A couple of days ago I received one more e-mail appearing to originate from Nedbank Limited. The e-mail was about some new security measures taken by the bank to prevent fraud. The e-mail, as you can see bellow, is asking the user to download the attached file which is a link to the false logon page. Having tried to access the link today appeared to not work. Probably the service provider realised this was a fake page or the incident has been reported and disabled the account. Banks never send such e-mails, never require users to confirm their details in that way. Only the bank’s official page (assuming there’s no DNS poisoning) is the most secure way to keep up to date. Even if you think there is something suspicious with the banks website, you can always call them and ask for assistance.
On my MacBook I have a nVIDIA GeForce 8600M GT which is CUDA enabled, something I never bothered checking until very recently. nVIDIA provides online the required driver, SDK and additional “CUDA Developer”, as they call it, resources with lots of sample files to test the hardware of your system as well as actual code, including some parallel samples.
The CUDA toolkit seem to provide all you need to start with:
- C/C++ compiler
- Visual Profiler
- GPU-accelerated BLAS library
- GPU-accelerated FFT library
- GPU-accelerated Sparse Matrix library
- GPU-accelerated RNG library
- Additional tools and documentation
It does also include OpenCL samples to play about. However, the OpenCL driver will need to be installed at first place. There’s a pre-release version and in order to download it you’d need to register yourself with nVIDIA. They have also published a book, “CUDA by example”, which is not for free apart from some fragments. Nevertheless, the sample codes of the book are free to download.
AMD / ATI have also their answer to CUDA, “ATI Stream“. From what I got it seems to support only OpenCL. I don’t have a Stream-supported ATI card at the moment so I couldn’t try that one.
To close this, there’s an interesting presentation that covers basics of GPUs and how to program them (CUDA based): Programming and optimization of applications for multiple GPU
A quick entry on LCFG wiki on how to set up lcfg-libvirt on a LCFG host: https://wiki.lcfg.org/bin/view/LCFG/LcfgLibvirt. Assumes the existence of/access to a LCFG profile server.
The last couple of years I have been partly looking into coherent management of virtual machines and their integration within an existing managed infrastructure. I have tried to outline the issues, complications etc on a number of posters   (based on tools that have been/are being developed) and also through a paper . A couple of days ago, I read the very interesting article of Evangelos Kotsovinos, “Virtualisation: Blessing or Curse?” on ACM Queue, which recaps all the main considerations and implications when comes to deploy virtualised services in large scale. Anyone interested in large scale system administration that involves virtualisation management should read it. The article is trying to seriously outline the importance and complexity of managing not only the “inside” of virtual machines, but their “outside” as well and their integration with a pre-existing, established and well-functioned infrastructure with thousands of systems under a cloud computing scope.
The poster hosted recently at LISA 2010 – Integrated Configuration of Multiple Virtualisation Platforms within Virtual Infrastructures