AMD vs. Intel GeForce RTX 3080 Benchmark

[Steve]

For today's article we'll be once again looking at many benchmark graphs filled with RTX 3080 data, though this one is going to be a little different. While we're benchmarking the new GeForce RTX 3080, it won't be the main focus of our attention but rather we'll be looking deeper into CPU performance.

Read the full article here.

https://www.techspot.com/article/2103-amd-vs-intel-rtx-3080/

 

[QuantumPhysics]

Thank You TECHSPOT for the comparison.

based on your findings I will build my next desktop using an Intel CPU + my 3080.

every little bit of advantage is appreciated.

 

[Strawman]

Your reasons for testing on the 3950x don't make sense to be frank. PCIE 4 makes little to no difference, and most of your viewers are not buying a 3950x. It's either the 3600 or the 3300x. So yeah...

Red team sadly has become a religion, you can make a poll asking if they want you to skew the numbers to favor AMD, they will vote yes. Does that mean you'll do it?

 

[Srhnd]

Your reasons for testing on the 3950x don't make sense to be frank. PCIE 4 makes little to no difference, and most of your viewers are not buying a 3950x. It's either the 3600 or the 3300x. So yeah...

Red team sadly has become a religion, you can make a poll asking if they want you to skew the numbers to favor AMD, they will vote yes. Does that mean you'll do it?

Honestly, for 10900k it is the same. Not everyone is buying 10900k. Most people buy some i5, maybe 10600k or at best 10700k. There are also a lot of people who still cling onto their older CPUs like me e.g. with my 6850k.

What they do here is to simply compare the best available on Intel side with best available on AMD side. It has no favouritism this way. But you are right, I would also, like many others I assume, see more of mainstream CPUs being tested even with 3080 and 3070. Like 10600k vs 3600x or 10700k vs 3700x/3800x.

 

[Irata]

Small correction:

Wolfenstein: Youngblood sees no difference in performance between the 10900K and 3950X at 1440p and 4K, at least a difference worth talking about. The 10900K was 8 fps faster than the 3950X when running the RTX 3080 at 1440p, that remains a small 2% increase though.

Ryzen is actually faster than the 10900k at all resolutions for this game with the RTX 3080.

As I said, just a small nitpick.

 

[Steve]

Your reasons for testing on the 3950x don't make sense to be frank. PCIE 4 makes little to no difference, and most of your viewers are not buying a 3950x. It's either the 3600 or the 3300x. So yeah...

Red team sadly has become a religion, you can make a poll asking if they want you to skew the numbers to favor AMD, they will vote yes. Does that mean you'll do it?

It makes no difference so you're just lowering yourself to fanboy type arguments. For example if we didn't list the CPU tested and instead just showed the results (the overall margins and cost per frame) you'd have no issue with the review. As far as you'd be concerned, our conclusion is inline with that of other trusted media outlets and our margins/cost per frame was virtually identical.

Also you're 3300X/3600 argument is flawed, though someone else has already picked you up on that.

Finally if you could have assured us PCIe 4.0 would make no difference before we got the RTX 3080, that would have been helpful.

 

[quadibloc]

If I'm a serious competitive gamer, aren't high frame rates more important than higher resolution? However, I'm not a serious competitive gamer myself, but I play RuneScape, and I notice that on my 1080p screen, the interface is kind of cramped. So maybe 4K does have enough benefits that it's very important to get decent performance at that resolution.

 

[godrilla]

On this note remember when I said Crysis remastered can do more damage than good for their rep, well these boasting fools kept ot single threaded besting a i9 10900k even! ?.

 

[Irata]

Your reasons for testing on the 3950x don't make sense to be frank. PCIE 4 makes little to no difference, and most of your viewers are not buying a 3950x. It's either the 3600 or the 3300x. So yeah...

Red team sadly has become a religion, you can make a poll asking if they want you to skew the numbers to favor AMD, they will vote yes. Does that mean you'll do it?

I do agree with you that polls can be problematic as yes, sadly GPU or CPU preference has turned into a religion for many (and claiming it only affects one 'team' makes you part of this group).
The same can be said about quoting the number of forum posts...

