Files
rocm-systems/tests/workloads/dev01p3/mi100/SQ_INST_LEVEL_LDS.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

40 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjSQ_INSTS_LDSSQ_INST_LEVEL_LDSSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000931859931864335544322560083264640x00x7fa2f460418000012076538010346649120765382502648361207653825058851512076538250679036
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00293185993186432768256002424124800x00x7fa2f463510000012076538265124998120765382654202631207653826542682312076538265432269
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0049318599318644194304256002424129280x7fa40034b9000x7fa2f463514000012076538265550439120765382657177021207653826585946212076538265863321
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0069318599318644194304256003624136320x7fa40034b8000x7fa2f463518000012076538265960702120765382661417011207653826639386012076538266436517
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0089318599318644194304256002824140800x7fa40034b7000x7fa2f46351c000012076538266503442120765382666700191207653826692665812076538266967535
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00109318599318644194304256002424145280x7fa40034b6000x7fa2f463520000012076538267047314120765382672223371207653826736025712076538267364083
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00129318599318644194304256002424149760x7fa40034b5000x7fa2f463524000012076538267415248120765382676021761207653826773993512076538267743599
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00149318599318644194304256002424154240x7fa40034b4000x7fa2f463528000012076538267827625120765382679954541207653826812649412076538268130448
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00169318599318644194304256002824161280x7fa40034b3000x7fa2f46352c000012076538268181353120765382683629731207653826862233212076538268663349
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00189318599318644194304256002824168320x7fa40034ba000x7fa2f463530000012076538268686803120765382688685721207653826912713112076538269166916
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00209318599318644194304256002424175360x7fa40034b9000x7fa2f463534000012076538269192474120765382693828101207653826951416912076538269517819
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00229318599318644194304256002424182400x7fa40034b8000x7fa2f463538000012076538269567952120765382697532081207653826989144812076538269895021
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00249318599318644194304256002424189440x7fa40034b7000x7fa2f46353c000012076538269962386120765382701348071207653827026504712076538270268876
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00269318599318644194304256002824199040x7fa40034b6000x7fa2f463540000012076538270321033120765382704983261207653827075720512076538270797219
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00289318599318644194304256002824206080x7fa40034b5000x7fa2f463544000012076538270822295120765382710037641207653827125896312076538271299673
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00309318599318644194304256002424213120x7fa40034b4000x7fa2f463548000012076538271323718120765382715063231207653827164168212076538271644946
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00329318599318644194304256002424220160x7fa40034b3000x7fa2f46354c000012076538271694187120765382718690411207653827200632112076538272009935
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00349318599318644194304256002424227200x7fa40034ba000x7fa2f463550000012076538272074865120765382722396001207653827237816012076538272381756
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00369318599318644194304256002824236800x7fa40034b9000x7fa2f463554000012076538272431419120765382726072791207653827286487812076538272904719
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00389318599318644194304256002824243840x7fa40034b8000x7fa2f463558000012076538272928944120765382731258371207653827338455612076538273423935
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00409318599318644194304256002424250880x7fa40034b7000x7fa2f46355c000012076538273449142120765382736317551207653827376519512076538273768696
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00429318599318644194304256002424257920x7fa40034b6000x7fa2f463560000012076538273818950120765382739959141207653827413063412076538274134256
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00449318599318644194304256002424264960x7fa40034b5000x7fa2f463564000012076538274197914120765382743608731207653827449719212076538274500668
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00469318599318644194304256002824277120x7fa40034b4000x7fa2f463568000012076538274549949120765382747237521207653827498215112076538275023490
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00489318599318644194304256002824284160x7fa40034b3000x7fa2f46356c000012076538275049008120765382752327101207653827548902912076538275529341
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00509318599318644194304256002424291200x7fa40034ba000x7fa2f463570000012076538275553195120765382757311081207653827586262812076538275866108
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00529318599318644194304256002424300800x7fa40034b9000x7fa2f463574000012076538275918645120765382761016671207653827623606612076538276239823
