Dryad and DryadLINQ in Beta
I’ve just seen the news on the Windows HPC blog that Dryad and DryadLINQ are now in beta:
If you’re wondering what Dryad is, Daniel Moth has blogged a great collection of introductory links; and Jamie and I have been following Dryad for some time too. Although it seems like its integration with SSIS has fallen by the wayside its relevance for very large-scale ETL problems remains: it will allow you to crunch terabytes or petabytes of data in a highly parallel way. And given that you can now join Windows Azure nodes to your HPC cluster, it sounds like it’s a solution that can scale out via the cloud, making it even more exciting. I hope the people working on Microsoft’s regular and cloud BI solutions are talking to the HPC/Dryad teams.