Entries tagged as: Hardware
AMD launches contest giving away an $8,100 Magny Cours 48 core setup
Posted by
Tony DeYoung on March 05, 2010
The AMD ”What would you do with 48 cores?” contest asks you to write an essay/blog or video describing what you would do with a 48 core system to make the world a better place. The winner receives an $8,100 setup including a TYAN 4S board and four 12-core Opteron Magny Cours processors.
Hopefully, there will be some interesting entries and the winner will be someone who can really take advantage of what is essentially a supercomputer setup. In particular I was thinking that some OpenCL-savvy developer would describe a compelling new solution since OpenCL can take advantage of all 48 CPU cores (as well as the more traditional GPU cores).
The actual prize is:
- Four new AMD Opteron processors Model 6174, 12-core (2.2 GHz)
- TYAN S8812 motherboard: the motherboard is a Tyan S8812 that features 4 processor sockets with the capacity for you to install up to 8 DIMMs per socket
- one copy of Windows Server 2008
Rumor: Apple to adopt Radeon HD 5750 for next-gen iMacs
Posted by
Tony DeYoung on March 04, 2010
I typically try to avoid propagating rumors of unannounced/unconfirmed products but since I have an iMac here on my desk, in need of a replacement, I was excited to read a rumor on BSN that Apple will be incorporating ATI Radeon HD 5750’s into an upcoming iMac refresh (the current Core i5/i7 iMacs use ATI Radeon HD 4850s).
What makes this particularly interesting: screaming OpenGL 3.2 support, screaming DirectX 11 support when running as a PC (or under virtualization?), and a great engine for OpenCL which is an integral part of the Mac OS.
Barco releases graphics controller optimized for mammography & radiology 3D based on FirePro GPU
Posted by
Tony DeYoung on March 01, 2010

Barco has introduced a new graphics display controller, the MXRT-7300, specifically designed to speed up 3D imaging and digital mammography applications in radiology departments. It is powered by a FirePro workstation GPU with 1 GB memory. It supports 10-bit (1,024 simultaneous levels of gray and over 1 billion colors) display of up to 3,280 x 2,048 pixel images. This level of shading gradation and resolution is critical for accurate visual diagnosis using digital images,.
“With the brand-new MXRT-7300 graphics processor, our customers will enjoy an immediate performance improvement when manipulating large datasets in mammography, as well as an acceleration of OpenGL and DirectX functions increasingly common in high-end PACS (picture archiving and communication systems) environments”
Radeon HD 5870 Eyefinity 6 - driving 6 HD displays from one GPU
Posted by
Tony DeYoung on February 25, 2010
AMD announced the ATI Radeon HD 5870 Eyefinity6 Edition, which lets you drive six monitors from a single extreme GPU for a maximum resolution of 6 X 2560 X 1600 pixels, powered by a single extreme GPU. It provides six Mini DisplayPort connectors to directly drive the display or through adapters for single-link DVI and HDMI. Essentially the Radeon 5870 E6 is a 2GB version of the Radeon 5870 equipped with 6 mini-DisplayPorts for its output and 2GB of GDDR5 memory to accommodate the extremely large frame buffer needed by six HD displays.
No performance or pricing information has been set. Also no mention specifically of a CrossFireX option to offer additional power to drive the 6 displays without lag.
Since this is a Radeon card, everyone is talking about the 6 displays in terms of game play by the enthusiast. But where I see this as really relevant will be in productivity (multiple apps on multiple screens) and of course as it moves into professional CAD and VizSim for things like virtual prototyping and design.
The story behind the RV870 - a.k.a the Evergreen line
Posted by
Tony DeYoung on February 16, 2010
AnandTech has an insightful and interesting article about the release of the RV870 chipset (a.k.a. Evergreen line, a.k.a. Radeon 5XXX) and how AMD’s graphics division has really begun to shine. Think VH1’s “Behind the Music” but for the tech world.
Actually the story of the risks ATI took to keep the GPU size down and keep power requirements low without sacrificing performance is pretty interesting. Then there is the whole Eyefinity project and how it came into being!
Intrique from the article: “Other than the obvious, there was one real problem with Carrell’s secrecy. In order for Eyefinity to work, it needed support from external companies.... For a feature like SunSpot (later to be named Eyefinity) to go completely unnoticed during the development of a GPU is unheard of. Carrell even developed a rating system. The gold standard is launch; if SunSpot could remain a secret until the launch, that’s gold. Silver is if they can keep it a secret until they get chips back. And the effort would get a bronze if they could keep it a secret up to tape out, at that point NVIDIA would be at least one full product cycle behind ATI.”
And in closing: “Carrell Killebrew helped turn ATI from a traditional GPU company with a poor track record, to one that could be known for its execution. The past three product generations have been executed extremely well. Regardless of whether you’re an AMD, Intel or NVIDIA fan, you must give credit where it’s due. The past couple of years have shown us a dramatic turn around from the graphics group at AMD. To go from the shakiness of the R500 and R600 GPUs to solidly executing on the RV670, 770 and 870 year after year is praiseworthy. I almost wonder if AMD’s CPU team could learn from the graphics group’s execution. I do hope that along with the ATI acquisition came the open mindedness to learn from one another.”
A great read - highly recommended.
upFront eZine talks to AMD at SolidWorks World 2010 - How do you distinguish yourselves from nVidia?
Posted by
Tony DeYoung on February 08, 2010
upFront ezine is an independent newsletter and great resource for anyone in the CAD industry. The latest issue is filled with news and interviews from SolidWorks World 2010 including an interview with AMD’s World Wide Senior Product Marketing Manager for Workstation Graphics, Bahman Dara. I’m going to repeat several of the Q&As here, but check out the newsletter for the full scoop.
“How do you distinguish yourselves from nVidia,” was my first question.
For one, AMD focuses on workstation and DCC graphics only. (DCC is digital content creation, those guys who create graphics for games and TV commercials.) For another, their graphics boards cost less than those from nVidia, when measured by performance per dollar. (nVidia skipped this show; in their place was retail proxy PNY.) AMD has just two product names: Radeon for consumers and FirePro for professionals. FirePro is divided into:
- FirePro V-series for CAD and DCC.
- FirePro Multi-View for multimonitor “text” users like financial traders.
And then both are available in desktop and notebook ("mobile") versions.
“And what about the future?” I wondered.
Mr Dara told me that AMD is working on remote graphics, using compression to deliver graphics from a central server through a cable to desktops via Ethernet or USB.
See the issue to learn more about the SolidWorks World keynotes, future plans for SolidWorks, as well more on AMD plans.
SIGGRAPH CG Quarterly Newsletter: Ending the Tradeoff of Time vs Quality when Creating 3D Graphics
Posted by
Tony DeYoung on February 05, 2010
SIGGRAPH's Computer Graphics Quarterly Newsletter features an article titled "Ending the Tradeoff of Time vs. Quality when Creating 3D Computer Graphics Content - Stepping Up the Production Workflow with Real-Time Rendering Software".
The article is about MachStudio Pro specifically, but more generally about how today's fully programmable hardware GPUs (e.g. FirePro V8750) can be optimally tapped by writing software that structures advanced rendering effects as separate independent processing passes.
"MachStudio Pro exploits a confluence of enablers emerging on the 3D graphics scene to address a glaring and unfilled need. Real-time rendering coupled with a comprehensive 3D workspace streamlines workflow, ending the compromise between time and quality."

