I promised in the blog post vNUMA: What it is and why it matters to share the full research paper with you when it became available. It can now be downloaded here . If you find the paper useful, please click to give it a star rating on that same page. As a reminder, here is the paper abstract: A major obstacle to virtualizing HPC workloads is a concern about the performance loss due to virtualization. We will demonstrate that new features significantly enhance the performance and scalability of virtualized HPC workloads on VMware’s virtualization platform. Specifically, we will discuss VMware’s ESXi Server performance for virtual machines with up to 64 virtual CPUs as well as support for exposing virtual NUMA topology...
Posts Tagged ‘ numa ’
vNUMA: What it is and why it matters
In vSphere 5 , we introduced vNUMA which allows interested guest operating systems to see that they are running on a NUMA (Non Uniform Memory Architecture) topology. For those not familar, here is a one-diagram NUMA explanation. As you can see, in the UMA case, the cost of accessing a particular memory address is the same regardless of which socket your program is running on. In the NUMA case, however, it does matter. With memory attached directly to each socket there can be significant performance penalties if an application gener ates large numbers of non-local memory accesses. The ESX hypervisor has been NUMA-aware for quite some time, making memory and CPU allocation decisions based on its full understanding of the topology...
VMware at HPCvirt 2011 in Bordeaux France
I am very excited that VMware had two papers accepted to the 5th Workshop on System Level Virtualization for High Performance Computing ( HPCvirt 2011 ), which will be held as part of Europar 2011 in Bordeaux on August 29th. My only regret is that I won’t be able to attend because this overlaps with VMworld 2011 at which I am scheduled to do two presentations. But there will be VMware engineers attending to present their work — very cool! Here are the abstracts for the papers accepted to HPCvirt 2011: Virtualizing Performance Counters by Benjamin Serebrin and Daniel Hecht Abstract: Virtual machines are becoming commonplace as a stable and flexible platform to run many workloads. As developers continue to move more workloads...
Virtual Cloud Infrastructure for HPC
Yesterday we announced a pile of new software releases all aimed at creating the integrated virtual cloud infrastructure needed to support cloud computing. Among the announcements was vSphere 5.0 , a major release of our virtualization platform. This quick post is intended to mention a few items of interest to HPC users. First, with vSphere 5.0 we now support virtual machines with up to 32 virtual CPUs (vCPUs) and 1 TB of memory, up from eight vCPUs and 256 GB in the current version. This is much friendlier to OpenMP and other threaded applications capable of consuming large amounts of on-node resources. We are also introducing virtual NUMA (vNUMA) support in vSphere 5.0, which should be of great interest to the HPC...
