Schlagwort: Supercomputer

AMD EPYC™ Processors Picked by Argonne National Laboratory to Prepare for Exascale Future

- The new Pola­ris super­com­pu­ter will opti­mi­ze AI, engi­nee­ring, and sci­en­ti­fic pro­jects for forth­co­m­ing exas­ca­le super­com­pu­ter at Argon­ne Natio­nal Laboratory -

SANTA CLARA, Calif., Aug. 30, 2021 (GLOBE NEWSWIRE) — AMD (NASDAQ: AMD) announ­ced that the U.S. Depart­ment of Energy’s (DOE) Argon­ne Natio­nal Labo­ra­to­ry (Argon­ne) has cho­sen AMD EPYC™ pro­ces­sors to power a new super­com­pu­ter, cal­led Pola­ris, which will pre­pa­re rese­ar­chers for the forth­co­m­ing exas­ca­le super­com­pu­ter at Argon­ne cal­led Auro­ra. Pola­ris is built by Hew­lett Packard Enter­pri­se (HPE), will use 2nd Gen EPYC pro­ces­sors and then upgrade to 3rd Gen AMD EPYC pro­ces­sors, and will allow sci­en­tists and deve­lo­pers to test and opti­mi­ze soft­ware codes and app­li­ca­ti­ons to tack­le a ran­ge of AI, engi­nee­ring, and sci­en­ti­fic pro­jects. (…) Wei­ter­le­sen »

Berkeley Lab Deploys Next-Gen Supercomputer, Perlmutter, Bolstering U.S. Scientific Research

New Heterogeneous System Will Support Research in Advanced Computing, AI, Data Science & More

MAY 27, 2021 — The Natio­nal Ener­gy Rese­arch Sci­en­ti­fic Com­pu­ting Cen­ter (NERSC) at Law­rence Ber­ke­ley Natio­nal Labo­ra­to­ry (Ber­ke­ley Lab) today for­mal­ly unvei­led the first pha­se of its next-genera­ti­on super­com­pu­ter, Perl­mut­ter. The new sys­tem, named in honor of the Lab’s Nobel Pri­ze-win­ning astro­phy­si­cist Saul Perl­mut­ter, will great­ly incre­a­se the high per­for­mance com­pu­ting (HPC) capa­bi­li­ty for a broad spec­trum of unclas­si­fied sci­en­ti­fic rese­arch wit­hin the U.S. Depart­ment of Ener­gy (DOE) Office of Science.

(…) Wei­ter­le­sen »

AMD EPYC™ Processors to Power New System for National Supercomputing Centre Singapore

—Singapore’s most power­ful super­com­pu­ter to fea­ture AMD EPYC™ 7003 Seri­es processors—

SANTA CLARA, Calif. 05/11/2021
AMD (NASDAQ: AMD) announ­ced that AMD EPYC™ 7003 Seri­es pro­ces­sors will be used to power a new super­com­pu­ter for the Natio­nal Super­com­pu­ting Cent­re (NSCC) Sin­g­a­po­re, the natio­nal high-per­for­mance com­pu­ting (HPC) resour­ce cen­ter dedi­ca­ted to sup­por­ting sci­ence and engi­nee­ring com­pu­ting needs.

The sys­tem will be based on the HPE Cray EX super­com­pu­ter and will use a com­bi­na­ti­on of the EPYC 7763 and EPYC 75F3 pro­ces­sors. The super­com­pu­ter is plan­ned to be ful­ly ope­ra­tio­nal by 2022 and is expec­ted to have a peak theo­re­ti­cal per­for­mance of 10 peta­FLOPS, 8x fas­ter than NSCC’s exis­ting pool of HPC resour­ces. Rese­ar­chers will use the sys­tem to advan­ce sci­en­ti­fic rese­arch across bio­me­di­ci­ne, geno­mics, dise­a­ses, cli­ma­te, and more. (…) Wei­ter­le­sen »

