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.” (…) Wei­ter­le­sen »