Introduction
Intel Fortran Compiler, also known as IFORT, is a group of Fortran compilers from Intel Corporation. The compilers generate code for IA-32 and Intel 64 processors and certain non-Intel but compatible processors, such as certain AMD processors. A specific release of the compiler (11.1) remains available for development of Linux-based applications for IA-64 ( Itanium 2) processors. On Windows, it is known as Intel Visual Fortran. On Linux and OS X, it is known as Intel Fortran.
The 13.0 release announced on September 5, 2012 adds support for the Intel Xeon Phi coprocessor. This release continues support for automatic vectorization, which can generate SSE, SSE2, SSE3, SSSE3, SSE4 and AVX SIMD instructions. Use of such instructions through the compiler can lead to improved application performance in some applications as run on IA-32 and Intel 64 architectures, compared to applications built with compilers that do not support these instructions.
It also continues with support for OpenMP 3.1, automatic parallelization for symmetric multiprocessing, almost all of the Fortran 2003 standard and much of the Fortran 2008 standard including Coarray Fortran. When used with Intel cluster tools (see the "Description of Packaging" below) the compiler can also automatically generate Message Passing Interface calls for distributed memory multiprocessing from OpenMP directives.
Optimizations
Intel compilers are optimized to computer systems using processors that support Intel architectures. They are designed to minimize stalls and to produce code that executes in the fewest possible number of cycles. Intel Fortran Compilers support three separate high-level techniques for optimizing the compiled program: interprocedural optimization (IPO), profile-guided optimization (PGO), and other high-level optimizations (HLO). They also support a directives-based approach to application offloading to Intel coprocessors, such as the Intel Xeon Phi coprocessor.
The compiler supports profile-guided optimization, which is a mode of optimization where the compiler is able to access data from a sample run of the program across a representative input set. The data would indicate which areas of the program are executed more frequently, and which areas are executed less frequently. All optimizations benefit from profile-guided feedback because they are less reliant on heuristics when making compilation decisions.
High-level optimizations are optimizations performed on a version of the program that more closely represents the source code. This includes loop interchange, loop fusion, loop unrolling, loop distribution, data prefetch, and more.[2]
Interprocedural optimization applies typical compiler optimizations (such as constant propagation) but using a broader scope that may include multiple procedures, multiple files, or the entire program.[3]
Standards Support
The Intel Fortran compiler supports all of the features of the Fortran 90 and 95 Standards. It also supports various extensions found in VAX Fortran and Compaq Visual Fortran.
A partial list of items from the Fortran 2003 standard supported by Intel Fortran:
- Enumerators
- Type extension and type-bound procedures
- FINAL routines and GENERIC, OPERATOR, and ASSIGNMENT overloading in type-bound procedures
- Polymorphic data and the CLASS declaration
- Allocatable scalar variables (not deferred-length character)
- SOURCE= keyword for ALLOCATE
- Intrinsic modules IEEE_EXCEPTIONS, IEEE_ARITHMETIC and IEEE_FEATURES
- ASSOCIATE construct
- DO CONCURRENT construct
- PROCEDURE declaration and procedure pointers
- CONTIGUOUS attribute
- Structure constructors with component names and default initialization
- Array constructors with type and character length specifications
- I/O keywords BLANK, DECIMAL, DELIM, ENCODING, IOMSG, PAD, ROUND, SIGN, and SIZE
- PUBLIC types with PRIVATE components and PRIVATE types with PUBLIC components
- A file can be opened for stream access (ACCESS='STREAM')
- BIND attribute and ISO_C_BINDING intrinsic module
- ASYNCHRONOUS attribute
- VALUE attribute
- FLUSH statement
- WAIT statement
- IMPORT statement
- Allocatable components of derived types, allocatable dummy arguments, and allocatable function results
- VOLATILE attribute
- Names of length up to 63 characters
- Statements up to 256 lines
A partial list of items from the Fortran 2008 standard supported by Intel Fortran:
- Coarrays
- CRITICAL construct
- The Fortran 2008 Standard specifies a maximum rank of 15; the maximum array rank has been raised to 31 dimensions in Intel Fortran
- A generic interface may have the same name as a derived type
- Bounds specification and bounds remapping list on a pointer assignment
- NEWUNIT= specifier in OPEN
- A CONTAINS section can be empty
- Coarrays can be specified in ALLOCATABLE, ALLOCATE, and TARGET statements
- MOLD keyword in ALLOCATE
- DO CONCURRENT statement
- ERROR STOP statement
Architectures
Description of Packaging
Intel Fortran 13.0 compilers are not available as a standalone compilers. They are available in packages, some of which include other build-tools, such as libraries, and others which include performance and threading analysis tools. Intel Fortran is part of Intel Parallel Studio XE, which includes Intel C++ (available for Windows and Linux) and Intel Fortran Studio XE, both of which include performance analysis and thread-diagnostic tools. Intel Fortran Composer XE (available for Windows, Linux and OS X) and Intel Composer XE, which also includes Intel C++ (available for Windows and Linux) do not include the analysis and thread-diagnostic tools. Intel compilers are also included in Intel Cluster Studio (no analysis tools) and Intel Cluster Studio XE (analysis tools included). The cluster tools are available for use on Windows and Linux. Packages that include Intel C++ also include the Intel Math Kernel Library (Intel MKL), Intel Integrated Performance Primitives (Intel IPP) and Intel Threading Building Blocks (Intel TBB). Fortran-only packages only include Intel MKL.
