Cooperative Rendezvous Protocols for Improved Performance and Overlap

Chakraborty, Sourav; Bayatpour, Mohammadreza; Hashmi, Jahanzeb Maqbool; Subramoni, Hari; Panda, Dhabaleswar K.

doi:10.1109/sc.2018.00031

Cited by 7 publications

(1 citation statement)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, this scheme has to resend unexpected large messages in the presence of application skew, which does not affect our design. Chakraborty et al [7] investigate different approaches to increase the overlap of intra-node communication and computation with inter-node communication. As we can see, no work exists in literature that can provide maximum overlap of computation and communication in a communication-aware fashion while taking advantage of state-of-the-art solutions in hardware and software in an adaptive fashion as "CHAMPION" is able to do.…”

Section: Related Workmentioning

confidence: 99%

Communication-Aware Hardware-Assisted MPI Overlap Engine

Bayatpour

Maqbool

Chakraborty

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Overlap of computation and communication is critical for good application-level performance. Modern high-performance networks offer Hardware-assisted tag matching and rendezvous offload to enable communication progress without involving the host CPU. However, hardware based offload cannot be used in many situations due to various hardware limitations and performance issues. Furthermore, hardware-based designs cannot provide good overlap for common communication patterns involving unexpected messages or non-contiguous datatypes. In this paper, we address these limitations by designing a communication-aware overlap engine for MPI that uses novel hardware-assisted and softwarebased solutions to extract overlap for both expected and unexpected messages. The proposed design adapts to the application's communication requirements including message size, datatype, and relative timing of processes using heuristics and history-driven predictions. We evaluate the proposed designs against state-of-the-art MPI libraries and show up to 41% and 22% reduction in latency for collective operations and stencil-based application kernels on 1024 and 128 nodes, respectively, as well as 23% improvement in communication performance of the P3DFFT application.

show abstract

Section: Related Workmentioning

confidence: 99%

Communication-Aware Hardware-Assisted MPI Overlap Engine

Bayatpour

Maqbool

Chakraborty

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

Sparbit: Towards to a Logarithmic-Cost and Data Locality-Aware MPI Allgather Algorithm

Loch

Koslovski

2023

J Grid Computing

View full text Add to dashboard Cite

Exploiting copy engines for intra-node MPI collective communication

Cho,

Seo,

Jin

2023

J Supercomput

View full text Add to dashboard Cite

As multi/many-core processors are widely deployed in high-performance computing systems, efficient intra-node communication becomes more important. Intra-node communication involves data copy operations to move messages from source to destination buffer. Researchers have tried to reduce the overhead of this copy operation, but the copy operation performed by CPU still wastes the CPU resources and even hinders overlapping between computation and communication. The copy engine is a hardware component that can move data between intra-node buffers without intervention of CPU. Thus, we can offload the copy operation performed by CPU onto the copy engine. In this paper, we aim at exploiting copy engines for MPI blocking collective communication, such as broadcast and gather operations. MPI is a messaging-based parallel programming model and provides point-to-point, collective, and one-sided communications. Research has been conducted to utilize the copy engine for MPI, but the support for collective communication has not yet been studied. We propose the asynchronism in blocking collective communication and the CE-CPU hybrid approach to utilize both copy engine and CPU for intra-node collective communication. The measurement results show that the proposed approach can reduce the overall execution time of a microbenchmark and a synthetic application that perform collective communication and computation up to 72% and 57%, respectively.

show abstract

Cooperative Rendezvous Protocols for Improved Performance and Overlap

Cited by 7 publications

References 32 publications

Communication-Aware Hardware-Assisted MPI Overlap Engine

Communication-Aware Hardware-Assisted MPI Overlap Engine

Sparbit: Towards to a Logarithmic-Cost and Data Locality-Aware MPI Allgather Algorithm

Exploiting copy engines for intra-node MPI collective communication

Contact Info

Product

Resources

About