Kategorie: News

Prime95 30.5 build 1

Das weit ver­brei­te­te Tool Prime95, das ger­ne zu Sta­bi­li­täts­tests für über­tak­te­te Sys­te­me her­an­ge­zo­gen wird, ist in einer neu­en Ver­si­on erschie­nen. Das Test­pro­gramm fühlt ins­be­son­de­re der CPU und dem ver­bau­ten Arbeits­spei­cher auf den Zahn. Dabei mel­det das Pro­gramm Feh­ler, die bei den Berech­nun­gen auf­tre­ten, lan­ge bevor sich Insta­bi­li­tä­ten durch einen Absturz des Betriebs­sys­tems bemerk­bar machen oder ande­re Daten­sät­ze beschä­digt wer­den. Prime95 kann daher auch dazu ver­wen­det wer­den, die Gren­zen beim Sys­tem­tu­ning aus­zu­lo­ten. (…) Wei­ter­le­sen »

ASRock Rack Announces The Broadest Compatibility of AMD EPYC™ 7003 Series Processor Solutions for Breakthrough Performance

Tai­pei, Tai­wan – March 16 , 2021 – ASRock Rack Inc., spe­cia­li­zed in the field of high per­for­mance cloud com­pu­ting ser­ver hard­ware, desi­gned to meet the huge demand for more com­pu­te in big data ana­ly­tics, HPC and cloud com­pu­ting of enti­re port­fo­lio of new ser­ver solu­ti­ons ful­ly sup­ports the new­ly announ­ced high-fre­quen­cy AMD EPYC™ 7003 Series pro­ces­sors. (…) Wei­ter­le­sen »

Nvidia GeForce-Treiber (GRD) 461.92 WHQL

Der Nvi­dia GeForce-Game-Rea­dy-Trei­ber für Win­dows ist in einer neu­en Ver­si­on erschie­nen. Er unter­stützt alle Nvi­dia-Kar­ten seit der GeForce 600er, über die GeForce 700er, die GeForce 900er, die GeForce 10xx, die GeForce 16xx, die RTX 20xx und bis hin zur aktu­el­len GeForce RTX 30xx Serie, sowie alle Kar­ten der Titan-Serie. (…) Wei­ter­le­sen »

Rambus verlängert Patentabkommen mit AMD

Bereits im Febru­ar hat Ram­bus eine Ver­län­ge­rung des Patent­ab­kom­mens mit AMD per Pres­se­er­klä­rung bekannt­ge­ben. Nach­dem die letz­te Ver­län­ge­rung der erst­mals 2006 geschlos­se­nen Ver­ein­ba­rung 2016 erfolg­te, wur­den Details über die neue Lauf­zeit die­ses mal nicht kom­mu­ni­ziert. (…) Wei­ter­le­sen »

HWiNFO64 v7.01–4410 Beta

Das Hard­ware-Dia­gno­se­pro­gramm HWiNFO64 (sowie das 32-Bit-Pen­dant HWiNFO32) von REA­LiX war­tet mit vie­len Funk­tio­nen der Kate­go­rien Hard­ware- und Sys­tem-Infor­ma­ti­on auf. Für CPU und GPU wer­den unter ande­rem Takt­ra­ten, Tem­pe­ra­tu­ren und Span­nun­gen ange­zeigt und auf Wunsch mit­ge­loggt. Seit der Ver­si­on 7.00 exis­tiert auch eine PRO-Vari­an­te der Soft­ware für kom­mer­zi­el­le Zwe­cke und eini­gen Zusatz­funk­tio­nen. Gleich­zei­tig wur­den Funk­tio­nen der kos­ten­frei­en Vari­an­te begrenzt. (…) Wei­ter­le­sen »

AMD stellt Ryzen PRO 5000 Mobile vor

Mit der Ryzen PRO 5000 Mobi­le Serie stellt AMD heu­te die haus­ei­ge­nen Pro­zes­so­ren für den Unter­neh­mens­be­reich vor. Die­se basie­ren im Gegen­satz zu den am Anfang des Jah­res vor­ge­stell­ten Ryzen 5000 Mobi­le aus­schließ­lich auf der Zen-3-Archi­tek­tur und bestehen aus dem Ryzen 3 PRO 5450U, dem Ryzen 5 PRO 5650U und dem Ryzen 7 PRO 5850U. (…) Wei­ter­le­sen »

Microsoft zieht Windows-10-Update nach Bluescreens beim Drucken zurück (Update)

Micro­soft hat inzwi­schen einen Hot­fix KB5001567 frei­ge­ge­ben, der das Pro­blem mit dem Blue­screen beim Dru­cken behe­ben soll. Beim letz­ten Patch­day hat­te das kumu­la­ti­ve Update KB5000802 einen Feh­ler ent­hal­ten, der den Com­pu­ter beim Dru­cken zum Absturz brin­gen konn­te. (…) Wei­ter­le­sen »

