The Game of Latency, Bandwidth, and Hardware Prefetching
- 3 June 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Computer
- Vol. 57 (6) , 122-126
Abstract
A processor’s cache hierarchy exploits locality in memory accesses to reduce latency but can’t satisfy all memory accesses. Modern processors contain hardware prefetchers to predict data to be used in the future and bring them into a cache in a timely manner.Keywords
This publication has 7 references indexed in Scilit:
- A Two Level Neural Approach Combining Off-Chip Prediction with Adaptive Prefetch Filtering2024
- CLIP: Load Criticality based Data Prefetching for Bandwidth-constrained Many-core Systems2023
- Drishyam: An Image is Worth a Data Prefetcher2023
- Berti: an Accurate Local-Delta Data Prefetcher2022
- Pythia: A Customizable Hardware Prefetching Framework Using Online Reinforcement Learning2021
- A hierarchical neural model of data prefetching2021
- Spectre Attacks: Exploiting Speculative Execution2019