169 lines
101 KiB
CSV
169 lines
101 KiB
CSV
Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,sig,obj,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,DispatchNs,BeginNs,EndNs,CompleteNs
|
|
0,__amd_rocclr_fillBuffer.kd,0,0,0,851908,851913,33554432,256,0,0,8,32,6464,0x0,0x7f16e3a04180,1048576,0,1048576,9437184,0,4194304,1048576,0,506765,506765,0,0,3145728,524288,32505856,374667926,219574763,122587307,32505856,4005136,3805741,56961485,11534336,0,0,14155776,13631488,0,3670016,1048576,1048576,0,4194304,9437184,905969664,6291456,0,0,0,524288,524288,0,0,0,0,33554432,0,0,0,0,0,8388608,336,144,0,0,0,480,0,6291456,6289457,96,2186,1819322,0,0,4194304,4189863,144,4297,2097152,524288,1572864,12074890142342317,12074904556684405,12074904557010162,12074890391224712
|
|
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,851908,851913,32768,256,0,0,24,24,12480,0x0,0x7f16e3a35100,0,4096,4096,512,0,512,4096,0,27610,27610,0,0,512,512,35328,1108710,1055334,17024,36352,225392,77450,1080338,26624,0,0,30208,1024,0,1024,4096,0,4096,512,512,1933312,8192,0,0,0,512,512,0,0,0,0,32768,0,0,0,0,0,1024,432,48,0,0,0,480,0,8192,6578,48,1566,1058,0,0,512,0,48,464,0,512,0,12074890405606408,12074904572874025,12074904572881385,12074890405950457
|
|
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,4,851908,851913,4194304,256,0,0,24,24,12928,0x7f1813b26900,0x7f16e3a35140,0,524288,524288,65536,0,65536,524288,0,214967,214967,0,0,65536,65536,4128768,152547403,55797172,92490391,4259840,1831576,1658706,24593622,3014656,0,0,3473408,131072,0,131072,524288,0,524288,65536,65536,222298112,917504,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,384,48,0,0,0,432,0,917504,914912,48,7430,204790,0,0,65536,64048,48,1440,0,65536,0,12074890406038090,12074904572956424,12074904573090983,12074890406424128
|
|
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,6,851908,851913,4194304,256,0,0,36,24,13632,0x7f1813b26800,0x7f16e3a35180,0,524288,524288,917504,0,65536,524288,0,395286,395286,0,0,131072,65536,6291456,228690756,55747078,166521150,6422528,3135448,2961730,44100310,4259840,0,0,4718592,983040,0,196608,524288,0,524288,65536,917504,301989888,1245184,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,480,48,0,0,0,528,0,1245184,1240949,48,6962,204420,0,0,65536,64048,48,1440,0,65536,0,12074890406509747,12074904573166663,12074904573411140,12074890407029823
|
|
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,8,851908,851913,4194304,256,0,0,28,24,14080,0x7f1813b26700,0x7f16e3a351c0,0,524288,524288,65536,0,65536,524288,0,390438,390438,0,0,65536,65536,4128768,326254008,109698139,211967159,4588674,3244504,3070489,45764207,3014656,0,0,3802242,131072,0,131072,524288,0,524288,65536,65536,243269632,983040,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,384,48,0,0,0,432,0,983040,978379,48,4824,206426,0,0,65536,64048,48,1440,0,65536,0,12074890407064017,12074904573559139,12074904573808737,12074890407590515
|
|
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,10,851908,851913,4194304,256,0,0,24,24,14528,0x7f1813b26600,0x7f16e3a35200,0,524288,524288,131072,0,65536,524288,0,218151,218151,0,0,65536,65536,4653056,141329387,48895163,87650096,4784128,1749144,1585234,23494834,3473408,0,0,3932160,196608,0,131072,524288,0,524288,65536,131072,251658240,1048576,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,432,48,0,0,0,480,0,1048576,1045672,48,8099,208481,0,0,65536,64048,48,1440,0,65536,0,12074890407619098,12074904573955296,12074904574080735,12074890407966474
|
|
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,12,851908,851913,4194304,256,0,0,24,24,14976,0x7f1813b26500,0x7f16e3a35240,0,524288,524288,65536,0,65536,524288,0,213750,213750,0,0,65536,65536,4259840,146177673,51443129,90081488,4653056,1828120,1659026,24596901,3145728,0,0,3866624,131072,0,131072,524288,0,524288,65536,65536,247463936,983040,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,432,48,0,0,0,480,0,983040,980156,48,7520,207391,0,0,65536,64048,48,1440,0,65536,0,12074890408039410,12074904574135774,12074904574260413,12074890408378119
|
|
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,14,851908,851913,4194304,256,0,0,24,24,15424,0x7f1813b26400,0x7f16e3a35280,0,524288,524288,65536,0,131072,524288,0,213479,213479,0,0,65536,65536,4915200,155015018,50323006,99842348,4849664,1735768,1573924,23377764,3538944,0,0,3997696,196608,0,131072,524288,0,524288,131072,65536,255852544,1048576,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,432,48,0,0,0,480,0,1048576,1046426,48,5322,221458,0,0,131072,129584,48,1440,65536,65536,0,12074890408464520,12074904574338972,12074904574463291,12074890408792178
|
|
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,16,851908,851913,4194304,256,0,0,28,24,16128,0x7f1813b26300,0x7f16e3a352c0,0,524288,524288,917504,0,131072,524288,0,392414,392414,0,0,131072,65536,8781824,307393341,118363833,180444292,8585216,3246872,3061770,45730276,6356992,0,0,6815744,1048576,0,196608,524288,0,524288,131072,917504,436207616,1572864,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,624,48,0,0,0,672,0,1572864,1568619,114,6965,205955,0,0,131072,129584,48,1440,0,131072,0,12074890408858011,12074904574515291,12074904574765209,12074890409377646
|
|
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,18,851908,851913,4194304,256,0,0,28,24,16832,0x7f1813b26a00,0x7f16e3a35300,0,524288,524288,65536,0,65536,524288,0,399238,399238,0,0,65536,65536,5373952,253357273,113372866,133866173,6118523,3178008,3009492,44926717,3997696,0,0,5332091,131072,0,131072,524288,0,524288,65536,65536,339738624,1179648,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,480,48,0,0,0,528,0,1179648,1177571,48,3559,134789,0,0,65536,64048,48,1440,0,0,65536,12074890409424854,12074904574903928,12074904575150645,12074890409939010
|
|
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,20,851908,851913,4194304,256,0,0,24,24,17536,0x7f1813b26900,0x7f16e3a35340,0,524288,524288,131072,0,131072,524288,0,210718,210718,0,0,65536,65536,5439488,156182177,55761991,95046234,5373952,1741528,1567114,23209771,3997696,0,0,4456448,262144,0,131072,524288,0,524288,131072,131072,285212672,1114112,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,480,48,0,0,0,528,0,1114112,1111581,48,5198,218111,0,0,131072,129584,48,1440,65536,65536,0,12074890409967984,12074904575293044,12074904575417203,12074890410317754
|
|
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,22,851908,851913,4194304,256,0,0,24,24,18240,0x7f1813b26800,0x7f16e3a35380,0,524288,524288,65536,0,131072,524288,0,215902,215902,0,0,65536,65536,5570560,138475593,49137487,83046650,6291456,1771416,1610628,23796417,4194304,0,0,5439488,196608,0,131072,524288,0,524288,131072,65536,348127232,1114112,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,480,48,0,0,0,528,0,1114112,1111582,48,4649,217430,0,0,131072,129584,48,1440,65536,65536,0,12074890410383045,12074904575467763,12074904575592082,12074890410722225
|
|
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,24,851908,851913,4194304,256,0,0,24,24,18944,0x7f1813b26700,0x7f16e3a353c0,0,524288,524288,65536,0,131072,524288,0,215575,215575,0,0,65536,65536,5439488,160426548,49020050,106032546,5373952,1840344,1677672,24812064,4063232,0,0,4521984,196608,0,131072,524288,0,524288,131072,65536,289406976,1179648,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,480,48,0,0,0,528,0,1179648,1177177,48,4835,220997,0,0,131072,129584,48,1440,65536,65536,0,12074890410802464,12074904575655281,12074904575779760,12074890411124623
|
|
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,26,851908,851913,4194304,256,0,0,28,24,19904,0x7f1813b26600,0x7f16e3a35400,0,524288,524288,917504,0,131072,524288,0,395375,395375,0,0,131072,65536,10813440,340775213,116797035,213295810,10682368,3774424,3111450,46315034,8454144,0,0,8912896,1048576,0,196608,524288,0,524288,131072,917504,570425344,1835008,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,720,48,0,0,0,768,0,1835008,1831568,96,8304,205800,0,0,131072,129584,48,1440,0,131072,0,12074890411191798,12074904575829200,12074904576075438,12074890411717124
|
|
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,28,851908,851913,4194304,256,0,0,28,24,20608,0x7f1813b26500,0x7f16e3a35440,0,524288,524288,65536,0,65536,524288,0,393575,393575,0,0,65536,65536,5898240,276971872,113251523,156557626,7160961,3240792,3048216,45433699,4521984,0,0,6374529,131072,0,131072,524288,0,524288,65536,65536,406847488,1310720,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,528,48,0,0,0,576,0,1310720,1308419,48,3591,206756,0,0,65536,64048,48,1440,0,0,65536,12074890411746959,12074904576218636,12074904576462634,12074890412276173
|
|
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,30,851908,851913,4194304,256,0,0,24,24,21312,0x7f1813b26400,0x7f16e3a35480,0,524288,524288,131072,0,131072,524288,0,213375,213375,0,0,65536,65536,5963776,160938268,54951086,100088942,5898240,1756632,1563339,23146613,4521984,0,0,4980736,262144,0,131072,524288,0,524288,131072,131072,318767104,1245184,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,528,48,0,0,0,576,0,1245184,1242580,48,5222,223347,0,0,131072,129584,48,1440,65536,65536,0,12074890412303564,12074904576576073,12074904576700712,12074890412648916
|
|
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,32,851908,851913,4194304,256,0,0,24,24,22016,0x7f1813b26300,0x7f16e3a354c0,0,524288,524288,65536,0,131072,524288,0,218559,218559,0,0,65536,65536,6619136,154309402,52402281,94042801,7864320,1813976,1640075,24286096,5242880,0,0,7012352,196608,0,131072,524288,0,524288,131072,65536,448790528,1310720,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,528,48,0,0,0,576,0,1310720,1308179,48,4991,222728,0,0,131072,129584,48,1440,65536,65536,0,12074890412708136,12074904576748872,12074904576873831,12074890413048819
|
|
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,34,851908,851913,4194304,256,0,0,24,24,22720,0x7f1813b26a00,0x7f16e3a35500,0,524288,524288,65536,0,131072,524288,0,213615,213615,0,0,65536,65536,5963776,164145197,54180427,104066530,5898240,1737304,1537097,22882303,4587520,0,0,5046272,196608,0,131072,524288,0,524288,131072,65536,322961408,1310720,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,528,48,0,0,0,576,0,1310720,1308284,48,4735,222665,0,0,131072,129584,48,1440,65536,65536,0,12074890413130290,12074904576934630,12074904577059589,12074890413450175
|
|
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,36,851908,851913,4194304,256,0,0,28,24,23680,0x7f1813b26900,0x7f16e3a35540,0,524288,524288,917504,0,131072,524288,0,400798,400798,0,0,131072,65536,12976128,281511849,112006934,156725395,12779520,3265560,3087088,45898833,10551296,0,0,11010048,1048576,0,196608,524288,0,524288,131072,917504,704643072,2097152,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,816,48,0,0,0,864,0,2097152,2092162,96,9389,205601,0,0,131072,129584,48,1440,0,131072,0,12074890413518261,12074904577109189,12074904577357986,12074890414043337
|
|
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,38,851908,851913,4194304,256,0,0,28,24,24384,0x7f1813b26800,0x7f16e3a35580,0,524288,524288,65536,0,65536,524288,0,390166,390166,0,0,65536,65536,6356992,318009700,110640654,199156760,8213740,3183576,3012029,44864378,5046272,0,0,7427308,131072,0,131072,524288,0,524288,65536,65536,473956352,1441792,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,576,48,0,0,0,624,0,1441792,1439264,48,3757,204542,0,0,65536,64048,48,1440,0,0,65536,12074890414071209,12074904577446946,12074904577690144,12074890414597076
|
|
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,40,851908,851913,4194304,256,0,0,24,24,25088,0x7f1813b26700,0x7f16e3a355c0,0,524288,524288,131072,0,131072,524288,0,215767,215767,0,0,65536,65536,6488064,168538613,49577646,112538439,6422528,1743640,1571484,23276199,5046272,0,0,5505024,262144,0,131072,524288,0,524288,131072,131072,352321536,1376256,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,576,48,0,0,0,624,0,1376256,1373805,48,4818,216343,0,0,131072,129584,48,1440,65536,65536,0,12074890414627242,12074904577798463,12074904577922622,12074890414966282
|
|
