An Imitation Learning Approach for Cache Replacement
Jul 12, 2020
Speakers
Evan Zheran Liu
Sprecher:in · 0 Follower:innen
Milad Hashemi
Sprecher:in · 0 Follower:innen
Kevin Swersky
Sprecher:in · 0 Follower:innen
Partha Ranganathan
Sprecher:in · 0 Follower:innen
Junwhan Ahn
Sprecher:in · 0 Follower:innen
About
Program execution speed critically depends on reducing cache misses, as cache misses are orders of magnitude slower than hits. To reduce cache misses, we focus on the problem of cache replacement: choosing which cache line to evict upon inserting a new line. This is challenging because it requires planning far ahead and currently there is no known practical solution. As a result, current replacement policies typically resort to heuristics designed for specific common access patterns, which fail on more diverse and complex access patterns. In contrast, we propose an imitation learning approach to automatically learn cache access patterns by leveraging Belady’s, an oracle policy that computes the optimal eviction decision given the future cache accesses. While directly applying Belady's is infeasible since the future is unknown, we train a policy conditioned only on past accesses that accurately approximates Belady's even on diverse and complex access patterns. When evaluated on four of the most memory-intensive SPEC applications, our learned policy reduces cache miss rates by 15Program execution speed critically depends on reducing cache misses, as cache misses are orders of magnitude slower than hits. To reduce cache misses, we focus on the problem of cache replacement: choosing which cache line to evict upon inserting a new line. This is challenging because it requires planning far ahead and currently there is no known practical solution. As a result, current replacement policies typically resort to heuristics designed for specific common access patterns, which fail…
Categories
KI und Datenwissenschaft
Kategorie · 10,8k Präsentationen
About ICML 2020
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Bayesian model averaging is suboptimal for generalization under model misspecification
Später ansehen
Q&A with Rachel Ward
Später ansehen
On the Variational Posterior of DP-DLGMs
Später ansehen
An end-to-end approach for the verification problem: learning the right distance
Später ansehen
TrajectoryNet: A Dynamic Optimal Transport Network for Modeling Cellular Dynamics
Später ansehen
