Skip to main content

Aparapi

The massive scalability of modern GPUs has led to many things, from Bitcoin mining to folding@home, seti@home and various other general purpose tasks that involve huge amounts of number crunching. While not as flexible as CPUs, modern GPUs can be hugely scalable thanks to the massive number of stream processors they contain.

I've long been impressed by the technology, and long known that to implement something using it you can use CUDA and/or OpenCL. For about the same amount of time there have been low level Java wrappers too that mean you can execute OpenCL without resorting to native languages - even if it meant you had to write the OpenCL directly, as well as huge amounts of boilerplate code to interface with it. Of course, if you wanted your application to work in the real world, a completely separate load of code for it to fall back on if the device didn't support OpenCL was needed too.

For about the same amount of time, I've thought that what we really need is a near transparent layer in (insert high level language of your choice here) which manages all the boilerplate / fallback code, OpenCL generation etc. for you. Of course, I could have sat down and looked at implementing it myself but I decided to wait for someone to do the hard work for me, thinking that it was inevitable that they would.

Fortunately I was correct, a bit of digging around today turned up Aparapi. It's an initiative started by AMD that enables to bring GPGPU programming to the average Joe Java developer completely transparent (almost) of any OpenCL calls and boilerplate. All it requires is for you to write your code inside a fabricated closure (anonymous inner class at present) and then call an execute method for the number of times you want it to run, in parallel. You can get the index of your essentially parallelised *loop* from within the kernel and crunch away on the GPU.

When lambdas come out of course there will be less boilerplate still - essentially having compresssed the hundreds of lines previously required to do this sort of thing with no more than a couple. Suddenly we've gone from stupidly hard and not worth doing to about as easy as it can get.

I envision this to be the first, but most important (and arguably hardest, but perhaps that's because I'm not a low level guy) step in providing the sort of transparent GPGPU access to Java that I continually dream of. The next step would be for API designers to take advantage of this technology in turn to produce classes like ParallelBufferedImage for instance. When this comes then ordinary Java folk will be able to utilise hugely parallel operations without so much as lifting a finger. We won't have to do anything different and all such API lifting will be done in the background, creating a huge (in some cases) but near invisible performance boost, just using one class rather than another.

Following on from that, the final step if it really takes on would be for it to be included in the API as standard. Possible? Sure. Likely? Who knows, but if so then it'd truly expose GPGPU to the masses.

Of course, that doesn't prohibit playing around until my completely transparent API-level pipe dream comes into play. Me being me I haven't actually got an OpenCL compatible card to try it out (I tend to live in the past a bit on the gaming front) but am thinking of ordering one just to have a play! And next step (naturally) is to see what we can integrate into Quelea to potentially speed that up with GPU hardware. It might even make my idea of keystone correction in software viable, we shall see! Perhaps 2012 will bring us a few more developments. Watch this space!

Comments

Popular posts from this blog

The comprehensive (and free) DVD / Blu-ray ripping Guide!

Note: If you've read this guide already (or when you've read it) then going through all of it each time you want to rip something can be a bit of a pain, especially when you just need your memory jogging on one particular section. Because of that, I've put together a quick "cheat sheet" here  which acts as a handy reference just to jog your memory on each key step. I've seen a few guides around on ripping DVDs, but fewer for Blu-rays, and many miss what I believe are important steps (such as ensuring the correct foreign language subtitles are preserved!) While ripping your entire DVD collection would have seemed insane due to storage requirements even a few years ago, these days it can make perfect sense. This guide doesn't show you a one click approach that does all the work for you, it's much more of a manual process. But the benefits of putting a bit more effort in really do pay off - you get to use entirely free tools with no demo versions, it...

Draggable and detachable tabs in JavaFX 2

JavaFX currently doesn't have the built in ability to change the order of tabs by dragging them, neither does it have the ability to detach tabs into separate windows (like a lot of browsers do these days.) There is a general issue for improving TabPanes filed here , so if you'd like to see this sort of behaviour added in the main JavaFX libraries then go ahead and cast your vote, it would be a very welcome addition! However, as nice as this would be in the future, it's not here at the moment and it looks highly unlikely it'll be here for Java 8 either. I've seen a few brief attempts at reordering tabs in JavaFX, but very few examples on dragging them and nothing to do with detaching / reattaching them from the pane. Given this, I've decided to create a reusable class that should hopefully be as easy as possible to integrate into existing applciations - it extends from Tab, and for the most part you create it and use it like a normal tab (you can just add it...

Dropbox Java API

This code will no longer work! It uses the old v1 API, which has been turned off. See here for working code with the latest v2 API. As well as being useful as general cloud storage, dropbox also has an API that lets you access its contents programmatically. It's a straightforward REST API with a number of language specific libraries to make the going a bit easier. Java is included on the list of SDKs, but at present only Android is included on the list of tutorials. This can be somewhat frustrating because simple examples using Java are lacking. Fortunately, the process was described by Josh here . So I've taken it and implemented it in Java, and it seems to work. It's a very basic example that authenticates with dropbox then uploads a file called "testing.txt" containing "hello world." Of course, more functionality is available than this, but this is the hard part (at least I found working this bit out the hard part.) Once you've got your Dro...