with Tags:
hpc
X

## Polyhedral-based Loop Optimizations and Dependence Analysis Part 1
Polyhedral model is a linear algebraic model to represent, reason about, and transform loop nests that perform a significant amount of computation on large arrays. These types of loop nests are typically found in High-Performance Computing applications. The model can make it possible for the XLC compiler to generate more efficient code for parts of programs that contain "affine" (or linear) accesses such as a[i][j][k] or a[i+j][i-j][2*k], where a is an array and i, j, and k are loop induction variables. Using the option -qhot=level=1... [More]
Tags: xlc loop polyhedral xlf hpc |

## MASS auto-vectorization paper now on developerWorks
If your applications call mathematical functions such as sin, cos, exp, log, etc. and you are interested in maximizing performance with minimum effort, here is something that will interest you! My colleague Daniel Zabawa and I have written a paper, "How to improve the performance of programs calling mathematical functions -- taking advantage of IBM XL C/C++ or XL Fortran compiler auto-vectorization". Our paper introduces the IBM MASS high-performance mathematical libraries, and demonstrates how to benefit from them — without the need for... [More]
Tags: elementary_functions performance vectorization numerical mass simd vector autovecgtorization library scientific cppcafe hpc |

## MASS high-performance mathematical function libraries
Hello -- I'm the technical leader for the IBM MASS math libraries. MASS stands for Mathematical Acceleration Subsystem, and consists of libraries of mathematical functions specifically tuned for optimum performance on various computing platforms. MASS was originally launched by IBM in 1995, and has been continuously improved and expanded since then. I've been involved with MASS since 2002. There are currently versions of MASS for all the POWER processors, running AIX or Linux operating systems. There are also versions for BlueGene/L and... [More]
Tags: performance mass simd scientific scalar elementary_functions vector numerical cppcafe library hpc |

## Welcome to Scientific Computing with C/C++
Welcome to the blog on Scientific Computing with C/C++. IBM has a long history of Scientific Computing starting with the creation of FORTRAN in 1957 to the control systems for the Apollo missions in the 1960s. Today, various user groups and wikis exist to support IBM’s scientific computer users: SCICOMP (see http://www.spscicomp.org/ ) SPXXL (see http://www.spxxl.org/new_website/html/index.html ) HPC Central (see http://www.ibm.com/developerworks/wikis/display/hpccentral/HPC+Central ) My Name is Roch Archambault and I have over 20 years... [More]
Tags: cppcafe scientific performance darpa hpc doe nsf programmers applications |