Thursday, May 14th 2026
AMD FSR Upscaling 4.1 Officially Arrives to Radeon RX 7000/6000 GPUs
AMD has responded to what gamers have been most vocal about: bringing its FSR 4.1 upscaling technology to older RDNA 3 and RDNA 2 GPUs. Today, we learn that this dream is becoming a reality, as AMD is officially introducing its FSR Upscaling 4.1 technology to millions of Radeon RX 7000 Series graphics cards worldwide. Arriving this July, millions of RDNA 3 gamers will enjoy official support for FSR Upscaling 4.1 in over 300 supported games. This means that, just like the latest RDNA 4-based Radeon RX 9000 Series, RDNA 3 gamers will also benefit from the upscaling algorithms based on various machine learning techniques without needing to upgrade to the latest Radeon RX 9000 GPUs if their current GPU performs adequately.
Interestingly, the FSR Upscaling 4.1 will use the same underlying model on RDNA 3 as it does on RDNA 4. However, differences in hardware create some background variations, as RDNA 4 has FP8 processing units and INT8, whereas RDNA 3 only has INT8. AMD explains that the company has developed FSR Upscaling 4.1 with the FP8 format in mind, while the latest ML algorithm has been optimized and ported for the INT8 data format to work with RDNA 3. This difference in hardware support delayed AMD's port of FSR technologies to RDNA GPU IP below version four, but it is now finally making an appearance.
Finally, FSR Upscaling 4.1 is also coming to older RDNA 2 GPUs, but that port will have to wait until early 2027. This indicates that AMD is doing additional optimization for RDNA 2 cards, as it is challenging to port this upscaling algorithm to hardware that isn't optimal for the latest techniques. However, it is promising that it is possible, and RDNA 2 gamers will just have to wait a bit longer.
Source:
Jack Huynh on X
Interestingly, the FSR Upscaling 4.1 will use the same underlying model on RDNA 3 as it does on RDNA 4. However, differences in hardware create some background variations, as RDNA 4 has FP8 processing units and INT8, whereas RDNA 3 only has INT8. AMD explains that the company has developed FSR Upscaling 4.1 with the FP8 format in mind, while the latest ML algorithm has been optimized and ported for the INT8 data format to work with RDNA 3. This difference in hardware support delayed AMD's port of FSR technologies to RDNA GPU IP below version four, but it is now finally making an appearance.
252 Comments on AMD FSR Upscaling 4.1 Officially Arrives to Radeon RX 7000/6000 GPUs
Their muted response to providing highly requested features like this in a reasonable time frame sold more GeForce cards than Jensen ever could by now.
I've messed with the leaked FSR4.0 INT8 on my RDNA2 GPUs, and while the performance impact is greater than FSR3 or XeSS, it looks way better than both of those.
I've been pretty happy with how much better FSR4 is over 3 on my 9070 XT (especially with Optiscaler to replace DLSS with it).
Even a "we're looking into it and this is why it's taking a while" a year ago would have calmed the storm considerably.
Now that tons of people have sworn off AMD,n possibly picked up a 5xxx series instead of a 9xxx series, literally had April Fools articles poking fun at the situation... They make this announcement.
Incredible.
Also, this only costs them money and doesn't generate money. So low priority. FoLlOw tHe mOnEy!
Scarlet Cortex next, let's gooo!!!I would have to disagree!
It creates fanbase loyalty, people like to be treated nicely, if they are chances are they will come back to you for future products, if you treat them like crap and lock them out of features their hardware supports and also cut driver support earlier than the competition chances are they will look elsewhere for what they want!
"As a lifelong gamer I spend a lot of time thinking about..." no, you don't.We've known it's possible before it even released for RX 9000 GPUs. AMD took every step, technical and legal, to block it until now.
As for costs, all the bad PR of this and a lot of other things with Radeon in the last time costs them more money in the long run, becuse it costs them losing more revenue (sales) and users in the long time.
I wonder if this is somehow AI related, like AMD checking where it was all heading and like Nvidia they are probably holding off making new consumer cards in favor of datacenter hardware.
Therefor they will keep selling 6000/7000 and 9000 longer then planned, with that in mind it makes more sense to now bring this software to older (now longer relevant) hardware.
GCN products remain on 23.19 which is very old, and consolidated at this point. Very minor bug fixes only every 6 months, unless security issues are found.
It's Ryzen 3000 and 5000 on B350/X370 all over again. What I gotta wonder is in AMD's management, are their engineers solving these "problems" (clearly yes) but management is simply too incompetent to let them cook because they're paralyzed by.... quarterly revenue projections? board partner complaints? WTFFFF is it???
As usual complaining customers and tech media have seemingly straightened AMD's ship yet again, should we get a pool together and bet what AMD's next PR faceplant will be?
Whatever.
My 6800 XT and 6600 XT will emerge from their cocoons in July to see how this all plays out.