ACADEMIA

Visual Numerics, Inc., celebrating 36 years of producing advanced numerical analysis and visualization software, announced today that it will integrate and distribute the Intel Math Kernel Library (Intel MKL) with its IMSL Fortran Numerical Library version 6.0. The combination of libraries will provide a substantial performance increase for IMSL Fortran users developing high performance computing (HPC) applications, and improve installation and support for IMSL library customers running on Intel processor-based platforms. The bundle covers both distributed and shared memory computing models. Visual Numerics plans to bundle the Intel optimized BLAS, LAPACK, and ScaLAPACK functionality from the Intel Math Kernel Library into the company’s IMSL Fortran Numerical Library with its version 6.0 release in early 2007. Intel MKL is a set of highly optimized, extensively threaded, mathematical functions for engineering, scientific and financial applications requiring high performance on Intel processors. The joint offering provides improved IMSL computational performance across all Intel platforms including Intel Core 2 Duo, Intel Pentium 4, Intel Itanium 2, and the new Dual and Quad-Core Intel Xeon processors. “Integrating the Intel Math Kernel Library with Visual Numerics’ IMSL Fortran Numerical Library will enable developers using IMSL to fully harness the computing power of Intel processors for their high performance computing numerical analysis applications,” said James Reinders, director of marketing for Intel Software Development Products. “Whether they engage in cluster computing or desktop computing, this integrated software development toolset will benefit companies who want to get the most out of their hardware system investments including Intel’s dual-core and quad-core processor-based systems.” For nearly 10 years, Visual Numerics and Intel have engaged in joint development activities. Visual Numerics began supporting Intel processors before the release of the x86 processor series. “Our IMSL developer community demands the most reliable libraries and tools to enable them to build high performance applications on a variety of platforms,” said Phil Fraher, president and CEO of Visual Numerics. “With Intel MKL we’re giving developers a fully integrated set of libraries that are compatible with all Intel processor-based platforms to simplify the migration of legacy applications and development of new applications.”