Sunday July 25, 2010
At least this problem description didn't mention 'gouda' in the title; that would have been cheesy. To prepare for this problem, familiarize yourself with the basics of CUDA programming.
How do CPUbound 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 matrixmatrix multiply performance running on the CPU with matrixmatrix multiply performance running on the GPU. Perform the identical matrixmatrix 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.
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.
Show solution
Challenge Resources:
©19942014

Shodor

Privacy Policy

NSDL

XSEDE

Blue Waters

ACM SIGHPC





Not Logged In. Login