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,42,851908,851913,4194304,256,0,0,24,24,25792,0x7f1813b26600,0x7f16e3a35600,0,524288,524288,65536,0,131072,524288,0,214406,214406,0,0,65536,65536,7667712,159714693,50101214,100176295,9437184,1833688,1659251,24579265,6291456,0,0,8585216,196608,0,131072,524288,0,524288,131072,65536,549453824,1507328,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,624,48,0,0,0,672,0,1507328,1503607,48,6112,221891,0,0,131072,129584,48,1440,65536,65536,0,12074890415031513,12074904577972701,12074904578097980,12074890415379791
|
|
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,44,851908,851913,4194304,256,0,0,24,24,26496,0x7f1813b26500,0x7f16e3a35640,0,524288,524288,65536,0,131072,524288,0,211526,211526,0,0,65536,65536,6488064,158659588,50589853,101647207,6422528,1691736,1521784,22571594,5111808,0,0,5570560,196608,0,131072,524288,0,524288,131072,65536,356515840,1441792,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,576,48,0,0,0,624,0,1441792,1438609,48,5556,221228,0,0,131072,129584,48,1440,65536,65536,0,12074890415458807,12074904578159420,12074904578283099,12074890415775286
|
|
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,46,851908,851913,4194304,256,0,0,28,24,27712,0x7f1813b26400,0x7f16e3a35680,0,524288,524288,917504,0,131072,524288,0,395431,395431,0,0,131072,65536,15073280,359438191,116829806,227731713,14876672,3257368,3091937,46091996,12648448,0,0,13107200,1048576,0,196608,524288,0,524288,131072,917504,838860800,2359296,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,912,48,0,0,0,960,0,2359296,2356069,119,5902,205773,0,0,131072,129584,48,1440,0,131072,0,12074890415840607,12074904578332378,12074904578584376,12074890416368177
|
|
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,48,851908,851913,4194304,256,0,0,28,24,28416,0x7f1813b26300,0x7f16e3a356c0,0,524288,524288,65536,0,65536,524288,0,397014,397014,0,0,65536,65536,6946816,295438013,106472398,179699606,9267054,3224408,3050997,45475253,5570560,0,0,8480622,131072,0,131072,524288,0,524288,65536,65536,541065216,1572864,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,624,48,0,0,0,672,0,1572864,1570438,48,3691,207388,0,0,65536,64048,48,1440,0,0,65536,12074890416397452,12074904578670615,12074904578917653,12074890416922878
|
|
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,50,851908,851913,4194304,256,0,0,24,24,29120,0x7f1813b26a00,0x7f16e3a35700,0,524288,524288,131072,0,131072,524288,0,213991,213991,0,0,65536,65536,7012352,164815412,48730652,109137944,6946816,1714072,1552605,22982391,5570560,0,0,6029312,262144,0,131072,524288,0,524288,131072,131072,385875968,1507328,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,624,48,0,0,0,672,0,1507328,1504619,48,4945,224432,0,0,131072,129584,48,1440,65536,65536,0,12074890416952483,12074904579035412,12074904579159571,12074890417301031
|
|
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,52,851908,851913,4194304,256,0,0,24,24,30080,0x7f1813b26900,0x7f16e3a35740,0,524288,524288,65536,0,131072,524288,0,215006,215006,0,0,65536,65536,8716288,156629780,52050218,93569514,11010048,1782808,1617561,23873662,7340032,0,0,10158080,196608,0,131072,524288,0,524288,131072,65536,650117120,1703936,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,672,48,0,0,0,720,0,1703936,1699933,48,6725,224197,0,0,131072,129584,48,1440,65536,65536,0,12074890417367264,12074904579215091,12074904579340529,12074890417699822
|
|
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,54,851908,851913,4194304,256,0,0,24,24,30784,0x7f1813b26800,0x7f16e3a35780,0,524288,524288,65536,0,131072,524288,0,211558,211558,0,0,65536,65536,7012352,166051222,51950146,107154260,6946816,1775384,1613575,23886467,5636096,0,0,6094848,196608,0,131072,524288,0,524288,131072,65536,390070272,1572864,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,576,48,0,0,0,624,0,1572864,1568494,48,6715,224505,0,0,131072,129584,48,1440,65536,65536,0,12074890417779851,12074904579404369,12074904579529168,12074890418095788
|
|
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,56,851908,851913,4194304,256,0,0,28,24,32000,0x7f1813b26700,0x7f16e3a357c0,0,524288,524288,917504,0,131072,524288,0,394447,394447,0,0,131072,65536,17170432,338971414,111684660,210312930,16973824,3215896,3049819,45370290,14745600,0,0,15204352,1048576,0,196608,524288,0,524288,131072,917504,973078528,2621440,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1008,48,0,0,0,1056,0,2621440,2617179,48,8771,204172,0,0,131072,129584,48,1440,0,131072,0,12074890418162352,12074904579581007,12074904579831725,12074890418685153
|
|
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,58,851908,851913,4194304,256,0,0,28,24,32960,0x7f1813b26600,0x7f16e3a35800,0,524288,524288,65536,0,65536,524288,0,392414,392414,0,0,65536,65536,7471104,275079001,107132923,157629816,10314213,3196952,3018465,44978065,6094848,0,0,9527781,131072,0,131072,524288,0,524288,65536,65536,608174080,1703936,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,672,48,0,0,0,720,0,1703936,1701151,48,4024,208233,0,0,65536,64048,48,1440,0,0,65536,12074890418709308,12074904579920524,12074904580165322,12074890419235806
|
|
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,60,851908,851913,4194304,256,0,0,24,24,33920,0x7f1813b26500,0x7f16e3a35840,0,524288,524288,131072,0,131072,524288,0,210159,210159,0,0,65536,65536,7536640,162564150,48561350,106531696,7471104,1706264,1538933,22783208,6094848,0,0,6553600,262144,0,131072,524288,0,524288,131072,131072,419430400,1638400,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,672,48,0,0,0,720,0,1638400,1634939,48,5666,221070,0,0,131072,129584,48,1440,65536,65536,0,12074890419263257,12074904580274441,12074904580399240,12074890419603510
|
|
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,62,851908,851913,4194304,256,0,0,24,24,34880,0x7f1813b26400,0x7f16e3a35880,0,524288,524288,65536,0,131072,524288,0,216343,216343,0,0,65536,65536,9764864,164107321,54739500,96784909,12582912,1803160,1639509,24217208,8388608,0,0,11730944,196608,0,131072,524288,0,524288,131072,65536,750780416,1900544,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,768,48,0,0,0,816,0,1900544,1895233,96,7530,220547,0,0,131072,129584,48,1440,65536,65536,0,12074890419669903,12074904580447080,12074904580572839,12074890420006719
|
|
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,64,851908,851913,4194304,256,0,0,24,24,35840,0x7f1813b26300,0x7f16e3a358c0,0,524288,524288,65536,0,131072,524288,0,215199,215199,0,0,65536,65536,7536640,162649290,56588514,98589672,7471104,1651736,1481890,22023472,6160384,0,0,6619136,196608,0,131072,524288,0,524288,131072,65536,423624704,1703936,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,672,48,0,0,0,720,0,1703936,1700356,48,5712,222201,0,0,131072,129584,48,1440,65536,65536,0,12074890420081448,12074904580631718,12074904580756837,12074890420405871
|
|
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,66,851908,851913,4194304,256,0,0,28,24,37312,0x7f1813b26a00,0x7f16e3a35900,0,524288,524288,917504,0,131072,524288,0,394855,394855,0,0,131072,65536,19267584,355837641,114395779,222370886,19070976,3263512,3088161,45956963,16842752,0,0,17301504,1048576,0,196608,524288,0,524288,131072,917504,1107296256,2883584,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1104,48,0,0,0,1152,0,2883584,2879023,68,7181,208631,0,0,131072,129584,48,1440,0,131072,0,12074890420465341,12074904580804517,12074904581051715,12074890420987452
|
|
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,68,851908,851913,4194304,256,0,0,28,24,38272,0x7f1813b26900,0x7f16e3a35940,0,524288,524288,65536,0,65536,524288,0,395743,395743,0,0,65536,65536,7995392,338116508,105097101,221648992,11367591,3192792,3021469,45018112,6619136,0,0,10581159,131072,0,131072,524288,0,524288,65536,65536,675282944,1835008,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,720,48,0,0,0,768,0,1835008,1832397,48,3763,207112,0,0,65536,64048,48,1440,0,0,65536,12074890421020814,12074904581144994,12074904581389312,12074890421557130
|
|
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,70,851908,851913,4194304,256,0,0,24,24,39232,0x7f1813b26800,0x7f16e3a35980,0,524288,524288,131072,0,131072,524288,0,218039,218039,0,0,65536,65536,8060928,169241729,53444189,107802148,7995392,1738008,1575198,23311566,6619136,0,0,7077888,262144,0,131072,524288,0,524288,131072,131072,452984832,1769472,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,720,48,0,0,0,768,0,1769472,1764465,96,8361,158514,0,0,131072,129584,48,1440,65536,65536,0,12074890421585904,12074904581480991,12074904581606270,12074890421926857
|
|
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,72,851908,851913,4194304,256,0,0,24,24,40192,0x7f1813b26700,0x7f16e3a359c0,0,524288,524288,65536,0,131072,524288,0,216830,216830,0,0,65536,65536,10813440,160004371,44365188,101483407,14155776,1856344,1682476,24850730,9437184,0,0,13303808,196608,0,131072,524288,0,524288,131072,65536,851443712,2097152,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,816,48,0,0,0,864,0,2097152,2089056,48,11390,223011,0,0,131072,129584,48,1440,65536,65536,0,12074890421996036,12074904581656190,12074904581782108,12074890422332581
|
|
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,74,851908,851913,4194304,256,0,0,24,24,41152,0x7f1813b26600,0x7f16e3a35a00,0,524288,524288,65536,0,131072,524288,0,209046,209046,0,0,65536,65536,8060928,170430482,50709292,111725798,7995392,1682520,1523284,22590487,6684672,0,0,7143424,196608,0,131072,524288,0,524288,131072,65536,457179136,1835008,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,720,48,0,0,0,768,0,1835008,1831844,48,5346,223516,0,0,131072,129584,48,1440,65536,65536,0,12074890422410717,12074904581841788,12074904581965947,12074890422722286
|
|
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,76,851908,851913,4194304,256,0,0,28,24,42624,0x7f1813b26500,0x7f16e3a35a40,0,524288,524288,917504,0,131072,524288,0,394463,394463,0,0,131072,65536,21364736,360224115,113076302,225979685,21168128,3279192,3110076,46306350,18939904,0,0,19398656,1048576,0,196608,524288,0,524288,131072,917504,1241513984,3145728,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1200,48,0,0,0,1248,0,3145728,3141808,117,6533,205556,0,0,131072,129584,48,1440,0,131072,0,12074890422787817,12074904582020186,12074904582268824,12074890423303736
|
|
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,78,851908,851913,4194304,256,0,0,28,24,43584,0x7f1813b26400,0x7f16e3a35a80,0,524288,524288,65536,0,65536,524288,0,386455,386455,0,0,65536,65536,8519680,250955472,105971380,132564514,12421299,3185816,3007051,44803288,7143424,0,0,11634867,131072,0,131072,524288,0,524288,65536,65536,742391808,1966080,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,768,48,0,0,0,816,0,1966080,1963254,48,4228,206983,0,0,65536,64048,48,1440,0,0,65536,12074890423331488,12074904582361303,12074904582607061,12074890423853869
|
|
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,80,851908,851913,4194304,256,0,0,24,24,44544,0x7f1813b26300,0x7f16e3a35ac0,0,524288,524288,131072,0,131072,524288,0,211726,211726,0,0,65536,65536,8585216,161993595,52668394,100805521,8519680,1729368,1561559,23100928,7143424,0,0,7602176,262144,0,131072,524288,0,524288,131072,131072,486539264,1900544,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,768,48,0,0,0,816,0,1900544,1896165,48,6600,216393,0,0,131072,129584,48,1440,65536,65536,0,12074890423879446,12074904582699381,12074904582824339,12074890424222804
|
|
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,82,851908,851913,4194304,256,0,0,24,24,45760,0x7f1813b26a00,0x7f16e3a35b00,0,524288,524288,65536,0,131072,524288,0,219407,219407,0,0,65536,65536,11862016,163812924,43460804,104623480,15728640,1852312,1689530,24865956,10485760,0,0,14876672,196608,0,131072,524288,0,524288,131072,65536,952107008,2293760,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,912,48,0,0,0,960,0,2293760,2288427,48,7681,217046,0,0,131072,129584,48,1440,65536,65536,0,12074890424282465,12074904582873939,12074904583000178,12074890424630682
|
|
