169 lines
66 KiB
CSV
169 lines
66 KiB
CSV
|
|
Index,KernelName,gpu-id,queue-id,queue-index,pid,tid,grd,wgr,lds,scr,vgpr,sgpr,fbar,sig,obj,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,TCP_TCC_READ_REQ_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RDREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WRREQ_sum,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,SQ_LDS_IDX_ACTIVE,SQ_LDS_BANK_CONFLICT,DispatchNs,BeginNs,EndNs,CompleteNs
|
||
|
|
0,"__amd_rocclr_fillBufferAligned.kd",0,0,0,205593,205593,33554432,256,0,0,4,32,4160,0x0,0x7fb29e004280,0,0,0,0,0,0,0,0,0.0000000000,8388608.0000000000,4194304.0000000000,0.0000000000,0.0000000000,311.0000000000,4128768.0000000000,4128768.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328148540641,17298633283344,17328294281885,17328294388625
|
||
|
|
1,"void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]",0,0,2,205593,205593,32768,256,0,0,12,24,13888,0x0,0x7fb29e023f80,0,0,0,0,0,0,0,0,8192.0000000000,16384.0000000000,0.0000000000,0.0000000000,0.0000000000,8261.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328300094873,17328294281885,17328300453942,17328300461664
|
||
|
|
2,"void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]",0,0,5,205593,205593,4194304,256,0,0,12,24,14336,0x7fb2a0fd2380,0x7fb29e023fc0,0,0,0,0,0,0,262144,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097345.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328301054088,17328300453942,17328301719073,17328301718850
|
||
|
|
3,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,8,205593,205593,4194304,256,0,0,16,24,15040,0x7fb2a0fd2200,0x7fb29e024000,0,0,0,0,0,0,262144,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194593.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328302318134,17328301719073,17328303113647,17328303113173
|
||
|
|
4,"void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]",0,0,11,205593,205593,4194304,256,0,0,16,24,15488,0x7fb2a0fd2080,0x7fb29e024040,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194659.0000000000,0.0000000000,0.0000000000,0,0,262144,0,0,0,0,0,0.0000000000,0,0,17328303707418,17328303113647,17328304329338,17328304328441
|
||
|
|
5,"void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]",0,0,14,205593,205593,4194304,256,0,0,12,24,15936,0x7fb29e931f00,0x7fb29e024080,0,0,262144,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097345.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328304925515,17328304329338,17328305564070,17328305563978
|
||
|
|
6,"void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]",0,0,17,205593,205593,4194304,256,0,0,12,24,16384,0x7fb29e931d80,0x7fb29e0240c0,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097343.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328306156853,17328305564070,17328306818961,17328306818675
|
||
|
|
7,"void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]",0,0,20,205593,205593,4194304,256,0,0,12,24,17088,0x7fb29e931c00,0x7fb29e024100,0,0,0,0,0,0,655360,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097342.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328307425379,17328306818961,17328308081693,17328308081252
|
||
|
|
8,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,23,205593,205593,4194304,256,0,0,16,24,17792,0x7fb29e931a80,0x7fb29e024140,0,0,0,0,0,0,786432,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194597.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328308676366,17328308081693,17328309416426,17328309416006
|
||
|
|
9,"void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]",0,0,26,205593,205593,4194304,256,0,0,16,24,18496,0x7fb29e931900,0x7fb29e024180,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194589.0000000000,0.0000000000,0.0000000000,0,0,786432,0,0,0,0,0,0.0000000000,0,0,17328310010780,17328309416426,17328310740598,17328310739441
|
||
|
|
10,"void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]",0,0,29,205593,205593,4194304,256,0,0,16,24,19200,0x7fb29e931780,0x7fb29e0241c0,0,0,786432,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097350.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328311333965,17328310740598,17328312046370,17328312045916
|
||
|
|
11,"void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]",0,0,32,205593,205593,4194304,256,0,0,16,24,19904,0x7fb29e931600,0x7fb29e024200,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097349.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328312639761,17328312046370,17328313232142,17328313230295
|
||
|
|
12,"void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]",0,0,35,205593,205593,4194304,256,0,0,12,24,20608,0x7fb2a0fd2480,0x7fb29e024240,0,0,0,0,0,0,1048576,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097346.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328313833319,17328313232142,17328314444153,17328314443003
|
||
|
|
13,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,38,205593,205593,4194304,256,0,0,16,24,21312,0x7fb2a0fd2300,0x7fb29e024280,0,0,0,0,0,0,1310720,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194616.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328315038657,17328314444153,17328315713605,17328315712150
|
||
|
|
14,"void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]",0,0,41,205593,205593,4194304,256,0,0,16,24,22016,0x7fb2a0fd2180,0x7fb29e0242c0,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194580.0000000000,0.0000000000,0.0000000000,0,0,1310720,0,0,0,0,0,0.0000000000,0,0,17328316307444,17328315713605,17328317025777,17328317024365
|
||
|
|
15,"void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]",0,0,44,205593,205593,4194304,256,0,0,16,24,22720,0x7fb2a0fd2000,0x7fb29e024300,0,0,1310720,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097351.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328317619859,17328317025777,17328318259869,17328318259372
|
||
|
|
16,"void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]",0,0,47,205593,205593,4194304,256,0,0,12,24,23424,0x7fb29e931e80,0x7fb29e024340,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097348.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328318854107,17328318259869,17328319468520,17328319467550
|
||
|
|
17,"void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]",0,0,50,205593,205593,4194304,256,0,0,12,24,24128,0x7fb29e931d00,0x7fb29e024380,0,0,0,0,0,0,1441792,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097345.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328320071034,17328319468520,17328320661971,17328320660459
|
||
|
|
18,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,53,205593,205593,4194304,256,0,0,16,24,24832,0x7fb29e931b80,0x7fb29e0243c0,0,0,0,0,0,0,1835008,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194581.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328321256363,17328320661971,17328321925663,17328321926915
|
||
|
|
19,"void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]",0,0,56,205593,205593,4194304,256,0,0,16,24,25536,0x7fb29e931a00,0x7fb29e024400,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194592.0000000000,0.0000000000,0.0000000000,0,0,1835008,0,0,0,0,0,0.0000000000,0,0,17328322519929,17328321925663,17328323243916,17328323242420
