FFTc is a Domain-Specific Language (DSL) for designing and generating Fast Fourier Transforms (FFT) libraries. The FFTc uniqueness is that it leverages and extend Multi-Level Intermediate Representation (MLIR) dialects to optimize FFT code generation. In this work, we present FFTc extensions and improvements such as the possibility of using different data layout for complex-value arrays, and sparsification to enable efficient vectorization, and a seamless porting of FFT libraries to GPU systems. We show that, on CPUs, thanks to vectorization, the performance of the FFTc-generated FFT is comparable to performance of FFTW, a state-of-the-art FFT libraries. We also present the initial performance results for FFTc on Nvidia GPUs.
Cite
@article{arxiv.2308.00497,
title = {Leveraging MLIR for Loop Vectorization and GPU Porting of FFT Libraries},
author = {Yifei He and Artur Podobas and Stefano Markidis},
journal= {arXiv preprint arXiv:2308.00497},
year = {2023}
}