Performance essentials using OpenMP* 4.0 vectorization with C/C++

Performance essentials using OpenMP* 4.0 vectorization with C/C++
Start: April 29, 2014
iCal Import

This webinar teaches you about Vectorization, what it is and why you should care about it as a software developer.

It will cover terms such as SIMD and vectorization, Vector Lanes, Vector Length and discusses performance expectations per core.

It will also explores the tradeoff between using compiler autovectorization versus explicit vector programming versus SIMD intrinsics and assembly.

It compares explicit vector programming as being similar to explicit parallel programming using OpenMP parallelism constructs, where the developer takes control and responsibility for vectorizing specified loops.

Also gives quick examples of the two big ideas in explicit vector programming: omp SIMD loops, and SIMD-enabled functions enabled with the pragma omp declare simd family of constructs.

Register

Source: Intel
TAGS:
CATEGORY: Events, Webinars
 
 

Popular posts

Related posts