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,84,851908,851913,4194304,256,0,0,24,24,46720,0x7f1813b26900,0x7f16e3a35b40,0,524288,524288,65536,0,131072,524288,0,215031,215031,0,0,65536,65536,8585216,154974618,54873709,91581229,8519680,1715032,1524239,22586830,7208960,0,0,7667712,196608,0,131072,524288,0,524288,131072,65536,490733568,1966080,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,768,48,0,0,0,816,0,1966080,1960193,96,8534,225360,0,0,131072,129584,48,1440,65536,65536,0,12074890424710510,12074904583058737,12074904583183856,12074890425027319
|
|
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,86,851908,851913,4194304,256,0,0,28,24,48448,0x7f1813b26800,0x7f16e3a35b80,0,524288,524288,917504,0,131072,524288,0,406318,406318,0,0,131072,65536,23461888,275978145,157708024,95004841,23265280,3325656,3127225,46569203,21037056,0,0,21495808,1048576,0,196608,524288,0,524288,131072,917504,1375731712,3407872,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1296,48,0,0,0,1344,0,3407872,3401538,49,11142,202313,0,0,131072,129584,48,1440,0,131072,0,12074890425094855,12074904583232016,12074904583488654,12074890425620251
|
|
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,88,851908,851913,4194304,256,0,0,28,24,49408,0x7f1813b26700,0x7f16e3a35bc0,0,524288,524288,65536,0,65536,524288,0,391031,391031,0,0,65536,65536,9043968,278541763,101535659,163526554,13472094,3721752,3032653,45181138,7667712,0,0,12685662,131072,0,131072,524288,0,524288,65536,65536,809500672,2097152,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,816,48,0,0,0,864,0,2097152,2094226,48,4449,206385,0,0,65536,64048,48,1440,0,0,65536,12074890425649225,12074904583556653,12074904583800811,12074890426170464
|
|
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,90,851908,851913,4194304,256,0,0,24,24,50368,0x7f1813b26600,0x7f16e3a35c00,0,524288,524288,131072,0,131072,524288,0,220502,220502,0,0,65536,65536,9109504,163441192,50495903,103901321,9043968,1711448,1533966,22718795,7667712,0,0,8126464,262144,0,131072,524288,0,524288,131072,131072,520093696,2031616,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,816,48,0,0,0,864,0,2031616,2027936,96,5882,224341,0,0,131072,129584,48,1440,65536,65536,0,12074890426198987,12074904583866091,12074904583990569,12074890426540762
|
|
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,92,851908,851913,4194304,256,0,0,24,24,51584,0x7f1813b26500,0x7f16e3a35c40,0,524288,524288,65536,0,131072,524288,0,217687,217687,0,0,65536,65536,12910592,166515407,49639891,99574012,17301504,1821592,1645617,24355818,11534336,0,0,16449536,196608,0,131072,524288,0,524288,131072,65536,1052770304,2490368,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,960,48,0,0,0,1008,0,2490368,2484469,48,8179,223160,0,0,131072,129584,48,1440,65536,65536,0,12074890426607836,12074904584060809,12074904584187848,12074890426938100
|
|
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,94,851908,851913,4194304,256,0,0,24,24,52544,0x7f1813b26400,0x7f16e3a35c80,0,524288,524288,65536,0,131072,524288,0,210263,210263,0,0,65536,65536,9109504,170103927,52642425,108417534,9043968,1743064,1555431,23033424,7733248,0,0,8192000,196608,0,131072,524288,0,524288,131072,65536,524288000,2097152,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,816,48,0,0,0,864,0,2097152,2091984,48,7451,224048,0,0,131072,129584,48,1440,65536,65536,0,12074890427022647,12074904584248647,12074904584373126,12074890427338083
|
|
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,96,851908,851913,4194304,256,0,0,28,24,54272,0x7f1813b26300,0x7f16e3a35cc0,0,524288,524288,917504,0,131072,524288,0,408303,408303,0,0,131072,65536,25559040,280959004,152199765,103396807,25362432,3357208,3177902,47272811,23134208,0,0,23592960,1048576,0,196608,524288,0,524288,131072,917504,1509949440,3670016,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1392,48,0,0,0,1440,0,3670016,3663671,97,10972,199502,0,0,131072,129584,48,1440,0,131072,0,12074890427407533,12074904584422406,12074904584676164,12074890427932618
|
|
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,98,851908,851913,4194304,256,0,0,28,24,55488,0x7f1813b26a00,0x7f16e3a35d00,0,524288,524288,65536,0,65536,524288,0,392414,392414,0,0,65536,65536,9568256,251719113,103651293,133542359,14533611,3183192,3013342,44994055,8192000,0,0,13747179,131072,0,131072,524288,0,524288,65536,65536,876609536,2228224,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,864,48,0,0,0,912,0,2228224,2223151,48,6449,207614,0,0,65536,64048,48,1440,0,0,65536,12074890427959358,12074904584743363,12074904584988001,12074890428497628
|
|
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,100,851908,851913,4194304,256,0,0,24,24,56704,0x7f1813b26900,0x7f16e3a35d40,0,524288,524288,131072,0,131072,524288,0,211886,211886,0,0,65536,65536,9633792,155292225,55310219,90413750,9568256,1744152,1569726,23298657,8192000,0,0,8650752,262144,0,131072,524288,0,524288,131072,131072,553648128,2162688,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,864,48,0,0,0,912,0,2162688,2154260,48,11560,218856,0,0,131072,129584,48,1440,65536,65536,0,12074890428530630,12074904585059840,12074904585184479,12074890428867295
|
|
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,102,851908,851913,4194304,256,0,0,24,24,58176,0x7f1813b26800,0x7f16e3a35d80,0,524288,524288,65536,0,131072,524288,0,227167,227167,0,0,65536,65536,13959168,173947142,42118247,112954527,18874368,1854232,1669418,24633267,12582912,0,0,18022400,196608,0,131072,524288,0,524288,131072,65536,1153433600,2686976,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1056,48,0,0,0,1104,0,2686976,2676367,96,13204,223250,0,0,131072,129584,48,1440,65536,65536,0,12074890428932617,12074904585231839,12074904585361278,12074890429276436
|
|
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,104,851908,851913,4194304,256,0,0,24,24,59392,0x7f1813b26700,0x7f16e3a35dc0,0,524288,524288,65536,0,131072,524288,0,209582,209582,0,0,65536,65536,9633792,164740825,53194965,101977604,9568256,1740056,1576321,23280810,8257536,0,0,8716288,196608,0,131072,524288,0,524288,131072,65536,557842432,2228224,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,864,48,0,0,0,912,0,2228224,2222715,48,7911,224639,0,0,131072,129584,48,1440,65536,65536,0,12074890429354751,12074904585418877,12074904585543676,12074890429666901
|
|
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,106,851908,851913,4194304,256,0,0,28,24,61376,0x7f1813b26600,0x7f16e3a35e00,0,524288,524288,917504,0,131072,524288,0,407135,407135,0,0,131072,65536,27721728,310837369,149144418,134102295,27590656,3357592,3186567,47416870,25362432,0,0,25821184,1048576,0,196608,524288,0,524288,131072,917504,1652555776,3932160,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1488,48,0,0,0,1536,0,3932160,3926047,48,10262,224459,0,0,131072,129584,48,1440,0,131072,0,12074890429732183,12074904585591676,12074904585847194,12074890430257519
|
|
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,108,851908,851913,4194304,256,0,0,28,24,62592,0x7f1813b26500,0x7f16e3a35e40,0,524288,524288,65536,0,65536,524288,0,397838,397838,0,0,65536,65536,10092544,240147013,100720789,123853510,15581167,3201368,3035752,45175344,8716288,0,0,14794735,131072,0,131072,524288,0,524288,65536,65536,943718400,2359296,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,912,48,0,0,0,960,0,2359296,2355953,96,4630,205601,0,0,65536,64048,48,1440,0,0,65536,12074890430285391,12074904585910873,12074904586157111,12074890430816958
|
|
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,110,851908,851913,4194304,256,0,0,24,24,63808,0x7f1813b26400,0x7f16e3a35e80,0,524288,524288,131072,0,131072,524288,0,223182,223182,0,0,65536,65536,10158080,162473621,53132327,99248750,10092544,1760856,1590460,23486019,8716288,0,0,9175040,262144,0,131072,524288,0,524288,131072,131072,587202560,2293760,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,912,48,0,0,0,960,0,2293760,2287376,48,9036,218608,0,0,131072,129584,48,1440,65536,65536,0,12074890430842366,12074904586235350,12074904586360629,12074890431223975
|
|
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,112,851908,851913,4194304,256,0,0,24,24,65280,0x7f1813b26300,0x7f16e3a35ec0,0,524288,524288,65536,0,131072,524288,0,225254,225254,0,0,65536,65536,15007744,181853405,39023422,122382751,20447232,1787416,1621208,23841900,13631488,0,0,19595264,196608,0,131072,524288,0,524288,131072,65536,1254096896,2883584,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1104,48,0,0,0,1152,0,2883584,2873659,48,11547,226358,0,0,131072,129584,48,1440,65536,65536,0,12074890431290689,12074904586408309,12074904586536468,12074890431634668
|
|
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,114,851908,851913,4194304,256,0,0,24,24,66496,0x7f1813b26a00,0x7f16e3a35f00,0,524288,524288,65536,0,131072,524288,0,211807,211807,0,0,65536,65536,10158080,167449611,47251981,110105086,10092544,1726936,1540086,22780954,8781824,0,0,9240576,196608,0,131072,524288,0,524288,131072,65536,591396864,2359296,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,912,48,0,0,0,960,0,2359296,2354055,96,7556,226067,0,0,131072,129584,48,1440,65536,65536,0,12074890431714987,12074904586595347,12074904586720626,12074890432029321
|
|
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,116,851908,851913,4194304,256,0,0,28,24,68480,0x7f1813b26900,0x7f16e3a35f40,0,524288,524288,917504,0,131072,524288,0,409271,409271,0,0,131072,65536,29818880,341850692,161821909,150340975,29687808,3308568,3136961,46655292,27459584,0,0,27918336,1048576,0,196608,524288,0,524288,131072,917504,1786773504,4194304,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1584,48,0,0,0,1632,0,4194304,4186673,49,12428,216723,0,0,131072,129584,48,1440,0,131072,0,12074890432096276,12074904586768306,12074904587031503,12074890432627102
|
|
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,118,851908,851913,4194304,256,0,0,28,24,69696,0x7f1813b26800,0x7f16e3a35f80,0,524288,524288,65536,0,65536,524288,0,449662,449662,0,0,65536,65536,10616832,258584123,100656096,141289985,16639007,3218200,3041431,45377393,9240576,0,0,15852575,131072,0,131072,524288,0,524288,65536,65536,1010827264,2490368,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,960,48,0,0,0,1008,0,2490368,2486596,48,5035,204838,0,0,65536,64048,48,1440,0,0,65536,12074890432653692,12074904587099823,12074904587347181,12074890433213292
|
|
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,120,851908,851913,4194304,256,0,0,24,24,70912,0x7f1813b26700,0x7f16e3a35fc0,0,524288,524288,131072,0,131072,524288,0,216463,216463,0,0,65536,65536,10682368,164028166,53826406,99584928,10616832,1746072,1578744,23389017,9240576,0,0,9699328,262144,0,131072,524288,0,524288,131072,131072,620756992,2424832,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,960,48,0,0,0,1008,0,2424832,2415577,48,12360,223669,0,0,131072,129584,48,1440,65536,65536,0,12074890433238699,12074904587417100,12074904587542219,12074890433586405
|
|
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,122,851908,851913,4194304,256,0,0,24,24,72384,0x7f1813b26600,0x7f16e3a36000,0,524288,524288,65536,0,131072,524288,0,224742,224742,0,0,65536,65536,16056320,189078302,35181749,131876457,22020096,1805400,1626736,24104084,14680064,0,0,21168128,196608,0,131072,524288,0,524288,131072,65536,1354760192,3080192,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1200,48,0,0,0,1248,0,3080192,3068411,48,14832,221752,0,0,131072,129584,48,1440,65536,65536,0,12074890433652829,12074904587589579,12074904587725897,12074890433994353
|
|
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,124,851908,851913,4194304,256,0,0,24,24,73600,0x7f1813b26500,0x7f16e3a36040,0,524288,524288,65536,0,131072,524288,0,212807,212807,0,0,65536,65536,10682368,165245048,56013548,98614668,10616832,1781976,1619120,23973355,9306112,0,0,9764864,196608,0,131072,524288,0,524288,131072,65536,624951296,2490368,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,960,48,0,0,0,1008,0,2490368,2483490,48,10239,225420,0,0,131072,129584,48,1440,65536,65536,0,12074890434073330,12074904587787817,12074904587912616,12074890434389818
|
|
