Friday, August 7th 2026

AMD RDNA 4m iGPU Support Arrives in Open-Source Mesa GPU Driver

AMD's mysterious RDNA 4m integrated graphics have reappeared after a few months of silence, as the GPU has officially been merged into the Mesa 26.3 open-source driver stack. Running under the GFX1171 GPU target, this RDNA 4m is neither a true RDNA 4 design nor a simple RDNA 3 GPU IP. It sits just above RDNA 3.5, with supposed capabilities to support INT8 data types and native FSR 4 technology. However, since AMD announced that older RDNA generations are now getting FSR 4 upscaling, the true purpose of RDNA 4m remains unclear.

As readers may recall, AMD plans to keep its RDNA 3.5 iGPU in use until 2029, meaning most consumers buying laptops in the coming years will experience the same integrated graphics capabilities as those found in today's Ryzen AI 300 and 400 series processors. This suggests that the RDNA 4m, despite its limitations, will be a welcome addition to integrated graphics. "Redstone" features such as ML-based upscaling and rendering technologies rely on the RDNA 4 IP to function effectively. With RDNA 4m support now merged into the Mesa open-source graphics driver, the RADV and RadeonSI drivers are being updated for RDNA 4m.
We can expect the first appearance of RDNA 4m in "Medusa Point," which will introduce a desktop-exclusive RDNA 4 with the new RDNA 4m variant. In contrast, "Medusa Halo" will utilize AMD's next-generation RDNA 5/UDNA GPU microarchitecture. Although initial comparisons between the two are lacking, some instruction set extensions, such as WMMA and SWMMAC instructions, indicate support in the new "GFX1170" GPU, which should be associated with the GFX11 generation, also known as RDNA 3. Currently, this is believed to be an upgraded RDNA 3 with many RDNA 4 modules, enabling FSR 4 support even on the less powerful "Medusa Point" APU.
Source: Phoronix
Add your own comment

32 Comments on AMD RDNA 4m iGPU Support Arrives in Open-Source Mesa GPU Driver

#1
Space Lynx
Astronaut
yes, old tech until 2029, which means this article shouldn't even exist tbh

AI has bought all the factory time for next two years, this is vaporware announcement
Posted on Reply
#2
ymdhis
Space Lynxyes, old tech until 2029, which means this article shouldn't even exist tbh

AI has bought all the factory time for next two years, this is vaporware announcement
Gorgon Point for desktop was also vaporware. It seems desktop APUs from AMD are dead until 2030 the earliest. That's assuming they'll even bother to keep their GPU IPs in development at all - ever since they made it big with Zen, they've bee marginalizing their GPUs.
Posted on Reply
#3
Space Lynx
Astronaut
ymdhisGorgon Point for desktop was also vaporware. It seems desktop APUs from AMD are dead until 2030 the earliest. That's assuming they'll even bother to keep their GPU IPs in development at all - ever since they made it big with Zen, they've bee marginalizing their GPUs.
yep even before AI they kept bragging about AMD gpu laptops, and like a total of one hit the market at best buy, and we just never saw anything after that ever again. AMD is a joke imo
Posted on Reply
#4
lambda
Space Lynxyep even before AI they kept bragging about AMD gpu laptops, and like a total of one hit the market at best buy, and we just never saw anything after that ever again. AMD is a joke imo
Their laptops rarely sell well and are usually found in cheaper lineups which in turn contributes negatively to their brand perception.
Posted on Reply
#5
Space Lynx
Astronaut
lambdaTheir laptops rarely sell well and are usually found in cheaper lineups which in turn contributes negatively to their brand perception.
i think you missed my overall point, but i mean yea i agree with that too. they did try to fix this image with that single laptop i referenced in my previous post, it was ASUS brand + had liquid metal on cpu and gpu from the factory, so cooling was decent on it, forget the gpu, but it wasn't that many years ago.

my point is though they didn't even try. one model is not enough.
Posted on Reply
#6
Xaser04
That would be the Strix G15 Advantage edition. Came with a Ryzen 5900HX (fastest they offered at the time) and a Radeon 6800M XT (later revised to the 6850M XT - basically a rebranded 6700XT).

Decent device with performance comparable to the laptop 3070 / 3080 (lower TGP) and an overall decent laptop.

