New NVIDIA DGX A100 sys­tem harnes­ses PCIe® 4 sup­port, high-core count, and over­all per­for­mance of 2nd Gen AMD EPYC™ Pro­ces­sors to crea­te the world’s most advan­ced AI system

SANTA CLARA, Calif., June 08, 2020 (GLOBE NEWSWIRE) — AMD (NASDAQ: AMD) today announ­ced the NVIDIA DGX™ A100, the third gene­ra­ti­on of the world’s most advan­ced AI sys­tem, is the latest high-per­for­mance com­pu­ting sys­tem fea­turing 2nd Gen AMD EPYC™ pro­ces­sors. Deli­ve­ring 5 peta­flops of AI per­for­mance, the ela­s­tic archi­tec­tu­re of the NVIDIA DGX A100 enables enter­pri­ses to acce­le­ra­te diver­se AI workloads such as data ana­ly­tics, trai­ning, and inference.

NVIDIA DGX A100 lever­a­ges the high-per­for­mance capa­bi­li­ties, 128 cores, DDR4-3200MHz and PCIe® 4 sup­port from two AMD EPYC 7742 pro­ces­sors run­ning at speeds up to 3.4 GHz¹. The 2nd Gen AMD EPYC pro­ces­sor is the first and only cur­rent x86-archi­tec­tu­re ser­ver pro­ces­sor that sup­ports PCIe® 4, pro­vi­ding lea­der­ship high-band­width I/O that’s cri­ti­cal for high per­for­mance com­pu­ting and con­nec­tions bet­ween the CPU and other devices like GPUs.

“Only 2nd Gen AMD EPYC pro­ces­sors can pro­vi­de up to 64 cores and 128 lanes of PCIe 4 inter­con­nec­ti­vi­ty in a sin­gle x86 data cen­ter pro­ces­sor, and we’re exci­ted to see how the power of the NVIDIA DGX A100 sys­tem enables the I/O band­width to be effec­tively dou­bled,” said Rag­hu Nam­bi­ar, cor­po­ra­te vice pre­si­dent, data cen­ter eco­sys­tems and appli­ca­ti­on engi­nee­ring, AMD. “With 2nd Gen AMD EPYC pro­ces­sors, our part­ners and cus­to­mers can maxi­mi­ze per­for­mance and cost effi­ci­en­ci­es in hete­ro­ge­neous com­pu­ting, vir­tua­li­zed and hyper con­ver­ged infra­struc­tu­re workloads, pro­vi­ding teams with the fle­xi­bi­li­ty and capa­bi­li­ty to stay at the fore­front of innovation.”

“The NVIDIA DGX A100 deli­vers a tre­men­dous leap in per­for­mance and capa­bi­li­ties,” said Char­lie Boyle, vice pre­si­dent and gene­ral mana­ger, DGX sys­tems at NVIDIA. “The 2nd Gen AMD EPYC pro­ces­sors used in DGX A100 pro­vi­de high per­for­mance and sup­port for PCIe Gen4. NVIDIA has put tho­se fea­tures to work to crea­te the world’s most powerful AI sys­tem while main­tai­ning com­pa­ti­bi­li­ty with the GPU-opti­mi­zed soft­ware stack used across the enti­re DGX family.”

Sup­port­ing Resources

• Learn more about the 2nd Gen AMD EPYC Processor
• Beco­me a fan of AMD on Face­book
• Fol­low AMD on Twit­ter

About AMD
For more than 50 years AMD has dri­ven inno­va­ti­on in high-per­for­mance com­pu­ting, gra­phics and visua­liza­ti­on tech­no­lo­gies ― the buil­ding blocks for gam­ing, immersi­ve plat­forms and the dat­a­cen­ter. Hundreds of mil­li­ons of con­su­mers, lea­ding For­tu­ne 500 busi­nesses and cut­ting-edge sci­en­ti­fic rese­arch faci­li­ties around the world rely on AMD tech­no­lo­gy dai­ly to impro­ve how they live, work and play. AMD employees around the world are focu­sed on buil­ding gre­at 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, Face­book and Twit­ter pages.

^{AMD, the AMD Arrow logo, EPYC and com­bi­na­ti­ons the­reof, are trade­marks of Advan­ced Micro Devices, Inc. PCIe is a regis­tered trade­mark of PCI-SIG Cor­po­ra­ti­on. Other names are for infor­ma­tio­nal pur­po­ses only and may be trade­marks of their respec­ti­ve owners.}

____________________________________

^{¹ Max boost for AMD EPYC pro­ces­sors is the maxi­mum fre­quen­cy achie­va­ble by any sin­gle core on the pro­ces­sor under nor­mal ope­ra­ting con­di­ti­ons for ser­ver sys­tems. EPYC-18}

 

Contact:
Aaron Grabein AMD Communications
(512) 602-8950
aaron.grabein@amd.com Laura Graves
AMD Investor Relations
(408) 749-5467
laura.graves@amd.com