AMD EPYC processor ecosystem grows with integration into NVIDIA’s DGX A100 system


Chip maker AMD has announced the NVIDIA DGX A100, the third generation of the advanced artificial intelligence (AI) system, is the latest high-performance computing system featuring second 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 second gen AMD EPYC processor is the 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 second gen AMD EPYC processors can provide up to 64 cores and 128 lanes of PCIe 4 interconnectivity in a single x86 data centre 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 centre ecosystems and application engineering, AMD.

“With 2nd Gen AMD EPYC processors, our partners and customers can maximise performance and cost efficiencies in heterogeneous computing, virtualised 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 second 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-optimised software stack used across the entire DGX family.”

About Author

Leave A Reply