November 15, 2012
SALT LAKE CITY, Nov. 15 – The Portland Group (PGI), a wholly-owned subsidiary of STMicroelectronics and the leading independent supplier of compilers and tools for high-performance computing, announced at SC12 today that the PGI 2013 release of its PGI Accelerator compilers due out in early December will add support for the new family of NVIDIA Tesla K20 GPU accelerators and the CUDA 5 parallel computing platform and programming model.
The PGI compilers and tools are used by scientists and engineers to create and run high-performance computing applications for complex modeling and simulations in weather forecasting, geophysical processing, aerodynamic simulation, structural analysis, automotive crash-testing, computational chemistry, and related fields. PGI compilers and tools support the latest 64-bit processors from AMD and Intel, and the new NVIDIA Tesla K20X and K20 GPU accelerators based on the next-generation NVIDIA Kepler compute architecture running on Linux, Apple OS X and Microsoft Windows platforms.
"We are tracking closely with NVIDIA and CUDA 5.0 to deliver support for dynamic parallelism and general function calls on this latest generation of GPU accelerators," said Douglas Miles, director, The Portland Group. "We've also been tuning code generation to optimize performance on Tesla K20 accelerators, and early reports from customers indicate that this is paying significant dividends on their GPU-enabled codes."
Introduced in 2009, PGI Accelerator compilers were the industry's first standard-compliant Fortran and C compilers to automatically offload computations from an x64 host program to a GPU accelerator. Also introduced in 2009, PGI CUDA Fortran is a Fortran analog of NVIDIA CUDA C. CUDA Fortran, included in all PGI Accelerator Fortran products, is comprised of a Fortran 2003 compiler and tool chain for programming NVIDIA GPUs using Fortran. PGI Release 2013 coming in December 2012 will include CUDA Fortran extensions for developers interested in accessing the new dynamic parallelism capabilities in the latest Kepler-based Tesla GPU accelerators, and the separate compilation and GPU object file linking capabilities of CUDA 5. PGI will be demonstrating the latest PGI Accelerator compilers in booth 1321 during the SC12 exhibition.
"PGI's powerful Accelerator compilers enable developers to take full advantage of the advanced new performance and efficiency features of CUDA 5 and the Tesla K20 accelerators," said Sumit Gupta, general manager of the Tesla accelerated computing business at NVIDIA. "Innovative technologies such as dynamic parallelism to Hyper-Q make the Kepler GPUs high performing and highly energy efficient, and more applicable to a wider set of developers and applications."
Source: The Portland Group
10/30/2013 | Cray, DDN, Mellanox, NetApp, ScaleMP, Supermicro, Xyratex | Creating data is easy… the challenge is getting it to the right place to make use of it. This paper discusses fresh solutions that can directly increase I/O efficiency, and the applications of these solutions to current, and new technology infrastructures.
10/01/2013 | IBM | A new trend is developing in the HPC space that is also affecting enterprise computing productivity with the arrival of “ultra-dense” hyper-scale servers.
Ken Claffey, SVP and General Manager at Xyratex, presents ClusterStor at the Vendor Showdown at ISC13 in Leipzig, Germany.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?