Phopojijo writes: While it looks like utilizing multiple GPUs in DirectX 12 will take off, much of this setup was exposed to game developers for years. Previously, it was held back by the low number of machines with (available) mismatched graphics, the lack of compute shader support in consoles, and the difficulty in using OpenCL for a video game product. While the editorial elaborates on each of these points, it doesn't mention Explicit Linked Multiadapter in DirectX 12, which allows game developers to make similar assumptions that AMD and NVIDIA do for CrossFire and SLI, respectively, making their job even easier.
Phopojijo writes: Guennadi Riguer, chief architect of Mantle at AMD, answered a few questions about the technical details of their new graphics API. Of particular note, he discussed the potential for game developers to load balance across mismatched Mantle-supporting GPUs (for example, if an end user purchased a new video card and installed it alongside their old one). He also discussed how the graphics pipeline is evolving and the possibility of fixed-function hardware doing the same.
Phopojijo writes: So, you can encrypt your password library using a client-side manager or encrypted file container. You could practice your password every day, keep no written record, and do everything else right. You then go in for a serious operation or get in a terrible accident and, when you wake up, suffer severe memory loss. Slashdot readers, what do you consider an acceptable trade-off between proper security and preventing a data-loss catastrophe? I will leave some details and assumptions up to interpretation (budget, whether you have friends or co-workers to rely on, whether your solution will defend against the Government, chance of success, and so forth). For instance, would you split your master password in pieces and pay an attourney to contact you with a piece of it in case of emergency? Would you get a safe deposit box? Some biometric device? Leave the password with your husband, wife, or significant other? What can Slashdot come up with?
Phopojijo writes: The recently released AMD Radeon R9 290X has an advertised shader clock rate of "up to 1GHz". The card brought formerly $1000-level performance down to a $550 price point. Its benchmarks tend to fluctuate wildly, however, based on the card's ability to maintain an intended maximum temperature of 95C. By analyzing across a variety of fan speeds, AMD's default settings are characteristic of a 727 MHz base clock with an average boost to 850-880 MHz. At these defaults, the card will not maintain 1GHz for more than a couple of minutes (or less).
Phopojijo writes: A monitor redraws itself top to bottom because of how the electron guns in CRT monitors used to operate. VSync was created to align the completed frames, computed by a videocard, to the start of each monitor draw; without it, midway through a monitor's draw process, a break (horizontal tear) would be visible on screen between the two time-slices of animation.
Pixels on LCD monitors do not need to wait for above lines of pixels to be drawn, but they do. G-Sync is a technology from NVIDIA to make monitor refresh rates variable. The monitor will time its draws to whenever the GPU is finished rendering. A scene which requires 40ms to draw will have a smooth "framerate" of 25FPS instead of trying to fit in some fraction of 60 FPS.
Phopojijo writes: OpenGL and DirectX have been the dominant real-time graphics APIs for decades. Both are catalogs of functions which convert geometry into images using predetermined mathematical algorithms (scanline rendering, triangles, etc.). Software rendering engines calculate colour values directly from the fundamental math. Reliance on OpenGL and DirectX could diminish when GPUs are utilized as general "large batches of math" solvers which software rendering engines offload to. Developers would then be able to choose their algorithms for best suits their project, even native to web browsers with the upcoming WebCL.
Phopojijo writes: "Art of the past only persists today because they were based on timeless platforms such as canvas and inks. Fans want their medium to be art and will fight any critic who refutes the artistic merits of video games. These gamers also ignore community-supported platforms in exchange for proprietary and often intentionally disposable ones such as consoles and DRM in the name of simplicity and fear over piracy or used sales. If video games are intrinsically valuable art – shouldn’t we be fighting for it to be accessible forever like all other art mediums by using platforms like Linux or BSD?"
Phopojijo writes: "To wrap up his “The Programmers Guide to a Universe of Possibility” keynote during the 2012 AMD Fusion Developer’s Summit, Phil Rogers of AMD announced the establishment of the HSA Foundation. The foundation has been instituted to create and maintain open standards to ease programming for a wide variety of processing resources including discrete and integrated GPUs. Founding members include ARM, Texas Instruments, Imagination, MediaTek, Texas Instruments, as well as AMD. Parallels can be drawn between this and AMD’s “virtual gorilla” initiative back from the late 1990’s."
Phopojijo writes: "It is easy to pass judgment on the netbook form factor but the problem was always its processing ability — the form factor just inherited the blame by association. Low-voltage adaptations of mainstream architectures will soon collide against ARM and leave low-power x86 architectures with no legitimate room to exist: “Intel is likely to continue on with Atom in computers, but only because it will be easy to offer the fruits of its smartphone endeavors in desktop and laptop PCs. There’s no particular reason for Intel to kill it but – in regards to laptops and desktops – there’s no reason for Intel to make it better.”"
Phopojijo writes: "Microsoft was at AMD's Fusion Developer Summit with a keynote this morning outlining Microsoft's part in the unified computing initiative. Currently your options for easily utilizing all your computing power are limited to Apple-founded OpenCL maintained by the Khronos Group. Microsoft's alternative is called C++ Accelerated Massive Parallelism (or C++ AMP). Microsoft was clear to announce that C++ AMP would be an open specification. Any interested compiler developer would be allowed to support this specification."
Phopojijo writes: "AMD kicked off their AMD Fusion Developer Summit 2011 today and reviews of their new Llano APU are starting to trickle out. The thought is that combining a GPU on the CPU decreases the barrier to entry to having a decent GPU in your system. While the CPU performance seemed to be a bit behind Intel's offering the GPU performance is definitely a step or more above Intel's offering."