GPU Kernel Main

Version's name: GPU Kernel Main ; a version of the GPU-Kernel program.
Repository: [home] and version downloads: [.zip] [.tar.gz] [.tar.bz2] [.tar]
Patterns and behaviours:

GPU uncoalesced memory transfer

Recommended best-practices:

GPU align memory accesses

- Available version(s):

GPU Kernel Optimized

This kernel is to showcase the importance of memory coalescing with a simple matrix multiplication. In this case two 1024x1024 matrices of random integers get multiplied. The matrix multiplication is implemented the naive way, i.e. the threads get distributed in a two-dimensional grid and iterate over the row and down the column. No optimization techniques like blocking or tiling were used.

The following experiments have been registered:

GPU-kernel analysis of initial version