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

#1
jesdals
I could live with that if the price is belowe the 3080
Posted on Reply
#2
TheLostSwede
News Editor
But which SKU did they show off? Everyone assumes it's the top tier card...
Posted on Reply
#3
Shou Miko
TheLostSwedeBut which SKU did they show off? Everyone assumes it's the top tier card...
That's possible and what most people believe.

We don't believe it to be like a RX 6900 but the XT or XTX (Last one AMD ref only) but if it's a regular RX 6900 it would be wow :laugh:
Posted on Reply
#4
R0H1T
TheLostSwedeBut which SKU did they show off? Everyone assumes it's the top tier card...
Do you know something that we don't, any insider scoops?
Posted on Reply
#5
kayjay010101
Yeah... as you say yourself, comparing between two different benchmark passes means nothing. You'd have to have the least amount of variables possible, including using the exact same benchmark pass. It seemed like they used the internal benchmark in their presentation, so comparing to your own custom route in the game isn't a valid form of comparison.

And this might not be the top SKU. A lot of other news publications have stated AMD stressed to them that they didn't tell which SKU this was, which to me seems like they're trying to imply it's not the top dog.
Posted on Reply
#6
Anymal
puma99dk|That's possible and what most people believe.

We don't believe it to be like a RX 6900 but the XT or XTX (Last one AMD ref only) but if it's a regular RX 6900 it would be wow :laugh:
Maybe 6700xt ?
Posted on Reply
#7
TheLostSwede
News Editor
puma99dk|That's possible and what most people believe.

We don't believe it to be like a RX 6900 but the XT or XTX (Last one AMD ref only) but if it's a regular RX 6900 it would be wow :laugh:
Personally I think it would be a bad move by AMD to show it's full hand this early, as it potentially allows Nvidia to make adjustments. I guess it might be too late for that though, but who knows. Even so, all we can do for now is to speculate. That said, I doubt AMD will have a product that beats the RTX 3080, but I could be wrong.
Posted on Reply
#8
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...
Posted on Reply
#9
Shou Miko
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...
Every company cherry pick games and benchmarks that's nothing new...
TheLostSwedePersonally I think it would be a bad move by and to show it's full hand this early, as it potentially allows Nvidia to make adjustments. I guess it might be too late though, but who knows.
Well AMD doesn't really compete with RTX 3090 and I don't believe they will because if the majority of people using a graphics card is still at 1920x1080 pixel they not make something that crushes this resolution instead og focusing on 4k@120fps+ and 8K@60hz? Because the majority of people in 2020 and properly 2021 doesn't game at 4K or 8K yet.
AnymalMaybe 6700xt ?
I haven't heard much about this card I only been focusing on the RX 6900 series because that's properly the card to replace my RX 5700 XT since the RTX 3080 20GB won't be in stock until 2021 sadly according to Nvidia.
Posted on Reply
#10
Chrispy_
If that's the 80CU variant I'd be surprised since that implies lower IPC for RDNA2 than RDNA1, and AMD have been touting their IPC gains as a big deal for RDNA2.

I would imagine that's a downclocked 72CU variant with cheaper GDDR6, perhaps it's the 12GB variant that's effectively double the 5600XT.

I honestly don't care what card it is as long as AMD can move the price/performance curve forwards and beat whatever Nvidia are offering, and if they can do it at a lower power draw (not excactly the hardest challenge given Nvidia's shocking TDP this generation) then that's just the cherry on the cake.
Posted on Reply
#11
Erazor6000
Finally, they made a better graphic card that my RTX 2080.

Now AMD have both excellent CPUs and (probably) GPUs when compared to Intel and nVidia.
...NOT with Ryzen 3000, which were nothing special if you are into gaming only.
For me, RX 5700 XT was nothing to consider, especially because it was announced as late as Q3 2019, and it wasn't even better than RTX 2080 (non super).
Posted on Reply
#12
Shou Miko
Erazor6000Finally, they made a better graphic card that my RTX 2080.

Now AMD have both excellent CPUs and (probably) GPUs when compared to Intel and nVidia.
...NOT with Ryzen 3000, which were nothing special if you are into gaming only.
For me, RX 5700 XT was nothing to consider, especially because it was announced as late as Q3 2019, and it wasn't even better than RTX 2080 (non super).
You cannot compare the 2 cards because AMD made the RX 5700 series for 1080p.
Posted on Reply
#13
john_
I guess the dilemma will be like this:

3080: Faster, Raytracing performance, DLSS, CUDA, (theory or fact you decide) better drivers

Big Navi: Lower price, 16GB of VRAM, FreeSync (if I am not mistaken NOT all FreeSync monitors are supported by Nvidia).

PS. Su called the card "Big Navi", so probably the top model. People gave that nick name to the big model, not some second mid range model.
Posted on Reply
#14
docnorth
puma99dk|That's possible and what most people believe.

