Broadcast Trees for Heterogeneous Platforms

Beaumont, Olivier; Marchal, Loris; Robert, Yves

doi:10.1109/ipdps.2005.131

Cited by 20 publications

(30 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The multiple tree approach in [3] uses linear programming to determine the maximum multicast throughput given the bandwidth of links between hosts, but requires a very complicated algorithm to derive the set of multicast trees that would achieve that throughput. Therefore, the linear programming solution is only used to optimize the throughput of a single multicast tree.…”

Section: Optimization Of Multicast Treesmentioning

confidence: 99%

See 1 more Smart Citation

Balanced Multicasting: High-throughput Communication for Grid Applications

Burger

Kielmann²,

Bal³

ACM/IEEE SC 2005 Conference (SC'05)

View full text Add to dashboard Cite

Many grid applications need to transfer large amounts of data between the geographically distributed sites of a grid environment. Network heterogeneity between these sites makes throughput optimization of data transfers to multiple sites (multicast) hard or even impossible. We present a technique called balanced multicasting that uses monitoring information for both bandwidth capacity and achievable bandwidth to compute balanced multicast trees at runtime that use application-level traffic shaping at the sender side to avoid self-induced congestion. Our experimental evaluation shows that our approach outperforms existing multicast strategies by large margins.

show abstract

Section: Optimization Of Multicast Treesmentioning

confidence: 99%

“…Unlike with other approaches (e.g., [3]), it is not necessary to construct trees from the result of our linear program. This is because its input already consists of a set of trees, computed by the FPFR algorithm.…”

Section: Algorithmmentioning

confidence: 99%

Balanced Multicasting: High-throughput Communication for Grid Applications

Burger

Kielmann²,

Bal³

ACM/IEEE SC 2005 Conference (SC'05)

View full text Add to dashboard Cite

show abstract

“…Finding an efficient k-ary tree taking into account the topology of the NoC is a complex problem [4] and it is orthogonal to the design of OC-Bcast. It is outside the scope of this paper since our goal is to show the advantage of using RMA to implement broadcast.…”

Section: Principle Of the Broadcast Algorithmmentioning

confidence: 99%

High-performance RMA-based broadcast on the intel SCC

Petrović

Shahmirzadi

Ropars

et al. 2012

Proceedings of the Twenty-Fourth Annual ACM Symposium on Parallelism in Algorithms and Architectures

View full text Add to dashboard Cite

Many-core chips with more than 1000 cores are expected by the end of the decade. To overcome scalability issues related to cache coherence at such a scale, one of the main research directions is to leverage the message-passing programming model. The Intel Single-Chip Cloud Computer (SCC) is a prototype of a message-passing many-core chip. It offers the ability to move data between on-chip Message Passing Buffers (MPB) using Remote Memory Access (RMA). Performance of message-passing applications is directly affected by efficiency of collective operations, such as broadcast. In this paper, we study how to make use of the MPBs to implement an efficient broadcast algorithm for the SCC. We propose OC-Bcast (On-Chip Broadcast), a pipelined k-ary tree algorithm tailored to exploit the parallelism provided by on-chip RMA. Using a LogP-based model, we present an analytical evaluation that compares our algorithm to the state-of-the-art broadcast algorithms implemented for the SCC. As predicted by the model, experimental results show that OC-Bcast attains almost three times better throughput, and improves latency by at least 27%. Furthermore, the analytical evaluation highlights the benefits of our approach: OC-Bcast takes direct advantage of RMA, unlike the other considered broadcast algorithms, which are based on a higher-level send/receive interface. This leads us to the conclusion that RMA-based collective operations are needed to take full advantage of hardware features of future message-passing many-core architectures.

show abstract

“…In [1,2], heuristics for pipelined communication on heterogeneous clusters were devised. These heuristics focus on the heterogeneity of links and nodes, but not the network contention issue.…”

Section: Related Workmentioning

confidence: 99%

Techniques for pipelined broadcast on ethernet switched clusters

Patarasuk

Yuan

Faraj³

2008

Journal of Parallel and Distributed Computing

View full text Add to dashboard Cite

By splitting a large broadcast message into segments and broadcasting the segments in a pipelined fashion, pipelined broadcast can achieve high performance in many systems. In this paper, we investigate techniques for efficient pipelined broadcast on clusters connected by multiple Ethernet switches. Specifically, we develop algorithms for computing various contention-free broadcast trees that are suitable for pipelined broadcast on Ethernet switched clusters, extend the parametrized LogP model for predicting appropriate segment sizes for pipelined broadcast, show that the segment sizes computed based on the model yield high performance, and evaluate various pipelined broadcast schemes through experimentation on Ethernet switched clusters with various topologies. The results demonstrate that our techniques are practical and efficient for contemporary fast Ethernet and Giga-bit Ethernet clusters.

show abstract

Broadcast Trees for Heterogeneous Platforms

Cited by 20 publications

References 32 publications

Balanced Multicasting: High-throughput Communication for Grid Applications

Balanced Multicasting: High-throughput Communication for Grid Applications

High-performance RMA-based broadcast on the intel SCC

Techniques for pipelined broadcast on ethernet switched clusters

Contact Info

Product

Resources

About