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,126,851908,851913,4194304,256,0,0,28,24,75840,0x7f1813b26400,0x7f16e3a36080,0,524288,524288,917504,0,131072,524288,0,409735,409735,0,0,131072,65536,31981568,287105629,137700722,117619947,31784960,3292504,3101292,46044112,29556736,0,0,30015488,1048576,0,196608,524288,0,524288,131072,917504,1920991232,4456448,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1680,48,0,0,0,1728,0,4456448,4449689,48,12152,204774,0,0,131072,129584,48,1440,0,131072,0,12074890434454348,12074904587960455,12074904588213733,12074890434979003
|
|
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,128,851908,851913,4194304,256,0,0,28,24,77056,0x7f1813b26300,0x7f16e3a360c0,0,524288,524288,65536,0,65536,524288,0,394062,394062,0,0,65536,65536,11141120,306669107,103627176,185352891,17692292,3187992,3000775,44788440,9764864,0,0,16905860,131072,0,131072,524288,0,524288,65536,65536,1077936128,2621440,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,1008,48,0,0,0,1056,0,2621440,2617848,48,4762,201276,0,0,65536,64048,48,1440,0,0,65536,12074890435009860,12074904588283813,12074904588527970,12074890435542450
|
|
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,130,851908,851913,4194304,256,0,0,24,24,78272,0x7f1813b26a00,0x7f16e3a36100,0,524288,524288,131072,0,131072,524288,0,211102,211102,0,0,65536,65536,11206656,169026521,49184034,108701367,11141120,1802904,1634982,24152257,9764864,0,0,10223616,262144,0,131072,524288,0,524288,131072,131072,654311424,2555904,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1008,48,0,0,0,1056,0,2555904,2549712,96,8453,220045,0,0,131072,129584,48,1440,65536,65536,0,12074890435567577,12074904588593250,12074904588718049,12074890435906667
|
|
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,132,851908,851913,4194304,256,0,0,24,24,80000,0x7f1813b26900,0x7f16e3a36140,0,524288,524288,65536,0,131072,524288,0,232414,232414,0,0,65536,65536,17170432,196970949,34118985,139259004,23592960,1875032,1701038,25148858,15728640,0,0,22740992,196608,0,131072,524288,0,524288,131072,65536,1455423488,3276800,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1248,48,0,0,0,1296,0,3276800,3268585,48,11805,203019,0,0,131072,129584,48,1440,65536,65536,0,12074890435971818,12074904588765248,12074904588906527,12074890436324704
|
|
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,134,851908,851913,4194304,256,0,0,24,24,81216,0x7f1813b26800,0x7f16e3a36180,0,524288,524288,65536,0,131072,524288,0,211054,211054,0,0,65536,65536,11206656,165699749,49895452,104663177,11141120,1801112,1611040,23834162,9830400,0,0,10289152,196608,0,131072,524288,0,524288,131072,65536,658505728,2621440,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1008,48,0,0,0,1056,0,2621440,2615760,48,8321,222451,0,0,131072,129584,48,1440,65536,65536,0,12074890436404612,12074904588964127,12074904589089086,12074890436722984
|
|
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,136,851908,851913,4194304,256,0,0,28,24,83456,0x7f1813b26700,0x7f16e3a361c0,0,524288,524288,917504,0,131072,524288,0,410343,410343,0,0,131072,65536,34078720,334709927,150424786,150403029,33882112,3338968,3137332,46676437,31653888,0,0,32112640,1048576,0,196608,524288,0,524288,131072,917504,2055208960,4718592,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1776,48,0,0,0,1824,0,4718592,4710376,96,11972,207467,0,0,131072,129584,48,1440,0,131072,0,12074890436787153,12074904589138365,12074904589395483,12074890437322969
|
|
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,138,851908,851913,4194304,256,0,0,28,24,84928,0x7f1813b26600,0x7f16e3a36200,0,524288,524288,65536,0,65536,524288,0,398167,398167,0,0,65536,65536,11665408,249355183,98290881,132332893,18747746,3224920,3060183,45668171,10289152,0,0,17961314,131072,0,131072,524288,0,524288,65536,65536,1145044992,2752512,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,1056,48,0,0,0,1104,0,2752512,2748892,48,4889,204935,0,0,65536,64048,48,1440,0,0,65536,12074890437349588,12074904589455322,12074904589699960,12074890437881908
|
|
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,140,851908,851913,4194304,256,0,0,24,24,86400,0x7f1813b26500,0x7f16e3a36240,0,524288,524288,131072,0,131072,524288,0,208678,208678,0,0,65536,65536,11730944,169583580,55360382,102557790,11665408,1770648,1603719,23645903,10289152,0,0,10747904,262144,0,131072,524288,0,524288,131072,131072,687865856,2686976,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1056,48,0,0,0,1104,0,2686976,2676588,96,13447,225178,0,0,131072,129584,48,1440,65536,65536,0,12074890437906674,12074904589765880,12074904589891319,12074890438244872
|
|
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,142,851908,851913,4194304,256,0,0,24,24,88128,0x7f1813b26400,0x7f16e3a36280,0,524288,524288,65536,0,131072,524288,0,300463,300463,0,0,65536,65536,18219008,204229308,29164055,149899429,25165824,1933784,1769940,26213892,16777216,0,0,24313856,196608,0,131072,524288,0,524288,131072,65536,1556086784,3473408,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1344,48,0,0,0,1392,0,3473408,3462515,49,16034,203935,0,0,131072,129584,48,1440,65536,65536,0,12074890438309963,12074904589938678,12074904590089717,12074890438767423
|
|
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,144,851908,851913,4194304,256,0,0,24,24,89600,0x7f1813b26300,0x7f16e3a362c0,0,524288,524288,65536,0,131072,524288,0,222167,222167,0,0,65536,65536,11730944,167548174,52173806,103708960,11665408,1752856,1585137,23412497,10354688,0,0,10813440,196608,0,131072,524288,0,524288,131072,65536,692060160,2752512,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1056,48,0,0,0,1104,0,2752512,2744446,96,10927,137228,0,0,131072,129584,48,1440,65536,65536,0,12074890438830721,12074904590168916,12074904590294195,12074890439166565
|
|
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,146,851908,851913,4194304,256,0,0,28,24,92096,0x7f1813b26a00,0x7f16e3a36300,0,524288,524288,917504,0,131072,524288,0,396591,396591,0,0,131072,65536,36175872,313094172,137177608,139937300,35979264,3361368,3162403,46892026,33751040,0,0,34209792,1048576,0,196608,524288,0,524288,131072,917504,2189426688,4980736,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1872,48,0,0,0,1920,0,4980736,4971193,48,15814,204328,0,0,131072,129584,48,1440,0,131072,0,12074890439231396,12074904590342835,12074904590602353,12074890439756972
|
|
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,148,851908,851913,4194304,256,0,0,28,24,93568,0x7f1813b26900,0x7f16e3a36340,0,524288,524288,65536,0,65536,524288,0,385806,385806,0,0,65536,65536,12189696,304015693,97188985,187026219,19800646,3183576,3015817,45018160,10813440,0,0,19014214,131072,0,131072,524288,0,524288,65536,65536,1212153856,2883584,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,1104,48,0,0,0,1152,0,2883584,2880276,97,4505,210290,0,0,65536,64048,48,1440,0,0,65536,12074890439780787,12074904590662672,12074904590910350,12074890440304059
|
|
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,150,851908,851913,4194304,256,0,0,24,24,95040,0x7f1813b26800,0x7f16e3a36380,0,524288,524288,131072,0,131072,524288,0,210734,210734,0,0,65536,65536,12255232,167880877,49659992,106031189,12189696,1742808,1568837,23200334,10813440,0,0,11272192,262144,0,131072,524288,0,524288,131072,131072,721420288,2818048,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1104,48,0,0,0,1152,0,2818048,2811106,48,10391,225055,0,0,131072,129584,48,1440,65536,65536,0,12074890440330117,12074904590971149,12074904591096908,12074890440673425
|
|
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,152,851908,851913,4194304,256,0,0,24,24,96768,0x7f1813b26700,0x7f16e3a363c0,0,524288,524288,65536,0,131072,524288,0,251534,251534,0,0,65536,65536,19202048,220466323,21809016,171918619,26738688,1998808,1841883,27373258,17825792,0,0,25886720,196608,0,131072,524288,0,524288,131072,65536,1656750080,3670016,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1392,48,0,0,0,1440,0,3670016,3654663,48,21406,225016,0,0,131072,129584,48,1440,65536,65536,0,12074890440739137,12074904591147308,12074904591304427,12074890441097764
|
|
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,154,851908,851913,4194304,256,0,0,24,24,98240,0x7f1813b26600,0x7f16e3a36400,0,524288,524288,65536,0,131072,524288,0,217342,217342,0,0,65536,65536,12255232,165479733,57554623,95735414,12189696,1802136,1630949,24047310,10878976,0,0,11337728,196608,0,131072,524288,0,524288,131072,65536,725614592,2883584,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1104,48,0,0,0,1152,0,2883584,2874127,103,14864,223367,0,0,131072,129584,48,1440,65536,65536,0,12074890441178193,12074904591363626,12074904591489065,12074890441500542
|
|
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,156,851908,851913,4194304,256,0,0,28,24,100736,0x7f1813b26500,0x7f16e3a36440,0,524288,524288,917504,0,131072,524288,0,407215,407215,0,0,131072,65536,38273024,301772349,112236633,151459300,38076416,3376024,3189938,47270688,35848192,0,0,36306944,1048576,0,196608,524288,0,524288,131072,917504,2323644416,5177344,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1968,48,0,0,0,2016,0,5177344,5165219,49,16907,207108,0,0,131072,129584,48,1440,0,131072,0,12074890441564992,12074904591538665,12074904591801222,12074890442096580
|
|
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,158,851908,851913,4194304,256,0,0,28,24,102208,0x7f1813b26400,0x7f16e3a36480,0,524288,524288,65536,0,65536,524288,0,385910,385910,0,0,65536,65536,12713984,316438083,98638224,196948654,20860744,3213976,3039908,45365099,11337728,0,0,20074312,131072,0,131072,524288,0,524288,65536,65536,1279262720,3014656,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,1152,48,0,0,0,1200,0,3014656,3010845,96,5134,207173,0,0,65536,64048,48,1440,0,0,65536,12074890442121456,12074904591866982,12074904592147939,12074890442650099
|
|
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,160,851908,851913,4194304,256,0,0,24,24,103680,0x7f1813b26300,0x7f16e3a364c0,0,524288,524288,131072,0,131072,524288,0,219575,219575,0,0,65536,65536,12779520,167324770,48563221,106047565,12713984,1802456,1636652,24183118,11337728,0,0,11796480,262144,0,131072,524288,0,524288,131072,131072,754974720,2949120,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1152,48,0,0,0,1200,0,2949120,2939924,48,12337,224843,0,0,131072,129584,48,1440,65536,65536,0,12074890442676217,12074904592218659,12074904592344418,12074890443025216
|
|
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,162,851908,851913,4194304,256,0,0,24,24,105664,0x7f1813b26a00,0x7f16e3a36500,0,524288,524288,65536,0,131072,524288,0,265326,265326,0,0,65536,65536,20250624,234141387,21208785,184621050,28311552,2107416,1939140,28839532,18874368,0,0,27459584,196608,0,131072,524288,0,524288,131072,65536,1757413376,3866624,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1488,48,0,0,0,1536,0,3866624,3853822,96,15755,223412,0,0,131072,129584,48,1440,65536,65536,0,12074890443103702,12074904592391617,12074904592557856,12074890443464342
|
|
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,164,851908,851913,4194304,256,0,0,24,24,107136,0x7f1813b26900,0x7f16e3a36540,0,524288,524288,65536,0,131072,524288,0,213678,213678,0,0,65536,65536,12779520,164524869,51952426,99858459,12713984,1744152,1565080,23061929,11403264,0,0,11862016,196608,0,131072,524288,0,524288,131072,65536,759169024,3014656,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1152,48,0,0,0,1200,0,3014656,3004831,48,11677,220970,0,0,131072,129584,48,1440,65536,65536,0,12074890443542447,12074904592617695,12074904592743454,12074890443859426
|
|
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,166,851908,851913,4194304,256,0,0,28,24,109888,0x7f1813b26800,0x7f16e3a36580,0,524288,524288,917504,0,131072,524288,0,398471,398471,0,0,131072,65536,40370176,342314847,135933686,166207593,40173568,3336408,3138895,46547272,37945344,0,0,38404096,1048576,0,196608,524288,0,524288,131072,917504,2457862144,5439488,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,2064,48,0,0,0,2112,0,5439488,5426874,99,19408,209463,0,0,131072,129584,48,1440,0,131072,0,12074890443925158,12074904592793214,12074904593048252,12074890444451406
|
|
