/home/tgrogers/github-purdue/aalp/gpgpu-sim_simulations/util/correlation/../../benchmarks/bin/9.1/release/transpose Starting...

> Device 0: "TITAN X (Pascal)"
> SM Capability 6.1 detected:
> [TITAN X (Pascal)] has 28 MP(s) x -1 (Cores/MP) = -28 (Cores)
> Compute performance scaling factor = 1.00

Matrix size: 512x512 (32x32 tiles), tile size: 16x16, block size: 16x16


transpose-Outer-simple copy       , Throughput = 65.3481 GB/s, Time = 0.02989 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-simple copy       , Throughput = 59.8384 GB/s, Time = 0.03264 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-shared memory copy, Throughput = 70.8064 GB/s, Time = 0.02758 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-shared memory copy, Throughput = 63.3145 GB/s, Time = 0.03085 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-naive             , Throughput = 50.9050 GB/s, Time = 0.03837 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-naive             , Throughput = 43.4105 GB/s, Time = 0.04499 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-coalesced         , Throughput = 73.8924 GB/s, Time = 0.02643 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-coalesced         , Throughput = 59.6046 GB/s, Time = 0.03277 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-optimized         , Throughput = 75.0740 GB/s, Time = 0.02602 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-optimized         , Throughput = 64.7244 GB/s, Time = 0.03018 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-coarse-grained    , Throughput = 72.4023 GB/s, Time = 0.02698 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-coarse-grained    , Throughput = 66.1269 GB/s, Time = 0.02954 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-fine-grained      , Throughput = 74.7064 GB/s, Time = 0.02614 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-fine-grained      , Throughput = 64.9310 GB/s, Time = 0.03008 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-diagonal          , Throughput = 73.2715 GB/s, Time = 0.02666 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-diagonal          , Throughput = 62.0276 GB/s, Time = 0.03149 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
