Managing Distributed, Shared L2 Caches through OS-Level Page Allocation
Authors:
Top Cited Papers
- 1 December 2006
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 40th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO 2007)
- No. 10724451,p. 455-468
Abstract
This paper presents and studies a distributed L2 cache management approach through OS-level page allocation for future many-core processors. L2 cache management is a crucial multicore processor design aspect to overcome non-uniform cache access latency for good program performance and to reduce on-chip network traffic and related power consumption. Unlike previously studied hardware-based private and shared cache designs implementing a "fixed" caching policy, the proposed OS-micro architecture approach is flexible; it can easily implement a wide spectrum of L2 caching policies without complex hardware support. Furthermore, our approach can provide differentiated execution environment to running programs by dynamically controlling data placement and cache sharing degrees. We discuss key design issues of the proposed approach and present preliminary experimental results showing the promise of our approachKeywords
This publication has 23 references indexed in Scilit:
- Cooperative Caching for Chip MultiprocessorsACM SIGARCH Computer Architecture News, 2006
- A NUCA substrate for flexible CMP cache sharing2005
- Niagara: A 32-Way Multithreaded Sparc ProcessorIEEE Micro, 2005
- An adaptive, non-uniform cache structure for wire-delay dominated on-chip caches2002
- SimpleScalar: an infrastructure for computer system modelingComputer, 2002
- Data prefetch mechanismsACM Computing Surveys, 2000
- Reducing cache misses using hardware and software page placement1999
- Page placement algorithms for large real-indexed cachesACM Transactions on Computer Systems, 1992
- Experimental comparison of memory management policies for NUMA multiprocessorsACM Transactions on Computer Systems, 1991
- Space/time trade-offs in hash coding with allowable errorsCommunications of the ACM, 1970