Episode 67 - Technical Computing with Windows Azure and Wenming Ye
- Posted: Dec 09, 2011 at 1:39 PM
- 61,632 Views
- 3 Comments
Loading User Information from Channel 9
Something went wrong getting user information from Channel 9
Loading User Information from MSDN
Something went wrong getting user information from MSDN
Loading Visual Studio Achievements
Something went wrong getting the Visual Studio Achievements
Right click “Save as…”
Join Wade and Steve each week as they cover the Windows Azure Platform. You can follow and interact with the show at @CloudCoverShow.
In this episode, Wade is joined by Wenming Ye—Technical Evangelist for Windows Azure—who explains how to use HPC on Windows Azure. Wenming shows how you can use Windows Azure to process massive amounts of work without having to own a Cray computer (even though he himself has three).
In the news:
Comments have been closed since this content was published more than 30 days ago, but if you'd like to continue the conversation,
please create a new thread in our Forums,
or
Contact Us and let us know.
Follow the Discussion
Oops, something didn't work.
What does this mean?
Following an item on Channel 9 allows you to watch for new content and comments that you are interested in. You need to be signed in to Channel 9 to use this feature.What does this mean?
Following an item on Channel 9 allows you to watch for new content and comments that you are interested in and view them all on your notifications page.sign up for email notifications?
Is there any special price for using HPC Scheduler SDK on Azure (on-line version)?
On the following web page:
http://www.windowsazure.com/en-us/home/tour/compute/
there is only price for the compute instance. There is nothing about HPC computing.
From the presentation I got an impression that it is necessary to copy separate executable file on each compute node separately.
Is there anything like UNC-path on azure? Is there anything like current directory on azure mpi cluster?
There is no special pricing for the HPC Scheduler, other than the components it uses:
CPU hours - head node role, compute role, and frontend role. You will be billed for the number of cpu hours those machine use, which depends on the type of machines and the number of instances you defined (the default is 5xSmall node) during the deployment.
Storage - to hold your deployed HPC applications, so you will be billed for the storage (GB/month), and for storage transaction (that can reach a couple of hundreds of thousands transactions per month, which is a couple of cents).
SQL Azure - the cluster uses a server with one database (other than the master), which is either 1 or 5 gb (depends on the technique of deployment). You will pay for those databases as you pay for other SQL Azure databases.
Of course if your client is outside the cloud, you will also be billed for download bandwidth of getting result from the cloud (upload of data is free in azure)
Thank you for the information about the pricing.
According to my experience in the area of hpc computing there is a lot of linux/unix software, which can be used also on the Windows platform. The only problem is the unix build system and basic scripting functionality (e.g. bash).
Adding something like MSYS and basic unix tools like in SUA but for Win32 to Widnows HPC Server and/or Azure would be probably a good idea. In this way utilization and development of open source software on Windows would be much faster.
There is SUA however, the support for SUA is very bad and this subsystem is deprecated in Windows 8. So it looks like it is better to stay away from that.
Remove this comment
Remove this thread
close