MORE POSTS
ACML Engineer Interviewed – Listen to the Podcast
I recently had a different sort of meeting. I was on the receiving end of an interview by Jeff Squyres and Brock Palen of RCE (http://www.rce-cast.com/). Brock has been chiming in on the ACML forum and Jeff is one of … Continue reading
ADIT Episode #11: Intro to ACML
This is an introduction to the AMD Core Math Library that covers what it is, who it is for, what platforms it works on, and where to find support. Continue reading
ACML 4.4.0 PathScale Support
Explaining why the new ACML 4.4.0 does not include PathScale builds. Continue reading
ACML 4.4.0 Released!
Most of the Linux builds of ACML 4.4.0 are now live on the ACML download page. The NAG builds will follow very soon. We have not yet posted any Windows builds, although there are links for them on the download … Continue reading
SuperComputing 2009 – Day 2
Of the Wednesday sessions, one of the most interesting was a talk on Matlab. Matlab has language constructs such as parfor that enable rapid migration to multicore. And the distributed keyword marks an array as suitable for parallel processing. Matlab … Continue reading
SuperComputing 2009
Online at last. I can’t believe some hotels still charge for wireless internet. Here at the SuperComputing 2009 show in sunny Portland Oregon, wireless is free, fast, and reliable. For the first time at an super computing show, I have … Continue reading
ACML 4.3.0 Performance Data
Now that the ACML 4.3.0 release is completed and posted live on AMD Developer Central, I’ve been spending time collecting all the performance data needed to document the improvements in the 4.3.0 release. There are several new features that should … Continue reading
Removing C wrapper functions from the AMD Core Math Library (ACML) to resolve linking issues.
ACML is a significant library of (mostly) FORTRAN subroutines, provided in binary form and available for download at http://developer.amd.com/acml. Each version of the library has been compiled with a particular FORTRAN compiler, and is compatible with application programs written and … Continue reading
ACML Example Programs and the Bonus RNG
The ACML examples directory contains a wealth of programs that demonstrate how to use many of the routines found in AMD’s Core Math Library (ACML) Two of these programs in particular provide a primary source of documentation on how to … Continue reading
“Barcelona” Processor Feature: 128-bit FPU
The new AMD “Barcelona” processors introduce dramatically improved numerical performance when using the standard SSE, SSE2 and SSE3 instruction extensions. Previous AMD processors typically could execute a vectorized SSE instruction (for example, MULPS to perform four multiplies) every two clock … Continue reading
