An ultra-sound scanner, developed by TechniScan, utilizes four Tesla C870 boards and is programmed in with CUDA.
The company continued to run tests with Pentium 4 and Core 2 generations of processors, but even with the fastest Core 2 Duo and Quad processors, the render time could not be cut under 45 minutes.
A possible solution popped up when TechniScan senior software engineer Jim Hardwick bought a GeForce 8-series card and discovered Nvidia’s CUDA SDK. Jim is an avid gamer, so he bought the card to enjoy latest and upcoming games, but a quick run of his code on a GPU apparently lit up more than just one bulb. Fast forward to 2008 – today the code is ported to CUDA and utilizes four Tesla C870 boards. The render time was cut from 45 minutes on a 16-core Core 2 cluster to only 16 minutes.
The GPU scored major speedups in calculating 2D FFT’s, in which a single 8800 GTX was eight times faster than a Core 2 Quad at 2.66 GHz, while complex exponentiation with 12 million elements ended up being accelerated by a factor of 320x. Complex Exponentiation is usually run 50-60 times, so you can see how a 4-GPU setup was able to cut the total rendering time.
Read the complete article HERE
Tom’s Hardware recently received a monster gaming rig from Falcon Northwest: a Mach V Quad SLI system that came with two Nvidia 9800 GX2 cards. With such a rig, they were eager to see how a Quad SLI system performed compared to a 3-way SLI scheme.
Read the full review HERE
A single 9800 GX2 on its own is a formidable graphics card, but users should be warned that investing in another card won’t blow the doors off a system. In fact, we may characterize Quad SLI with two 9800 GX2s as a comparable and cheaper alternative to an expensive 3-way SLI configuration – one that will save you both some space inside your system and some money in your wallet. Quad SLI with 9800 GX2s is still in its infancy, so we expect that Nvidia will deliver improvements to this configuration as time goes on. But if it’s vastly superior performance gamers are looking for, then they’re advised to wait for the forthcoming release of Nvidia’s GTX 280 model.
A new site from ATI has been launched: www.unleashonetera.com.
More info about this website later we hope…
The chinese site it168 published some high-resolution screenshots of NVIDIA’s new GT200 Medusa tech demo:
MAXON Computer, a German-based, world-renowned developer of 3D software for the creative industries, is pleased to announce the establishment of an official presence in France. In cooperation with the French distributor of its award-winning products CINEMA 4D and BodyPaint 3D, MAXON can now offer even greater support for its French user base.
MAXON France can be reached at:
MAXON centre de compétence
1, rue de Vanves
+33 (0)1 46 21 82 22
Read more HERE
techPowerUp has reviewed Sapphire’s Radeon HD 3870 X2 Atomic Watercooled.
Sapphire’s HD 3870 X2 Atomic is the fastest HD 3870 X2 card money can buy you today. Unfortunately the extra performance gained from the overclocks is not as big as one would expect, but still, it’s the fastest X2 card.
AMD will add the Havok Physics engine to both its multi-core CPUs and GPUs, but AMD managing director noted that the focus is on CPUs given feedback from gaming developers who like the idea of offsetting physics computation to CPU cores.
Read whole article HERE
AMD is hoping to accelerate Havok Physics on both its multi-core CPUs and GPUs and claims that it’s striving to deliver the best of both worlds. However, the main focus at the moment appears to be AMD’s CPUs. AMD and Havok say that they’re planning to optimise the ‘full range of Havok technologies on AMD x86 superscalar processors, and AMD claims that Havok Physics scales extremely well across the entire family of AMD processors.
Havok’s managing director, David O’Meara, explained the priority for CPUs, saying that the feedback that we consistently receive from leading game developers is that core game play simulation should be performed on CPU cores. However, he added that GPU physics acceleration could become a feature in the future, saying that ‘the capabilities of massively parallel products offer technical possibilities for computing certain types of simulation.
– AMD’s physics secret revealed: It’s Havok @ TG Daily
Here is an article that explains what is CUDA, the NVIDIA technology for GPU programming. Sorry for english readers but this article is in french.
Read the complete article HERE.
Voici un article, en français, de vulgarisation de la technologie CUDA de NVIDIA.
L’article complet se trouve ICI.
NVIDIA boss Roy Taylor talks about PC Gaming and says that consoles don’t threaten PC gaming.
Read the full interview HERE
The console is now a baseline. If you look at Gears of War or Assassin’s Creed, they came out on console and they were great experiences – but the PC versions had additional aspects to them that also made them attractive, whether you owned the console version or not. The PC version was better. That’s something that people need to get their heads around – the console is a baseline, the PC is going to be an improved version. That’s an exciting future, and that’s why I don’t see anything threatening about console at all.
The Radeon HD 48×0 series will have 800 SPU (Shader Processing Unit).
LinceoVR is an innovative OpenGL real-time rendering engine with stereoscopic visualization, which uses state-of-the-art lighting techniques to generate and display – in real time – exceptionally realistic images in computer graphics, thanks the HDRI and OPENEXR lighting, to the dynamic management of shadows using Hard and Soft Percentage Closer Shadows algorithms and a new and innovative approach to global lighting, Natural Lighting, which offers even more realistic shadow rendering.
LinceoVR homepage: english.seac02.it/prodotti/linceo.aspx.
Voici la liste des extensions OpenGL supportées par les pilotes Forceware 175.80 / WinXP32
Here is the list of OpenGL extensions supported by Forceware 175.80 / WinXP 32 drivers.
[French]Carte graphique utilisée[/French]
[English]Graphics card used[/English]: NVIDIA GeForce 8800 GTS / 640Mb
– Drivers Version: Forceware 22.214.171.12480
– OpenGL Version: 2.1.2
– GLSL (OpenGL Shading Language) Version: 1.20 NVIDIA via Cg compiler
OpenGL Extensions: 161 extensions
DirectX 11 will be presented at the upcoming nVision 2008. Among the news features, there will be tessellation, multithreaded rendering, compute shaders, Shader Model 5.
– Introduction to DirectX 11 @ nVision 2008
Guru3D has reviewed the XFX’s GeForce 9800 GX2. Read the complete 14-page review HERE.
I also just have to mention this; for a 9800 GX2 to reach 700 MHz; wow… that’s quite something. XFX make selections of their products, and are testing their product pretty rigorously, only with a very stringent and low-yield approach they select these black editions by first selecting the normal yields, then then the XXX editions … and finally the gems that pass all performance, heat and stability tests combined becoming the Black Editions. This selection is what will make this more expensive.
So then, if a game is SLI supported (and 95% of the games today are), this is the fastest product you can purchase for that gaming experience. With the computational power that the 9800 GX2 brings you’ll reach new performance heights that surpasses the mighty GeForce 8800 Ultra at a steep yet lesser price. Any game to date can be played in the highest resolution with the finest image quality settings.
The Sapphire Radeon HD3870 Ultimate features a fanless heatsink for cooling. As expected, the card is bigger than a dual-slot cooling solution, but it’s well worth the sacrifice for passive cooling.
Read the full review HERE.