Kategorie: Pressemitteilungen

TYAN Introduces HPC, Cloud and Storage Server Platforms Featuring 4th Gen AMD EPYC™ Processors at SC22

New 2‑GPU pedestal design, high-density with front I/O and all-flash storage servers maximize performance and energy efficiency for the data center

[cap­ti­on id=“attachment_67032” align=“aligncenter” width=“900”] Pro­ducts : S8050 FT65TB8050 GC68AB8056 TS70AB8056 TS70B8056[/caption]

Dal­las, Texas – Super­com­pu­ting 2022 – Nov 15, 2022 – TYAN®, an indus­try-lea­ding ser­ver plat­form design manu­fac­tu­rer and a MiT­AC Com­pu­ting Tech­no­lo­gy Cor­po­ra­ti­on sub­si­dia­ry, brings the latest HPC, cloud and sto­rage plat­forms powered by AMD EPYC™ 9004 Series pro­ces­sors for the next gene­ra­ti­on ser­ver archi­tec­tu­re and ener­gy effi­ci­en­cy at SC22, Booth #2000 in the Kay Bai­ley Hut­chison Con­ven­ti­on Cen­ter Dal­las on Novem­ber 14–17.

Facing the post-COVID eco­no­my world, data cen­ters are requi­red to build on more envi­ron­men­tal­ly fri­end­ly, secu­re and fle­xi­ble fea­tures to respond to the gro­wing of tele­wor­king, video strea­ming, IoT and 5G,” said Dan­ny Hsu, Vice Pre­si­dent of MiT­AC Com­pu­ting Tech­no­lo­gy Corporation’s Ser­ver Infra­struc­tu­re BU. “TYAN’s new ser­ver plat­forms, powered by 4th Gen AMD EPYC pro­ces­sors, effi­ci­ent­ly enable data cen­ters by doing more tasks with the same num­ber of ser­vers.” (…) Wei­ter­le­sen »

AMD Drives Leadership Performance and Energy Efficiency in Supercomputing

AMD EPYC pro­ces­sors and AMD Instinct acce­le­ra­tors powered 101 super­com­pu­ters in the latest Top500 list, a 38% increase year-over-year —

SANTA CLARA, 11/15/2022

At the Super­com­pu­ting Con­fe­rence 2022 (SC22)AMD (NASDAQ: AMD) show­ca­sed its con­tin­ued momen­tum and domi­na­ting pre­sence within the high per­for­mance com­pu­ting (HPC) indus­try. AMD EPYC™ CPUs and AMD Instinct™ acce­le­ra­tors con­ti­nue to be the pro­ces­sors of choice for the most deman­ding HPC workloads powe­ring the most com­plex simu­la­ti­ons and mode­ling tools.

Inno­va­ti­on in high per­for­mance com­pu­ting has a dra­ma­tic impact on socie­ty, advan­cing ground­brea­king rese­arch that has the poten­ti­al to vast­ly impro­ve qua­li­ty of life for peo­p­le ever­y­whe­re,” said For­rest Nor­rod, seni­or vice pre­si­dent and gene­ral mana­ger, Data Cen­ter Solu­ti­ons Group, AMD. “AMD is con­stant­ly inno­vat­ing and evol­ving our EPYC pro­ces­sors and Instinct acce­le­ra­tors to ensu­re sci­en­tists and rese­ar­chers working on sol­ving the world’s toug­hest chal­lenges have the most cut­ting-edge tools for their rese­arch.” (…) Wei­ter­le­sen »

AMD Announces Completion of Class B Qualification for First Space-Grade Versal Adaptive SoCs Enabling On-Board AI Processing in Space

— First ship­ments of radia­ti­on-tole­rant Ver­sal AI Core devices deli­ve­ring high-band­width signal pro­ces­sing and AI infe­ren­cing for space appli­ca­ti­ons on track for ear­ly next year —

SANTA CLARA, Calif. 11/15/2022

AMD (NASDAQ: AMD) today announ­ced it has com­ple­ted Class B qua­li­fi­ca­ti­on for the company’s first space-gra­de Ver­sal™ adap­ti­ve SoCs. The XQR Ver­sal™ AI Core XQRVC1902 devices deli­ver full radia­ti­on tole­rance, acce­le­ra­ted AI infe­ren­cing and high-band­width signal pro­ces­sing per­for­mance for satel­li­te and space appli­ca­ti­ons. The com­ple­ti­on of Class B qua­li­fi­ca­ti­on, deri­ved from the US mili­ta­ry spe­ci­fi­ca­ti­on MIL-PRF-38535, allows the devices to begin ship­ping in ear­ly 2023.

