admin
Alongside AMD’s broadly anticipated shopper product bulletins this night for desktop CPUs, cellular CPUs, and cellular GPUs, AMD’s CEO Dr. Lisa Su additionally had a shock up her sleeve for the massive crowd gathered for her prime CES keynote: a sneak peak at MI300, AMD’s next-generation information middle APU that’s presently beneath improvement. With silicon actually in hand, the short teaser laid out the fundamental specs of the half, together with reiterating AMD’s intentions of taking management within the HPC market.
First unveiled by AMD throughout their 2022 Monetary Analyst Day again in June of 2022, MI300 is AMD’s first shot at building a true data center/HPC-class APU, combining one of the best of AMD’s CPU and GPU applied sciences. As was laid out on the time, MI300 could be a disaggregated design, utilizing a number of chiplets constructed on TSMC’s 5nm course of, and utilizing 3D die stacking to position them over a base die, all of which in flip will probably be paired with on-package HBM reminiscence to maximise AMD’s out there reminiscence bandwidth.
AMD for its half isn’t any stranger to combining the skills of its CPUs and GPUs – one solely wants to take a look at their laptop computer CPUs/APUs – however up to now they’ve by no means finished so on a big scale. AMD’s present best-in-class HPC {hardware} is to mix the discrete AMD Intuition MI250X (a GPU-only product) with AMD’s EPYC CPUs, which is strictly what’s been finished for the Frontier supercomputer and different HPC tasks. MI300, in flip, is the subsequent step within the course of, bringing the 2 processor varieties collectively on to a single bundle, and never simply wiring them up in an MCM style, however going the total chiplet route with TSV stacked dies to allow extraordinarily excessive bandwidth connections between the assorted components.
The important thing level of tonight’s reveal was to point out off the MI300 silicon, which has reached preliminary manufacturing and is now in AMD’s labs for bring-up. AMD had beforehand promised a 2023 launch for the MI300, and having the silicon again from the fabs and assembled is a powerful signal that AMD is on observe to make that supply date.
Together with an opportunity to see the titanic chip in particular person (or at the least, over a video stream), the temporary teaser from Dr. Su additionally provided a couple of new tantalizing particulars in regards to the {hardware}. At 146 billion transistors, MI300 is the most important and most advanced chip AMD has ever constructed – and simply so. Although we are able to solely examine it to present chip designs, that is considerably extra transistors than both Intel’s 100B transistor Xeon Max GPU (Ponte Vecchio), or NVIDIA’s 80B transistor GH100 GPU. Although in equity to each, AMD is stuffing each a GPU and a CPU into this half.
The CPU aspect of the MI300 has been confirmed to make use of 24 of AMD’s Zen 4 CPU cores, lastly giving us a primary thought of what to anticipate with reference to CPU throughput. In the meantime the GPU aspect is (nonetheless) utilizing an undisclosed variety of CDNA 3 structure CUs. All of this, in flip, is paired with 128GB of HBM3 reminiscence.
In line with AMD, MI300 is comprised of 9 5nm chiplets, sitting on high of 4 6nm chiplets. The 5nm chiplets are undoubtedly the compute logic chipets – i.e. the CPU and GPU chiplets – although a exact breakdown of what’s what is just not out there. An affordable guess at this level could be 3 CPU chiplets (8 Zen 4 cores every) paired with presumably 6 GPU chiplets; although there’s nonetheless some cache chiplets unaccounted for. In the meantime, taking AMD’s “on high of” assertion actually, the 6nm chiplets would then be the bottom dies all of this sits on high of. Based mostly on AMD’s renders, it appears to be like like there’s 8 HBM3 reminiscence stacks in play, which means round 5TB/second of reminiscence bandwidth, if no more.
Close to efficiency expectations, AMD isn’t saying something new right now. Earlier claims have been for a >5x enchancment in AI performance-per-watt versus the MI250X, and an total >8x enchancment in AI coaching efficiency, and that is nonetheless what AMD is claiming as of CES.
The important thing benefit of AMD’s design, apart from the operational simplicity of placing CPU cores and GPU cores on the identical design, is that it’ll enable each processor varieties to share a high-speed, low-latency unified reminiscence house. This could make it quick and simple to go information between the CPU and GPU cores, letting every deal with the points of computing that they do greatest. As nicely, it might considerably simplify HPC programming at a socket stage by giving each processor varieties direct entry to the identical reminiscence pool – not only a unified digital reminiscence house with copies to cover the bodily variations, however a very shared and bodily unified reminiscence house.
AMD FAD 2022 Slide
When it launches within the later half of 2023, AMD’s MI300 is predicted to be going up towards a couple of competing merchandise. Probably the most notable of which is probably going NVIDIA’s Grace Hopper superchip, which mixes an NVIDIA Armv9 Grace CPU with a Hopper GPU. NVIDIA has not gone for fairly the identical stage of integration as AMD is, which arguably makes MI300 a extra bold venture, although NVIDIA’s resolution to take care of a cut up reminiscence pool is just not with out advantage (e.g. capability). In the meantime, AMD’[s schedule would have them coming in well ahead of arch rival Intel’s Falcon Shores XPU, which isn’t due until 2024.
Expect to hear a great deal more from AMD about Instinct MI300 in the coming months, as the company will be eager to show off their most ambitious processor to date.
