AMD: Instinct MI300 APU with Zen 4 and CDNA 3 Up and Running in the Lab

(Image credit: AMD)

Mark Papermaster, chief technology officer of AMD, said at a conference that the company's next-generation Instinct MI300 accelerated processing unit for data centers and high-performance computing is already up and running in AMD's labs. The APU uses AMD's Zen 4 and CDNA 3 architectures and will power the El Capitan supercomputer that is expected to break the 2 ExaFLOPS barriers sometimes in 2024.

"But with what we announced and have rolled out with our next-generation Instinct that we already have back in the labs, the MI300, it is a true datacenter APU," said Papermaster at the Wells Fargo 2022 TMT Summit (via SeekingAlpha). "It is a CPU and a GPU acceleration that is leveraging the Infinity architecture to share the same memory fully coherently. It is all sharing high-bandwidth memory."

AMD's Instinct MI300 is a multi-chiplet APU carrying Zen 4 general-purpose x86 cores, and CDNA 3-based compute GPU that share a unified on-package pool of memory comprising of Infinity Cache as well as HBM. AMD will use TSMC's N5 (5nm-class) fabrication process to produce CPU/GPU chiplets for the MI300, but the company has yet to disclose how many CPU cores and GPU stream processors are set to be packed into the hybrid processor.

Putting CPU cores and GPU accelerators into one package and making them use unified memory is the Holy Grail of supercomputing as it not only combines the best of both worlds (general purpose processing and highly parallel acceleration), but it also dramatically simplifies programming and makes it easier to get all performance potential out of execution engines.

The Instinct MI300 APU is set to power the U.S. Department of Energy's El Capitan supercomputer, which will be installed at the Lawrence Livermore National Laboratory (LLNL) sometime in 2023 and will become fully operational in mid-2024. 

AMD plans to roll out its Instinct MI300 sometime in 2023, which is why it is not surprising that the processor is already up and running in its labs. Meanwhile, it is unclear whether the company will supply the MI300 to any clients outside the supercomputer world in mass quantities next year.

Since AMD's Instinct MI300 will be the industry's first data center and HPC-grade APU, there will be a lot of interest in it in the supercomputing community. Meanwhile, AMD's Instinct MI300 will not be the only hybrid processor for data centers packing x86 and GPU resources that will be available in the coming years. For example, Intel is working on its codenamed Falcon Shores product with x86 and Xe-HPC cores in the same package and expects to make it available in 2024.

Anton Shilov
Freelance News Writer

Anton Shilov is a Freelance News Writer at Tom’s Hardware US. Over the past couple of decades, he has covered everything from CPUs and GPUs to supercomputers and from modern process technologies and latest fab tools to high-tech industry trends.

  • quadibloc2
    I will definitely agree that having both the CPU and a GPU compute accelerator working from unified memory is good. But the Holy Grail? Don't we already have something that also works from unified memory, but is much more flexible, and hence usable, than a GPU accelerator? I'm thinking of the SX-Aurora TSUBASA from NEC, which is, or at least was, the last survivor of the vector supercomputers that began with the Cray I. Although it appears that today both ARM and RISC-V are adding similar capabilities.
  • bit_user
    it is unclear whether the company will supply the MI300 to any clients outside the supercomputer world in mass quantities next year.
    I think that depends a lot on what socket or form factor it uses. OAM?

    Also, I have to wonder whether it'll have any external DRAM, or if it'll be limited to just the in-package HBM.