Cisco and AMD Help Businesses Improve Performance, Security and Hybrid Cloud Operations

News Sum­ma­ry:    

  • Buil­ding on their mul­ti-year enga­ge­ment, Cis­co and AMD help cus­to­mers boost per­for­mance, secu­ri­ty and automation 
  • New Cis­co UCS rack ser­ver models, based on the AMD EPYC™ 7003 Pro­ces­sors, are opti­mi­zed to address workloads requi­ring high input/output (I/O) and core count com­pu­te, and rich memo­ry density 
  • Com­bi­ned with the Cis­co Nexus Ultra Low Laten­cy net­wor­king port­fo­lio (form­er­ly Exab­la­ze), Cis­co now offers the lea­ding end-to-end solu­ti­on for High Fre­quen­cy Trading 

SAN JOSE, Calif — March 15, 2021 – Cis­co today announ­ced an expan­ded enga­ge­ment with AMD to help busi­nesses acce­le­ra­te advan­ced digi­tal expe­ri­en­ces and impro­ve hybrid cloud operations. 

With 55 per­cent of all enter­pri­se on-pre­mi­ses appli­ca­ti­ons deploy­ed on pri­va­te clouds and expec­ta­ti­ons this num­ber will increase to 60 per­cent in two years (Source: IDC’s Cloud Pul­se Q120, March 2020, n=2000), orga­niza­ti­ons are tran­si­tio­ning to new inno­va­tions in sys­tems and manage­ment plat­forms to meet dyna­mic per­for­mance, secu­ri­ty, and sca­le requi­re­ments for hybrid cloud infra­struc­tu­re. (…) Wei­ter­le­sen »

Qualcomm Cloud AI 100, AMD EPYC 7003 Series Processor, and Gigabyte server solutions breaks the Peta Operations Per Second barrier for AI Inferencing

The­re is no doubt that AI is the dri­ving force for next-gene­ra­ti­on con­su­mer expe­ri­en­ces. Vir­tual­ly every expe­ri­ence on a mobi­le device somehow invol­ves AI, whe­ther it’s scrol­ling through your favo­ri­te social apps or online shop­ping that offers recom­men­da­ti­ons based on tens of thou­sands of AI infe­ren­ces on its own. Now what hap­pens when the­se plat­forms are ser­ving mil­li­ons of users on a given day? That real­ly requi­res racks upon racks of powerful ser­vers that can deli­ver the AI infe­ren­cing per­for­mance requi­red to keep the­se plat­forms hum­ming along.

Today, Qual­comm Tech­no­lo­gies is enab­ling a powerful ser­ver rack that can meet the­se high-per­for­mance requi­re­ments by pai­ring with the latest AMD EPYC 7003 Series pro­ces­sors and Gigabyte’s latest G292-Z43 ser­ver solu­ti­ons. This amal­ga­ma­ti­on of hard­ware exper­ti­se offers incre­di­ble per­for­mance and rai­ses the bar for the modern data cen­ter. Qual­comm Tech­no­lo­gies’ cut­ting-edge Qual­comm Cloud AI 100 fits per­fect­ly into Gigabyte’s ser­ver sys­tem and is capa­ble of dri­ving the incre­di­ble AI use cases in the field of high-speed data ana­ly­sis, per­so­na­li­zed recom­men­da­ti­ons, smart cities, 5G com­mu­ni­ca­ti­ons, and more.

The Giga­byte G292-Z43 ser­ver sup­ports two AMD EPYC 7003 Series pro­ces­sors for its pro­ces­sing power along with mul­ti­ple Qual­comm Cloud AI 100 cards for com­pu­ta­tio­nal­ly inten­si­ve appli­ca­ti­ons sup­port­ing AI infe­ren­cing workloads. The Qual­comm Cloud AI 100 Infe­rence Acce­le­ra­tor boasts up to 400 TOPS with breakth­rough performance/Watt and that’s just with one sin­gle Qual­comm Cloud AI 100 card. Now ima­gi­ne a Giga­byte ser­ver can host up to 16 Qual­comm Cloud AI 100 infe­ren­cing cards per ser­ver that, cumu­la­tively, can deli­ver up to 6.4 Peta OPS (400 TOPS x 16, one Peta OPS is 1000 TOPS). This marks the first time a Qual­comm Tech­no­lo­gies AI-based solu­ti­on brea­king the Peta­OPs bar­ri­er. And it gets even bet­ter:  A ser­ver rack can host 19 or more of the­se ser­ver units, which easi­ly exceeds 100 Peta OPS. That is a lot of Qual­comm Tech­no­lo­gies AI mus­cle. See the info­gra­phic below on how it is being con­fi­gu­red. (…) Wei­ter­le­sen »

