Archive Home arrow Reviews: arrow Video Cards arrow Zotac GeForce GTX-480 Fermi Video Card

Zotac GeForce GTX-480 Fermi Video Card E-mail
Reviews - Featured Reviews: Video Cards
Written by Olin Coles   
Tuesday, 11 May 2010
Table of Contents: Page Index
Zotac GeForce GTX-480 Fermi Video Card
Features and Specifications
NVIDIA GF100 GPU Fermi Architecture
Closer Look: Zotac GeForce GTX480
Video Card Testing Methodology
3DMark Vantage GPU Tests
Battlefield: Bad Company 2
BattleForge Performance
Crysis Warhead Tests
Far Cry 2 Benchmark
Resident Evil 5 Tests
Metro 2033 DX11 Performance
Unigine Heaven Benchmark
NVIDIA APEX PhysX Enhancements
NVIDIA 3D-Vision Effects
GeForce GTX480 Temperatures
VGA Power Consumption
Editors Opinion: Fermi GF100
ZOTAC GTX-480 Conclusion

Editor's Opinion: Fermi GF100

NVIDIA heard the dinner bell ring many months ago when Microsoft introduced DirectX-11 along side Windows 7, and they've been crawling to the table ever since. Details of the new NVIDIA Fermi GPU architecture were first leaked out to the Web as early as September 2009, which makes exactly half a year between myth and reality. ATI helped set the table with their Radeon HD 5000 series, and even enjoyed some appetizers while a few DX11 games were released, but NVIDIA managed to take a seat just in time for supper. Unfortunately for NVIDIA, ATI showed up wearing its best Sunday blue's, while Fermi's suit is still at the cleaners. None of this really matters though, because now NVIDIA can eat as much as they want.

My analogy plays out well you consider the facts behind GF100 and the launch of NVIDIA's GeForce GTX470/480. AMD may not have launched with more than a few hundred full-fledged 40nm ATI Cypress-XT GPUs having all eighty texture units, but they made it to market first and created a strong consumer demand for a limited supply of parts. NVIDIA decided on an alternate route, and binned their GPU yields based on streaming multiprocessors. The GF100 GPU is designed to have 16 streaming multiprocessors and 512 discrete cores, and while the Fermi architecture is still in-tact, there's one SMP disabled on the GeForce GTX 480, and two SMPs disabled on the GTX 470. The world has yet to see what the full 512 cores can accomplish, although NVIDIA is already revolutionizing the military with CUDA technology.

So now ATI and NVIDIA are even-Steven in the running for DirectX-11, and all that they need are video games to increase demand for their product. This becomes a real problem (for them both) because very few existing games demand any more graphical processing power than games demanded back in 2006. Video cards have certainly gotten bigger and faster, but video games has lacked fresh development. DirectX-10 helped the industry, but every step forward received two steps back because of the dislike for Microsoft's Windows Vista O/S. Introduced with Windows 7 (and also available for Windows Vista with an update), enthusiasts now have DirectX-11 detail and special effects in their video games.


NVIDIA GeForce GTX 480 Graphics Card

Even if you're only after raw gaming performance and have no real-world interest in CUDA, there's reason to appreciate the GF100 GPU. New enhancement products, such as the NVIDIA GeForce 3D Vision Gaming Kit, double the demands on frame rate output and hence require more powerful graphics processing. This is where products like the GeForce GTX470 and GTX480 deliver the performance necessary to enjoy the extended gaming experience. I'm a huge fan of GeForce 3D-Vision, which is why it's earned our Editor's Choice Award, and Fermi delivers the power necessary to drive up to three monitors. The newly dubbed NVIDIA 3D-Vision Surround (stereo) requires three 3D-Vision capable LCD, projector, or DLP devices and offers bezel correction support. Alternatively, NVIDIA Surround (non-stereo) supports mixed displays with common resolution/timing.

