IBM Sequoia

From Wikipedia, the free encyclopedia
Jump to: navigation, search
IBM Sequoia
Sequoia6.1000pix.jpg
Operators LLNL
Location Livermore, Alameda County,
SFBA, Northern California,
United States
Power 7.9 MW
Operating system CNK operating system
Red Hat Enterprise Linux
Space 3,000 square feet (280 m2)
Memory 1.5 PiB
Speed 16.32 PFLOPS
Purpose Nuclear weapons, astronomy, energy, human genome, and climate change

IBM Sequoia is a petascale Blue Gene/Q supercomputer constructed by IBM for the National Nuclear Security Administration as part of the Advanced Simulation and Computing Program (ASC). It was delivered to the Lawrence Livermore National Laboratory (LLNL) in 2011 and was fully deployed in June 2012.[1]

On 14 June 2012, the TOP500 Project Committee announced that Sequoia replaced the K computer as the world's fastest supercomputer, with a LINPACK performance of 16.32 petaflops, 55% faster than the K computer's 10.51 petaflops, having 123% more cores than the K computer's 705,024 cores. Sequoia is also more energy efficient, as it consumes 7.9 MW, 37% less than the K computer's 12.6 MW.[2][3]

As of 17 June 2013, Sequoia had dropped to #3 on the TOP500 ranking, behind Tianhe-2 and Titan.[4] It is still #3 on the TOP500 ranking of November 2013.[5]

Record-breaking science applications have been run on Sequoia, the first to cross 10 petaflops of sustained performance. The cosmology simulation framework HACC achieved almost 14 petaflops with a 3.6 trillion particle benchmark run,[6] while the Cardioid code,[7][8] which models the electrophysiology of the human heart, achieved nearly 12 petaflops with a near real-time simulation.

The entire supercomputer runs on Linux, with CNK running on over 98,000 nodes, and Red Hat Enterprise Linux running on 768 I/O nodes that are connected to the Lustre filesystem.[9]

Dawn prototype[edit]

IBM built a prototype, called "Dawn," capable of 500 teraflops, using the Blue Gene/P design, to evaluate the Sequoia design. This system was delivered in April 2009 and entered the Top500 list at 9th place in June 2009.[10]

Purpose[edit]

Sequoia will be used primarily for nuclear weapons simulation, replacing the current Blue Gene/L and ASC Purple supercomputers at Lawrence Livermore National Laboratory. Sequoia will also be available for scientific purposes such as astronomy, energy, lattice QCD, study of the human genome, and climate change.

Design[edit]

Node architecture[edit]

Sequoia is a Blue Gene/Q design, building off previous Blue Gene designs. It consists of 96 racks containing 98,304 compute nodes [1024/rack]. The compute nodes are 16-core PowerPC A2 processor chips with 16 GB of DDR3 memory each. Thus the system contains in total 1,572,864 processor cores [96*1024*16] with 1.5 PiB memory. It covers an area of about 3,000 square feet (280 m2). The computer nodes are interconnected in a 5-dimensional torus topology.

Job scheduler[edit]

LLNL will use the SLURM job scheduler, which is also used by the Dawn prototype and China's Tianhe-IA, to manage Sequoia's resources.[11]

Filesystem[edit]

LLNL uses Lustre as the parallel filesystem, and has ported ZFS to Linux as the Lustre OSD (Object Storage Device) to take advantage of the performance and advanced features of the filesystem.[12]

In Sept 2011, NetApp announced that the DoE had selected the company for 55 PB of storage.[13][14]

Power usage[edit]

The complete system will draw about 6 MW of power but is projected to have an unprecedented efficiency in performance per watt. The Sequoia design will perform 3000 Mflops/watt, about 7 times as efficient as the Blue Gene/P design it is replacing, and more than 3 times as efficient as a prior (June 2011) Top 500 leader.[15][16]

Application[edit]

In January 2013, the Sequoia sets the record for the first supercomputer using more than one million computing cores at a time for a single application. The Stanford Engineering's Center for Turbulence Research (CTR) used it to solve a complex fluid dynamics problem — the prediction of noise generated by a supersonic jet engine.[17][18]

See also[edit]

References[edit]

  1. ^ NNSA awards IBM contract to build next generation supercomputer, February 3, 2009
  2. ^ "TOP500 Press Release: Lawrence Livermore’s Sequoia Supercomputer Towers above the Rest in Latest TOP500 List". TOP500. July 14, 2012. 
  3. ^ Naveena Kottoor (18 June 2012). "BBC News - IBM supercomputer overtakes Fujitsu as world's fastest". BBC News. 
  4. ^ "China’s Tianhe-2 Supercomputer Takes No. 1 Ranking on 41st TOP500 List". TOP500. June 17, 2013. 
  5. ^ "Top500 List - November 2013". TOP500. November 2013. 
  6. ^ S. Habib, V. Morozov, H. Finkel, A. Pope, K. Heitmann, K. Kumaran, T. Peterka, J. Insley, D. Daniel, P. Fasel, N. Frontiere, and Z. Lukic. "The Universe at Extreme Scale: Multi-Petaflop Sky Simulation on the BG/Q". 
  7. ^ "Cardioid Cardiac Modeling Project". 
  8. ^ "Venturing into the Heart of High-Performance Computing Simulations". 
  9. ^ "IBM supercomputer overtakes Japan's Fujitsu as world's fastest". TechSpot. June 18, 2012. 
  10. ^ Dawn Ranking History
  11. ^ Multi-Petascale Computing on the Sequoia Architecture 17 June 2009
  12. ^ ZFS on Linux for Lustre April 13, 2011, Brian Behlendorf, LLNL
  13. ^ U.S. Department of Energy Selects NetApp as the Storage Foundation for One of the World’s Most Powerful Supercomputers, September 28, 2011
  14. ^ Sequoia's 55PB Lustre+ZFS Filesystem on YouTube, 24-Apr-2012, RichReport
  15. ^ The Top500 List - June 2011
  16. ^ The Green500 List - June 2011
  17. ^ "Stanford Researchers Break Million-core Supercomputer Barrier"Standford Engineering, 25 January 2013.
  18. '^ Stanford engineering Videoss channel on YouTube, 30 January 2013.

External links[edit]

Records
Preceded by
K Computer
10.51 petaflops
World's most powerful supercomputer
June 2012 – November 2012
Succeeded by
Titan
17.59 petaflops