The radia­ti­on-tole­rant XQR Ver­sal AI Core XQRVC1902 devices repre­sent a major leap for­ward in enab­ling sophisti­ca­ted on-board data pro­ces­sing and AI infe­ren­cing appli­ca­ti­ons in space. Until now, high­ly com­plex AI appli­ca­ti­ons could only be per­for­med with cus­tom-desi­gned ASICs, which are pro­hi­bi­tively expen­si­ve for most space pro­grams. (…) Wei­ter­le­sen »

SiPearl and AMD collaborate to address exascale supercomputing in Europe

SiPearl, the com­pa­ny desig­ning the high-per­for­mance, low-power micro­pro­ces­sor for Euro­pean super­com­pu­ters, is col­la­bo­ra­ting with AMD to address the needs of exas­ca­le super­com­pu­ting in Euro­pe. Com­bi­ning SiPearl’s Rhea micro­pro­ces­sor with AMD Instinct™ acce­le­ra­tors, the two com­pa­nies will help Euro­pe to meet stra­te­gic, sci­en­ti­fic, socie­tal, and indus­tri­al challenges.

Mai­sons-Laf­fit­te (France), 14th Novem­ber 2022 – SiPearl, the com­pa­ny desig­ning the high­per­for­mance, low-power micro­pro­ces­sor for Euro­pean super­com­pu­ters, has ente­red into a busi­ness col­la­bo­ra­ti­on agree­ment with AMD to pro­vi­de a joint offe­ring for exas­ca­le super­com­pu­ting sys­tems, com­bi­ning SiPearl’s HPC micro­pro­ces­sor, Rhea, with AMD Instinct™ accelerators.

Initi­al­ly, AMD and SiPearl will joint­ly assess the inter­ope­ra­bi­li­ty of the AMD ROCm™ open soft­ware with the SiPearl Rhea micro­pro­ces­sor and build an opti­mi­zed soft­ware solu­ti­on that would streng­then the capa­bi­li­ties of a SiPearl micro­pro­ces­sor com­bi­ned with an AMD InstinctTM acce­le­ra­tor. This joint work tar­gets port­ing and opti­miza­ti­on acti­vi­ties of the AMD HIP backend, openMP com­pi­lers and libra­ri­es, will enable sci­en­ti­fic appli­ca­ti­ons to bene­fit from both tech­no­lo­gies. (…) Wei­ter­le­sen »

ASUS Announces AMD EPYC 9004-Powered Rack Servers and Liquid-Cooling Solutions

Over 90%-lower fan power con­sump­ti­on for huge saving on data cen­ter ope­ra­ti­on Supe­ri­or liquid-coo­­ling solu­ti­ons: Over 90%-lower fan power con­sump­ti­on for huge saving on data-cen­­­ter ope­ra­ti­ons New ther­mal design: Hard-dri­­ve tray design with 44%-wider ven­ti­la­ti­on holes, plus opti­mi­zed lay­out to mini­mi­ze impe­dance and enhan­ce air­flow No. 1 Bench­mark: World-record-set­­ting per­for­mance with 24 results on the latest SPEC CPU2017 (…) Wei­ter­le­sen »

Offering Unmatched Performance, Leadership Energy Efficiency and Next-Generation Architecture, AMD Brings 4th Gen AMD EPYC™ Processors to The Modern Data Center

—New AMD EPYC™ pro­ces­sors are the world’s fas­test and most ener­gy effi­ci­ent, allo­wing cus­to­mers to moder­ni­ze their data cen­ters to dri­ve actionable insights for bet­ter busi­ness results— 

