211962819619212076228151391646120762281515500331207622815168827212076228151692075
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020691594391594841943042560020241457280x7f587084d4000x7f5764c36a801310722249082870810412076228151738972120762281519092311207622815224635012076228152292010
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020891594391594841943042560028241477120x7f587084d3000x7f5764c36ac0655361706582190441612076228152318138120762281524965891207622815275930812076228152805614
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021091594391594841943042560024241496960x7f587084da000x7f5764c36b001310722234002858132012076228152834909120762281530074671207622815314730612076228153151477
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021291594391594841943042560024241521920x7f587084d9000x7f5764c36b401310722215962819077612076228153203283120762281533706651207622815359802412076228153644653
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021491594391594841943042560024241541760x7f587084d8000x7f5764c36b801310722237622860191212076228153686151120762281538463431207622815398266212076228153986048
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021691594391594841943042560020241556480x7f587084d7000x7f5764c36bc01310722496783194928012076228154034849120762281542212211207622815455098012076228154595801
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021891594391594841943042560028241576320x7f587084d6000x7f5764c36c00655361446961840998412076228154622200120762281547984991207622815505753812076228155084780
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022091594391594841943042560024241596160x7f587084d5000x7f5764c36c401310722324562959243212076228155128201120762281552917771207622815542985612076228155433598
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022291594391594841943042560024241623680x7f587084d4000x7f5764c36c801310722173102792838412076228155482098120762281556461201207622815589091912076228155940059
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022491594391594841943042560024241646080x7f587084d3000x7f5764c36cc01310722227662841438412076228155981386120762281561489971207622815628835612076228156292164
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022691594391594841943042560020241663360x7f587084da000x7f5764c36d001310722196122812124812076228156343880120762281565080351207622815688451312076228156930831
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022891594391594841943042560028241685760x7f587084d9000x7f5764c36d40655361686822151504012076228156956238120762281571477121207622815740915112076228157456698
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023091594391594841943042560024241708160x7f587084d8000x7f5764c36d801310722182122789556812076228157481334120762281576581101207622815779827012076228157801679
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023291594391594841943042560024241740800x7f587084d7000x7f5764c36dc01310722307722934522412076228157852544120762281580229091207622815830338712076228158349066
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023491594391594841943042560024241765760x7f587084d6000x7f5764c36e001310722250922892528812076228158386857120762281585569861207622815869762612076228158701321
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023691594391594841943042560020241777920x7f587084d5000x7f5764c36e401310722215522834440812076228158752306120762281589157051207622815933938312076228159386745
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023891594391594841943042560028241802880x7f587084d4000x7f5764c36e80655361527001937618412076228159411661120762281595907421207622815985394112076228159898837
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024091594391594841943042560024241827840x7f587084d3000x7f5764c36ec01310722425743095655212076228159926117120762281601133001207622816025249912076228160256261
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024291594391594841943042560024241863040x7f587084da000x7f5764c36f001310722442363116121612076228160305132120762281604758581207622816079153712076228160837030
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024491594391594841943042560024241893120x7f587084d9000x7f5764c36f401310722510563212713612076228160876463120762281610457761207622816119777512076228161201738
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024691594391594841943042560020241907840x7f587084d8000x7f5764c36f801310722195782783253612076228161252031120762281614184141207622816193553212076228161980966
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024891594391594841943042560028241937920x7f587084d7000x7f5764c36fc0655361400601789820012076228162009219120762281621942511207622816249537012076228162540636
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025091594391594841943042560024241968000x7f587084d6000x7f5764c370001310722177382770272012076228162565392120762281627416091207622816289600812076228162899794
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025291594391594841943042560024242010880x7f587084d5000x7f5764c370401310722199442830148812076228162950117120762281631278471207622816351344512076228163560141
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025491594391594841943042560024242046080x7f587084d4000x7f5764c370801310722239822859284012076228163602830120762281637660841207622816394176412076228163945507
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025691594391594841943042560020242060800x7f587084d3000x7f5764c370c01310722401503055776012076228163993276120762281641710431207622816478096012076228164827616
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025891594391594841943042560028242096000x7f587084da000x7f5764c37100655361679162148199212076228164854236120762281650414391207622816537199812076228165420308
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026091594391594841943042560024242131200x7f587084d9000x7f5764c371401310722182162807173612076228165456485120762281656233561207622816580239612076228165806005
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026291594391594841943042560024242181760x7f587084d8000x7f5764c371801310722601583327140812076228165859825120762281660369551207622816649279312076228166539959
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026491594391594841943042560024242222080x7f587084d7000x7f5764c371c01310722185322809758412076228166587497120762281667543921207622816695423112076228167004542
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026691594391594841943042560020242239360x7f587084d6000x7f5764c372001310722215062819832012076228167032224120762281672169501207622816792062712076228167966790
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026891594391594841943042560028242279680x7f587084d5000x7f5764c37240655361372261756785612076228167988721120762281681822261207622816855518412076228168601470
