/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 = 128
> MatrixSize Y = 128

Matrix size: 128x128 (8x8 tiles), tile size: 16x16, block size: 16x16


transpose-Outer-simple copy       , Throughput = 4.2151 GB/s, Time = 0.02896 s, Size = 16384 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-simple copy       , Throughput = 4.3153 GB/s, Time = 0.02829 s, Size = 16384 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-shared memory copy, Throughput = 4.9032 GB/s, Time = 0.02490 s, Size = 16384 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-shared memory copy, Throughput = 4.6351 GB/s, Time = 0.02634 s, Size = 16384 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-naive             , Throughput = 5.1760 GB/s, Time = 0.02358 s, Size = 16384 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-naive             , Throughput = 4.6578 GB/s, Time = 0.02621 s, Size = 16384 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-coalesced         , Throughput = 5.1760 GB/s, Time = 0.02358 s, Size = 16384 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-coalesced         , Throughput = 4.6071 GB/s, Time = 0.02650 s, Size = 16384 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-optimized         , Throughput = 5.1690 GB/s, Time = 0.02362 s, Size = 16384 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-optimized         , Throughput = 4.6634 GB/s, Time = 0.02618 s, Size = 16384 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-coarse-grained    , Throughput = 5.1620 GB/s, Time = 0.02365 s, Size = 16384 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-coarse-grained    , Throughput = 4.7565 GB/s, Time = 0.02566 s, Size = 16384 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-fine-grained      , Throughput = 5.1550 GB/s, Time = 0.02368 s, Size = 16384 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-fine-grained      , Throughput = 4.5359 GB/s, Time = 0.02691 s, Size = 16384 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-diagonal          , Throughput = 5.3278 GB/s, Time = 0.02291 s, Size = 16384 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-diagonal          , Throughput = 4.6464 GB/s, Time = 0.02627 s, Size = 16384 fp32 elements, NumDevsUsed = 1, Workgroup = 256