Atos’s supercomputer to pave the way for Bulgaria’s leading position in high-tech

This will be the most power­ful super­com­pu­ter in Eas­tern Euro­pe and is expec­ted to be ope­ra­tio­nal in July 2021

Paris (France), Prague (Czech Republic), Sofia (Bulgaria) 11 May 2021

Atos today announ­ces that Bulgaria’s new EuroHPC super­com­pu­ter, which is based on Atos’ power­ful Bull­Se­qua­na XH2000 archi­tec­tu­re, is now ful­ly deli­ve­r­ed and assem­bled at Sofia Tech Park in Bul­ga­ria. Atos was selec­ted to build Bulgaria’s petas­ca­le super­com­pu­ter by the Euro­pean High Per­for­mance Com­pu­ting Joint Under­ta­king (EuroHPC JU), the hos­ting enti­ty, and the con­sor­ti­um “Petas­ca­le Super­com­pu­ter Bul­ga­ria” (PetaSC-Bul­ga­ria) who­se lea­ding part­ner is Sofia Tech Park.

This will be the most power­ful super­com­pu­ter in Eas­tern Euro­pe and will help to leverage Bulgaria’s high-tech ambi­ti­ons. Atos’ Czech Repu­blic pro­ject teams have alrea­dy star­ted the con­fi­gu­ra­ti­on tests and the super­com­pu­ter is expec­ted to start working ope­ra­tio­nal­ly in July 2021. (…) Wei­ter­le­sen »

Hewlett Packard Enterprise Selected to Build New Supercomputer for the National Supercomputing Centre Singapore to Support Scientific Research

Natio­nal Super­com­pu­ting Cent­re (NSCC) Sin­g­a­po­re advan­ces R&D across bio­me­di­ci­ne, geno­mics, dise­a­ses, cli­ma­te and more with an 8X fas­ter sys­tem powe­red by the HPE Cray EX supercomputer

April 27, 2021 10:00 PM Eas­tern Day­light Time

HOUSTON–(BUSINESS WIRE)–Hew­lett Packard Enter­pri­se (NYSE: HPE) today announ­ced it has been awar­ded $40M SGD to build a new super­com­pu­ter for the Natio­nal Super­com­pu­ting Cent­re (NSCC) Sin­g­a­po­re, the natio­nal high-per­for­mance com­pu­ting (HPC) resour­ce cen­ter dedi­ca­ted to sup­por­ting sci­ence and engi­nee­ring com­pu­ting needs for aca­de­mic, rese­arch and indus­try com­mu­nities. The new sys­tem, which will be 8X fas­ter com­pa­red to NSCC’s exis­ting pool of HPC resour­ces, will expand and aug­ment ongo­ing rese­arch efforts by enab­ling tools such as arti­fi­cial intel­li­gence (AI) and deep machi­ne lear­ning to opti­mi­ze mode­ling, simu­la­ti­on and even soft­ware simu­la­ti­on for quan­tum com­pu­ting. NSCC will use the sys­tem to unlock sci­en­ti­fic dis­co­ve­ries across medi­ci­ne, dise­a­ses, cli­ma­te, engi­nee­ring and more. (…) Wei­ter­le­sen »

Fujitsu and RIKEN Complete Joint Development of Japan’s Fugaku, the World’s Fastest Supercomputer

Begin­ning of shared use offers rese­ar­chers glo­bal­ly access to top-class com­pu­ting resour­ces RIKEN, The Rese­arch Orga­niz­a­ti­on for Infor­ma­ti­on Sci­ence and Tech­no­lo­gy, Fuji­tsu Limi­ted   Tokyo, March 09, 2021 RIKEN, the Rese­arch Orga­niz­a­ti­on for Infor­ma­ti­on Sci­ence and Tech­no­lo­gy (RIST), and Fuji­tsu today announ­ced the com­ple­ti­on and begin­ning of shared use of super­com­pu­ter Fug­aku, which has been joint­ly (…) Wei­ter­le­sen »

