POSTER: Performance modeling for GPUs using abstract kernel emulation

  • Hong, C.; 
  • Sukumaran-Rajam, A.; 
  • Kim, J.; 
  • Rawat, P.S.; 
  • Krishnamoorthy, S.; 
  • 외 3명
Citations

SCOPUS

1

초록

Performance modeling of GPU kernels is a significant challenge. In this paper, we develop a novel approach to performance modeling for GPUs through abstract kernel emulation along with latency/gap modeling of resources. Experimental results on all benchmarks from the Rodinia suite demonstrate good accuracy in predicting execution time on multiple GPU platforms. © 2018 Copyright held by the owner/author(s).

제목
POSTER: Performance modeling for GPUs using abstract kernel emulation
저자
Hong, C.; Sukumaran-Rajam, A.; Kim, J.; Rawat, P.S.; Krishnamoorthy, S.; Pouchet, L.-N.; Rastello, F.; Sadayappan, P.
DOI
10.1145/3178487.3178524
발행일
2018-02
유형
Conference Paper
저널명
Proceedings of the ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPOPP
페이지
397 ~ 398