Towards Verified Compilation of Floating-point Optimization in Scientific Computing Programs

📅 2025-09-10
📈 Citations: 0
Influential: 0
📄 PDF

career value

205K/year
🤖 AI Summary
Scientific computing programs rely on aggressive floating-point optimizations—such as fused multiply-add (FMA)—to improve performance, yet must rigorously preserve numerical correctness. Method: This work presents the first formal verification of FMA optimization at the LLVM IR level within the Rocq theorem prover, built upon the Verified LLVM framework. It formally models IEEE 754-compliant floating-point semantics in LLVM IR, enables path-sensitive, precise preservation reasoning, and designs a scalable verification architecture to accommodate more complex program structures and optimization patterns. Contribution/Results: The approach proves semantic equivalence for FMA replacements of arithmetic expressions of the form $a imes b + c$ within basic blocks. Experimental validation confirms the mathematical correctness of FMA substitution, establishing the first end-to-end, IR-level formal verification of floating-point optimizations for trustworthy high-performance compilers.

Technology Category

Application Category

📝 Abstract
Scientific computing programs often undergo aggressive compiler optimization to achieve high performance and efficient resource utilization. While performance is critical, we also need to ensure that these optimizations are correct. In this paper, we focus on a specific class of optimizations, floating-point optimizations, notably due to fast math, at the LLVM IR level. We present a preliminary work, which leverages the Verified LLVM framework in the Rocq theorem prover, to prove the correctness of Fused-Multiply-Add (FMA) optimization for a basic block implementing the arithmetic expression $a * b + c$ . We then propose ways to extend this preliminary results by adding more program features and fast math floating-point optimizations.
Problem

Research questions and friction points this paper is trying to address.

Verifying correctness of floating-point compiler optimizations
Ensuring accuracy in scientific computing program transformations
Proving Fused-Multiply-Add optimization validity mathematically
Innovation

Methods, ideas, or system contributions that make the work stand out.

Leveraging Verified LLVM framework
Proving FMA optimization correctness
Extending to more optimizations
🔎 Similar Papers
No similar papers found.
M
Mohit Tekriwal
Lawrence Livermore National Laboratory, Livermore, CA, USA
J
John Sarracino
Lawrence Livermore National Laboratory, Livermore, CA, USA