Schwedischer Supercomputer “Dardel” mit 13,5 Petaflops und AMD CPUs und GPUs

Bereits Ende letz­ter Woche hat HPE in einer Pres­se­mit­tei­lung ange­kün­digt, dass man für die König­li­che Tech­ni­sche Hoch­schu­le in Stock­holm einen Super­com­pu­ter mit dem Namen “Dard­el” bau­en wird, der sowohl auf AMD Epyc Pro­zes­so­ren, als auch AMD Rade­on Instinct Gra­fik­kar­ten der nächs­ten Genera­ti­on set­zen wird. Dard­el soll eine Peak­per­for­mance von 13,5 Peta­flops errei­chen, was aktu­ell einen Platz unter den ers­ten 50 in der TOP500-Lis­te der Super­com­pu­ter garan­tie­ren wür­de. Der Super­com­pu­ter wird aller­dings in zwei Pha­sen aus­ge­baut und soll dann im Janu­ar 2022 sei­ne vol­le Aus­bau­stu­fe errei­chen. (…) Wei­ter­le­sen »

Sweden’s KTH Royal Institute of Technology selects Hewlett Packard Enterprise to build new supercomputer to advance academic and industrial research

Sweden’s largest technical university advances R&D across life sciences, automotive, transportation and energy industries with next-generation system, powered by the HPE Cray EX supercomputer

San Jose, Calif. – Febru­a­ry 26, 2021 – Hew­lett Packard Enter­pri­se (HPE) today announ­ced that it is buil­ding a new super­com­pu­ter for KTH Roy­al Insti­tu­te of Tech­no­lo­gy (KTH) in Stock­holm, one of Sweden’s lar­gest tech­ni­cal uni­ver­si­ties dedi­ca­ted to sci­ence and engi­nee­ring rese­arch. The new super­com­pu­ter, which is fun­ded by Swe­dish Natio­nal Infra­st­ruc­tu­re for Com­pu­ting (SNIC), will enab­le a signi­fi­cant level of com­pu­ta­tio­nal per­for­mance, powe­red by the HPE Cray EX super­com­pu­ter, to impro­ve mode­ling and simu­la­ti­on from com­plex data to make bre­akthroughs in aca­de­mia and for a ran­ge of indus­tri­al are­as, inclu­ding drug design, rene­wa­ble ener­gy, and advan­ced auto­mo­ti­ve and fleet vehi­cles. (…) Wei­ter­le­sen »

Neue AMD-Supercomputer in den Niederlanden und an der Universität von Durham

In die­ser Woche gibt es wie­der zwei neue Super­com­pu­ter auf Basis von AMD-Pro­zes­so­ren zu ver­mel­den. Zum einem soll in den Nie­der­lan­den der neue natio­na­le Super­com­pu­ter von Leno­vo bis Mit­te des Jah­res instal­liert wer­den und zum ande­ren wird die im Nor­den von Eng­land gele­ge­ne Uni­ver­si­tät von Durham den Super­com­pu­ter COSMA 8 eben­falls bis Ende 2021 deut­lich aus­bau­en. Bei­de set­zen dabei haupt­säch­lich auf AMD Epyc 7H12 Pro­zes­so­ren der zwei­ten Genera­ti­on Epyc (“Rome”), aller­dings sol­len im noch namen­lo­sen nie­der­län­di­schen Sys­tem wohl auch Epyc Pro­zes­so­ren der drit­ten Genera­ti­on (“Milan”) zum Ein­satz kom­men. (…) Wei­ter­le­sen »

Lenovo to Power SURF Dutch National Supercomputer

AMSTERDAM, Feb. 8, 2021 — Leno­vo Data Cen­ter Group (DCG) announ­ced it will deli­ver high-per­for­mance com­pu­ter (HPC) infra­st­ruc­tu­re for SURF, the ICT coope­ra­ti­ve for edu­ca­ti­on and rese­arch in the Nether­lands. The €20 mil­li­on pro­ject, which begins in ear­ly 2021, will result in the crea­ti­on of the lar­gest and most power­ful super­com­pu­ter in the country.

