Apple's Graphics Performance Claims Proven Exaggerated by Mac Studio Reviews

[TheLostSwede]

Apple made some bold claims at the launch of its new Mac Studio computers when it came to the performance of the new systems and it looks like Apple was exaggerating those claims by quite some margin when it comes to the graphics performance. The first reviews of the new Mac Studio went live today and thanks to those reviews, despite the limited benchmarks that were performed on the new systems from Apple, that as so often Apple's performance metrics are still relying on the reality distortion field. Most of the publications that got their hands on the new systems focused on CPU benchmarks and there's no doubt the Ultra version of the M1 processor is a beast when used for things like video rendering and complex image manipulation, where it's butting heads with an AMD Ryzen Threadripper 3970X.

However, Apple's 64-core GPU isn't quite what the company claimed. In the presentation footnotes Apple provided details on the "highest-end discrete GPU" that they compared to, which was an NVIDIA GeForce RTX 3090. If we were to be kind to Apple, we would say that the company was slightly off target here, but it's actually not even remotely close. Tom's Guide tested the M1 Ultra SoC in Sid Meier's Civilization 6 and got a whopping 38.85 FPS at 1440p, which is beaten soundly by a Lenovo ThinkPad P1 Gen 4 with a GeForce RTX 3070 laptop GPU that scored 64.9 FPS at 4K. Likewise, The Verge decided to test the claims and had a system with an actual GeForce RTX 3090 in it and ran Shadow of the Tomb Raider and the PC managed 142 FPS at 1080p, with the M1 Ultra coming in quite far behind at 108 FPS. Moving up to 1440p the 3090 came in at 114 FPS, with the M1 still trailing behind, if not quite as badly at 96 FPS.




The issue here isn't the actual performance, as it's no doubt decent figures considering the max power draw of the Mac Studio is 370 W, far less than any PC with a GeForce RTX 3090 in it. However, Apple's inflated performance claims are getting old and tired and the company really needs to do better. It's highly unlikely that anyone will be buying a US$4999 Mac Studio to play games on, as that's what the base model with the 64-core GPU costs. As such, Apple should provide realistic benchmark comparisons, as overall the Mac Studio is an impressive piece of kit in its own right. Based on the first reviews, it's likely going to end up being used by a lot of creative companies that would normally use Macs for their workflow.

View at TechPowerUp Main Site | Source

 

[john_]

Apple's Graphics Performance Claims Proven Exaggerated

No. No. No. NO. NO. NO. This is impossible. It can't be true. This is a lie. I do not believe it. Apple? Never. NEVER. NEVER! NEVER!!!!
No. No. No. No. ...........

 

[WhitetailAni]

Apple based their GPU claims off of the Media Engine, which soundly destroys a 3090. People aren't buying a Mac Studio for gaming.

 

[claes]

Yeah, anyone buying a Mac Studio (it’s in the name) for gaming is a moron. Exaggerated, I guess, but inaccurate? Only if you don’t understand “context.”

Still, comparing performance to a 3090 was definitely a mistake on their part. Sure, some people are using 3090’s for “studio” work, and maybe they’re conceding that the Mac Pro is better for studios/m1 isn’t ready to take on the “Pro” or their own afterburner cards, and that the Mac Studio is geared towards entry-level professional work, but certainly no actual studios are using consumer GPUs for professional work… pretty lazy on their part.

Edit: but also lazy on TPU’s part? Why even bother comparing gaming performance if you’re not talking about mobile games?

Edit 2: looking for the 3090 asterisk on the Studio’s page, but can’t find it in the main ad. I hate scrolling frames on the web. There’s a way to enhance UX and be subtle about but this is not that. I’d search the source but I’m on mobile and can’t be bothered

 

[TheLostSwede]

Edit: but also lazy on TPU’s part? Why even bother comparing gaming performance if you’re not talking about mobile games?

Sorry? This is a desktop computer, no? I don't really understand your point here.

Did you even bother reading my post? The Mac Studio performs well, the question I asked why Apple felt like they had to lie about the 3D performance to make themself look better somehow, when even the most basic tests are showing it to be far from the truth. It was unnecessary, as the M1 is a very decent chip for what it is and Apple has put together a decent system, which makes their made up performance numbers even more stupid.

 

[Xuper]

I just checked Shadow of the Tomb raider and RoTTR uses same game engine as shadow of the tomb raider so perhaps It's equal to 6800/3070TI

MSI GeForce RTX 3080 Suprim X 12 GB Review

The MSI GeForce RTX 3080 12 GB Suprim X is the highest-clocked RTX 3080 12 GB on the market and almost as fast as the RTX 3080 Ti. The large triple-slot, triple-fan cooler has the card achieve great noise levels of less than 33 dBA, which is excellent for this performance class.

www.techpowerup.com

 

[TheoneandonlyMrK]

Apple based their GPU claims off of the Media Engine, which soundly destroys a 3090. People aren't buying a Mac Studio for gaming.

