Design by Transformation: Application to Dense Linear Algebra Libraries
23 May 2012
Talk by Robert van de Geijn on 1 June (2pm) in the Frank Adams Seminar Room, Alan Turing Building.
Professor Robert van de Geijn will be visiting the UK in June and will deliver the above talk to the Numerical Algorithm and High Performance Computing Network in the School of Mathematics on 1 June.
The talk will take place at 2pm in the Frank Adams Seminar Rooms of the Alan Turing Building.
The talk is open to all, but please confirm attendance by email to:
Abstract
The FLAME project has yielded modern alternatives to LAPACK and related effort. An attractive feature of this work is the complete vertical integration of the entire software stack, starting with low level kernels that support the BLAS and finishing with a new distributed memory library, Elemental. In between are layers that target a single core, multicore, and multiGPU architectures.
What this now enables is a new approach where libraries are viewed not as instantiations in code but instead as a repository of algorithms, knowledge about those algorithm, and knowledge about target architectures. Representations in code are then mechanically generated by a tool that performs optimizations for a given architecture by applying high-level transformations much like a human expert would.
We discuss how this has been used to mechanically generate tens of thousands of different distributed memory implementations given a single sequential algorithm. By attaching cost functions to the component operations, a highly optimized implementation is chosen by the tool. The chosen optimization invariably matches or exceeds the performance of implementations by human experts. We call the underlying approach Design by Transformation (DxT).