By Jamie Lendino
While the US has plenty of representation in the current
TOP500 list of the fastest supercomputers in the world, it lost the #1
slot to China’s several years ago. President Obama wants to fix that
immediately, and as such has signed an executive order
Wednesday that dictates the creation of a coordinated federal strategy
for high-performance computing (HPC) research, development, and
deployment. It establishes the National Strategic Computing Initiative
(NSCI) — tasked with building the first exascale (1,000-petaflop)
system, and by extension the fastest supercomputer in the world.
The three lead agencies for the NSCI are the Department of Energy (DOE), the Department of Defense (D)D, and the National Science Foundation (NSF). In particular, the DOE Office of Science and the DOE National Nuclear Security Administration will together form a joint exascale computing program. The program would accelerate research and development in a variety of fields across the government, industry, and academia.
More specifically — here come the juicy parts — from a technical perspective, the order will establish the following:
The
order calls for beginning the implementation of NSCI within the next 90
days, and then providing updates for at least the next five years on
its progress.
The backdrop for all this is pretty obvious. Earlier this month, and for the fifth consecutive time, China’s Tianhe-2 remained in the lead as the fastest supercomputer in the world, according to the 45th edition of the twice-annual TOP500 list of the world’s most powerful supercomputers. The Tianhe-2 scored a Linpack benchmark performance of 33.86 petaflops, or quadrillions of floating-point calculations per second.
The second-fastest supercomputer in the world belongs to the US. It’s Titan (pictured at top), a Cray XK7 system located at the Department of Energy’s Oak Ridge National Laboratory — that one scores 17.59 petaflops. It spans a total of 38,400 processors: 19,200 Opteron 6200s and 19,200 Tesla GPUs.
The total combined performance of all 500 supercomputers on the list is 363 petaflops. The US has the most representation, with 233 of the 500 supercomputers, followed by Europe with 141. China has 37, down from 61 last year. An exascale supercomputer would be a tremendous leap, and be more powerful than all 500 supercomputers on the list put together. That’s assuming IBM or someone else doesn’t figure out quantum computing sooner than that, of course.
While the US has plenty of representation in the current
TOP500 list of the fastest supercomputers in the world, it lost the #1
slot to China’s several years ago. President Obama wants to fix that
immediately, and as such has signed an executive order
Wednesday that dictates the creation of a coordinated federal strategy
for high-performance computing (HPC) research, development, and
deployment. It establishes the National Strategic Computing Initiative
(NSCI) — tasked with building the first exascale (1,000-petaflop)
system, and by extension the fastest supercomputer in the world.The three lead agencies for the NSCI are the Department of Energy (DOE), the Department of Defense (D)D, and the National Science Foundation (NSF). In particular, the DOE Office of Science and the DOE National Nuclear Security Administration will together form a joint exascale computing program. The program would accelerate research and development in a variety of fields across the government, industry, and academia.
More specifically — here come the juicy parts — from a technical perspective, the order will establish the following:
- Accelerating delivery of a capable exascale computing system that integrates hardware and software capability to deliver approximately 100 times the performance of current 10 petaflop systems across a range of applications representing government needs. (emphasis added)
- Increasing coherence between the technology base used for modeling and simulation and that used for data analytic computing.
- Establishing, over the next 15 years, a viable path forward for future HPC systems even after the limits of current semiconductor technology are reached (the “post- Moore’s Law era”). (emphasis added)
- Increasing the capacity and capability of an enduring national HPC ecosystem by employing a holistic approach that addresses relevant factors such as networking technology, workflow, downward scaling, foundational algorithms and software, accessibility, and workforce development.
- Developing an enduring public-private collaboration to ensure that the benefits of the research and development advances are, to the greatest extent, shared between the United States Government and industrial and academic sectors.
NASA’s Pleiades supercomputer, currently #11 on the TOP500 list.
The backdrop for all this is pretty obvious. Earlier this month, and for the fifth consecutive time, China’s Tianhe-2 remained in the lead as the fastest supercomputer in the world, according to the 45th edition of the twice-annual TOP500 list of the world’s most powerful supercomputers. The Tianhe-2 scored a Linpack benchmark performance of 33.86 petaflops, or quadrillions of floating-point calculations per second.
The second-fastest supercomputer in the world belongs to the US. It’s Titan (pictured at top), a Cray XK7 system located at the Department of Energy’s Oak Ridge National Laboratory — that one scores 17.59 petaflops. It spans a total of 38,400 processors: 19,200 Opteron 6200s and 19,200 Tesla GPUs.
The total combined performance of all 500 supercomputers on the list is 363 petaflops. The US has the most representation, with 233 of the 500 supercomputers, followed by Europe with 141. China has 37, down from 61 last year. An exascale supercomputer would be a tremendous leap, and be more powerful than all 500 supercomputers on the list put together. That’s assuming IBM or someone else doesn’t figure out quantum computing sooner than that, of course.
No comments:
Post a Comment