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,168,851908,851913,4194304,256,0,0,28,24,111360,0x7f1813b26700,0x7f16e3a365c0,0,524288,524288,65536,0,65536,524288,0,399790,399790,0,0,65536,65536,13238272,260998541,96078048,143024448,21912262,3235352,3058184,45584087,11862016,0,0,21125830,131072,0,131072,524288,0,524288,65536,65536,1346371584,3145728,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,1200,48,0,0,0,1248,0,3145728,3141599,48,5394,207052,0,0,65536,64048,48,1440,0,0,65536,12074890444481552,12074904593118171,12074904593399769,12074890445018871
|
|
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,170,851908,851913,4194304,256,0,0,24,24,112832,0x7f1813b26600,0x7f16e3a36600,0,524288,524288,131072,0,131072,524288,0,223711,223711,0,0,65536,65536,13303808,166559873,54479033,98842568,13238272,1744472,1570387,23219153,11862016,0,0,12320768,262144,0,131072,524288,0,524288,131072,131072,788529152,3080192,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1200,48,0,0,0,1248,0,3080192,3070093,48,14839,225556,0,0,131072,129584,48,1440,65536,65536,0,12074890445043026,12074904593471768,12074904593597047,12074890445391113
|
|
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,172,851908,851913,4194304,256,0,0,24,24,114816,0x7f1813b26500,0x7f16e3a36640,0,524288,524288,65536,0,131072,524288,0,276559,276559,0,0,65536,65536,21299200,247589148,18465047,199239685,29884416,2198936,2040103,30326767,19922944,0,0,29032448,196608,0,131072,524288,0,524288,131072,65536,1858076672,4063232,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1536,48,0,0,0,1584,0,4063232,4049395,96,16979,220712,0,0,131072,129584,48,1440,65536,65536,0,12074890445456184,12074904593644406,12074904593817205,12074890445826762
|
|
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,174,851908,851913,4194304,256,0,0,24,24,116288,0x7f1813b26400,0x7f16e3a36680,0,524288,524288,65536,0,131072,524288,0,216487,216487,0,0,65536,65536,13303808,162302784,50042569,99021943,13238272,1726680,1557503,23023493,11927552,0,0,12386304,196608,0,131072,524288,0,524288,131072,65536,792723456,3145728,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1200,48,0,0,0,1248,0,3145728,3136563,48,13307,223375,0,0,131072,129584,48,1440,65536,65536,0,12074890445932318,12074904593875284,12074904594001203,12074890446261240
|
|
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,176,851908,851913,4194304,256,0,0,28,24,119040,0x7f1813b26300,0x7f16e3a366c0,0,524288,524288,917504,0,131072,524288,0,401606,401606,0,0,131072,65536,42467328,315899237,95747961,177880556,42270720,3271128,3071140,45625334,40042496,0,0,40501248,1048576,0,196608,524288,0,524288,131072,917504,2592079872,5701632,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,2160,48,0,0,0,2208,0,5701632,5683656,105,30404,205337,0,0,131072,129584,48,1440,0,131072,0,12074890446327543,12074904594051603,12074904594310161,12074890446856366
|
|
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,178,851908,851913,4194304,256,0,0,28,24,120768,0x7f1813b26a00,0x7f16e3a36700,0,524288,524288,65536,0,65536,524288,0,401422,401422,0,0,65536,65536,13762560,258417825,88426164,147046249,22952310,3214296,3016071,44884811,12386304,0,0,22165878,131072,0,131072,524288,0,524288,65536,65536,1413480448,3276800,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,1248,48,0,0,0,1296,0,3276800,3272803,48,5018,204867,0,0,65536,64048,48,1440,0,0,65536,12074890446879949,12074904594374480,12074904594623758,12074890447424572
|
|
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,180,851908,851913,4194304,256,0,0,24,24,122496,0x7f1813b26900,0x7f16e3a36740,0,524288,524288,131072,0,131072,524288,0,216702,216702,0,0,65536,65536,13828096,170214501,49301821,107150120,13762560,1800984,1629772,24074900,12386304,0,0,12845056,262144,0,131072,524288,0,524288,131072,131072,822083584,3211264,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1248,48,0,0,0,1296,0,3211264,3201094,109,17507,225251,0,0,131072,129584,48,1440,65536,65536,0,12074890447450600,12074904594687597,12074904594813196,12074890447795110
|
|
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,182,851908,851913,4194304,256,0,0,24,24,124736,0x7f1813b26800,0x7f16e3a36780,0,524288,524288,65536,0,131072,524288,0,289687,289687,0,0,65536,65536,22347776,258658075,18331018,208869777,31457280,2324696,2156426,32055872,20971520,0,0,30605312,196608,0,131072,524288,0,524288,131072,65536,1958739968,4259840,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1632,48,0,0,0,1680,0,4259840,4245183,48,17627,223189,0,0,131072,129584,48,1440,65536,65536,0,12074890447860522,12074904594861196,12074904595043434,12074890448248954
|
|
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,184,851908,851913,4194304,256,0,0,24,24,126464,0x7f1813b26700,0x7f16e3a367c0,0,524288,524288,65536,0,131072,524288,0,212598,212598,0,0,65536,65536,13828096,167332963,48080045,105490358,13762560,1838168,1669259,24637920,12451840,0,0,12910592,196608,0,131072,524288,0,524288,131072,65536,826277888,3276800,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1248,48,0,0,0,1296,0,3276800,3263786,111,21937,224435,0,0,131072,129584,48,1440,65536,65536,0,12074890448357736,12074904595106794,12074904595233673,12074890448679534
|
|
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,186,851908,851913,4194304,256,0,0,20,24,127936,0x7f1813b26600,0x7f16e3a36800,0,524288,524288,4653056,0,131072,524288,0,413351,413351,0,0,1703936,65536,51642368,381051621,151468961,179054404,50528256,3295384,3125663,46531693,42926080,0,0,43450368,4784128,0,1769472,524288,0,524288,131072,4653056,2780823552,7733248,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1200,48,0,0,0,1248,0,7733248,7729691,48,4274,221746,0,0,131072,129584,48,1440,0,131072,0,12074890448742371,12074904595280392,12074904595576070,12074890449276964
|
|
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,188,851908,851913,4194304,256,0,0,28,24,129664,0x7f1813b26500,0x7f16e3a36840,0,524288,524288,65536,0,65536,524288,0,396918,396918,0,0,65536,65536,14286848,314774383,92953017,197808872,24014327,3202840,3031851,45083582,12910592,0,0,23227895,131072,0,131072,524288,0,524288,65536,65536,1480589312,3407872,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,1296,48,0,0,0,1344,0,3407872,3402097,96,7915,207982,0,0,65536,64048,48,1440,0,0,65536,12074890449303032,12074904595636709,12074904595917027,12074890449835001
|
|
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,190,851908,851913,4194304,256,0,0,24,24,131392,0x7f1813b26400,0x7f16e3a36880,0,524288,524288,131072,0,131072,524288,0,213191,213191,0,0,65536,65536,14352384,162656757,52850239,95519670,14286848,1826712,1649309,24280568,12910592,0,0,13369344,262144,0,131072,524288,0,524288,131072,131072,855638016,3342336,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1296,48,0,0,0,1344,0,3342336,3330170,48,15881,225580,0,0,131072,129584,48,1440,65536,65536,0,12074890449862432,12074904595980706,12074904596106145,12074890450210709
|
|
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,192,851908,851913,4194304,256,0,0,24,24,133632,0x7f1813b26300,0x7f16e3a368c0,0,524288,524288,65536,0,131072,524288,0,302998,302998,0,0,65536,65536,23396352,273295176,19465541,220799491,33030144,2444312,2265912,33628776,22020096,0,0,32178176,196608,0,131072,524288,0,524288,131072,65536,2059403264,4456448,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1680,48,0,0,0,1728,0,4456448,4444824,96,14103,224762,0,0,131072,129584,48,1440,65536,65536,0,12074890450276982,12074904596154305,12074904596345663,12074890450734453
|
|
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,194,851908,851913,4194304,256,0,0,24,24,135360,0x7f1813b26a00,0x7f16e3a36900,0,524288,524288,65536,0,131072,524288,0,220246,220246,0,0,65536,65536,14876672,175671658,53346070,107514452,14811136,1789208,1591657,23459819,13500416,0,0,13959168,196608,0,131072,524288,0,524288,131072,65536,893386752,3538944,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1344,48,0,0,0,1392,0,3538944,3523619,48,21199,219100,0,0,131072,129584,48,1440,65536,65536,0,12074890450770820,12074904596401663,12074904596528222,12074890451104580
|
|
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,196,851908,851913,4194304,256,0,0,20,24,136832,0x7f1813b26900,0x7f16e3a36940,0,524288,524288,5701632,0,131072,524288,0,435591,435591,0,0,2228224,65536,57933824,403248579,101163205,245789950,56295424,3496728,3332665,49592226,47120384,0,0,47644672,5832704,0,2293760,524288,0,524288,131072,5701632,3049259008,8978432,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1104,48,0,0,0,1152,0,8978432,8976731,49,2075,220424,0,0,131072,129584,48,1440,0,131072,0,12074890451170042,12074904596576221,12074904596890139,12074890451727007
|
|
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,198,851908,851913,4194304,256,0,0,28,24,138560,0x7f1813b26800,0x7f16e3a36980,0,524288,524288,65536,0,65536,524288,0,392551,392551,0,0,65536,65536,15335424,259524826,85331741,148083993,26118583,3150296,2970435,44223143,13959168,0,0,25332151,131072,0,131072,524288,0,524288,65536,65536,1614807040,3670016,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,1392,48,0,0,0,1440,0,3670016,3665268,49,6277,205257,0,0,65536,64048,48,1440,0,0,65536,12074890451753977,12074904596951258,12074904597200056,12074890452283491
|
|
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,200,851908,851913,4194304,256,0,0,24,24,140288,0x7f1813b26700,0x7f16e3a369c0,0,524288,524288,131072,0,131072,524288,0,213575,213575,0,0,65536,65536,15400960,164824012,54843803,94644785,15335424,1800472,1621020,24049459,13959168,0,0,14417920,262144,0,131072,524288,0,524288,131072,131072,922746880,3604480,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1392,48,0,0,0,1440,0,3604480,3594362,64,16988,222216,0,0,131072,129584,48,1440,65536,65536,0,12074890452310862,12074904597268375,12074904597395094,12074890452652226
|
|
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,202,851908,851913,4194304,256,0,0,24,24,142784,0x7f1813b26600,0x7f16e3a36a00,0,524288,524288,65536,0,131072,524288,0,330919,330919,0,0,65536,65536,25493504,297516624,18993218,242347534,36175872,2646104,2478570,36831104,24117248,0,0,35323904,196608,0,131072,524288,0,524288,131072,65536,2260729856,4849664,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1824,48,0,0,0,1872,0,4849664,4828849,96,25063,224715,0,0,131072,129584,48,1440,65536,65536,0,12074890452717838,12074904597441654,12074904597651412,12074890453169317
|
|
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,204,851908,851913,4194304,256,0,0,24,24,144768,0x7f1813b26500,0x7f16e3a36a40,0,524288,524288,65536,0,131072,524288,0,218335,218335,0,0,65536,65536,15925248,177347117,49338164,112149241,15859712,1782680,1612363,23726917,14548992,0,0,15007744,196608,0,131072,524288,0,524288,131072,65536,960495616,3801088,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1440,48,0,0,0,1488,0,3801088,3786850,48,23079,221934,0,0,131072,129584,48,1440,65536,65536,0,12074890453221244,12074904597719251,12074904597847090,12074890453547400
|
|
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,206,851908,851913,4194304,256,0,0,20,24,145728,0x7f1813b26400,0x7f16e3a36a80,0,524288,524288,13041664,0,131072,524288,0,471799,471799,0,0,5898240,65536,76808192,437616118,112298023,253818319,71499776,4148440,3617647,53865637,51314688,0,0,51838976,13172736,0,5963776,524288,0,524288,131072,13041664,3317694464,14548992,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,816,48,0,0,0,864,0,14548992,14547292,51,2069,225733,0,0,131072,129584,48,1440,0,131072,0,12074890453604456,12074904597895410,12074904598201647,12074890454188171
|
|
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,208,851908,851913,4194304,256,0,0,28,24,147712,0x7f1813b26300,0x7f16e3a36ac0,0,524288,524288,65536,0,65536,524288,0,390214,390214,0,0,65536,65536,16384000,261354759,73448210,159697623,28231238,3260632,3074361,45711148,15007744,0,0,27444806,131072,0,131072,524288,0,524288,65536,65536,1749024768,3932160,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,1488,48,0,0,0,1536,0,3932160,3925427,48,7991,204753,0,0,65536,64048,48,1440,0,0,65536,12074890454212216,12074904598268207,12074904598551244,12074890454743613
|
|
