A Cache Modeling Framework for Accelerator Systems
ACM Transactions on Architecture and Code Optimization · 22.08.2026
DOI: 10.1145/3838806 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Architecture and Code Optimization, online erschienen am 22.08.2026. Verfasst von Lingfeng Pei und 3 weiteren Autor:innen. Die Arbeit nennt 59 Literaturangaben.
Abstract (Originalsprache)
Modern hardware accelerators increasingly rely on cache-based memory systems to improve modularity and tolerate irregular memory behavior in sparse and data-dependent workloads. However, configuring accelerator caches remains challenging: designers must choose cache capacity, Miss Status Holding Register (MSHR) count, subentry provisioning, and fill bandwidth without a fast model that captures the timing-dependent behavior of non-blocking caches. Existing analytical models often focus on cache residency or miss counts, while cycle-level simulation captures miss merging and resource contention at substantially higher cost. This paper presents PlastiCache, a timing-augmented reuse-distance model for non-blocking accelerator caches. PlastiCache represents an accelerator memory stream as address–time pairs and extends reuse-distance analysis with predicted service intervals for outstanding misses. This formulation classifies each request as a cache-resident hit, an in-flight MSHR merge, or a new off-chip miss, while incorporating miss-handling capacity, memory-service timing, and return-path bandwidth as event constraints over the request stream. As a result, PlastiCache identifies whether a cache design is limited by cache capacity, MSHR availability, subentry pressure, DRAM service, or fill bandwidth. PlastiCache targets early-stage cache design-space exploration by preserving the relative ordering of candidate configurations. Across broad sweeps of workloads and cache designs, PlastiCache achieves a mean Spearman ranking correlation of 0.93 with RTL on latency–area tradeoff curves, while achieving geometric-mean speedups of 545 × over tree-based analytical models and 303 × over Verilator-based RTL simulation. We further integrate PlastiCache into an end-to-end accelerator cache sizing flow with a Chisel-based sparse matrix multiplication processing element and a synthesizable cache generator. FPGA prototyping across real-world workloads, including SuiteSparse matrices and a large language model, shows that the PlastiCache-Balanced design reduces delay–area product by 45.6% and 25.9% on average compared with MOMS and MiCache, respectively, with maximum reductions of 73.8% and 37.3%.
Zitieren
APA
Pei, L., Liew, W. S., Kanewala, U. C. H., & Carlson, T. E. (2026). A Cache Modeling Framework for Accelerator Systems. ACM Transactions on Architecture and Code Optimization. https://doi.org/10.1145/3838806
Vancouver
Pei L, Liew WS, Kanewala UCH, Carlson TE. A Cache Modeling Framework for Accelerator Systems. ACM Transactions on Architecture and Code Optimization. 2026. doi:10.1145/3838806
BibTeX
@article{Pei2026,
author = {Pei, Lingfeng and Liew, Wei Siew and Kanewala, Udaree Chathurangee Hiranthika and Carlson, Trevor E.},
title = {A Cache Modeling Framework for Accelerator Systems},
journal = {ACM Transactions on Architecture and Code Optimization},
year = {2026},
doi = {10.1145/3838806}
}
EUVIMED