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00549318599318644194304256002424307840x7fa40034b8000x7fa2f463578000012076538276302399120765382764619861207653827659558512076538276599061
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00569318599318644194304256002824320000x7fa40034b7000x7fa2f46357c000012076538276648433120765382768303041207653827708998312076538277131201
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00589318599318644194304256002824329600x7fa40034b6000x7fa2f463580000012076538277155907120765382773464631207653827760118212076538277641831
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00609318599318644194304256002424339200x7fa40034b5000x7fa2f463584000012076538277666126120765382778458211207653827797878012076538277982244
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00629318599318644194304256002424348800x7fa40034b4000x7fa2f463588000012076538278033499120765382782128601207653827835157912076538278355388
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00649318599318644194304256002424358400x7fa40034b3000x7fa2f46358c000012076538278416802120765382785770181207653827870821812076538278711821
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00669318599318644194304256002824373120x7fa40034ba000x7fa2f463590000012076538278762766120765382789341371207653827919861612076538279240554
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00689318599318644194304256002824382720x7fa40034b9000x7fa2f463594000012076538279264248120765382794448551207653827969893512076538279739202
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00709318599318644194304256002424392320x7fa40034b8000x7fa2f463598000012076538279762585120765382799451741207653828008437312076538280088041
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00729318599318644194304256002424401920x7fa40034b7000x7fa2f46359c000012076538280141701120765382803158931207653828045861212076538280462397
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00749318599318644194304256002424411520x7fa40034b6000x7fa2f4635a0000012076538280526396120765382806864511207653828082005112076538280823779
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00769318599318644194304256002824426240x7fa40034b5000x7fa2f4635a4000012076538280872360120765382810715701207653828133508912076538281376478
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00789318599318644194304256002824435840x7fa40034b4000x7fa2f4635a8000012076538281400713120765382815798881207653828183892712076538281879283
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00809318599318644194304256002424445440x7fa40034b3000x7fa2f4635ac000012076538281903658120765382820894861207653828222548612076538282229745
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00829318599318644194304256002424457600x7fa40034ba000x7fa2f4635b0000012076538282280930120765382824563651207653828259924512076538282602869
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00849318599318644194304256002424467200x7fa40034b9000x7fa2f4635b4000012076538282664774120765382828248441207653828295876312076538282962498
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00869318599318644194304256002824484480x7fa40034b8000x7fa2f4635b8000012076538283015717120765382831954031207653828346244212076538283504646
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00889318599318644194304256002824494080x7fa40034b7000x7fa2f4635bc000012076538283527729120765382837088411207653828396580012076538284014134
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00909318599318644194304256002424503680x7fa40034b6000x7fa2f4635c0000012076538284041825120765382842205191207653828435139912076538284354617
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00929318599318644194304256002424515840x7fa40034b5000x7fa2f4635c4000012076538284404630120765382845768381207653828472131712076538284724986
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00949318599318644194304256002424525440x7fa40034b4000x7fa2f4635c8000012076538284788504120765382849467571207653828507875612076538285082792
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00969318599318644194304256002824542720x7fa40034b3000x7fa2f4635cc000012076538285134277120765382853232351207653828559411512076538285633847
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00989318599318644194304256002824554880x7fa40034ba000x7fa2f4635d0000012076538285658733120765382858365141207653828608995312076538286133226
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001009318599318644194304256002424567040x7fa40034b9000x7fa2f4635d4000012076538286157070120765382863376321207653828647235212076538286476033
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001029318599318644194304256002424581760x7fa40034b8000x7fa2f4635d8000012076538286527118120765382866987511207653828684355012076538286847264
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001049318599318644194304256002424593920x7fa40034b7000x7fa2f4635dc000012076538286910832120765382870749091207653828720418912076538287208195
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001069318599318644194304256002824613760x7fa40034b6000x7fa2f4635e0000012076538287259000120765382874336281207653828774130712076538287781942
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001089318599318644194304256002824625920x7fa40034b5000x7fa2f4635e4000012076538287805366120765382879821061207653828824082612076538288280840