Ryzen Master 2.6.2.1818

AMD hat auf sei­ner Web­sei­te das Tool Ryzen Mas­ter in einer neu­en Ver­si­on zum Down­load bereit gestellt, seit der Ver­si­on 2.6.0.x wer­den Ryzen 5000 Pro­zes­so­ren unter­stützt. Mit Ryzen Mas­ter für Win­dows 10 (64 Bit) kön­nen Ryzen-Pro­zes­so­ren auf Sockel-AM4-Main­boards und Ryzen-Thre­ad­rip­per-Pro­zes­so­ren auf Sockel-TR4-Main­boards und Sockel-sTR40-Main­boards mit benut­zer­de­fi­nier­ten Takt­ra­ten- und Span­nungs­ein­stel­lun­gen betrie­ben wer­den. (…) Wei­ter­le­sen »

Azure and AMD announce landmark in confidential computing evolution

Chief Tech­no­lo­gy Offi­cer and Tech­ni­cal Fel­low, Micro­soft Azure

The pan­de­mic has acce­le­ra­ted digi­tal trans­for­ma­ti­on glo­bal­ly and the sca­la­bi­li­ty and secu­ri­ty advan­ta­ges offe­red by Micro­soft Azu­re have hel­ped many cus­to­mers move for­ward. One key tenet we have in Azu­re is that your data is your data. 

In Azu­re, we take your data secu­ri­ty serious­ly and have built num­e­rous con­trols around data at rest and data at flight. As a foun­ding mem­ber of the Con­fi­den­ti­al Com­pu­ting Con­sor­ti­um, we are also an inno­va­tor in con­fi­den­ti­al com­pu­ting which extends tho­se pro­tec­tions to data run­ning on the pro­ces­sor its­elf. For more than 3 years finan­cial ser­vices, govern­ments, health care pro­vi­ders, and even mes­sa­ging com­pa­nies have been using Azu­re con­fi­den­ti­al com­pu­ting to unlock new sce­na­ri­os like mul­ti-par­ty machi­ne lear­ning and move their more sen­si­ti­ve appli­ca­ti­ons to the cloud.

Today, I am announ­cing that we are fur­ther broa­de­ning the con­fi­den­ti­al com­pu­ting opti­ons available to Azu­re cus­to­mers through our tech­no­lo­gy part­ner­ship with AMD, spe­ci­fi­cal­ly by being the first major cloud pro­vi­der to offer con­fi­den­ti­al vir­tu­al machi­nes on the new AMD EPYC™ 7003 series pro­ces­sors. This new approach com­ple­ments exis­ting Azu­re con­fi­den­ti­al com­pu­ting solu­ti­ons such as con­fi­den­ti­al con­tai­ners for Azu­re Kuber­netes Ser­vice and opens the pos­si­bi­li­ty to crea­te new con­fi­den­ti­al appli­ca­ti­ons wit­hout requi­ring code modi­fi­ca­ti­ons which in turn sub­stan­ti­al­ly sim­pli­fies the pro­cess of crea­ting con­fi­den­ti­al appli­ca­ti­ons.
(…) Wei­ter­le­sen »

Supermicro Introduces the Most Versatile Portfolio of AMD EPYC™ 7003 Based Systems Delivering World Record Performance – 36% Improvement — for Today’s Most Critical Workloads

The Ver­sa­ti­li­ty and Breadth of Ultra, Twin, Super­Bla­de®, Sto­rage, GPU Opti­mi­zed Sys­tems Pro­vi­des Exact­ly the Best Workload Per­for­mance for Cloud Dat­a­Cen­ters, Enter­pri­se, and AI and Machi­ne Learning

San Jose, Calif., March 15, 2021 — Super Micro Com­pu­ter, Inc. (Nasdaq: SMCI), a glo­bal lea­der in enter­pri­se com­pu­ting, sto­rage, net­wor­king solu­ti­ons, and green com­pu­ting tech­no­lo­gy, announ­ces the avai­la­bi­li­ty of the most com­ple­te ser­ver lin­e­up sup­port­ing the AMD EPYC™ 7003 Series Pro­ces­sors in the indus­try today. Supermicro’s Super­Bla­de on the SPEC­jbb 2015-Dis­tri­bu­ted achie­ved back-to-back world record bench­marks on the cri­ti­cal-jOPS and max-jOPS tests. The Super­Bla­de deli­ver­ed up to a 36% impro­ve­ment from the 2nd Gen to 3rd Gen of AMD EPYC CPUs1, which is a signi­fi­cant boost to satis­fy per­for­mance-hun­gry enter­pri­se workloads