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,210,851908,851913,4194304,256,0,0,24,24,149696,0x7f1813b26a00,0x7f16e3a36b00,0,524288,524288,131072,0,131072,524288,0,214358,214358,0,0,65536,65536,16449536,171530353,47288655,107857698,16384000,1789080,1604281,23686288,15007744,0,0,15466496,262144,0,131072,524288,0,524288,131072,131072,989855744,3866624,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1488,48,0,0,0,1536,0,3866624,3852033,96,18208,223691,0,0,131072,129584,48,1440,65536,65536,0,12074890454768189,12074904598613804,12074904598742603,12074890455110725
|
|
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,212,851908,851913,4194304,256,0,0,24,24,152192,0x7f1813b26900,0x7f16e3a36b40,0,524288,524288,65536,0,131072,524288,0,358542,358542,0,0,65536,65536,27590656,324272353,20789737,264161016,39321600,2889240,2678618,39906306,26214400,0,0,38469632,196608,0,131072,524288,0,524288,131072,65536,2462056448,5242880,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1968,48,0,0,0,2016,0,5242880,5218969,48,28423,220679,0,0,131072,129584,48,1440,65536,65536,0,12074890455176758,12074904598789322,12074904599017480,12074890455673942
|
|
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,214,851908,851913,4194304,256,0,0,24,24,154176,0x7f1813b26800,0x7f16e3a36b80,0,524288,524288,65536,0,131072,524288,0,223718,223718,0,0,65536,65536,16973824,174064328,44748754,112407286,16908288,1801752,1616170,23869826,15597568,0,0,16056320,196608,0,131072,524288,0,524288,131072,65536,1027604480,4063232,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1536,48,0,0,0,1584,0,4063232,4048597,118,22257,222469,0,0,131072,129584,48,1440,65536,65536,0,12074890455710881,12074904599095720,12074904599222599,12074890456043499
|
|
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,216,851908,851913,4194304,256,0,0,20,24,155648,0x7f1813b26700,0x7f16e3a36bc0,0,524288,524288,5701632,0,131072,524288,0,504166,504166,0,0,2228224,65536,66322432,472354595,90389417,317281146,64684032,4375576,3864541,57566653,55508992,0,0,56033280,5832704,0,2293760,524288,0,524288,131072,5701632,3586129920,10027008,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1200,48,0,0,0,1248,0,10027008,10024906,48,2376,219773,0,0,131072,129584,48,1440,0,131072,0,12074890456110363,12074904599271558,12074904599599235,12074890456715938
|
|
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,218,851908,851913,4194304,256,0,0,28,24,157632,0x7f1813b26600,0x7f16e3a36c00,0,524288,524288,65536,0,65536,524288,0,403782,403782,0,0,65536,65536,17432576,350155516,72131838,247678688,30310380,3261016,3056261,45405447,16056320,0,0,29523948,131072,0,131072,524288,0,524288,65536,65536,1883242496,4194304,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,1584,48,0,0,0,1632,0,4194304,4187282,96,8298,207733,0,0,65536,64048,48,1440,0,0,65536,12074890456740604,12074904599662755,12074904599913153,12074890457277041
|
|
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,220,851908,851913,4194304,256,0,0,24,24,159616,0x7f1813b26500,0x7f16e3a36c40,0,524288,524288,131072,0,131072,524288,0,229295,229295,0,0,65536,65536,17498112,173190925,46243096,109515253,17432576,1826328,1652053,24375728,16056320,0,0,16515072,262144,0,131072,524288,0,524288,131072,131072,1056964608,4128768,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1584,48,0,0,0,1632,0,4128768,4115928,83,23082,223446,0,0,131072,129584,48,1440,65536,65536,0,12074890457303150,12074904599976512,12074904600105471,12074890457655645
|
|
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,222,851908,851913,4194304,256,0,0,24,24,162368,0x7f1813b26400,0x7f16e3a36c80,0,524288,524288,65536,0,131072,524288,0,383742,383742,0,0,65536,65536,29687808,351529992,18564320,290498344,42467328,3063000,2897411,43078994,28311552,0,0,41615360,196608,0,131072,524288,0,524288,131072,65536,2663383040,5636096,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,2112,48,0,0,0,2160,0,5636096,5614088,96,24819,211533,0,0,131072,129584,48,1440,65536,65536,0,12074890457721347,12074904600152991,12074904600396348,12074890458233058
|
|
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,224,851908,851913,4194304,256,0,0,24,24,164608,0x7f1813b26300,0x7f16e3a36cc0,0,524288,524288,65536,0,131072,524288,0,220254,220254,0,0,65536,65536,19070976,179004808,48935071,111064297,19005440,1790104,1590231,23352207,17694720,0,0,18153472,196608,0,131072,524288,0,524288,131072,65536,1161822208,4587520,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1728,48,0,0,0,1776,0,4587520,4574575,66,20553,215453,0,0,131072,129584,48,1440,65536,65536,0,12074890458269505,12074904600474588,12074904600604667,12074890458604518
|
|
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,226,851908,851913,4194304,256,0,0,20,24,166336,0x7f1813b26a00,0x7f16e3a36d00,0,524288,524288,5701632,0,131072,524288,0,574822,574822,0,0,2228224,65536,74711040,540258566,88146122,379039804,73072640,4594200,4424170,65912414,63897600,0,0,64421888,5832704,0,2293760,524288,0,524288,131072,5701632,4123000832,11075584,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1296,48,0,0,0,1344,0,11075584,11073690,49,2135,224107,0,0,131072,129584,48,1440,0,131072,0,12074890458669459,12074904600653146,12074904601028503,12074890459312504
|
|
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,228,851908,851913,4194304,256,0,0,28,24,168576,0x7f1813b26900,0x7f16e3a36d40,0,524288,524288,65536,0,65536,524288,0,408358,408358,0,0,65536,65536,19529728,301134651,61601901,205012722,34521033,3243544,3064662,45518945,18153472,0,0,33734601,131072,0,131072,524288,0,524288,65536,65536,2151677952,4718592,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,1728,48,0,0,0,1776,0,4718592,4711376,48,9599,201661,0,0,65536,64048,48,1440,0,0,65536,12074890459338692,12074904601098262,12074904601358420,12074890459882563
|
|
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,230,851908,851913,4194304,256,0,0,24,24,170816,0x7f1813b26800,0x7f16e3a36d80,0,524288,524288,131072,0,131072,524288,0,225439,225439,0,0,65536,65536,19595264,183583682,46064322,117989632,19529728,1820504,1642854,24073763,18153472,0,0,18612224,262144,0,131072,524288,0,524288,131072,131072,1191182336,4653056,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1776,48,0,0,0,1824,0,4653056,4636687,66,24935,227158,0,0,131072,129584,48,1440,65536,65536,0,12074890459906488,12074904601438899,12074904601569778,12074890460265054
|
|
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,232,851908,851913,4194304,256,0,0,24,24,174080,0x7f1813b26700,0x7f16e3a36dc0,0,524288,524288,65536,0,131072,524288,0,435991,435991,0,0,65536,65536,33882112,402653246,17905400,335989062,48758784,3488280,3299016,49157226,32505856,0,0,47906816,196608,0,131072,524288,0,524288,131072,65536,3066036224,6422528,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,2400,48,0,0,0,2448,0,6422528,6400176,96,25556,223179,0,0,131072,129584,48,1440,65536,65536,0,12074890460322911,12074904601617938,12074904601896976,12074890460875078
|
|
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,234,851908,851913,4194304,256,0,0,24,24,176576,0x7f1813b26600,0x7f16e3a36e00,0,524288,524288,65536,0,131072,524288,0,222975,222975,0,0,65536,65536,21168128,185827238,41243204,123481442,21102592,1817368,1619255,23928083,19791872,0,0,20250624,196608,0,131072,524288,0,524288,131072,65536,1296039936,5111808,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1920,48,0,0,0,1968,0,5111808,5093391,112,34538,223199,0,0,131072,129584,48,1440,65536,65536,0,12074890460914701,12074904601976015,12074904602110894,12074890461266986
|
|
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,236,851908,851913,4194304,256,0,0,20,24,177792,0x7f1813b26500,0x7f16e3a36e40,0,524288,524288,9895936,0,131072,524288,0,680503,680503,0,0,4325376,65536,91488256,611243605,96876800,426614101,87752704,5179096,5009357,74634440,72286208,0,0,72810496,10027008,0,4390912,524288,0,524288,131072,9895936,4659871744,15007744,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1008,48,0,0,0,1056,0,15007744,15006204,48,2063,223963,0,0,131072,129584,48,1440,0,131072,0,12074890461334581,12074904602160333,12074904602583050,12074890462053698
|
|
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,238,851908,851913,4194304,256,0,0,28,24,180288,0x7f1813b26400,0x7f16e3a36e80,0,524288,524288,65536,0,65536,524288,0,406390,406390,0,0,65536,65536,21626880,299771876,58992336,202106024,38651716,3292376,3080704,45684710,20250624,0,0,37865284,131072,0,131072,524288,0,524288,65536,65536,2420113408,5242880,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,1968,48,0,0,0,2016,0,5242880,5221460,48,23049,207696,0,0,65536,64048,48,1440,0,0,65536,12074890462078825,12074904602648809,12074904602904487,12074890462618007
|
|
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,240,851908,851913,4194304,256,0,0,24,24,182784,0x7f1813b26300,0x7f16e3a36ec0,0,524288,524288,131072,0,131072,524288,0,221462,221462,0,0,65536,65536,21692416,189488239,45048858,122812501,21626880,1826200,1654864,24476315,20250624,0,0,20709376,262144,0,131072,524288,0,524288,131072,131072,1325400064,5177344,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1968,48,0,0,0,2016,0,5177344,5157444,159,35377,224258,0,0,131072,129584,48,1440,65536,65536,0,12074890462642222,12074904602972486,12074904603107205,12074890462987383
|
|
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,242,851908,851913,4194304,256,0,0,24,24,186304,0x7f1813b26a00,0x7f16e3a36f00,0,524288,524288,65536,0,131072,524288,0,490446,490446,0,0,65536,65536,38076416,456859487,19788887,382020360,55050240,3898072,3723926,55515232,36700160,0,0,54198272,196608,0,131072,524288,0,524288,131072,65536,3468689408,7208960,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,2688,48,0,0,0,2736,0,7208960,7173512,96,43865,219819,0,0,131072,129584,48,1440,65536,65536,0,12074890463052053,12074904603158725,12074904603502882,12074890463644684
|
|
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,244,851908,851913,4194304,256,0,0,24,24,189312,0x7f1813b26900,0x7f16e3a36f40,0,524288,524288,65536,0,131072,524288,0,243095,243095,0,0,65536,65536,25362432,216232221,24940930,165994395,25296896,1944280,1780801,26479759,23986176,0,0,24444928,196608,0,131072,524288,0,524288,131072,65536,1564475392,6160384,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,2304,48,0,0,0,2352,0,6160384,6138127,107,32034,220936,0,0,131072,129584,48,1440,65536,65536,0,12074890463680130,12074904603582401,12074904603733760,12074890464030381
|
|
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,246,851908,851913,4194304,256,0,0,20,24,190784,0x7f1813b26800,0x7f16e3a36f80,0,524288,524288,9895936,0,131072,524288,0,784454,784454,0,0,4325376,65536,108265472,749651457,95513943,549607594,104529920,6286168,6112522,91192204,89063424,0,0,89587712,10027008,0,4390912,524288,0,524288,131072,9895936,5733613568,17104896,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1104,48,0,0,0,1152,0,17104896,17103129,48,2116,225962,0,0,131072,129584,48,1440,0,131072,0,12074890464096023,12074904603781759,12074904604297755,12074890464885180
|
|
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,248,851908,851913,4194304,256,0,0,28,24,193792,0x7f1813b26700,0x7f16e3a36fc0,0,524288,524288,65536,0,65536,524288,0,461095,461095,0,0,65536,65536,25821184,388733640,46704756,294977139,47042792,3647000,3452741,51116415,24444928,0,0,46256360,131072,0,131072,524288,0,524288,65536,65536,2956984320,6291456,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,2352,48,0,0,0,2400,0,6291456,6269845,96,23097,125882,0,0,65536,64048,48,1440,0,0,65536,12074890464910737,12074904604366874,12074904604663192,12074890465489342
|
|
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,250,851908,851913,4194304,256,0,0,24,24,196800,0x7f1813b26600,0x7f16e3a37000,0,524288,524288,131072,0,131072,524288,0,247430,247430,0,0,65536,65536,25886720,219625789,26444310,167360295,25821184,1977048,1808540,26890165,24444928,0,0,24903680,262144,0,131072,524288,0,524288,131072,131072,1593835520,6225920,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,2352,48,0,0,0,2400,0,6225920,6200392,137,43155,223541,0,0,131072,129584,48,1440,65536,65536,0,12074890465515160,12074904604734551,12074904604927829,12074890465878235
|
|
