Head in the Clouds

I have something to confess.  Just when I think specialty server design can’t get any better or more interesting, I am proven wrong.  Even since Dell’s Data Center Solutions team was founded and kept coming up with more dense, more powerful, more efficient servers, I thought to myself that at some point we were going to get to a place where we just can’t do something so unique and so revolutionary that literally everyone you show it to says “wow…I really need one of those for <insert favorite application here>”…until now.  With the release today of the PowerEdge c8000 server, you can have your system any way you want it.Why is this so interesting?  The PowerEdge c8000 is the first and only platform that enables mix and match of compute, storage and GPU in the same 4U shared infrastructure chassis. Flexibility, density, performance and efficiency, all in one platform.  Nobody else does this, and when you look at the potential configuration options and how this product scales, you quickly see that you can start with a single chassis and ramp it up as far as your imagination will take you.

Mix and Match Compute, Compute/GPU and Storage Sleds

The PowerEdge c8000 shared infrastructure chassis holds up to eight single-wide sleds or four double-wide sleds. Each compute sled is equivalent to a standard server built with a processors, memory, network interface, baseboard management controller, and local hard drive storage. Dell customers can speed up their most resource-intensive workloads by mixing and matching the following compute, GPU/coprocessor and storage sleds in the same 4U chassis:

• The PowerEdge c8220 compute sled: packs a lot of compute power in a dense space. Up to eight c8220 nodes can slide into the C8000 chassis mounted on specially-designed single-width sleds, delivering the compute power of up to 16 next-generation processors in just 4U of rack space.
• The PowerEdge c8220X compute/GPU sled: further increases the performance and compute/memory density per rack, as well as allowing the use of GPUs and other accelerators. Customers can run multiple workloads in a single chassis in scientific visualizations and other resource-intensive workloads.
• The PowerEdge c8000XD storage sled: fits up to 1.4x more local storage in 40U of rack space. This sled is ideal for workloads requiring flexible storage expansion, such as HPC, Hadoop and hosting environments.

One of the early adopters of the c8000 is the Texas Advanced Computing Center (TACC).  They are leveraging the performance and flexibility benefits of the PowerEdge C8000 series in its new supercomputer “Stampede” which is expected to become a model for supporting petascale-level computational science.