Physical Architecture

The physical architecture of Titan is just as interesting as the high level core and transistor counts. I mentioned earlier that Titan is built from 200 cabinets. Inside each cabinets are Cray XK7 boards, each of which has four AMD G34 sockets and four PCIe slots. These aren't standard desktop PCIe slots, but rather much smaller SXM slots. The K20s NVIDIA sells to Cray come on little SXM cards without frivolous features like display outputs. The SXM form factor is similar to the MXM form factor used in some notebooks.

There's no way around it. ORNL techs had to install 18,688 CPUs and GPUs over the past few weeks in order to get Titan up and running. Around 10 of the formerly-Jaguar cabinets had these new XK boards but were using Fermi GPUs. I got to witness one of the older boards get upgraded to K20. The process isn't all that different from what you'd see in a desktop: remove screws, remove old card, install new card, replace screws. The form factor and scale of installation are obviously very different, but the basic premise remains.

As with all computer components, there's no guarantee that every single chip and card is going to work. When you're dealing with over 18,000 computers as a part of a single entity, there are bound to be failures. All of the compute nodes go through testing, and faulty hardware swapped out, before the upgrade is technically complete.

OS & Software

Titan runs the Cray Linux Environment, which is based on SUSE 11. The OS has to be hardened and modified for operation on such a large scale. In order to prevent serialization caused by interrupts, Cray takes some of the cores and uses them to run all of the OS tasks so that applications running elsewhere aren't interrupted by the OS.

Jobs are batch scheduled on Titan using Moab and Torque.

AMD CPUs and NVIDIA GPUs

If you're curious about why Titan uses Opterons, the explanation is actually pretty simple. Titan is a large installation of Cray XK7 cabinets, so CPU support is actually defined by Cray. Back in 2005 when Jaguar made its debut, AMD's Opterons were superior to the Intel Xeon alternative. The evolution of Cray's XT/XK lines simply stemmed from that point, with Opteron being the supported CPU of choice.

The GPU decision was just as simple. NVIDIA has been focusing on non-gaming compute applications for its GPUs for years now. The decision to partner with NVIDIA on the Titan project was made around 3 years ago. At the time, AMD didn't have a competitive GPU compute roadmap. If you remember back to our first Fermi architecture article from back in 2009, I wrote the following:

"By adding support for ECC, enabling C++ and easier Visual Studio integration, NVIDIA believes that Fermi will open its Tesla business up to a group of clients that would previously not so much as speak to NVIDIA. ECC is the killer feature there."

At the time I didn't know it, but ORNL was one of those clients. With almost 19,000 GPUs, errors are bound to happen. Having ECC support was a must have for GPU enabled Jaguar and Titan compute nodes. The ORNL folks tell me that CUDA was also a big selling point for NVIDIA.

Finally, some of the new features specific to K20/GK110 (e.g. Hyper Q and GPU Direct) made Kepler the right point to go all-in with GPU compute.

Power Delivery & Cooling

Titan's cabinets require 480V input to reduce overall cable thickness compared to standard 208V cabling. Total power consumption for Titan should be around 9 megawatts under full load and around 7 megawatts during typical use. The building that Titan is housed in has over 25 megawatts of power delivered to it.

In the event of a power failure there's no cost effective way to keep the compute portion of Titan up and running (remember, 9 megawatts), but you still want IO and networking operational. Flywheel based UPSes kick in, in the event of a power interruption. They can power Titan's network and IO for long enough to give diesel generators time to come on line.

The cabinets themselves are air cooled, however the air itself is chilled using liquid cooling before entering the cabinet. ORNL has over 6600 tons of cooling capacity just to keep the recirculated air going into these cabinets cool.

Oak Ridge National Laboratory Applying for Time on Titan & Supercomputing Applications
POST A COMMENT

130 Comments

View All Comments

  • UltraTech79 - Monday, November 05, 2012 - link

    It could simulate a cpu/gpu though minecraft redstore that could play Crysis at 4K better than anything any of us have. Reply
  • yottabit - Wednesday, October 31, 2012 - link

    Probably about 5-10% more than 4 way SLI. LOL Reply
  • martixy - Thursday, November 01, 2012 - link

    And where exactly do you see a parallel between game code and a complex project like one of those? Reply
  • karasaj - Thursday, November 01, 2012 - link

    I'm not sure if you're trolling or don't get it. Reply
  • This Guy - Thursday, November 01, 2012 - link

    Looked on Bench. I can't find 18,688x Tesla K20's any where. I also looked for 18,688x AMD Optrons. This ain't like Anandtech. Normally Bench is updated when the article is released. Reply
  • jleach1 - Sunday, November 04, 2012 - link

    1GPU per CPU. No Sli here.

    These clusters dont parralelize workload like SLI does.
    Reply
  • lambchowder - Thursday, November 01, 2012 - link

    50 spreadsheets per second Reply
  • mike55 - Wednesday, October 31, 2012 - link

    This is pretty awesome. I'm jealous you got to go. The comment about the thickness requirement of the cables for 480V compared to 208V in the first power delivery video is staggering. I'm surprised there's such a difference.

    Some of the videos seem to be stopping early when I play them, and I have to skip ahead a bit to continue watching.
    Reply
  • Peanutsrevenge - Wednesday, October 31, 2012 - link

    I've had that problem with all youtube videos when I watch the HD stream for a while.
    It's not specific to Anandtech at all, for me at least.

    This doesn't happen with <480p video.

    Nice to know it's not just me
    Reply
  • B3an - Wednesday, October 31, 2012 - link

    Same. For me, most YouTube vids will get about 75% of the way through and then stop.

    And great article.
    Reply

Log in

Don't have an account? Sign up now