AMD EPYC™ pro­ces­sors are sup­port­ed by a com­ple­te cloud, enter­pri­se, hard­ware and soft­ware ecosystem—

SANTA CLARA, Calif., Nov. 10, 2022 (GLOBE NEWSWIRE) — Today, at the “tog­e­ther we advance_data cen­ters” event, AMD (NASDAQ: AMD) announ­ced the gene­ral avai­la­bi­li­ty of the 4th Gen AMD EPYC™ pro­ces­sors; with unmat­ched per­for­mance for cri­ti­cal workloads across cloudi, enter­pri­seii and high per­for­mance com­pu­tingiii.

The 4th Gen AMD EPYC pro­ces­sors bring next-gene­ra­ti­on archi­tec­tu­re, tech­no­lo­gy, and fea­tures to the modern data cen­ter. Built on the “Zen 4” core, the hig­hest per­for­mance core ever from AMDiv, the pro­ces­sors deli­ver lea­der­ship per­for­mance, ener­gy effi­ci­en­cyv and help cus­to­mers acce­le­ra­te data cen­ter moder­niza­ti­on for grea­ter appli­ca­ti­on through­put and more actionable insights.

Choo­sing the right data cen­ter pro­ces­sor is more important than ever, and 4th Gen EPYC pro­ces­sors deli­ver lea­der­ship in every dimen­si­on,” said Dr. Lisa Su, Chair and CEO, AMD. “The data cen­ter repres­ents the lar­gest growth oppor­tu­ni­ty and most stra­te­gic prio­ri­ty for AMD, and we are com­mit­ted to making AMD the part­ner of choice by offe­ring the industry’s broa­dest port­fo­lio of high-per­for­mance and adap­ti­ve com­pu­ting engi­nes. We have built the best data cen­ter CPU road­map in the indus­try, and with 4th Gen EPYC we deli­ver ano­ther major step for­ward in per­for­mance and effi­ci­en­cy to make the best ser­ver pro­ces­sor road­map even bet­ter. With a signi­fi­cant­ly expan­ded set of solu­ti­ons on-track to launch from our eco­sys­tem of part­ners, cus­to­mers sel­ec­ting 4th Gen EPYC to power their data cen­ters can impro­ve per­for­mance, con­so­li­da­te their infra­struc­tu­re, and lower ener­gy costs.”

Acce­le­ra­ting Results and Dri­ving Actionable Insights for Businesses

4th Gen AMD EPYC pro­ces­sors are desi­gned to deli­ver opti­miza­ti­ons across mar­ket seg­ments and appli­ca­ti­ons, while hel­ping busi­nesses free data cen­ter resour­ces to crea­te addi­tio­nal workload pro­ces­sing and acce­le­ra­te output.
With 4th Gen AMD EPYC pro­ces­sors, busi­nesses can:

(…) Wei­ter­le­sen »

Cloud Hypervisor Project welcomes AMD as a Member of the Advisory Board

As a mem­ber of the Advi­so­ry Board, AMD will help dri­ve open source col­la­bo­ra­ti­on and deve­lo­p­ment in the Cloud Hyper­vi­sor community.

SAN FRANCISCO, Novem­ber 8, 2022 – The Cloud Hyper­vi­sor Pro­ject, a lea­ding vir­tu­al machi­ne moni­tor (VMM) for run­ning modern cloud workloads, is exci­ted to wel­co­me AMD to their Advi­so­ry Board. The Linux Foun­da­ti­on and the foun­ding mem­bers of the Cloud Hyper­vi­sor Pro­ject would like to wel­co­me AMD and look for­ward to working with them to fos­ter an envi­ron­ment of open source col­la­bo­ra­ti­on. (…) Wei­ter­le­sen »

AMD Unveils World’s Most Advanced Gaming Graphics Cards, Built on Groundbreaking AMD RDNA 3 Architecture with Chiplet Design

– High­ly effi­ci­ent AMD RDNA 3 archi­tec­tu­re deli­vers world-class per­for­mance, and fea­tures new uni­fied com­pu­te units, world’s fas­test inter­con­nect, second-gene­ra­ti­on AMD Infi­ni­ty Cache tech­no­lo­gy, new dis­play and media engi­nes, and more –

