English

PPT-SASMM: Scalable Analytical Shared Memory Model: Predicting the Performance of Multicore Caches from a Single-Threaded Execution Trace

Distributed, Parallel, and Cluster Computing 2021-03-26 v1 Performance

Abstract

Performance modeling of parallel applications on multicore processors remains a challenge in computational co-design due to multicore processors' complex design. Multicores include complex private and shared memory hierarchies. We present a Scalable Analytical Shared Memory Model (SASMM). SASMM can predict the performance of parallel applications running on a multicore. SASMM uses a probabilistic and computationally-efficient method to predict the reuse distance profiles of caches in multicores. SASMM relies on a stochastic, static basic block-level analysis of reuse profiles. The profiles are calculated from the memory traces of applications that run sequentially rather than using multi-threaded traces. The experiments show that our model can predict private L1 cache hit rates with 2.12% and shared L2 cache hit rates with about 1.50% error rate.

Keywords

Cite

@article{arxiv.2103.10635,
  title  = {PPT-SASMM: Scalable Analytical Shared Memory Model: Predicting the Performance of Multicore Caches from a Single-Threaded Execution Trace},
  author = {Atanu Barai and Gopinath Chennupati and Nandakishore Santhi and Abdel-Hameed Badawy and Yehia Arafa and Stephan Eidenbenz},
  journal= {arXiv preprint arXiv:2103.10635},
  year   = {2021}
}

Comments

11 pages, 5 figures. arXiv admin note: text overlap with arXiv:1907.12666

R2 v1 2026-06-24T00:20:34.938Z