Copyrights to these papers may be held by the publishers. The download files are preprints. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

N. Zhang, Sanil Rao, M. Franusich and Franz Franchetti (Proc. ACM SIGPLAN Symposium on Principles of Programming Languages (POPL), 2025)
Towards Semantics Lifting for Scientific Computing: A Case Study on FFT
Comment: Theory and Practice of Static Analysis Workshop (TPSA)
Preprint (554 KB)
Bibtex

The rise of automated code generation tools, such as large language models (LLMs), has introduced new challenges in ensuring the correctness and efficiency of scientific software, particularly in complex kernels, where numerical stability, domain-specific optimizations, and precise floating-point arithmetic are critical. We propose a stepwise semantics lifting approach using an extended SPIRAL framework with symbolic execution and theorem proving to statically derive high-level code semantics from LLM-generated kernels. This method establishes a structured path for verifying the source code’s correctness via a step-by-step lifting procedure to high-level specification. We conducted preliminary tests on the feasibility of this approach by successfully lifting GPT-generated fast Fourier transform code to high-level specifications.

Keywords:
Fast Fourier Transform, SPIRAL, FFT, Semantics, Scientific computing, Static analysis, Semantics lifting