AMD then followed this up with..... er.... um..... well there were a few Asus TUF, Zephyrus and HP Omen* models with the 6600/7600 and 6700/6800(S) models - all basically variants of the 6600/7600 desktop parts.

Rumour was there was meant to have been a 7900M XT (likely a binned 7900 GRE or 7800XT desktop die) but that seemingly never happened.
Posted on Reply
#7
LabRat 891
Xaser04Rumour was there was meant to have been a 7900M XT (likely a binned 7900 GRE or 7800XT desktop die) but that seemingly never happened.
I think it was a Tom's hardware article that mentioned 7900M existed in-quantity but OEM/ODMs had little-to-no-interest in implementing.
Notably, both the Desktop 7900GRE and Mobile 7900M use Navi 32-sized packaging while retaining Navi31's MCM structure (though, shader-cut and gimped to 256-bit).


It is my sincere and deeply-held belief that the lack of interest in 7900M, is what facilitated 7900 GRE's global launch.
IMO, 7900M-destined silicon, got turned into Navi 31 XL 7900GREs
Posted on Reply
#8
Mysteoa
As far as I know the biggest issue for iGPU is the RAM bandwidth. Spending the money and time to designed a new igpu for APUs that is going to be limited, seems a like just waist of company resource. I think AMD will wait for when DDR6 is out, to introduce a new iGPU arch if nothing else forces them.
Posted on Reply
#9
xBruce88x
I'm guessing rdna4 is gonna show up in some WX (radeon pro) series cards first at this rate
Posted on Reply
#10
lambda
Space Lynxi think you missed my overall point, but i mean yea i agree with that too. they did try to fix this image with that single laptop i referenced in my previous post, it was ASUS brand + had liquid metal on cpu and gpu from the factory, so cooling was decent on it, forget the gpu, but it wasn't that many years ago.

my point is though they didn't even try. one model is not enough.
I think I didn't phrase it properly. It's somewhat of a catch 22 situation with AMD laptops. They don't put in enough effort in first party led designs and even if they do, it doesn't sell well. So, AMD and whoever they collaborate with aren't consistent with execution.

There's a reason they had so many mobile 7600M units that found their way to the Steam Machine.

Lastly, I think AMD still considers themselves to be a hardware company first and foremost while Nvidia considers itself an ecosystem of sorts. The latter offers a more complete solution. They have made some changes though due to the AI boom and have started to put effort into ROCm.
Posted on Reply
#11
TheinsanegamerN
lambdaI think I didn't phrase it properly. It's somewhat of a catch 22 situation with AMD laptops. They don't put in enough effort in first party led designs and even if they do, it doesn't sell well. So, AMD and whoever they collaborate with aren't consistent with execution.

There's a reason they had so many mobile 7600M units that found their way to the Steam Machine.

Lastly, I think AMD still considers themselves to be a hardware company first and foremost while Nvidia considers itself an ecosystem of sorts. The latter offers a more complete solution. They have made some changes though due to the AI boom and have started to put effort into ROCm.
Ice long suggested AMD needed to partner with a ODM and produce their own Ultrabook to show other ODMs how it's done. Remember how bad thing and light laptops were before the Ultrabook?
Posted on Reply
#12
lambda
TheinsanegamerNIce long suggested AMD needed to partner with a ODM and produce their own Ultrabook to show other ODMs how it's done. Remember how bad thing and light laptops were before the Ultrabook?
I think AMD has tried a couple of times but it's been specific to certain vendors and hardware combinations that never took hold due to various factors. ThinkPad Z, Asus G14 etc. were some good designs.

These were discontinued after a generation or two.

While Nvidia is talking about N1 and N1X series, AMD's Strix Halo can only be found in a laptop or two.

They aren't consistent with their vision and execution.
Posted on Reply
#13
jesdals
LabRat 891I think it was a Tom's hardware article that mentioned 7900M existed in-quantity but OEM/ODMs had little-to-no-interest in implementing.
Notably, both the Desktop 7900GRE and Mobile 7900M use Navi 32-sized packaging while retaining Navi31's MCM structure (though, shader-cut and gimped to 256-bit).


