Argonne National Laboratory

Efficient Generated Libraries for Asynchronous Derivative Computation

TitleEfficient Generated Libraries for Asynchronous Derivative Computation
Publication TypeConference Paper
Year of Publication2010
AuthorsBuntinas, D, Malozemoff, A, Utke, J
Conference NameProcedia Computer Science, Proc. ICCS 2010
Date Published05/2010
PublisherElsevier B.V.
Conference LocationAmsterdam, Netherlands
Other NumbersANL/MCS-P1717-0110

The computation of derivatives via automatic di fferentiation is a valuable technique in many science and engineering applications. While the implementation of automatic di fferentiation via source transformation yields the highest-efficiency results, the implementation via operator overloading remains a viable alternative for some application contexts, such as the computation of higher-order derivatives or in cases where C++ still proves to be too complicated for the currently available source transformation tools. The Rapsodia code generator creates libraries that overload intrinsics for derivative computation. In this paper, we discuss modifications to Rapsodia to improve the efficiency of the generated code, first via limited loop unrolling and second via multithreaded asynchronous derivative computation. We introduce the approaches and present run time results.