Nvidia has finally unveiled its next-generation Fermi GPU. According to Jen-Hsun Huang, Fermi architecture represents the “foundation” of the world’s first computational graphics processing units.Nvidia has finally unveiled its next-generation Fermi GPU. According to Jen-Hsun Huang, Fermi architecture represents the “foundation” of the world’s first computational GPUs – which will include GeForce, Quadro and Tesla.
“GPU computing has reached an important tipping point. GPU computing is for real. It is not just used by scientists or hobbyists, but by mainstream developers and companies that have adopted a parallel computing model,” said Jen-Hsun. “GPUs are everywhwere – in notebooks, PCs, servers and cloud computing systems.”
Jen-Hsun explained that Fermi’s architecture was designed using a ground-up approach.
“We built it completely from scratch. The GPU has 3 billion transistors,” stated Jen-Hsun. “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.”
Jen-Hsun also commented on Nvidia’s relatively “late” response to ATI’s recently introduced (DX 11) Radeon HD 5800 GPU series.
“No one likes it when competition has a product out in the marketplace. But we have a different vision and it is not only about market share. Of course, we don’t want to keep our fans and enthusiasts waiting for the next generation GPU. But we want to take the industry forward and won’t change the way we are doing things even by a little iota. We want to make sure the product is ready when it ships in a few months. And it will be – modular, flexible and powerful.”
Finally, Jen-Hsun emphasized that Nvidia was focused on advancing the computing industry and had little interest in replacing the CPU.
“Nvidia doesn’t focus on baseline PCs, but is interested in parallel computing. Fermi will do no harm to the current user install base,” added Jen-Hsun.
Fermi is expected to support 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.
- Parallel DataCache – A true 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.
- 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.