/home/tgrogers/github/purdue-aalp/gpgpu-sim_simulations/util/correlation/../../benchmarks/bin/10.1/release/transpose Starting...

> Device 0: "GeForce RTX 2060"
> SM Capability 7.5 detected:
> [GeForce RTX 2060] has 30 MP(s) x -1 (Cores/MP) = -30 (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 = 0.0578 GB/s, Time = 33.80967 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-simple copy       , Throughput = 0.0611 GB/s, Time = 31.98624 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-shared memory copy, Throughput = 0.0461 GB/s, Time = 42.37111 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-shared memory copy, Throughput = 0.0460 GB/s, Time = 42.50061 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-naive             , Throughput = 0.0453 GB/s, Time = 43.09629 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-naive             , Throughput = 0.0470 GB/s, Time = 41.53318 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-coalesced         , Throughput = 0.0515 GB/s, Time = 37.95638 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-coalesced         , Throughput = 0.0485 GB/s, Time = 40.23325 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-optimized         , Throughput = 0.0532 GB/s, Time = 36.72829 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-optimized         , Throughput = 0.0546 GB/s, Time = 35.74566 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-coarse-grained    , Throughput = 0.0578 GB/s, Time = 33.81453 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-coarse-grained    , Throughput = 0.0571 GB/s, Time = 34.22019 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-fine-grained      , Throughput = 0.0557 GB/s, Time = 35.04054 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-fine-grained      , Throughput = 0.0489 GB/s, Time = 39.92282 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256

transpose-Outer-diagonal          , Throughput = 0.0522 GB/s, Time = 37.43696 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
transpose-Inner-diagonal          , Throughput = 0.0538 GB/s, Time = 36.27136 s, Size = 262144 fp32 elements, NumDevsUsed = 1, Workgroup = 256