It is my sincere and deeply-held belief that the lack of interest in 7900M, is what facilitated 7900 GRE's global launch.
IMO, 7900M-destined silicon, got turned into Navi 31 XL 7900GREs
Thats a interesting point
Posted on Reply
#14
dgianstefani
TPU Proofreader
MysteoaAs far as I know the biggest issue for iGPU is the RAM bandwidth. Spending the money and time to designed a new igpu for APUs that is going to be limited, seems a like just waist of company resource. I think AMD will wait for when DDR6 is out, to introduce a new iGPU arch if nothing else forces them.
Panther Lake does just fine.
Posted on Reply
#15
Tek-Check
lambdaI think AMD has tried a couple of times but it's been specific to certain vendors and hardware combinations that never took hold due to various factors. ThinkPad Z, Asus G14 etc. were some good designs.
OEMs have been in bed with Intel and Nvidia on laptop front for many years. It's almost an impenetrable fortress for AMD in several laptop segments, to the point that some OEMs were afraid to lose access to Nvidia mGPUs if they had deployed more ambitious AMD gear. We know this from backdoor interviews with reps. AMD gave up on some laptop segments to focus more other avenues, which is fine. Why waste time and silicon on something that has been entrenched? They don't need to be everywhere.
lambdaWhile Nvidia is talking about N1 and N1X series, AMD's Strix Halo can only be found in a laptop or two.
Memory price crisis has stopped any attempts of wider adoption of Strix Halo.
lambdaThey aren't consistent with their vision and execution.
They have actually increased laptop market share in recent years, despite obstacles with OEMs.
Posted on Reply
#16
Punkenjoy
Tek-CheckMemory price crisis has stopped any attempts of wider adoption of Strix Halo.
For gaming, i am in the opinion that it's useless for most use case on desktop (except maybe mini PC under the TV for small form factor). It's probably a much better design option for laptop than a dedicated GPU that require more complex cooling.

But since it have to make compromise on memory (using lpddr6 instead of GDDR7 by example), the bandwidth will still be less than a comparable GPU. The Radeon 7700 is a 40 compute unit (RDNA3) like the 8060s in the top strix halo (but on RDNA 3.5). the 7700 have about 640 GB/s Bandwidth where the 8060s is capped at 256 GB/s. The difference is quite significant and explain why the dedicated GPU is much more powerful dans the large IGPU of similar size.

The main advantages of Strix Halo is how much memory it can support. For gaming, that is pretty much useless as of now (vs comparable GPU with 16GB, it is indeed way better than a 4 GB GPU) but for running local llm that run in VRAM/RAM, it do wonder.

This is why strix halo sell quite well, but people that are buying it aren't playing games. They run local llm to code with privacy and without explosive token cost.

A lot of people see the writing on the wall that we are entering in a enshitification phase from the large LLM where they try to jack up the price to start making money. People just try to become autonomous and limit cost.

For hardware, this mean the pressure on hardware will remain high for quite some time. I think that it's in the interest of the large ai shop that Ram stay as expensive as it is. Local LLM aren't as good as the largest frontier model like Anthropic Fable, but they are very usable and getting better and better every year.

The scenario where an individual can purchase a 256GB large iGPU like one of the future AMD halo product for a reasonable price is not something that the large ai company want. People will be able to get a lot of stuff done with free open weight model that are very good. Maybe not as good as the largest model, but good enough.

This can't last forever.
Posted on Reply
#17
Tomorrow
People complaining that AMD iGPU's are stuck at RDNA 3.5 and dont support FSR4.
People complaining that iGPU using RDNA4 is "old tech".

Make up your mind. We're talking about iGPU's here not mGPU's.
Posted on Reply
#18
THANATOS
lambdaTheir laptops rarely sell well and are usually found in cheaper lineups which in turn contributes negatively to their brand perception.
And this is based on what data? I can find AMD in both cheap and expensive laptops and I am not sure from where you have the info they sell poorly, but that could be true.

As I see It, AMD's fault is their stupid rebrandings along with naming and that they didn't update their APUs for some time. CPU performance is Ok, they are using their latest cores, what is worse is that IGP was not updated to RDNA4, which is much better than RDNA3/3.5. Then battery life is not bad but Intel's latest is better.

For AMD the good news is that Panther Lake with B390 IPU is expensive and the rest is using only the much weaker 4EU variant.