AMD Rade­on RX 7900 Series gra­phics cards deli­ver up to 1.7X hig­her 4K gaming
per­for­mance than the pre­vious flag­ship gra­phics cards –

LAS VEGAS, Nov. 03, 2022 (GLOBE NEWSWIRE) — AMD (NASDAQ: AMD) today unvei­led new gra­phics cards built on the next-gene­ra­ti­on high-per­for­mance, ener­gy-effi­ci­ent AMD RDNA™ 3 archi­tec­tu­re – the AMD Rade­on™ RX 7900 XTX and Rade­on RX 7900 XT gra­phics cards. Fol­lo­wing on the high­ly suc­cessful AMD “Zen”-based AMD Ryzen™ chip­let pro­ces­sors, the new gra­phics cards are the world’s first gam­ing gra­phics cards to fea­ture an advan­ced AMD chip­let design. They deli­ver excep­tio­nal per­for­mance and superb ener­gy effi­ci­en­cy to power high-frame­ra­te 4K and hig­her reso­lu­ti­on gam­ing in the most deman­ding titles.

The AMD RDNA 3 architecture’s chip­let design com­bi­nes 5nm and 6nm pro­cess nodes, each opti­mi­zed for spe­ci­fic jobs. The breakth­rough archi­tec­tu­re deli­vers up to 54% more per­for­mance per watt than AMD RDNA 2 archi­tec­tu­re1, and fea­tures the world’s fas­test inter­con­nect lin­king the gra­phics and memo­ry sys­tem chip­lets at up to 5.3 TB/s2. It also offers up to 96 new uni­fied com­pu­te units, second-gene­ra­ti­on AMD Infi­ni­ty Cache™ tech­no­lo­gy, and up to 24 GB of high-speed GDDR6 memo­ry with up to a 384-bit memo­ry inter­face. It also includes increased AI through­put that deli­vers up to 2.7X hig­her AI per­for­mance, and second-gene­ra­ti­on ray­tra­cing tech­no­lo­gy that pro­vi­des up to 1.8X hig­her ray­tra­cing per­for­mance than AMD RDNA 2 archi­tec­tu­re3.

Altog­e­ther, the­se fea­tures and advance­ments deli­ver up to a 1.7X per­for­mance uplift in sel­ect titles at 4K com­pared to AMD RDNA 2 archi­tec­tu­re4. The new gra­phics cards also sup­port Dis­play­Po­rt™ 2.1 dis­plays capa­ble of deli­ve­ring ultra-high frame­ra­tes and stun­ning visu­als at up to 4K 480Hz and 8K 165Hz refresh rates. (…) Wei­ter­le­sen »

AMD Reports Third Quarter 2022 Financial Results

― Data Cen­ter, Gam­ing and Embedded seg­ments each grew signi­fi­cant­ly year-over-year and Cli­ent seg­ment reve­nue was lower than expected ―

― Cash and ope­ra­ting cash flow increased year-over-year ―

SANTA CLARA, Calif., Nov. 01, 2022 (GLOBE NEWSWIRE) — AMD (NASDAQ:AMD) today announ­ced reve­nue for the third quar­ter of 2022 of $5.6 bil­li­on, gross mar­gin of 42%, ope­ra­ting loss of $64 mil­li­on, net inco­me of $66 mil­li­on and diluted ear­nings per share of $0.04. On a non-GAAP(*) basis, gross mar­gin was 50%, ope­ra­ting inco­me was $1.3 bil­li­on, net inco­me was $1.1 bil­li­on and diluted ear­nings per share was $0.67.

