Collective-Optimized FFTs
Evelyn Namugwanya, Amanda Bienz, Derek Schafer, Anthony Skjellum
TL;DR
This paper evaluates different alltoallv communication methods within Beatnik, a Z-model solver reliant on FFTs, to understand their impact on performance.
Contribution
It provides an analysis of alltoallv methods' effects on FFT-based application performance using Beatnik as a benchmark.
Findings
Certain alltoallv methods significantly improve FFT performance
Performance bottlenecks are identified in specific communication strategies
Results guide optimal method selection for FFT applications
Abstract
This paper measures the impact of the various alltoallv methods. Results are analyzed within Beatnik, a Z-model solver that is bottlenecked by HeFFTe and representative of applications that rely on FFTs.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsParallel Computing and Optimization Techniques · Matrix Theory and Algorithms