English

Per-Row Activation Counting on Real Hardware: Demystifying Performance Overheads

Hardware Architecture 2025-11-04 v2 Cryptography and Security

Abstract

Per-Row Activation Counting (PRAC), a DRAM read disturbance mitigation method, modifies key DRAM timing parameters, reportedly causing significant performance overheads in simulator-based studies. However, given known discrepancies between simulators and real hardware, real-machine experiments are vital for accurate PRAC performance estimation. We present the first real-machine performance analysis of PRAC. After verifying timing modifications on the latest CPUs using microbenchmarks, our analysis shows that PRAC's average and maximum overheads are just 1.06% and 3.28% for the SPEC CPU2017 workloads -- up to 9.15x lower than simulator-based reports. Further, we show that the close page policy minimizes this overhead by effectively hiding the elongated DRAM row precharge operations due to PRAC from the critical path.

Keywords

Cite

@article{arxiv.2507.05556,
  title  = {Per-Row Activation Counting on Real Hardware: Demystifying Performance Overheads},
  author = {Jumin Kim and Seungmin Baek and Minbok Wi and Hwayong Nam and Michael Jaemin Kim and Sukhan Lee and Kyomin Sohn and Jung Ho Ahn},
  journal= {arXiv preprint arXiv:2507.05556},
  year   = {2025}
}

Comments

5 pages, 4 figures, modified on top of the IEEE Computer Architecture Letters

R2 v1 2026-07-01T03:50:34.532Z