(…) Wei­ter­le­sen »

Meteorological Service Singapore advances weather forecasting with new supercomputer from Hewlett Packard Enterprise

The new super­com­pu­ter will speed up wea­ther pre­dic­tions and bols­ter cli­ma­te rese­arch into Singapore’s tro­pi­cal cli­ma­te trends with up to 2X more per­for­mance and advan­ced mode­ling and simu­la­ti­on capabilities

HOUSTON, Oct. 26, 2022 – Hew­lett Packard Enter­pri­se (NYSE: HPE) today announ­ced that it has built a new super­com­pu­ter for the Meteo­ro­lo­gi­cal Ser­vice Sin­ga­po­re (MSS) to advan­ce wea­ther fore­cas­ting and tro­pi­cal cli­ma­te rese­arch for Sin­ga­po­re and the broa­der Sou­the­ast Asia regi­on. The new super­com­pu­ter replaces MSS’ exis­ting sys­tem, deli­ve­ring near­ly twice as much per­for­mance and advan­ced capa­bi­li­ties across com­pu­te, sto­rage, soft­ware and net­wor­king. (…) Wei­ter­le­sen »

ASUS stellt das exklusive PBO Enhancement für AMD X670- und B650-Mainboards vor

Erweiterte Temperaturkontrolle für AMD Ryzen 7000er Prozessoren in der ASUS ROG‑, TUF Gaming‑, ProArt- und Prime AM5-Mainboard-Produktreihe.

  • Das PBO Enhance­ment, das über ein BIOS-Update akti­viert wird, kann die Höchst­tem­pe­ra­tu­ren von AMD Ryzen™ 7000er Pro­zes­so­ren um bis zu 25 °C senken
  • Die Sen­kung der Tem­pe­ra­tu­ren kann die CPU-Leis­tung in bestimm­ten Sze­na­ri­en sogar erhöhen
  • Das Update ist für das gesam­te ASUS X670 und B650 Main­board Lin­e­up verfügbar 

Ratin­gen, Deutsch­land, 25. Okto­ber 2022 — ASUS kün­dig­te heu­te das neue Pre­cis­i­on Boost Over­dri­ve (PBO) Enhance­ment an, eine exklu­si­ve Tem­pe­ra­tur­kon­troll­funk­ti­on für die X670 und B650 Main­boards, die für AMD Ryzen™ 7000er Pro­zes­so­ren ent­wi­ckelt wurden.

Die­se neu­es­ten CPUs ver­schie­ben die Gren­zen der Leis­tung wei­ter als je zuvor. Sie nut­zen dyna­misch den ver­füg­ba­ren ther­mi­schen Spiel­raum, um den Benut­zern höhe­re Takt­ra­ten zu ermög­li­chen. Das bedeu­tet, dass Benut­zer mög­li­cher­wei­se höhe­re CPU-Tem­pe­ra­tu­ren in einem neu­en AMD Ryzen-betrie­be­nen Gerät sehen, als sie es gewohnt sind. Um den Benut­zern die Kon­trol­le zu geben, bringt ASUS ein BIOS-Update für sei­ne X670- und B650-Main­boards mit neu­en Optio­nen für die Fea­tures des PBO Enhance­ment her­aus, die es ein­fach macht, Wär­me­ent­wick­lung und Leis­tung aus­zu­glei­chen. Mit nur weni­gen Klicks kön­nen Benut­zer die CPU-Tem­pe­ra­tu­ren dras­tisch sen­ken – und dabei viel­leicht sogar die Leis­tung erhö­hen und das Lüf­ter­ge­räusch reduzieren.

Um es klar zu sagen: AMD ver­si­chert sei­nen Kun­den, dass sei­ne neu­es­ten Chips bei den Stan­dard­tem­pe­ra­tu­ren sicher arbei­ten kön­nen. Moder­ne Pro­zes­so­ren haben selbst auf­er­leg­te Grenz­wer­te, die ver­hin­dern, dass sie Tem­pe­ra­tu­ren errei­chen, die tat­säch­lich schäd­lich sind. Außer­dem wer­den die Benut­zer die Höchst­tem­pe­ra­tu­ren von 95 °C wahr­schein­lich erst dann errei­chen, wenn sie eine Arbeits­last initi­ie­ren, die alle CPU-Ker­ne bean­sprucht. Im all­täg­li­chen Betrieb, von leich­ten Arbeits­las­ten bis hin zu den meis­ten Spie­le­sit­zun­gen, wer­den Benut­zer in der Regel viel nied­ri­ge­re CPU-Tem­pe­ra­tu­ren fest­stel­len. (…) Wei­ter­le­sen »

