Improved-MOESI Cache Coherence Protocol

Altwaijry, Hesham; Alzahrani, Diyab S.

doi:10.1007/s13369-013-0787-7

Cited by 4 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Prior work [3,81] shows that MOESI-based protocols can implement different ownership policies without loss of correctness when sharing dirty lines. The ownership policy designates whether the requesting cache or responding cache ends a transaction as the line owner.…”

Section: Optimization: Greedy Local Ownershipmentioning

confidence: 99%

“…We thus reason about MOESI-prime in the context of a MOESI baseline. We also assume that the MOESI baseline correctly implements greedy local ownership ( §4.3), noting that prior work [3,68,81] demonstrates the validity of denoting either the requestor or responder as the owner.…”

Section: Protocol Correctnessmentioning

confidence: 99%

“…State-of-the-art ccNUMA protocols are inspired by the DASH architecture's directory protocol [67]. AMD [68] and Improved-MOESI [3] propose an "always migrate" ownership policy similar to MOESI-prime's "greedy local" policy, except MOESI-prime does not migrate ownership from the local node when possible. Other work proposes mechanisms (e.g., coherence states) to optimize producer-consumer [19] and migratory [24,110] sharing.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

MOESI-prime

Loughlin

Saroiu

Wolman

et al. 2022

Proceedings of the 49th Annual International Symposium on Computer Architecture

View full text Add to dashboard Cite

Prior work shows that Rowhammer attacks-which flip bits in DRAM via frequent activations of the same row(s)-are viable. Adversaries typically mount these attacks via instruction sequences that are carefully-crafted to bypass CPU caches. However, we discover a novel form of hammering that we refer to as coherenceinduced hammering, caused by Intel's implementations of cache coherent non-uniform memory access (ccNUMA) protocols. We show that this hammering occurs in commodity benchmarks on a major cloud provider's production hardware, the first hammering found to be generated by non-malicious code. Given DRAM's rising susceptibility to bit flips, it is paramount to prevent coherenceinduced hammering to ensure reliability and security in the cloud.Accordingly, we introduce MOESI-prime, a ccNUMA coherence protocol that mitigates coherence-induced hammering while retaining Intel's state-of-the-art scalability. MOESI-prime shows that most DRAM reads and writes triggering such hammering are unnecessary. Thus, by encoding additional information in the coherence protocol, MOESI-prime can omit these reads and writes, preventing coherence-induced hammering in non-malicious and malicious workloads. Furthermore, by omitting unnecessary reads and writes, MOESI-prime has negligible effect on average performance (within ±0.61% of MESI and MOESI) and average DRAM power (0.03%-0.22% improvement) across evaluated ccNUMA configurations. CCS CONCEPTS• Security and privacy → Security in hardware; Systems security; • Hardware → Hardware reliability.

show abstract

Section: Optimization: Greedy Local Ownershipmentioning

confidence: 99%

Section: Protocol Correctnessmentioning

confidence: 99%