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027091594391594841943042560024242320000x7f587084d4000x7f5764c372801310722218042831538412076228168633329120762281688084631207622816901198212076228169059471
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027291594391594841943042560024242378240x7f587084d3000x7f5764c372c01310722201382812052812076228169088335120762281692663811207622816979261912076228169841444
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027491594391594841943042560024242423680x7f587084da000x7f5764c373001310722455763149307212076228169880818120762281700462181207622817027149712076228170320154
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027691594391594841943042560020242435840x7f587084d9000x7f5764c373401310722536763251107212076228170345291120762281705262161207622817132429212076228171372079
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027891594391594841943042560028242481280x7f587084d8000x7f5764c37380655361688642159006412076228171397586120762281715772511207622817199788912076228172045160
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028091594391594841943042560024242526720x7f587084d7000x7f5764c373c01310722197542800769612076228172081908120762281722471681207622817247340712076228172519972
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028291594391594841943042560024242592640x7f587084d6000x7f5764c374001310722640723371770412076228172548145120762281727188461207622817331692412076228173385681
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028491594391594841943042560024242648320x7f587084d5000x7f5764c374401310722336562970503212076228173427739120762281735910031207622817386140212076228173927278
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028691594391594841943042560020242663040x7f587084d4000x7f5764c374801310722542783247051212076228173954759120762281741497201207622817513547612076228175204762
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028891594391594841943042560028242718720x7f587084d3000x7f5764c374c0655361417201826726412076228175233716120762281754140351207622817594683312076228176018695
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029091594391594841943042560024242774400x7f587084da000x7f5764c375001310722494563159367212076228176043671120762281762338721207622817650555012076228176570400
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029291594391594841943042560012242799360x7f587084d9000x7f5764c375401310722394263077485612076228176596138120762281767713091207622817750954612076228177576450
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029491594391594841943042560024242865280x7f587084d8000x7f5764c375801310722267022884437612076228177618137120762281777839451207622817809946412076228178170544
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029691594391594841943042560020242880000x7f587084d7000x7f5764c375c01310722200822807708012076228178210338120762281783722621207622817954329812076228179611472
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029891594391594841943042560032242945920x7f587084d6000x7f5764c37600655361653822108430412076228179640636120762281798221761207622818043417412076228180502027
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030091594391594841943042560024243011840x7f587084d5000x7f5764c376401310722173542787680012076228180532984120762281807092131207622818102809112076228181094548
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030291594391594841943042560012243049600x7f587084d4000x7f5764c376801310722487963184249612076228181124524120762281813016901207622818218040612076228182247551
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030491594391594841943042560024243136000x7f587084d3000x7f5764c376c01310722359263011964812076228182291993120762281824602451207622818286856312076228182934537
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030691594391594841943042560020243148160x7f587084da000x7f5764c377001310722184762798637612076228182972017120762281831388021207622818468567612076228184755381
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030891594391594841943042560020243175680x7f587084d9000x7f5764c37740655361404421805484812076228184785638120762281849685551207622818576359112076228185830189
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031091594391594841943042560012243203200x7f587084d8000x7f5764c377801310722210922819196012076228185859844120762281860450301207622818645942812076228186526032
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031291594391594841943042560012243240960x7f587084d7000x7f5764c377c01310722485883163958412076228186551750120762281867307871207622818788950212076228187957302
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031491594391594841943042560012243288960x7f587084d6000x7f5764c378001310722227942852832812076228188000102120762281881699811207622818895605812076228189024535
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031691594391594841943042560020243301120x7f587084d5000x7f5764c378401310722462863159607212076228189061845120762281892230971207622819227284412076228192339947
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031891594391594841943042560020243328640x7f587084d4000x7f5764c37880655361428981830341612076228192367478120762281925501221207622819409107612076228194158877
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032091594391594841943042560012243356160x7f587084d3000x7f5764c378c01310722466223178413612076228194188332120762281943691551207622819515875112076228195225299
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032291594391594841943042560012243393920x7f587084da000x7f5764c379001310722488223189626412076228195253802120762281954453101207622819772850112076228197797139
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032491594391594841943042560012243441920x7f587084d9000x7f5764c379401310722182742804577612076228197844637120762281980116991207622819954705312076228199617502
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032691594391594841943042560020243454080x7f587084d8000x7f5764c379801310722381843065941612076228199651776120762281998240121207622820587726612076228205946775
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032891594391594841943042560020243481600x7f587084d7000x7f5764c379c0655361730642222500812076228205982711120762282061628651207622820920621212076228209275321
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033091594391594841943042560012243509120x7f587084d6000x7f5764c37a001310722783783544358412076228209315185120762282094799711207622821101996412076228211087939
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332915943915948419430425600122400x7f587084d5000x7f5764c37a401310722584143290561612076228211126250120762282112882831207622821581610412076228215883922