It's been four years since AMD launched RDNA, the successor to the venerable GCN graphics architecture. We take a look through the tech and numbers to see...
The problem is that where they are falling isn’t a massive issue today but will be in 5-10 years.
This situation with AMD tech (FSR) being just basically the nvidia equivalent but worse and their refusal to incorporate any hardware into the equation to keep up is going to cause a massive vacuum in the value proposition. (It already is to a certain extent)
This is a good point. Some FSR acceleration on either AMD cards or processors, while retaining it’s ability to be used on different hardware could help bridge the gap, if it’s possible.
AMD has been playing catch up for very long. They finally got an edge on intel gaming with the X3D chip lineup. I wonder if the same tech would benefit their graphics cards.
Some FSR acceleration on either AMD cards or processors, while retaining it’s ability to be used on different hardware could help bridge the gap, if it’s possible.
This is pretty much how intel’s XeSS works, it will look best on an ARC gpu but will work with other brands albeit with lower quality
Honestly I think it should become a lot better in 5 to 10 years, since a lot of their problems seem to come from being understaffed. Keep in mind, they were a fairly small company on the verge of bankruptcy just a few years ago, and you can only onboard so many people each year without causing inefficiency.
So their competence in software as well as hardware should be improving, not getting worse.
Only if they do a complete 180 in philosophy as a course correction, which I just don’t see being the case; They’d have to admit that nvidia (and intel) are correct and their way was a mistake.
AMD GPU division is usually more than willing to double down on their mistakes when it comes to vision/philosophy over admitting that they made a mistake.
The problem is that where they are falling isn’t a massive issue today but will be in 5-10 years.
This situation with AMD tech (FSR) being just basically the nvidia equivalent but worse and their refusal to incorporate any hardware into the equation to keep up is going to cause a massive vacuum in the value proposition. (It already is to a certain extent)
This is a good point. Some FSR acceleration on either AMD cards or processors, while retaining it’s ability to be used on different hardware could help bridge the gap, if it’s possible.
AMD has been playing catch up for very long. They finally got an edge on intel gaming with the X3D chip lineup. I wonder if the same tech would benefit their graphics cards.
This is pretty much how intel’s XeSS works, it will look best on an ARC gpu but will work with other brands albeit with lower quality
Honestly I think it should become a lot better in 5 to 10 years, since a lot of their problems seem to come from being understaffed. Keep in mind, they were a fairly small company on the verge of bankruptcy just a few years ago, and you can only onboard so many people each year without causing inefficiency.
So their competence in software as well as hardware should be improving, not getting worse.
Only if they do a complete 180 in philosophy as a course correction, which I just don’t see being the case; They’d have to admit that nvidia (and intel) are correct and their way was a mistake.
AMD GPU division is usually more than willing to double down on their mistakes when it comes to vision/philosophy over admitting that they made a mistake.