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001109318599318644194304256002424638080x7fa40034b4000x7fa2f4635e8000012076538288305366120765382884846651207653828862002412076538288623738
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001129318599318644194304256002424652800x7fa40034b3000x7fa2f4635ec000012076538288674002120765382888477031207653828898786312076538288991592
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001149318599318644194304256002424664960x7fa40034ba000x7fa2f4635f0000012076538289053768120765382892222621207653828935970212076538289363504
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001169318599318644194304256002824684800x7fa40034b9000x7fa2f4635f4000012076538289415261120765382895875411207653828985794012076538289898439
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001189318599318644194304256002824696960x7fa40034b8000x7fa2f4635f8000012076538289925299120765382901132991207653829036897812076538290410211
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001209318599318644194304256002424709120x7fa40034b7000x7fa2f4635fc000012076538290438885120765382906169771207653829075217712076538290756025
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001229318599318644194304256002424723840x7fa40034b6000x7fa2f463600000012076538290805326120765382909796961207653829111681612076538291120813
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001249318599318644194304256002424736000x7fa40034b5000x7fa2f463604000012076538291183640120765382913465751207653829148033412076538291484129
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001269318599318644194304256002824758400x7fa40034b4000x7fa2f463608000012076538291533441120765382917084941207653829198001312076538291998676
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001289318599318644194304256002824770560x7fa40034b3000x7fa2f46360c000012076538292048429120765382922235321207653829248641112076538292505348
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001309318599318644194304256002424782720x7fa40034ba000x7fa2f463610000012076538292552045120765382927124901207653829284753012076538292851392
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001329318599318644194304256002424800000x7fa40034b9000x7fa2f463614000012076538292899131120765382930865691207653829323152812076538293235537
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001349318599318644194304256002424812160x7fa40034b8000x7fa2f463618000012076538293300678120765382934585681207653829359200712076538293595777
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001369318599318644194304256002824834560x7fa40034b7000x7fa2f46361c000012076538293645509120765382938201661207653829409040612076538294109973
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001389318599318644194304256002824849280x7fa40034b6000x7fa2f463620000012076538294160978120765382943224051207653829458240412076538294602179
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001409318599318644194304256002424864000x7fa40034b5000x7fa2f463624000012076538294647884120765382948139231207653829495520312076538294958933
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001429318599318644194304256002424881280x7fa40034b4000x7fa2f463628000012076538295010779120765382951913621207653829534336112076538295347365
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001449318599318644194304256002424896000x7fa40034b3000x7fa2f46362c000012076538295430049120765382955915201207653829572384012076538295727713
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001469318599318644194304256002824920960x7fa40034ba000x7fa2f463630000012076538295779309120765382959519991207653829622319812076538296241969
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001489318599318644194304256002824935680x7fa40034b9000x7fa2f463634000012076538296286853120765382964492781207653829671071712076538296729827
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001509318599318644194304256002424950400x7fa40034b8000x7fa2f463638000012076538296776694120765382969430361207653829708191512076538297085979
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001529318599318644194304256002424967680x7fa40034b7000x7fa2f46363c000012076538297136984120765382973094351207653829746831412076538297472147
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001549318599318644194304256002424982400x7fa40034b6000x7fa2f463640000012076538297535004120765382976942331207653829782399312076538297827769
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015693185993186441943042560028241007360x7fa40034b5000x7fa2f463644000012076538297878343120765382980691121207653829833855112076538298358055
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015893185993186441943042560028241022080x7fa40034b4000x7fa2f463648000012076538298403710120765382985651101207653829882574912076538298843418
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016093185993186441943042560024241036800x7fa40034b3000x7fa2f46364c000012076538298888953120765382990591891207653829919438812076538299198589
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016293185993186441943042560024241056640x7fa40034ba000x7fa2f463650000012076538299249153120765382994235071207653829959038712076538299594265
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016493185993186441943042560024241071360x7fa40034b9000x7fa2f463654000012076538299660578120765382998217461207653829995758612076538299961388
