Monday, June 24th 2024

AMD Ryzen AI 300 Pro Series Could be Equipped with up to 128 GB of Memory

by
AleksandarK
 Discuss (43 Comments)
According to the leaked listing posted on X by user @Orlak29_, reports suggest that Pro versions of the AMD Ryzen 7 AI and Ryzen 9 AI are in the pipeline, with a potential game-changer in the form of the high-end "Strix Halo" model. The standout feature of the Strix Halo is its rumored support for up to 128 GB of RAM, a significant leap from AMD's current offerings. This massive memory capacity could prove valuable for AI workloads and data-intensive applications, potentially positioning AMD better against offerings from Intel and Qualcomm. Leaked diagrams hint at a unique design for the Strix Halo, featuring a chiplet layout reminiscent of a graphics card. The processor is reportedly surrounded by memory on three sides, enabling the massive 128 GB capacity.

While this top-tier model is expected to carry a premium price, it could find a ready market among professionals and enthusiasts demanding both raw processing power and extensive memory resources. On the performance front, rumors suggest the Strix Halo will boast up to 16 Zen 5 cores and a GPU with 40 Compute Units based on RDNA 3.5 architecture. This combination might rival the performance of high-end mobile GPUs like the RTX 4060 or even the RTX 4070 for laptops.
As with previous generations, AMD is expected to release Pro versions of these processors with additional features like ECC memory support.
Sources: @Orlak29_, via ComputerBase.de, Chiphell

Related News

Add your own comment

43 Comments on AMD Ryzen AI 300 Pro Series Could be Equipped with up to 128 GB of Memory

#26
Wirko
Tek-CheckTop Strix Halo SKU should have LPDDR5X at 8000 or 8500 MT/s, so 256-270 GB/s.
That will require at least 4-dies-high stacking, probably TSV because of high speed. That looks awfully expensive, like those ultra-expensive server DIMMs up to 512 GB, also with stacked dies.
Posted on Reply
#27
Minus Infinity
Tek-CheckTop Strix Halo SKU should have LPDDR5X at 8000 or 8500 MT/s, so 256-270 GB/s.
Halo is also moving to 256 bit bus, RDNA3.5, will support much higher speed (LP)DDR5 memory as you point out and is rated at 120W TDP. It should be able to deliver a huge uplift compared to 780M. I wouldn't be surprised to see 7600XT+ levels of performance.
Posted on Reply
#28
Vayra86
usinameThe comparison is with mobile x70 card, not desktop. About 4070 mobile, this card is insult for the x70 tier so its very achievable, 25% slower then 7600xt which has 32 CUs, 20% less than Strix Halo. Also 7600xt has 288GB/s bandwidth vs ~200GB/s shared between the CPU and GPU.
Plus this is RDNA 3.5 vs RDNA 3, 780m 12CU is already as fast as the desktop rx 6400 with 12CU, so I expect it to be at least as fast as 4070 mobile
hahaha wow an x70 (!!) mobile is 20% slower than an x60 desktop nowadays? Oh man the sadness of marketing in mobile GPUs knows no bounds. Its like they progress backwards
LabRat 891AMD APU with On-package ultra low latency RAM?
Been waiting for this for *years*.

Now, do HBM :rockout:
God no, please no. We've seen where that ends in consumer GPU
Posted on Reply
#29
ADB1979
AnarchoPrimitivWell, despite what some people may say, I think Strix Halo will be a revolutionary product and will fundamentally shake up the product stack and offer the most competition to nvidia in years, and most interestingly, not from the above (halo products), but below (entry and mid range).
Strix Halo will be the (latest) reformation of the Workstation / HEDT market and will create a whole new entrant to the sector. Interestingly this is actually a lot like the SGI Xeon systems, their big selling point was that the graphics had access to vast amounts of RAM, far more than their competitors and for some that was an instant sell.

It will be interesting to see the various uses, custom software, tweaks, etc that people do to Strix Halo systems when they end up in the hands of consumers, this will be self perpetuating for a while as people keep on tweaking and generating more interest and competition, plus we all get to learn about the various things that can be done with huge amounts of graphics RAM, itself a preview into the future.
Tek-CheckThere should be entire segment, with 4-5 SKUs, from top Halo to entry systems.
There is a list leaked by MLID (albeit it's very old) that lists 4-5 SKU's, although he noted that one of them makes no sense except to use up every piece of silicon regardless (because everything (literally) is selling) so why not.

Personally I want to see a NUC style mini PC with 2x 128-bit LPCAMM2 (or CAMM2) modules for the DIY market, plus one in some kind of ATX form factor to make use of the (limited) PCIe lanes.
Posted on Reply
#30
Wirko
ADB1979plus we all get to learn about the various things that can be done with huge amounts of graphics RAM
Fill it with various LLMs... I mean, what else?
Posted on Reply
#31
Sound_Card


Credit Tomshardware: but I am sticking to my internal hype that Halo is going to be at least as fast as the 6800m. The highest end modal at least. 32mb of Infinity Cache and 64mb of L3. This APU is designed to murder the industry.

