/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 = 64.9310 GB/s, Time = 0.03008 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-simple copy       , Throughput = 61.2188 GB/s, Time = 0.03190 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-shared memory copy, Throughput = 73.4478 GB/s, Time = 0.02659 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-shared memory copy, Throughput = 63.9112 GB/s, Time = 0.03056 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-naive             , Throughput = 73.7140 GB/s, Time = 0.02650 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-naive             , Throughput = 45.3119 GB/s, Time = 0.04310 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-coalesced         , Throughput = 65.2782 GB/s, Time = 0.02992 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-coalesced         , Throughput = 63.1180 GB/s, Time = 0.03094 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-optimized         , Throughput = 72.6609 GB/s, Time = 0.02688 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-optimized         , Throughput = 63.5783 GB/s, Time = 0.03072 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-coarse-grained    , Throughput = 78.6536 GB/s, Time = 0.02483 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-coarse-grained    , Throughput = 64.8620 GB/s, Time = 0.03011 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 = 67.2934 GB/s, Time = 0.02902 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-diagonal          , Throughput = 77.7518 GB/s, Time = 0.02512 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-diagonal          , Throughput = 62.6002 GB/s, Time = 0.03120 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
