New Developments in Supercomputing

Over the past 33 years the International Super Computing conference in Germany has become one of the world's major computing events with the bi-annual announcement of the Top500 systems, which continues to be dominated in entirety by Linux systems. In June this year over 3,500 people attended ISC with a programme of tutorials, workshops and miniconferences, poster sessions, student competitions, a vast vendor hall, and numerous other events.

Exploring Issues in Event-Based HPC Cloudbursting

The use of cloud compute, especially in proportion to single-node tasks, provides a more effective allocation of financial resources. The introduction of cloud-bursting to scheduling systems could ideally provide on-demand compute resources for High Performance Computing (HPC) systems, where queue wait-times are a source of user consternation.

Transparency and Immersion in HPC

The development of the graphic user-interface is widely considered a major phenomenological contribution to the Human-Computer Interaction (HCI) by providing an intuitive framework for data storage and processing, encapsulated in the term "user friendly". Whilst for a very large number of everyday computational tasks this Windows-Icons-Menu-Pointer (WIMP) interface has been highly successful, the field of high performance computing (HPC) continues to use the command line interface.

Being An Acrobat: Linux and PDFs

The PDF file format can be efficiently manipulated in Linux and other free software that may not be easy in proprietary operating systems or applications.

Installation of MrTrix 3.0_RC2 on HPC Systems

MrTrix is "a set of tools to perform various types of diffusion MRI analyses, from various forms of tractography through to next-generation group-level analyses". It is mostly designed with post-processing visualisation in mind, but for intensive computational tasks it can make use of high-performance computing systems. It is not designed with messing-passing in mind, but it can be useful for job arrays.

Net Promoter Score: The Most Useless Metric of All

A number of organisations use a customer service metric known as "Net Promoter", first suggested in the Harvard Business Review. Indeed, it is so common that apparently two-thirds of Fortune 500 companies are using the metric. It simply asks a single question: "How likely is it that you would recommend [company X] to a friend or colleague?".

Drupal "Access denied" Message

It happens rarely enough, but on occasion (such as an upgrade to a database system (e.g., MySQL, MariaDB) or system version of a web-scripting language (e.g., PHP), you can end up with one's Drupal site failing to load, displaying only the error message similar to:

PDOException: SQLSTATE[HY000] [1044] Access denied for user 'username'@'localhost' to database 'database' in lock_may_be_available() (line 167 of /website/includes/

A Tale of Two Conferences: ISC and TERATEC 2017

This year the International Supercomputing Conference and TERATEC were held in close proximity, the former in Frankfurt from June 17-21 and the latter in Paris from June 27-28. Whilst the two conferences differ greatly in scope (one international, one national) and language (one Anglophone, the other Francophone), the dominance of Linux as the operating system of
choice at both was overwhelming.

Rattus Norvegicus ESTs with BLAST and Slurm

The following is a short tutorial on using BLAST with Slurm using fasta nucleic acid (fna) FASTA formatted sequence files for Rattus Norvegicus. It assumes that BLAST (Basic Local Alignment Search Tool) is already installed.

First, create a database directory, download the datafile, extract, and load the environment variables for BLAST.

mkdir -r ~/applicationtests/BLAST/dbs
cd ~/applicationtests/BLAST/dbs
gunzip rat.1.rna.fna.gz
module load BLAST/2.2.26-Linux_x86_64

Having extracted the file, there will be a fna formatted sequence file, rat.1.rna.fna. An example header line for a sequence:

>NM_175581.3 Rattus norvegicus cathepsin R (Ctsr), mRNA

Spartan and NEMO: Two HPC-Cloud Hybrid Implementations

High Performance Computing systems offer excellent metrics for speed and efficiency when using bare metal hardware, a high speed interconnect, and parallel applications. This however does not represent a significant portion of scientific computational tasks. In contrast cloud computing has provided management and implementation flexibility at a cost of performance. We therefore suggest two approaches to make HPC resources available in a dynamically reconfigurable hybrid HPC/Cloud architecture. Both can can be achieved with few modifications to existing HPC/Cloud environments.


Subscribe to RSS - blogs