Friday, October 9th 2020

AMD Big Navi Performance Claims Compared to TPU's Own Benchmark Numbers of Comparable GPUs

AMD in its October 8 online launch event for the Ryzen 5000 "Zen 3" processors, provided a teaser of the company's next flagship graphics card slotted in the Radeon RX 6000 series. This particular SKU has been referred to by company CEO Lisa Su as "Big Navi," meaning it could be the top part from AMD's upcoming client GPU lineup. As part of the teaser, Su held up the reference design card, and provided three performance numbers of the card as tested on a machine powered by a Ryzen 9 5900X "Zen 3" processor. We compared these performance numbers, obtained at 4K UHD, with our own testing data for the games, to see how the card compares to other current-gen cards in its class. Our testing data for one of the games is from the latest RTX 30-series reviews, find details of our test bed here. We obviously have a different CPU since the 5900X is unreleased, but use the highest presets in our testing.

With "Borderlands 3" at 4K, with "badass" performance preset and DirectX 12 renderer, AMD claims a frame-rate of 61 FPS. We tested the game with its DirectX 12 renderer in our dedicated performance review (test bed details here). AMD's claimed performance ends up 45.9 percent higher than that of the GeForce RTX 2080 Ti as tested by us, which yields 41.8 FPS on our test bed. The RTX 3080 ends up 15.24 percent faster than Big Navi, with 70.3 FPS. It's important to note here that AMD may be using a different/lighter test scene than us, since we don't use internal benchmark tools of games, and design our own test scenes. It's also important to note that we tested Borderlands 3 with DirectX 12 only in the game's launch-day review, and use the DirectX 11 renderer in our regular VGA reviews.
With Gears 5, AMD claims performance of 73 FPS at 4K, with its DirectX 12 renderer, with the "Ultra" preset. This number ends up 16.24 percent faster than that of the RTX 2080 Ti, which scores 62.8 FPS on our test bed. The RTX 3080 is 15.61 percent faster than the AMD card, at 84.4 FPS.

Call of Duty: Modern Warfare was never added to our VGA review test selection, but we tested the game separately at launch (find its test bed information here). In this testing, we found the RTX 2080 Ti to score 77.9 FPS at Ultra Settings, with RTX-off. In comparison, AMD claims Big Navi scores 88 FPS, making it 12.96 percent faster.

We know this is a very coarse and unscientific way to compare AMD's numbers to ours, and AMD has probably cherry-picked games that are most optimized to its GPUs, but it lends plausibility to a theory that Big Navi may end up comparable to the RTX 2080 Ti, and trade blows with the upcoming RTX 3070, which NVIDIA claims outperforms the RTX 2080 Ti. The RX 6000 "Big Navi" ends up with a geometric mean of 21% higher frame-rates than the RTX 2080 Ti in these three tests, which would imply almost double the performance of the RX 5700 XT. Big Navi is rumored to feature double the CUs as the the RX 5700 XT, so the claims somewhat line up.
Add your own comment

