Home » Blog » 2015 » April » CppCon 2014 Introduction to C++ AMP (GPGPU Computing)--Marc Gregoire

CppCon 2014 Introduction to C++ AMP (GPGPU Computing)--Marc Gregoire

By Adrien Hamelin | Apr 8, 2015 08:00 AM | Tags: performance

While we wait for CppCon 2015 in September, we’re featuring videos of some of the 100+ talks from CppCon 2014. Here is today’s feature:

Introduction to C++ AMP (GPGPU Computing)

by Marc Gregoire

(watch on YouTube) (watch on Channel 9)

Summary of the talk:

Meet C++ AMP (Accelerated Massive Parallelism), an abstraction layer on top of accelerators such as GPUs. In its current version it allows you to run code on any DX11 GPU, independent of the vendor, and it will even distribute workload across GPUs of different vendors simultaneously. C++ AMP was originally designed by Microsoft but is now an open standard. C++ AMP can deliver orders of magnitude performance increase with certain algorithms by utilizing the GPU to perform mathematical calculations. This talk will give a high level overview of what C++ AMP is and what it can do for you. It is time to start taking advantage of the computing power of GPUs!

Add a Comment

Comments are closed.

Comments (1)

0 0

Yakk said on Apr 8, 2015 11:41 AM:

In my experience, the requirement that your array_views be over int (32 bit) or larger types renders AMP quite annoying to use. And quick per-byte work looked 2x or more slower than the equivalent OpenCL code.

The idea of embedding a restricted subset of C++ is a good one. I'm looking forward to SYCL or something similar that hopefully does a better job.