Sequoia (supercomputer)
{{Short description|IBM supercomputer at Lawrence Livermore National Laboratory}}
{{Use mdy dates|date=October 2014}}
{{Infobox custom computer
| Image = frameless
| Caption =
| Dates =
| Operators = LLNL
| Sponsors =
| Location = Livermore, California,
United States
| Architecture =
| Memory = 1.5 PiB
| Storage =
| Speed = 20.13 PFLOPS
| Power = 7.9 MW
| OS = CNK operating system
Red Hat Enterprise Linux
| Space = {{convert|3000|sqft|m2}}
| Cost = {{USD|250 million}}{{cite news|last1=Brodkin|first1=John|title=With 16 petaflops and 1.6M cores, DOE supercomputer is world's fastest|url=https://arstechnica.com/information-technology/2012/06/with-16-petaflops-and-1-6m-cores-doe-supercomputer-is-worlds-fastest/|access-date=17 August 2019|publisher=Ars Technica|date=18 June 2012}} (undisclosed by IBM{{cite web|title=IBM US nuke-lab beast 'Sequoia' is top of the flops|url=https://www.theregister.co.uk/2012/06/18/top_500_supercomputers_june_2012/|website=The Register}}); equivalent to ${{Inflation|US|250|2011}} million in {{Inflation/year|US}}
| ChartName =
| ChartPosition =
| ChartDate =
| Purpose = Nuclear weapons, astronomy, energy, human genome, and climate change
| Legacy =
| Emulators =
| Website =
| Sources =
}}
IBM Sequoia was 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.[https://www.llnl.gov/news/newsreleases/2009/NR-09-02-01.html NNSA awards IBM contract to build next generation supercomputer], February 3, 2009 Sequoia was dismantled in 2020, its last position on the top500.org list was #22 in the November 2019 list.
On June 14, 2012, the TOP500 Project Committee announced that Sequoia replaced the K computer as the world's fastest supercomputer, with a LINPACK performance of 17.17 petaflops, 63% 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.{{cite web |url=http://www.top500.org/lists/2012/06/press-release |title=TOP500 Press Release: Lawrence Livermore's Sequoia Supercomputer Towers above the Rest in Latest TOP500 List |publisher=TOP500 |date=July 14, 2012 |url-status=dead |archive-url=https://web.archive.org/web/20120807052400/http://www.top500.org/lists/2012/06/press-release |archive-date=August 7, 2012 |df=mdy-all }}{{cite web |url=https://www.bbc.com/news/technology-18457716 |title=BBC News – IBM supercomputer overtakes Fujitsu as world's fastest |publisher=BBC News |date= June 18, 2012 |author=Naveena Kottoor}}
{{As of|November 2017}}, Sequoia had dropped to sixth place on the TOP500 ranking, while it was at third position on June 17, 2013, behind Tianhe-2 and Titan.{{cite web |url=http://www.top500.org/blog/lists/2013/06/press-release/ |title= China's Tianhe-2 Supercomputer Takes No. 1 Ranking on 41st TOP500 List |publisher=TOP500 |date=June 17, 2013}}
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,{{ cite arXiv | eprint=1211.4864| title=The Universe at Extreme Scale: Multi-Petaflop Sky Simulation on the BG/Q |author1=S. Habib |author2=V. Morozov |author3=H. Finkel |author4=A. Pope |author5=K. Heitmann|author5-link=Katrin Heitmann |author6=K. Kumaran |author7=T. Peterka |author8=J. Insley |author9=D. Daniel |author10=P. Fasel |author11=N. Frontiere |author12=Z. Lukic | class=cs.DC | year=2012 }} while the Cardioid code,{{ cite web | url=http://researcher.watson.ibm.com/researcher/view_project.php?id=2992 | title=Cardioid Cardiac Modeling Project}}{{ cite web | url=https://str.llnl.gov/Sep12/streitz.html| title=Venturing into the Heart of High-Performance Computing Simulations}} which models the electrophysiology of the human heart, achieved nearly 12 petaflops with a near real-time simulation.
