AMD has confirmed that a next-generation multi-chip, multi-IP Instinct CDNA 4 accelerator is currently under development and is expected to be released in 2023, known as the Instinct MI300 GPU. Technically speaking, this is actually an APU that will combine the next generation of CDNA 3 cores with the next generation Zen 4 CPU cores.
That's right: this chip combines CPU and GPU cores in a single package for data centers and AI, and the expected performance boost is reportedly monstrous.
The Instinct MI300 accelerator has a unified memory APU architecture and new math formats to deliver a 5x performance per watt improvement over CDNA 2, as well as a projected 8x improvement in AI drive performance compared to its spiritual predecessor, the MI250X.
Instinct will make this possible using a 5nm process node and a fourth-generation Infinity architecture. Essentially, we should see performance improvements as the unified architecture eliminates redundant copies of memory and removes the need for a second pool of DRAM attached to the CPU.
These are, of course, internal AMD stats, so take performance predictions with a grain of salt until actual performance can be documented. No official launch date was provided, though AMD confirmed at its Financial Analyst Day 2022 that it plans to release the Instinct MI300 in 2023.
David Wang announced the Instinct-class chips for the AI and data center segment along with the Compute GPU roadmap, which also includes AMD RDNA 4 Gaming GPUs.
"This is where we think we can win in terms of differentiation," AMD CEO Lisa Su said in her keynote address at the event. "It's about IT leadership. It's about expanding data center leadership. It's about expanding our AI footprint. It's about expanding our software capability. And then it's really about putting together a custom solutions effort broader because we think it's a growth area for the future."
Analysis: It won't be an easy win for AMD
This is far from AMD's first rodeo with supercomputing, as it released its first data center GPU (the GCN-based Vega II) in late 2018, followed by its first CDNA-based Radeon Instinct MI100 GPU in 2020. .
Nvidia also unveiled its GPU roadmap for the year in March with the announcement of its Hopper GPU architecture and has long dominated supercomputer accelerator sales, reporting a 90% market share in 2021.
AMD's latest foray into the data center market won't be an easy win, especially with Intel's Falcon Shores XPU poised to add more competition in 2024, though that means AMD, Nvidia and Intel will all have hybrid CPU-GPU chips. who enter data. central market in the coming years.
Still, Team Red is more confident than ever, so we'll just have to watch this space and see if Nvidia can hold on to its supercomputer crown.