|
||
|
|
20,"void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]",0,0,59,205593,205593,4194304,256,0,0,12,24,26240,0x7fb29e931880,0x7fb29e024440,0,0,1835008,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097344.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328323837535,17328323243916,17328324444247,17328324443068
|
||
|
|
21,"void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]",0,0,62,205593,205593,4194304,256,0,0,12,24,26944,0x7fb29e931700,0x7fb29e024480,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097347.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328325038323,17328324444247,17328325665378,17328325663796
|
||
|
|
22,"void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]",0,0,65,205593,205593,4194304,256,0,0,12,24,27648,0x7fb2a0fd2580,0x7fb29e0244c0,0,0,0,0,0,0,1835008,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097332.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328326267310,17328325665378,17328326861870,17328326860424
|
||
|
|
23,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,68,205593,205593,4194304,256,0,0,16,24,28608,0x7fb2a0fd2400,0x7fb29e024500,0,0,0,0,0,0,2359296,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194591.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328327455449,17328326861870,17328328142202,17328328140540
|
||
|
|
24,"void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]",0,0,71,205593,205593,4194304,256,0,0,16,24,29312,0x7fb2a0fd2280,0x7fb29e024540,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194593.0000000000,0.0000000000,0.0000000000,0,0,2359296,0,0,0,0,0,0.0000000000,0,0,17328328736385,17328328142202,17328329451814,17328329452686
|
||
|
|
25,"void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]",0,0,74,205593,205593,4194304,256,0,0,12,24,30016,0x7fb2a0fd2100,0x7fb29e024580,0,0,2359296,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097346.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328330046860,17328329451814,17328330676305,17328330674583
|
||
|
|
26,"void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]",0,0,77,205593,205593,4194304,256,0,0,8,24,30976,0x7fb29e931f80,0x7fb29e0245c0,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097348.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328331269837,17328330676305,17328331847676,17328331845992
|
||
|
|
27,"void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]",0,0,80,205593,205593,4194304,256,0,0,12,24,31680,0x7fb29e931e00,0x7fb29e024600,0,0,0,0,0,0,2228224,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097342.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328332449036,17328331847676,17328333056168,17328333054460
|
||
|
|
28,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,83,205593,205593,4194304,256,0,0,16,24,32640,0x7fb29e931c80,0x7fb29e024640,0,0,0,0,0,0,2883584,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194601.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328333650244,17328333056168,17328334326420,17328334324696
|
||
|
|
29,"void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]",0,0,86,205593,205593,4194304,256,0,0,12,24,33600,0x7fb29e931b00,0x7fb29e024680,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194601.0000000000,0.0000000000,0.0000000000,0,0,2883584,0,0,0,0,0,0.0000000000,0,0,17328334920331,17328334326420,17328335625472,17328335623742
|
||
|
|
30,"void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]",0,0,89,205593,205593,4194304,256,0,0,12,24,34560,0x7fb29e931980,0x7fb29e0246c0,0,0,2883584,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097348.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328336218756,17328335625472,17328336812043,17328336810481
|
||
|
|
31,"void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]",0,0,92,205593,205593,4194304,256,0,0,8,24,35520,0x7fb29e931800,0x7fb29e024700,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097354.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328337404965,17328336812043,17328338020854,17328338019289
|
||
|
|
32,"void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]",0,0,95,205593,205593,4194304,256,0,0,12,24,36224,0x7fb29e931680,0x7fb29e024740,0,0,0,0,0,0,2621440,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097344.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328338623532,17328338020854,17328339238786,17328339237026
|
||
|
|
33,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,98,205593,205593,4194304,256,0,0,12,24,37184,0x7fb2a0fd2500,0x7fb29e024780,0,0,0,0,0,0,3407872,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194607.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328339833000,17328339238786,17328340514798,17328340512922
|
||
|
|
34,"void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]",0,0,101,205593,205593,4194304,256,0,0,12,24,38144,0x7fb2a0fd2380,0x7fb29e0247c0,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194588.0000000000,0.0000000000,0.0000000000,0,0,3407872,0,0,0,0,0,0.0000000000,0,0,17328341107877,17328340514798,17328341796090,17328341794448
|
||
|
|
35,"void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]",0,0,104,205593,205593,4194304,256,0,0,12,24,39104,0x7fb2a0fd2200,0x7fb29e024800,0,0,3407872,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097353.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328342389833,17328341796090,17328343012101,17328343010466
|
||
|
|
36,"void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]",0,0,107,205593,205593,4194304,256,0,0,8,24,40320,0x7fb2a0fd2080,0x7fb29e024840,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097352.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328343606550,17328343012101,17328344202673,17328344200835
|
||
|
|
37,"void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]",0,0,110,205593,205593,4194304,256,0,0,12,24,41280,0x7fb29e931f00,0x7fb29e024880,0,0,0,0,0,0,3014656,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097351.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328344804429,17328344202673,17328345410044,17328345408203
|
||
|
|
38,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,113,205593,205593,4194304,256,0,0,12,24,42240,0x7fb29e931d80,0x7fb29e0248c0,0,0,0,0,0,0,3932160,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194605.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328346002157,17328345410044,17328346719496,17328346717668
|
||
|
|
39,"void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]",0,0,116,205593,205593,4194304,256,0,0,12,24,43200,0x7fb29e931c00,0x7fb29e024900,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194589.0000000000,0.0000000000,0.0000000000,0,0,3932160,0,0,0,0,0,0.0000000000,0,0,17328347312902,17328346719496,17328347993588,17328347991694
|
||
|
|
40,"void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]",0,0,119,205593,205593,4194304,256,0,0,8,24,44160,0x7fb29e931a80,0x7fb29e024940,0,0,3932160,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097354.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328348586518,17328347993588,17328349183199,17328349181463
