bradc@fpssun.UUCP (Brad Carlile ext 3699) (08/03/89)
FPS COMPUTING MATH LIBRARY OFFERED AT NO CHARGE BEAVERTON, Oregon, June 23 -- FPS Computing today announced "at-cost" availability of FPSMath(TM), the de facto standard library for engineering and scientific algorithms. This permits organizations to have common mathematical tools across their entire computing environment at nominal cost, speeding application development and research, assuring portability, and taking advantage of supercomputer and accelerator features. FPS Computing has been dedicated for 20 years to providing the best in high-end computing. FPSMath has been installed on over 400 minisupercomputers and over 8,000 array processors during that history. Only a nominal one-time duplication and shipping fee will be charged now for the extended use of FPSMath. Updates will also be offered on a regular basis. Effective immediately, users will have low-cost access to the extensive FPSMath software library without the typical high costs, constraints and difficulties associated with site licensing fees. FPSMath is a scientific and engineering math library containing over 300 routines which has evolved into a de facto industry standard during the past 20 years. The library consists of high performance, high precision subroutines which support hundreds of diverse applications. This software package is extensively utilized by customers around the world who use minisupercomputers and array processors from FPS Computing. "FPS is taking a bold and innovative action by making FPSMath so accessible," said Donald L. McDougall, vice president-marketing, sales, and service. "This software library has tremendous respect within the industry." "We consider our customers to be our partners," he said, "and we are helping them be as successful as possible with the best software available for supercomputer solutions in modern computing environments. The expanded FPSMath user base will be achieving exciting results." Math for the Entire Platform ---------------------------- FPSMath provides a toolkit to the application developer which may be used on the entire computing platform, and which fully yields the performance potential of the FPS components. All subroutines in FPSMath have names and calling sequences compatible with their counterparts in the well-established FPS Math Library. FPSMath includes subroutines which address geophysical applications, image processing, signal processing, simulation, and hundreds of commonly used vector and matrix algorithms which support applications in structural analysis, computational fluid dynamics, and other disciplines. User Advantages --------------- According to Terry Bennett, FPS director of marketing, "The big benefit of FPSMath is having high precision, high performance libraries -- comparable to expensive libraries costing tens of thousands of dollars -- available for all elements of the computing environment." "The researcher or applications developer may focus on producing function rather than coding math. The algorithms are highly efficient on standard platforms such as those from DEC or Sun. However, when the application is handled on the FPS platform," he said, "it may automatically invoke accelerator features, including vector, long instruction word, and array processor hardware." The entire FPS Math Library, now available as FPSMath, is optimized for use on the FPS Model 500 departmental supercomputer and Model 350/300 graphics and workgroup supercomputers. The Model 500, designed for large-scale projects in a modern multi-user computing environment network, is a 64-bit supercomputer which offers high-end compute power and the ease-of-use of the UNIX operating system. The Model 350 series is designed for graphics computing environments. The Model 300, used for a variety of compute-intensive applications, is an entry-level parallel machine which packs supercomputer power at a minicomputer price. Customers can get FPSMath product information by calling 1-800-635-0938, or the nearest FPS sales office. The firm maintains sales outlets across the U.S. and internationally. FPS Computing (Floating Point Systems, Inc.) has the largest installed base of high performance computing equipment in the industry. Founded in 1970, FPS is headquartered in Beaverton, Oregon, and is listed on the New York Stock Exchange. Features Summary FPSMath ------------------------- + over 300 routines. + covering all popular engineering and scientific algorithms. + may be utilized on any machine. + FPSMath has existed over 20 years. + on over 400 minisupercomputers. + on over 8,000 array processors. + callable from FORTRAN or C. + no-cost license for FORTRAN source. + on-line documentation -- UNIX "man pages". FPSMath Library Categories -------------------------- Geophysical Processing - contains the normal moveout, filtering, and scanning routines that have become the standard in the seismic community. Image Processing - two-dimensional Fast Fourier Transforms, convolution, correlation, and a variety of matrix filter routines. Matrix Basic and Extended Arithmetic - commonly used real and complex matrix kernels, including matrix multiplication, matrix inversion, matrix transpose, linear system solution, and eigensystem solution routines. Matrix Sparse Arithmetic - real and complex symmetric and nonsymmetric sparse factor and solve routines, as well as tridiagonal, skyline format, and sparse iterative matrix solvers. Signal Processing - all of the routines expected from the leader in signal processing: cross-correlation, auto-correlation, windowing, Fast Fourier Transform, and tapered convolution routines to name a few. Simulation - prediction and correlation routines, Bessel functions, Runge- Kutta-Gill integration, and linear interpolation routines. Basic Vector Arithmetic - real and complex vector routines from vector add to vector integration. Includes all basic vector arithmetic operations, a mixed-radix FFT package, and coordinate transformation and conversion routines. Vector Data Processing - contains a variety of routines for sorting, clipping, merging, and determining the maximum and minimum values between two vectors. Vector Logical - routines which can be used to determine the logical relationship between the elements of two vectors. Vector Scalar Function - dot products, determination of vector maximums, and minimums, root-mean-square of vector elements, and several other common vector calculations which produce a scalar output. News Release Contact: Terry Pennington Manager of Marketing Programs (503) 641-3151 FPSMath product information can be obtained by calling 1-800-635-0938, or by contacting the nearest FPS sales office. The following trademarks are owned by their respective companies: FPSMath, FPS Computing, Floating Point Systems, Inc.; Sun(TM), Sun Microsystems, Inc.; DEC(R), VAX(R), Digital Equipment Corporation.