Speaker
Jiří Vyskočil
(Czech Technical University in Prague)
Description
Large scale scientific computing raises questions on different levels ranging from the fomulation of the problems to the choice of the best algorithms and their implementation for a specific platform. There are similarities in these different topics that can be exploited by modern-style C++ template metaprogramming techniques to produce readable, maintainable and generic code. Traditional low-level code tend to be fast but platform-dependent, and it obfuscates the meaning of the algorithm. On the other hand, object-oriented approach is nice to read, but may come with an inherent performance penalty.
These lectures aim to present he basics of the Expression Template (ET) idiom which allows us to keep the object-oriented approach without sacrificing performance. We will in particular show to to enhance ET to include SIMD vectorization. We will then introduce techniques for abstracting iteration, and introduce thread-level parallelism for use in heavy data-centric loads. We will show to to apply these methods in a way which keeps the "front end" code very readable.
---
LECTURE 1
In this lecture, we will have a quick look at the basics of Template Metaprogramming - how does the computing handle "types", and how these types map more or less naturally to physical quantities. We will then introduce the idea of using Expression Templates (ET) as a means to bride the gap between the low-level high-performance approach, and the object-oriented, readable but often severely under-performing approach. We will study the structure of the ETs, and show the basic steps needed to build them.