|
||
|
|
41,"void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]",0,0,122,205593,205593,4194304,256,0,0,12,24,45376,0x7fb29e931900,0x7fb29e024980,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097360.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328349775817,17328349183199,17328350357610,17328350355631
|
||
|
|
42,"void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]",0,0,125,205593,205593,4194304,256,0,0,12,24,46336,0x7fb29e931780,0x7fb29e0249c0,0,0,0,0,0,0,3407872,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097351.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328350959365,17328350357610,17328351573462,17328351571539
|
||
|
|
43,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,128,205593,205593,4194304,256,0,0,12,24,47552,0x7fb29e931600,0x7fb29e024a00,0,0,0,0,0,0,4456448,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194591.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328352167203,17328351573462,17328352857474,17328352855595
|
||
|
|
44,"void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]",0,0,131,205593,205593,4194304,256,0,0,12,24,48512,0x7fb2a0fd2480,0x7fb29e024a40,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194582.0000000000,0.0000000000,0.0000000000,0,0,4456448,0,0,0,0,0,0.0000000000,0,0,17328353450379,17328352857474,17328354133646,17328354132251
|
||
|
|
45,"void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]",0,0,134,205593,205593,4194304,256,0,0,8,24,49472,0x7fb2a0fd2300,0x7fb29e024a80,0,0,4456448,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097357.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328354727686,17328354133646,17328355334937,17328355332939
|
||
|
|
46,"void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]",0,0,137,205593,205593,4194304,256,0,0,12,24,50688,0x7fb2a0fd2180,0x7fb29e024ac0,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097363.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328355929644,17328355334937,17328356521508,17328356519988
|
||
|
|
47,"void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]",0,0,140,205593,205593,4194304,256,0,0,12,24,51648,0x7fb2a0fd2000,0x7fb29e024b00,0,0,0,0,0,0,3801088,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097359.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328357124562,17328356517373,17328357723454,17328357725626
|
||
|
|
48,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,143,205593,205593,4194304,256,0,0,12,24,52864,0x7fb29e931e80,0x7fb29e024b40,0,0,0,0,0,0,4980736,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194593.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328358321520,17328357723454,17328358986016,17328358988363
|
||
|
|
49,"void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]",0,0,146,205593,205593,4194304,256,0,0,12,24,54080,0x7fb29e931d00,0x7fb29e024b80,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194565.0000000000,0.0000000000,0.0000000000,0,0,4980736,0,0,0,0,0,0.0000000000,0,0,17328359582967,17328358986016,17328360230177,17328360232140
|
||
|
|
50,"void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]",0,0,149,205593,205593,4194304,256,0,0,8,24,55296,0x7fb29e931b80,0x7fb29e024bc0,0,0,4980736,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097355.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328360826864,17328360230177,17328361441539,17328361443667
|
||
|
|
51,"void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]",0,0,152,205593,205593,4194304,256,0,0,12,24,56768,0x7fb29e931a00,0x7fb29e024c00,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097364.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328362037372,17328361441539,17328362753220,17328362755443
|
||
|
|
52,"void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]",0,0,155,205593,205593,4194304,256,0,0,12,24,57728,0x7fb29e931880,0x7fb29e024c40,0,0,0,0,0,0,4194304,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097357.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328363357317,17328362753220,17328363946342,17328363948641
|
||
|
|
53,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,158,205593,205593,4194304,256,0,0,12,24,58944,0x7fb29e931700,0x7fb29e024c80,0,0,0,0,0,0,5505024,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194590.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328364543205,17328363946342,17328365234184,17328365236487
|
||
|
|
54,"void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]",0,0,161,205593,205593,4194304,256,0,0,12,24,60160,0x7fb2a0fd2580,0x7fb29e024cc0,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194573.0000000000,0.0000000000,0.0000000000,0,0,5505024,0,0,0,0,0,0.0000000000,0,0,17328365830631,17328365234184,17328366515625,17328366517793
|
||
|
|
55,"void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]",0,0,164,205593,205593,4194304,256,0,0,8,24,61376,0x7fb2a0fd2400,0x7fb29e024d00,0,0,5505024,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097358.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328367114297,17328366515625,17328367705387,17328367707491
|
||
|
|
56,"void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]",0,0,167,205593,205593,4194304,256,0,0,12,24,62848,0x7fb2a0fd2280,0x7fb29e024d40,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097361.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328368302896,17328367705387,17328368903628,17328368905770
|
||
|
|
57,"void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]",0,0,170,205593,205593,4194304,256,0,0,12,24,63808,0x7fb2a0fd2100,0x7fb29e024d80,0,0,0,0,0,0,4587520,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097357.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328369510744,17328368903628,17328370099790,17328370102458
|
||
|
|
58,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,173,205593,205593,4194304,256,0,0,12,24,65024,0x7fb29e931f80,0x7fb29e024dc0,0,0,0,0,0,0,6029312,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194564.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328370698262,17328370099790,17328371398352,17328371400483
|
||
|
|
59,"void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]",0,0,176,205593,205593,4194304,256,0,0,12,24,66240,0x7fb29e931e00,0x7fb29e024e00,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194558.0000000000,0.0000000000,0.0000000000,0,0,6029312,0,0,0,0,0,0.0000000000,0,0,17328371995608,17328371398352,17328372689233,17328372691309
|
||
|
|
60,"void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]",0,0,179,205593,205593,4194304,256,0,0,8,24,67456,0x7fb29e931c80,0x7fb29e024e40,0,0,6029312,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097359.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328373285764,17328372689233,17328373867795,17328373870428
|
||
|
|
61,"void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]",0,0,182,205593,205593,4194304,256,0,0,12,24,68928,0x7fb29e931b00,0x7fb29e024e80,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097357.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328374466052,17328373867795,17328375076116,17328375078506
|
||
|
|
