/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 = 0.0017 GB/s, Time = 1132.93860 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-simple copy       , Throughput = 0.0019 GB/s, Time = 1022.78534 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-shared memory copy, Throughput = 0.0017 GB/s, Time = 1120.47705 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-shared memory copy, Throughput = 0.0019 GB/s, Time = 1051.55371 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-naive             , Throughput = 0.0020 GB/s, Time = 1001.20630 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-naive             , Throughput = 0.0020 GB/s, Time = 992.28070 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-coalesced         , Throughput = 0.0020 GB/s, Time = 995.73901 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-coalesced         , Throughput = 0.0019 GB/s, Time = 1035.40759 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-optimized         , Throughput = 0.0019 GB/s, Time = 1033.41272 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-optimized         , Throughput = 0.0020 GB/s, Time = 978.96759 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-coarse-grained    , Throughput = 0.0019 GB/s, Time = 1010.90973 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-coarse-grained    , Throughput = 0.0019 GB/s, Time = 1016.17200 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-fine-grained      , Throughput = 0.0020 GB/s, Time = 995.70587 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-fine-grained      , Throughput = 0.0020 GB/s, Time = 983.66846 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-diagonal          , Throughput = 0.0018 GB/s, Time = 1056.49573 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-diagonal          , Throughput = 0.0018 GB/s, Time = 1085.04309 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
