Other product variants may be available, please contact us or request a call back if you cannot see what you are looking for.

Product Information

Intel Composer XE is a parallel processing tool that delivers improvements to the best optimising C++ and Fortran compilers, scalable multithreading with OpenMP, new parallelism models, and Co-Array Fortran as part of the Fortran 2008 standard, including optimised libraries. A simple recompile with Intel Composer XE compilers can boost performance by 20 percent or more. Intel Composer XE is part of Intel Parallel Studio XE, the all-in-one parallel processing software for serial and parallel C/C++ applications.

Documents & Downloads

New Features

Intel Composer XE 2011 SP1 new features

Improved performance

Memory, auto-parallelisation and vectorisation optimisations have resulted in enhanced performance. C/C++ Compiler v12.1 is now up to 11% faster than v12 and Fortran Compiler v12.1 is up to 22% faster than v12.

Enhanced standards and support

Intel C++ Compiler 12.1 features support for the IEEE 754-2008 standard for binary and decimal floating point arithmetic. Support for C++0x standards have been increased with support for Variadic templates that enable a variable number of arguments, plus there is support for OpenMP 3.1.

Threading Build Blocks 4.0 new features

• Flow graph - a flexible API for expressing static and dynamic dependencies between computations
• Concurrent unordered set - thread-safe container for storing and accessing user objects
• Memory pools - get enhanced flexibility and performance by getting thread-safe and scalable object allocation
• Generic GCC atomics support - library portability enables development of TBB-based solutions on more platforms
• Task and task group priorities - specify task execution order based on three different priority levels
• Concurrent Priority Queue - a new queue that allows pulling data out in a user-defined priority order.

Intel Cilk Plus new features

• Enhanced SIMD pragma support - improved scalability and performance with SIMD pragma loops, vector length, and elemental functions support
• SIMD pragma clause - 'vectorlengthfor' provides a more architectural and scalable way to define vector lengths of loops
• Holder hyperobjects - saves time and improves performance by enabling per-thread temporary storage
• New Mac OS X support.

Intel Composer XE 2011 new features

Intel C++ Compiler XE new features

• Optimisations for the latest Intel architectures - with Intel AVX support the C/C++ compiler optimises for the latest Intel architecture - codenamed Sandy Bridge
• Intel Parallel Building Blocks - the inclusion of the new Intel Parallel Building Blocks expands the types of problems that can be solved more easily in parallel by taking advantage of the multicore optimisation opportunities in Intel Clik Plus, Intel Threading Building Blocks and Intel Array Building Blocks
• Vector optimisations - support for vector optimisations with Intel AVX, with SIMD pragmas, and help in auto-parallelisation for the highest performance and parallelism on the latest IA multicore CPUs

Intel Fortran Compiler XE new features

• Support for co-array Fortran in the Fortran 2008 standards which provides support for single multi-cpu shared memory nodes
• Support for other Fortran 2008 features including DO CONCURRENT, CONTIGUOUS, I/O enhancements, and new intrinsic functions, a set of which includes matrix multiply intrinsic functions that support calls into Intel MKL
• More complete support for the Fortran 2003 standard including complete type-bound procedures such as GENERIC and OPERATOR
• Interacts with the new C++ 0x and C99 features in the Intel C++ Compiler
• OpenMP 3.0 support for simplifying pragma-based development of parallelism
• Support for Intel Advanced Vector Extensions (Intel AVX)

Intel Math Kernel Library new features

• Intel Math Kernel Library - the latest version of the Intel Math Kernel Library features better Intel AVX support, a new summary statistics library, enhanced C support for LAPACK and much more.

Intel Integrated Performance Primitives new features

• Intel Integrated Performance Primitives - the latest version of Intel Integrated Performance Primitives includes enhanced support for Intel AVX and AES instructions, improved data compression, improved codecs and more.

Features

Intel C++ Compiler XE

Intel C++ Composer XE enables software engineers to develop high performance applications for the latest Intel IA-32 and Intel 64 architectures. The compiler supports OpenMP, advanced vectorisation, Intel Parallel Building Blocks and more.

Intel Fortran Composer XE

Intel Fortran Composer XE is a powerful Fortran compiler that compiles highly optimised Fortran code designed for maximum performance on Intel processor-based platforms. Amongst the compiler's advanced features are automatic vectorisation which can safely optimise loops to run in parallel, automatic processor dispatch, loop unrolling and more.

Intel Integrated Performance Primitives

Intel Integrated Performance Primitives provide a library of ready-to-use, highly optimised functions in the areas of media and data processing. Intel Integrated Performance Primitives features functions in a range of categories including video and audio coding, image coding and processing, speech recognition, data compression, cryptography, vector and matrix mathematics, ray tracing/rendering and more.

Intel Threading Building Blocks

Intel Threading Building Blocks is a powerful C++ library that helps create parallel applications. Take advantage of task-based routines that scale to all available processor cores and work across multiple platforms but do not require low level threading programming. Intel Threading Building Blocks can future-proof your applications by taking advantage of additional processor cores as new processors are released, enhance the speed of your applications and reduce development time.

Intel Math Kernel Library

Intel Math Kernel Library (Intel MKL) is a library of highly optimised, extensively threaded math routines for science, engineering, and financial applications that require maximum performance. Core math functions include BLAS, LAPACK, ScaLAPACK, Sparse Solvers, Fast Fourier Transforms, Vector Math and much more.