# IMSL Fortran Numerical Libraries

## Get Both 32-bit & 64-bit IMSL

for the Price of Just One on Windows & OS X!

*The Gold Standard Mathematical and Statistical Code Library for Fortran*

*Only Absoft Offers IMSL Bundles for Windows, OS X & Linux!*

- IMSL Bundles Save Money
- Accelerate Development
- Develop Better Software Applications
- Improve Quality and Reduce Uncertainty
- Reduce Costs
- Mathematical Functionality Categories
- Statistical Functionality Categories
- Special Features
- Ease of Use
- IMSL Documentation

The IMSL Fortran Numerical Libraries are a complete collection of mathematical and statistical algorithms which integrates the world-renowned IMSL F90 Library, Math & Stat and Fortran 77 libraries into a single, cohesive package. Absoft offers versions for all popular computing platforms thus providing a common solution from desktop to HPC cluster. Absoft offers special bundle pricing for customers purchasing compilers+IMSL, and includes specially optimized math libraries which can improve the performance on several platforms at no additional charge.

Save development time by eliminating the need to write code from scratch. Using only two or three IMSL Library mathematical or statistical routines will more than pay for the product in time-savings alone. The complete mainframe implementation of the IMSL Fortran Library Mathematical and Statistical special functions is available to Absoft users on Windows, OS X, and Linux platforms.

The strength and precision of the IMSL Numerical Libraries have been evolving steadily for over three decades. Each subroutine and algorithm has undergone rigorous testing and quality assurance, providing users with more time to focus on their application.

Parallel Processing Functions for Numerical Analysis

Developing applications for parallel systems can be painstaking. The IMSL Fortran Library combines the powerful and flexible interface features of the Fortran language with the performance benefits of both distributed memory and shared memory multiprocessing architectures. For example, interface modules to ScaLAPACK give users easy access to MPI-enabled algorithms, and allow them to write parallel code without needing to be experts in parallel programming. LAPACK integration provides easy access to SMP-enabled algorithms and allows users to write parallel code without needing to know parallel programming.

Performance Improvements from CUDA BLAS Integration

As GPU hardware becomes more prevalent in both research and commercial institutions, software that takes advantage of this specialized hardware is growing in demand. In many cases, it is infeasible or impossible to rewrite an existing program to run entirely on the GPU, so the goal is often to offload as much work as possible. The IMSL Fortran Library offloads CPU work to NVIDIA GPU hardware where the CUDA BLAS library is utilized. Users with supported hardware will be able to link the IMSL Fortran Library with CUDA BLAS version 3.1 to gain significant performance improvements for many linear algebra functions. The calling sequences for IMSL functions are untouched, so there is no learning curve and users can be productive immediately.

What’s New:

**NEW IN VERSION 7.0:**

**Basic Matrix/Vector Operations**

- Basic Linear Algebra Subprograms

(BLAS) - Matrix manipulation operations
- NVIDIA GPU (Various BLAS enabled and

supporting utilities)

**Time Series Enhancements**

- Regression ARIMA
- Automatic ARIMA modeling
- AUTO_PARM to estimate structural

breaks

**Differential Equations**

- Solution to generalized Feynman-Kac
- PDE and Black-Scholes program

**Partial Least Squares Regression**

**Maximum Likelihood Estimation**

**Normality Tests**

- Anderson-Darling
- Cramer-Von Mises

**Many Noncentral Distribution Functions**

**New in IMSL v6.0:**

**Includes new Algorithms for SMP and MPI Parallel Programming.**

**The gold standard in Fortran numerical libraries is compatible with all existing v5 routines and adds powerful new features including:**

**New High Performance Linear Programming Optimizer**

- New state-of-the-art constrained dense Linear Programming Optimizers which, in comparison tests, have performed up to 400% FASTER than leading competitors’.
- World’s fastest dense LP solver in a general mathematical library
- Includes MPS (Mathematical Programming System) format reader to facilitate usage with large optimization problems

**ScaLAPACK Integration for MPI**

- Provides easy access to MPI-enabled algorithms, and allows users to write parallel code without needing to know parallel MPI programming
- New SCALAPACK_SETUP function automatically configures MPI and ScaLAPACK, and combines with other convenience routines to allow non-expert users to solve large problems on distributed systems while avoiding many of the messy details.

**LAPACK Integration for SMP**

- Provides easy access to SMP-enabled algorithms and allows users to write parallel code without needing to know SMP parallel programming algorithm names.

**Mersenne Twister random number generator**

- Algorithm featuring fast generation of very high quality pseudorandom numbers. Especially well suited for financial applications.

**SuperLU for Sparse Linear Algebra**

- A direct solver for large sparse systems of linear equations