Nvidia lagged behind rival AMD in the introduction of a Direct X 11 GPU but it seems that the company is ready to make an impressive come back with the upcoming GT300 chip, which bloggers already describe as a "computational beast".
Nvidia's upcoming 40nm GPU codenamed "Fermi" or simpler "GT300" is slated for a Q4 2009 launch, meaning that it will most probably show up around the end of November.
Rumors about the new chip indicate that it will pack a lot of architectural changes compared to Nvidia's GT200 generation of GPUs.
Manufactured by TSMC, the 40nm chip is expected to pack three billion transistors and 16 Streaming Multiprocessor (former Shader Cluster). Each multiprocessor has 32 cores, with each core to be able to execute an integer or a floating point instruction per clock per thread.
The chip also packs six 64-bit GDDR5 memory controllers for a grand total of 384-bit, matching AMD's current offering with the Radeon HD 5800 series.
Possible configurations of the new boards should include 1.5, 3.0 GB and 6GB of GDDR5 memory.
Of course, the GT300 gives direct hardware access for CUDA 3.0, DirectX 11, OpenGL 3.1 and OpenCL.
Nvidia should have been very busy with the design of the new architecture fir the GT300 chip. According to early reports, the chip will be more than three times more powerful than the GT200 GPU.
Nvidia has made an official statement on the state of the GT300 yields last week, after some stories online reported that the GT300 yields were bad, with only nine chips to work per wafer. An Nvidia' product manager said that the company's 40nm yields were "fine" and described the information as "baseless."
It seems that the complicated design of the new GT300 chip was the reason behind the "late" introduction of the chip in the market. AMD has already made a strong statement with the release of its Radeon HD5800 series but Nvidia believes that they can make its DirectX 11 GPU even faster.
All we have to do is to wait to see if the GT300 can outperform the HD 5870, HD 5850X2 and the HD 5870X2 chips, in a very interesting race in the GPU market.
NVIDIA Unveils Next Generation CUDA GPU Architecture - Codenamed "Fermi"
Nvidia today officially introduced its next generation CUDA GPU architecture, codenamed "Fermi". An entirely new ground-up design, the "Fermi" architecture is the foundation for the world's first computational graphics processing units (GPUs), promising to deliver breakthroughs in both graphics and GPU computing.
"NVIDIA and the Fermi team have taken a giant step towards making GPUs attractive for a broader class of programs," said Dave Patterson, director Parallel Computing Research Laboratory, U.C. Berkeley and co-author of Computer Architecture: A Quantitative Approach. "I believe history will record Fermi as a significant milestone."
Presented at the company's inaugural GPU Technology Conference, in San Jose, California, "Fermi" delivers a feature set that accelerates performance on a wider array of computational applications than ever before. Joining NVIDIA's press conference was Oak Ridge National Laboratory who announced plans for a new supercomputer that will use NVIDIA GPUs based on the "Fermi" architecture. "Fermi" also garnered the support of leading organizations including Bloomberg, Cray, Dell, HP, IBM and Microsoft.
"It is completely clear that GPUs are now general purpose parallel computing processors with amazing graphics, and not just graphics chips anymore," said Jen-Hsun Huang, co-founder and CEO of NVIDIA. "The Fermi architecture, the integrated tools, libraries and engines are the direct results of the insights we have gained from working with thousands of CUDA developers around the world. We will look back in the coming years and see that Fermi started the new GPU industry."
As the foundation for NVIDIA's family of next generation GPUs namely GeForce, Quadro and Tesla − "Fermi" features a host of new technologies including:
- C++, complementing existing support for C, Fortran, Java, Python, OpenCL and DirectCompute.
- ECC, a critical requirement for datacenters and supercomputing centers deploying GPUs on a large scale
- 512 CUDA Cores featuring the new IEEE 754-2008 floating-point standard, surpassing even the most advanced CPUs
- 8x the peak double precision arithmetic performance over NVIDIA?s last generation GPU. Double precision is critical for high-performance computing (HPC) applications such as linear algebra, numerical simulation, and quantum chemistry
- NVIDIA Parallel DataCache - a cache hierarchy in a GPU that speeds up algorithms such as physics solvers, raytracing, and sparse matrix multiplication where data addresses are not known beforehand
- NVIDIA GigaThread Engine with support for concurrent kernel execution, where different kernels of the same application context can execute on the GPU at the same time (eg: PhysX fluid and rigid body solvers)
- Nexus - a fully integrated heterogeneous computing application development environment within Microsoft Visual Studio
Nvidia described the "Fermi" architecture as the most significant leap forward in GPU architecture since the original G80. G80 was Nvidia's initial vision of what a unified graphics and computing parallel processor should look like. GT200 extended the performance and functionality of G80. With Fermi, Nvidia has taken all they have learned from the two prior processors and all the applications that were written for them, and employed a completely new approach to design to create the world?s first computational GPU.
No comments:
Post a Comment