Ten Year Version History
| Compiler version | Release date | Major New Features |
|---|
| Intel Fortran Composer XE 2013 (compiler 13.0) | Sep 5, 2012 | Linux-based support for Intel Xeon Phi coprocessors, support for Microsoft Visual Studio 12 (Desktop), support for gcc 4.7, support for Intel AVX 2 instructions, updates to existing functionality focused on delivering improved application performance. Continued availability of the Visual Studio 2010 Shell for Windows versions. |
| Intel Fortran Composer XE 2011 Update 6 and above (compiler 12.1) | Sep 8, 2011 | OpenMP 3.1, additional 2003 (ALLOCATE with SOURCE=, polymorphic source) and 2008 standards support, Windows version ships with Visual Studio 2010 Shell. |
| Intel Fortran Composer XE 2011 up to Update 5 (compiler 12.0) | Nov 7, 2010 | Coarray Fortran, additional 2003 (FINAL subroutines, GENERIC keyword,) and 2008 (Coarrays, CODIMENSION, SYNC ALL, SYNC IMAGES, SYNC MEMORY, CRITICAL, LOCK, ERROR STOP, ALLOCATE/DEALLOCATE) |
| Intel Fortran Compiler 11.1 | June 23, 2009 | Support for latest Intel SSE, AVX and AES instructions. More Fortran 2003 support. Support for latest Intel MKL release (included in compiler products). Commercial licenses for Windows version include Microsoft Visual Studio 2008 Shell and libraries. |
| Intel Fortran Compiler 11.0 | November 2008 | More Fortran 2003 support. Support for OpenMP 3.0. Source Checker for static memory/parallel diagnostics. Commercial licenses for Windows version include Microsoft Visual Studio 2005 Premier Partner Edition. |
| Intel Fortran Compiler 10.1 | November 7, 2007 | New OpenMP* compatibility runtime library. To use the new libraries, you need to use the new option "-Qopenmp /Qopenmp-lib:compat" on Windows, and "-openmp -openmp-lib:compat" on Linux. This version of the Intel compiler supports more intrinsics from Microsoft Visual Studio 2005. VS2008 support - command line only in this release. |
| Intel Fortran Compiler 10.0 | June 5, 2007 | Improved parallelizer and vectorizer, Streaming SIMD Extensions 4 (SSE4), new and enhanced optimization reports for advanced loop transformations, new optimized exception handling implementation. |
| Intel Fortran Compiler 9.0 | June 14, 2005 | AMD64 architecture (for Windows), software-based speculative pre-computation (SSP) optimization, improved loop optimization reports. |
| Intel Fortran Compiler 8.1 | September, 2004 | AMD64 architecture (for Linux). |
| Intel Fortran Compiler 8.0 | December 15, 2003 | Precompiled headers, code-coverage tools. |
Debugging
The Intel compiler provides debugging information that is standard for the common debuggers (DWARF 2 on Linux, similar to gdb, and COFF for Windows). The flags to compile with debugging information are /Zi on Windows and -g on Linux. Debugging is done on Windows using the Visual Studio debugger and, on Linux, using gdb.
While the Intel compiler can generate a gprof compatible profiling output, Intel also provides a kernel level, system-wide statistical profiler as a separate product called VTune. VTune features an easy-to-use GUI (integrated into Visual Studio for Windows, Eclipse for Linux) as well as a command line interface.
Intel also offers a tool for memory and threading error detection called Intel Inspector XE. Regarding memory errors, it helps detect memory leaks, memory corruption, allocation/de-allocation of API mismatches and inconsistent memory API usage. Regarding threading errors, it helps detect data races (both heap and stack), deadlocks and thread and synch API errors.
See also
References
External links