262 Comments on AMD Big Navi Performance Claims Compared to TPU's Own Benchmark Numbers of Comparable GPUs

#51
nguyen
bug
One thing people gloss over is AMD has just announced "the fastest gaming CPUs". I bet these results are obtained running said CPUs.
Yeah pretty funny that AMD used a 2080 Ti for benchmarking their CPU against 10900K, but somehow can't bench the 2080 Ti against their RX 6000. Pretty much a dead giveaway that AMD aren't so confident about their RX 6000 GPU.
AMD is now trying to crank as much clocks outta these chip so that they can be justifiable purchase.
Posted on Reply
#52
EarthDog
If we average the average of the average, the numbers are real. :p
Posted on Reply
#53
bug
Viilutaja
It is weird that only TPU gets +10FPS boost on 4K in Borderlands, but Nvidias own official slide on their webpage shows 3080FE card scoring exactly 61 fps in that game... hmmmm
Also Youtuber "joker" tested his 3080FE card and got 57.7fps at 4K, which is in line what Nvidia officialy got. And now TPU gets 70fps :D Suspicious.
Yup, very weird. It's almost as people are testing using different systems or something.
nguyen
Yeah pretty funny that AMD used a 2080 Ti for benchmarking their CPU against 10900K, but somehow can't bench the 2080 Ti against their RX 6000. Pretty much a dead giveaway that AMD aren't so confident about their RX 6000 GPU.
Well, of course they can't bench against RX 6000, they're also under NDA.
Posted on Reply
#54
nguyen
bug
Well, of course they can't bench against RX 6000, they're also under NDA.
Huh, they are the one who give out NDA :D, not under NDA.
Posted on Reply
#55
Viilutaja
They (AMD) are the one who knocks!
Posted on Reply
#56
pal
I belive there is only 1 BIg Navi.
Posted on Reply
#57
Vya Domus
nguyen
Yeah pretty funny that AMD used a 2080 Ti for benchmarking their CPU against 10900K, but somehow can't bench the 2080 Ti against their RX 6000. Pretty much a dead giveaway that AMD aren't so confident about their RX 6000 GPU.
Pretty funny that they didn't want to benchmark GPUs that aren't even announced yet. Yeah, funny and strange ...
nguyen
AMD is now trying to crank as much clocks outta these chip so that they can be justifiable purchase.
You mean like Ampere which basically has zero frequency headroom left ? Anyway, those aspects are decided early in the development process as they are closely linked with the manufacturing process, so they aren't cranking up anything.
Posted on Reply
#58
kapone32
pal
I belive there is only 1 BIg Navi.
That is counter intuitive.
Posted on Reply
#59
SIGSEGV
Simple, give me good price/perf ratio then I will gladly switch to RED for my 2nd workstation rig. (2x 5700XT performance with the same MSRP of 5700XT or 600$ territory, then I will take 2 of your 6000 series or even your XTX version)
Otherwise, I will stay with green. :laugh:
Posted on Reply
#60
Mark Little
nguyen
Yeah pretty funny that AMD used a 2080 Ti for benchmarking their CPU against 10900K, but somehow can't bench the 2080 Ti against their RX 6000. Pretty much a dead giveaway that AMD aren't so confident about their RX 6000 GPU.
AMD is now trying to crank as much clocks outta these chip so that they can be justifiable purchase.
The 2080Ti is probably the fastest commercially available GPU that AMD could get it's hands on (3080/3090 are too hard to get even for AMD). As to why they would use commercially available hardware, so that all us readers, reviewers and tech news analysts can make sense of the results based on our own experience with the hardware. According to you, it would be okay for AMD to take a future 1 year down the road GPU that is working in their labs and release public numbers with it. That makes no sense. With the 2080Ti we can all verify AMD's claims about how the CPU competition performs.
Posted on Reply
#61
bug
nguyen
Huh, they are the one who give out NDA :D, not under NDA.
Hm, somebody never worked on unreleased products...
Posted on Reply
#62
john_
Vya Domus
I didn't put any words in your moth, you gotta chill. You said this is "probably the top model" because she mentioned Big Navi and I pointed out that "Big Navi" was never thought of as a specific model but rather simply the silicon. You basically phrased in a way that implies Big Navi could only mean the top end card and I don't think so, there are going to be at least two cards on that "Big Navi" die.
Oh come on now. Give me a break. Yes you did. Because you want to create an argument based on which, you will come out and say that this is NOT the top model. Well, you can't say that, I can't say that, most people can't say which model it is.

But we can speculate.

And when people talk about "Big Navi" they talk about the TOP model. Not the silicon. You can have 15 models based on the biggest core, but that "Big Navi" nickname was always, in discussions between people or tech cites, the TOP MODEL. NOT one of the top models. But THE TOP MODEL. You don't start conversations about the second model of an unknown line of cards.

And let me ask you a question. Almost everyone are asking the same question. Will Big Navi be faster than 2080 Ti? And how much? Can it be close, equal or faster than 3080?
Tell me. Does those questions make any sense if they are about the SECOND in line top model?

