A Multi-Stage CUDA Kernel for Floyd-Warshall

Details A Multi-Stage CUDA Kernel for Floyd-Warshall A Multi-Stage CUDA Kernel for Floyd-Warshall

2010-01-23

arxiv.org/abs/1001.4108v2

Computer Science

Distributed, Parallel, and Cluster Computing

9 pages, 7 figures, 1 table

Scientific paper

We present a new implementation of the Floyd-Warshall All-Pairs Shortest
Paths algorithm on CUDA. Our algorithm runs approximately 5 times faster than
the previously best reported algorithm. In order to achieve this speedup, we
applied a new technique to reduce usage of on-chip shared memory and allow the
CUDA scheduler to more effectively hide instruction latency.

Affiliated with

Also associated with

No associations

Rating

A Multi-Stage CUDA Kernel for Floyd-Warshall does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with A Multi-Stage CUDA Kernel for Floyd-Warshall, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A Multi-Stage CUDA Kernel for Floyd-Warshall will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-514598