learn more about AMD’s current and future technology and how we are using VMware’s leading edge products as a center point for Cloud Computing.
AMD SUPER SESSION: Journey to the CORE (SUP1002)
Wednesday, August 31st – 1:00 p.m.
Join AMD's GM of server products, Pat Patla, AMD’s Server CTO, Don Newell, and VMware’s Chief Platform Architect, CTO Office, Rich Brunner as they present a look in to the future of virtualization and cloud computing. We will be highlighting AMD’s innovative use of VMware View to support engineering efforts and will feature customer Digital Globe who provides high-resolution earth imaging satellites and a comprehensive geo-information product and is using AMD/VMware technology as a core component of their business.
Advanced Multi-core Architecture for Unlimited Virtualization Possibilities (SPO3968) - Tim Mueting
Tuesday, August 30th - 4:30 p.m.
Server and virtualization technology continue to evolve at an incredible pace, enabling some of the most demanding, business critical workloads to efficiently run in a virtualized environment. As the number of processor cores and the amount of memory bandwidth continue to increase, it is becoming more and more important to configure your virtualization environment to take full advantage of these resources while keeping your power and cooling costs under control. During this session you will learn about important vSphere scheduling parameters, which will enable you to get the most out of your current server and virtualization investment. In addition, this session will give you an overview of AMD’s next generation processor, featuring a completely new redesigned core architecture codenamed “Bulldozer,” and demonstrate how it will provide unprecedented performance and value. We will also highlight real world vSphere implementations on AMD OpteronTM based servers, showcasing the advantages gained by using this powerful virtualization combination.
Scaling Memcached - Harnessing the Power of Virtualization (SPO2115) - Dr. Rema Hariharan
Thursday, September 1st - 11:00 a.m. Memcached is a distributed memory object caching system used to speed up data access by large cloud/web2.0 service providers such as Facebook, Twitter, YouTube, and Flickr. Previous studies have indicated that memcached is thread limited, not scaling in performance beyond 4-6 threads on linux and a slightly higher number of threads in some proprietary operating systems. This severely limits the usage of the number of cores on the native system restricting the scaling to horizontal scaling only, requiring more and more systems as the workload scales up.
The study presented here, demonstrates a 12-times improvement in throughput using ESX with 24 VMs(from 350K req/sec to 5M requests/s), while keeping the response times below a value of 100 ms. Our study indicates that the throughput levels scale linearly with the number of VMs used, thus making it attractive to use systems with larger number of cores. All our data and analysis are based on measurements using AMD Opteron Processor - 6000 Series platform.
Expiring the announcement will not delete it but will remove it from the public announcement list. Are you sure you want to expire this announcement?
Are you sure you want to delete this announcement?
