I'm at the NVIDIA GPU conference and yesterday they announced their next generation GPU called Fermi. Here are the key points:
- 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 Coresâ¢ featuring the new IEEE 754-2008 floating-point standard, surpassing even the most advanced CPUs
- 8x the peak double precision arithmetic performance over NVIDIAâs last generation GPU. Double precision is critical for high-performance computing (HPC) applications such as linear algebra, numerical simulation, and quantum chemistry
- NVIDIA Parallel DataCacheâ¢ - the worldâs first 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
- NVIDIA GigaThreadâ¢ 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: PhysXÂ® fluid and rigid body solvers)
To get the full technical story, grab the Fermi White Paper. The bottom line, NVIDIA is paying attention to HPC in a BIG way.