We don't believe it to be like a RX 6900 but the XT or XTX (Last one AMD ref only) but if it's a regular RX 6900 it would be wow :laugh:
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.
Posted on Reply
#15
demu
Please check your RTX 3080 Borderland 3 results.
You are saying, that the RTX 3080 FE:s score (70.3 FPS) is tested using DX12.
We tested the game with its DirectX 12 renderer in our dedicated performance review (test bed details here).

However, in RTX 3080FE review you are stating that due to instability problems, you tested Borderland 3 with DX11:

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.

www.techpowerup.com/review/nvidia-geforce-rtx-3080-founders-edition/10.html
Posted on Reply
#16
Erazor6000
puma99dk|You cannot compare the 2 cards because AMD made the RX 5700 series for 1080p.
I am aware of that.
My point is that we will have a choice between GeForce and Radeon for high-end gaming at 2K/4K in the years to come.
Posted on Reply
#17
ratirt
I think these games were not cherry picked in the means of showing the best performance. If that was the case I'm sure AMD would have picked different, more like Battlefield V. Also the assumption is that the tests were performed with the top model card but "big navi" not necessarily mean top tier but the new 6000 series.
If I were AMD, i wouldn't use top tier card for that showcase. NV did similar with Ampere. Although it might have been top AMD's card. I guess, in a month, we will all know what sort of performance the 6000 RDNA2 navi will bring.
Posted on Reply
#18
JAB Creations
ratirtI think these games were not cherry picked in the means of showing the best performance. If that was the case I'm sure AMD would have picked different, more like Battlefield V. Also the assumption is that the tests were performed with the top model card but "big navi" not necessarily mean top tier but the new 6000 series.
If I were AMD, i wouldn't use top tier card for that showcase. NV did similar with Ampere. Although it might have been top AMD's card. I guess, in a month, we will all know what sort of performance the 6000 RDNA2 navi will bring.
Are you replying to me? That is a Facebook thing, leave confusing responses there please.

I'm saying TPU cherry picked. Gamers Nexus said that AMD was very honest in the benchmarks they picked. I'm saying whoever wrote this article clearly has a bias as they presented a sneak peak as the end-all-be-all.
Posted on Reply
#19
ratirt
JAB CreationsAre you replying to me? That is a Facebook thing, leave confusing responses there please.

I'm saying TPU cherry picked. Gamers Nexus said that AMD was very honest in the benchmarks they picked. I'm saying whoever wrote this article clearly has a bias as they presented a sneak peak as the end-all-be-all.
why you assume I replied to your post? Did I quote anything you've posted? It's not just you posting here and I replied in general by reading comments of other people.
Posted on Reply
#20
Vya Domus
john_PS. Su called the card "Big Navi", so probably the top model. People gave that nick name to the big model, not some second mid range model.
People gave that name to the chip itself not to a card, as in the largest die. You really think they'll just have 1 product based on that chip ? I don't, that has never happened.
ratirtI think these games were not cherry picked in the means of showing the best performance.
Indeed, notably Borderlands 3 was one of the main games to be shown on RTX 3080. They didn't chose it by mistake, it's a direct "confrontation" of sorts.
Posted on Reply
#21
Bytales
AnymalMaybe 6700xt ?
Nah, the benched numbers are for the entry level navy 6300XT with 64bit 16Gb GDDR7x
Nvidia is faqed !
Posted on Reply
#22
john_
Vya DomusYou really think they'll just have 1 product based on that chip ?
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.
Posted on Reply
#23
cueman
naah,i say different is about 20-25% for rtx 3080 .

amd use its new ryzen 5900 cpu,its help alot,also it help rtx 3080 nd evn more rtx 3090.


20% faster than rtx 2080 ti is max it can reach...i wonder what is big navi tdp thouse speed.. sure over 300W.

well, let see, but real world is that kind...
Posted on Reply
#24
Bytales
BytalesNah, the benched numbers are for the entry level navy 6300XT with 64bit 16Gb GDDR7x
Nvidia is faqed !
6500 series uses 128bit memory still 16gb, because hey, the memory is so cheap and the performance is so big, that it was worth it to give the entry level cards 16gb of video ram.

6700 uses 256 bit memory 32gb, 6800series uses 384bit memory 48 gb, and the 6900 series uses 512bit memory 64gb, with a special "Lisa Su edition" XTX version with 8192bit HBM3 memory, double the bandwith of the normal 6900 navi, and 128gb of video memory.

Nvidia can file for bankruptcy !
Posted on Reply
#25
nguyen
AMD CPU Slides: woohoo we are number one
AMD GPU slides: yeahhhh, here are our FPS, take it or leave it
Posted on Reply
Add your own comment
Nov 21st, 2024 13:08 EST change timezone

New Forum Posts

Popular Reviews

Controversial News Posts