Home / Products / Numerical Libraries / NAG Library for SMP & multicore

Download
Brochure More about the NAG Library for SMP & multicore

• Library contents
• What's new at Mark 22
• Software engineering for multicore & HPC
• HPC and multicore Software Consulting
• Client List
• Technical Hints & Tips
• Technical Reports
• Thread Safety
• Using the NAG Library for SMP & multicore in C
• Contact Us

NAG Library for SMP & multicore

Unrivalled functionality, increased speed and heightened performance for shared memory parallelism

The NAG Library for SMP & multicore is the largest commercial numerical algorithm library developed to harness the huge performance gains from the shared memory parallelism of Symmetric Multi-Processors (SMP) and multicore processors.

Many of the algorithms, or routines, in the Library are specifically tuned to run significantly faster on multi-socket and multicore systems.

The graph below shows the speed increases of using the NAG Library for SMP & multicore. NAG Routine used Nearest Correlation Matrix - problem size of N=10,000

Read a write up of the NAG Library for SMP & multicore by a NAG user at the University of Manchester, including benchmarks.

New functionality at Mark 22

Why should I use the NAG Library for SMP & multicore?

The NAG Library for SMP & multicore has proven scalability, speed and correctness making it easy to exploit the power of SMP and multicore systems without requiring the user to modify their code. It contains all the powerful, robust and flexible algorithms in the NAG Library but is specifically optimized for SMP and multicore systems, so by purchasing the multicore version of the NAG Library you're future proofing your numerical software investment as your hardware grows.

Specialized multicore functionality

• Dense and Sparse Linear Algebra
• Fast fourier transforms (FFTs)
• Random Number Generators
• Quadrature
• Partial Differenial Equations
• Interpolation
• Curve and Surface Fitting
• Correlation and Regression Analysis
• Multivariate Methods
• Time Series Analysis
• Financial Option Pricing
• Dense linear algebra (LAPACK)
• Sparse iterative solvers
• Sparse direct solvers (based on SuperLU)
• Sparse iterative eigensolvers (based on ARPACK)

Other areas that benefit from tuned routines

• Ordinary differential equations (ODEs)
• Optimization
• Multivariate statistics
• Linear algebra

Replacing NAG Fortran Library routines with their multi-core equivalents

The NAG Library for SMP & multicore is based on, and includes, the full functionality of the NAG Fortran Library so the arguments list and routines names are identical. This provides an easy upgrade path because the same code can call a routine that performs the same function, in either the Fortran Library or the NAG Library for SMP & multicore. The distinction between the two is only made when the final code is linked to a library. Applications that reference a NAG Library routine can therefore take advantage of the performance improvement simply by recompiling and linking your code on a multicore system.

No specialist parallel programming knowledge is required to apply the multicore techniques to your code. The parallelism is carried out automatically and transparently in certain distinct regions within the routines.

The software in the library is accompanied by first-class online documentation giving you the detailed information you need to carry out your work quickly and effectively.

To ensure that we fulfil your existing and future requirements, the library is regularly updated with new and enhanced algorithms for use in evolving business areas.

If you subscribe to our dedicated Customer Support Service, not only will you automatically receive any update that is produced, but you will have direct access via the NAG Response Centre to our experts, who are there to assist you with your technical queries or difficulties.

The validity of each component is tested on each of the machine ranges for which the product is available. Only when an implementation satisfies our stringent accuracy standards is it released. As a result, you can rely on the proven accuracy and reliability of the components to give you the right answers.