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

#26
Betty (Kung Pow)
Did you do any percentage reduction as the AMD numbers were on the 5900x? Which might be some % up from the TPU test bench?
Posted on Reply
#27
r.h.p
Not sure to call it Red vs Blue and Green Noww..... :)
Posted on Reply
#28
AnarchoPrimitiv
I'm a fan of moore's law is dead (if you're going to be critical of him, provide evidence of why he's wrong and abstain from ad hominem personal attacks, otherwise it's completely irrelevant), and based on his sources and other things, he thinks the numbers Lisa Su shared might be the second to top card, as his sources, which have been proven correct again and again, have said that "AMD is going all out", and that the final clocks on the fastest sku haven't been decided yet

Posted on Reply
#29
Mats
JAB Creations
Lame, no mention of TPU's test rig and then they claim AMD cherry picked?
Which part of "a very coarse and unscientific way to compare AMD's numbers to ours" don't you understand? Are you even able to click the link in the OP?
Our testing data for one of the games is from the latest RTX 30-series reviews, find details of our test bed here.
Posted on Reply
#30
Dristun
puma99dk|
You cannot compare the 2 cards because AMD made the RX 5700 series for 1080p.
what? They didn't tout it as such - in their own slides.
Posted on Reply
#31
Turmania
From looks of it, it will contest with rtx 3700 not against 3800. Basically a 2080 ti competitor. Obviously we know very little about it and power consumption etc... but Lisa said it is big navi, therefore it is safe to assume that it will be its leading card. Unless they come up with uber navi etc.
Posted on Reply
#32
Mats
Turmania
Obviously we know very little about it and power consumption etc... but Lisa said it is big navi, therefore it is safe to assume that it will be its leading card.
I dunno, they focused on CPU's and mostly talked about the 5900X, the top model only got a few minutes at the end. They could have the picked graphics card to preview in a similar way.
I don't expect AMD's fastest card to run faster than a 3080, all I'm saying is we just don't know what they showed us.
Posted on Reply
#33
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.

You need to do benchmarks with 3080 and Ryzen 5000, it should add another 5-10% to 3080.

Same thing with 2080Ti, if you do 2080Ti with Ryzen 5000 you should get values closer to Big Navi, so Big Navi will be competing with 3070 or 3070Ti .

FORGET THAT IT WILL COMPETE WITH 3080, IT WONT HAPPEN.

Nvidia will also optimize their drivers and unlock another 10-15% performance, they done this many times in the past.

I have for a long time suspected Nvidia by default locks away a certain % of performance in their drivers that they can access in case of emergency. To many times in the past Nvidia just magicly found 5-15% performance by doing a so called "driver optimization" just when they needed it the most to compete with AMD/ATI.
Posted on Reply
#34
Vya Domus
john_
Oh come on. Don't put words in my mouth that I never said. And especially don't put words in my mouth that in a way call me a stupid noob that bought his first PC yesterday.
Damn, I am not even going to answer that BS question. I know that your average posts are much better than this.
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.

If you have any reason to believe "Big Navi" is a specific card/model go ahead and explain that.
Posted on Reply
#35
kapone32
At the end of the day we in the world have no better understanding of what exactly Big Navi is at 9 AM this morning vs 24 hours ago. Everything that anyone says is pure conjecture. The only thing I know is that Oct 28 should be very interesting. November will be a good month for AMD, Intel and Nvidia.
Posted on Reply
#36
Vya Domus
I've also just noticed that for some reason they paired it with a 5900X not 5950X and also slower memory, you'd think they would use the fastest system. Hmm.
Posted on Reply
#37
renz496
kapone32
At the end of the day we in the world have no better understanding of what exactly Big Navi is at 9 AM this morning vs 24 hours ago. Everything that anyone says is pure conjecture. The only thing I know is that Oct 28 should be very interesting. November will be a good month for AMD, Intel and Nvidia.
that day probably will give us more question than answer (along with more hype depending on how AMD wants to play it). we need to see the card being reviewed ASAP. hopefully we will see one before mid november. personally i hope this high end GPU battle to end already. give us the performance increase that we want to see in sub $250 already.
Posted on Reply
#38
DemonicRyzen666
AnarchoPrimitiv
I'm a fan of moore's law is dead (if you're going to be critical of him, provide evidence of why he's wrong and abstain from ad hominem personal attacks, otherwise it's completely irrelevant), and based on his sources and other things, he thinks the numbers Lisa Su shared might be the second to top card, as his sources, which have been proven correct again and again, have said that "AMD is going all out", and that the final clocks on the fastest sku haven't been decided yet


considering that he was talking about The Prosumer/work station card a short while ago. He was talking about Bignavi was competing with Nvidia series card work station cards, I don't really believe.
Because Those prosumer/work station card are suppose to be CDNA 1.0 and not RDNA 2.0.

CDNA 1.0 has 3 times the number CU's vs 5700 XT.
Posted on Reply
#39
Vya Domus
renz496
give us the performance increase that we want to see in sub $250 already.
Then you're going to be disappointed, I don't think any sub 300$ cards will be announced.
Posted on Reply
#40
kapone32
renz496
that day probably will give us more question than answer (along with more hype depending on how AMD wants to play it). we need to see the card being reviewed ASAP. hopefully we will see one before mid november. personally i hope this high end GPU battle to end already. give us the performance increase that we want to see in sub $250 already.
If Big Navi pushes the 5700 into the $250 range your wish would have been fulfilled. The only thing I am looking at is is that chip as much faster in performance than the 5700XT vs Polaris vs Vega.
Posted on Reply
#42
kapone32
Turmania
Will AMD ever make a 75w GPU?
There is no market for that you are better off buying a APU today or in the near future for low budget Gaming.
Posted on Reply
#43
Turmania
kapone32
There is no market for that you are better off buying a APU today or in the near future for low budget Gaming.
Gtx 1650 is selling like hot cakes though even with 150 USD price tag. There is a huge market and profit there.
Posted on Reply
#44
kapone32
Turmania
Gtx 1650 is selling like hot cakes though even with 150 USD price tag. There is a huge market and profit there.
That competes with the 5500XT.
Posted on Reply
#45
delshay
I'm just going to leave this link here. For the record I upvoted the top two user in the sub thread, read why.

Amd/comments/j7jx6z
Posted on Reply
#46
Turmania
kapone32
That competes with the 5500XT.
5500XT competes with 1650 super.

there is no AMD solution for 1650 Vanilla. Which I find it odd, and perhaps they fix it this generation.
Posted on Reply
#47
bug
One thing people gloss over is AMD has just announced "the fastest gaming CPUs". I bet these results are obtained running said CPUs.
Posted on Reply
#48
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.
Posted on Reply
#49
kapone32
Turmania
5500XT competes with 1650 super.

there is no AMD solution for 1650 Vanilla. Which I find it odd, and perhaps they fix it this generation.
I would say Polaris and you may be on to something. Polaris rather old but I am sure it has sold well for AMD. Navi did go through a rough patch but everything seems to be roses now (the memory clock jumps all over the place). A budget refresh that has the same GPU as the PS5 or Xbox1 would be nice for $169 US.
Posted on Reply
#50
wheresmycar
fynxer
Nvidia will also optimize their drivers and unlock another 10-15% performance, they done this many times in the past.
Cheeky monkeys. Not only are these cards SUPER expensive they tap away the higher performance ceiling.
Posted on Reply
Add your own comment