I was surprised to learn that AMD's Torrenza technology, which connects devices directly to the Hyper Transport links of the CPU, is not limited to a few extremely high-end niche markets (like Cray Inc., the supercomputer company).

Supermicro showed its H8QGL-6F+ to us. From a virtualization point of view, this is a pretty mediocre board: only 16 DIMM slots for a total of four G34 sockets, and thus a total of up 48 Opteron 6000 cores. However this board is not targeted at the huge virtualization market. Supermicro daisychained two I/O hub togethers to get 80 PCIe lanes. As a result the board can add the crunching power of  5 GPUs to the 48 Opteron cores .

The HTX slot offers a low latency 6.4 GB/s interface. Together with these kind of "NUMA connected" cards, it is easier to build a very low latency HPC cluster.

However, it seems that the HTX slot is at the end of its lifetime. The upcoming Xeons seem to come with a PCI-express 3.0 controller integrated,  so they should be able to offer a low latency interface of up to 12.8 GB/s, or twice as much.

If that is not enough crunching power for you, Supermicro presents you the Superserver 5086B-TRF.

Four daughterboards can each carry two 10-core Westmere-EX. That is good for 80 cores, 160 logical CPUs. Those who have been looking through the new specifications of the VMware vsphere 4.1 update 1 might have noticed that the maximum amount of logical CPUs has been increased from 128 (vSphere 4.1) to 160. No coïncidence if you ask us.

There are 10 PCIe 2.0 slots available, which should make it possible to add 4 GPUs. The maximum amount of memory is an impressive 2 TB (!!), if you equip the server with 64 mega expensive 32 GB DIMMs. At the moment, the server supports only 16 GB DIMMs, so you are "limited" to 1 TB.

This beast is powered by 2+2 Gold Level 2800W power supplies.

Atom Servers...
Comments Locked

17 Comments

View All Comments

  • Gami - Monday, March 14, 2011 - link

    Damn, I wish I was Limited to 1 TB of RAM right now.
  • AlExAkE - Tuesday, March 15, 2011 - link

    hahaha u wish u had such a problem hah? :) xxaxa I'd take my 4GB to the corner and stay there without saying anything...
  • vol7ron - Tuesday, March 15, 2011 - link

    I can hardly imagine what you would need that much RAM in a PC for. Servers I understand, PCs not so much.
  • Gami - Tuesday, March 15, 2011 - link

    for VM Hosts servers,
    after getting pass the first problem of storage space...

    the next problem is normally not enough Real Memory.
    4 CPUs with 24 Cores in total, can handle a lot of VMs, but you normally run out of storage space first (which can actually be resolved), but Memory, you've basically hit a Brick wall..
  • vbrisebo - Wednesday, March 16, 2011 - link

    Companies like V3sys.com use the Fusion-io cards to break past those barriers. They can run 50 to 100 VM's on one server as the Fusion-io card can serve as both storage and RAM for the VMs.
  • oneoho - Tuesday, March 15, 2011 - link

    werd, 1TB of ram? holy shiet think of the VMs!
  • Griswold - Monday, March 14, 2011 - link

    You spent only a few hours at the largest IT fair there is and come to the conclusion its becoming less international every year just because the few booths you visited mostly presented you with german material?

    Did you go there during the press days or public opening?
  • JMC2000 - Monday, March 14, 2011 - link

    "The HTX slot offers a low latency 6.4 GB/s interface. Together with these kind of "NUMA connected" cards, it is easier to build a very low latency HPC cluster.

    However, it seems that the HTX slot is at the end of its lifetime. The upcoming Xeons seem to come with a PCI-express 3.0 controller integrated, so they should be able to offer a low latency interface of up to 12.8 GB/s, or twice as much."

    I was just looking at the HTX specs/whitepapers, and HTX 3.0 has an aggregate bandwidth of 20.8GB/sec or 10.4GB/sec in each direction. Are you sure it is just a HTX 1.0/2.0 slot or is it HTX 3.0? All 6000-series Opterons support up to 3.2GHz or 6.4GT/s.
  • mino - Monday, March 14, 2011 - link

    Plus a lower latency on top of it.

    PCIe is not really a HTX competitor. That hypothetical QPI slot is.
  • MySchizoBuddy - Monday, March 14, 2011 - link

    When will we see Tegra 2 based Server.

Log in

Don't have an account? Sign up now