Reducing Load Latency with Cache Level Prediction
Open Access
- 1 April 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 39, 648-661
Abstract
High load latency that results from deep cache hierarchies and relatively slow main memory is an important limiter of single-thread performance. Data prefetch helps reduce this latency by fetching data up the hierarchy before it is requested by load instructions. However, data prefetching has shown to be imperfect in many situations. We propose cache-level prediction to complement prefetchers. Our method predicts which memory hierarchy level a load will access allowing the memory loads to start earlier, and thereby saves many cycles. The predictor provides high prediction accuracy at the cost of just one cycle added latency to L1 misses. Level prediction reduces the memory access latency by 20% on average, and provides speedup of 10.3% over a conventional baseline, and 6.1% over a boosted baseline on generic, graph, and HPC applications.Keywords
All Related Versions
Funding Information
- National Science Foundation
This publication has 29 references indexed in Scilit:
- A Top-Down method for performance analysis and counters architecture2014
- Linearizing irregular memory accesses for improved correlated prefetching2013
- Efficient virtual memory for big memory serversACM SIGARCH Computer Architecture News, 2013
- Fundamental Latency Trade-off in Architecting DRAM Caches: Outperforming Impractical SRAM-Tags with a Simple and Practical Design2012
- A Mostly-Clean DRAM Cache for Effective Hit Speculation and Self-Balancing Dispatch2012
- Proactive instruction fetch2011
- The gem5 simulatorACM SIGARCH Computer Architecture News, 2011
- Multi-level Hardware Prefetching Using Low Complexity Delta Correlating Prediction Tables with Partial Matching2010
- Reducing set-associative cache energy via way-prediction and selective direct-mapping2005
- Run-time cache bypassingIEEE Transactions on Computers, 1999