AMD Releases Versal Gen 2 Adaptive SoCs, Strongly Competing Embedded AI Markets

The edge AI computing markets will get much more competitive as AMD unveils the next generation of its Versal Series chips, specifically designed for dedicated AI engines.

At the Embedded World conference, AMD decided to unveil its new Versal AI Edge Series Gen 2 and Versal Prime Series Gen 2 adaptive chips, explicitly designed to address the growing AI needs of the markets. The new SoCs are said to deliver up to three times more performance than the previous generation, with the integration of "high-performing" ARM CPUs delivering 10x faster scalar compute.

The demand for AI-enabled embedded applications is exploding and driving the need for single-chip solutions for the most efficient end-to-end acceleration within the power and area constraints of embedded systems.

Backed by over 40 years of adaptive computing leadership, these latest generation Versal devices bring together multiple compute engines on a single architecture offering high compute efficiency and performance with scalability from the low-end to high-end.

- Salil Raje, SVP and GM of Adaptive and Embedded Computing Group, AMD

The Versal AI Gen 2 chips have a rather diverse CPU configuration, featuring eight Cortex A78AE processors and ten Cortex R52 cores, along with an ARM Mali-G78AE GPU for display use. AMD doesn't disclose many details regarding the new Versal series, but it has been revealed that the platform does support DDR5/LPDDR5X memory controllers along with several other connectivity upgrades that make them more widely adopted among audiences.

The enhanced Versal lineup does look to be progressing towards being a viable competitor in the embedded segments. Given that AMD continues to develop at this pace, it is likely to gain immense attention.

Another exciting factor noticed by the presentation slides released by AMD is that the company is heavily investing in the AI ecosystem, especially regarding advancements being made within Vitis AI, the firm's libraries built for efficient AI processing. Team Red has lagged significantly behind NVIDIA in the software ecosystem department, but this looks to change moving ahead, especially when we see AMD's focus on the embedded AI markets.

News Source: Global Newswire