Reducing branch divergence in GPU programs

  title={Reducing branch divergence in GPU programs},
  author={Tianyi David Han and Tarek S. Abdelrahman},
Branch divergence has a significant impact on the performance of GPU programs. We propose two novel software-based optimizations, called iteration delaying and branch distribution that aim to reduce branch divergence. Iteration delaying targets a divergent branch enclosed by a loop within a kernel. It improves performance by executing loop iterations that take the same branch direction and delaying those that take the other direction until later iterations. Branch distribution reduces the… CONTINUE READING
Highly Influential
This paper has highly influenced 10 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 165 citations. REVIEW CITATIONS
95 Citations
1 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 95 extracted citations

166 Citations

Citations per Year
Semantic Scholar estimates that this publication has 166 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.

Similar Papers

Loading similar papers…