Monday, September 28th 2009
NVIDIA Collaborates With Microsoft On High Performance GPU Computing
NVIDIA today announced work with Microsoft to promote NVIDIA Tesla graphics processing units (GPUs) for high performance parallel computing using the Windows HPC Server 2008 operating system.
"The coupling of GPUs and CPUs illustrates the enormous power and opportunity of multicore co-processing," said Dan Reed, corporate vice president of Extreme Computing at Microsoft. "NVIDIA's work with Microsoft and the Windows HPC Server platform, is helping enable scientists and researchers in many fields achieve supercomputer performance on diverse applications."
NVIDIA Research developed several GPU-enabled applications on the Windows HPC Server 2008 platform, such as a ray tracing application that can be used for advanced photo-realistic modeling of automobiles. Related to this, NVIDIA worked with Microsoft Research to install a large Tesla GPU computing cluster and is studying applications that are optimized for the GPU.
In addition, a whole range of enterprise applications - such as data mining, machine learning and business intelligence, as well as scientific applications like molecular dynamics, financial computing and seismic processing - are taking advantage of the massively parallel CUDA architecture on which NVIDIA's GPUs are based to achieve higher levels of productivity.
The CUDA architecture enables developers to use the CPU and the GPU together in a co-processing model. Compute-intensive sections of an application use the parallel computing capabilities of the GPU, while the sequential part of an application's code runs on the CPU.
"The combination of GPUs and the Windows platform has been a great benefit to our VMD (Visual Molecular Dynamics) user community, bringing advanced molecular visualization and analysis capabilities to thousands of users," said John Stone, senior research programmer at the University of Illinois Urbana-Champaign. "As we move toward even larger biomolecular structures, GPUs will become increasingly important as they bring even more computational power to bear on what will be highly parallelizable computational problems."
"The scientific community was one of the first to realize the potential of the GPU to transform its work, observing speedups ranging from 20 to 200 times while using a range of compute-intensive applications," said Andy Keane, general manager of NVIDIA's Tesla business. "Researchers are increasingly using Windows on workstations and in data centers due to strong development tools like Microsoft Visual Studio, its ease of system management and its lower total cost of ownership."
NVIDIA Tesla high-performance GPU computing products support Windows XP and Windows Vista in the workstation and Windows Server 2003 and Windows Server 2008 in the data center. Tesla C1060 and S1070 GPU computing products are available from most major system vendors including Cray, Dell, HP and Lenovo.
"The coupling of GPUs and CPUs illustrates the enormous power and opportunity of multicore co-processing," said Dan Reed, corporate vice president of Extreme Computing at Microsoft. "NVIDIA's work with Microsoft and the Windows HPC Server platform, is helping enable scientists and researchers in many fields achieve supercomputer performance on diverse applications."
NVIDIA Research developed several GPU-enabled applications on the Windows HPC Server 2008 platform, such as a ray tracing application that can be used for advanced photo-realistic modeling of automobiles. Related to this, NVIDIA worked with Microsoft Research to install a large Tesla GPU computing cluster and is studying applications that are optimized for the GPU.
In addition, a whole range of enterprise applications - such as data mining, machine learning and business intelligence, as well as scientific applications like molecular dynamics, financial computing and seismic processing - are taking advantage of the massively parallel CUDA architecture on which NVIDIA's GPUs are based to achieve higher levels of productivity.
The CUDA architecture enables developers to use the CPU and the GPU together in a co-processing model. Compute-intensive sections of an application use the parallel computing capabilities of the GPU, while the sequential part of an application's code runs on the CPU.
"The combination of GPUs and the Windows platform has been a great benefit to our VMD (Visual Molecular Dynamics) user community, bringing advanced molecular visualization and analysis capabilities to thousands of users," said John Stone, senior research programmer at the University of Illinois Urbana-Champaign. "As we move toward even larger biomolecular structures, GPUs will become increasingly important as they bring even more computational power to bear on what will be highly parallelizable computational problems."
"The scientific community was one of the first to realize the potential of the GPU to transform its work, observing speedups ranging from 20 to 200 times while using a range of compute-intensive applications," said Andy Keane, general manager of NVIDIA's Tesla business. "Researchers are increasingly using Windows on workstations and in data centers due to strong development tools like Microsoft Visual Studio, its ease of system management and its lower total cost of ownership."
NVIDIA Tesla high-performance GPU computing products support Windows XP and Windows Vista in the workstation and Windows Server 2003 and Windows Server 2008 in the data center. Tesla C1060 and S1070 GPU computing products are available from most major system vendors including Cray, Dell, HP and Lenovo.
18 Comments on NVIDIA Collaborates With Microsoft On High Performance GPU Computing
+1 for lingo
Oh wait... DX11 isn't mentioned once in the article D:
It probably has something to do with their past experience with the issue. Their statement seems pretty logical actually, if you look at it from their eyes, after seeing huge amounts of users flock to their 8800 series, but stick with XP... Pretty clear sign that the latest DX version doesn't sell cards, horse power does.
And as far as I can tell, this article has nothing to do with DX11. Just because the words Ray Tracing come up, that doesn't mean it has to do with DX11.
This is more along the lines of CUDA and doing computational work on the GPU then it has to do with DX11.
Must be for the press then a bit of bigging oneself up!
A lot of the major performance issues were caused by driver and program incompatibilities, not the OS itself. Almost all of which have been worked out to the point where it is hard to tell the difference between Vista and XP performance wise(measure the difference, yes, but actually feel the difference in everyday use, no).
And it isn't like Windows 7 made huge leaps in performance over Vista either, the two performance relatively identically.
And Vista wasn't supposed to be Windows 7. Vista was supposed to be Vista. It is Microsoft's standard to release an unrefined OS first, refine it, then release it as a new OS with a few pretty addons. They did it with 95 and 98, they did it with 2000 and XP, and now they are doing it with Vista and Win7.
Vista served its purpose, to get a radically new OS out into the public, to make people asking for a new OS happy, and still allowing MS more time to refine a better OS.
What makes you think they are doing it because of DX11 and not just because the cards perform better?
And i have to agree with Newtekie on this one, most people are gonna buy for the horsepower, not for DX11 specifically. DX11 is just an added bonus.
I want DX11 just like I wanted DX10, force the move forward, and punish those lagging.
However after seeing the possability of what we can still get with DX9 in HL FF mods it is amazing. I want more of the other options it brings, the ability to really work in quality with AVCHD files and have the muchmore powerful GPU do it. A quad is OK, but a 2GB 5870 should eat it up.