Here you can find all of the information about AMD. This includes their CPU’s, as well as their GPU’s built by ATI and the related software like the Stream SDK. In addition, we have information regarding CrossFire and EyeFinity hardware systems.
You may also want to check out:
It’s been a long time coming, but AMD and NVidia have finally traded an olive branch and soon you’ll be able to drop your NVidia GPU’s in SLI configuration on an AMD-powered motherboard.
“Long term gamers probably remember that for a long time AMD offered great high-end CPUs, but in recent years, AMD’s stature as the preferred gaming CPU fell by the wayside and Intel CPUs have been the gamers’ choice. For this reason, we’ve only licensed SLI for motherboards with Intel chipsets,” Nvidia explains. “However, we’ve been recently hearing chants of “SLI for AMD CPUs”, and figured that now is a great time to do it.”
This is great for budget gamers, as AMD chipsets are typically a lot cheaper than their Intel counterparts and perform just as well (if not better in many cases), and matching them with NVidia GPU’s will make for some amazing gaming systems.
via Nvidia and AMD Hug It Out, SLI Coming to AMD Motherboards! – HotHardware.
The video compares an Intel Core i7-2600 CPU with an AMD 3510MX. The Intel CPU is a Sandy Bridge processor and has Intel HD 3000 graphics. The AMD quad-core processor A8-3510MX has Radeon HD 6620M graphics. Of course it shows that AMD’s Llano performs better.
AMD is getting ready to launch their new Radeon HD6450, a budget card targeted at all those poor souls suffering through integrated Intel graphics chips. It’s not exactly ‘high-end’, but for most people it’ll be well beyond what they’re going to use it for, making it a great entry card for gaming.
Ultra high-framerates with cutting edge titles may not be in the cards for Radeon HD 6450 owners, but because the 6450 uses AMD’s tried and true Catalyst drivers and offers full DX11 support, game compatibility and rendering quality should be much better than Intel’s integrated graphics solutions. And the Radeon HD 6450 also handles multimedia and video playback very well. The video engine on the 6450 offers hardware acceleration of Flash video and DivX, Edge Enhancement and De-Noise filters, and a number of other features available as part of the UVD engine in other 6000-series Radeons.
AMD is backpedaling on their earlier statements about DirectX and graphics API’s, stating that they were taken out of context. As I originally suspected, the number of developers eager (or willing?) to code to bare metal is a startling minority.
The previous interview claimed that developers want the API to “go away,” that it’s getting in the way of creating some truly amazing graphics. Huddy himself was even quoted saying that developers have admitted this in conversations. But in this latest interview, he said that only a handful of high-end gaming developers were looking to bypass DirectX and code directly to hardware.
“It’s not something most developers want,” he said. “If you held a vote among developers, they would go for DirectX or OpenGL, because it’s a great platform. It’s hard to crash a machine with Direct X, as there’s lots of protection to make sure the game isn’t taking down the machine, which is certainly rare especially compared to ten or fifteen years ago. Stability is the reason why you wouldn’t want to move away from Direct X, and differentiation is why you might want to.”
I’m sure some people want that kind of access to the hardware, but they’re predominantly in the research world. Most developers would happily trade away that tiny bit of performance for the ease of development and portability of a good api. I just don’t think DirectX is a particularly good API.
A somewhat controversial piece over on Bit-Tech mentions a comment from AMD’s developer relations manager where he says that many game developers just want the API to go away.
‘It’s funny,’ says AMD’s worldwide developer relations manager of its GPU division, Richard Huddy. ‘We often have at least ten times as much horsepower as an Xbox 360 or a PS3 in a high-end graphics card, yet it’s very clear that the games don’t look ten times as good. To a significant extent, that’s because, one way or another, for good reasons and bad – mostly good, DirectX is getting in the way.’ Huddy says that one of the most common requests he gets from game developers is: ‘Make the API go away.’
Now, I think there’s a bit of a miscommunication here. I sincerely doubt many game designers want to go back to the old days of IRQ21 and manually mapping pixels to memory spaces. I suspect the real comment is that ‘DirectX is a pain to deal with’ and ‘I want a more transparent & easy to use API’. Not that OpenGL is any better, but many developers want to be rid of the classis glTransform & rasterization commands and move to a new generation of API’s, as evidenced by the success of things like Unity and Ogre.
What do you think?
Triple-GPU systems are still a fair rarity in the consumer space, but frequently discussed and coveted by hard-core gamers all over. In a recent benchmark by Toms Hardware, they put NVidia’s Triple-SLI against AMD’s Crossfire 3-way to see which one performs better. Much to my own surprise, the AMD solution not only yields slightly better performance, but much better efficiently with a vastly lower power consumption and heat output.
CrossFire came out with a huge overall scaling lead over SLI, and removing the one title that didn’t reflect that average would have made the lead even bigger. Superior scaling allowed two mid-priced Radeon HD 6950s to approximate the performance of two higher-cost GeForce GTX 570s, while three HD 6950s took the performance win over three GTX 570s.
If these figures cross over into the Multi-GPU/single-PCB space like the basis of AMD and NVidia’s newest announcements, AMD could have a big win on it’s hands in CrossFire Scaling.
Triple-GPU Scaling: AMD CrossFire Vs. Nvidia SLI : Is Multi-GPU The Game Changer?.
AMD’s Shane Parfitt helps you set up AMD HD3D gaming in 60 seconds on an AMD Radeon graphics card.
