Adaptive Cooperation of Prefetching and Warp Scheduling on GPUs
- 30 October 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 68 (4) , 609-616
Abstract
This paper proposes a new architecture, called Adaptive PREfetching and Scheduling (APRES), which improves cache efficiency of GPUs. APRES relies on the observation that GPU loads tend to have either high locality or strided access patterns across warps. APRES schedules warps so that as many cache hits are generated as possible before the generation of any cache miss. Without directly predicting future cache hits/misses for each warp, APRES creates a warp group that will execute the same static load shortly and prioritizes the grouped warps. If the first executed warp in the group hits the cache, grouped warps are likely to access the same cache lines. Unless, APRES considers the load as a strided type and generates prefetch requests for the grouped warps. In addition, APRES includes a new dynamic L1 prefetch and data cache partitioning to reduce contentions between demand-fetched and prefetched lines. In our evaluation, APRES achieves 27.8% performance improvement.Keywords
Funding Information
- National Research Foundation of Korea (NRF-2018R1A2A2A05018941)
- Technology Innovation Program (10080590)
This publication has 23 references indexed in Scilit:
- Warped-compression2015
- GREEN Cache: Exploiting the Disciplined Memory Model of OpenCL on GPUsIEEE Transactions on Computers, 2015
- Mitigating Prefetcher-Caused Pollution Using Informed Caching Policies for Prefetched BlocksACM Transactions on Architecture and Code Optimization, 2015
- Spare register aware prefetching for graph algorithms on GPUs2014
- Orchestrated scheduling and prefetching for GPGPUs2013
- Prefetching and cache management using task lifetimes2013
- OWL2013
- Cache-Conscious Wavefront Scheduling2012
- Characterizing and improving the use of demand-fetched caches in GPUs2012
- Improving GPU performance via large warps and two-level warp scheduling2011