A fine-grain clock synchronization mechanism for Myrinet clusters

Chakravarthi, S. Sreenivasa; Pillai, A.; Neelamegam, Jothi P.; Apte, M.; Skjellum, Anthony

doi:10.1109/lcn.2002.1181848

Cited by 7 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A new cell with value Cmax is inserted at the right. To maintain synchronization, all resources must be synchronized to a global time base with an accuracy of at least ±Cmax cycles using a technique such as [9].…”

Section: Reservationmentioning

confidence: 99%

Channel reservation protocol for over-subscribed channels and destinations

Jiang

Becker

Dally

2013

Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis

View full text Add to dashboard Cite

Channels in system-wide networks tend to be over-subscribed due to the cost of bandwidth and increasing traffic demands. To make matters worse, workloads can overstress specific destinations, creating hotspots. Lossless networks offer attractive advantages compared to lossy networks but suffer from tree saturation. This led to the development of explicit congestion notification (ECN). However, ECN is very sensitive to its configuration parameters and acts only after congestion forms. We propose channel reservation protocol (CRP) to enable sources to reserve bandwidth in multiple resources in advance of packet transmission and with a single request, but without idling resources like circuit switching. CRP prevents congestion from ever occurring and thus reacts instantly to traffic changes, whereas ECN requires 300,000 cycles to stabilize in our experiments. Furthermore, ECN may not prevent congestion formed by short-lived flows generated by a large combination of source-destination pairs.

show abstract

Section: Reservationmentioning

confidence: 99%

Channel reservation protocol for over-subscribed channels and destinations

Jiang

Becker

Dally

2013

Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis

View full text Add to dashboard Cite

show abstract

“…The vast majority of work attempts to understand the fine details of moving bits of information from point A to point B. In high performance networks this requires specialized fine-grained techniques such as sophisticated clocks [5] and faster sampling rates [31].…”

Section: Network Performance and Adaptabilitymentioning

confidence: 99%

Exploring the relationship between parallel application run-time variability and network performance in clusters

Evans

Groop

Hood

28th Annual IEEE International Conference on Local Computer Networks, 2003. LCN '03. Proceedings.

View full text Add to dashboard Cite

show abstract

“…The master node periodically broadcasts a 64-bit nanosecond-precision host clock value, using which each slave node builds a synchronized virtual clock. The design uses a novel technique to greatly improve the achievable accuracy, compared to traditional master-slave schemes [2]. Clock values sent by the master are kept "ticking" by adding the protocol-processing delays encountered by clock messages.…”

Section: Clock Synchronization Modulementioning

confidence: 99%

A synchronized real-time linux based myrinet cluster for deterministic high performance computing and MPI/RT

Apte

Chakravarthi

Padmanabhan

et al.

Proceedings 15th International Parallel and Distributed Processing Symposium. IPDPS 2001

Self Cite

View full text Add to dashboard Cite

This paper describes the design and implementation of a real-time cluster of PCs that provides globally synchronized scheduling and predictable message passing. A high-accuracy, fine-grain global clock implementation has been closely coupled with a timebased scheduler to facilitate finely synchronized global scheduling across the cluster. A real-time messaging layer provides predictable communication latencies over the interconnecting Myrinet network. This system provides a solid framework for QoS based real-time communication, and in particular facilitates efficient layering of high-performance real-time distributed middleware such as MPI/RT. We present experiments and results to demonstrate the degree of predictability and synchronization achieved on an 8-node Myrinet cluster.

show abstract

A fine-grain clock synchronization mechanism for Myrinet clusters

Cited by 7 publications

References 10 publications

Channel reservation protocol for over-subscribed channels and destinations

Channel reservation protocol for over-subscribed channels and destinations

Exploring the relationship between parallel application run-time variability and network performance in clusters

A synchronized real-time linux based myrinet cluster for deterministic high performance computing and MPI/RT

Contact Info

Product

Resources

About