Fortunately, there are often other data points to check for validation, like e.g. sales numbers / rankings of shops who sell to the DIY crowd, numbers from gaming platforms etc.

 

[CrazyBeard]

Maybe compare a Ryzen 3900xt to 10900k since the core count is closer as well as the price and release date. I always thought the 3950x was more of productivity cpu due to the core count and the cost. the 10900k and the 3950x just seem like they are for different use cases.

 

[Strawman]

Honestly, for 10900k it is the same. Not everyone is buying 10900k. Most people buy some i5, maybe 10600k or at best 10700k. There are also a lot of people who still cling onto their older CPUs like me e.g. with my 6850k.

Βut the reason for using the 10900k isn't because people buy it, it's because it's the fastest gaming CPU, therefore you can actually see the maximum potential of the GPU that's being benchmarked.

 

[Strawman]

It makes no difference so you're just lowering yourself to fanboy type arguments. For example if we didn't list the CPU tested and instead just showed the results (the overall margins and cost per frame) you'd have no issue with the review. As far as you'd be concerned, our conclusion is inline with that of other trusted media outlets and our margins/cost per frame was virtually identical.

Of course I would have no issue, cause I would assume you tested with the fastest gaming CPU. For example, right now I have a 1080ti and I'm thinking about upgrading cause I can't really play metro exodus on my current resolution with max settings. But looking at your review, it seems like a waste of money to upgrade to a 3080 for that game, cause the gains are minimal. Little would I know that that is because of the CPU you are testing it with

Also you're 3300X/3600 argument is flawed, though someone else has already picked you up on that.

No it's not, that someone else didn't address the argument I made. Again, based on popularity, you should be testing the 3300x and the 3600. Your argument was based on popularity, not mine. I'm saying test with the fastest gaming CPU, whatever brand it is.

Finally if you could have assured us PCIe 4.0 would make no difference before we got the RTX 3080, that would have been helpful.

Ofc I couldn't, but you could. You could run 3 tests, see that it makes no difference and then proceed to benchmark with the fastest gaming CPU.

 

[Steve]

Ofc I couldn't, but you could. You could run 3 tests, see that it makes no difference and then proceed to benchmark with the fastest gaming CPU.

So you think we benchmark around 20 GPUs in like what? A day? All of this was explained in the original content. The issue was, we had to update all our data and we weren't sure where to invest the time. So we did the initial investigation and found that the 3950X wouldn't influence the performance in a meaningful way, but it would allow us to test with PCIe 4.0. There were a few other factors that went into the decision but I'm not going to explain all that for the 10th time.

 

[actionjksn]

I haven't built a gaming system in years but I always used Intel. But if I were to build one now it would be Ryzen with an Nvidia GPU without question.

However I think at this point for your test system I think you should still be using whatever the fastest Intel processor is.

For myself I would buy about a $300.00 AMD processor and some fast RAM, even though I always hated AMD CPUs before, but they can not be ignored now and AMD makes the best overall CPUs.

But for a website that tests the newest most elite graphics cards you gotta use the one that consistently gives the highest frame rates and that is still Intel. This is all about science not fanboy stuff.

BTW about three years ago I bought a 27" LG monitor that was only about ,$300.00. it's 4K with 60hz. I couldn't afford to build a system that can game at 4K with more than 60 frames per second. So I'm good for a long time. I love this monitor it looks beautiful

 

[BoboOOZ]

Of course I would have no issue, cause I would assume you tested with the fastest gaming CPU. For example, right now I have a 1080ti and I'm thinking about upgrading cause I can't really play metro exodus on my current resolution with max settings. But looking at your review, it seems like a waste of money to upgrade to a 3080 for that game, cause the gains are minimal. Little would I know that that is because of the CPU you are testing it with

Look at it that way, for most of the people looking at that review, that is the exact gain that is to be expected: minimal. Hence the poll with so many answers. This is actually useful information.

While this approach doesn't find the absolute truth (I would argue there is no absolute truth in this case), the result of the review is much more useful to the public, because it gives them a view which is much closer to what they should expect.

 

[Irata]

So you think we benchmark around 20 GPUs in like what? A day?

So being upside down the whole time makes you work slower, is that what you‘re saying Steve ?