62,"void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]",0,0,185,205593,205593,4194304,256,0,0,12,24,70144,0x7fb29e931980,0x7fb29e024ec0,0,0,0,0,0,0,4980736,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097355.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328375692990,17328375076116,17328376299478,17328376301884
|
||
|
|
63,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,188,205593,205593,4194304,256,0,0,12,24,71616,0x7fb29e931800,0x7fb29e024f00,0,0,0,0,0,0,6553600,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194548.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328376896578,17328376299478,17328377620760,17328377622969
|
||
|
|
64,"void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]",0,0,191,205593,205593,4194304,256,0,0,12,24,72832,0x7fb29e931680,0x7fb29e024f40,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194569.0000000000,0.0000000000,0.0000000000,0,0,6553600,0,0,0,0,0,0.0000000000,0,0,17328378218433,17328377620760,17328378911641,17328378913964
|
||
|
|
65,"void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]",0,0,194,205593,205593,4194304,256,0,0,8,24,74048,0x7fb2a0fd2500,0x7fb29e024f80,0,0,6553600,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097353.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328379507769,17328378911641,17328380094843,17328380096913
|
||
|
|
66,"void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]",0,0,197,205593,205593,4194304,256,0,0,12,24,75776,0x7fb2a0fd2380,0x7fb29e024fc0,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097350.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328380691567,17328380094843,17328381275324,17328381277432
|
||
|
|
67,"void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]",0,0,200,205593,205593,4194304,256,0,0,12,24,76992,0x7fb2a0fd2200,0x7fb29e025000,0,0,0,0,0,0,5373952,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097356.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328381878996,17328381275324,17328382517726,17328382519749
|
||
|
|
68,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,203,205593,205593,4194304,256,0,0,12,24,78464,0x7fb2a0fd2080,0x7fb29e025040,0,0,0,0,0,0,7077888,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194548.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328383115123,17328382517726,17328383759328,17328383761316
|
||
|
|
69,"void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]",0,0,206,205593,205593,4194304,256,0,0,12,24,79936,0x7fb29e931f00,0x7fb29e025080,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194566.0000000000,0.0000000000,0.0000000000,0,0,7077888,0,0,0,0,0,0.0000000000,0,0,17328384355680,17328383759328,17328385008769,17328385010603
|
||
|
|
70,"void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]",0,0,209,205593,205593,4194304,256,0,0,8,24,81408,0x7fb29e931d80,0x7fb29e0250c0,0,0,7077888,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097359.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328385603907,17328385008769,17328386169731,17328386171922
|
||
|
|
71,"void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]",0,0,212,205593,205593,4194304,256,0,0,12,24,83136,0x7fb29e931c00,0x7fb29e025100,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097346.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328386765956,17328386169731,17328387335172,17328387337311
|
||
|
|
72,"void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]",0,0,215,205593,205593,4194304,256,0,0,12,24,84352,0x7fb29e931a80,0x7fb29e025140,0,0,0,0,0,0,5767168,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097359.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328387938955,17328387335172,17328388517574,17328388519820
|
||
|
|
73,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,218,205593,205593,4194304,256,0,0,12,24,85824,0x7fb29e931900,0x7fb29e025180,0,0,0,0,0,0,7602176,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194568.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328389116654,17328388517574,17328389796456,17328389798506
|
||
|
|
74,"void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]",0,0,221,205593,205593,4194304,256,0,0,12,24,87296,0x7fb29e931780,0x7fb29e0251c0,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194565.0000000000,0.0000000000,0.0000000000,0,0,7602176,0,0,0,0,0,0.0000000000,0,0,17328390394110,17328389796456,17328391070697,17328391072752
|
||
|
|
75,"void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]",0,0,224,205593,205593,4194304,256,0,0,12,24,88768,0x7fb29e931600,0x7fb29e025200,0,0,7602176,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097357.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328391666726,17328391070697,17328392270219,17328392272600
|
||
|
|
76,"void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]",0,0,227,205593,205593,4194304,256,0,0,12,24,90752,0x7fb2a0fd2480,0x7fb29e025240,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097340.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328392867004,17328392270219,17328393504940,17328393507137
|
||
|
|
77,"void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]",0,0,230,205593,205593,4194304,256,0,0,12,24,91968,0x7fb2a0fd2300,0x7fb29e025280,0,0,0,0,0,0,6160384,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097359.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328394112851,17328393504940,17328394706702,17328394708966
|
||
|
|
78,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,233,205593,205593,4194304,256,0,0,12,24,93440,0x7fb2a0fd2180,0x7fb29e0252c0,0,0,0,0,0,0,8126464,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194574.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328395304520,17328394706702,17328395974704,17328395976882
|
||
|
|
79,"void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]",0,0,236,205593,205593,4194304,256,0,0,12,24,94912,0x7fb2a0fd2000,0x7fb29e025300,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194575.0000000000,0.0000000000,0.0000000000,0,0,8126464,0,0,0,0,0,0.0000000000,0,0,17328396571917,17328395974704,17328397247505,17328397249809
|
||
|
|
80,"void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]",0,0,239,205593,205593,4194304,256,0,0,12,24,96384,0x7fb29e931e80,0x7fb29e025340,0,0,8126464,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097361.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328397843473,17328397247505,17328398443667,17328398446047
|
||
|
|
81,"void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]",0,0,242,205593,205593,4194304,256,0,0,12,24,98368,0x7fb29e931d00,0x7fb29e025380,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097343.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328399041221,17328398443667,17328399661748,17328399664185
|
||
|
|
82,"void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]",0,0,245,205593,205593,4194304,256,0,0,12,24,99584,0x7fb29e931b80,0x7fb29e0253c0,0,0,0,0,0,0,6553600,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097361.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328400266419,17328399661748,17328400848630,17328400851133
|
||
|
|
