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

> Device 0: "Quadro GV100"
> SM Capability 7.0 detected:
> [Quadro GV100] 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 = 67.5915 GB/s, Time = 0.02890 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-simple copy       , Throughput = 57.9081 GB/s, Time = 0.03373 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-shared memory copy, Throughput = 72.6609 GB/s, Time = 0.02688 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-shared memory copy, Throughput = 64.7932 GB/s, Time = 0.03014 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-naive             , Throughput = 78.8568 GB/s, Time = 0.02477 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-naive             , Throughput = 55.3858 GB/s, Time = 0.03526 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-coalesced         , Throughput = 78.9588 GB/s, Time = 0.02474 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-coalesced         , Throughput = 65.4884 GB/s, Time = 0.02982 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-optimized         , Throughput = 77.2597 GB/s, Time = 0.02528 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-optimized         , Throughput = 66.6323 GB/s, Time = 0.02931 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-coarse-grained    , Throughput = 77.9504 GB/s, Time = 0.02506 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-coarse-grained    , Throughput = 64.1800 GB/s, Time = 0.03043 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-fine-grained      , Throughput = 72.4883 GB/s, Time = 0.02694 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-fine-grained      , Throughput = 65.1389 GB/s, Time = 0.02998 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-diagonal          , Throughput = 75.2591 GB/s, Time = 0.02595 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-diagonal          , Throughput = 66.3426 GB/s, Time = 0.02944 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