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,252,851908,851913,4194304,256,0,0,24,24,201088,0x7f1813b26500,0x7f16e3a37040,0,524288,524288,65536,0,131072,524288,0,594103,594103,0,0,65536,65536,46596096,559638410,19864016,472010170,67764224,5060248,4587447,68416217,45219840,0,0,66912256,196608,0,131072,524288,0,524288,131072,65536,4282384384,8781824,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,3264,48,0,0,0,3312,0,8781824,8750034,96,42454,218536,0,0,131072,129584,48,1440,65536,65536,0,12074890465942755,12074904604996629,12074904605381266,12074890466600467
|
|
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,254,851908,851913,4194304,256,0,0,24,24,204608,0x7f1813b26400,0x7f16e3a37080,0,524288,524288,65536,0,131072,524288,0,280767,280767,0,0,65536,65536,29556736,250080691,25722783,194866708,29491200,2257304,2080676,30925575,28180480,0,0,28639232,196608,0,131072,524288,0,524288,131072,65536,1832910848,7208960,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,2688,48,0,0,0,2736,0,7208960,7179268,134,54560,221014,0,0,131072,129584,48,1440,65536,65536,0,12074890466636374,12074904605470865,12074904605647343,12074890467010700
|
|
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,256,851908,851913,4194304,256,0,0,20,24,206080,0x7f1813b26300,0x7f16e3a370c0,0,524288,524288,9895936,0,131072,524288,0,928078,928078,0,0,4325376,65536,125042688,889807161,96037106,672462919,121307136,7400152,7233241,107959040,105840640,0,0,106364928,10027008,0,4390912,524288,0,524288,131072,9895936,6807355392,19202048,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1200,48,0,0,0,1248,0,19202048,19200326,50,2069,219970,0,0,131072,129584,48,1440,0,131072,0,12074890467107890,12074904605697103,12074904606307498,12074890467975332
|
|
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,258,851908,851913,4194304,256,0,0,28,24,209600,0x7f1813b26a00,0x7f16e3a37100,0,524288,524288,65536,0,65536,524288,0,503375,503375,0,0,65536,65536,30015488,461300475,21049165,384837564,55413022,4006296,3833625,56988057,28639232,0,0,54626590,131072,0,131072,524288,0,524288,65536,65536,3493855232,7340032,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,2736,48,0,0,0,2784,0,7340032,7321907,97,19242,203453,0,0,65536,64048,48,1440,0,0,65536,12074890467999297,12074904606381417,12074904606712134,12074890468613148
|
|
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,260,851908,851913,4194304,256,0,0,24,24,213120,0x7f1813b26900,0x7f16e3a37140,0,524288,524288,131072,0,131072,524288,0,284239,284239,0,0,65536,65536,30081024,254272306,24881468,199375350,30015488,2285336,2102437,31266244,28639232,0,0,29097984,262144,0,131072,524288,0,524288,131072,131072,1862270976,7274496,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,2736,48,0,0,0,2784,0,7274496,7246798,101,41218,218370,0,0,131072,129584,48,1440,65536,65536,0,12074890468638284,12074904606783654,12074904606962532,12074890469027317
|
|
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,262,851908,851913,4194304,256,0,0,24,24,218176,0x7f1813b26800,0x7f16e3a37180,0,524288,524288,65536,0,131072,524288,0,698895,698895,0,0,65536,65536,54984704,664434639,22525089,561562414,80347136,5876056,5416780,80875876,53608448,0,0,79495168,196608,0,131072,524288,0,524288,131072,65536,5087690752,10354688,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,3840,48,0,0,0,3888,0,10354688,10317397,133,63958,221928,0,0,131072,129584,48,1440,65536,65536,0,12074890469123847,12074904607015492,12074904607470528,12074890469808148
|
|
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,264,851908,851913,4194304,256,0,0,24,24,222208,0x7f1813b26700,0x7f16e3a371c0,0,524288,524288,65536,0,131072,524288,0,314286,314286,0,0,65536,65536,33751040,283039592,25465676,223888412,33685504,2522584,2346185,34890313,32374784,0,0,32833536,196608,0,131072,524288,0,524288,131072,65536,2101346304,8257536,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,3072,48,0,0,0,3120,0,8257536,8227341,268,64695,221513,0,0,131072,129584,48,1440,65536,65536,0,12074890469867839,12074904607555167,12074904607754685,12074890470328205
|
|
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,266,851908,851913,4194304,256,0,0,20,24,223936,0x7f1813b26600,0x7f16e3a37200,0,524288,524288,9895936,0,131072,524288,0,1066678,1066678,0,0,4325376,65536,141819904,1028683902,96422838,794176712,138084352,8521560,8355568,124720543,122617856,0,0,123142144,10027008,0,4390912,524288,0,524288,131072,9895936,7881097216,21299200,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1296,48,0,0,0,1344,0,21299200,21297319,48,2160,222679,0,0,131072,129584,48,1440,0,131072,0,12074890470352460,12074904607820285,12074904608530518,12074890471336529
|
|
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,268,851908,851913,4194304,256,0,0,28,24,227968,0x7f1813b26500,0x7f16e3a37240,0,524288,524288,65536,0,65536,524288,0,567526,567526,0,0,65536,65536,34209792,532659927,19677854,449184228,63798147,4869464,4385005,65351964,32833536,0,0,63011715,131072,0,131072,524288,0,524288,65536,65536,4030726144,8388608,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,3120,48,0,0,0,3168,0,8388608,8364332,96,25662,202457,0,0,65536,64048,48,1440,0,0,65536,12074890471362377,12074904608607958,12074904608981555,12074890472027693
|
|
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,270,851908,851913,4194304,256,0,0,24,24,232000,0x7f1813b26400,0x7f16e3a37280,0,524288,524288,131072,0,131072,524288,0,318854,318854,0,0,65536,65536,34275328,289512978,28799607,226503579,34209792,2560472,2386743,35512761,32833536,0,0,33292288,262144,0,131072,524288,0,524288,131072,131072,2130706432,8323072,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,3120,48,0,0,0,3168,0,8323072,8288654,206,67129,225213,0,0,131072,129584,48,1440,65536,65536,0,12074890472059382,12074904609058674,12074904609261232,12074890472539845
|
|
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,272,851908,851913,4194304,256,0,0,24,24,237824,0x7f1813b26300,0x7f16e3a372c0,0,524288,524288,65536,0,131072,524288,0,802967,802967,0,0,65536,65536,63373312,768461267,24622017,650909202,92930048,6435480,6254532,93385821,61997056,0,0,92078080,196608,0,131072,524288,0,524288,131072,65536,5892997120,11927552,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,4416,48,0,0,0,4464,0,11927552,11880443,144,65198,226543,0,0,131072,129584,48,1440,65536,65536,0,12074890472563930,12074904609329872,12074904609854987,12074890473364758
|
|
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,274,851908,851913,4194304,256,0,0,24,24,242368,0x7f1813b26a00,0x7f16e3a37300,0,524288,524288,65536,0,131072,524288,0,350422,350422,0,0,65536,65536,37945344,321192368,30406351,252906209,37879808,2795736,2630971,39129952,36569088,0,0,37027840,196608,0,131072,524288,0,524288,131072,65536,2369781760,9306112,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,3456,48,0,0,0,3504,0,9306112,9269893,240,71259,213861,0,0,131072,129584,48,1440,65536,65536,0,12074890473401296,12074904609934666,12074904610157544,12074890473889403
|
|
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,276,851908,851913,4194304,256,0,0,20,24,243584,0x7f1813b26900,0x7f16e3a37340,0,524288,524288,18284544,0,131072,524288,0,1206951,1206951,0,0,8519680,65536,175374336,1168785988,119120424,882221084,167444480,9676504,9487985,141668138,139395072,0,0,139919360,18415616,0,8585216,524288,0,524288,131072,18284544,8954839040,29163520,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1008,48,0,0,0,1056,0,29163520,29162231,48,1589,146424,0,0,131072,129584,48,1440,0,131072,0,12074890473912937,12074904610232264,12074904611030657,12074890475008613
|
|
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,278,851908,851913,4194304,256,0,0,28,24,248128,0x7f1813b26800,0x7f16e3a37380,0,524288,524288,65536,0,65536,524288,0,639342,639342,0,0,65536,65536,38404096,601864308,20844314,508833670,72186157,5104344,4938242,73590266,37027840,0,0,71399725,131072,0,131072,524288,0,524288,65536,65536,4567597056,9437184,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,3504,48,0,0,0,3552,0,9437184,9389580,96,50229,205375,0,0,65536,64048,48,1440,0,0,65536,12074890475033860,12074904611105536,12074904611524893,12074890475733590
|
|
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,280,851908,851913,4194304,256,0,0,24,24,252672,0x7f1813b26700,0x7f16e3a373c0,0,524288,524288,131072,0,131072,524288,0,354159,354159,0,0,65536,65536,38469632,320721397,26204690,256112611,38404096,2826008,2656764,39584636,37027840,0,0,37486592,262144,0,131072,524288,0,524288,131072,131072,2399141888,9371648,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,3504,48,0,0,0,3552,0,9371648,9337374,164,56674,225532,0,0,131072,129584,48,1440,65536,65536,0,12074890475759839,12074904611593532,12074904611818970,12074890476262974
|
|
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,282,851908,851913,4194304,256,0,0,24,24,259264,0x7f1813b26600,0x7f16e3a37400,0,524288,524288,65536,0,131072,524288,0,910214,910214,0,0,65536,65536,71761920,873265461,27213115,740539386,105512960,7305176,7113391,106199197,70385664,0,0,104660992,196608,0,131072,524288,0,524288,131072,65536,6698303488,13500416,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,4992,48,0,0,0,5040,0,13500416,13447967,154,82781,224200,0,0,131072,129584,48,1440,65536,65536,0,12074890476288181,12074904611885210,12074904612481845,12074890477167364
|
|
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,284,851908,851913,4194304,256,0,0,24,24,264832,0x7f1813b26500,0x7f16e3a37440,0,524288,524288,65536,0,131072,524288,0,418638,418638,0,0,65536,65536,46465024,383279412,25901913,310978011,46399488,3720472,3173216,47219692,45088768,0,0,45547520,196608,0,131072,524288,0,524288,131072,65536,2915041280,11403264,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,4224,48,0,0,0,4272,0,11403264,11363238,338,95384,225233,0,0,131072,129584,48,1440,65536,65536,0,12074890477204824,12074904612561524,12074904612829522,12074890477744838
|
|
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,286,851908,851913,4194304,256,0,0,20,24,266304,0x7f1813b26400,0x7f16e3a37480,0,524288,524288,18284544,0,131072,524288,0,1487558,1487558,0,0,8519680,65536,208928768,1446227010,117156670,1128071428,200998912,11911896,11736213,175270509,172949504,0,0,173473792,18415616,0,8585216,524288,0,524288,131072,18284544,11102322688,33357824,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1104,48,0,0,0,1152,0,33357824,33356088,97,1909,222808,0,0,131072,129584,48,1440,0,131072,0,12074890477775354,12074904612897201,12074904613881672,12074890479031980
|
|
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,288,851908,851913,4194304,256,0,0,28,24,271872,0x7f1813b26300,0x7f16e3a374c0,0,524288,524288,65536,0,65536,524288,0,778454,778454,0,0,65536,65536,46923776,737896621,18738178,630068719,89090333,6221720,6059659,90361611,45547520,0,0,88303901,131072,0,131072,524288,0,524288,65536,65536,5649727488,11534336,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,4272,48,0,0,0,4320,0,11534336,11496581,97,49933,185725,0,0,65536,64048,48,1440,0,0,65536,12074890479058359,12074904613964392,12074904614478627,12074890479850992
|
|
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,290,851908,851913,4194304,256,0,0,24,24,277440,0x7f1813b26a00,0x7f16e3a37500,0,524288,524288,131072,0,131072,524288,0,422999,422999,0,0,65536,65536,46989312,391177995,26712595,317541624,46923776,3381208,3211545,47756539,45547520,0,0,46006272,262144,0,131072,524288,0,524288,131072,131072,2944401408,11534336,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,4272,48,0,0,0,4320,0,11534336,11506458,759,94709,225514,0,0,131072,129584,48,1440,65536,65536,0,12074890479874405,12074904614554467,12074904614825344,12074890480429026
|
|
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,292,851908,851913,4194304,256,0,0,12,24,279936,0x7f1813b26900,0x7f16e3a37540,0,524288,524288,4849664,0,131072,524288,0,1125830,1125830,0,0,2162688,65536,97845248,1088203693,79939390,869852271,138412032,9019416,8846915,132039276,87949312,0,0,130678784,4980736,0,2228224,524288,0,524288,131072,4849664,8363442176,19267584,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1968,48,0,0,0,2016,0,19267584,19260976,48,6613,137488,0,0,131072,129584,48,1440,65536,65536,0,12074890480454443,12074904614893824,12074904615631257,12074890481466013
