Editor’s take: Within the ever-evolving world of GenAI, essential advances are taking place throughout chips, software program, fashions, networking, and techniques that mix all these parts. That is what makes it so exhausting to maintain up with the most recent AI developments. The problem issue turns into even larger if you happen to’re a vendor constructing these sorts of merchandise and dealing not solely to maintain up, however to drive these advances ahead. Toss in a competitor that is just about cornered the market – and within the course of, grown into one of many world’s most dear corporations – and, effectively, issues can seem fairly difficult.
That is the scenario AMD discovered itself in because it entered its newest Advancing AI occasion. However somewhat than letting these potential roadblocks deter them, AMD made it clear that they’re impressed to develop their imaginative and prescient, their vary of choices, and the tempo at which they’re delivering new merchandise.
From unveiling their Intuition MI400 GPU accelerators and next-generation “Vulcan” networking chips, to model 7 of their ROCm software program and the debut of a brand new Helios Rack structure. AMD highlighted all the important thing elements of AI infrastructure and GenAI-powered options. In reality, one of many first takeaways from the occasion was how far the corporate’s attain now extends throughout all of the important components of the AI ecosystem.
AMD Intuition roadmap
As anticipated, there was an excessive amount of give attention to the official launch of the Intuition MI350 and higher-wattage, faster-performing MI355X GPU-based chips, which AMD had beforehand introduced final yr. Each are constructed on a 3nm course of and have as much as 288 MB of HBM3E reminiscence and can be utilized in each liquid-cooled and air-cooled designs.
In accordance with AMD’s testing, these chips not solely match Nvidia’s Blackwell 200 efficiency ranges, however even surpass them on sure benchmarks. Specifically, AMD emphasised enhancements in inferencing pace (over 3x quicker than the earlier technology), in addition to price per token (as much as 40% extra tokens per greenback vs. the B200, in accordance with AMD).
AMD additionally offered extra particulars on its next-generation MI400, scheduled for launch subsequent yr, and even teased the MI500 for 2027. The MI400 will supply as much as 432 GB of HBM4 reminiscence, reminiscence bandwidth of 19.6 TB/sec, and 300 GB/sec of scale-out reminiscence bandwidth – all of which might be essential for each working bigger fashions and assembling the varieties of huge rack techniques anticipated to be wanted for next-generation LLMs.
A number of the extra stunning bulletins from the occasion centered on networking.
First was a dialogue of AMD’s next-generation Pensando networking chip and a community interface card they’re calling the AMD Pensando Pollara 400 AI NIC, which the corporate claims is the business’s first transport AI-powered community card. AMD is a part of the Extremely Ethernet Consortium and, not surprisingly, the Pollara 400 makes use of the Extremely Ethernet commonplace. It reportedly gives 20% enhancements in pace and 20x extra capability to scale than aggressive playing cards utilizing InfiniBand know-how.
As with its GPUs, AMD additionally introduced its next-generation networking chip, codenamed “Vulcano,” designed for big AI clusters. It would supply 800 GB/sec community speeds and as much as 8x the scale-out efficiency for big teams of GPUs when launched in 2026.
AMD additionally touted the brand new open-source Extremely Accelerator Hyperlink (UAL) commonplace for GPU-to-GPU and different chip-to-chip connections. A direct reply to Nvidia’s NVLink know-how, UAL relies on AMD’s Infinity Material and matches the efficiency of Nvidia’s know-how whereas offering extra flexibility by enabling connections between any firm’s GPUs and CPUs.
Placing all of those numerous parts collectively, arguably the most important {hardware} information – each actually and figuratively – from the Advancing AI occasion was AMD’s new rack structure designs.
Giant cloud suppliers, neocloud operators, and even some subtle enterprises have been shifting towards rack-based full options for his or her AI infrastructure, so it was not stunning to see AMD make these bulletins – significantly after buying experience from ZT Techniques, an organization that designs rack computing techniques, earlier this yr.
Nonetheless, it was an essential step to point out an entire aggressive providing with much more superior capabilities towards Nvidia’s NVL72 and to show how all of the items of AMD’s silicon options can work collectively.
Along with exhibiting techniques primarily based on their present 2025 chip choices, AMD additionally unveiled their Helios rack structure, coming in 2026. It would leverage an entire suite of AMD chips, together with next-generation Epyc CPUs (codenamed Venice), Intuition MI400 GPUs, and the Vulcano networking chip. What’s essential about Helios is that it demonstrates AMD is not going to solely be on equal footing with next-generation Vera Rubin-based rack techniques Nvidia has introduced for subsequent yr, however might even surpass them.
In reality, AMD arguably took a web page from the latest Nvidia playbook by providing a multi-year preview of its silicon and rack-architecture roadmaps, making it clear that they don’t seem to be resting on their laurels however shifting aggressively ahead with important know-how developments.
Importantly, they did so whereas touting what they count on might be equal or higher efficiency from these new choices. (In fact, all of those are primarily based on estimates of anticipated efficiency, which may – and certain will – change for each corporations.) No matter what the ultimate numbers show to be, the larger level is that AMD is clearly assured sufficient in its present and future product roadmaps to tackle the hardest competitors. That claims so much.
ROCm and software program developments
As talked about earlier, the important thing software program story for AMD was the discharge of model 7 of its open-source ROCm software program stack. The corporate highlighted a number of efficiency enhancements on inferencing workloads, in addition to elevated day-zero compatibility with lots of the hottest LLMs. Additionally they mentioned ongoing work with different important AI software program frameworks and growth instruments. There was a selected give attention to enabling enterprises to make use of ROCm for their very own in-house growth efforts by means of ROCm Enterprise AI.
On their very own, a few of these adjustments are modest, however collectively they present clear software program momentum that AMD has been constructing. Strategically, that is important, as a result of competitors towards Nvidia’s CUDA software program stack continues to be the most important problem AMD faces in convincing organizations to undertake its options. It will likely be fascinating to see how AMD integrates a few of its latest AI software-related acquisitions – together with Lamini, Brium, and Untether AI – into its vary of software program choices.
One of many extra stunning bits of software program information from AMD was the mixing of ROCm assist into Home windows and the Home windows ML AI software program stack. This helps make Home windows a extra helpful platform for AI builders and probably opens up new alternatives to raised leverage AMD GPUs and NPUs for on-device AI acceleration.
Talking of builders, AMD additionally used the occasion to announce its AMD Developer Cloud for software program designers, which provides them a free useful resource (at the least initially, through free cloud credit) to entry MI300-based infrastructure and construct functions with ROCm-based software program instruments. Once more, a small however critically essential step in demonstrating how the corporate is working to develop its affect throughout the AI software program growth ecosystem.
Clearly, the collective actions the corporate is taking are beginning to make an impression. AMD welcomed a broad vary of consumers leveraging its options in an enormous approach, together with OpenAI, Microsoft, Oracle Cloud, Humane, Meta, xAI, and plenty of extra.
Additionally they talked about all their work in creating sovereign AI deployments in international locations around the globe. And finally, as the corporate began the keynote with, it is all about persevering with to construct belief amongst its clients, companions and potential new shoppers.
AMD has the advantage of being a particularly robust various to Nvidia – one which many available in the market wish to see improve its presence for aggressive stability. Based mostly on what was introduced at Advancing AI, it appears like AMD is shifting in the precise route.
Bob O’Donnell is the founder and chief analyst of TECHnalysis Analysis, LLC a know-how consulting agency that gives strategic consulting and market analysis providers to the know-how business {and professional} monetary group. You possibly can comply with him on X @bobodtech