You ignore logic and in my case, make me look like someone stupid, just so you can build an argument about something that you also don't know.
If you have any reason to believe "Big Navi" is a specific card/model go ahead and explain that.
See what you are doing here? Again you put words in my mouth by distorting what I mean. because you should know and you probably know, that saying that "Big Navi" is a reference for the TOP model, does not have ANYTHING to do with how many models will be based on the biggest chip.
Posted on Reply
#63
Blueberries
Maybe we'll see a Crossfired Pro Duo 6000 series competing with green team in Port Royal

... or AMD did some engineering voodoo to offer a 4k 60 FPS card cheaper than NVIDIA
Posted on Reply
#64
TheLostSwede
nguyen
Huh, they are the one who give out NDA :D, not under NDA.
Note the part highlighted in red...
Until a product is announced or launched, it tends to be confidential.

Posted on Reply
#65
nguyen
TheLostSwede
Note the part highlighted in red...
Until a product is announced or launched, it tends to be confidential.
Then why bother show anything at all. These FPS figures are useless by themselves.

"Hey let just bench the lightest scenes in these games, get some useless FPS numbers to hype our product." - AMD CEO to PR guys

Sure that worked out well for Polaris and Vega, just some bullshit numbers here and there until the actual release and then boom yeah our GPUs are so bad, we are selling them for almost nothing.
Posted on Reply
#66
B-Real
Gears 5 results from different sources (all using DX12): Guru 76 fps



Techspot: 72 fps




Eurogamer: 80 fps

Average of the 3 is 76 fps. AMD shows 73 fps.
cueman
amd use its new ryzen 5900 cpu,its help alot,also it help rtx 3080 nd evn more rtx 3090.

well, let see, but real world is that kind...
What the heck are you talking about? In 4K, there is no difference between CPUs as there is a GPU bottleneck.
I would bet there is not much manipulation in the results. Why? Because they showed the CPU gaming results where there was one game in which Intel was faster.
bug
One thing people gloss over is AMD has just announced "the fastest gaming CPUs". I bet these results are obtained running said CPUs.
Huge difference, isn't it? :D :D
Posted on Reply
#67
efikkan
PerfectWave
"AMD has probably cherry-picked games that are most optimized to its GPUs "
i dont think the engine is optimized for AMD instead it is for Nvidia...
It's neither.
You would need to have special API features to optimize for one of them.
Sponsored titles might have exclusive graphical features, but not vendor-specific performance optimizations.
docnorth
It is rumored that Big Navi will at some point get a memory bandwidth upgrade, probably GDDR6X. Some reasons for the launch with GDDR6 might be:
1)Limited availability of GDDR6X
2)Cost
3)No time or resources to develop the memory controler. GDDR6X uses PAM4, it's a four state coding format instead of binary coding and needs a different memory controller.
The time required to implement it is measured in years. Regardless of the choice of memory controller, this was decided a long time ago.
Posted on Reply
#68
medi01
jesdals
I could live with that if the price is belowe the 3080
3080 is a virtual product, so don't hold your breath.

I love how performance between 2080Ti and 3080 is just "trades blows with 3070".
Posted on Reply
#69
neatfeatguy
Viilutaja
It is weird that only TPU gets +10FPS boost on 4K in Borderlands, but Nvidias own official slide on their webpage shows 3080FE card scoring exactly 61 fps in that game... hmmmm
Also Youtuber "joker" tested his 3080FE card and got 57.7fps at 4K, which is in line what Nvidia officialy got. And now TPU gets 70fps :D Suspicious.

I made couple of modified slides from available benchmarks with RTX3080 and where that Navi 6000 series stacks up againts.
That card what AMD showed yesterday is dead on 1:1 level with RTX3080 FE model!

Everybody saying that RTX3080 will gain performance also with Ryzen 5000 series cpu.. no it wont. Because @4k where you are still very GPU limited.
But if I am in giving mood- I would say that at best case scenario RTX3080 may benefit max 1-2fps with AMD's new best of the best CPU: 5950X.
TPU has done a benchmark/performance test on Borderlands 3 when it came out - pre RTX 3080. They tested the game in DX12 with available cards at the time and 2080Ti was the top tier card then.

