AMD’s Big Navi Is Supposedly 40 to 50 Percent Faster than the RTX 2080 Ti

Tsing

The FPS Review
Staff member
Joined
May 6, 2019
Messages
11,245
Points
83
amd-radeon-logo-red-circular-1024x576.jpg
Image: AMD



There’s been a lot speculation as to how powerful AMD’s upcoming lineup of high-performance, RDNA 2-based graphics cards will be and whether red team has finally come up with a GPU design that’s competitive with NVIDIA’s greatest offerings. Judging by the rumors that we’ve seen so far regarding the RTX 30 Series, that seems rather unlikely, but YouTuber Moore’s Law Is Dead has shared a few claims that should help Radeon fanatics sleep better at night.



According to his sources, the performance of AMD’s Big Navi will be around 40 to 50 percent higher than NVIDIA’s GeForce RTX 2080 Ti! Assuming that those figures weren’t drawn out of a hat, that’s pretty exciting, especially when you consider the prospect of Big Navi being cheaper than the competition. Could we be looking at RTX 2080 Ti performance at a...

Continue reading...
 
So unless AMD is leapfrogging their 2080ti performance by around 75% with their high end card... we could see two sets of cards to choose from that are competitive with each-other. That's actually pretty cool sounding.
 
As much as I'd like this to be true
1: I've literally heard this every new launch for nearly 20 years so I'll believe it when I see it.

2: Even if the claims are true I don't know if I'd be willing to drop $800+ on a card with questionable, at best, driver performance. If I'm spending that much money I want as much stability and support as possible and AMD has never been able to provide that.
 
To be fair this isn't the same AMD as... current... well ****. They have great CPU's tho!! ;)
 
I don't know. Seems like both teams make these claims leading up to new releases. Occasionally they're spot on but I feel like they end up performing a bit less as more testing gets done. I'm wishing the best for AMD. It really would be nice to see both come out swinging, for a change, at the top tier level.
 
I have no doubt that the successor to the RTX 2080 Ti will be at least 35%-40% faster than its predecessor. I seriously doubt AMD has the ability to produce a Big Navi variant that will be 40-50% faster than an RTX 2080 Ti. We've seen no evidence that Navi is capable of that.
 
I was under the impression from the MLiD video that Big Navi was to be 2x (Little?) Navi's performance (and that's assuming they ditch energy savings for performance). I don't doubt it surpassing the 2080ti, but I don't see how that puts it near Nvidia's next gen.
 
I was under the impression from the MLiD video that Big Navi was to be 2x (Little?) Navi's performance (and that's assuming they ditch energy savings for performance). I don't doubt it surpassing the 2080ti, but I don't see how that puts it near Nvidia's next gen.

I have doubts too but neither is out.
 
I think it could happen if the die is large enough.
 
So, AMD has been claiming an "up to 50% improvement in perf per watt".

I'm not sure where this will be coming from considering it's basically the same architecture, and on the same process node, but lets take them at their word for a thought experiment here.

Typical desktop GPU's tend to max out at 250W TDP somewhere. If AMD is able to get 50% higher perf per watt, and they cap it at 250W, we should be seeing something that is ~60% faster than a 5700xt, which based on a quick googling of benchmarks would make it trade blows with a 2080ti.

Now, as we saw with Vega, AMD has been willing to stomp all over convention in the past and go with very high TDP designs, shipping them with expensive AIO coolers. If they are willing to go up to 350W again like they did with one of the liquid cooled Vega 64 (Fronteir edition or something?) we could be talking 125% faster than the 5700 XT, which would make it 40% faster than a 2080ti.

So, based on what they have said to date, unless they are hiding something, the absolute fastest we can expect is 40% faster than 2080ti.

That is only if they both somehow succeed in pulling a rabbit out of a hat and gaining 50% more performance per watt out of the same arch on the same process node (which seems unlikely, but I am going to reserve judgment until I see what they launch) AND go with the nuclear option of releasing a massive chip with a 350W TDP as a consumer GPU.

Remember, the version of the Vega that went to 350w in the past was:
1.) Very expensive at $1,499
2.) Targeted at professional users

So, I would love to see an amazing consumer big Navi come out, but to say I am a skeptic is an understatement....

...unless they have a very well kept secret we don't know about.
 
Has anyone said they haven't tweaked the architecture? They've already pushed out improved Zen2 for higher clocked. Maybe they made from improvements to Navi and are getting considerably better yields for much better clocks.

We just don't know.

But it's probably not in AMD's best interests to lie at this point in the game. Past aside, I think they're past that.
 
I think they could have pushed something faster on Navi 1, but my guess is that at the top end wouldn't have really competed with Turing
 
I don't think navi 2 is just a simple refresh.
Navi is a tiny chip also. If they do a 600mm 80cu or 96cu could be loads of performance. More than 40% 2080ti... Key word could.
 
I think they could have pushed something faster on Navi 1, but my guess is that at the top end wouldn't have really competed with Turing

First generation Navi has power/heat problems if scaled any higher than the chip used for the 5700 which is why I think they didn't bring out anything bigger with it. Instead of trying to release something to compete at higher levels which would have been problematic they left it as is and concentrated on the next generation. By doing this they show the promise of Navi without attaching a stigma of being a bad architecture.

If they've been able to solve Navi 1's heat and power problems and made it run more efficiently then second generation Navi could very well be a competitor up and down the line with increased performance. Numbers would indicate that a doubled Navi 5700XT chip would have been able to compete with the 2080TI with regards to performance if memory serves. If Navi 2 is capable of that level of scaling as well as other performance improvements it's possible Navi 2 can compete with 3xxx nVidia assuming the numbers we've seen about nVidia 3xxx are close to correct.

I'm not saying AMD has been able to pull all of this off but if they have there's no reason not to believe that AMD could compete up and down the lineup. Of course this assumes yields work out among a number of other factors. It's also assuming that nVidia hasn't had a stumble with the 3xxx series which would only make AMD more competitive.
 
It would be nice for them to be competitive to drive prices down, but I will wait to see if this actually happens.
 
So I've read its 2x 36cu for 72cu... Wonder if they be doing chiplet style or mono die. Io die and chiplet is entirely possible, though never mentioned or even suggested, ... Don't know if AMD can be this tight lipped. Now imagine multiples of 36, so could be 36, 72, 108, and 144? Nah couldn't be..
Otherwise i think 40% above 2080ti is possible and probable. But while I wish it was something so advanced as a chiplet gpu, I doubt it.
 
Become a Patron!
Back
Top