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

> Device 0: "Tesla P100-SXM2-16GB"
> SM Capability 6.0 detected:
> [Tesla P100-SXM2-16GB] has 56 MP(s) x -1 (Cores/MP) = -56 (Cores)
> Compute performance scaling factor = 1.00

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


transpose-Outer-simple copy       , Throughput = 75.2591 GB/s, Time = 0.02595 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-simple copy       , Throughput = 79.2664 GB/s, Time = 0.02464 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-shared memory copy, Throughput = 47.9459 GB/s, Time = 0.04074 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-shared memory copy, Throughput = 79.2664 GB/s, Time = 0.02464 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-naive             , Throughput = 45.6167 GB/s, Time = 0.04282 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-naive             , Throughput = 54.0613 GB/s, Time = 0.03613 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-coalesced         , Throughput = 42.4740 GB/s, Time = 0.04598 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-coalesced         , Throughput = 67.5915 GB/s, Time = 0.02890 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-optimized         , Throughput = 50.4006 GB/s, Time = 0.03875 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-optimized         , Throughput = 65.1389 GB/s, Time = 0.02998 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-coarse-grained    , Throughput = 48.8672 GB/s, Time = 0.03997 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-coarse-grained    , Throughput = 71.1365 GB/s, Time = 0.02746 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-fine-grained      , Throughput = 46.2388 GB/s, Time = 0.04224 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-fine-grained      , Throughput = 82.0365 GB/s, Time = 0.02381 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-diagonal          , Throughput = 45.3119 GB/s, Time = 0.04310 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-diagonal          , Throughput = 68.4251 GB/s, Time = 0.02854 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
