The Portland Group(R), a wholly-owned subsidiary of STMicroelectronics (NYSE: STM), announced the general availability of Release 7.1 of its suite of Fortran, C and C++ compilers and development tools. PGI(R) compilers and tools are used widely in high-performance computing (HPC), the field of technical computing engaged in the modeling and simulation of complex phenomena, such as ocean modeling, weather forecasting, seismic analysis, bioinformatics and other areas. PGI compilers, which convert software programs into the binary instructions that a computer can understand, are recognized in the HPC community for delivering world-class performance across a wide spectrum of applications and benchmarks, and they are referenced regularly as the industry standard for performance and reliability.
The latest PGI 7.1 compilers and tools deliver all existing best-practices software components for developing highly efficient parallel applications to multi-core Linux desktops. For the past 10 years, applications for parallel supercomputers have been developed almost exclusively using the de facto standard Message Passing Interface (MPI) programming model or OpenMP directive-based extensions to Fortran, C and C++. HPC developers now face the daunting task of adapting these MPI and OpenMP applications to run effectively on clusters of multi-core CPUs, while general-purpose developers face the substantial challenge of adapting serial legacy applications to effectively use multiple cores. The coming wave of multi-core processors will require developers to leverage the existing knowledge base of software development from HPC.
PGI 7.1 delivers comprehensive support for both OpenMP and MPI, including graphical OpenMP and MPI debugging and profiling tools, in all PGI product configurations for Linux. This includes PGI’s lowest-cost configuration: PGI C/C++ Workstation for a single academic user, which is priced at $299 USD for a permanent license. Until now, such a comprehensive parallel-programming environment was available only on dedicated HPC or cluster systems at a cost of thousands of dollars per seat. PGI’s latest offering makes all of these capabilities plus state-of the-art automatic parallelization available and affordable to virtually any developer with a need to adapt applications to run in parallel on multi-core processors.
“We continue to invest heavily in delivering performance-oriented compilers and tools to our core science and engineering users while making a concerted effort to enable parallel application development by more general- purpose developers,” said Douglas Miles, director, The Portland Group. “With Release 7.1, we are delivering our fastest Fortran compiler yet, and also C and C++ compilers that show performance gains of more than 10% versus PGI 7.0 on standard benchmarks running on the latest multi-core processors. We are taking a practical approach to helping our customers cross the multi-core divide by delivering increasingly better compile-and-go performance as part of a complete parallel programming toolkit for systems ranging from dual- or quad-core laptops and desktops to the world’s fastest supercomputers.”
“HP and its customers value PGI’s practical approach to optimizing software for multi-core processors,” said Ed Turkel, Manager of Product Marketing for High Performance Computing at HP. “HP is delighted to have PGI participate in our Multi-core Optimization Program. We recognize the significant value that PGI’s comprehensive set of processor-independent compilers and tools brings to our joint customers in tuning applications on HP’s servers and clusters using the latest multi-core processors from both AMD and Intel.”
The PGI 7.1 compilers have enabled AMD to publish SPECfp_rate_base2006 performance results on Quad-Core AMD Opteron 2.5 Ghz processors that are over 27% faster than the best published performance results on the same benchmark running on Intel Xeon X5365 Quad Core 3.0 Ghz processors using Intel 10.1 compilers.* “With Release 7.1, PGI has made a significant advance in bringing the performance of their C and C++ compilers up to the same high level that we have come to expect from their Fortran compilers,” said Michael Goddard, senior director, AMD Performance Center of Excellence. “PGI and AMD have been cooperating throughout 2007 to ensure PGI compilers are highly tuned for the new micro-architecture and features of AMD’s latest Quad-Core AMD Opteron processors.”
PGI Release 7.1 also marks the introduction of two new products: optimizing PGI compilers and tools for Intel processor-based Apple Macintosh systems, and a compiler and tools suite for Windows that includes the first commercially available debugger to support debugging of MSMPI applications on Microsoft’s flagship HPC product, Windows Compute Cluster Server (CCS). PGI 7.1 includes numerous under-the-hood compiler optimizations, and it features improved support for what already is the most comprehensive developer-tools offering for migration of UNIX applications to AMD and Intel processor-based systems. PGI is unique in offering developers the option of migrating from UNIX to Linux or to Windows x64 using either a UNIX-like development environment on native Windows or through Microsoft’s Subsystem for UNIX-based Applications environment. PGI 7.1 for Windows platforms includes the ability to use all of the PGI compilers and tools on both native Windows and from within Windows SUA (Subsystem for UNIX-based Applications).
All PGI products include the ability to generate PGI Unified Binary(TM) executable files. The PGI Unified Binary enables developers to leverage the latest processor innovations from both AMD and Intel while treating x64 as a single platform, maximizing flexibility and eliminating the need to target and optimize for two separate processors. Evaluation copies of the new PGI compilers are available from The Portland Group web site. Registration is required.
About The Portland Group
The Portland Group, a wholly-owned subsidiary of STMicroelectronics, is the premier supplier of high-performance Fortran, C, and C++ compilers and tools for high-end computing systems and X86 processor-based workstations, servers, and clusters. Further information on The Portland Group products can be found by calling Sales at (503) 682-2806, or by email to firstname.lastname@example.org.
* SPEC(R) and the benchmark name SPECfp(R) are registered trademarks of the Standard Performance Evaluation Corporation. Competitive benchmark results stated above reflect results published on http://www.spec.org as of October 11, 2007. The comparison presented above is based on the best published performance on competing AMD and Intel Quad-Core platforms.