When the 3080 launched, Borderlands 3 was benched with it, but only in DX11. It says so above the charts on the 3080 review for the Borderlands 3 game, just go here and read for yourself or click the spoiler button below.

Borderlands 3 is brought to life with Unreal Engine 4, which takes advantage of DirectX 12 and Direct X 11 with some AMD-specific features, such as FidelityFX. In our testing, we used DirectX 11 because the DirectX 12 renderer has extremely long loading times and some instability. We will switch to the new renderer once these issues are ironed out.

AMD showed that their "Big Navi" card was running 61FPS in DX12 for Borderlands 3.
TPU has not ran the 3080 in DX12 for Borderlands 3. They only ran DX11 and that is the benchmark that shows 70.3 FPS.

I don't know where your confusion is other than you probably overlooked the fact that TPU's RTX 3080 benchmark for Borderlands 3 is only for DX11 and maybe you thought it was for DX12.
Posted on Reply
#70
d0x360
I would imagine AMD wouldn't give out the numbers for their top end card. They want to wow people in Nov and while coming close to the 3080 is awesome I have a feeling they were talking about a card that's 1 model down from the current high end one and that doesn't mean they couldn't one up it again later like nVidia does with super or ti's.
Posted on Reply
#71
nguyen
B-Real
Gears 5 results from different sources (all using DX12): Guru 76 fps
Techspot: 72 fps
Eurogamer: 80 fps
Average of the 3 is 76 fps. AMD shows 73 fps.
What the heck are you talking about? In 4K, there is no difference between CPUs as there is a GPU bottleneck.
I would bet there is not much manipulation in the results. Why? Because they showed the CPU gaming results where there was one game in which Intel was faster.
Huge difference, isn't it? :D :D
You are just wasting time, I can just look at the ground in those games to get 200FPS at 4K.

There are too many variables involved that you can't compare results from one review site to the other. Even results from the same review site can't be used if there are changes to the testing systems (new CPU, RAM, Motherboard, Drivers, etc...).

Those FPS figures are useless without any base for comparison, which AMD are witholding.
Posted on Reply
#72
medi01
fynxer
Lisa clearly said Big Navi optimization was done with Ryzen 5000 series SO because Ryzen 5000 is faster it will yield more performance in games for the 3080 too so you cannot make a direct comparison like that.
Which one of the tested games is CPU bottlenecked at 4k pretty please for CPU to even matter?
Of course AMD tested with own CPU as they now claim gaming CPU top spot.
Posted on Reply
#73
TheLostSwede
nguyen
Then why bother show anything at all. These FPS figures are useless by themselves.

"Hey let just bench the lightest scenes in these games, get some useless FPS numbers to hype our product." - AMD CEO to PR guys

Sure that worked out well for Polaris and Vega, just some bullshit numbers here and there until the actual release and then boom yeah our GPUs are so bad, we are selling them for almost nothing.
Are you saying other companies have done it differently in the past?
This isn't something new as far as I'm concerned.
It's all about the hype train...
Posted on Reply
#74
pcminirace
[QUOTE = "jesdals, publicación: 4365578, miembro: 127487"]
Podría vivir con eso si el precio es inferior al 3080
[/CITAR]oh yes

But how much does it cost? Will it happen as with the ryzen 5000?

But how much does it cost? Will it happen as with the ryzen 5000?
Posted on Reply
#75
Darmok N Jalad
The way I took Lisa’s comment in the live stream was that it was nicknamed “Big Navi” not internally, but affectionately, because that’s what the internet at large was calling it with all the speculating. It’s a nuanced distinction, but I think what they demoed was the best they have. They did the same with the 5700XT. The only ace they may have left is clock speeds, and that is what they probably are tweaking right now since NVIDIA has already played their hand, well, at least initially anyway.
Posted on Reply
Add your own comment