83,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,248,205593,205593,4194304,256,0,0,12,24,101312,0x7fb29e931a00,0x7fb29e025400,0,0,0,0,0,0,8650752,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194577.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328401444868,17328400848630,17328402132472,17328402134629
|
||
|
|
84,"void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]",0,0,251,205593,205593,4194304,256,0,0,12,24,102784,0x7fb29e931880,0x7fb29e025440,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194583.0000000000,0.0000000000,0.0000000000,0,0,8650752,0,0,0,0,0,0.0000000000,0,0,17328402729994,17328402132472,17328403411193,17328403413405
|
||
|
|
85,"void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]",0,0,254,205593,205593,4194304,256,0,0,12,24,104256,0x7fb29e931700,0x7fb29e025480,0,0,8650752,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097361.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328404008540,17328403411193,17328404614075,17328404616254
|
||
|
|
86,"void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]",0,0,257,205593,205593,4194304,256,0,0,12,24,106240,0x7fb2a0fd2580,0x7fb29e0254c0,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097338.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328405211598,17328404614075,17328405826556,17328405828941
|
||
|
|
87,"void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]",0,0,260,205593,205593,4194304,256,0,0,12,24,107712,0x7fb2a0fd2400,0x7fb29e025500,0,0,0,0,0,0,6946816,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097358.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328406432335,17328405826556,17328407036798,17328407038809
|
||
|
|
88,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,263,205593,205593,4194304,256,0,0,16,24,109440,0x7fb2a0fd2280,0x7fb29e025540,0,0,0,0,0,0,9175040,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194548.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328407634613,17328407036798,17328408324960,17328408327025
|
||
|
|
89,"void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]",0,0,266,205593,205593,4194304,256,0,0,16,24,111168,0x7fb2a0fd2100,0x7fb29e025580,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194569.0000000000,0.0000000000,0.0000000000,0,0,9175040,0,0,0,0,0,0.0000000000,0,0,17328408921869,17328408324960,17328409608641,17328409611001
|
||
|
|
90,"void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]",0,0,269,205593,205593,4194304,256,0,0,8,24,112896,0x7fb29e931f80,0x7fb29e0255c0,0,0,9175040,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097367.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328410206285,17328409608641,17328410786883,17328410789430
|
||
|
|
91,"void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]",0,0,272,205593,205593,4194304,256,0,0,12,24,115136,0x7fb29e931e00,0x7fb29e025600,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097344.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328411383174,17328410786883,17328412023844,17328412026347
|
||
|
|
92,"void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]",0,0,275,205593,205593,4194304,256,0,0,12,24,116608,0x7fb29e931c80,0x7fb29e025640,0,0,0,0,0,0,7340032,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097361.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328412629001,17328412023844,17328413209126,17328413211356
|
||
|
|
93,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,278,205593,205593,4194304,256,0,0,16,24,118336,0x7fb29e931b00,0x7fb29e025680,0,0,0,0,0,0,9699328,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194576.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328413806550,17328413209126,17328414503368,17328414506241
|
||
|
|
94,"void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]",0,0,281,205593,205593,4194304,256,0,0,16,24,120064,0x7fb29e931980,0x7fb29e0256c0,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194578.0000000000,0.0000000000,0.0000000000,0,0,9699328,0,0,0,0,0,0.0000000000,0,0,17328415101626,17328414503368,17328415789609,17328415791837
|
||
|
|
95,"void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]",0,0,284,205593,205593,4194304,256,0,0,12,24,121792,0x7fb29e931800,0x7fb29e025700,0,0,9699328,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097363.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328416386431,17328415789609,17328416979211,17328416981526
|
||
|
|
96,"void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]",0,0,287,205593,205593,4194304,256,0,0,12,24,124032,0x7fb29e931680,0x7fb29e025740,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097334.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328417576290,17328416979211,17328418193932,17328418196703
|
||
|
|
97,"void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]",0,0,290,205593,205593,4194304,256,0,0,12,24,125504,0x7fb2a0fd2500,0x7fb29e025780,0,0,0,0,0,0,8126464,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097368.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328418799327,17328418193932,17328419437614,17328419440090
|
||
|
|
98,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,293,205593,205593,4194304,256,0,0,12,24,127488,0x7fb2a0fd2380,0x7fb29e0257c0,0,0,0,0,0,0,10747904,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194606.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328420036435,17328419437655,17328420708056,17328420710167
|
||
|
|
99,"void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]",0,0,296,205593,205593,4194304,256,0,0,12,24,129216,0x7fb2a0fd2200,0x7fb29e025800,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194602.0000000000,0.0000000000,0.0000000000,0,0,10747904,0,0,0,0,0,0.0000000000,0,0,17328421305041,17328420708056,17328421992698,17328421994743
|
||
|
|
100,"void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]",0,0,299,205593,205593,4194304,256,0,0,12,24,130944,0x7fb2a0fd2080,0x7fb29e025840,0,0,10747904,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097364.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328422591457,17328421992698,17328423157499,17328423159702
|
||
|
|
101,"void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]",0,0,302,205593,205593,4194304,256,0,0,12,24,133440,0x7fb29e931f00,0x7fb29e025880,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097330.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328423755216,17328423157499,17328424416861,17328424418978
|
||
|
|
102,"void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]",0,0,305,205593,205593,4194304,256,0,0,12,24,134912,0x7fb29e931d80,0x7fb29e0258c0,0,0,0,0,0,0,8912896,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097364.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328425022902,17328424416861,17328425627743,17328425629776
|
||
|
|
103,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,308,205593,205593,4194304,256,0,0,12,24,136896,0x7fb29e931c00,0x7fb29e025900,0,0,0,0,0,0,11796480,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194617.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328426226231,17328425627743,17328426906304,17328426908592
|
||
|
|
