Displaying items by tag: nVidia

The average GPU is a pretty powerful computational device. The highly parallel design and efficient memory structure means that you can execute operations at a rate that puts most CPUs to shame. With the advent of Cuda and OpenCL the door was opened for developers to push workloads to the GPU and get back some pretty nice returns. Microsoft and many others joined in and began making access to the GPU simpler starting with DirectX 10.

As most people are aware, AMD dropped the first GPUs to utilize HBM (High Bandwidth Memory). These GPUs use a form of HBM called 2.5D which requires the use of an interproser layer than both the memory and the GPU sit on. This is opposed to the 3D stack in which the memory sits on top of the processor that owns it. The traditional stacking of 3D Memory provides significant performance benefits, but would require a different chip for every memory density you plan on releasing. In the GPU world this can be a big problem and is why both AMD and NVIDIA have opted for the 2.5D method.

It seems that at least one person is rather annoyed at AMD for making claims about certain FX series CPUs running Bulldozer cores. On November 4th the news went out that Tony Dickey had filed a class-action lawsuit on behalf of himself and others. The suit was actually filed back on October 26th and alleges violations of the Consumer Legal Remedies Act. This act covers misrepresentation and false advertising. Dicky alleges that AMD knowing mislead consumers about the number of functional cores Bulldozer CPUs have. AMD claims that Bulldozer has eight independent cores, Dickey says that there are only four that are functional.

The idea of the “cloud” is nothing new and has, in fact, been around for a number of years in one form or another. The concept goes back to the use of small “dumb” terminals that were nothing more than display devices for com putting done in a central location. After it became possible to put more power into the systems we used the cloud faded into the back ground. With the production of mobile devices that did not typically have the same power and capacity as a desktop the cloud returned. It had a major resurgence when the smartphone and tablet leaped onto the scene and now it seems that everything is trying to become cloud based; including gaming.

Last week there was an announcement by Global Foundries that they were licensing Samsung’s 14nm FinFET process for their own use. This immediately started the internet going with talk about how AMD would be using this new process despite there not being any indication that AMD was ready for 14nm for APUs, CPUs, or GPUs for that matter. Now, in true internet fashion the rumor mill has shifted from AMD to NVIDIA. The claim is that NVIDIA will soon utilize Samsung’s 14nm FinFET tech too.

During NVIDIA’s recent GTC announcements the world was shown the new Titian X with 12GB of GDDR5. This impressive monster of a card has shown that it has a large amount of power to push your games and other graphical information. While the Titian X received adoration and several very positive reviews from the technical press there was another story that was also very important. This was the conversation about NVIDIA’s next GPU, Pascal.

It seems that the little “error” that was made when listing the specifications of NVIDIA’s GTX970 it getting ugly. A Law firm in Alabama has taken a single complaint and request for monetary compensation and pulled it into a full blown class action law suit against both NVIDIA and Gigabyte. For those of you that have been living under a rock for the last couple of months, where is a summary of the issue.

CES 2015 – Las Vegas NV

At the Consumer Electronics Show, nVidia showed off something that was interesting, but also confusing: The Tegra X1. This is a Maxwell based version of the Tegra that sports 256 Maxwell GPU cores, an 8-core 64-Bit CPU and is capable of pushing 4k 60Hz 10-Bit video in either H.265 or VP9. This new member of the Tegra family was hailed by nVidia CEO Jen-sun Huang as the first mobile superchip for its expected performance. Of course nVidia has always like to use the term “super” when talking about new products. I can remember them trying to coin the term Super Phone when Tegra 2 hit the market.

The US patent system is broken. There is not really much more to say about that it is and has been broken for many years and probably will continue to be broken for many years to come. Now why am I bringing this up? Well in looking over the way patents are filed, processed, and approved you will find that there are a large number of patents that are essentially the same thing just with a little twist. This type of patent allows for someone to put a legal hold on a very broad concept and then comeback and sue someone at a later date. Over the last few years we have watched a number of companies work the system with this type of patent and worse.

When I first started covering the computer world the most common resolution was 640x680 with the hard core gamers getting 800x600. The dream of the day, which some called the golden age of gaming, was 1600x1200 with around 30Fps. Now the dream is “photo realistic” resolutions without the need for heavy anti-aliasing and texture filtering. Even in the mobile world this is becoming a bigger issue with retina displays on the Apple side of the world and 3 and 4k screens on the PC side.