• Competitor rules

    Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.

AMD RDNA3 unveiling event

Actually you are fooling yourself if you believe they downclocked the card. Because that is not what I said nor implied to say. There are no AIBs showing off any cards as of yet. That's the sandbagging I'm talking about. Not about AMD limited their cards intentionally. Perhaps AMD may limit their reference cards, don't know. But I am sure they've designed the card to work the way they intended it to.

Therefore, I am more interested in the AIB variants like the Sapphire Toxic, Asus, etc.
ASUS already teased a 3x8 pins card. And will probably be faster than the reference but the reality is the 7900xtx will be judged by the day one review, even if the ASUS card that will come later is more powerful. It happened with the RDNA 2 too, even if by the end they were pretty much beating Nvidia on a lot of games.
 
the reality is the 7900xtx will be judged by the day one review, even if the ASUS card that will come later is more powerful.
No, it's not it. It will be judge based on what they see available to buy and at what price. Those AIBs will certainly charge more then the reference if it indeed performance better. Which is why I will keep a keen eye out on those benchmark results.
 
Last edited:
I've been seeing fanboys well intentioned raytracing enthusiast, cream themselves over the kepler Tweet about Ray triangle intersection. Funny enough a lot of them haven't realised that it doesn't actually show what they think it shows.

The conclusions you can draw from that chart are as follows

1. Nvidia design is less efficient with ray triangle intersection than AMDs.
2. AMD's design may scale better than Nvidia when increasing ray triangle intersection.
3. Let us assume that AMD design has hit the limit and Nvidia design is the only way forward. This is bad news for anyone who is a fan of RT.

And I will explain why that is right after this message from our sponsor RAID SHADOW LEGENDS!!!


1. Nvidia design is less efficient with ray triangle intersection than AMDs
Lets start from the top. What did certain people say about RDNA 3 RT ability.

THEY ARE A GENERATION BEHIND!!! LOL!!! THEY ARE ONLY AS FAST AS A 3090TI in RT!!!!

So AMD's new card is as fast as a 3090ti while only being able to process ~30% fewer ray triangle intersection per second.

Let that sink in. I'll wait.


2. AMD's design may scale better than Nvidia when increasing ray triangle intersection.
As someone on Twitter pointed out the 4090ti has 4x the ray triangle intersection operation per second than the 3090ti and is only twice as fast in actual games and 3D rendering.
What people didn't notice is that the 7900XTX has 16% more ray triangle intersection operation per second than the 6950XT, but has about double the performance from early indications.

You explain to me how that works.

3. Let us assume that AMD design has hit the limit and Nvidia design is the only way forward. This is very bad news for anyone who is a fan of RT.
Let us say that AMD design is a dead end and only Nvidia's design is the way to go.

From the 2080ti to the 3090ti, there is a 3x ray intersection increase for a doubling of performance(is this true?).
From the 3090ti to the 4090, there is a 4x ray intersection increase for a doubling of performance.
So for the 4090 to the 5090 are we looking at a 5x increase for a doubling of performance?
5090 to 6090, will that be a 6x increase for double the performance?
What about after that? How long can such a trend be maintained, especially with the slow down in node shrinkage?
That assumes that it is a linear increase, God help us if it is an exponential increase.

I think that tweet from Kepler was very informative. Just not for the reason some people thought :D
 
Last edited:
ASUS already teased a 3x8 pins card. And will probably be faster than the reference but the reality is the 7900xtx will be judged by the day one review, even if the ASUS card that will come later is more powerful. It happened with the RDNA 2 too, even if by the end they were pretty much beating Nvidia on a lot of games.

The AIB cards should be interesting, anyone know when reviews will be out? I don't recall amd mentioning it

According to Coreteks, who claims to have spoken with AIBs they said the reference 7900XTX can't really be overclocked - we don't know why, we don't t know if it's because the 355w power limit is not enough and if that is the case then the AIB 450w cards should have more headroom. But if the problem is because rdna3 has the same boost clock frequency limit as rdna2 then it's possible reference cards are already hitting the frequency limit
 
Last edited:
The AIB cards should be interesting, anyone know when reviews will be out? I don't recall amd mentioning it

According to Coreteks, who claims to have spoken with AIBs they said the reference 7900XTX can't really be overclocked - we don't know why, we don't t know if it's because the 355w power limit is not enough and if that is the case then the AIB 450w cards should have more headroom. But if the problem is because rdna3 has the same boost clock frequency limit as rdna2 then it's possible reference cards are already hitting the frequency limit
Already told you it is too early to say they can't be overclocked. They won't release 3x8 pins cards if they can't use that power in the card. Most likely the drivers right now are limited for whatever reason.( for example to prevent leaks ).
 
The AIB cards should be interesting, anyone know when reviews will be out? I don't recall amd mentioning it

According to Coreteks, who claims to have spoken with AIBs they said the reference 7900XTX can't really be overclocked - we don't know why, we don't t know if it's because the 355w power limit is not enough and if that is the case then the AIB 450w cards should have more headroom. But if the problem is because rdna3 has the same boost clock frequency limit as rdna2 then it's possible reference cards are already hitting the frequency limit
Coretek AIB source is primarily MSI. FYI
And from what I recall MSI isn't a 1st tier AIB for Radeon.
 
Last edited:
It certainly is dangerous as buyers place far too much emphasis on launch day drivers, but is it possible that AMD are actually going out of their way to treat their AIBs well and privately hinting at the contrast with Nvidia?

As long as AIBs are ready with samples on launch day, this mighty not be that dangerous.
 
It certainly is dangerous as buyers place far too much emphasis on launch day drivers, but is it possible that AMD are actually going out of their way to treat their AIBs well and privately hinting at the contrast with Nvidia?

As long as AIBs are ready with samples on launch day, this mighty not be that dangerous.
On RDNA 2 the AIBs were not allowed to release their cards 2 weeks after the reference launch. They were all selling reference design cards but their own designs were released after 2 weeks. I believe it is a mistake but this is how AMD works.
 
On RDNA 2 the AIBs were not allowed to release their cards 2 weeks after the reference launch. They were all selling reference design cards but their own designs were released after 2 weeks. I believe it is a mistake but this is how AMD works.
Are you sure it was 2 weeks? I thought it was 1 week before AIBs came out
 
Or one week. It doesn't really matter, all that matters is that the 7900 will be judged by most people by the reference performance on day one.
I agree, though if those AIB cards really do offer some sweet, sweet performance improvements (10+%) with the OC, I think it could change the perception of the cards, regardless of if they come out a week later.
 
Has anyone else noticed that "Can it Run Crysis" has evolved into "Can it run Cyberpunk 2077 in 4k 60hz with Ray Tracing Enabled"
yea and it could with a lesser DP port.

people are making a huge deal out of it but neither card is powerful enough to take advantage of a dp2.1 port anyway and I'm guessing 99% of users won't have a monitor that does uber high refresh either.


It's like adding 50gb of vram to the card instead of 24gb or whatever they went with, just because they can even though it will make 0 difference
 
Last edited:
yea and it could with a lesser DP port.

people are making a huge deal out of it but neither card is powerful enough to take advantage of a dp2.1 port anyway and I'm guessing 99% of users won't have a monitor that does uber high refresh either.


It's like adding 50gb of vram to the card instead of 24gb or whatever they went with.

But it's fun though it gets the Nvidia fanatics worked up
 
Back
Top Bottom