104,"void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]",0,0,311,205593,205593,4194304,256,0,0,12,24,138880,0x7fb29e931a80,0x7fb29e025940,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194599.0000000000,0.0000000000,0.0000000000,0,0,11796480,0,0,0,0,0,0.0000000000,0,0,17328427503607,17328426906304,17328428182786,17328428184979
|
||
|
|
105,"void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]",0,0,314,205593,205593,4194304,256,0,0,12,24,140864,0x7fb29e931900,0x7fb29e025980,0,0,11796480,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097336.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328428778873,17328428182786,17328429357348,17328429359467
|
||
|
|
106,"void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]",0,0,317,205593,205593,4194304,256,0,0,12,24,143616,0x7fb29e931780,0x7fb29e0259c0,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097338.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328429954712,17328429357348,17328430630790,17328430632984
|
||
|
|
107,"void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]",0,0,320,205593,205593,4194304,256,0,0,12,24,145344,0x7fb29e931600,0x7fb29e025a00,0,0,0,0,0,0,9699328,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097368.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328431236228,17328430630790,17328431833351,17328431835782
|
||
|
|
108,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,323,205593,205593,4194304,256,0,0,12,24,147584,0x7fb2a0fd2480,0x7fb29e025a40,0,0,0,0,0,0,12845056,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194612.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328432430186,17328431833351,17328433094633,17328433097018
|
||
|
|
109,"void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]",0,0,326,205593,205593,4194304,256,0,0,12,24,149568,0x7fb2a0fd2300,0x7fb29e025a80,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194597.0000000000,0.0000000000,0.0000000000,0,0,12845056,0,0,0,0,0,0.0000000000,0,0,17328433691033,17328433094633,17328434434475,17328434436353
|
||
|
|
110,"void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]",0,0,329,205593,205593,4194304,256,0,0,12,24,151552,0x7fb2a0fd2180,0x7fb29e025ac0,0,0,12845056,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097342.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328435031797,17328434434475,17328435634636,17328435636771
|
||
|
|
111,"void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]",0,0,332,205593,205593,4194304,256,0,0,12,24,154304,0x7fb2a0fd2000,0x7fb29e025b00,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097339.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328436231935,17328435634636,17328436926638,17328436928967
|
||
|
|
112,"void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]",0,0,335,205593,205593,4194304,256,0,0,12,24,156288,0x7fb29e931e80,0x7fb29e025b40,0,0,0,0,0,0,11272192,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097358.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328437531081,17328436926638,17328438117520,17328438120155
|
||
|
|
113,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,338,205593,205593,4194304,256,0,0,12,24,158784,0x7fb29e931d00,0x7fb29e025b80,0,0,0,0,0,0,14942208,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194643.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328438715479,17328438117520,17328439380882,17328439386002
|
||
|
|
114,"void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]",0,0,341,205593,205593,4194304,256,0,0,12,24,161024,0x7fb29e931b80,0x7fb29e025bc0,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194652.0000000000,0.0000000000,0.0000000000,0,0,14942208,0,0,0,0,0,0.0000000000,0,0,17328439978126,17328439380882,17328440658963,17328440661078
|
||
|
|
115,"void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]",0,0,344,205593,205593,4194304,256,0,0,12,24,163264,0x7fb29e931a00,0x7fb29e025c00,0,0,14942208,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097337.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328441255142,17328440658963,17328441877045,17328441879456
|
||
|
|
116,"void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]",0,0,347,205593,205593,4194304,256,0,0,12,24,166528,0x7fb29e931880,0x7fb29e025c40,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097331.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328442475370,17328441877045,17328443207127,17328443250549
|
||
|
|
117,"void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]",0,0,350,205593,205593,4194304,256,0,0,12,24,168512,0x7fb29e931700,0x7fb29e025c80,0,0,0,0,0,0,12845056,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097350.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328443811764,17328443207127,17328444401848,17328444403919
|
||
|
|
118,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,353,205593,205593,4194304,256,0,0,12,24,171264,0x7fb2a0fd2580,0x7fb29e025cc0,0,0,0,0,0,0,17039360,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194637.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328444998743,17328444401848,17328445679930,17328445684225
|
||
|
|
119,"void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]",0,0,356,205593,205593,4194304,256,0,0,12,24,173760,0x7fb2a0fd2400,0x7fb29e025d00,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194643.0000000000,0.0000000000,0.0000000000,0,0,17039360,0,0,0,0,0,0.0000000000,0,0,17328446279269,17328445679930,17328446954492,17328446958471
|
||
|
|
120,"void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]",0,0,359,205593,205593,4194304,256,0,0,12,24,176256,0x7fb2a0fd2280,0x7fb29e025d40,0,0,17039360,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097327.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328447551825,17328446954492,17328448185374,17328448187388
|
||
|
|
121,"void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]",0,0,362,205593,205593,4194304,256,0,0,12,24,179776,0x7fb2a0fd2100,0x7fb29e025d80,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097346.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328448782523,17328448185374,17328449493855,17328449560602
|
||
|
|
122,"void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]",0,0,365,205593,205593,4194304,256,0,0,12,24,182272,0x7fb29e931f80,0x7fb29e025dc0,0,0,0,0,0,0,15990784,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097336.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328450109787,17328449493855,17328450735297,17328450737611
|
||
|
|
123,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,368,205593,205593,4194304,256,0,0,12,24,185536,0x7fb29e931e00,0x7fb29e025e00,0,0,0,0,0,0,21233664,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194635.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328451332205,17328450735297,17328452006339,17328452048356
|
||
|
|
124,"void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]",0,0,371,205593,205593,4194304,256,0,0,12,24,188544,0x7fb29e931c80,0x7fb29e025e40,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194637.0000000000,0.0000000000,0.0000000000,0,0,21233664,0,0,0,0,0,0.0000000000,0,0,17328452602981,17328452006339,17328453302181,17328453370251
|
||
|
|
