O

Allinea Software Blog

Thu August 20, 2015 by David Lecomber

We’re proud to announce the release of our latest version of Allinea Forge - including DDT and MAP - and Allinea Performance Reports.

I know you are asking "what’s new and how will this help me?"   You can read the release notes but here is my top five.

1. Power and Energy Profiling in Allinea MAP and Performance Reports

Power and energy are major issues for HPC today as physical limitations on available power are hit and growing costs of energy consumption in HPC systems are causing financial headaches. 

Our solution to help address the issues is the Energy Pack.  The add-on is available for our profiling and benchmarking performance tools. This allows measurement of power and energy metrics such as peak load or total for supported hardware. The impact of your server, processor and GPU can all...

Tue August 18, 2015 by Mark O'Connor
The Story So Far

In Part 1 I ran Discovar, a life sciences genome assembly code, on one of our internal systems and optimized it to run the benchmark code 7% faster. Of course, physical hardware often performs very differently to cloud-hosted machines as I discovered to my surprise when I ran the same code on an EC2 instance.

Wed July 29, 2015 by Mark O'Connor
Part 1: Optimizing on physical hardware Introduction

For those who don't know it, Discovar is a life sciences variant caller and small genome assembly code. It turns the output from sequencers into entire genomes given a reference sequence. This is computationally very expensive and I decided to take a look at it under MAP, our OpenMP and MPI profiler.

Wed February 11, 2015

Python is pretty commonplace in scientific computing these days. It is easy to code and powerful - but numerical computation is not a strength that Python has. Its interpreter simply can’t apply the advanced optimizations to your loops and floating point operations that a C++ or Fortran compiler can.

Wed February 4, 2015 by Mark O'Connor
A whirlwind tour of Allinea MAP's new OpenMP profiling capabilities

We're going to see what Allinea MAP 5.0 can do by profiling three versions of a simple PI calculator program with some added I/O for good fun:

A serial version An OpenMP version A mixed OpenMP and MPI version

Let's get started!

Sat January 10, 2015 by Mark O'Connor
Faster sequence alignment with Allinea Performance Reports

Recently we've been running bowtie2 on a 16 CPU server with 32 GB RAM. I've tried using the “-p” flag to use more cores but it doesn't seem to make a lot of difference after 8 or so.

Tue November 25, 2014 by Mark O'Connor

We’ve been profiling and tuning a lot of real-world HPC codes since the release of Allinea MAP and Allinea Performance Reports and one thing that’s consistently surprised us has been the number of codes that are memory-bound.