Coalesced communication: a design pattern for complex parallel scientific software
This work addresses performance bottlenecks in high-performance parallel scientific software, particularly for domain-specific applications like blood flow simulations, and is incremental as it builds on existing communication methods.
The authors tackled the problem of communication overhead in parallel scientific software by introducing a new design pattern called coalesced communication, which reduced communication overhead by approximately 40% in simulations of a lattice-Boltzmann blood flow solver with streaming visualization.
We present a new design pattern for high-performance parallel scientific software, named coalesced communication. This pattern allows for a structured way to improve the communication performance through coalescence of multiple communication needs using two communication management components. We apply the design pattern to several simulations of a lattice-Boltzmann blood flow solver with streaming visualisation which engenders a reduction in the communication overhead of approximately 40%.