Zero Directory Eviction Victim: Unbounded Coherence Directory and Core Cache Isolation

Chaudhuri, Mainak

doi:10.1109/hpca51647.2021.00032

Cited by 7 publications

(6 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Increase memory access complexity Shukla, et al [18] ZEV [13] OS-supported cache coherence Fensch, et al [19] Retrofit the function of directory to OS SARC [22] coherence information by using VCs as the victim buffers for DEs.…”

Section: Reduce Directory Area Overheadmentioning

confidence: 99%

“…Second, several architectural supports from the memory hierarchy were investigated to mitigate DE eviction-induced invalidations, such as expanding the directory with LLC [13], [18] or DRAM [17]. These approaches are beneficial in reducing invalidations owing to DE eviction with a negligible area overhead; however, they complicate the memory access procedure, thus increasing the directory access latency.…”

Section: Reduce Directory Area Overheadmentioning

confidence: 99%

“…DE eviction necessarily invalidates the associated L1 cache lines. This type of invalidation degrades TCMP performance because it is unaware of memory locality [13], [24]. Configuring the associativity of the sparse directory to match the aggregated associativity of the L1 cache (core count × number of L1 cache associativity) can completely prevent DE eviction; however, it prolongs latency with significant area overhead.…”

Section: A Sparse Directorymentioning

confidence: 99%

“…Meanwhile, the number of ways in the sparse directory are opted to those of the LLC, to mimic an eligible shared memory structure. This sparse directory configuration has been empirically established to perform sufficiently close to an unbounded sparse directory [13]. To be clear, this sparse directory configuration was not chosen to provide an undue advantage to the proposed idea.…”

Section: Evaluation a Simulation Setupmentioning

confidence: 99%

“…As a result, DE eviction-induced invalidations increase the miss rate of private caches and consequently hamper the overall system performance of TCMP. The performance-criticality of DE eviction was investigated by Chaudhuri [13] through running multithreaded workloads with varying directory sizes. The results indicate that by reducing the number of DEs by 25%, the execution time for the multithreaded workloads can be prolonged by up to 10% due to the increased DE evictions, which causes coherence cache miss.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

NCDE: In-Network Caching for Directory Entries to Expedite Data Access in Tiled-Chip Multiprocessors

2023

View full text Add to dashboard Cite

The processing of data-intensive applications, followed by an unprecedented amount of data traffic, drives explosive accesses to the memory subsystem. The overloaded memory subsystem experiences increased data access latency. To expedite data access, a network caching technique that leverages networkon-chip (NoC) virtual channels (VCs) as an expanded memory subsystem has emerged. Previous network caching studies focused on utilizing VCs on the NoC's local input port as a victim cache to reduce local data access latency. In contrast to previous studies, we explore the opportunity of mitigating problems associated with shared data access via in-network caching for directory entry (NCDE), which can utilize every input port's VCs to hold directory entries. NCDE exploits VCs as the victim and prefetch buffers of the directory entries, each reducing directory eviction-induced invalidations and simplifying the cache-to-cache (C2C) data transfer. The effectiveness of NCDE was evaluated using a gem5 full-system simulator, and the results show that the average memory access time (AMAT) and workload execution time were reduced by 7.69% and 5.82%, respectively. As a cost for accelerating the data access latency, implementing NCDE incurs a negligible router area overhead of 1.56%.INDEX TERMS Directory-based cache coherence protocol, directory caching, network-on-chip, sparse directory, virtual channel (VC) utilization

show abstract