125,"void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]",0,0,374,205593,205593,4194304,256,0,0,12,24,191552,0x7fb29e931b00,0x7fb29e025e80,0,0,21233664,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097332.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328453898917,17328453302181,17328454555142,17328454557239
|
||
|
|
126,"void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]",0,0,377,205593,205593,4194304,256,0,0,12,24,195840,0x7fb29e931980,0x7fb29e025ec0,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097353.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328455152644,17328454555142,17328455944424,17328456010731
|
||
|
|
127,"void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]",0,0,380,205593,205593,4194304,256,0,0,12,24,198592,0x7fb29e931800,0x7fb29e025f00,0,0,0,0,0,0,19136512,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097336.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328456550487,17328455944424,17328457170986,17328457173180
|
||
|
|
128,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,383,205593,205593,4194304,256,0,0,12,24,202368,0x7fb29e931680,0x7fb29e025f40,0,0,0,0,0,0,25427968,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194638.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328457767754,17328457170986,17328458481068,17328458548384
|
||
|
|
129,"void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]",0,0,386,205593,205593,4194304,256,0,0,12,24,205888,0x7fb2a0fd2500,0x7fb29e025f80,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194636.0000000000,0.0000000000,0.0000000000,0,0,25427968,0,0,0,0,0,0.0000000000,0,0,17328459078510,17328458481068,17328459749549,17328459814180
|
||
|
|
130,"void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]",0,0,389,205593,205593,4194304,256,0,0,12,24,209408,0x7fb2a0fd2380,0x7fb29e025fc0,0,0,25427968,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097343.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328460346626,17328459749549,17328461024591,17328461026508
|
||
|
|
131,"void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]",0,0,392,205593,205593,4194304,256,0,0,12,24,214464,0x7fb2a0fd2200,0x7fb29e026000,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097371.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328461622282,17328461024591,17328462449873,17328462517168
|
||
|
|
132,"void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]",0,0,395,205593,205593,4194304,256,0,0,12,24,217728,0x7fb2a0fd2080,0x7fb29e026040,0,0,0,0,0,0,22282240,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097349.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328463056544,17328462449873,17328463721235,17328463723606
|
||
|
|
133,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,398,205593,205593,4194304,256,0,0,12,24,222016,0x7fb29e931f00,0x7fb29e026080,0,0,0,0,0,0,29622272,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194610.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328464319121,17328463721235,17328465048597,17328465114000
|
||
|
|
134,"void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]",0,0,401,205593,205593,4194304,256,0,0,12,24,226048,0x7fb29e931d80,0x7fb29e0260c0,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194596.0000000000,0.0000000000,0.0000000000,0,0,29622272,0,0,0,0,0,0.0000000000,0,0,17328465645785,17328465048597,17328466386839,17328466453554
|
||
|
|
135,"void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]",0,0,404,205593,205593,4194304,256,0,0,12,24,230080,0x7fb29e931c00,0x7fb29e026100,0,0,29622272,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097345.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328466983960,17328466386839,17328467707320,17328467773609
|
||
|
|
136,"void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]",0,0,407,205593,205593,4194304,256,0,0,12,24,235904,0x7fb29e931a80,0x7fb29e026140,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097379.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328468303815,17328467707320,17328469174042,17328469240940
|
||
|
|
137,"void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]",0,0,410,205593,205593,4194304,256,0,0,12,24,239424,0x7fb29e931900,0x7fb29e026180,0,0,0,0,0,0,25427968,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097345.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328469780146,17328469174042,17328470476924,17328470478927
|
||
|
|
138,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,413,205593,205593,4194304,256,0,0,12,24,244224,0x7fb29e931780,0x7fb29e0261c0,0,0,0,0,0,0,33816576,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194606.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328471075002,17328470476924,17328471803646,17328471846771
|
||
|
|
139,"void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]",0,0,416,205593,205593,4194304,256,0,0,12,24,248768,0x7fb29e931600,0x7fb29e026200,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194591.0000000000,0.0000000000,0.0000000000,0,0,33816576,0,0,0,0,0,0.0000000000,0,0,17328472400956,17328471803646,17328473141568,17328473208355
|
||
|
|
140,"void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]",0,0,419,205593,205593,4194304,256,0,0,12,24,253312,0x7fb2a0fd2480,0x7fb29e026240,0,0,33816576,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097355.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328473739201,17328473141568,17328474489890,17328474557149
|
||
|
|
141,"void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]",0,0,422,205593,205593,4194304,256,0,0,8,24,255552,0x7fb2a0fd2300,0x7fb29e026280,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097321.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328475088385,17328474489890,17328476041892,17328476085009
|
||
|
|
142,"void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]",0,0,425,205593,205593,4194304,256,0,0,12,24,259840,0x7fb2a0fd2180,0x7fb29e0262c0,0,0,0,0,0,0,31719424,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097357.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328476648034,17328476041892,17328477375334,17328477418334
|
||
|
|
143,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,428,205593,205593,4194304,256,0,0,12,24,265664,0x7fb2a0fd2000,0x7fb29e026300,0,0,0,0,0,0,42205184,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194617.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328477973549,17328477375334,17328478791975,17328478859266
|
||
|
|
144,"void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]",0,0,431,205593,205593,4194304,256,0,0,12,24,271232,0x7fb29e931e80,0x7fb29e026340,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194609.0000000000,0.0000000000,0.0000000000,0,0,42205184,0,0,0,0,0,0.0000000000,0,0,17328479389252,17328478791975,17328480187817,17328480251749
|
||
|
|
145,"void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]",0,0,434,205593,205593,4194304,256,0,0,8,24,273216,0x7fb29e931d00,0x7fb29e026380,0,0,42205184,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097323.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328480784175,17328480187817,17328481570859,17328481634802
|
||
|
|
