/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 = 66.4871 GB/s, Time = 0.02938 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-simple copy       , Throughput = 62.5360 GB/s, Time = 0.03123 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-shared memory copy, Throughput = 70.7244 GB/s, Time = 0.02762 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-shared memory copy, Throughput = 64.4511 GB/s, Time = 0.03030 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-naive             , Throughput = 77.2597 GB/s, Time = 0.02528 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-naive             , Throughput = 44.7472 GB/s, Time = 0.04365 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-coalesced         , Throughput = 65.5587 GB/s, Time = 0.02979 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-coalesced         , Throughput = 63.9112 GB/s, Time = 0.03056 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-optimized         , Throughput = 75.8201 GB/s, Time = 0.02576 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-optimized         , Throughput = 65.6998 GB/s, Time = 0.02973 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-coarse-grained    , Throughput = 75.9144 GB/s, Time = 0.02573 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 = 76.6773 GB/s, Time = 0.02547 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-fine-grained      , Throughput = 65.9840 GB/s, Time = 0.02960 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-diagonal          , Throughput = 78.5523 GB/s, Time = 0.02486 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-diagonal          , Throughput = 63.7776 GB/s, Time = 0.03062 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
