Memory coherence in the age of multicores

As we enter an era of exascale multicores, the question of efficiently supporting a shared memory model has become of paramount importance. On the one hand, programmers demand the convenience of coherent shared memory; on the other, growing core counts place higher demands on the memory subsystem an...

Full description

Bibliographic Details
Main Authors: Lis, Mieszko, Shim, Keun Sup, Cho, Myong Hyon, Devadas, Srinivas
Other Authors: Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Format: Article
Language:en_US
Published: Institute of Electrical and Electronics Engineers (IEEE) 2012
Online Access:http://hdl.handle.net/1721.1/72582
https://orcid.org/0000-0001-8253-7714
_version_ 1826208256444334080
author Lis, Mieszko
Shim, Keun Sup
Cho, Myong Hyon
Devadas, Srinivas
author2 Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
author_facet Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Lis, Mieszko
Shim, Keun Sup
Cho, Myong Hyon
Devadas, Srinivas
author_sort Lis, Mieszko
collection MIT
description As we enter an era of exascale multicores, the question of efficiently supporting a shared memory model has become of paramount importance. On the one hand, programmers demand the convenience of coherent shared memory; on the other, growing core counts place higher demands on the memory subsystem and increasing on-chip distances mean that interconnect delays are becoming a significant part of memory access latencies. In this article, we first review the traditional techniques for providing a shared memory abstraction at the hardware level in multicore systems. We describe two new schemes that guarantee coherent shared memory without the complexity and overheads of a cache coherence protocol, namely execution migration and library cache coherence. We compare these approaches using an analytical model based on average memory latency, and give intuition for the strengths and weaknesses of each. Finally, we describe hybrid schemes that combine the strengths of different schemes.
first_indexed 2024-09-23T14:02:40Z
format Article
id mit-1721.1/72582
institution Massachusetts Institute of Technology
language en_US
last_indexed 2024-09-23T14:02:40Z
publishDate 2012
publisher Institute of Electrical and Electronics Engineers (IEEE)
record_format dspace
spelling mit-1721.1/725822022-10-01T18:47:40Z Memory coherence in the age of multicores Lis, Mieszko Shim, Keun Sup Cho, Myong Hyon Devadas, Srinivas Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Devadas, Srinivas Lis, Mieszko Shim, Keun Sup Cho, Myong Hyon Devadas, Srinivas As we enter an era of exascale multicores, the question of efficiently supporting a shared memory model has become of paramount importance. On the one hand, programmers demand the convenience of coherent shared memory; on the other, growing core counts place higher demands on the memory subsystem and increasing on-chip distances mean that interconnect delays are becoming a significant part of memory access latencies. In this article, we first review the traditional techniques for providing a shared memory abstraction at the hardware level in multicore systems. We describe two new schemes that guarantee coherent shared memory without the complexity and overheads of a cache coherence protocol, namely execution migration and library cache coherence. We compare these approaches using an analytical model based on average memory latency, and give intuition for the strengths and weaknesses of each. Finally, we describe hybrid schemes that combine the strengths of different schemes. 2012-09-07T19:35:51Z 2012-09-07T19:35:51Z 2011-11 2011-10 Article http://purl.org/eprint/type/ConferencePaper 978-1-4577-1953-0 1063-6404 http://hdl.handle.net/1721.1/72582 Lis, Mieszko et al. “Memory Coherence in the Age of Multicores.” IEEE 29th International Conference on Computer Design 2011 (ICCD). 1–8. https://orcid.org/0000-0001-8253-7714 en_US http://dx.doi.org/10.1109/ICCD.2011.6081367 IEEE 29th International Conference on Computer Design 2011 (ICCD) Creative Commons Attribution-Noncommercial-Share Alike 3.0 http://creativecommons.org/licenses/by-nc-sa/3.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) MIT web domain
spellingShingle Lis, Mieszko
Shim, Keun Sup
Cho, Myong Hyon
Devadas, Srinivas
Memory coherence in the age of multicores
title Memory coherence in the age of multicores
title_full Memory coherence in the age of multicores
title_fullStr Memory coherence in the age of multicores
title_full_unstemmed Memory coherence in the age of multicores
title_short Memory coherence in the age of multicores
title_sort memory coherence in the age of multicores
url http://hdl.handle.net/1721.1/72582
https://orcid.org/0000-0001-8253-7714
work_keys_str_mv AT lismieszko memorycoherenceintheageofmulticores
AT shimkeunsup memorycoherenceintheageofmulticores
AT chomyonghyon memorycoherenceintheageofmulticores
AT devadassrinivas memorycoherenceintheageofmulticores