/home/tgrogers/github/purdue-aalp/gpgpu-sim_simulations/util/correlation/../../benchmarks/bin/10.1/release/transpose Starting...

> Device 0: "TITAN V"
> SM Capability 7.0 detected:
> [TITAN V] has 80 MP(s) x -1 (Cores/MP) = -80 (Cores)
> Compute performance scaling factor = 1.00
> MatrixSize X = 512
> MatrixSize Y = 512

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


transpose-Outer-simple copy       , Throughput = 0.0381 GB/s, Time = 51.25747 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-simple copy       , Throughput = 0.0427 GB/s, Time = 45.72944 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-shared memory copy, Throughput = 0.0410 GB/s, Time = 47.62448 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-shared memory copy, Throughput = 0.0431 GB/s, Time = 45.27174 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-naive             , Throughput = 0.0434 GB/s, Time = 45.02039 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-naive             , Throughput = 0.0430 GB/s, Time = 45.46992 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-coalesced         , Throughput = 0.0432 GB/s, Time = 45.21299 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-coalesced         , Throughput = 0.0411 GB/s, Time = 47.47456 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-optimized         , Throughput = 0.0425 GB/s, Time = 46.00752 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-optimized         , Throughput = 0.0425 GB/s, Time = 45.93120 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-coarse-grained    , Throughput = 0.0357 GB/s, Time = 54.77904 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-coarse-grained    , Throughput = 0.0421 GB/s, Time = 46.42522 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-fine-grained      , Throughput = 0.0429 GB/s, Time = 45.51043 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-fine-grained      , Throughput = 0.0431 GB/s, Time = 45.34992 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-diagonal          , Throughput = 0.0418 GB/s, Time = 46.75389 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-diagonal          , Throughput = 0.0351 GB/s, Time = 55.58339 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
