PGI High-performance Compilers and Tools for Microsoft Windows
Fortran 2003, ANSI C and C++ for Microsoft Windows
PGI® parallel compilers and tools for Microsoft Windows operating systems harness the full power of today's high-performance parallel workstations and servers based on 64-bit multi-core x64 processors from AMD and Intel for science and engineering applications. PGI's industry-leading performance, reliability, native auto-threading and OpenMP support, and parallel-capable graphical debugging and profiling tools provide a complete state-of-the art programming environment for scientists and engineers. PGI's support for legacy language and programming features ensures that existing applications will port easily and quickly from RISC/UNIX systems to the latest-generation multi-core x64 processor-based systems.
PGCC and PGC++ Compilers
Unlike most Windows compilers, PGCC® and PGC++® provide vectorization, interprocedural analysis, the convenient power of auto-parallelization and the flexibility of native OpenMP and OpenACC pragma-based parallel programming for multi-core systems and HPC accelerators. PGCC is an ANSI C11 compiler designed to extract maximum performance from compute-intensive, floating-point array-based applications. PGCC includes VAX/VMS and all K&R extensions and supports the ANSI C11 standard. PGC++ is substantially compatible with GNU GCC 4.8 g++, supports a large number of ANSI C++11 features and includes full support for NVIDIA CUDA C extensions (CUDA-x86) targeting multi-core CPUs as a compute device. All C++ functions are compatible with Fortran and C functions, so you can compose programs from components written in all three languages.
Even after 50 years Fortran remains the cornerstone of technical computing. PGI's standard-compliant PGFORTRAN compilers provide the features, quality, and reliability required for developing and maintaining advanced scientific and technical applications. Common IBM, DEC, Sun and Cray extensions and cpp pre-processing help to get existing applications up and running quickly on the latest 64-bit systems. Vectorization, interprocedural analysis, profile feedback and target-specific optimizations for both AMD and Intel processors deliver consistently high performance across all x64 systems. PGI Unified Binary technology streamlines cross-platform support by enabling a single executable to contain code optimized for multiple x64 processor and/or GPU accelerator families. Auto-parallelization, OpenMP user-directed parallel programming extensions, and PGI Accelerator with OpenACC directives and CUDA Fortran extensions deliver the full capabilities of today's multi-processor technical workstations, servers and clusters.
PGI Accelerator Compilers and CUDA Fortran
Programmers can use PGI Accelerator compilers to accelerate applications on x64+accelerator platforms by adding OpenACC compiler directives to existing high-level standard-compliant Fortran, C and C++ programs and then recompiling with appropriate compiler options. A Fortran analog to NVIDIA's CUDA C, CUDA Fortran includes a Fortran 2003 compiler and tool chain for programming NVIDIA GPU accelerators using Fortran.
The PGDBG® debugger is a graphical symbolic debugger for single-thread, multi-thread, OpenMP and MS-MPI applications. Use PGDBG to control execution and examine the state of a parallel Fortran, C or C++ program. Control and examine threads or OpenMP tasks or MPI processes individually, all at once, or in user-defined sub-groups. Debug 32-bit or 64-bit applications symbolically using source code or with interleaved assembly code and full access to the registers and hardware state of the processor. PGDBG is interoperable with the GNU gcc and g77 and Microsoft Visual C++ compilers.
The PGPROF® profiler is an interactive OpenMP thread-parallel and MS-MPI process parallel performance analysis tool. PGPROF can also profile code containing OpenACC directives and CUDA Fortran code. Use PGPROF to quickly determine where execution time is spent and to identify which functions were called and how often. PGPROF supports function-level, line-level and assembly-level profiling. The PGPROF GUI displays information in intuitive easy-to-use formats such as histograms, bar charts, percentages, counts or seconds. MPI capabilities include the ability to quickly analyze Sends, Receives and other MPI communication. Execution time in multi-threaded regions is also readily accessible. PGPROF offers a combined view showing both GPU and x64 host performance for OpenACC and CUDA Fortran applications. On GPUs, PGPROF reports performance critical information including initialization, data transfer and kernel execution times.
PGI Products for Windows
PGI Workstation is PGI's flagship scientific and engineering workstation compiler bundle. PGI Workstation is available in three configurations:
- PGI Fortran Workstation includes The Portland Group's native parallelizing and optimizing OpenMP Fortran 2003 and FORTRAN 77 compilers.
- PGI C/C++ Workstation includes The Portland Group's native parallelizing and optimizing OpenMP C++ and ANSI C compilers.
- PGI Fortran/C/C++ Workstation bundles PGI Fortran Workstation and PGI C/C++ Workstation into a single convenient package.
All PGI Workstation products include a single user node-locked license. Multi-seat volume packages are also available. Multi-user network floating license options are available as PGI Server.
The PGDBG debugger and the PGPROF performance profiler included with PGI Workstation and PGI Server class products for Windows support up to a maximum of 16 local MS-MPI processes.
PGI Visual Fortran® fully integrates the PGI optimizing Fortran compiler for multi-core x64 processors into Microsoft Windows using the Microsoft Visual Studio development system.
PVF® features deep integration with Visual Studio, including Fortran-specific text editor enhancements such as syntax coloring, intrinsics tips, and keyword completion. The PVF project system automatically manages all Fortran build dependencies, and the PVF Fortran debug engine fully supports debugging of single-thread, multi-thread, MS-MPI and OpenMP applications for multi-core systems. PVF is interoperable with Microsoft Visual C++ for development of applications that incorporate PGI Fortran and Microsoft Visual C++ components.
PGI Visual Fortran is available as a single user node-locked license or a multi-user network floating license. Both versions include the newest version of the Visual Studio shell.
PGI Workstation and PGI Server for Windows consist of command-level versions of the PGI compilers and both command-level and graphical versions of the PGDBG debugger and PGPROF performance profiler. An integrated development environment (IDE) is neither provided nor supported. PGI Visual Fortran is compatible with Visual Studio 2008, Visual Studio 2010, Visual Studio 2012 and Visual Studio 2013. PGI Visual Fortran is included with all PGI Workstation and PGI Server products for Windows containing Fortran.
PGI products for Windows are available either for x64+accelerator or x64 only platforms. PGI Accelerator products—the x64+accelerator platform products—include support for OpenACC directives, and from within the PGI Accelerator Fortran compiler, support for CUDA Fortran. PGI Accelerator compilers are supported on all Intel and AMD x64 processor-based systems with CUDA-enabled NVIDIA GPU and select AMD GPU accelerators.
System requirements: 64-bit or 32-bit versions of Microsoft Windows 7 or newer. Building 64-bit applications requires a 64-bit operating system.