Sup­por­ting sci­en­tists from over 100 edu­ca­ti­on and rese­arch insti­tu­ti­ons throughout the Nether­lands, the super­com­pu­ter will power high­ly com­plex cal­cu­la­ti­ons in life-enhan­cing work across all fiel­ds of sci­ence inclu­ding meteo­ro­lo­gy, astro­phy­sics, medi­cal and social sci­en­ces, and mate­ri­als and earth sci­en­ces, such as cli­ma­te chan­ge research.

Exp­lai­ning the signi­fi­can­ce of this col­la­bo­ra­ti­on, and the bene­fits to be pas­sed on to rese­arch pro­jects, Wal­ter Lio­en, Rese­arch Ser­vices Mana­ger at SURF, said: “The need of rese­ar­chers for com­pu­ting power, data sto­rage and pro­ces­sing is gro­wing expo­nen­ti­al­ly. In the design of the new super­com­pu­ter, the usa­bi­li­ty for sci­en­ti­fic rese­arch was para­mount. SURF has cho­sen Leno­vo becau­se of its qua­li­ty, per­for­mance and future fle­xi­bi­li­ty, as well as its con­si­de­ra­ti­ons for sus­taina­bi­li­ty.” (…) Wei­ter­le­sen »

TOP500 Expands Exaflops Capacity Amidst Low Turnover

FRANKFURT, Ger­ma­ny; BERKELEY, Calif.; and KNOXVILLE, Tenn.—The 56th edi­ti­on of the TOP500 saw the Japa­ne­se Fug­aku super­com­pu­ter soli­di­fy its num­ber one sta­tus in a list that reflects a flat­tening per­for­mance growth cur­ve.  Alt­hough two new sys­tems mana­ged to make it into the top 10, the full list recor­ded the smal­lest num­ber of new ent­ries sin­ce the pro­ject began in 1993.

The ent­ry level to the list moved up to 1.32 peta­flops on the High Per­for­mance Lin­pack (HPL) bench­mark, a small incre­a­se from 1.23 peta­flops recor­ded in the June 2020 ran­kings. In a simi­lar vein, the aggre­ga­te per­for­mance of all 500 sys­tems grew from 2.22 exa­flops in June to just 2.43 exa­flops on the latest list. Like­wi­se, average con­cur­ren­cy per sys­tem bare­ly incre­a­sed at all, gro­wing from 145,363 cores six mon­ths ago to 145,465 cores in the cur­rent list. (…) Wei­ter­le­sen »

Okinawa Institute of Science and Technology Graduate University Deploys AMD EPYC™ Processors with Over 2 Petaflops of Computing Power Dedicated to Scientific Research

 AMD EPYC™ Pro­ces­sors pro­vi­de supe­ri­or cost-per­for­mance and high core den­si­ty 

TOKYO, Oct. 01, 2020 (GLOBE NEWSWIRE) — Today, AMD (NASDAQ: AMD) and Oki­na­wa Insti­tu­te of Sci­ence and Tech­no­lo­gy Gra­dua­te Uni­ver­si­ty (OIST) , announ­ced the deploy­ment of AMD EPYC™ 7702 pro­ces­sors for use in a new, high per­for­mance com­pu­ting sys­tem. The EPYC pro­ces­sor-based super­com­pu­ter will deli­ver the 2.36 peta­flops of com­pu­ting power OIST plans to use for sci­en­ti­fic rese­arch at the Uni­ver­si­ty. (…) Wei­ter­le­sen »

AMD COVID-19 HPC Fund Adds 18 Institutions and Five Petaflops of Supercomputer Processing Power to Assist Researchers Fighting COVID-19 Pandemic

