A Fast Analytical Model of Fully Associative Caches

Tobias Gysi, Tobias Grosser, Laurin Brandner, Torsten Hoefler

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

While the cost of computation is an easy to understand local property, the cost of data movement on cached architectures depends on global state, does not compose, and is hard to predict. As a result, programmers often fail to consider the cost of data movement. Existing cache models and simulators provide the missing information but are computationally expensive. We present a lightweight cache model for fully associative caches with least recently used (LRU) replacement policy that gives fast and accurate results. We count the cache misses without explicit enumeration of all memory accesses by using symbolic counting techniques twice: 1) to derive the stack distance for each memory access and 2) to count the memory accesses with stack distance larger than the cache size. While this technique seems infeasible in theory, due to non-linearities after the first round of counting, we show that the counting problems are sufficiently linear in practice. Our cache model often computes the results within seconds and contrary to simulation the execution time is mostly problem size independent. Our evaluation measures modeling errors below 0.6% on real hardware. By providing accurate data placement information we enable memory hierarchy aware software development.
Original languageEnglish
Title of host publicationProceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation
PublisherACM
Pages816–829
Number of pages14
ISBN (Electronic)9781450367127
DOIs
Publication statusPublished - 8 Jun 2019
Event40th ACM SIGPLAN Conference on Programming Language Design and Implementation - Phoenix, United States
Duration: 24 Jun 201926 Jun 2019
https://pldi19.sigplan.org/home

Conference

Conference40th ACM SIGPLAN Conference on Programming Language Design and Implementation
Abbreviated titlePLDI 2019
Country/TerritoryUnited States
CityPhoenix
Period24/06/1926/06/19
Internet address

Fingerprint

Dive into the research topics of 'A Fast Analytical Model of Fully Associative Caches'. Together they form a unique fingerprint.

Cite this