Portals 3.0: protocol building blocks for low overhead communication

Brightwell, Ron; Riesen, Rolf; Lawry, B.; Maccabe, A.B.

doi:10.1109/ipdps.2002.1016564

Cited by 54 publications

(39 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The server coordinates the sending and receiving of these large data segments, so it is not overwhelmed by client requests. Nessie currently has implementations for Portals-based networks [7], such as those for the Cray XT series, and InfiniBand networks.…”

Section: Rpc Librarymentioning

confidence: 99%

See 1 more Smart Citation

Lightweight storage and overlay networks for fault tolerance.

Oldfield¹

2010

View full text Add to dashboard Cite

The next generation of capability-class, massively parallel processing (MPP) systems is expected to have hundreds of thousands to millions of processors, In such environments, it is critical to have fault-tolerance mechanisms, including checkpoint/restart, that scale with the size of applications and the percentage of the system on which the applications execute. For application-driven, periodic checkpoint operations, the state-of-the-art does not provide a scalable solution. For example, on today's massive-scale systems that execute applications which consume most of the memory of the employed compute nodes, checkpoint operations generate I/O that consumes nearly 80% of the total I/O usage. Motivated by this observation, this project aims to improve I/O performance for application-directed checkpoints through the use of lightweight storage architectures and overlay networks. Lightweight storage provide direct access to underlying storage devices. Overlay networks provide caching and processing capabilities in the compute-node fabric. The combination has potential to signifcantly reduce I/O overhead for large-scale applications. This report describes our combined efforts to model and understand overheads for application-directed checkpoints, as well as implementation and performance analysis of a checkpoint service that uses available compute nodes as a network cache for checkpoint operations.3

show abstract

Section: Rpc Librarymentioning

confidence: 99%

“…Each of the six links from each node can support 2.5GB/s, after protocol overheads . Low-level software access to the interconnects is provided through the Portals library [7], which provides a connectionless RDMA-based interface.…”

Section: Red Stormmentioning

confidence: 99%

Lightweight storage and overlay networks for fault tolerance.

Oldfield¹

2010

View full text Add to dashboard Cite

show abstract

“…The advantages of this form of offloading have been well established. In previous work, we have presented arguments for pushing more protocol information onto the network interface in order to better support upper-level transport protocols, and we have presented an architecture that provides the basic building blocks for constructing protocols for many different higherlevel programming interfaces [5].…”

Section: Motivationmentioning

confidence: 99%

“…For example, in [17] portions of a Portals [5] stack were offloaded. Similarly, the Quadrics network [20] offloads the MPI matching stack onto the network interface, and others have explored this approach for Myrinet [29].…”

Section: Related Workmentioning

confidence: 99%

“…Indeed, eliminating the PCI bus from much of the MPI processing path has significant advantages. Numerous microbenchmarks have been used to illustrate the improvements in bandwidth and latency that can be achieved; thus, aggressive supercomputer designs such as Red Storm [1] have chosen to effectively offload most of the MPI matching semantics by using Portals [5]. It should be expected that with the growth in silicon area available to NICs that even more of the MPI stack will be absorbed; however, NIC-based programmable processors are currently much slower than their host processor counterparts.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An analysis of NIC resource usage for offloading MPI

Brightwell

Underwood

18th International Parallel and Distributed Processing Symposium, 2004. Proceedings.

Self Cite

View full text Add to dashboard Cite

show abstract

Architectural specification for massively parallel computers: an experience and measurement‐based approach

Brightwell

Camp

Cole

et al. 2005

Concurrency and Computation

View full text Add to dashboard Cite

SUMMARYIn this paper, we describe the hardware and software architecture of the Red Storm system developed at Sandia National Laboratories. We discuss the evolution of this architecture and provide reasons for the different choices that have been made. We contrast our approach of leveraging high-volume, mass-market commodity processors to that taken for the Earth Simulator. We present a comparison of benchmarks and application performance that support our approach. We also project the performance of Red Storm and the Earth Simulator. This projection indicates that the Red Storm architecture is a much more cost-effective approach to massively parallel computing. Published in 2005 by John Wiley & Sons, Ltd.

show abstract

Portals 3.0: protocol building blocks for low overhead communication

Abstract: Abstract

Cited by 54 publications

References 25 publications

Lightweight storage and overlay networks for fault tolerance.

Lightweight storage and overlay networks for fault tolerance.

An analysis of NIC resource usage for offloading MPI

Architectural specification for massively parallel computers: an experience and measurement‐based approach

Contact Info

Product

Resources

About