The Super­mi­cro A+ line includes ser­vers that incor­po­ra­te sin­gle-socket and dual-socket sys­tem solu­ti­ons desi­gned to redu­ce the time to results and dri­ve bet­ter busi­ness decis­i­ons. For exam­p­le, the recent­ly announ­ced new 2U 2‑node mul­ti-GPU ser­ver is the per­fect plat­form for video strea­ming, high-end cloud gam­ing, and count­less social net­wor­king appli­ca­ti­ons. It has mar­ket-lea­ding sys­tem fle­xi­bi­li­ty, and cost savings will deli­ver unin­ter­rupt­ed per­for­mance. With inno­va­ti­ve ser­ver designs that redu­ce the power requi­red while lea­ding the indus­try in per­for­mance, Super­mi­cro paves the way with appli­ca­ti­on-opti­mi­zed ser­vers, enab­ling modern busi­nesses to redu­ce cos­ts and enhan­ce their user’s expe­ri­ence. (…) Wei­ter­le­sen »

Hewlett Packard Enterprise unveils industry’s broadest portfolio of AMD EPYC™ processor-based solutions to power the edge to exascale

HPE’s enhanced portfolio of computing solutions using the new AMD EPYC™ 7003 Series Processor breaks world records with up to 39% better performance and greater energy efficiency to target any workload

HOUSTON, Texas – March 15, 2021– Hew­lett Packard Enter­pri­se (NYSE: HPE) today announ­ced record-brea­king per­for­mance on a wide ran­ge of deman­ding workloads, sur­pas­sing com­pe­ti­tors by up to 39%1 with its new com­pu­ting solu­ti­ons as part of the industry’s broa­dest set of AMD EPYC™ pro­ces­sor-based offe­rings. By using the new AMD EPYC™ 7003 Series Pro­ces­sor laun­ched today, HPE has secu­red 19 world records in key are­as for opti­mi­zing workload expe­ri­en­ces, inclu­ding achie­ving lea­der­ship posi­ti­ons in vir­tua­liza­ti­on, ener­gy effi­ci­en­cy, data­ba­se ana­ly­tic workloads, and Java appli­ca­ti­ons. To date, HPE ser­vers and sys­tems using 2nd and 3rd Gen AMD EPYC pro­ces­sors com­bi­ned hold a total of 32 world records. (…) Wei­ter­le­sen »

TYAN Now Offering AMD EPYC™ 7003 Processor Powered Systems

New Cloud, AI, and Storage Server Platforms to Accelerate Breakthroughs in Big Data Processing for the Modern Data Center

 

[cap­ti­on id=“attachment_61881” align=“aligncenter” width=“900”] Pro­ducts : GC68AB8036 GC68AB8036-LE GC68B8036-LE GC79AB8252 GC79B8252 
TN73B8037 TN83B8251 TS65B8253 TS75AB8252 
TS75B8252 [/caption]

Newark, Calif. – March 15, 2021 – TYAN®, an indus­try-lea­ding ser­ver plat­form design manu­fac­tu­rer and a MiT­AC Com­pu­ting Tech­no­lo­gy Cor­po­ra­ti­on sub­si­dia­ry, today intro­du­ced AMD EPYC™ 7003 Series Pro­ces­sor-based ser­ver plat­forms fea­turing effi­ci­en­cy and per­for­mance enhance­ments in hard­ware, secu­ri­ty, and memo­ry den­si­ty for the modern data center.

“Big data has beco­me capi­tal today. Lar­ge amounts of data and fas­ter ans­wers dri­ve bet­ter decis­i­ons. TYAN’s indus­try-lea­ding ser­ver plat­forms powered by 3rd Gen AMD EPYC pro­ces­sors enable busi­nesses to make more accu­ra­te decis­i­ons with hig­her pre­cis­i­on,” said Dan­ny Hsu, Vice Pre­si­dent of MiT­AC Com­pu­ting Tech­no­lo­gy Corporation’s Ser­ver Infra­struc­tu­re BU. “Moving the bar once more for workload per­for­mance, EPYC™ 7003 Series pro­ces­sors pro­vi­de the per­for­mance nee­ded in the heart of the enter­pri­se to help IT pro­fes­sio­nals dri­ve fas­ter time to results,” said Ram Ped­dib­hot­la, cor­po­ra­te vice pre­si­dent, EPYC pro­duct manage­ment, AMD. “Time is the new metric for effi­ci­en­cy and EPYC 7003 Series pro­ces­sors are the per­fect choice for the most diver­se workloads, hel­ping pro­vi­de more and bet­ter data to dri­ve bet­ter busi­ness out­co­mes.” (…) Wei­ter­le­sen »