AMD to Unveil Next Generation EPYC Processors During “together we advance_data centers” Event

SANTA CLARA, Calif., Oct. 24, 2022 (GLOBE NEWSWIRE) — Today, AMD (NASDAQ: AMD) announ­ced “tog­e­ther we advance_data cen­ters,” an in-per­son and live­strea­med event to unveil the next gene­ra­ti­on of AMD EPYC™ data cen­ter pro­ces­sors. AMD exe­cu­ti­ves, along with other key eco­sys­tem part­ners, will pre­sent details on the next gene­ra­ti­on data cen­ter pro­ces­sor and solutions.

The live stream will start at 10 a.m. PT on Thurs­day, Novem­ber 10 at www.amd.com/en/events/epyc as well as the AMD You­Tube chan­nel.

About AMD (…) Wei­ter­le­sen »

AMD to Host Livestream Event to Unveil AMD RDNA 3 Graphics Generation

AMD today announ­ced “tog­e­ther we advance_gaming,” a live­stream event to unveil the next gene­ra­ti­on of AMD Rade­on™ gra­phics. AMD exe­cu­ti­ves will pro­vi­de details on the new high-per­for­mance, ener­gy-effi­ci­ent AMD RDNA™ 3 archi­tec­tu­re that will deli­ver new levels of per­for­mance, effi­ci­en­cy and func­tion­a­li­ty to gamers and con­tent creators.

The show pre­mie­res at 1:00 p.m. PDT on Thurs­day, Novem­ber 3, on the AMD You­Tube chan­nel. A replay can be acces­sed a few hours after the con­clu­si­on of the event at AMD.com/Radeon. (…) Wei­ter­le­sen »

AMD EPYC™ Processors Power The ‘AMD Creator Cloud’ Used For Pixar’s RenderMan Challenge 2022

Challengers Will Have Access To The ‘AMD Creator Cloud’ Powered by AMD EPYC™ Processors with AMD 3D V‑Cache™ Technology on Microsoft Azure, Helping to Fulfill Their Creative Dreams

SANTA CLARA, Calif., Oct. 12, 2022 (GLOBE NEWSWIRE) — AMD (NASDAQ: AMD), along with Pix­ar Ani­ma­ti­on Stu­di­os, are announ­cing the latest Rend­er­Man Chall­enge. This chall­enge offers gra­phic desi­gners, artists, and others around the world the oppor­tu­ni­ty to crea­te and achie­ve their cine­ma­tic visi­ons with Pixar’s RenderMan.

(…) Wei­ter­le­sen »

AMD Collaborates with The Energy Sciences Network on Launch of its Next-Generation, High-Performance Network to Enhance Data-Intensive Science

— ESnet6 leverages AMD adaptive networking technology for packet monitoring at extremely high transfer rates and to allow for continuous innovation in the network —

SANTA CLARA, Calif., Oct. 11, 2022 (GLOBE NEWSWIRE) — Today AMD (NASDAQ: AMD) announ­ced its col­la­bo­ra­ti­on with the Ener­gy Sci­en­ces Net­work (ESnet) on the launch of ESnet6, the newest gene­ra­ti­on of the U.S. Depart­ment of Energy’s (DOE’s) high-per­for­mance net­work dedi­ca­ted to science.

AMD work­ed clo­se­ly with ESnet sin­ce 2018 to inte­gra­te powerful adap­ti­ve com­pu­ting for the smart and pro­gramma­ble net­work nodes of ESnet6. ESnet6’s extre­me sca­le packet moni­to­ring sys­tem uses AMD Alveo™ U280 FPGA-based net­work-atta­ched acce­le­ra­tor cards at the core net­work swit­ching nodes. This will enable high-touch packet pro­ces­sing and help impro­ve the accu­ra­cy of net­work moni­to­ring and manage­ment to enhan­ce per­for­mance. The pro­gramma­ble hard­ware allows for new capa­bi­li­ties to be added for con­ti­nuous inno­va­ti­on in the net­work. (…) Wei­ter­le­sen »