Reuse-Aware Cache Partitioning Framework for Data-Sharing Multicore Systems

TL;DR

This paper introduces SRCP, a cache replacement mechanism for multi-core systems that improves cache efficiency and performance by being aware of shared data, outperforming existing algorithms.

Contribution

The paper proposes a novel reuse-aware cache replacement framework that reduces data replication and eviction, enhancing cache performance in data-sharing multicore systems.

Findings

SRCP outperforms TA-DRRIP and EHC by 13.34% in cache hit-rate.

SRCP improves overall system performance by 10.4%.

The approach effectively manages shared data in partitioned caches.

Abstract

Multi-core processors improve performance, but they can create unpredictability owing to shared resources such as caches interfering. Cache partitioning is used to alleviate the Worst-Case Execution Time (WCET) estimation by isolating the shared cache across each thread to reduce interference. It does, however, prohibit data from being transferred between parallel threads running on different cores. In this paper we present (SRCP) a cache replacement mechanism for partitioned caches that is aware of data being shared across threads, prevents shared data from being replicated across partitions and frequently used data from being evicted from caches. Our technique outperforms TA-DRRIP and EHC, which are existing state-of-the-art cache replacement algorithms, by 13.34% in cache hit-rate and 10.4% in performance over LRU (least recently used) cache replacement policy.