Even some older game titles benefit by the Fermi GF100 GPU, beyond just an increase in frame rates. For example, Far Cry 2 will receive 32x CSAA functionality native to the game, but future NVIDIA Forceware driver updates could also further add new features into existing co-developed video games. Additionally, NVIDIA NEXUS technology brings CPU and GPU code development together in Microsoft Visual Studio 2008 for a shared process timeline. NEXUS also introduces the first hardware-based shader debugger. NVIDIA's GF100 is the first GPU to ever offer full C++ support, the programming language of choice among game developers.

Fermi isn't for everyone. Many of NVIDIA's add-in card partners (what they call AICs) have already built inventory of the GeForce GTX 480. On 12 April 2010 ASUS will reveal the ENGTX480/2DI/1536MD5 GeForce GTX 480 graphics card kit, which online retailers are expected to price at around $500 for the 90-C3CH90-W0UAY0KZ SKU. The ASUS ENGTX470/2DI/1280MD5 kit (GeForce GTX 470) loses only one (more) SMP, but the price for their 90-C3CHA0-X0UAY0KZ kit drops to $350. While not based on anything other than these two prices, it seems that a full 16-SMP 512-core version could receive the GeForce "GTX-490" name and a price tag around $650. Certain to be an expensive enthusiast product, if and when it ever gets made, the GeForce "GTX-490" could keep company with the $1130 recently-announced Intel Core i7-980X 6-Core CPU BX80613I7980X.

Fermi is also the first GPU to support Error Correcting Code (ECC) based protection of data in memory. ECC was requested by GPU computing users to enhance data integrity in high performance computing environments. ECC is a highly desired feature in areas such as medical imaging and large-scale cluster computing. Naturally occurring radiation can cause a bit stored in memory to be altered, resulting in a soft error. ECC technology detects and corrects single-bit soft errors before they affect the system. Fermi's register files, shared memories, L1 caches, L2 cache, and DRAM memory are ECC protected, making it not only the most powerful GPU for HPC applications, but also the most reliable. In addition, Fermi supports industry standards for checking of data during transmission from chip to chip. All NVIDIA GPUs include support for the PCI Express standard for CRC check with retry at the data link layer. Fermi also supports the similar GDDR5 standard for CRC check with retry (aka "EDC") during transmission of data across the memory bus.

The true potential of NVIDIA's Fermi architecture has still yet to be seen. Sure, we've already poked around at the inner workings for our NVIDIA GF100 GPU Fermi Graphics Architecture article, but there's so much more that goes untested. Heading into April 2010, only a private alpha version of the [email protected] client is available. The difference between work unit performance on the GeForce GTX 480 is going to surpass ATI's Radeon HD 5870 without much struggle, but it's uncertain how much better the performance will be compared to the previous-generation GeForce GTX 285. Until the GeForce GTX470/480 appears on retail shelves, and until a mature GeForce 400-series WHQL Forceware driver is publicly available, many of the new technologies introduced will remain untapped.



# Other TestsFederico La Morgia 2010-05-13 22:57
3 x 480 ?
tests in OC ?
Report Comment
# Next Zotac 480 coming soonWW_Dagger 2010-05-26 16:44
I've set my heart on the recently announced Zotac FTX 480 AMP. This takes the cake! Faster yet quieter, and looks just awesome.
Report Comment
# RE: Next Zotac 480 coming soonFederico La Morgia 2010-05-26 22:09
Point my heart, I would like a Fermi limited to 480 SP, but having the full 512-SP.
Not only!, I wish to put in dual-GPU as my current GTX 295 and directly to the liquid cooled heat sink with copper entirely!
Report Comment
# HD5870Ansuex 2010-09-10 00:32
Is it just me? or is the 5870 losing less fps when resolution is turned higer compared to the GTX480 or?
Report Comment

Comments have been disabled by the administrator.

Search Benchmark Reviews

Like Benchmark Reviews on FacebookFollow Benchmark Reviews on Twitter