AMD CEO Says EPYC Turin “Zen 5” CPUs Deliver Significant Performance & Efficiency Gains, MI300 To Drive Over $2B Revenue In 2024, Talks Arm PC Competition

01.11.2023 - 10:21 / wccftech.com / Lisa Su

During their Q3 2023 earnings call, AMD CEO, Dr. Lisa Su, talked about the upcoming EPYC "Turin" CPU & Instinct "MI300" GPU portfolio for Data Centers/AI while also commenting on the surging competition from Arm-based chips in the PC segment.

Following its Q3 2023 earnings, AMD CEO commented about its next-gen CPU/GPU portfolio and how it will further drive revenue up.

Starting with EPYC, Dr. Lisa Su stated that the next-gen EPYC Turin family of server CPUs featuring the Zen 5 core architecture was on track for launch in 2024. This will mark two years since the launch of AMD's Zen 4-based Genoa CPUs which were launched in late 2022. The next-gen Turin family is said to deliver significant performance and efficiency gains. AMD also confirmed that the first Turin CPUs are already running in the labs of their top customers and partners with the early responses being very strong and in favor of the Turing family.

We are building on this momentum with our next-gen Turin server processors based on our new Zen 5 core that delivers significant performance and efficiency gains. Turin is in the labs of our top customers and partners now, and customer feedback has been very strong and we're on track to launch in 2024.

Dr. Lisa Su - AMD CEO (Q3 2023 Earnings Call)

AMD just completed its Zen 4 family of EPYC CPUs which comes in various flavors such as Genoa, Genoa-X, Bergamo, and Siena. The Zen 5 family is going to be just as diverse, offering higher core counts, more cache, and a revamped architecture that is certainly going to drive those efficiency & performance numbers up.

Further diving into the EPYC figures, AMD reported that the 4th Gen EPYC lineup saw its record quarterly revenue & the company also witnessed revenue share gains in the server CPU segment.

On the GPU, or should I say APU, side of things, AMD confirmed that it has struck a deal with multiple large hyper-scale customers who will be deploying the Instinct MI300 accelerators for powering their data center and AI requirements. The company continues to progress with the bring-up and validation of both MI300A and MI300X accelerators and the performance is said to exceed their expectations.

In the Data Center, multiple large hyperscale customers committed to deploy Instinct MI300 accelerators, supported by our latest ROCm software suite and the growing adoption of an open hardware-agnostic software ecosystem.

On the hardware side, bring-up and validation of our MI300A and MI300X accelerators continue progressing to plan with performance now meeting or exceeding our expectations.

Production shipments of Instinct MI300A APUs started earlier this month to support the El Capitan Exascale Supercomputer, and we are on track to begin production shipments of