Next-Generation AMD EPYC™ CPUs and Radeon™ Instinct GPUs Enable El Capitan Supercomputer at Lawrence Livermore National Laboratory to Break 2 Exaflops Barrier

— Col­la­bo­ra­ti­on with HPE tar­gets lea­ders­hip HPC and AI pro­ces­sing per­for­mance star­ting in ear­ly 2023 —

— El Capi­tan is set to be the second all AMD CPU and GPU exas­ca­le sys­tem in the U.S., and is expec­ted to be more power­ful than today’s 200 fas­test super­com­pu­ters com­bi­ned —

SANTA CLARA, Calif., March 04, 2020 (GLOBE NEWSWIRE) — AMD (NASDAQ: AMD) today joi­ned Law­rence Liver­mo­re Natio­nal Labo­ra­to­ry (LLNL) and HPE, in announ­cing that El Capi­tan, the upco­m­ing exas­ca­le class super­com­pu­ter at LLNL, will be powe­red by next genera­ti­on AMD EPYC™ CPUs, AMD Rade­on™ Instinct GPUs and open source AMD ROCm hete­ro­ge­ne­ous com­pu­ting soft­ware. 

With deli­very expec­ted in ear­ly 2023, the El Capi­tan sys­tem is expec­ted to be the world’s fas­test super­com­pu­ter with more than 2 exa­flops of dou­ble pre­cisi­on per­for­mance. This record set­ting per­for­mance will sup­port Natio­nal Nuclear Secu­ri­ty Admi­nis­tra­ti­on requi­re­ments for its pri­ma­ry mis­si­on of ensu­ring the safe­ty, secu­ri­ty and relia­bi­li­ty of the nation’s nuclear stock­pi­le.

The AMD based nodes will be opti­mi­zed to acce­le­ra­te arti­fi­cial intel­li­gence (AI) and machi­ne lear­ning (ML) workloads to poten­ti­al­ly enab­le the expan­ded use of AI and ML into the rese­arch, com­pu­ta­tio­nal tech­ni­ques and ana­ly­sis that bene­fits NNSA mis­si­ons.

El Capi­tan will dri­ve unpre­ce­den­ted advan­ce­ments in HPC and AI, powe­red by the next genera­ti­on AMD EPYC CPUs and Rade­on Instinct GPUs,” said For­rest Nor­rod, seni­or vice pre­si­dent and gene­ral mana­ger, Dat­a­cen­ter and Embed­ded Sys­tems Group, AMD. “Buil­ding on our strong foun­da­ti­on in high-per­for­mance com­pu­ting and adding trans­for­ma­ti­ve cohe­ren­cy capa­bi­li­ties, AMD is enab­ling the NNSA Tri-Lab community—LLNL and the Los Ala­mos and San­dia natio­nal laboratories—to achie­ve their mis­si­on cri­ti­cal objec­ti­ves and con­tri­bu­te new AI advan­ce­ments to the indus­try. We are extre­me­ly proud to con­ti­nue our exas­ca­le work with HPE and NNSA and look for­ward to the deli­very of the most power­ful super­com­pu­ter in the world expec­ted in ear­ly 2023.”

AMD Tech­no­lo­gy Powe­ring El Capi­tan
AMD is app­ly­ing its expe­ri­ence from the high-per­for­mance com­pu­ting indus­try and advan­cing its exis­ting CPU and GPU designs for El Capi­tan, enab­ling the sys­tem to be archi­tec­ted for maxi­mum per­for­mance and ease of use.

AMD tech­no­lo­gy wit­hin El Capi­tan inclu­des:

  • Next genera­ti­on AMD EPYC pro­ces­sors, code­n­a­med “Gen­oa” fea­turing the “Zen 4” pro­ces­sor core. The­se pro­ces­sors will sup­port next genera­ti­on memo­ry and I/O sub sys­tems for AI and HPC workloads,
  • Next genera­ti­on Rade­on Instinct GPUs based on a new com­pu­te-opti­mi­zed archi­tec­tu­re for workloads inclu­ding HPC and AI. The­se GPUs will use the next- genera­ti­on high band­width memo­ry and are desi­gned for opti­mum deep lear­ning per­for­mance,
  • The 3rd Gen AMD Infi­ni­ty Archi­tec­tu­re, which will pro­vi­de a high-band­width, low laten­cy con­nec­tion bet­ween the four Rade­on Instinct GPUs and one AMD EPYC CPU inclu­ded in each node of El Capi­tan. As well, the 3rd Gen AMD Infi­ni­ty Archi­tec­tu­re inclu­des uni­fied memo­ry across the CPU and GPU, easing pro­grammer access to acce­le­ra­ted com­pu­ting,
  • An enhan­ced ver­si­on of the open source ROCm hete­ro­ge­nous pro­gramming envi­ron­ment, being deve­lo­ped to tap into the com­bi­ned per­for­mance of AMD CPUs and GPUs, unlo­cking maxi­mum per­for­mance.

