Posted on 06/09/2008 11:50:57 AM PDT by Ernest_at_the_Beach
Armonk (NY) – IBM is prepared to deliver the Roadrunner supercomputer to the Department of Energy’s National Nuclear Security Administration (NNSA). The system was development over the past 18 months and is not only the first hybrid supercomputer using Cell processors, but also the first commercial system to exceed a performance of 1 PFlops.
Roadrunner is the NNSA’s third IBM-built supercomputer, adding to two IBM-built supercomputers at the Lawrence Livermore National Laboratory: BlueGene/L, completed in 2005, has 131,072 p5 processors and delivers a sustained performance of 280.6 TFlops. The 12,208 processor ASC Purple is estimated to provide a sustained performance of 75.8 teraflops.
The new Roadrunner, which is currently disassembled and will be shipped to the NNSA within 30 days, according to IBM, was originally described to deliver about 2.8x (3.5x peak: 1.6 TFlops ) the combined processing power of BlueGene/L and ASC Purple. Back in 2006, IBM said that the system would bet more than 16,000 Opteron processor cores and more than 16,000 Cell BE CPUs to deliver on the Petaflop goal.
The final system ended up with less processors – 13,896 Opteron cores (6948 dual-core processors) as well as 12,960 Cell BE chips with a total of 116,640 PPE and SPE cores for a combined 130,536 cores. The original design called for about 176,000 cores.
According to IBM, Roadrunner has the floating point performance of about 100,000 notebooks. To describe the horsepower of the system, IBM said that Roadrunner can do in one day what would take the entire population of the world 46 years on handheld calculators, assuming a pace of one second per calculation.
Other interesting facts of the supercomputer, which IBM said cost about $100 million, include a power consumption of about 3.9 Mwatts, as well as a structure that includes 80 TB of memory, 576 miles of fiber optic cable as well as 3456 tri-blades which can deliver 400 GFlops each.
Also noteworthy is that Roadrunner was supposed to become the flagship product of AMD’s Torrenza platform, a project which was pitched as an open AMD x86 platform that takes advantage of Direct Connect Architecture and the Hypertransport interface. However, we haven’t heard much about Torrenza anymore and we don’t expect AMD to make a big deal of it.
They’re probably getting the PF number through their extrapolation program. They run one unit through the linpack, the use a program to extrapolate the results so they don’t have to bother running the long HPLs.
Consider that it’s going to the NNSA, I doubt if that will be a problem.
It’s less than that crashed B2....
I don't don't about the availability of the compiler, though.
If you look at the architecture of the new Intel processors they are more akin to the Socket A AMD and the Mobile P3 processors...
C2D had to step backwards to where AMD and Intel had been there and done that...
Proving that Instructions per clock trumps final speed.
Intel rode that pony until it died...
National Nuclear Security Administration
From Wikipedia, the free encyclopedia
********************EXCERPT******************
The United States National Nuclear Security Administration (NNSA) is part of the United States Department of Energy. It works to improve national security through the military application of nuclear energy. The NNSA also maintains and improves the safety, reliability, and performance of the United States nuclear weapons stockpile, including the ability to design, produce, and test, in order to meet national security requirements.
NNSA has four missions with regard to National Security:
The NNSA maintains a database containing personal information on 37,000 persons who design and maintain nuclear weapons for the U. S. government.
The NNSA's Office of Secure Transportation (OST) provides safe and secure transportation of nuclear weapons and components and special nuclear materials, and conducts other missions supporting the national security of the United States of America. Since 1974, OST has been assigned responsibility to develop, operate, and manage a system for the safe and secure transportation of all government-owned, DOE or NNSA controlled special nuclear materials in "strategic" or "significant" quantities. Shipments are transported in specially designed equipment and are escorted by armed federal agents.
Damn it all man, what about the Flux Capacitor??!!
AMD is still whopping them in the heavy duty heavy data moving department...know as the Server marketplace.
Do we still need that?
Well duh!
How else to we keep the dust out of the core memory?
ROFL!
I thing that has been gone for awhile now....
The PS3s being used to help achieve petaflop processing with Folding@Home kind of proved a system like this would be useful.
A high-performance IBM XL Fortran compiler for the Cell Broadband Engine Processor.
So there is a compiler....for the Cell.
I understood “of,” “and,” and “the.”
**********************EXCERPT********************
Single precision floating point computation is geared for throughput of media and three-dimensional graphics objects. In this vein, the decision to support only a subset of IEEE floating point arithmetic and sacrifice full IEEE compliance was driven by the target applications. Thus, multiple rounding modes and IEEE-compliant exceptions are typically unimportant for these workloads, and are not supported. This design decision is based the real time nature of game workloads and other media applications: most often, saturation is mathematically the right solution. Also, occasional small display glitches caused by saturation in a display frame is tolerable. On the other hand, incomplete rendering of a display frame, missing objects or tearing video due to long exception handling is objectionable.
FAST
I don't know what that means...any idea?
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.