AMD Instinct™ MI200 Adopted for Large-Scale AI Training in Microsoft Azure

ꟷ Micro­soft Azu­re is the first public cloud to deploy AMD Instinct MI200 acce­le­ra­tors ꟷ

SANTA CLARA, Calif., May 26, 2022 (GLOBE NEWSWIRE) — AMD (NASDAQ: AMD) and Micro­soft con­tin­ued their col­la­bo­ra­ti­on in the cloud, with Micro­soft announ­cing the use of AMD Instinct™ MI200 acce­le­ra­tors to power lar­ge sca­le AI trai­ning workloads. In addi­ti­on, Micro­soft announ­ced it is working clo­se­ly with the PyTorch Core team and AMD data cen­ter soft­ware team to opti­mi­ze the per­for­mance and deve­lo­per expe­ri­ence for cus­to­mers run­ning PyTorch on Micro­soft Azu­re and ensu­re that deve­lo­pers’ PyTorch pro­jects take advan­ta­ge of the per­for­mance and fea­tures of AMD Instinct accelerators.

AMD Instinct MI200 acce­le­ra­tors pro­vi­de cus­to­mers with cut­ting-edge AI and HPC per­for­mance and will power many of the world’s fas­test super­com­pu­ter sys­tems that push the boun­da­ries of sci­ence,” said Brad McCre­die, cor­po­ra­te vice pre­si­dent, Data Cen­ter and Acce­le­ra­ted Pro­ces­sing, AMD. “Our work with Micro­soft to enable lar­ge-sca­le AI trai­ning and infe­rence in the cloud not only high­lights the expan­si­ve tech­no­lo­gy col­la­bo­ra­ti­on bet­ween the two com­pa­nies, but the per­for­mance capa­bi­li­ties of AMD Instinct MI200 acce­le­ra­tors and how they will ulti­m­ate­ly help cus­to­mers advan­ce the gro­wing demands for AI workloads.”

We’re proud to build upon our long-term com­mit­ment to inno­va­ti­on with AMD and make Azu­re the first public cloud to deploy clus­ters of the AMD Instinct MI200 acce­le­ra­tor for lar­ge sca­le AI trai­ning,” said Eric Boyd, cor­po­ra­te vice pre­si­dent, Azu­re AI, Micro­soft. “We have star­ted test­ing the MI200 with our own AI workloads and are see­ing gre­at per­for­mance, and we look for­ward to con­ti­nuing our col­la­bo­ra­ti­on with AMD to bring cus­to­mers more per­for­mance, choice and fle­xi­bi­li­ty for their AI needs.”

The AMD Instinct MI200 acce­le­ra­tors join other AMD pro­ducts being used at Micro­soft Azu­re inclu­ding the new­ly announ­ced Azu­re HBv3 vir­tu­al machi­nes which use 3rd Gen AMD EPYC™ pro­ces­sors with AMD 3D V‑Cache™ Tech­no­lo­gy, and num­e­rous other ins­tances for con­fi­den­ti­al com­pu­ting, gene­ral pur­po­se workloads, memo­ry bound workloads, visu­al workloads and more.

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: AMDweb­siteblogLin­ke­dIn and Twit­ter pages.

©2022 Advan­ced Micro Devices, Inc. All rights reser­ved. AMD, the AMD Arrow logo, CDNA, EPYC, Instinct, and com­bi­na­ti­ons the­reof are trade­marks of Advan­ced Micro Devices, Inc. Other pro­duct names used in this publi­ca­ti­on are for iden­ti­fi­ca­ti­on pur­po­ses only and may be trade­marks of their respec­ti­ve companies.