Date: 07/05/2010

PGI Accelerator compilers from Portland now supports NVIDIA GPUs

The Portland Group a subsidiary of STMicroelectronics has announced that its entire line of PGI Accelerator compiler products, including its new PGI 10.4 release, support the latest NVIDIA graphics processing units (GPU) based on the Fermi architecture. The NVIDIA Tesla 20-series supports many new features for HPC space as well as support for version 3.0 of the NVIDIA CUDA toolkit.

The newest PGI Accelerator compilers provide support for CUDA Fortran (an extended version of the Fortran 2003 programming language) on the NVIDIA GPU platforms. The PGI 10.4 release also enhances support for the PGI Accelerator directives-based programming model on Fermi platforms. The PGI Accelerator directives allow incremental porting and parallelization of loops and code segments using standard-compliant and portable Fortran or C.

The PGI 10.4 release features in the use of PGI Unified Binary technology to build one version of an application that will run on any CUDA-enabled GPU. PGI 10.4 compilers can generate code that is used for both Tesla C1060 GPU and the new Tesla C2050 GPU. It also extends support for new NVIDIA GPU platforms across Linux, Windows and MacOS, and within Microsoft Visual Studio via PGI Visual Fortran.

"With PGI 10.4, HPC users can create highly optimized heterogeneous multi-core applications for the latest CPUs from Intel and AMD in combination with the latest generation of GPUs from NVIDIA," said Douglas Miles, director The Portland Group. "Efficiently using all available host cores for certain parts of an application while accelerating other portions on GPUs is the key to squeezing maximum performance out of today's GPU-enabled workstations and cluster nodes. With Fermi's improvement in double-precision performance, we expect a big increase in the number and type of applications that benefit from GPU acceleration."

"A large part of the success of Tesla GPUs in the HPC space can be attributed to the quality of the development tools from NVIDIA and its partners," said Sanford Russell, general manager, GPU Computing at NVIDIA. "This announcement from PGI, building on the tools already in the market, is more evidence of the increasing momentum behind GPU computing in general and our CUDA architecture in particular."

Availability: Now

To know more visit: http://www.pgroup.com.