With the release and announcement of Visual Studio 2012 RC , you get among other things an updated version of C++ AMP . Our goal was that you could recompile your Visual Studio 11 Beta projects with the Visual Studio 2012 RC bits, and see no breaking...

Tiling seems to be one of the hardest parts to grasp for newcomers to GPU programming. We have explained the motivation (potential additional performance through the use of tile_static memory) and mechanics of tiling (use the tiled overload of parallel_for_each...

We have seen in previous blog posts that C++ AMP provides a comprehensive set of asynchronous APIs which enable users to continue performing useful work on the current CPU thread while an operation (such as transferring data between host and accelerator...

Just before the Beta was released, we shared some links to external coverage for C++ AMP . That included press (that picked up the C++ AMP open spec announcement), and also 5 chosen links to content that demonstrated the author had experimented with C...

If you’ve not read previous posts in this series about auto-vectorization, you may want to begin at the beginning . This post will explain how to find out which loops in your C++ program were auto-vectorized. Here is an example program, stored...

Many of you have been wondering about availability of additional C++ AMP libraries. As part of the shipping product you already have C++ AMP which itself is a library, and also the C++ AMP Math library . But you have been asking about additional libraries...

A number of us who you already know through our blog posts (Daniel, David, Jerry, Lukasz, Paul, Simon, Weirong) will be in San Jose all this week for NVIDIA's GPU Technology Conference (GTC). We'll be hanging out in the Microsoft lounge waiting to show...

With C++ AMP, you can use the templated array or array_view to work with your data types in a strongly typed manner by passing it in as the element type. Sometimes, however, you might need to reinterpret the element type, typically to adapt data to an...

With C++ AMP, you can use array or array_view to work with data in a multi-dimensional way, which often reflects your algorithm more naturally. Sometimes, however, you might need to reshape the data to adapt data to an existing interface or to use data...

Hello my name is David Callahan, I am a Distinguished Engineer at Microsoft working in parallelism features including C++ AMP. In this post I’ll explain one of our design choices, and we’ll use it as a base for future posts to build on. ...

Hello, readers! The C++ AMP Development Team is looking for experienced, motivated developers to work on the next generation of C++ AMP.  Here’s the job description : Location: Redmond, WA, US Job Category: Software Engineering: Development Location...

Background The way to express sequential logic in asynchronous programming with PPLTasks is task continuation chain; however, there is no easy way to construct a loop of continuations with tasks. In many scenarios, an asynchronous loop can be useful;...

If you haven’t read previous posts in this series about auto-vectorization, you may want to begin at the beginning . In the last post, we explained the rules for C++ loop headers that make your code amenable to auto-vectorization; we might say...

I’m working with the patterns & practices team on a Metro style app with C++ and XAML called Hilo. Hilo is a basic photo viewing and tagging app that totally re-imagines Hilo for Windows 7 by embracing new form factors and experiences that Windows...

Some of you might wonder why we chose int versus unsigned int versus size_t in some of the C++ AMP API signatures, particularly those in index , extent , array , etc. In this blog post, let’s take a close look at these integral type choices. We...

If you haven’t read previous posts in this series about auto-vectorization, you may want to begin at the beginning . In this post, we look at those C++ loop patterns that the auto-vectorizer recognizes. We will start by explaining its rules for...

So far, we have showed you how to use textures in C++ AMP with a series of blog posts . In this post, inspired by our “Hello world in C++ AMP” post, I will share a “Hello World” example demonstrating the main ingredients of using textures in C++ AMP....

Whether you are speaking about C++ AMP at a big conference or at small user group, a nice touch is to distribute a 1-page C++ AMP flyer on the attendee chairs before your session. The flyer should provides quick facts (a short FAQ and answers) that everyone...

In my previous post we looked at the bits_per_scalar_element property of textures . In this blog post, we will see how to write data to such textures. We will also take a look at the overflow semantics during such writes i.e. what happens when we try...

In a previous post I described how to measure the performance of C++ AMP algorithms . This time, I would like to show you the importance of warming up the data, so you can accurately measure the elapsed time of any operation performed on it. In the...

I assume you have read previous posts in this blog about auto-vectorization, starting with auto-vectorization-overview . In this post, we will look at how the auto-vectorizer works. Here is a tiny program that calculates the cube of each element...

So far, we have already talked about how to construct textures , and moreover, how to construct textures by specifying the bits_per_scalar_element property . Further, we explained how to read from and write to textures in restrict(amp) code. In this post...

Do you want to become an expert developer in GPU computing using C++ AMP? What better way than to take a 4-day, deep-dive, hands-on, training course delivered by well-known GPU computing experts: Acceleware . In a small class room environment, you...

We have already talked about how array , array_view , texture , and writeonly_texture_view are captured and passed into a parallel_for_each for use on the accelerator_view . In this blog, I’m going to draw your attention to a pattern of data capturing...

We have already talked about textures including how to read from textures , and we have shown how to read from textures packed with sub-words . In this post, we‘ll show how to write to textures. Writing to a texture object Unlike concurrency::array ,...