Also check out our extended deep-dive coverage:
AMD CEO Lisa Su will take to the stage here in San Jose, California, to share the company's latest progress on enabling AI from the cloud to the edge and PCs. The show begins today, December 6, at 10am PT, and we're here to provide live event coverage.
AMD says it will reveal its Instinct MI300 accelerators at the event. All signs point to these coming as both a GPU and a blended CPU+GPU product (APU), both of which are designed to unseat Nvidia's dominance in the AI market.
Make no mistake; the Instinct MI300 is a game-changing design - the data center APU blends a total of 13 chiplets, many of them 3D-stacked, to create a chip with twenty-four Zen 4 CPU cores fused with a CDNA 3 graphics engine and eight stacks of HBM3. Overall, the chip weighs in with 146 billion transistors, making it the largest chip AMD has pressed into production.
If you're more interested in the latest PC technology, AMD is also expected to unveil its "Hawk Point" Ryzen 8000 mobile series of chips. Rumors point to these chips offering many of the same characteristics as their predecessors, but targeted enhancements offer more performance. These are the follow-on to AMD's Ryzen 7040 series, the first PC chips to launch with a dedicated AI processing NPU unit, so we think there's a chance these enhanced models will debut at the show.
Pull up a seat; the show starts shortly.
LIVE: Latest Updates
AMD has begun displaying its cautionary statements on the screen, so the show is about to start.
AMD CEO Lisa Su has come out on the stage. She opened the presentation reminiscing on the launch of ChatGPT just one year ago, and the explosive impact it has had on the world.
Generative AI will require significant investments to meet the needs for training and inference workloads. One year ago, AMD predicted a $150 billion TAM for AI workloads by 2027. Now AMD has revised that estimate up to $400 billion in 2027.
AMD is currently focusing on tearing down the barriers to AI adoption and cooperating with its partners to develop new solutions.
Lisa Su said that the availability of GPU hardware is the biggest barrier, and now the company is helping address that with the launch of its Instinct MI300 accelerators. The new CDNA 3 architecture delivers huge performance gains in multiple facets.
The MI300 has 150 billion transistors. 128-channels of HBM3, fourth-gen Infinity Fabric, and eight CDNA 3 GPU chiplets.
The Instinct MI300 is a game-changing design - the data center APU blends a total of 13 chiplets, many of them 3D-stacked, to create a chip with twenty-four Zen 4 CPU cores fused with a CDNA 3 graphics engine and 8 stacks of HBM3. Overall, the chip weighs in with 146 billion transistors, making it the largest chip AMD has pressed into production.
AMD claims up to a 1.3X more performance than Nvidia's H100 GPUs in certain workloads. The slide above outlines the claimed performance advantages.
Scalability is incredibly important -- performance needs to increase linearly as more GPUs are employed. Here AMD shows they match Nvidia's eight-GPU H100 HGX system with an eight-GPU AMD platform.
The MI300 delivers performance parity in training with Nvidia, but exhibits the strongest advantages in inference. AMD highlights a 1.6X advantage in inferencing.
Microsoft CTO Kevin Scott has come to the stage to talk with Lisa Su about the challenges of building out AI infrastructure.
While they discuss the details, here are some details about MI300.
Microsoft will have MI300X coud instances available in preview today.
Lisa Su displayed the AMD Instinct MI300X platform.
AMD CTO Victor Peng has come to stage to talk about the latest advances in ROCM, AMD's open source competitor to Nvidia's CUDA.
Peng talked about the advantages of the open ROCm ecosystem, as opposed to Nvidia's proprietary approach.
AMD's next-gen ROCm 6 is launching later this month. Support for Radeon GPUs continues, but it also has new optimizations for MI300.
ROCm provides up to a 2.6X improvement in vLLM, among other optimizations that total an 8X improvement on MI300X compared to ROCm 5 on MI250X (this isn't a great comparison).
AMD continues to work with industry stalwarts like Hugging Face and PyTorch to expand the open source ecosystem.
AMD GPUs, including the MI300, will be supported in the standard Triton distribution starting with version 3.0.
Peng is now talking with leaders from Databricks, essential AI, and Lamini.