Sorry, couldn‘t resist. ?

 

[redhat]

For folks who ask to review amd 3600. Already on tomshardware found that at 4k res they are all same even old CPU like 4770K was nearly same. they said at 4k the stress is mostly on GPU.

@Steve like People said I think more mainstream CPUs would be better 8700k vs 3700x etc would be more interesting I know you intend to show the maximum perf but I think most people dont have Top End CPUs & GPUs still thank you for your work. being reading your reviews since 2004

 

[darkzelda]

Still buying a Ryzen for my next upgrade, I love playing games in my computer, but it also serves me as my main productivity platform.

 

[Toju Mikie]

NVIDIA has always advertised this 3080 as a 4K gaming card. You could choose to play in 1080p, but you will also have to buy a 360hz monitor ($699) and are going to miss out on those beautiful 4K textures. I just don't see the point, and in some titles (especially e-sports) in 1080p, the frame rate will be too high for the player to even see the result (I'm talking 400+ fps). It will just be a waste of money if you are not going to play on 1440p or 2160p.

 

[antiproduct]

based on your findings I will build my next desktop using an Intel CPU + my 3080.

While you're waiting on everything getting in stock, you might as well wait a couple weeks longer to see how the Zen 3 shapes up.

 

[Jayark1]

Thank You TECHSPOT for the comparison.

based on your findings I will build my next desktop using an Intel CPU + my 3080.

every little bit of advantage is appreciated.

I went with Ryzen with x570 as I've read that is the set up to have regarding upcoming RTX I/O technology. I heard current Intel mobos and processors won't be in alignment for that come 1st Quarter next year when Microsoft releases the update to support this tech. RTX I/O is supposed to make CPU less important in this case. I'd rather have a set up in place for that than regret buying Intel stuff and have to completely change Mobos and Processor again to meet the RTX I/O criteria

 

[Strawman]

Look at it that way, for most of the people looking at that review, that is the exact gain that is to be expected: minimal. Hence the poll with so many answers. This is actually useful information.

While this approach doesn't find the absolute truth (I would argue there is no absolute truth in this case), the result of the review is much more useful to the public, because it gives them a view which is much closer to what they should expect.

I disagree with that. Most of the people looking for a high end GPU to play in anything other than 4k SHOULD know that they need an Intel CPU. Basically a 3080 performs in 1440p pretty much the same as a 2080ti does in 1080p. Would you get a 2080ti for 1080p with anything less than the top CPU for gaming? Probably not.

So..if they have a Ryzen 3600 or something that performs similarly on aless than 4k monitor they shouldn't even be looking for such an upgrade in my opinion. The 3070 would so just fine.

 

[GNelson]

Great job as always. While PCIe4 is a great feature it still not fully ready from what has been seen by either NV or AMD. All Scoring is based to provide a snap shot so people can see what is real in 3080 usage by systems. This is not AMD vs Intel but which can provide enough zoom to play games or get work done. Dollar for Dollar AMD wins hands down in real world use (they call it work) and if I were a gamer I would be using Intel but only if I were making a living at it. It comes down to "How fast is Fast" and what gives you enough to get the fun done and work. Waiting on Big Navi to arrive and maybe see pricing compress some so I can upgrade, but only if the price is right as for now I can get real work done and far cheaper with AMD.

 

[mbrowne5061]

If I'm a serious competitive gamer, aren't high frame rates more important than higher resolution? However, I'm not a serious competitive gamer myself, but I play RuneScape, and I notice that on my 1080p screen, the interface is kind of cramped. So maybe 4K does have enough benefits that it's very important to get decent performance at that resolution.

You're better off splitting the difference right now. Consistent 4k60fps is really only possible with the toppest-of-top-tier hardware, but 2k60fps+ is very doable in most games and with more modest hardware.

1080 is good for budget entry, but 4k is just for showing off your wallet at this point. Another year or two, and 4k60fps will be ready (this latest gen of GPUs when paired with next gen CPUs ought to do it), but its not quite there yet.

 

[Arbie]

I'm a patron, and glad that my money went towards a Ryzen CPU. Those are what I'm buying - for all the obvious reasons - and so are most other people. When I want to know which GPU to get, the answers will be here.