What I want to know is what iGP architecture will Medusa Point use, Medusa Halo will use RDNA5.
Posted on Reply
#19
GenericUsername2001
dgianstefaniPanther Lake does just fine.
Yeah, PantherLake shows you can squeeze a fair bit more performance out of a 128 bit memory bus, if you are willing to toss more cache at it. The Arc B390 has 16 MB of L2 cache on it's tile, while the Radeon 890m on Strix point only has 2 MB. What's really obnoxious is that AMD originally planned for a much larger iGPU cache on Strix Point, but decided that appeasing Microsoft and the large laptop OEMs wanting Windows discounts with a Copilot compliant NPU was the better use of die space. Putting both on the die would have been really pricey (see how much Pantherlake laptops with the good iGPU cost).

It would be interesting to see if AMD has considered using its 3D cache tech for future APUs, making the main igpu chip smaller and slapping a big cache chip underneath seems like a reasonable path to take.
Posted on Reply
#20
Tek-Check
PunkenjoyBut since it have to make compromise on memory (using lpddr6 instead of GDDR7 by example), the bandwidth will still be less than a comparable GPU. The Radeon 7700 is a 40 compute unit (RDNA3) like the 8060s in the top strix halo (but on RDNA 3.5). the 7700 have about 640 GB/s Bandwidth where the 8060s is capped at 256 GB/s. The difference is quite significant and explain why the dedicated GPU is much more powerful dans the large IGPU of similar size.
7700 has 624 GB/s of bandwidth. 7700XT has 432 GB/s and it's still faster. Bandwidth is just one metric that matters. Besides, you are comparing desktop GPU to integrated GPU. Those are different classes of products, with different power envelops and market usage. You can't cram 7700 into a laptop. I would not make such crude comparisons.

AMD is taking a different route here. Even Nvidia is not able to ignore it, as they too are about to deploy N1X with integrated GPU. Strix Halo has been a pilot, experimental product exploring markets it could serve. More of gaming adoption is out of question during RAM prices crisis, but this can change easily in future, if or when RAM prices come down. Last year, before the crisis, Strix Halo mini-PC with 96GB was ~$1,600

For Medusa Halo, 384-bus with LPDDR6 is rumoured, so we will see how this works out. If they manage to utilise LP6 chips at 12.8 or 14.4 Gbps, that already going to be miles better. Bandwidth of mega iGPU is smaller, of course, but this is well-compensated by being more energy efficient and not requiring gigantic footprint in laptop case. It's been only one generation, so next iterations will only get better.
lambdaTheir laptops rarely sell well and are usually found in cheaper lineups which in turn contributes negatively to their brand perception.
Not really. Their x86 laptop share has grown from 13% in the beginning of 2019 to ~29% in 2026. Check out Mercury Research data. "Negative brand perception" is directly contradicted by those numbers. Essentially, the idea of "negative brand perception" is BS, unless you could convince us that increasing number of buyers of AMD laptops are idiots who buy and contribute to market share while creating "negative brand perception". Good luck with that one.
THANATOSWhat I want to know is what iGP architecture will Medusa Point use, Medusa Halo will use RDNA5.
Medusa Point will use GFX 1171/1172, which is RDNA4m, a hybrid of RDNA3.5 with some instructions from RDNA4.
Posted on Reply
#21
TheinsanegamerN
Tek-CheckOEMs have been in bed with Intel and Nvidia on laptop front for many years. It's almost an impenetrable fortress for AMD in several laptop segments, to the point that some OEMs were afraid to lose access to Nvidia mGPUs if they had deployed more ambitious AMD gear. We know this from backdoor interviews with reps.
Which is why they needed to team up with a ODM to show what could be done, which was the point of the entire argument.

There are plenty of asian ODMs that were not impenetrable that could have made their Radeon Books.
Tek-CheckAMD gave up on some laptop segments to focus more other avenues, which is fine. Why waste time and silicon on something that has been entrenched? They don't need to be everywhere.
Well, they ARE wasting time and silicon on that market, because that market is HUGE, so why not put a little effort in?