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016693185993186441943042560028241098880x7fa40034b8000x7fa2f463658000012076538300016150120765383001956651207653830046366412076538300482337
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016893185993186441943042560028241113600x7fa40034b7000x7fa2f46365c000012076538300529394120765383006926231207653830094798212076538300966097
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017093185993186441943042560024241128320x7fa40034b6000x7fa2f463660000012076538301020357120765383011919811207653830133118112076538301335193
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017293185993186441943042560024241148160x7fa40034b5000x7fa2f463664000012076538301389484120765383015595001207653830173406012076538301737812
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017493185993186441943042560024241162880x7fa40034b4000x7fa2f463668000012076538301806650120765383019673391207653830210253812076538302106408
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017693185993186441943042560028241190400x7fa40034b3000x7fa2f46366c000012076538302158464120765383023330971207653830259453712076538302614222
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017893185993186441943042560028241207680x7fa40034ba000x7fa2f463670000012076538302659496120765383028206161207653830308269512076538303101859
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018093185993186441943042560024241224960x7fa40034b9000x7fa2f463674000012076538303152844120765383033143741207653830344957412076538303453533
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018293185993186441943042560024241247360x7fa40034b8000x7fa2f463678000012076538303504458120765383036769331207653830385981212076538303863777
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018493185993186441943042560024241264640x7fa40034b7000x7fa2f46367c000012076538303927916120765383040926111207653830423261112076538304236720
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018693185993186441943042560020241279360x7fa40034b6000x7fa2f463680000012076538304285912120765383044602901207653830472732912076538304745176
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018893185993186441943042560028241296640x7fa40034b5000x7fa2f463684000012076538304791302120765383049628491207653830522348812076538305241449
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019093185993186441943042560024241313920x7fa40034b4000x7fa2f463688000012076538305289428120765383054559671207653830559020612076538305594145
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019293185993186441943042560024241336320x7fa40034b3000x7fa2f46368c000012076538305642515120765383058151661207653830600908512076538306027491
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019493185993186441943042560024241353600x7fa40034ba000x7fa2f463690000012076538306089126120765383062551641207653830638972412076538306393903
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019693185993186441943042560020241368320x7fa40034b9000x7fa2f463694000012076538306440449120765383066191631207653830690364212076538306922176
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019893185993186441943042560028241385600x7fa40034b8000x7fa2f463698000012076538306967320120765383071378811207653830740268012076538307421364
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020093185993186441943042560024241402880x7fa40034b7000x7fa2f46369c000012076538307466298120765383076285991207653830776363912076538307767478
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020293185993186441943042560024241427840x7fa40034b6000x7fa2f4636a0000012076538307815868120765383079917981207653830820347712076538308221863
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020493185993186441943042560024241447680x7fa40034b5000x7fa2f4636a4000012076538308281424120765383084420371207653830858331612076538308587173
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020693185993186441943042560020241457280x7fa40034b4000x7fa2f4636a8000012076538308634040120765383088140351207653830912203412076538309140472
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020893185993186441943042560028241477120x7fa40034b3000x7fa2f4636ac000012076538309185446120765383093546741207653830961595312076538309633489
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021093185993186441943042560024241496960x7fa40034ba000x7fa2f4636b0000012076538309684584120765383098481121207653830998475112076538309988800
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021293185993186441943042560024241521920x7fa40034b9000x7fa2f4636b4000012076538310041007120765383102196311207653831044907012076538310468302
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021493185993186441943042560024241541760x7fa40034b8000x7fa2f4636b8000012076538310526861120765383106871491207653831082218912076538310826238
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021693185993186441943042560020241556480x7fa40034b7000x7fa2f4636bc000012076538310876351120765383110543481207653831138570712076538311404563
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021893185993186441943042560028241576320x7fa40034b6000x7fa2f4636c0000012076538311451220120765383116111461207653831187130512076538311889555
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022093185993186441943042560024241596160x7fa40034b5000x7fa2f4636c4000012076538311938657120765383121204241207653831225610412076538312260035