Look it soundly destroys it in power efficiency too but the point of a 5k apple computer is to get work done, all sorts of work not one type, and their benchmark dataset should reflect that.

NOt hyperbole one or two data points beyond sense

 

[Dr_b_]

put another way, if it was possible to have the same performance as the 3090 with a fraction of the power, nvidia would already be doing this. Apple invited 3D comparisons by claiming it was superior to a 3090 (highest end discrete gpu). This is just apple marketing puff and blow.

 

[claes]

Sorry? This is a desktop computer, no? I don't really understand your point here.

I think we can agree, no, even if Apple invites the comparison? I never understood this contention from Apple, given their markets being mobile and media pro’s.

TBF, this is marketed as a workstation and, as impressive as the silicon is, I’m not sure it’s that, either? Maybe a managed appliance?

Did you even bother reading my post? The Mac Studio performs well, the question I asked why Apple felt like they had to lie about the 3D performance to make themself look better somehow, when even the most basic tests are showing it to be far from the truth. It was unnecessary, as the M1 is a very decent chip for what it is and Apple has put together a decent system, which makes their made up performance numbers even more stupid.

I did — did you read Apple’s PR? The comparison to a 3090 was vague and didn’t point to a specific benchmark outside of “performance.” The Tom’s article is garbage, and the The Verge article references an older Mac Pro without the updated CPU and GPU (I’m sure I could Google specs but why?)…. Maybe you have more insight into this and I’m just misreading!

IDK what this product is, but it’s certainly not a gaming PC, and I haven’t been sure what a computer is for more than a decade.

 

[IceShroom]

Apple based their GPU claims off of the Media Engine, which soundly destroys a 3090. People aren't buying a Mac Studio for gaming.

Destroys other gpu on media codec that only Apple supports. A dual-core TigerLake cpu can destroy the M1 Ultra when it comes to decode and encode AV1 codec.
Did Apple's slave reviewer tested anything like H.265/AV1/XAVC/RAW-Video beside ProRes???

 

[john_]

Still, comparing performance to a 3090 was definitely a mistake on their part.

No, it wasn't. It was deliberate, in my opinion. Apple is advertising itself as building and selling the best hardware and software. Nothing shorter than that. Their arrogance is part of their advertising campaign. Any and all of their advertising campaigns. So, they compared with the best GPU available. Comparing with something else, like a mid range GPU, I don't think they would do that. No. They are the best company in the world. Period. They only compare with the best and beat the best. Even when they don't really.

Even after these benchmarks show they exaggerated, the vast majority of people out there, yesterday, today, tomorrow, in a month or even a year from now, they will still think that Apple's GPU in M1 Ultra beats the 3090. Most of those are not the target group for Mac Studio, they wouldn't even think of buying something like that, but they are the target group for Apple in general, so they have to "know" that Apple is the best in everything and anything.

 

[TheUn4seen]

A corporation lying about their product? That's unheard of! And Apple no less, the squeaky clean company known for using slave and child labor to build their toys for the less intellectually inclined! This must be a lie or, at the very least, a misunderstanding on the part of poor reviewer who simply is ignorant of the pure awesomeness the rotten apple logo bestows on any hardware it touches!

You know how it is with corporate claims. Subtract 25% to be in the general vicinity of truth. 50% to be sure.

 

[mechtech]

meh, not like I or the majority of anyone else was ever going to buy one.

 

[Valantar]

Sorry? This is a desktop computer, no? I don't really understand your point here.

Did you even bother reading my post? The Mac Studio performs well, the question I asked why Apple felt like they had to lie about the 3D performance to make themself look better somehow, when even the most basic tests are showing it to be far from the truth. It was unnecessary, as the M1 is a very decent chip for what it is and Apple has put together a decent system, which makes their made up performance numbers even more stupid.

I think this is the core of the issue: Apple never mentioned 3D performance (and certainly not real time 3D performance like games), they said "GPU performance". What does GPU performance mean? To most people, and certainly PC enthusiasts, it means gaming. To Apple, it likely means some kind of GPGPU application, accelerating who knows what. Complex multipass tiled 3D rendering? CAD? Video rendering? Something entirely else?

The gaming performance on show here is, as expected, rather underwhelming. Given that Apple doesn't give a single crap about gaming, that shouldn't come as a surprise to anyone. The problem is that beyond whatever "industry standard benchmarks" means, Apple isn't actually saying what "GPU performance" means to them, which makes the claims inherently impossible to test.