Personally, I find these thins a bit disingenuous. If you have a 120 Hz 3-D TV that is HDMI 1.4a complaint, and if you have a suitable PC capable of supporting the Radeon card, and if you buy the TriDef software for $49.99, and if … well, you get the idea.
It is March 8th, and as we reported last week, the AMD Radeon HD 6990 is being released today. The Radeon HD 6990 has two Caymen GPUs. This is the same GPU found in the Radeon HD 6970. Essentially, the 6990 is running on-board CrossFire between the two GPUs. This gives it 3072 stream processors (2 x 1536), 192 texture units (2 x 96), and 4GB of GDDR5 (2 x 2 GB).
The 6990 will have a core speed of 830 MHz and an effective memory clock of 5.0 GHz. This makes the 6990 a tad slower than the single GPU 6970 which had clock speeds of 880 MHz on the core, and 5.5 GHz for the memory. Since this is the only difference between the 6990 and the 6970, one would expect that a 6990 would perform similarly to a pair of 6970′s in CrossFire.
The 6990 is very interesting in one respect. While the card idles at 37 Watts, when the graphics card is fully loaded, it consumes 375 Watts. This is outside the PCIe specifications. It makes the 6990 the most power hungry graphics card to date. To handle that heat, AMD has redesigned the heat sink. On the 6990, the fan is located in the middle of the graphics card, and each GPU on the 6990 has its own heat sink that is isolated from the other one. This allows the 6990 to dissipate over 450 Watts of thermal energy.
As mentioned, the 6990 is outside the PCIe specifications. It has two 8 pin power connectors, each of which can deliver 150 Watts. It can also draw up to 75 Watts from the PCIe connector. This means that it can, and will, draw 375 Watts. But that is not quite the whole story. Remember PowerTune? It allows AMD to control how much power the graphics card consumes. If the graphics card tries to draw too much power, PowerTune will throttle back the clock speeds to keep the card within specifications. In this case, PowerTune keeps the 6990 at 375 Watts. Most games will not be throttle back. However, there may be some games that are.
Did I mention that the 6990 is outside the PCIe specifications? To help the graphics card meet its energy budget, AMD is using cherry picked GPUs that run at a lower default clock voltage. Also to help reduce power consumption, AMD is using less expensive 5 GHz GDDR5 memory. This memory runs at a lower memory voltage than the 6 GHZ GDDR5 memory found on the 6970.
But who wants to run a stock 6990. Literally with the flick of a switch, you can run the 6990 at the same default clock speeds as the 6970. The 6990 comes with a physical switch that allows you to switch between the default BIOS that has a 830 MHz core speed, and a performance BIOS that comes at 880 MHz core speed. This will, of course, consume more power than 375 Watts. Fortunately the cooler can handle it. The question remains to whether or not the power supply in your system can handle it, as well as the increased thermal loads on the rest of the components in your system.
Anandtech has posted an in-depth review of the 6990. Here is what they thought of it:
Dual-GPU cards have always been a niche product, but the 6990 really takes this and runs with it. There’s no significant power/noise savings to be found by consolidating 2 GPUs on to a single card, and as we said earlier with the dual-exhaust cooler the 6990 is effectively 2 video cards on one PCB. This isn’t a bad thing – the 6990 is the world’s fastest video card after all – but it drives the card in to some very specific niches. If you fall in to these niches, then the 6990 is certainly the card for you.
The launch price for the 6990 is $699. This is going to be one expensive graphics card.
via : AMD’s Radeon HD 6990: The New Single Card King @ Anandtech
Realizing the success of Nvidia’s CUDA university initiatives, AMD recently announced a new OpenCL University Kit, a collection of materials that can be used in any university environment to teach OpenCL programming.
“Teaching students to effectively leverage the OpenCL standard involves all the intricacies of parallel programming plus support for a new class of heterogeneous computing devices built on a variety of hardware technologies,” said David Kaeli, professor and associate dean of undergraduate programs, Northeastern University College of Engineering. “The OpenCL University Kit introduced by AMD is an easy tool to enable educators to quickly introduce OpenCL learning into their curriculum, helping them strike a balance between teaching syntax and higher level architectural issues.”
The kit includes 13 lectures, with instructor and speaker notes, as well as code examples. Combined with the recently announced ‘Accelerated Parallel Processing SDK‘, (the new name for the old Stream SDK) it’s a great way to get into OpenCL development.
via AMD Helps Advance Parallel Computing with OpenCL™ University Kit.
Not wanting to let NVidia get all the hype for their announcements at GDC this week, AMD also announced new features in the OpenCL space. One of interest to many is a new OpenCL-driven Bullet Physics plugin for Maya 2011.
“AMD is committed to collaborating with partners like Autodesk on industry standards and open-source software solutions that open up a world of vivid visual experiences,” said Janet Matsuda, general manager of AMD Professional Graphics. “This new plug-in will give CG content developers an open development path with OpenCL and a powerful solution for incorporating high-quality physics that offer realistic animation of how rendered objects move in a game or film.”
Unfortunately, it’s not standard with Maya2012 like the NVidia PhysX solution but it’s at least another option.
via AMD Showcases New Open Source Physics Plug-in for Autodesk Maya 2011 at Game Developers Conference.
VizWorld.com Got an idea for a story? Drop us a line at [email protected] or other means.
Comments