VizWorld.com

Earlier this week, NVidia and NextIO announced that NextIO is taking over the Tesla S-series product. If you’re not familiar with the S-Series Tesla, it’s the rack-mount product that carries 4 Tesla cards in a 1U chassis, used by several GPU-computing clusters.  It uses a small half-height PCIe Expansion card to connect to the external box, and allows you to put GPU compute capability in the popular CPU-dense cluster designs from the major manufacturers.  NextIO will be taking over the product and they’re using Nvidia’s existing supply chain and their own, and they’ve rebranded it the “vCORE Express”.  They’re here at GTC talking about the product, their plans, and showing off some of their other options.

NextIO is known in the industry for their impressive PCI expansion and virtualization technology.  You can read my SC09 report, but to sum it up, their appliances enable:

• Connecting multiple PCIe devices up to multiple servers,
• Assigning any combination of these devices to any combination of the servers.
• Device virtualization for SR-IOV and MR-IOV devices (mainly Network interfaces)
• Hot-swap capability for any PCIe Device
• Full GUI & commandline control of everything.

It’s a great device for large datacenters that can solve many of the power, heating, and reliability issues of things like GPUs and Network interfaces by putting them all in a separate unit, making it easier to maintain and reducing downtime.  Imagine if the next time you lost a network interface or fried a GPU, you didn’t have to reboot the node to replace it?

So here at GTC, they’ve announced the vCORE Express product.  Currently, it’s an exact copy of the existing NVidia Tesla-S series product, offering 4 Tesla cards in a 1U Chassis connected to 2 servers.  Currently, it offers none of the “secret sauce” that makes NextIO attractive, but that’s a temporary situation.  NextIO is already looking to add more to the device, but what’s even better is the upcoming “vCORE Extreme” product.

Read more…

Hardware feature, nextio

It’s been while since we reporting on NextIO and their impressive PCI-Express virtualization and expansion technology.  Looks like they’ve been busy tho, and have just announced their newest product: The vCORE Express.  It’s a tiny 1U expansion system that is the first 1U to support the new Fermi-powered NVidia Tesla M2070 GPU’s.

vCORE Express is designed especially for parallel computing applications using NVIDIA Tesla 20-Series GPUs in cluster and datacenter deployments.  With four massively parallel CUDA-enabled GPUs in a 1U system, vCORE Express brings economies of scale to GPU customers by delivering the same performance of a traditional CPU-based cluster – all at 10 percent of the cost and five percent of the power consumption.

That right, four Tesla M2070′s in a 1U space.  The press release is a bit light on technical details, but you can read the Spec Sheets on the new website.  From the announcement, it sounds like NVidia has basically shut down their own internal 1U Tesla product and handed it over to NextIO to manage, which is smart since NextIO already has the necessary skills and technology to pull it off.  From their FAQ:

Q: Why is NextIO taking over the NVIDIA Telsa S-Series Product?

A: NextIO is focused on consolidating and virtualizing I/O. This includes traditional IO such as storage and network, but also GPU computing. The partnership of NVIDIA and NextIO is a perfect fit; allowing NVIDIA to continue focusing on their core competency of GPU development and NextIO to augment our product line of consolidated I/O to fit the needs of GPGPU customers.

I have a meeting with NextIO Wednesday and I’ll be sure to get you more information then!

Full press release after the break.

Update 9/22 7:14am – New header graphic, with corrected spelling.
Read more…

Hardware nextio, nvidia

Last week’s feature on the NextIO PCI-Express Virtualization & Expansion appliance drew some questions on what kind of bandwidth you could expect from the device.  Some people believed that you could get a full x16 of bandwidth out of it, so I sent the question on to NextIO and here’s their response:

GPU density and performance per server is application dependent. The NextIO appliances support multiple x8 Gen2 PCIe connections per server and a Gen2 PCIe connection per GPU. As a user adds more GPUs to the cluster, more bandwidth to the server can be added based on application demand. By way of comparison, the nVidia Tesla S1060 GPU appliance supports 4 GPUs with 2 x16 Gen2 server connections. This is an average of x8 Gen2 per GPU. The same server bandwidth is available with the NextIO appliance. Additionally, if an application does not require full x8 per GPU, more GPUs may be consolidated per server connect.

So essentially they say that the existing “top of the line” offering from NVidia, the S1060, offers 4 GPU’s on 2 x16 connections, giving you an effective x8 to each card, which is the same as their offering.

NextIO – PCIe Expandability, Virtualization, & Hot Swap | VizWorld.com.

Hardware feature, nextio

How many times have you looked at your motherboard in despair at the meager 2 or 3 PCI express slots? Maybe you’re one of the lucky people with the new Tyan board and have 6 or 8? As more and more power-hungry and io-hungry devices come to market, the PCIe bus is used more and more. Devices Like PCIe SSD disks, high speed networking interconnects, and (of course) GPUs are all fighting fir those precious slots. And, of course, Murphy’s Law dictates that just as your cluster is fully assembled and online, something will need to be upgraded or replaced.

NextIO has an intriguing solution for this common problem, but it’s not one many people have thought of. With their existing N1400-PCM, you can expand your PCIe bus out to an impressive 14 slots, and 24 with their newest product (N2800-ICA). But it doesn’t end there.

The NextIO product feature can be summed up in a few short words: extensibility, virtualization, and hot swap. These aren’t words people typically associate with PCIe devices, but the NextIO solution makes them all possible.

Read more…

Hardware feature, nextio, sc09

NextIO and NVidia have announced a partnership that will mix the NextIO Adaptive PCIe chassis and management software with Nvidia’s Tesla and Quadro GPU’s to provide pre-packaged GPU computing solutions.  The NextIO management software allows servers to be mapped across PCIe up to 10 GPU’s simultaneously.

“Our customers in the oil and gas, medical imaging, and simulation markets have been demanding low- cost, high-performance GPU solutions from NextIO as a means to scale their compute applications to 50 percent or greater workloads,” said K.C. Murphy, CEO, NextIO. “Our partnership with NVIDIA will provide turnkey supported NVIDIA solutions to those customers looking for scale-out solutions.”

via HPCwire: NextIO, NVIDIA Partner to Advance CUDA Development.

Hardware cuda, gpgpu, nextio, nvidia