|
|
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,294,851908,851913,4194304,256,0,0,24,24,286528,0x7f1813b26800,0x7f16e3a37580,0,524288,524288,65536,0,131072,524288,0,489270,489270,0,0,65536,65536,54853632,454739795,25811786,374139913,54788096,3911960,3741496,55696977,53477376,0,0,53936128,196608,0,131072,524288,0,524288,131072,65536,3451912192,13500416,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,4992,48,0,0,0,5040,0,13500416,13460794,644,124966,226423,0,0,131072,129584,48,1440,65536,65536,0,12074890481512750,12074904615710297,12074904616025974,12074890482087969
|
|
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,296,851908,851913,4194304,256,0,0,20,24,288000,0x7f1813b26700,0x7f16e3a375c0,0,524288,524288,18284544,0,131072,524288,0,1767847,1767847,0,0,8519680,65536,242483200,1724755675,116574351,1373627980,234553344,14129816,13973787,208747797,206503936,0,0,207028224,18415616,0,8585216,524288,0,524288,131072,18284544,13249806336,37552128,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1200,48,0,0,0,1248,0,37552128,37550478,48,1943,208410,0,0,131072,129584,48,1440,0,131072,0,12074890482117914,12074904616097813,12074904617270763,12074890483567538
|
|
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,298,851908,851913,4194304,256,0,0,32,24,294592,0x7f1813b26600,0x7f16e3a37600,0,524288,524288,65536,0,65536,524288,0,918295,918295,0,0,65536,65536,55312384,811011535,20642501,684500982,105866547,7354968,7167904,107053770,53936128,0,0,105080115,131072,0,131072,524288,0,524288,65536,65536,6723469312,13631488,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,5040,48,0,0,0,5088,0,13631488,13587286,146,66839,203007,0,0,65536,64048,48,1440,0,0,65536,12074890483598877,12074904617341003,12074904617951557,12074890484480946
|
|
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,300,851908,851913,4194304,256,0,0,24,24,301184,0x7f1813b26500,0x7f16e3a37640,0,524288,524288,131072,0,131072,524288,0,495086,495086,0,0,65536,65536,55377920,459661431,27632073,376716974,55312384,3937304,3771163,56114711,53936128,0,0,54394880,262144,0,131072,524288,0,524288,131072,131072,3481272320,13631488,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,5040,48,0,0,0,5088,0,13631488,13591806,755,136832,226203,0,0,131072,129584,48,1440,65536,65536,0,12074890484505922,12074904618032197,12074904618351234,12074890485102811
|
|
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,302,851908,851913,4194304,256,0,0,12,24,304960,0x7f1813b26400,0x7f16e3a37680,0,524288,524288,3801088,0,131072,524288,0,1337031,1337031,0,0,1638400,65536,112525312,1298218368,78681922,1057531454,162004992,10694936,10529327,157212742,104726528,0,0,155844608,3932160,0,1703936,524288,0,524288,131072,3801088,9974054912,21692416,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,2832,48,0,0,0,2880,0,21692416,21681518,96,11081,220891,0,0,131072,129584,48,1440,65536,65536,0,12074890485126706,12074904618428513,12074904619305146,12074890486288124
|
|
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,304,851908,851913,4194304,256,0,0,24,24,313600,0x7f1813b26300,0x7f16e3a376c0,0,524288,524288,65536,0,131072,524288,0,631526,631526,0,0,65536,65536,71630848,593613111,30070983,491976816,71565312,5034584,4867390,72475045,70254592,0,0,70713344,196608,0,131072,524288,0,524288,131072,65536,4525654016,17694720,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,6528,48,0,0,0,6576,0,17694720,17642606,954,179302,218592,0,0,131072,129584,48,1440,65536,65536,0,12074890486332707,12074904619389779,12074904619799856,12074890486999156
|
|
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,306,851908,851913,4194304,256,0,0,20,24,314816,0x7f1813b26a00,0x7f16e3a37700,0,524288,524288,35061760,0,131072,524288,0,2332167,2332167,0,0,16908288,65536,343146496,2284129928,162900246,1794401650,326828032,18652184,18493429,276268901,273612800,0,0,274137088,35192832,0,16973824,524288,0,524288,131072,35061760,17544773632,57475072,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1008,48,0,0,0,1056,0,57475072,57473654,49,1835,221848,0,0,131072,129584,48,1440,0,131072,0,12074890487029332,12074904619875694,12074904621424803,12074890488857890
|
|
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,308,851908,851913,4194304,256,0,0,20,24,317568,0x7f1813b26900,0x7f16e3a37740,0,524288,524288,4849664,0,65536,524288,0,1199262,1199262,0,0,2162688,65536,80871424,1160477453,83239589,930543300,146694444,9603224,9432828,140857639,71041024,0,0,139026732,4915200,0,2228224,524288,0,524288,65536,4849664,8896118784,19660800,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,2064,48,0,0,0,2112,0,19660800,19652594,51,8377,204934,0,0,65536,64048,48,1440,0,0,65536,12074890488887264,12074904621540322,12074904622335996,12074890489972992
|
|
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,310,851908,851913,4194304,256,0,0,12,24,320320,0x7f1813b26800,0x7f16e3a37780,0,524288,524288,4915200,0,131072,524288,0,676158,676158,0,0,2162688,65536,81461248,607917688,88296435,439798405,79822848,5400856,4958519,73985373,71499776,0,0,72024064,5046272,0,2228224,524288,0,524288,131072,4915200,4609540096,20381696,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,2112,48,0,0,0,2160,0,20381696,20371959,50,10719,217878,0,0,131072,129584,48,1440,65536,65536,0,12074890490007155,12074904622453275,12074904622867352,12074890490729378
|
|
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,312,851908,851913,4194304,256,0,0,12,24,324096,0x7f1813b26700,0x7f16e3a377c0,0,524288,524288,4849664,0,131072,524288,0,1757078,1757078,0,0,2162688,65536,148176896,1714909181,82711530,1418288147,213909504,14065176,13899068,207555370,138280960,0,0,206176256,4980736,0,2228224,524288,0,524288,131072,4849664,13195280384,28704768,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,2832,48,0,0,0,2880,0,28704768,28694035,96,11086,222714,0,0,131072,129584,48,1440,65536,65536,0,12074890490756167,12074904622979831,12074904624138702,12074890492190273
|
|
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,314,851908,851913,4194304,256,0,0,12,24,328896,0x7f1813b26600,0x7f16e3a37800,0,524288,524288,4849664,0,131072,524288,0,1197622,1197622,0,0,2162688,65536,148045824,1162155778,101894814,913853540,146407424,9580504,9424387,140685530,138149888,0,0,138674176,4980736,0,2228224,524288,0,524288,131072,4849664,8875147264,36634624,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,3600,48,0,0,0,3648,0,36634624,36613492,96,23350,220159,0,0,131072,129584,48,1440,65536,65536,0,12074890492228363,12074904624266221,12074904625051816,12074890493279597
|
|
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,316,851908,851913,4194304,256,0,0,20,24,330112,0x7f1813b26500,0x7f16e3a37840,0,524288,524288,68616192,0,131072,524288,0,4584231,4584231,0,0,33685504,65536,678690816,4515795814,255237877,3614962801,645595136,36681688,36511477,545577863,542048256,0,0,542572544,68747264,0,33751040,524288,0,524288,131072,68616192,34724642816,105840640,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1008,48,0,0,0,1056,0,105840640,105839287,98,1725,223874,0,0,131072,129584,48,1440,0,131072,0,12074890493310685,12074904625176135,12074904628227792,12074890496636555
|
|
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,318,851908,851913,4194304,256,0,0,20,24,332864,0x7f1813b26400,0x7f16e3a37880,0,524288,524288,9043968,0,65536,524288,0,2327278,2327278,0,0,4259840,65536,156368896,2275359828,94315184,1893838834,287205838,18591320,18425275,275245630,138149888,0,0,273246670,9109504,0,4325376,524288,0,524288,65536,9043968,17486053376,38535168,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,2064,48,0,0,0,2112,0,38535168,38529064,49,6473,207136,0,0,65536,64048,48,1440,0,0,65536,12074890496668745,12074904628345711,12074904629887139,12074890498488828
|
|
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,320,851908,851913,4194304,256,0,0,12,24,335616,0x7f1813b26300,0x7f16e3a378c0,0,524288,524288,9109504,0,131072,524288,0,1205447,1205447,0,0,4259840,65536,156958720,1166639179,113740190,899675821,153223168,9616280,9463275,141274331,138608640,0,0,139132928,9240576,0,4325376,524288,0,524288,131072,9109504,8904507392,39124992,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,2112,48,0,0,0,2160,0,39124992,39117824,101,7618,223142,0,0,131072,129584,48,1440,65536,65536,0,12074890498514155,12074904630005859,12074904630794813,12074890499591487
|
|
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,322,851908,851913,4194304,256,0,0,12,24,339392,0x7f1813b26a00,0x7f16e3a37900,0,524288,524288,9043968,0,131072,524288,0,3443614,3443614,0,0,4259840,65536,290783232,3386346289,104450692,2860368045,421527552,27543448,27381466,409132595,272498688,0,0,407502848,9175040,0,4325376,524288,0,524288,131072,9043968,26080182272,55771136,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,2832,48,0,0,0,2880,0,55771136,55759059,96,12390,220471,0,0,131072,129584,48,1440,65536,65536,0,12074890499621863,12074904630913692,12074904633195435,12074890502186249
|
|
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,324,851908,851913,4194304,256,0,0,12,24,344192,0x7f1813b26900,0x7f16e3a37940,0,524288,524288,9043968,0,131072,524288,0,2323551,2323551,0,0,4259840,65536,290652160,2275086735,133635926,1854534201,286916608,18575704,18415516,275131257,272367616,0,0,272891904,9175040,0,4325376,524288,0,524288,131072,9043968,17465081856,72548352,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,3600,48,0,0,0,3648,0,72548352,72533721,99,14915,201823,0,0,131072,129584,48,1440,65536,65536,0,12074890502234689,12074904633322314,12074904634857662,12074890504027040
|
|
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,326,851908,851913,4194304,256,0,0,20,24,345408,0x7f1813b26800,0x7f16e3a37980,0,524288,524288,135725056,0,131072,524288,0,9090510,9090510,0,0,67239936,65536,1349779456,8977865147,433798760,7260937043,1283129344,72699288,72532831,1084081346,1078919168,0,0,1079443456,135856128,0,67305472,524288,0,524288,131072,135725056,69084381184,210698240,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,1008,48,0,0,0,1056,0,210698240,210697043,49,1476,216718,0,0,131072,129584,48,1440,0,131072,0,12074890504059039,12074904634974621,12074904641031536,12074890510394623
|
|
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,328,851908,851913,4194304,256,0,0,20,24,348160,0x7f1813b26700,0x7f16e3a379c0,0,524288,524288,17432576,0,65536,524288,0,4575078,4575078,0,0,8454144,65536,307363840,4501632472,143940076,3789462299,568230643,36588952,36420313,544054474,272367616,0,0,541688563,17498112,0,8519680,524288,0,524288,65536,17432576,34665922560,76283904,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,131072,2064,48,0,0,0,2112,0,76283904,76277998,96,6076,210025,0,0,65536,64048,48,1440,0,0,65536,12074890510427003,12074904641151695,12074904644195353,12074890513746252
|
|
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,330,851908,851913,4194304,256,0,0,12,24,350912,0x7f1813b26600,0x7f16e3a37a00,0,524288,524288,17498112,0,131072,524288,0,2328319,2328319,0,0,8454144,65536,307953664,2280121574,152776406,1827321360,300023808,18625880,18466068,275781321,272826368,0,0,273350656,17629184,0,8519680,524288,0,524288,131072,17498112,17494441984,77398016,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,2112,48,0,0,0,2160,0,77398016,77390202,97,8056,223283,0,0,131072,129584,48,1440,65536,65536,0,12074890513777710,12074904644317912,12074904645857580,12074890515601179
|
|
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,332,851908,851913,4194304,256,0,0,12,24,0,0x7f1813b26500,0x7f16e3a37a40,0,524288,524288,17432576,0,131072,524288,0,6812694,6812694,0,0,8454144,65536,575995904,6723921276,124271951,5762885677,836763648,54494296,54334247,812025767,540934144,0,0,810156032,17563648,0,8519680,524288,0,524288,131072,17432576,51849986048,110821376,0,0,0,65536,65536,0,0,0,0,4194304,0,0,0,0,0,262144,2832,48,0,0,0,2880,0,110821376,110809880,97,12072,220446,0,0,131072,129584,48,1440,65536,65536,0,12074890515629211,12074904645981739,12074904650508745,12074890520442826
|