The entire supercomputer ran 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.{{cite web |title=IBM supercomputer overtakes Japan's Fujitsu as world's fastest |work=TechSpot |url=http://www.techspot.com/news/49026-ibm-supercomputer-overtakes-japans-fujitsu-as-worlds-fastest.html |date=June 18, 2012 }}
Dawn prototype
File:U.S. Department of Energy - Science - 477 020 010 (9444537887).jpg
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.[http://top500.org/system/ranking/9900 Dawn Ranking History] {{webarchive|url=https://web.archive.org/web/20101201143722/http://top500.org/system/ranking/9900 |date=December 1, 2010 }}
Purpose
Sequoia was used primarily for nuclear weapons simulation, replacing the current Blue Gene/L and ASC Purple supercomputers at Lawrence Livermore National Laboratory. Sequoia was also available for scientific purposes such as astronomy, energy, lattice QCD, study of the human genome, and climate change.
Design
=Node architecture=
Sequoia was a Blue Gene/Q design, based on previous Blue Gene designs. It consisted of 96 racks containing 98,304 compute nodes, i.e., 1024 per rack. The compute nodes were 16-core A2 processor chips with 16 GB of DDR3 memory each. Thus, the system contained a total of 96·1024·16 = 1,572,864 processor cores with 1.5 PiB memory. It covered an area of about {{convert|3000|sqft|m2}}. The compute nodes were interconnected in a 5-dimensional torus topology.
=Job scheduler=
LLNL used the SLURM job scheduler, also used by the Dawn prototype and China's Tianhe-IA, to manage Sequoia's resources.[https://hpcrd.lbl.gov/scidac09/talks/Seager-Sequoia4SciDACv1.pdf Multi-Petascale Computing on the Sequoia Architecture] {{webarchive|url=https://web.archive.org/web/20110807145429/https://hpcrd.lbl.gov/scidac09/talks/Seager-Sequoia4SciDACv1.pdf |date=August 7, 2011 }} June 17, 2009
=Filesystem=
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.[http://zfsonlinux.org/docs/LUG11_ZFS_on_Linux_for_Lustre.pdf ZFS on Linux for Lustre] {{webarchive|url=https://web.archive.org/web/20141031152502/http://zfsonlinux.org/docs/LUG11_ZFS_on_Linux_for_Lustre.pdf |date=October 31, 2014 }} April 13, 2011, Brian Behlendorf, LLNL
In September 2011, NetApp announced that the DoE had selected the company for 55 PB of storage.[http://www.netapp.com/us/company/news/news-rel-20110928-990734.html U.S. Department of Energy Selects NetApp as the Storage Foundation for One of the World’s Most Powerful Supercomputers], September 28, 2011{{YouTube|c5ASf53v4lI|Sequoia's 55PB Lustre+ZFS Filesystem}}, April 24, 2012, RichReport
=Power usage=
The complete system drew about 7.8 MW of power, but had a unprecedented energy efficiency, performing 2068 Mflops/watt, about 6 times as efficient as Dawn, and more than 2.5 times as efficient as the June 2011 Top 500 leader.[http://www.top500.org/lists/2011/06 The Top500 List – June 2011]
Application
In January 2013, Sequoia set 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{{snd}} the prediction of noise generated by a supersonic jet engine.[http://engineering.stanford.edu/news/stanford-researchers-break-million-core-supercomputer-barrier "Stanford Researchers Break Million-core Supercomputer Barrier"]Standford Engineering, January 25, 2013.{{YouTube|user=stanfordeng|title=Stanford engineering Videos}}, January 30, 2013.
See also
{{commons category}}
References
{{Reflist|30em}}
External links
- [https://web.archive.org/web/20110526004140/http://www-304.ibm.com/jct03004c/press/us/en/pressrelease/26599.wss 20 petaflop Sequoia Supercomputer]
- [https://computing.llnl.gov/tutorials/bgp/ Using the Dawn BG/P System] {{Webarchive|url=https://web.archive.org/web/20130510232455/https://computing.llnl.gov/tutorials/bgp/ |date=May 10, 2013 }}
- [https://www.hpcwire.com/2020/02/27/sequoia-decommissioned-making-room-for-el-capitan/ Sequoia Decommissioned, Making Room for El Capitan]
{{S-start}}
{{S-ach|rec}}
{{S-bef|before=K computer
10.51 petaflops}}
{{S-ttl
| title = World's most powerful supercomputer
| years = June 2012 – November 2012
}}
{{s-aft|after=Titan
17.59 petaflops}}
{{S-end}}
{{Lawrence Livermore National Laboratory}}
{{DEFAULTSORT:IBM Sequoia}}