AMD Unveils New Epyc Server CPU in Newest AI Push

1-AMD%20Instinct%20MI300X_OAM%20Card_TopLeft%20%283%29.jpg

AMD has launched its next-generation Epyc server processor: a high-performance, energy-efficient CPU that’s designed for cloud, enterprise, and synthetic intelligence workloads, the corporate introduced right this moment (October 10).

Constructed with the brand new Zen 5 core structure, the brand new fifth-generation AMD Epyc CPU options as much as 192 cores and can be utilized as a standalone chip for general-purpose workloads or AI inferencing. The {hardware} may also be paired with AI accelerators like AMD’s Intuition Collection GPUs for bigger AI fashions and functions, executives stated.

The brand new AMD Epyc 9005 collection processor, previously code-named Turin, gives as much as 17% higher directions per clock (IPC) for enterprise and cloud workloads and as much as 37% increased IPC for AI and high-performance computing workloads when in comparison with AMD’s Zen 4 chips that had been first launched two years in the past, the corporate stated.

With the discharge of the brand new processor, AMD will “as soon as once more take an enormous generational leap in efficiency,” stated Forrest Norrod, govt vp, and basic supervisor of AMD’s knowledge heart options enterprise Group, throughout a pre-briefing with media and analysts.

At its Advancing AI occasion in San Francisco right this moment, the corporate additionally introduced new GPUs and knowledge heart networking options, together with a brand new DPU and a NIC to hurry AI functions. The chipmaker reiterated its plan to launch a brand new GPU yearly, beginning with the AMD Intuition MI325X accelerator, which will probably be accessible in the course of the fourth quarter of this 12 months.

Associated:AI Accelerated Servers Gasoline Progress in Data Center Spending

Analysts’ Tackle AMD’s Bulletins

General, analysts say AMD is doing what it must do to compete towards rivals Intel and Nvidia – and it’s doing it very effectively. In actual fact, whereas Intel nonetheless dominates, AMD executives stated they’ve captured 34% market share within the server CPU market.

“AMD simply continues to execute 12 months after 12 months. They’ve gotten to the purpose the place it’s simply enchancment, enchancment, enchancment,” stated Jim McGregor, founder and principal analyst at Tirias Analysis.

Ian Cutress, chief analyst of Greater than Moore, agreed. “They’re hitting all the best company notes. They’re on observe with all the pieces they’ve talked about,” he stated. “This occasion is just not solely about their latest technology CPU, it’s their yearly cadence with the GPU, and so they’re speaking about networking and the synergy getting into between. They’re principally saying, ‘We’re nonetheless placing one foot in entrance of the opposite, and it seems, we’re fairly good at it.’”

AMD-Architecture.jpg

Intel has finished a great job with its roadmap and up to date launch of its Intel Xeon 6 CPUs and Gaudi 3 AI accelerator, however by capturing one-third of the information heart CPU market, AMD has momentum on its aspect, McGregor stated.

Associated:Data Center Chips in 2024: Prime Developments and Releases

AMD can also be doing effectively with its entry into the GPU market as an alternative choice to Nvidia’s GPUs, he stated. Many enterprises are simply beginning to discover the right way to combine GPUs and AI workloads into its knowledge facilities. There’s sturdy curiosity in AMD as one other supply for GPUs, he stated. 

“AMD has momentum. They’re nonetheless rising, and so long as they nonetheless proceed to execute on their roadmap, they’re in an excellent place,” McGregor stated.

Zen 5 Structure

The corporate is utilizing two completely different Zen 5 core architectures for its fifth-generation CPUs. Zen 5, constructed utilizing the 4-nanometer manufacturing course of, options as much as 128 cores and is constructed for efficiency. Zen 5c, constructed utilizing 3nm and options as much as 192 cores, is designed for effectivity and optimized for parallelization and throughput, McGregor famous.

It’s very very like the technique Intel took with its Intel Xeon 6 environment friendly cores (E-cores) and efficiency cores (P-cores), the {hardware} analyst stated. 

The reason being that knowledge heart operators’ wants are altering as a result of they’ve various kinds of workloads which have distinctive necessities and require completely different processors.

Associated:AI Server Market Projected to Attain $180B by 2032

“Each Intel and AMD have developed that efficiency and effectivity core technique,” McGregor stated. “They understand they need to be extra versatile as a result of we’ve seen some hyperscalers develop their very own processors for various functions. So that is type of their response to the wants of not simply the system distributors, however the finish clients – the information facilities.”

Staying On Message

AMD’s messaging at right this moment’s occasion is that it may possibly ship a full infrastructure answer that features CPUs, GPUs, DPUs, and networking, however the firm must beef up its software program, stated Peter Rutten, analysis vp in IDC’s worldwide infrastructure analysis group.

AMD right this moment stated it continues to put money into and enhance its AMD ROCm software program stack for constructing AI and HPC functions working on its GPUs. Nonetheless, Nvidia is much forward with CUDA, Nvidia AI Enterprise, Nvidia NIM microservices, and Omniverse, McGregor stated.

“AMD is principally saying we, too, can ship you your complete infrastructure and software program. That’s good. That’s what clients need,” Rutten stated. “So that you need these CPUs, GPUs, and quick networking. However I’m frightened concerning the precise developer story, the tip consumer story. The software program story continues to be getting short-changed and that needs to be a important focus.”

AMD’s GPU Roadmap and AI Networking Options

On the GPU entrance, the forthcoming AMD Intuition MI325X will provide 256GB of HBM3E reminiscence and 6TB/s of reminiscence bandwidth, which the corporate says is 1.8 instances extra capability and 1.3 instances extra bandwidth than Nvidia’s H200 Tensor Core GPU.

AMD stated server distributors are anticipated to start delivery servers with the MI325X within the 2025 first quarter, together with Dell Applied sciences, Hewlett Packard Enterprise, Lenovo, and Supermicro, and others are anticipated to start delivery servers working the AMD.

After the MI325X, the corporate plans to launch the Intuition MI350 collection accelerator in the course of the second half of 2025 and the MI400 collection in 2026.

The MI350 collection GPU will provide 288GB of HBM3E reminiscence capability and can present a 35x enhance in AI inferencing efficiency over AMD’s preliminary GPU – the MI300 collection accelerator, the corporate stated.

On the networking entrance, AMD introduced the brand new AMD Pensando Salina DPU, an accelerator that takes over knowledge processing duties, equivalent to networking and safety, to unlock CPU assets.

AMD’s new third-generation Pensando Salina DPU will present twice the efficiency, bandwidth, and scale as its earlier technology and is designed for the front-end of a knowledge heart community, which is able to enhance the efficiency, effectivity, safety, and scalability for data-driven AI functions, the corporate stated.

For the again finish of the community, which manages knowledge switch between accelerators and clusters, AMD introduced the Pensando Pollara 400 NIC, which the corporate claims would be the first Extremely Ethernet Consortium (UEC)-ready AI NIC, and can cut back latency, enhance throughput and forestall congestion.

The DPU and NIC are anticipated to be accessible in the course of the first half of 2025.