Skip to Main content Skip to Navigation
New interface
Journal articles

Source-to-Source Automatic Differentiation of OpenMP Parallel Loops

Abstract : This paper presents our work toward correct and efficient automatic differentiation of OpenMP parallel worksharing loops in forward and reverse mode. Automatic differentiation is a method to obtain gradients of numerical programs, which are crucial in optimization, uncertainty quantification, and machine learning. The computational cost to compute gradients is a common bottleneck in practice. For applications that are parallelized for multicore CPUs or GPUs using OpenMP, one also wishes to compute the gradients in parallel. We propose a framework to reason about the correctness of the generated derivative code, from which we justify our OpenMP extension to the differentiation model. We implement this model in the automatic differentiation tool Tapenade and present test cases that are differentiated following our extended differentiation procedure. Performance of the generated derivative programs in forward and reverse mode is better than sequential, although our reverse mode often scales worse than the input programs.
Document type :
Journal articles
Complete list of metadata
Contributor : Laurent Hascoet Connect in order to contact the contributor
Submitted on : Monday, November 15, 2021 - 6:43:21 PM
Last modification on : Friday, November 18, 2022 - 9:26:16 AM


Files produced by the author(s)




Jan Hückelheim, Laurent Hascoët. Source-to-Source Automatic Differentiation of OpenMP Parallel Loops. ACM Transactions on Mathematical Software, 2021, 48 (1), ⟨10.1145/3472796⟩. ⟨hal-03429677⟩



Record views


Files downloads