« on: July 05, 2013, 11:01:23 AM »
This section allows you to view all posts made by this member. Note that you can only see posts made in areas you currently have access to.
LibreOffice and AMD are working together to create a faster version of the office suite's spreadsheet that will make use of AMD's GPUs within its Heterogeneous System Architecture (HSA) based Accelerated Processing Units (APUs). The work is only just beginning though and there is no timescale for a production release of the software. AMD is joining the LibreOffice Advisory Board as part of the collaboration, sitting alongside Google, Intel, Red Hat, SUSE and the FSF, among others.
At its core, the aim of the work is to take the formulae of Calc spreadsheets, convert them into OpenCL, compile that OpenCL for the GPU and execute those formulae through the GPU. In a typical PC architecture, this would be rather complex because of the difficulty of feeding a large amount of data to the GPU through small memory apertures, but with AMD's HSA, the CPU and GPU have equal access to memory, resulting in an easier environment in which to GPU accelerate applications.
I’m very happy to announce that Qt 5.1 is now available. It has taken us a little more then 6 months since we released Qt 5.0 end of last year. While we originally planned that Qt 5.1 will mainly focus on bug fixing and stability of Qt 5.0, we have actually achieved a lot more. The release contains a large amount of new functionality in addition to numerous smaller improvements and bug fixes. For more information, please have a look at our Qt 5.1 launch page.
The final version of 2013 will also include a few C99 features. Microsoft has long avoided supporting C99, the major update to C++'s predecessor that was standardized last millennium, claiming that there was little demand for it among Visual Studio users. This was true, but only to a point; it's true that many Windows developers weren't especially interested in C99 because they had no good tooling to support it. Open source developers, however, embraced the update, as it makes C a lot less awkward to work with.
After 2013 is released, a CTP will deliver a bunch more C++11 features, with C++14's generic lambdas and return type deduction likely to be included, along with a selection of C++11 features. The remaining C++11 and C++14 features will be implemented in subsequent releases (as will a couple of C++98 features that Visual Studio doesn't quite get right).
LLVM 3.3 is also a major milestone for the Clang frontend: it is now fully C++'11 feature complete. At this point, Clang is the only compiler to support the full C++'11 standard, including important C++'11 library features like std::regex. Clang now supports Unicode characters in identifiers, the Clang Static Analyzer supports several new checkers and can perform interprocedural analysis across C++ constructor/destructor boundaries, and Clang even has a nice "C++'11 Migrator" tool to help upgrade code to use C++'11 features and a "Clang Format" tool that plugs into vim and emacs (among others) to auto-format your code.
Recently, Intel announced the release of the Intel® SDK for OpenCL Applications 2013 with certified OpenCL* 1.2 support on 3rd and 4th generation Intel® Core™ processors with Intel® Iris Graphics and Intel® HD Graphics family. Visual computing applications like content creation, home movies, music, and personal images will benefit from the value of OpenCL general purpose programmability combined with access to the combined power of the CPU and the hardware acceleration capabilities of Intel® Iris Graphics and Intel® HD Graphics to increase performance and improve battery life.
In fact, with the launch of the 3rd generation Intel® Core™ processors, Intel has made it possible for software developers to heterogeneously program both CPU and Intel HD Graphics through the OpenCL* framework.
This article documents lessons learned while accelerating video processing with OpenCL* on the 3rd generation Intel® Core™ processors. Common video effects in a commercial application were optimized with OpenCL, and then evaluated on Intel® HD Graphics 4000. Using OpenCL, key video effects were sped up by as much as 2.3x, and with further tuning for Intel® HD Graphics 4000, additional performance gains of up to 4.3x were achieved.
Many of the lessons learned and documented in this article are also applicable to the new versions of Intel® Iris Graphics and Intel® HD Graphics family.
start GpuTest.exe /test=fur /width=1280 /height=720 /msaa=4 /fullscreen /benchmark /benchmark_duration_ms=60000
Windows 8.1 will advance the bold vision set forward with Windows 8 to deliver the next generation of PCs, tablets, and a range of industry devices, and the experiences customers — both consumers and businesses alike — need and will just expect moving forward. It’s Windows 8 even better. Not only will Windows 8.1 respond to customer feedback, but it will add new features and functionality that advance the touch experience and mobile computing’s potential. Windows 8.1 will deliver improvements and enhancements in key areas like personalization, search, the built-in apps, Windows Store experience, and cloud connectivity. Windows 8.1 will also include big bets for business in areas such as management and security – we’ll have more to say on these next week at TechEd North America. Today, I am happy to share a “first look” at Windows 8.1 and outline some of the improvements, enhancements and changes customers will see.
Beachfront.iO "needs to service millions upon millions of requests a day, upwards of 5 to 10 thousand transactions per second and do this very reliably," Kuehnl said. "I was looking at different stacks and doing benchmarks to figure out how it would be most productive and most performant … and that's where I came across Go."
The code written in Go performs all the heavy lifting on the back end, including load balancing and choosing which ads to serve up when and where.
"The issue for PHP and even Node.js is obviously you're trapped in a single-threaded situation and what I really wanted was to be able to do a lot of things concurrently," Kuehnl continued. "My options were to go with something like Java, where you have more memory overhead, or I could go with something like Go that was built from the ground up for concurrency and using very modern patterns."
Kuehnl said Go combines those modern concurrency patterns with the "static execution speed of C or C++" but with "a more compositional feel, a script kind of feel. … I started first with the idea of trying to pick the most high-performance modern language, but as I explored it more the beauty of the language presented itself."
In March, readers followed along as Nate Anderson, Ars deputy editor and a self-admitted newbie to password cracking, downloaded a list of more than 16,000 cryptographically hashed passcodes. Within a few hours, he deciphered almost half of them. The moral of the story: if a reporter with zero training in the ancient art of password cracking can achieve such results, imagine what more seasoned attackers can do.
If you typically follow GPU performance as it related to gaming but have become curious about Bitcoin mining, you’ve probably noticed and been surprised by the fact that AMD GPUs are the uncontested performance leaders in the market. This is in stark contrast to the PC graphics business, where AMD’s HD 7000 series has been playing a defensive game against Nvidia’s GK104 / GeForce 600 family of products. In Bitcoin mining, the situation is almost completely reversed — the Radeon 7970 is capable of 550MHash/second, while the GTX 680 is roughly 1/5 as fast.
It's what we've always envisioned for Leap Motion — to break down the barriers between people and technology. Here's a video to show you how close we are. With Leap Motion technology, Windows OS is natural, easy, and fun to use. You'll navigate your desktop, browse the web, flip through photos, and do everything you do everyday in extraordinary ways —all with the wave of a hand or lift of a finger.
Modern GPU is code and commentary intended to promote new and productive ways of thinking about GPU computing.
This project is a library, an algorithms book, a tutorial, and a best-practices guide. If you are new to CUDA, start here. If you're already familiar with CUDA, are ready for a challenge, and want to learn design patterns for parallel programming, enjoy this series.