This unpre­ce­den­ted com­pu­ting capa­bi­li­ty, powe­red by advan­ced CPU and GPU tech­no­lo­gy from AMD, will sus­tain America’s posi­ti­on on the glo­bal sta­ge in high per­for­mance com­pu­ting and pro­vi­de an obser­v­a­ble examp­le of the com­mit­ment of the coun­try to main­tai­ning an unpar­al­leled nuclear deter­rent,” said LLNL Lab Direc­tor Bill Gold­stein. “Today’s news pro­vi­des a prime examp­le of how government and indus­try can work tog­e­ther for the bene­fit of the ent­i­re nati­on.”

We are plea­sed to part­ner with AMD to bring tog­e­ther HPE’s Cray Shas­ta archi­tec­tu­re with latest AMD EPYC CPUs and Rade­on Instinct GPUs and pro­vi­de lea­ders­hip tech­no­lo­gy in sup­port of the mis­si­on cri­ti­cal HPC and AI workloads for Law­rence Liver­mo­re Natio­nal Labo­ra­to­ry,” said Peter Unga­ro, seni­or vice pre­si­dent and gene­ral mana­ger, HPC and Mis­si­on Cri­ti­cal Solu­ti­ons (MCS) at HPE. “In our three U.S. exas­ca­le wins this last year, which inclu­des the U.S. Depart­ment of Energy’s Fron­tier at Oak Ridge Natio­nal Labo­ra­to­ry, the HPE sys­tems and tech­no­lo­gies along with AMD pro­ces­sors and GPUs have beco­me a uni­que solu­ti­on for high-per­for­mance and exas­ca­le-class com­pu­ting and we look for­ward to con­ti­nuing our col­la­bo­ra­ti­on to fur­ther bols­ter inno­va­ti­on.”

Addi­tio­nal Resour­ces

About AMD
For 50 years AMD has dri­ven inno­va­ti­on in high-per­for­mance com­pu­ting, gra­phics and visua­liz­a­ti­on tech­no­lo­gies ― the buil­ding blocks for gaming, immer­si­ve plat­forms and the dat­a­cen­ter. Hund­reds of mil­li­ons of con­su­mers, lea­ding For­tu­ne 500 busi­nes­ses and cut­ting-edge sci­en­ti­fic rese­arch faci­li­ties around the world rely on AMD tech­no­lo­gy dai­ly to impro­ve how they live, work and play. AMD employees around the world are focu­sed on buil­ding gre­at pro­ducts that push the bounda­ries of what is pos­si­ble. For more infor­ma­ti­on about how AMD is enab­ling today and inspi­ring tomor­row, visit the AMD (NASDAQ:AMDweb­siteblogFace­book and Twit­ter pages. 

