Characterizing multi-threaded applications for designing sharing-aware last-level cache replacement policies

Natarajan, Ragavendra; Chaudhuri, Mainak

doi:10.1109/iiswc.2013.6704665

Cited by 14 publications

(6 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Frequency based LRU Eviction based on frequency of cache access Natarajan et al (2013) Sharing-aware policy Reuse of shared LLC blocks by crossthreads Warrier et al (2013) Application-aware replacement policy Depriving high access rate application to override low access rate application Li et al (2014) Reference affinity scheme Allocating frequently used data closely Lathigara et al (2015) Application behaviour-aware replacement policy (ABRip) Predictions of re-reference interval of the block based on application behaviour and block locality Mahto et al (2017) AB-aware adaptive cache management policy (ACAM) Eviction based on application behaviour towards cache access Thread level parallelism aware partitioning (TAP) Eviction based on UCP and RRIP Mekkat et al (2013) LLC management policy GPUs tolerance towards the latency in accessing memory The research community has proposed several techniques to address main memory contention which we discuss next.…”

Section: Replacement Policy Referencementioning

confidence: 99%

A review on shared resource contention in multicores and its mitigating techniques

Jain¹,

Surve²

2020

IJHPSA

View full text Add to dashboard Cite

Chip multiprocessor (CMP) systems have become inevitable to meet high computing demands. In such systems sharing of resources is imperative for better resource utilisation. The challenge arises when various application programs running on neighbouring cores compete for these resources concurrently and introduce contention. We aim to present in a simple, lucid and captivating manner a review of previous work on contention in multicores due to various shared resources like shared caches, main memory, memory bus bandwidth, prefetchers etc. The work investigates key ideas proposed by the research community to alleviate resource contention due to these various resources, under a single umbrella. The prime objective of the study is to throw light upon the fact that, alone a single shared component is not a dominant reason for performance degradation in CMPs, rather all elements in the memory hierarchy introduce resource contention thereby affecting performance cumulatively. The work presented would assist novice readers, researchers and academicians to further serve to propose optimal policies to address contention in designing multicore applications, considering the overall impact of these resources on the performance of multicore systems.

show abstract

Section: Replacement Policy Referencementioning

confidence: 99%

A review on shared resource contention in multicores and its mitigating techniques

Jain¹,

Surve²

2020

IJHPSA

View full text Add to dashboard Cite

show abstract

“…In this section I am going to discuss some more. Natarajan and Chaudhuri [4] studied biasing of LLC cache replacement towards shared lines within multiple cores in a single socket. They show that cross-thread reuses of shared cache lines in LLC are more important than intra-thread reuses of private data in multithreaded applications.…”

Section: Os Scheduling Optimizationmentioning

confidence: 99%

OS Scheduling Algorithms for Memory Intensive Workloads in Multi-socket Multi-core Servers

Durbhakula

2019

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Major chip manufacturers have all introduced multicore microprocessors. Multi-socket systems built from these processors are used for running various server applications. Depending on the application, remote cache-to-cache transfers can severely impact the performance of such workloads. This paper presents a cache optimization that can cut down remote cache-tocache transfers. By keeping track of remote cache lines loaded from remote caches into last-level-cache and by biasing the cache replacement policy towards such remote cache lines we can reduce the number of cache misses. This in turn results in improvement of overall performance. I present the design details in this paper. I do a qualitative comparison of various solutions to the problem of performance impact of remote cache-to-cache transfers. This work can be extended by doing a quantitative evaluation.

show abstract

“…12 In addition, Band-pass prefetching could append thread-criticality information [Du Bois et al 2013;Panda and Balachandran 2013] for performing prefetcher aggressiveness control. However, when the threads of a parallel application share data and work co-operatively (observed by Natarajan and Chaudhuri [2013] and Panda and Balachandran [2012]), it is possible to append Band-pass prefetching with data sharing characteristics for further improving the execution time of parallel applications.…”

Section: Applying Band-pass Prefetching To Parallel Workloadsmentioning

confidence: 99%

Band-Pass Prefetching

Sridharan

Panda

Seznec

2017

ACM Trans. Archit. Code Optim.

View full text Add to dashboard Cite

In multi-core systems, an application's prefetcher can interfere with the memory requests of other applications using the shared resources, such as last level cache and memory bandwidth. In order to minimize prefetcher-caused interference, prior mechanisms have been proposed to dynamically control prefetcher aggressiveness at runtime. These mechanisms use several parameters to capture prefetch usefulness as well as prefetcher-caused interference, performing aggressive control decisions. However, these mechanisms do not capture the actual interference at the shared resources and most often lead to incorrect aggressiveness control decisions. Therefore, prior works leave scope for performance improvement. Toward this end, we propose a solution to manage prefetching in multicore systems. In particular, we make two fundamental observations: First, a positive correlation exists between the accuracy of a prefetcher and the amount of prefetch requests it generates relative to an application's total (demand and prefetch) requests. Second, a strong positive correlation exists between the ratio of total prefetch to demand requests and the ratio of average last level cache miss service times of demand to prefetch requests. In this article, we propose Band-pass prefetching that builds on those two observations, a simple and low-overhead mechanism to effectively manage prefetchers in multicore systems. Our solution consists of local and global prefetcher aggressiveness control components, which altogether, control the flow of prefetch requests between a range of prefetch to demand requests ratios. From our experiments on 16-core multi-programmed workloads, on systems using stream prefetching, we observe that Band-pass prefetching achieves 12.4% (geometric-mean) improvement on harmonic speedup over the baseline that implements no prefetching, while aggressive prefetching without prefetcher aggressiveness control and state-of-the-art HPAC, P-FST, and CAFFEINE achieve 8.2%, 8.4%, 1.4%, and 9.7%, respectively. Further evaluation of the proposed Band-pass prefetching mechanism on systems using AMPM prefetcher shows similar performance trends. For a 16-core system, Band-pass prefetching requires only a modest hardware cost of 239 bytes.

show abstract

Characterizing multi-threaded applications for designing sharing-aware last-level cache replacement policies

Cited by 14 publications

References 36 publications

A review on shared resource contention in multicores and its mitigating techniques

A review on shared resource contention in multicores and its mitigating techniques

OS Scheduling Algorithms for Memory Intensive Workloads in Multi-socket Multi-core Servers

Band-Pass Prefetching

Contact Info

Product

Resources

About