We know that SSD's help any system perform better by reducing the storage bottlenecks we all experienced from hard disk drives. But how far can flash storage go in increasing performance if money is no object?? Enter the multi-million dollar world of supercomputers. Historically supercomputers have relied on the addition of more CPU cores to increase performance, but two new system projects funded by the National Science Foundation (NSF) will try a different approach: obscene amounts of high-speed flash storage!
The news comes as the NSF is requesting a cool $7 billion in research money for 2015, and construction has apparently already begun on two new storage-centered supercomputers. Memory and high-speed flash storage arrays will be loaded on the Wrangler supercomputer at Texas Advanced Computing Center (TACC), and the Comet supercomputer at the San Diego Supercomputer Center (SDSC).
Check out the crazy numbers from the TACC's Wrangler: a combination of 120 servers, each with Haswell-based Xeon CPU's, and a total of 10 petabytes (10,000TB!) of high performance flash data storage. The NSF says the supercomputer will have 3,000 processing cores dedicated to data analysis, with flash storage layers for analytics. The Wrangler supercomputer's bandwidth is said to be 1TB/s, with 275 million IOPS! By comparison, the Comet supercomputer will have “only” 1,024 Xeon CPU cores, with a 7 petabyte high-speed flash storage array. (Come on, guys… That’s like, wayyy less bytes.)
Supercomputer under construction…probably (Image credit CBS/Paramount)
The supercomputers are part of the NSF's “Extreme Digital” (XD) research program, and their current priorities are "relevant to the problems faced in computing today”. Hmm, kind of makes you want to run a big muilti-SSD deathwish RAID, huh?
Psh, way ahead of them with
Psh, way ahead of them with my 4x256gb 840 pro raid 0 config 🙂
As long as you have a use for
As long as you have a use for all those IOPs, then fine, otherwise it’s just a waste of money. I am waiting for descrete GPUs to finally get their own intregrated CPU cores and the ability to game, or fully compute will move off of just the motherboard and Fully onto the descrete card itself. Supercomputing will really come to the PC when home users can buy complete gaming/compute systems that can be plugged into a PCIe slot, and give the users an instent computiting cluster/s that is only limited by the number of PCIe slots on the motherboard, and the available power. I see no reason for home PC users to be limited in their ability to have a complete gaming console/computing platform on a PCI card form factor, as that would enable users to upgrade their systems more easily. One of the reasons PC sales are in a slump, besides Windows 8.*, is that PC users have grown tired of constantly having to upgrade their motherboards for more CPU power, or be limited by the high cost of multi-CPU die motherboards. Eventually the CPU will be merged with the GPU and even on descrete GPUs there will be complete CPU cores, and these systems SOCs will have the advantage of sharing a more powerfull GPU type of memory controller with a wide data bus to GDDR5 memory, without all the latency issues between the motherboard CPU to descrete GPU to deal with. These systems will probably incorporate a large on die RAM, and will really turn a home PC into a supercomputer.
Interesting!
Sebastian, I’m
Interesting!
Sebastian, I’m waiting for the link between the USS Entreprise and these super computers! “Computer; clarify this link Sebastian speaks of!” 😀
Ah 24th century Federation
Ah 24th century Federation computer technology based on isolinear chips. You are going to need a faster than light connection to tap in to all of that bandwidth, not to mention communicating with the the 24th century ship going warp 9, to watch all of those tribble videos.