Global reactive congestion control in multicomputer networks

Smai, Abdel-Halim; Thorelli, Lars-Erik

doi:10.1109/hipc.1998.737987

Cited by 32 publications

(45 citation statements)

References 16 publications

(20 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, these solutions address multi-computer networks, in which the design considerations are significantly different from those of NoCs. For example, some works modify the network routers in order to throttle packet injection at high loads (e.g., [13], [14]), discard packets (e.g., [15]), deflect packets away from loaded locations (e.g. [16], [17]), use separate buffers for traffic destined at a hot-module (e.g.…”

Section: Related Workmentioning

confidence: 99%

Access Regulation to Hot-Modules in Wormhole NoCs

Walter

Cidon

Ginosar

et al. 2007

First International Symposium on Networks-on-Chip (NOCS'07)

View full text Add to dashboard Cite

Network on Chip (NoC) may be the primary interconnect mechanism for future Systems-on-Chip (SoC). Real-life SoCs typically include hot-modules such as DRAM controller or floating point unit, which are bandwidth limited and in high demand by other units. In this paper we demonstrate that the mere existence of one or more hot-modules in a wormholebased NoC dramatically reduces network efficiency and causes an unfair allocation of system resources. We demonstrate that a single hot-module destroys the performance of the entire SoC, even if network resources are over-provisioned. In order to resolve the hot-module effect, we introduce a novel low-cost credit based distributed access regulation technique that fairly allocates access rights to the hot-module. Unlike other methods, this technique directly addresses the root cause of network buffer congestion phenomena. Using simulation, we show the effectiveness of the suggested mechanism in various NoC scenarios.

show abstract

Section: Related Workmentioning

confidence: 99%

Access Regulation to Hot-Modules in Wormhole NoCs

Walter

Cidon

Ginosar

et al. 2007

First International Symposium on Networks-on-Chip (NOCS'07)

View full text Add to dashboard Cite

show abstract

“…This causes a sudden, severe drop in throughput and corresponding increase in packet latency. Several proposed schemes prevent the performance degradation that accompanies saturation by throttling packet injection when saturation is imminent [1,16,20,25,30]. Our approach goes further as it increases the applied load at which saturation occurs and avoids throughput degradation at saturation without placing limits on packet injection beyond those imposed by simple back-pressure.…”

Section: Background and Related Workmentioning

confidence: 99%

“…Anjan and Pinkston [25] have shown that eager misrouting can hurt performance for uniform traffic. As such, we want a lazy misrouting strategy that postpones misrouting until it is either hurting performance because of packets stalling behind it or because misrouting is mandated by the packet exchange protocol to avoid deadlocks in adaptive channels.…”

Section: Misroutesmentioning

confidence: 99%

BLAM: a high-performance routing algorithm for virtual cut-through networks

Thottethodi

Lebeck

Mukherjee³

Proceedings International Parallel and Distributed Processing Symposium

View full text Add to dashboard Cite

show abstract

“…In that sense, many HOL blocking elimination strategies have been proposed: Virtual Output Queues (VOQs) [31], Dynamically Allocated Multiqueues (DAMQs) [32], congestion buers [33], etc.…”

Section: Congestion Managementmentioning

confidence: 99%

High-performance architectures for high-radix switches.

Porta¹

View full text Add to dashboard Cite

As the optimal radix for switches increases due to the benets in lower latencies, overall reduction in cost and power consumption; the traditional switch architectures are no longer valid because of either low-performance or non-scalability with the number of ports.This dissertation proposes a new switch architecture suitable for highradix switches called Partitioned Crossbar Input Queued (PCIQ) that deals with one of the main constraints in high-radix switch design, the excessive memory requirements. Also, in general terms, PCIQ forms a new family of switch microarchitectures.PCIQ relies on a smart partition of the crossbar into sub-crossbars, thus requiring less memory resources than other proposals for high-radix, yet obtaining high-performance and also increasing the arbiter eciency. PCIQ uses two round-robin packet-based arbiters (one for each crossbar) that exhibit a linear cost and a logarithmic response time as the radix of the switch increases.Here it is shown that PCIQ exhibits a cost (measured in terms of memory requirements, crossbar complexity and arbiter complexity) similar to or lower than basic organizations like CIOQ. However, it is able to achieve maximum switch eciency for uniform trac distribution, thus leveling costly organizations like BC.The other big issue on high-radix switches is the HOL blocking problem, which reduces dramatically the switch performance. Traditional solutions for removing the HOL blocking problem were based on VOQ schemes, but having high number of ports on a high-radix switch prevents the use of any of them. In this dissertation, a new congestion management technique has been proposed. This solution is called RECN-IQ, is specic for IQ switches and diers from the original RECN idea (suitable only for CIOQ switches) in being highly ecient and simple to implement, reducing the memory requirements to the maximum. RECN-IQ introduced by rst time a novel statistical approach for detecting congestion using just a single queue per input port. Results proved that by using RECN-IQ switches, the network will benet from low cost switches and high-eciency under any type of trac pattern or network circumstances. All this makes the network predictable and stable in performance, no more drops in throughput because of congestion. AcknowledgementsAbove all I would like to acknowledge my darling Raquel. We have walked together this life since we decided to share our lives many years ago, helping each other, growing, and sharing many experiences jointly. She was responsible of supporting me in pointing my career towards computers, so I could nally pursue my passion since I had my rst computer (a C-64 by the way).She has been my muse all this years; inspiring me in putting passion, eciency and love in this job. For that and many other moments in which she has been essential, this work should be honored to her as well. This work represents an academic milestone for us as a couple. Now it should be time for us to have her pursuing her PhD in Physics. José Duato opened to me this worl...

show abstract

Global reactive congestion control in multicomputer networks

Cited by 32 publications

References 16 publications

Access Regulation to Hot-Modules in Wormhole NoCs

Access Regulation to Hot-Modules in Wormhole NoCs

BLAM: a high-performance routing algorithm for virtual cut-through networks

High-performance architectures for high-radix switches.

Contact Info

Product

Resources

About