How do CPU-bound applications compare with GPGPU applications in terms of performance? How can you tell where the bottlenecks are? In this problem you are to examine the matrix-matrix multiply performance running on the CPU with matrix-matrix multiply performance running on the GPU. Perform the identical matrix-matrix multiply task on the system's GPGPU as on the CPU, and compare the results.

Resources:

- CUDA SDK and Toolkit (can be found on nVidia's site here)
- nvcc compiler for CUDA (included in the CUDA toolkit)
- gcc and Intel compilers, or a proper installation with the cl compiler
- CUDA Walkthrough: Dr. Dobb's Journal

Logistics:

- Many articles and howto's exist on matrix multiplication in CUDA. You are free to base your solution on any howto or article that you find. However, the source code provided in the CUDA SDK is a convenient place to start.