Exploit temporal locality of shared data in SRC enabled CMP

Authors:
Haixia Wang;Dongsheng Wang;Peng Li;Jinglei Wang;XianPing Fu
Affiliations:
Research Institute of Information Technology, National Laboratory for Information Science and Technology, Tsinghua University, Beijing, P.R. China;Research Institute of Information Technology, National Laboratory for Information Science and Technology, Tsinghua University, Beijing, P.R. China;Research Institute of Information Technology, National Laboratory for Information Science and Technology, Tsinghua University, Beijing, P.R. China;Research Institute of Information Technology, National Laboratory for Information Science and Technology, Tsinghua University, Beijing, P.R. China;Research Institute of Information Technology, National Laboratory for Information Science and Technology, Tsinghua University, Beijing, P.R. China
Venue:
NPC'07 Proceedings of the 2007 IFIP international conference on Network and parallel computing
Year:
2007

Citing 14
Cited 1

The SPLASH-2 programs: characterization and methodological considerations

ISCA '95 Proceedings of the 22nd annual international symposium on Computer architecture
The case for a single-chip multiprocessor

Proceedings of the seventh international conference on Architectural support for programming languages and operating systems
Implementing a cache consistency protocol

ISCA '85 Proceedings of the 12th annual international symposium on Computer architecture
A Single-Chip Multiprocessor

Computer
Simics: A Full System Simulation Platform

Computer
The Stanford Hydra CMP

IEEE Micro
Using cache memory to reduce processor-memory traffic

ISCA '83 Proceedings of the 10th annual international symposium on Computer architecture
Token coherence: decoupling performance and correctness

Proceedings of the 30th annual international symposium on Computer architecture
Using destination-set prediction to improve the latency/bandwidth tradeoff in shared-memory multiprocessors

Proceedings of the 30th annual international symposium on Computer architecture
Improving Multiple-CMP Systems Using Token Coherence

HPCA '05 Proceedings of the 11th International Symposium on High-Performance Computer Architecture
Multifacet's general execution-driven multiprocessor simulator (GEMS) toolset

ACM SIGARCH Computer Architecture News - Special issue: dasCMP'05
SRC-based Cache Coherence Protocol in Chip Multiprocessor

FCST '06 Proceedings of the Japan-China Joint Workshop on Frontier of Computer Science and Technology
A New Solution to Coherence Problems in Multicache Systems

IEEE Transactions on Computers
Cache system design in the tightly coupled multiprocessor system

AFIPS '76 Proceedings of the June 7-10, 1976, national computer conference and exposition

A Novel Cache Organization for Tiled Chip Multiprocessor

APPT '09 Proceedings of the 8th International Symposium on Advanced Parallel Processing Technologies

Quantified Score

Hi-index	0.01

Visualization

Abstract

By run-time characteristic analysis of parallel workloads, we found that a majority of shared data accesses of parallel workload has temporal locality. Based on this characteristic, we present a sharing relation cache (SRC for short) based CMP architecture, saving recently used sharing relations to provide destination set information for following cache-to-cache miss requests. Token-SRC protocol integrates SRC into token protocol,reducing network traffic of token protocol.Simulations using SPLASH-2 benchmarks show that, a 16-core CMP system with token-SRC achieved average 15% network traffic reduction of that with token protocol.