Cost-effective contention avoidance in a CMP with shared memory controllers

Authors:
Samuel Rodrigo;Frank Olaf Sem-Jacobsen;Hervé Tatenguem;Tor Skeie;Davide Bertozzi
Affiliations:
Simula Research Laboratory, Norway;Simula Research Laboratory, Norway;Dept. Engineering, University of Ferrara, Italy;Simula Research Laboratory, Norway,Dept. of Informatics, University of Oslo, Norway;Dept. Engineering, University of Ferrara, Italy
Venue:
Euro-Par'12 Proceedings of the 18th international conference on Parallel Processing
Year:
2012

Citing 15
Cited 0

Self-Tuned Congestion Control for Multiprocessor Networks

HPCA '01 Proceedings of the 7th International Symposium on High-Performance Computer Architecture
Improving routing efficiency for network-on-chip through contention-aware input selection

ASP-DAC '06 Proceedings of the 2006 Asia and South Pacific Design Automation Conference
DyXY: a proximity congestion-aware deadlock-free dynamic routing method for network on chip

Proceedings of the 43rd annual Design Automation Conference
QoS policies and architecture for cache/memory in CMP platforms

Proceedings of the 2007 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
Congestion-controlled best-effort communication for networks-on-chip

Proceedings of the conference on Design, automation and test in Europe
Application mapping for chip multiprocessors

Proceedings of the 45th annual Design Automation Conference
Achieving predictable performance through better memory controller placement in many-core CMPs

Proceedings of the 36th annual international symposium on Computer architecture
Preemptive virtual clock: a flexible, efficient, and cost-effective QOS scheme for networks-on-chip

Proceedings of the 42nd Annual IEEE/ACM International Symposium on Microarchitecture
Application-aware prioritization mechanisms for on-chip networks

Proceedings of the 42nd Annual IEEE/ACM International Symposium on Microarchitecture
An analysis of on-chip interconnection networks for large-scale chip multiprocessors

ACM Transactions on Architecture and Code Optimization (TACO)
Addressing Manufacturing Challenges with Cost-Efficient Fault Tolerant Routing

NOCS '10 Proceedings of the 2010 Fourth ACM/IEEE International Symposium on Networks-on-Chip
Improved Utilization of NoC Channel Bandwidth by Switch Replication for Cost-Effective Multi-processor Systems-on-Chip

NOCS '10 Proceedings of the 2010 Fourth ACM/IEEE International Symposium on Networks-on-Chip
Segment-based routing: an efficient fault-tolerant routing algorithm for meshes and Tori

IPDPS'06 Proceedings of the 20th international conference on Parallel and distributed processing
Virtualizing network-on-chip resources in chip-multiprocessors

Microprocessors & Microsystems
Designing Network On-Chip Architectures in the Nanoscale Era

Designing Network On-Chip Architectures in the Nanoscale Era

Quantified Score

Hi-index	0.00

Visualization

Abstract

Efficient CMP utilisation requires virtualisation. This forces multiple applications to contend for the same network resources and memory bandwidth. In this paper we study the cause and effect of network congestion with respect to traffic local to the applications, and traffic caused by memory access. This reveals that applications close to the memory controller suffer because of congestion caused by memory controller traffic from other applications. We present a simple mechanism to reduce head-of-line blocking in the switches, which efficiently reduces network congestion, increases network performance, and evens out the performance differences between the CMP applications.