High per­for­mance AMD EPYC CPUs and Rade­on Instinct GPUs to power COVID-19 focu­sed rese­arch at Stan­ford School of Medi­ci­ne, The Uni­ver­si­ty of Texas at Aus­tin, UCLA, Uni­ver­si­ty of Toron­to and other insti­tu­ti­ons across the U.S., Euro­pe, and India


AMD (NASDAQ: AMD) today announ­ced a second round of high-per­for­mance tech­no­lo­gy con­tri­bu­ti­ons to assist in the glo­bal fight against the COVID-19 pan­de­mic. AMD is now con­tri­bu­ting high-end com­pu­ting sys­tems or access to Pen­gu­in-On-Demand (POD) cloud-based clus­ters powe­red by 2nd  Gen AMD EPYC™ and AMD Rade­on Instinct™ pro­ces­sors to 21 insti­tu­ti­ons and rese­arch faci­li­ties con­duc­ting COVID-19 rese­arch. With 12 peta­flops of total super­com­pu­ting capa­ci­ty now awar­ded, the com­bi­ned com­pu­te capa­ci­ty dona­ted through the AMD COVID-19 HPC Fund would rank among the fas­test super­com­pu­ters in the world accord­ing to the most recent Top500 list. (…) Wei­ter­le­sen »

GIGABYTE Technology, Northern Data AG and AMD Join Forces to Drive HPC Mega-Project

Tai­pei, Tai­wan, Sep­tem­ber 9th 2020 – GIGABYTE Tech­no­lo­gy, (TWSE: 2376), an indus­try lea­der in high-per­for­mance ser­vers and work­sta­tions, today is announ­cing a part­ners­hip with Nort­hern Data AG (XETRA: NB2, ISIN: DE000A0SMU87) to crea­te a HPC mega-pro­ject with com­pu­ting power of around 3.1 exaflops.

GIGABYTE will sup­ply GPU-based ser­ver sys­tems equip­ped with pro­ven AMD EPYC™ pro­ces­sors and AMD Rade­on Instinct™ acce­le­ra­tors from tech­no­lo­gy part­ner AMD, a lea­ding pro­vi­der of high per­for­mance com­pu­ting and gra­phics tech­no­lo­gies, to Nort­hern Data.

Nort­hern Data deve­lo­ps a dis­tri­bu­t­ed com­pu­ting clus­ter based on the hard­ware at loca­ti­ons in Nor­way, Swe­den and Cana­da, which in its final sta­ge of deploy­ment will pro­vi­de FP32 com­pu­ting power of around 3.1 exa­flops (3.1 mil­li­on tera­flops and 274.54 peta­flops FP64). The world’s fas­test super­com­pu­ter, the Japa­ne­se “Fuka­gu” (Fuji­tsu), has a cal­cu­la­ti­on power of 1.07 exa­flops FP32 and 415.3 peta­flops FP64, whe­re­as the second fas­test, the US super­com­pu­ter “Sum­mit” (IBM) has a cal­cu­la­ti­on power of 0.414 exa­flops FP32 and 148.0 peta­flops FP64. (…) Wei­ter­le­sen »

University of Florida, NVIDIA to Build Fastest AI Supercomputer in Academia

Effort will infu­se AI throughout UF’s cur­ri­cu­lum and help address wide ran­ge of chal­len­ges across the sta­te.     July 21, 2020      The Uni­ver­si­ty of Flo­ri­da and NVIDIA Tues­day unvei­led a plan to build the world’s fas­test AI super­com­pu­ter in aca­de­mia, deli­vering 700 peta­flops of AI per­for­mance. The effort is ancho­red by a $50 (…) Wei­ter­le­sen »

Durch die weitere Nutzung der Seite stimmst du der Verwendung von Cookies zu. Weitere Informationen

Die Cookie-Einstellungen auf dieser Website sind auf "Cookies zulassen" eingestellt, um das beste Surferlebnis zu ermöglichen. Wenn du diese Website ohne Änderung der Cookie-Einstellungen verwendest oder auf "Akzeptieren" klickst, erklärst du dich damit einverstanden.