I still think it's likely there are real-world usage scenarios where Apple's claims are mostly true - but I also think those are quite selective and limited to certain pro-level productity apps, and likely ones that are either Mac exclusive or highly Mac optimized. In general, I expect performance to be good, but nothing spectacular, while efficiency is likely a cut above the rest.



Also, not that it matters much, but it's pretty impressive that the M1 Max in the MBP is barely slower than the one in their 400W PSU SFF desktop. Speaks to the efficiency of the chip, if nothing else - though also the lack of frequency scaling past the sweet spot it's clearly tuned to.



As with everything: horses for courses. And as with all marketing: critical reading is paramount, but so is careful reading to not get into silly fights about whether or not someone lied. And unless they're also lagging significantly in GPGPU benchmarks, there might still be a (selective, as with all marketing) truth to be found somewhere in that statement.

 

[DrCR]

to not get into silly fights about whether or not someone [whatevered]

That’s almost the entire internet now, though.

 

[seth1911]

Thats the golden cage Something will be really good but ure in a cage.

I can use and play whatever i want with Windows, Linux and BSD.

 

[Denver]

No, it wasn't. It was deliberate, in my opinion. Apple is advertising itself as building and selling the best hardware and software. Nothing shorter than that. Their arrogance is part of their advertising campaign. Any and all of their advertising campaigns. So, they compared with the best GPU available. Comparing with something else, like a mid range GPU, I don't think they would do that. No. They are the best company in the world. Period. They only compare with the best and beat the best. Even when they don't really.

Even after these benchmarks show they exaggerated, the vast majority of people out there, yesterday, today, tomorrow, in a month or even a year from now, they will still think that Apple's GPU in M1 Ultra beats the 3090. Most of those are not the target group for Mac Studio, they wouldn't even think of buying something like that, but they are the target group for Apple in general, so they have to "know" that Apple is the best in everything and anything.

Yes, exactly. Apple specializes in winning minds and making them pay much more, thinking they are buying the best possible product in every aspect, when the reality is quite different...

They have just expensive products with positives and negatives points, just like everything else.

 

[goodeedidid]

Isn't it too early to call it?!? Firstly things have to be optimized.. also who plays games on a Mac?

 

[ThrashZone]

Hi,
So apple convinced their fan base ?

 

[Garrus]

The entire internet is making up their mind without actually looking at software optimized for Mac Silicon. Here we have the M1 Ultra easily beating an RTX 3070. Only a few percentage points slower than an RTX 3090. Apple has a lot of software issues to work through to get performance. Mac OS versus Windows. Metal versus Vulkan etc. Apple Silicon versus nVidia and x86. I've said it so many times but I'll repeat myself. Apple badly needs to create a game console to get native high performing code on their systems, to take advantage of their hardware.

 

[Nephilim666]

The internet is making up their mind based on Apple's marketing statement, not edge use cases and "if only they used mac optimised software".

 

[Assimilator]

The entire internet is making up their mind without actually looking at software optimized for Mac Silicon. Here we have the M1 Ultra easily beating an RTX 3070. Only a few percentage points slower than an RTX 3090. Apple has a lot of software issues to work through to get performance. Mac OS versus Windows. Metal versus Vulkan etc. Apple Silicon versus nVidia and x86. I've said it so many times but I'll repeat myself. Apple badly needs to create a game console to get native high performing code on their systems, to take advantage of their hardware.
View attachment 240188

We aren't talking about GTX 3070, dear child. Nor was Apple. Do try to keep up.

 

[mama]

This seems to be a classic example of Apple cherry picking performance aspects of a product and making grandiose generalised claims. Those graphs in their presentations are hilarious. The populous refrain is "they all do it". But that certainly doesn't make it right or acceptable. Another lesson in not believing the hype and waiting for independent reviews.

 

[watzupken]

This seems to be a classic example of Apple cherry picking performance aspects of a product and making grandiose generalised claims. Those graphs in their presentations are hilarious. The populous refrain is "they all do it". But that certainly doesn't make it right or acceptable. Another lesson in not believing the hype and waiting for independent reviews.

I am hard pressed to find a company that does not cherry pick data for marketing. In this case, Apple claimed that their GPU is faster than the RTX 3090, and it is indeed the case, only not for gaming. At least on their site below, nowhere did they say that it offers 2x gaming performance over the RTX 3090. Reviewers seems very fixated at the 2x RTX 3090 claim and take it as 2x gaming performance. To them, GPU = gaming, but is It just about gaming since Apple don’t really market Macs as gaming machines?

Apple unveils M1 Ultra, the world’s most powerful chip for a personal computer

Apple today announced M1 Ultra, the next giant leap for Apple silicon and the Mac.

www.apple.com

 

[enzolt]

GraphicsGate