In die­ser Sek­ti­on wer­den Pres­se­mit­tei­lun­gen der Her­stel­ler 1:1 ver­öf­fent­licht. Pla­net 3DNow! über­nimmt weder für die Rich­tig­keit der Anga­ben noch für die Art der For­mu­lie­rung jed­we­de Ver­ant­wor­tung. Die Anga­ben kön­nen sub­jek­tiv sein und geben nicht not­wen­di­ger­wei­se die Mei­nung der auf Pla­net 3DNow! schrei­ben­den Autoren wieder.

AMD Showcases Leadership Cloud Performance with New Amazon EC2 Instances Powered by 4th Gen AMD EPYC Processors

Verfasst vonpipin

—Ama­zon EC2 M7a ins­tances offer up to 50 per­cent more com­pu­te per­for­mance than M6a ins­tances and bring an even broa­der ran­ge of workloads to AWS—

—Ama­zon EC2 Hpc7a ins­tances, powered by 4th Gen AMD EPYC pro­ces­sors, deli­ver up to 2.5x bet­ter per­for­mance com­pared to Ama­zon EC2 Hpc6a instances—

SANTA CLARA, Calif., Aug. 18, 2023 (GLOBE NEWSWIRE) — Today, AMD (NASDAQ: AMD) announ­ced Ama­zon Web Ser­vices (AWS) has expan­ded its 4th Gen AMD EPYC™ pro­ces­sor-based offe­rings with the gene­ral avai­la­bi­li­ty of Ama­zon Ela­s­tic Com­pu­te Cloud (EC2) M7a and Ama­zon EC2 Hpc7a ins­tances, which offer next-gene­ra­ti­on per­for­mance and effi­ci­en­cy for appli­ca­ti­ons that bene­fit from high per­for­mance, high through­put and tight­ly cou­pled HPC workloads, respectively.

“For cus­to­mers with incre­asing­ly com­plex and com­pu­te-inten­si­ve workloads, 4th Gen EPYC pro­ces­sor-powered Ama­zon EC2 ins­tances deli­ver a dif­fe­ren­tia­ted offe­ring for cus­to­mers,” said David Brown, vice pre­si­dent of Ama­zon EC2 at AWS. “Com­bi­ned with the power of the AWS Nit­ro Sys­tem, both M7a and Hpc7a ins­tances allow for fast and low-laten­cy inter­node com­mu­ni­ca­ti­ons, advan­cing what our cus­to­mers can achie­ve across our gro­wing fami­ly of Ama­zon EC2 instances.”

“4th Gen EPYC pro­ces­sors have unmat­ched per­for­mance lea­der­ship; and our col­la­bo­ra­ti­on with AWS is deli­ve­ring the full 4th Gen EPYC per­for­mance per core in new M7a and Hpc7a ins­tances,” said Dan McNa­ma­ra, seni­or vice pre­si­dent and gene­ral mana­ger, Ser­ver Busi­ness Unit, AMD. “As a result, our cus­to­mers can do more with less across a wide ran­ge of workloads, while simul­ta­neous­ly opti­mi­zing their businesses.”

AMD and AWS Expand EC2 for Grea­ter Per­for­mance and New Applications
Ama­zon EC2 M7a ins­tances, first pre­view­ed at this year’s AMD Data Cen­ter and AI Tech­no­lo­gy Pre­mie­re, cater to a wide ran­ge of workloads, pro­vi­ding cus­to­mers with up to 50 per­cent more com­pu­te per­for­mance than Ama­zon EC2 M6a ins­tances, while offe­ring new pro­ces­sor capa­bi­li­ties, such as AVX3-512, VNNI, and BFloat16. In addi­ti­on to high per­for­mance in gene­ral pur­po­se workloads, the Ama­zon EC2 M7a ins­tances are ide­al for appli­ca­ti­ons that bene­fit from high per­for­mance and high through­put such as finan­cial appli­ca­ti­ons, simu­la­ti­on mode­ling, gam­ing, mid-sized data stores and more.

Ama­zon EC2 Hpc7a ins­tances are desi­gned for tight­ly cou­pled high per­for­mance com­pu­ting workloads and deli­ver 2.5x bet­ter per­for­mance com­pared to Ama­zon EC2 Hpc6a ins­tances. The­se ins­tances meet the demands of incre­asing workload com­ple­xi­ty by offe­ring AWS cus­to­mers more com­pu­te, memo­ry and net­work per­for­mance. Powered by 300 Gb/s EFA net­work band­width, the Hpc7a ins­tances are ide­al­ly sui­ted for com­pu­te-inten­si­ve, laten­cy-sen­si­ti­ve workloads such as com­pu­ta­tio­nal flu­id dyna­mics, wea­ther fore­cas­ting, mole­cu­lar dyna­mics, and com­pu­ta­tio­nal che­mis­try. Ama­zon EC2 Hpc7a ins­tances also bring next-gene­ra­ti­on ser­ver tech­no­lo­gy like DDR5 memo­ry, which pro­vi­des 50 per­cent hig­her memo­ry band­width com­pared to DDR4 memo­ry to enable high-speed access to data in memory.

“To deli­ver high-level ope­ra­tio­nal intel­li­gence for wea­ther-depen­dent indus­tries, DTN deploys a suite of wea­ther data and models that deli­ver sophisti­ca­ted, high-reso­lu­ti­on out­puts and requi­re con­ti­nu­al pro­ces­sing of vast amounts of data from inputs across the glo­be,” said Lars Ewe, Chief Pro­duct and Tech­no­lo­gy Offi­cer, DTN. “Our col­la­bo­ra­ti­on with AWS allows us to bet­ter ser­ve our cus­to­mers with the most up-to-date wea­ther intel­li­gence that feed tho­se ana­ly­tic engi­nes. We are exci­ted to see how the next gene­ra­ti­on of Ama­zon EC2 Hpc7a ins­tances can poten­ti­al­ly sup­port our mis­si­on to pro­vi­de cus­to­mers with the insights they need at the moment they are needed.”

AMD began working with AWS in 2018 and now pro­vi­des more than 100 EPYC pro­ces­sor-based ins­tances for gene­ral pur­po­se, com­pu­te opti­mi­zed, memo­ry opti­mi­zed and high per­for­mance com­pu­ting workloads. Cus­to­mers such as DNT, Sprinklr, and True­Car have all bene­fit­ted from signi­fi­cant cost and cloud uti­liza­ti­on opti­miza­ti­on with AMD based Ama­zon EC2 ins­tances. With the­se new ins­tances, AWS cus­to­mers can con­ti­nue to take advan­ta­ge of the excel­lent per­for­mance, sca­la­bi­li­ty, and effi­ci­en­cy offe­red by AMD EPYC processors.

Sup­port­ing Resources

About AMD
For more than 50 years AMD has dri­ven inno­va­ti­on in high-per­for­mance com­pu­ting, gra­phics and visua­liza­ti­on tech­no­lo­gies. Bil­li­ons of peo­p­le, lea­ding For­tu­ne 500 busi­nesses and cut­ting-edge sci­en­ti­fic rese­arch insti­tu­ti­ons around the world rely on AMD tech­no­lo­gy dai­ly to impro­ve how they live, work and play. AMD employees are focu­sed on buil­ding lea­der­ship high-per­for­mance and adap­ti­ve 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: AMD) web­site, blog, Lin­ke­dIn and Twit­ter pages.

AMD, the AMD Arrow logo, EPYC 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.