Beta Release Includes Initial Support for Standardized Directive-Based Programming Model for GPUs and Accelerators
Portland, Oregon - The Portland Group, a wholly-owned subsidiary of STMicroelectronics and a leading supplier of PGI® compilers for high-performance computing (HPC), announced immediate availability of the initial release of its PGI Accelerator(TM) Fortran and C compilers with partial support for the new OpenACC® specification for directive-based programming of GPUs and accelerators. In the next few months, PGI plans to include additional OpenACC features with full support for the OpenACC 1.0 specifications scheduled for release in June.
"PGI continues to invest in technologies to make GPU programming more straightforward and productive for domain experts in science and engineering," said Douglas Miles, Director of The Portland Group. "The OpenACC standard was developed in direct response to HPC community's interest for a vendor-neutral, platform-independent, directive-based accelerator programming model, and dovetails perfectly into our existing compiler products as a standardized subset of the PGI Accelerator programming model."
The OpenACC standard, unveiled at SC11 in November, 2011, as founded by PGI, Cray, and NVIDIA, with support from CAPS, is fully compatible and interoperable with the NVIDIA® CUDA® parallel programming architecture. The OpenACC 1.0 specification was developed in cooperation by the founding members and is based in large part on the PGI Accelerator programming model. The OpenACC Application Program Interface (API) describes a collection of compiler directives to specify loops and regions of code in standard C, C++ and Fortran to be offloaded from a host CPU to an attached accelerator, providing portability across operating systems, host CPUs and accelerators. By using directives, developers can have a single code base that is multi-platform and multi-vendor compatible, a key advantage for multi-platform and multi-generation application development.
The use of OpenACC allows parallel programmers to provide simple hints, known as "directives," to the compiler, which identify areas of code to accelerate, without requiring programmers to modify or adapt the underlying code itself. By exposing parallelism to the compiler, directives allow the compiler to do the detailed work of mapping the computation onto the accelerator to deliver significant improvements to application performance.
"OpenACC is key to enabling the extensive community of new researchers and programmers to, for the first time, take advantage of the transformative benefits of parallel computing," said Ian Buck, general manager, GPU computing software at NVIDIA. "OpenACC makes it very easy for individuals with or without extensive parallel programming experience to accelerate new applications using a familiar programming model. And, it breathes new life into legacy applications by maintaining code portability during the transition to high-performance parallel computing architectures."
A trial version of the beta release of the PGI Accelerator compilers with support for the OpenACC standard is available for free from the PGI website at www.pgroup.com/support/downloads.php. The beta software includes a restricted use license. The license agreement is available at www.pgroup.com/support/BTLA. More information on the PGI Accelerator compilers with OpenACC support is available at www.pgroup.com/accel. More information on the OpenACC API and standard can be found at: www.openacc-standard.org.
About The Portland Group (PGI)
The Portland Group, a wholly-owned subsidiary of STMicroelectronics (NYSE: STM), is the premier supplier of high-performance parallel Fortran, C, and C++ compilers and tools for workstations, servers, and clusters based on x64 processors from Intel and AMD, and GPU accelerators from NVIDIA. Further information on The Portland Group products can be obtained at www.pgroup.com, by calling Sales at (503) 682-2806, or by email to email@example.com.
OFFICE: +1 5035703884