Winners of the “Innovation Revolution 2010” FirePro V3750 giveaway - Next phase: Win a V5700!
Posted by
Tony DeYoung on February 03, 2010
The winners in the FirePro V3750 graphics accelerators giveaway, were published today. I received a little background on the winners and what they do.
Albert Chosky: Uses a V8700 today. Has been working for 10 years as a graphics designer, 4 years as a photo-retoucher and is moving into working with Maya to add animation and compositing to his work. He used to buy Nvidia, but when he was looking for a high-end card, the V8700 was 1/3rd the price of a comparable Nvidia card. He’s been using his v8700 for a couple of months now and loves it!
Jayson Morales: aspiring graphics game animator. Has a V3750 today, and is working on his last 4 courses for a computer engineering degree.
Larry Kevin: media communications at the East Bay Coast guard center. He uses ATI FirePro at work and has an older Nvidia board at home.
Also the next phase of the Innovation Revolution 2010 Contest: Win a FirePro V5700!
AMD Eyefinity displays at SolidWorks World 2010
Posted by
Tony DeYoung on February 01, 2010
AMD has a strong presence at SolidWorks World 2010 (hence the timing of last week's news that the entire FirePro family is certified for SolidWorks 2010 running Windows 7).
The 3 Eyefinity screens look pretty amazing as you can see in the photos below from the AMD booth.



What is not mentioned about the Nvidia GF100 - power consumption, tesselation and manufacturing
Posted by
Tony DeYoung on January 21, 2010
The hype and FUD machine is ratcheting up to full speed for the released-sometime-this-spring Nvidia DirectX 11 card, the GF100, a.k.a. Fermi. I’ve been reading the recently reported Nvidia specs and then someone pointed me to this article on SemiAccurate: Nvidia GF100 pulls 280W and is unmanufacturable.
The gist of the article is: The GF100 was never meant to be a graphics chip but rather a GPGPU compute “generalist” chip. In this new role as a GPU, the GF100 too costly to manufacture, too power hungry, and really is not equipped to do real-life gaming or professional rendering (but not bad in specialized benchmark comparisons).
Read the articles for the specifics, but for me (being a fan of tessellation), the following stuck out: “On ATI 5xxx cards, tessellation performance takes almost no shader time other than dealing with the output just like any other triangle. On GF100, there is no real dedicated hardware, so the more you crank up the tessellation, the more shaders you co-opt.”.
I am guessing the level of FUD will only increase. It will be interesting to see where the market goes.