EDIT: Also, didn't the 6800m only have 8x lanes of PCIe 4.0? and was limited to DDR4 system ram? That is when it ran out of its GDDR memory. I think there will be situations where the 6800m (paired with the 6900hx) comes out on top, and situations where this APU comes out on top, but I think HALO is going to come out on top more.
Posted on Reply
#32
Tek-Check
WirkoThat will require at least 4-dies-high stacking, probably TSV because of high speed. That looks awfully expensive, like those ultra-expensive server DIMMs up to 512 GB, also with stacked dies.
Videocardz says the top SKU competes with 4070 mobile.
WirkoThat will require at least 4-dies-high stacking, probably TSV because of high speed. That looks awfully expensive, like those ultra-expensive server DIMMs up to 512 GB, also with stacked dies.
No stacking. Three dies, most likely.
Posted on Reply
#33
Wirko
Tek-CheckNo stacking. Three dies, most likely.
Stacking of LPDDR dies is what I mean. If there are 8 packages, the capacity of each package has to be 16 GB or 128 Gbit. Largest dies that (almost) exist are 32 Gbit.
Posted on Reply
#34
Tek-Check
WirkoStacking of LPDDR dies is what I mean. If there are 8 packages, the capacity of each package has to be 16 GB or 128 Gbit. Largest dies that (almost) exist are 32 Gbit.
There must be higher capacity chips in existence for LPCAMM2 module.

I can see Samsung has on their website several 128Gbit modules.
Posted on Reply
#35
Wirko
Tek-CheckThere must be higher capacity chips in existence for LPCAMM2 module.

I can see Samsung has on their website several 128Gbit modules.
Yes but they're always stacked. Even higher than I thought, as I see 16-dies-tall stacks are possible. It checks out:

one die = 16 Gbit = 2 GB
up to 16 dies = up to 32 GB per package
four packages = up to 128 GB.

www.micron.com/about/blog/memory/dram/lpcamm2-no-compromise-for-next-gen-laptops
Posted on Reply
#37
Sound_Card
There is no way the upper SKU's of Strix Halo are going to make it into Laptops. Nvidia is not going to allow it. Instead, I see Strix Halo dominating mini-pc's and quite potentially being the forerunner to the next consoles and handhelds. I do see Strix Point being the industry darling for all other laptops not radically marketed for gaming.
Posted on Reply
#38
R0H1T
Sound_CardNvidia is not going to allow it.
Ok but who the heck is Nvidia to not "allow" it?
Posted on Reply
#39
Yashyyyk
Sound_CardThere is no way the upper SKU's of Strix Halo are going to make it into Laptops. Nvidia is not going to allow it. Instead, I see Strix Halo dominating mini-pc's and quite potentially being the forerunner to the next consoles and handhelds. I do see Strix Point being the industry darling for all other laptops not radically marketed for gaming.
Why would consoles pay for extra CPU power they won't use when they are GPU-bound (and have not much more GPU performance than the current consoles)?

Nvidia needs to get rid of their VRAM allergy and give better memory bandwidth if they care, their cards are already more efficient
Posted on Reply
#40
Wirko
Tek-CheckAlso, some laptops can simply have two LPCAMM2 modules, each 64GB onn 128-bit bus.
This has been demonstrated for CAMM2. Its connector is made up of two parallel sections that look identical to each other, so using two half-bit-width modules is possible, apparently. LPCAMM2 doesn't seem to be designed with this in mind.
Posted on Reply
#41
Tek-Check
WirkoThis has been demonstrated for CAMM2. Its connector is made up of two parallel sections that look identical to each other, so using two half-bit-width modules is possible, apparently. LPCAMM2 doesn't seem to be designed with this in mind.
Two full separate modules, one 128-bit interface for each, on each side of the APU.
Posted on Reply
#42
Wirko
Tek-CheckTwo full separate modules, one 128-bit interface for each, on each side of the APU.
Yes, that's a possibility too.
Posted on Reply
#43
hsew
DenverTechnically this is a regular GPU chip integrated into an MCM design, so if you consider this an iGPU, also consider that the mi300A is an APU that fulfills your nonsensical sarcastic dream.
Let’s completely ignore the clarification I made after that initial post and throw in yet another product in a completely different and specialized market segment… which is also operating in a power envelope an entire order of magnitude above laptop iGPUs! MCM or not is obviously irrelevant to your point, as the claim originally made in the article is speculation about an upcoming product as a whole. As it is, ahem, INTEGRATED INTO THE SOC AS A WHOLE, AS OPPOSED TO BEING A DISCRETE, STANDALONE GPU.

Christ…
Posted on Reply
Add your own comment
Apr 12th, 2025 15:26 EDT change timezone

Latest GPU Drivers

New Forum Posts

Popular Reviews

Controversial News Posts