Cau­tio­na­ry State­ment

This press release con­tains for­ward-loo­king state­ments con­cer­ning Advan­ced Micro Devices, Inc. (AMD) inclu­ding the fea­tures, func­tio­n­a­li­ty, avai­la­bi­li­ty, timing, deploy­ment and expec­ta­ti­ons of an EPYCCPU and Rade­on™ Instinct GPU powe­red exas­ca­le class super­com­pu­ter with open source AMD ROCm hete­ro­ge­ne­ous com­pu­ting soft­ware, which are made pur­suant to the Safe Har­bor pro­vi­si­ons of the Pri­va­te Secu­ri­ties Liti­ga­ti­on Reform Act of 1995. For­ward-loo­king state­ments are com­mon­ly iden­ti­fied by words such as “would,” “may,” “expects,” “belie­ves,” “plans,” “intends,” “pro­jects” and other terms with simi­lar mea­ning. Inves­tors are cau­tio­ned that the for­ward-loo­king state­ments in this pre­sen­ta­ti­on are based on cur­rent beliefs, assump­ti­ons and expec­ta­ti­ons, speak only as of the date of this pre­sen­ta­ti­on and invol­ve risks and uncer­tain­ties that could cau­se actu­al results to dif­fer mate­ri­al­ly from cur­rent expec­ta­ti­ons. Such state­ments are sub­ject to cer­tain known and unknown risks and uncer­tain­ties, many of which are dif­fi­cult to pre­dict and gene­ral­ly bey­ond AMD’s con­trol, that could cau­se actu­al results and other future events to dif­fer mate­ri­al­ly from tho­se expres­sed in, or implied or pro­jec­ted by, the for­ward-loo­king infor­ma­ti­on and state­ments. Mate­ri­al fac­tors that could cau­se actu­al results to dif­fer mate­ri­al­ly from cur­rent expec­ta­ti­ons inclu­de, without limi­ta­ti­on, the fol­lowing: Intel Corporation’s domi­nan­ce of the micro­pro­ces­sor mar­ket and its aggres­si­ve busi­ness prac­ti­ces; the abi­li­ty of third par­ty manu­fac­tu­rers to manu­fac­tu­re AMD’s pro­ducts on a time­ly basis in suf­fi­ci­ent quan­ti­ties and using com­pe­ti­ti­ve tech­no­lo­gies; expec­ted manu­fac­tu­ring yiel­ds for AMD’s pro­ducts; AMD’s abi­li­ty to intro­du­ce pro­ducts on a time­ly basis with fea­tures and per­for­mance levels that pro­vi­de value to its cus­to­mers while sup­por­ting and coin­ci­ding with signi­fi­cant indus­try tran­si­ti­ons; AMD’s abi­li­ty to gene­ra­te suf­fi­ci­ent reve­nue and ope­ra­ting cash flow or obtain exter­nal finan­cing for rese­arch and deve­lo­p­ment or other stra­te­gic invest­ments; the loss of a signi­fi­cant cus­to­mer; AMD’s abi­li­ty to gene­ra­te reve­nue from its semi-cus­tom SoC pro­ducts; glo­bal eco­no­mic uncer­tain­ty; poli­ti­cal, legal and eco­no­mic risks and natu­ral dis­as­ters; government actions and regu­la­ti­ons such as export admi­nis­tra­ti­on regu­la­ti­ons, tariffs and tra­de pro­tec­tion mea­su­res may limit our abi­li­ty export our pro­ducts to cer­tain cus­to­mers; poten­ti­al secu­ri­ty vul­nera­bi­li­ties; poten­ti­al IT outa­ges, data loss, data breaches and cyber-attacks; the abi­li­ty of GLOBALFOUNDRIES Inc. to satisfy AMD’s manu­fac­tu­ring requi­re­ments; uncer­tain­ties invol­ving the orde­ring and ship­ment of AMD’s pro­ducts; quar­ter­ly and sea­so­nal sales pat­terns; the restric­tions impo­sed by agree­ments gover­ning AMD’s notes and the secu­red credit faci­li­ty; the com­pe­ti­ti­ve mar­kets in which AMD’s pro­ducts are sold; the poten­ti­al dilu­ti­ve effect if the 2.125% Con­ver­ti­ble Seni­or Notes due 2026 are con­ver­ted; the mar­ket con­di­ti­ons of the indus­tries in which AMD pro­ducts are sold; AMD’s reli­an­ce on third-par­ty intel­lec­tu­al pro­per­ty to design and intro­du­ce new pro­ducts in a time­ly man­ner; AMD’s reli­an­ce on third-par­ty com­pa­nies for the design, manu­fac­tu­re and sup­ply of mother­boards, soft­ware and other com­pu­ter plat­form com­pon­ents; AMD’s reli­an­ce on Micro­soft Cor­po­ra­ti­on and other soft­ware ven­dors’ sup­port to design and deve­lop soft­ware to run on AMD’s pro­ducts; and AMD’s reli­an­ce on third-par­ty dis­tri­bu­tors and add-in-board part­ners. Inves­tors are urged to review in detail the risks and uncer­tain­ties in AMD’s Secu­ri­ties and Exchan­ge Com­mis­si­on filings, inclu­ding but not limi­ted to AMD’s Annu­al Report on Form 10‑K for the year ended Decem­ber 28, 2019.

AMD, the AMD Arrow logo, EPYC, Rade­on Instinct, and com­bi­na­ti­ons the­re­of, are trade­marks of Advan­ced Micro Devices, Inc. Other names are for infor­ma­tio­nal pur­po­ses only and may be trade­marks of their respec­ti­ve owners. 

Contact:
Gary Silcott
AMD Communications
+1 (512) 602-0889
Gary.Silcott@amd.com

Laura Graves
AMD Investor Relations
+1 (408) 749-5467
laura.graves@amd.com