But keep in mind, this is AMD, the same AMD that tried to force ODMs to write their own drivers for Ryzen APUs then pikachu faced when nobody used their chips.
TomorrowPeople complaining that AMD iGPU's are stuck at RDNA 3.5 and dont support FSR4.
This is true. AMD did stick with rDNA 3.5 in most of their products and refuses to support it like their competition
TomorrowPeople complaining that iGPU using RDNA4 is "old tech".
This is ALSO true. rDNA5 is coming and will be AMD's main focus, and with 3.5 we've already seen how AMD treats older oddball architectures. By 2029, rDNA4 will indeed be very old.
TomorrowMake up your mind.
More then 1 thing can be true at a time.
TomorrowWe're talking about iGPU's here not mGPU's.
There is nothing stopping an iGPU from using the newest uArch. See also: Intel.
Posted on Reply
#22
Tomorrow
By 2029 RDNA4 will be four years old.
What is four years old today? Oh wait - Ada Lovelace, that launched back in 2022.

Is someone calling 40 series very old today? I doubt it.
And i doubt anyone will call RDNA4 very old in 2029 when only RDNA5 is newer and RDNA6 is yet to launch.

Four years was old back when each new generation brought significant changes and performance uplifts. These days people can easily run 5+ year old hardware and it doesn't feel old by any means because the gains from newer generations have slowed down so much.
Posted on Reply
#23
Tek-Check
TheinsanegamerNWhich is why they needed to team up with a ODM to show what could be done, which was the point of the entire argument.
There are plenty of asian ODMs that were not impenetrable that could have made their Radeon Books.
They did team up with more companies. As a result, AMD laptop market share increased from ~13% to ~29% in 7 seven years only, which is a serious change in an entrenched segment where OEMs/ODMs are scared to fart because what would Nvidia say...
TheinsanegamerNWell, they ARE wasting time and silicon on that market, because that market is HUGE, so why not put a little effort in?
This market segment is much, much smaller than enterprise and data centre at the moment. Their bread and butter are Zen, especially EPYC, and data centre graphics. Everything else comes as a bonus. You may or may not agree with their business decisions, but it is what it is. Besides, they cancelled discrete mGPUs a few years ago already and put a lot of effort to design a mega-iGPU. They will continue to pursue it, as Strix Halo is versatile enough and can be used from client systems to AI systems to robotics. They are already developing Medusa Halo. Now, RAM price crisis obviously complicates several segments, as we will see how this pans out in a few years.
TheinsanegamerNThis is true. AMD did stick with rDNA 3.5 in most of their products and refuses to support it like their competition
Not really. This has been addressed. FSR4 is coming out for all relevant generations.
Also, AMD is the only company that broke the monopoly of HDMI Forum and created support for HDMI 2.1 48 Gbps and associated features for open source driver on Linux. Now, Intel is trying to catch up and they are doing the same, while Nvidia is dragging their feet.
TheinsanegamerNBy 2029, rDNA4 will indeed be very old.
Irrelevant. For example, majority of users use processors from 5-6 years ago, and they still work. If you are in a tiny group that upgrades regularly, you will be able to do this anyway.
TheinsanegamerNThere is nothing stopping an iGPU from using the newest uArch. See also: Intel.
As you said, more than one thing can be true at a time.
Intel has different cadence and different business priorities. They did a good job with Xe3 iGPU, but unfortunately, those top iGPU laptops and handhelds are very expensive due to memory price crisis. However, their discrete GPU business is done, plus Nvidia will enter into some iGPU deals. So, it's give and take. None of the three vendors is competitive or present in all possible segments, and that's fine.
Posted on Reply
#24
cucol
Typo on int8? Rdna 4m should add fp8 ai accelerated instructions to support native fsr 4. Afaik 3.5 already supports int8
Posted on Reply
#25
Punkenjoy
cucolTypo on int8? Rdna 4m should add fp8 ai accelerated instructions to support native fsr 4. Afaik 3.5 already supports int8
The confusion might come from the fact AMD is preparing a lighter model to run on APU for FSR 4.1+ that will probably run on INT8. Halo parts like medusa halo are rumored to be on RDNA 5 directly and will just run the full int8 model. The rdna4m uArch is just for smaller APU.

But indeed, FP8 was added to rdna 4m
Posted on Reply
Add your own comment
Nov 17th, 2026 13:53 CST change timezone

New Forum Posts

Popular Reviews

TPU on YouTube

Controversial News Posts