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022293185993186441943042560024241623680x7fa40034b4000x7fa2f4636c8000012076538312310549120765383124829831207653831272906212076538312748062
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022493185993186441943042560024241646080x7fa40034b3000x7fa2f4636cc000012076538312812252120765383129802611207653831312026112076538313124523
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022693185993186441943042560020241663360x7fa40034ba000x7fa2f4636d0000012076538313176930120765383133532271207653831372970712076538313750848
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022893185993186441943042560028241685760x7fa40034b9000x7fa2f4636d4000012076538313792455120765383139551451207653831421818512076538314236752
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023093185993186441943042560024241708160x7fa40034b8000x7fa2f4636d8000012076538314285512120765383144482641207653831458810412076538314590850
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023293185993186441943042560024241740800x7fa40034b7000x7fa2f4636dc000012076538314641765120765383148129031207653831509338312076538315112150
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023493185993186441943042560024241765760x7fa40034b6000x7fa2f4636e0000012076538315172773120765383153359421207653831547482212076538315477530
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023693185993186441943042560020241777920x7fa40034b5000x7fa2f4636e4000012076538315528514120765383157010621207653831612650112076538316144380
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023893185993186441943042560028241802880x7fa40034b4000x7fa2f4636e8000012076538316192089120765383163564201207653831662202012076538316638429
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024093185993186441943042560024241827840x7fa40034b3000x7fa2f4636ec000012076538316693481120765383168567391207653831699721912076538317005341
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024293185993186441943042560024241863040x7fa40034ba000x7fa2f4636f0000012076538317050956120765383172370591207653831758105812076538317597713
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024493185993186441943042560024241893120x7fa40034b9000x7fa2f4636f4000012076538317659358120765383178207371207653831797417712076538317976969
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024693185993186441943042560020241907840x7fa40034b8000x7fa2f4636f8000012076538318028685120765383182080971207653831872681612076538318744907
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024893185993186441943042560028241937920x7fa40034b7000x7fa2f4636fc000012076538318793668120765383189541751207653831925641512076538319274292
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025093185993186441943042560024241968000x7fa40034b6000x7fa2f463700000012076538319317222120765383194876141207653831964185412076538319644621
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025293185993186441943042560024242010880x7fa40034b5000x7fa2f463704000012076538319693752120765383198666531207653832028009312076538320297806
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025493185993186441943042560024242046080x7fa40034b4000x7fa2f463708000012076538320359150120765383205228121207653832069977212076538320702559
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025693185993186441943042560020242060800x7fa40034b3000x7fa2f46370c000012076538320752762120765383209258511207653832153721012076538321554533
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025893185993186441943042560028242096000x7fa40034ba000x7fa2f463710000012076538321600870120765383217658501207653832209448912076538322113674
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026093185993186441943042560024242131200x7fa40034b9000x7fa2f463714000012076538322168125120765383223320881207653832251272812076538322515551
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026293185993186441943042560024242181760x7fa40034b8000x7fa2f463718000012076538322564031120765383227495281207653832320616712076538323225171
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026493185993186441943042560024242222080x7fa40034b7000x7fa2f46371c000012076538323294119120765383234596061207653832365960612076538323676441
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026693185993186441943042560020242239360x7fa40034b6000x7fa2f463720000012076538323722246120765383238879251207653832459928412076538324618383
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026893185993186441943042560028242279680x7fa40034b5000x7fa2f463724000012076538324664839120765383248293641207653832520408312076538325221424
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027093185993186441943042560024242320000x7fa40034b4000x7fa2f463728000012076538325275214120765383254418421207653832568248212076538325699343
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027293185993186441943042560024242378240x7fa40034b3000x7fa2f46372c000012076538325757542120765383259229611207653832645112012076538326468534
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027493185993186441943042560024242423680x7fa40034ba000x7fa2f463730000012076538326530019120765383266930401207653832691815912076538326935202
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027693185993186441943042560020242435840x7fa40034b9000x7fa2f463734000012076538326984504120765383271533591207653832795543712076538327973834
