On Tuesday at SC12 Microsoft debuted a set of "big compute" capabilities for its Windows Azure offering. The company is courting the HPC space with more powerful hardware, new instance configurations, and the updated Microsoft HPC Pack 2012. The advanced management software has many new features and supports the running of compute-intensive workloads in three configurations: on premise, on Windows Azure, or a mixed use, hybrid scenario.

Big Compute on Windows Azure – it's unclear whether that's the final name – is available in two configurations. The entry-level HPC instance sports 8 cores and 60 GB RAM, while the higher-end option doubles these specs for a total of 16 cores and 120 GB of RAM. The new servers are outfitted with dual Xeon E5-2670s (2.6 GHz) with DDR3 1600 MHz RAM. The nodes are linked via a 40 Gbps InfiniBand network with RDMA, while a 10GbE backplane is used to hook up to external storage and the Internet.

The new configurations call to mind Amazon's High-Memory Instances. The High-Memory Double Extra Large Instance (m2.2xlarge) has 4 virtual cores with 34 GB of memory, while the High-Memory Quadruple Extra Large Instance (m2.4xlarge) has 8 virtual cores and 68.4 GB of memory.

An important distinction, however, is that Amazon is using 10GbE interconnect technology – and then only in its Cluster Compute and Cluster GPU instances – while Microsoft is introducing the ability to do RDMA (remote direct memory access) in a virtualized environment. The technology provides low-latency network capability for MPI (message passing interface) applications and allows an Azure cluster to send a 4 byte packet across machines in 2.1 microseconds. Alex Sutton, group program manager for Windows HPC Server, interviewed for this article at SC12, said that Microsoft is the first company to offer virtualized RDMA in a commercial environment.

"For applications written to use the message passing interface (MPI) library, RDMA allows memory on multiple computers to act as one pool of memory," writes Bill Hilf, general manager, Windows Azure Product Marketing, in a blog entry. "Our RDMA solution provides near bare metal performance (i.e., performance comparable to that of a physical machine) in the cloud, which is especially important for Big Compute applications."

According to Sutton, the performance penalty for running virtualization is down to about a 1 or 2 percent difference now. This will appeal to organizations that want to access the benefits of cloud (flexibility, scalability, on-demand, etc.), but aren't willing to sacrifice performance. The use of InfiniBand also enhances throughput, allowing applications to scale more effectively and improving time to results.

As a proof of concept, Microsoft ran the LINPACK benchmark across 504 16-core virtual machines (8,064 cores total). The test cluster, named Faenov, achieved 151.3 teraflops (167.7 peak) with 90.2 percent efficiency, earning it the 165th spot on the most recent TOP500 list. In terms of efficiency, the system placed 27th. Faenov ran Windows Server 2012 in virtual machines hosted on Windows Azure on top of Hyper-V virtualization. Sutton makes the point that 90.2 percent efficiency is better than many on-premise (non-virtualized) clusters.

Bringing system I/O latency under control still leaves the bandwidth barrier that is the consumer Internet, but for the majority of customers, this won't be an issue. For those that need to make large data transfer into and out of the cloud, Microsoft plans to support "FedEx net," (physical shipping of drives) at some point.

Pricing on the new configurations has not been announced, so price point comparisons to EC2, Google Compute Engine and other IaaS offerings won't be possible yet. Initially "Big Compute" will only run Windows, but they are looking into Linux. Of course, the hardware can support Linux, but the engineers still need to hammer out how to run it on virtualized RDMA.

Microsoft is describing early success stories around a segment of customers who run Windows and need low-latency. Initial interest and customer stories are in the areas of risk modeling, disease research and complex engineering tasks. Big data is also on Microsoft's radar, as the company anticipates many big data workloads benefiting from the new configurations.

Today's announcement shows us a Microsoft that continues to evolve on the cloud front, both to compete against EC2 and in its support for the HPC community. Azure was originally launched as a PaaS offering in 2010, but in June of this year, Microsoft added infrastructure as a service (IaaS) capabilities and began allowing users to spin up Linux VMs. Customers want choice, but with its purpose-built architecture and significant lead time, Amazon is going to be tough to catch. Microsoft has a dedicated following of Windows users, but most of the action in the HPC community is around Linux.

It will be interesting to see whether low-latency virtualization pans out as a differentiator for Azure. It might take some R&D work, but Amazon could similarly outfit their cloud if they see a call for it. In order for the cloud to be profitable, it has to maintain the right balance of utilization. Too much extra inventory is as bad for business in the long run as too little inventory is in the short run. Cloud companies want just the right about of cushion (or excess inventory). To this point, Microsoft says that it is tracking demand and keeping tight control on the ordering process.

Big Compute on Windows Azure is currently in private preview with select partners. A public beta period is expected to commence in the first half of 2013, followed by general availability in roughly the same time frame.