- This event has passed.
LANS Informal Seminar: Jan Huckelheim
November 9, 2017 @ 13:00 CST
Seminar Title: Reverse-differentiation of shared-memory parallel code
Speaker: Jan Huckelheim, Postdoctoral Researcher, Imperial College, London
Date/Time: 2017-11-09 13:00
Location: Bldg. 241, D173
Description:
Adjoint derivatives reveal the sensitivity of a computer program’s output to changes in its inputs. These derivatives are useful e.g. in optimisation. Algorithmic differentiation (AD) is an established method to transform a given computation into its corresponding adjoint computation. A key challenge in this process is the efficiency of the resulting adjoint computation. This becomes especially pressing with the increasing use of shared-memory parallelism on multi- and many-core architectures, for which AD support is currently insufficient.
This talk will give an overview of challenges and solutions for the differentiation of shared-memory-parallel code, using two examples: an unstructured-mesh CFD solver, and a structured-mesh stencil kernel, both parallelised with OpenMP. The methods shown in this talk result in AD-generated adjoint solvers that scale as well as their underlying original solvers on CPUs and a KNC XeonPhi.