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027893185993186441943042560028242481280x7fa40034b8000x7fa2f463738000012076538328027684120765383282079171207653832862855612076538328647848
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028093185993186441943042560024242526720x7fa40034b7000x7fa2f46373c000012076538328692020120765383288631151207653832912503512076538329143530
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028293185993186441943042560024242592640x7fa40034b6000x7fa2f463740000012076538329189726120765383293555951207653832995559312076538329973764
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028493185993186441943042560024242648320x7fa40034b5000x7fa2f463744000012076538330045388120765383302115931207653833048215212076538330501796
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028693185993186441943042560020242663040x7fa40034b4000x7fa2f463748000012076538330556148120765383307203921207653833170807012076538331752092
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028893185993186441943042560028242718720x7fa40034b3000x7fa2f46374c000012076538331780545120765383319669491207653833248422812076538332526022
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029093185993186441943042560024242774400x7fa40034ba000x7fa2f463750000012076538332550908120765383327375081207653833301126712076538333050297
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029293185993186441943042560012242799360x7fa40034b9000x7fa2f463754000012076538333073661120765383332559071207653833399606512076538334036712
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029493185993186441943042560024242865280x7fa40034b8000x7fa2f463758000012076538334073029120765383342373451207653833455590412076538334596413
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029693185993186441943042560020242880000x7fa40034b7000x7fa2f46375c000012076538334619095120765383347989441207653833597494112076538336019169
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029893185993186441943042560032242945920x7fa40034b6000x7fa2f463760000012076538336046280120765383362328611207653833684502012076538336884559
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030093185993186441943042560024243011840x7fa40034b5000x7fa2f463764000012076538336912291120765383370938191207653833741493912076538337455802
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030293185993186441943042560012243049600x7fa40034b4000x7fa2f463768000012076538337480037120765383376605381207653833853925612076538338579402
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030493185993186441943042560024243136000x7fa40034b3000x7fa2f46376c000012076538338616751120765383387818161207653833919269512076538339235312
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030693185993186441943042560020243148160x7fa40034ba000x7fa2f463770000012076538339265117120765383394486941207653834100069112076538341041472
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030893185993186441943042560020243175680x7fa40034b9000x7fa2f463774000012076538341066618120765383412547711207653834205172912076538342092236
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031093185993186441943042560012243203200x7fa40034b8000x7fa2f463778000012076538342117583120765383423072491207653834272356812076538342763605
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031293185993186441943042560012243240960x7fa40034b7000x7fa2f46377c000012076538342787009120765383429710871207653834413156512076538344172766
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031493185993186441943042560012243288960x7fa40034b6000x7fa2f463780000012076538344217479120765383443829251207653834516948312076538345210076
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031693185993186441943042560020243301120x7fa40034b5000x7fa2f463784000012076538345238739120765383454210031207653834847523712076538348518239
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031893185993186441943042560020243328640x7fa40034b4000x7fa2f463788000012076538348598749120765383487641961207653835030883312076538350351239
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032093185993186441943042560012243356160x7fa40034b3000x7fa2f46378c000012076538350427210120765383505929921207653835138307112076538351426509
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032293185993186441943042560012243393920x7fa40034ba000x7fa2f463790000012076538351498493120765383516648301207653835394882612076538353990007
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032493185993186441943042560012243441920x7fa40034b9000x7fa2f463794000012076538354071429120765383542401851207653835577698212076538355818419
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032693185993186441943042560020243454080x7fa40034b8000x7fa2f463798000012076538355902134120765383560611421207653836212000912076538362164774
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032893185993186441943042560020243481600x7fa40034b7000x7fa2f46379c000012076538362238771120765383624046491207653836544768312076538365491401
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033093185993186441943042560012243509120x7fa40034b6000x7fa2f4637a0000012076538365562283120765383657251221207653836726543912076538367306237
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332931859931864419430425600122400x7fa40034b5000x7fa2f4637a4000012076538367374494120765383675411191207653837206911012076538372116815