FBICM: Efficient Congestion Management for High-Performance Networks Using Distributed Deterministic Routing

Escudero-Sahuquillo, Jesús; García, Pedro J.; Quiles, Francisco J.; Flich, José; Duato, J.

doi:10.1007/978-3-540-89894-8_44

Cited by 13 publications

(13 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These blocked packets in turn block other packets further upstream. Many works [1], [9], [11], [36] have proposed allocating separate queues for different packet flows within a switch to avoid HoL blocking. For example, separate queues could be allocated by output port [1] or dynamically for congested packet flows [9].…”

Section: E Implementation Costmentioning

confidence: 99%

“…When this congestion occurs, packets contend for shared network resources frequently, and this can reduce overall system throughput. Congestion in onand off-chip interconnects is a well-known problem that has been described in many prior works (e.g., [2], [9], [11], [15], [30], [31], [32], [38]). Congestion can significantly degrade system performance if it is not properly managed.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

HAT: Heterogeneous Adaptive Throttling for On-Chip Networks

Chang

Ausavarungnirun

Fallin

et al. 2012

2012 IEEE 24th International Symposium on Computer Architecture and High Performance Computing

View full text Add to dashboard Cite

Abstract-The network-on-chip (NoC) is a primary shared resource in a chip multiprocessor (CMP) system. As core counts continue to increase and applications become increasingly data-intensive, the network load will also increase, leading to more congestion in the network. This network congestion can degrade system performance if the network load is not appropriately controlled. Prior works have proposed sourcethrottling congestion control, which limits the rate at which new network traffic (packets) enters the NoC in order to reduce congestion and improve performance. These prior congestion control mechanisms have shortcomings that significantly limit their performance: either 1) they are not application-aware, but rather throttle all applications equally regardless of applications' sensitivity to latency, or 2) they are not network-loadaware, throttling according to application characteristics but sometimes under-or over-throttling the cores.In this work, we propose Heterogeneous Adaptive Throttling, or HAT, a new source-throttling congestion control mechanism based on two key principles: application-aware throttling and network-load-aware throttling rate adjustment. First, we observe that only network-bandwidth-intensive applications (those which use the network most heavily) should be throttled, allowing the other latency-sensitive applications to make faster progress without as much interference. Second, we observe that the throttling rate which yields the best performance varies between workloads; a single, static, throttling rate underthrottles some workloads while over-throttling others. Hence, the throttling mechanism should observe network load dynamically and adjust its throttling rate accordingly. While some past works have also used a closed-loop control approach, none have been application-aware. HAT is the first mechanism to combine application-awareness and network-load-aware throttling rate adjustment to address congestion in a NoC.We evaluate HAT using a wide variety of multiprogrammed workloads on several NoC-based CMP systems with 16-, 64-, and 144-cores and compare its performance to two state-ofthe-art congestion control mechanisms. Our evaluations show that HAT consistently provides higher system performance and fairness than prior congestion control mechanisms.

show abstract

Section: E Implementation Costmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

HAT: Heterogeneous Adaptive Throttling for On-Chip Networks

Chang

Ausavarungnirun

Fallin

et al. 2012

2012 IEEE 24th International Symposium on Computer Architecture and High Performance Computing

View full text Add to dashboard Cite

show abstract

“…The first version of FBICM [6], is an early approach to a congestion management technique that efficiently eliminates HOL blocking in distributed deterministic routing networks.…”

Section: Fbicm Basicsmentioning

confidence: 99%

“…However, RECN was proposed for networks which use source routing, so not being applicable in networks where distributed deterministic routing is present, like Infiniband [5]. In order to cover this type of networks, Flow-Based Implicit Congestion Management (FBICM) [6] has been recently put forward. FBICM effectively eliminates HOL blocking following the same RECN philosophy, but in networks using distributed deterministic routing.…”

Section: Introductionmentioning

confidence: 99%

Cost-Effective Congestion Management for Interconnection Networks Using Distributed Deterministic Routing

Escudero-Sahuquillo

García

Quiles

et al. 2010

2010 IEEE 16th International Conference on Parallel and Distributed Systems

View full text Add to dashboard Cite

The Interconnection networks are essential elements in current computing systems. For this reason, achieving the best network performance, even in congestion situations, has been a primary goal in recent years. In that sense, there exist several techniques focused on eliminating the main negative effect of congestion: the Head of Line (HOL) blocking. One of the most successful HOL blocking elimination techniques is RECN, which can be applied in source routing networks. FBICM follows the same approach as RECN, but it has been developed for distributed deterministic routing networks. Although FBICM effectively eliminates HOL blocking, it requires too much resources to be implemented. In this paper we present a new FBICM version, based on a new organization of switch memory resources, that significantly reduces the required silicon area, complexity and cost. Moreover, we present new results about FBICM, in network topologies not yet analyzed. From the experiment results we can conclude that a far less complex and feasible FBICM implementation can be achieved by using the proposed improvements, while not losing efficiency.

show abstract

“…Instead of removing the congestion tree itself, these approaches strive to relieve the unfortunate side effects the congestion tree has on flows not contributing to the congestion. That is, they try to remove the HOL blocking by using special set aside queues for contributors to congestion, effectively making it possible for victim flows to bypass the contributors to congestion without actually removing the congestion tree [14], [15]. Such an approach has the advantage of being able to react immediately and locally at each switch, at the cost of the extra buffers needed for the set aside queues and the added complexity in the switch to manage them.…”

Section: Introductionmentioning

confidence: 97%

On the Relation between Congestion Control, Switch Arbitration and Fairness

Gran

Zahavi

Reinemo

et al. 2011

2011 11th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing

View full text Add to dashboard Cite

In lossless interconnection networks such as InfiniBand, congestion control (CC) can be an effective mechanism to achieve high performance and good utilization of network resources. The InfiniBand standard describes CC functionality for detecting and resolving congestion, but the design decisions on how to implement this functionallity is left to the hardware designer. One must be cautious when making these design decisions not to introduce fairness problems, as our study shows.In this paper we study the relationship between congestion control, switch arbitration, and fairness. Specifically, we look at fairness among different traffic flows arriving at a hot spot switch on different input ports, as CC is turned on. In addition we study the fairness among traffic flows at a switch where some flows are exclusive users of their input ports while other flows are sharing an input port (the parking lot problem).Our results show that the implementation of congestion control in a switch is vulnerable to unfairness if care is not taken. In detail, we found that a threshold hysteresis of more than one MTU is needed to resolve arbitration unfairness. Furthermore, to fully solve the parking lot problem, proper configuration of the CC parameters are required.

show abstract

FBICM: Efficient Congestion Management for High-Performance Networks Using Distributed Deterministic Routing

Cited by 13 publications

References 12 publications

HAT: Heterogeneous Adaptive Throttling for On-Chip Networks

HAT: Heterogeneous Adaptive Throttling for On-Chip Networks

Cost-Effective Congestion Management for Interconnection Networks Using Distributed Deterministic Routing

On the Relation between Congestion Control, Switch Arbitration and Fairness

Contact Info

Product

Resources

About