146,"void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]",0,0,437,205593,205593,4194304,256,0,0,8,24,275712,0x7fb29e931b80,0x7fb29e0263c0,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097325.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328482169018,17328481574047,17328483228458,17328483299068
|
||
|
|
147,"void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]",0,0,440,205593,205593,4194304,256,0,0,12,24,280768,0x7fb29e931a00,0x7fb29e026400,0,0,0,0,0,0,38010880,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097380.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328483831334,17328483228458,17328484611666,17328484674702
|
||
|
|
148,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,443,205593,205593,4194304,256,0,0,12,24,287616,0x7fb29e931880,0x7fb29e026440,0,0,0,0,0,0,50593792,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194620.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328485206188,17328484611666,17328486046395,17328486114293
|
||
|
|
149,"void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]",0,0,446,205593,205593,4194304,256,0,0,12,24,294208,0x7fb29e931700,0x7fb29e026480,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194621.0000000000,0.0000000000,0.0000000000,0,0,50593792,0,0,0,0,0,0.0000000000,0,0,17328486641599,17328486046395,17328487492484,17328487555775
|
||
|
|
150,"void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]",0,0,449,205593,205593,4194304,256,0,0,8,24,296960,0x7fb2a0fd2580,0x7fb29e0264c0,0,0,50593792,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097332.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328488088581,17328487492484,17328488923053,17328488986797
|
||
|
|
151,"void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]",0,0,452,205593,205593,4194304,256,0,0,8,24,299968,0x7fb2a0fd2400,0x7fb29e026500,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097329.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328489517243,17328488923053,17328490673945,17328490738761
|
||
|
|
152,"void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]",0,0,455,205593,205593,4194304,256,0,0,8,24,302720,0x7fb2a0fd2280,0x7fb29e026540,0,0,0,0,0,0,67371008,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097330.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328491277157,17328490673945,17328492221154,17328492282640
|
||
|
|
153,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,458,205593,205593,4194304,256,0,0,12,24,305472,0x7fb2a0fd2100,0x7fb29e026580,0,0,0,0,0,0,67371008,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194558.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328492816086,17328492221154,17328493769484,17328493830689
|
||
|
|
154,"void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]",0,0,461,205593,205593,4194304,256,0,0,12,24,308224,0x7fb29e931f80,0x7fb29e0265c0,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194558.0000000000,0.0000000000,0.0000000000,0,0,67371008,0,0,0,0,0,0.0000000000,0,0,17328494364845,17328493769484,17328495320374,17328495365958
|
||
|
|
155,"void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]",0,0,464,205593,205593,4194304,256,0,0,8,24,310976,0x7fb29e931e00,0x7fb29e026600,0,0,67371008,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097333.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328495913614,17328495320374,17328496871584,17328496935727
|
||
|
|
156,"void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]",0,0,467,205593,205593,4194304,256,0,0,8,24,313216,0x7fb29e931c80,0x7fb29e026640,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097320.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328497465512,17328496871584,17328498819437,17328498885165
|
||
|
|
157,"void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]",0,0,470,205593,205593,4194304,256,0,0,8,24,315968,0x7fb29e931b00,0x7fb29e026680,0,0,0,0,0,0,134479872,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097324.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328499422031,17328498819437,17328500779769,17328500843483
|
||
|
|
158,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,473,205593,205593,4194304,256,0,0,12,24,318720,0x7fb29e931980,0x7fb29e0266c0,0,0,0,0,0,0,134479872,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194550.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328501374089,17328500779769,17328502736422,17328502778732
|
||
|
|
159,"void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]",0,0,476,205593,205593,4194304,256,0,0,12,24,321472,0x7fb29e931800,0x7fb29e026700,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194550.0000000000,0.0000000000,0.0000000000,0,0,134479872,0,0,0,0,0,0.0000000000,0,0,17328503331137,17328502736422,17328504722514,17328504766629
|
||
|
|
160,"void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]",0,0,479,205593,205593,4194304,256,0,0,8,24,324224,0x7fb29e931680,0x7fb29e026740,0,0,134479872,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097329.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328505316004,17328504722514,17328506670367,17328506734347
|
||
|
|
161,"void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]",0,0,482,205593,205593,4194304,256,0,0,8,24,326464,0x7fb2a0fd2500,0x7fb29e026780,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097316.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328507264263,17328506670367,17328509462224,17328509526013
|
||
|
|
162,"void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]",0,0,485,205593,205593,4194304,256,0,0,8,24,329216,0x7fb2a0fd2380,0x7fb29e0267c0,0,0,0,0,0,0,268697600,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097326.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328510070608,17328509462224,17328512253442,17328512316499
|
||
|
|
163,"void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]",0,0,488,205593,205593,4194304,256,0,0,12,24,331968,0x7fb2a0fd2200,0x7fb29e026800,0,0,0,0,0,0,268697600,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194546.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328512848535,17328512253442,17328515070900,17328515138674
|
||
|
|
164,"void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]",0,0,491,205593,205593,4194304,256,0,0,12,24,334720,0x7fb2a0fd2080,0x7fb29e026840,0,0,0,0,0,0,0,0,4194304.0000000000,8388608.0000000000,0.0000000000,0.0000000000,0.0000000000,4194552.0000000000,0.0000000000,0.0000000000,0,0,268697600,0,0,0,0,0,0.0000000000,0,0,17328515665370,17328515070900,17328517901958,17328517965979
|
||
|
|
165,"void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]",0,0,494,205593,205593,4194304,256,0,0,8,24,337472,0x7fb29e931f00,0x7fb29e026880,0,0,268697600,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097328.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328518497405,17328517901958,17328520673656,17328520735206
|
||
|
|
166,"void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]",0,0,497,205593,205593,4194304,256,0,0,8,24,0,0x7fb29e931d80,0x7fb29e0268c0,0,0,0,0,0,0,0,0,2097152.0000000000,2097152.0000000000,0.0000000000,0.0000000000,0.0000000000,2097316.0000000000,0.0000000000,0.0000000000,0,0,0,0,0,0,0,0,0.0000000000,0,0,17328521267281,17328520673656,17328525132564,17328525201247
|