Tuesday, November 17th 2020

Apple M1 Beats Intel "Willow Cove" in Cinebench R23 Single Core Test?

Maxon ported the its latest Cinebench R23 benchmark to the macOS "Big Sur" Apple M1 platform, and the performance results are groundbreaking. An Apple M1-powered MacBook Pro allegedly scored 1498 points in the single-core Cinebench R23 test, beating the 1382 points of the Core i7-1165G7 reference score as tested by Maxon. These scores were posted to Twitter by an M1 MacBook Pro owner who goes by "@mnloona48_" The M1 chip was clocked at 3.10 GHz for the test. The i7-1165G7 uses Intel's latest "Willow Cove" CPU cores. In the same test, the M1 scores 7508 points in the multi-core test. If these numbers hold up, we can begin to see why Apple chose to dump Intel's x86 machine architecture in favor of its own Arm-powered custom silicon, as the performance on offer holds up against the highest IPC mobile processors in the market.
Sources: mloona48_ (Twitter), via Hexus.net Forums
Add your own comment

96 Comments on Apple M1 Beats Intel "Willow Cove" in Cinebench R23 Single Core Test?

#1
bonehead123
And so it begins....

waitin to see all the FANBOIS, doomer-gloomers, skeptics, arm-chair analysts etc etc coming out of the woodwork making all sorts of wild, unproven claims, conspiracy theories, etc etc.....
Posted on Reply
#2
z1n0x
Seems like a great SoC, congratulations to the engineers.
Too bad Apple is such PoS of a company and i would never spend money on their products ever.
Posted on Reply
#3
ShurikN
Was thinking about how that MP ratio of 5x is kinda low considering it's an 8 core cpu.
But it is a mobile chip so all core freq must be terribly low compared to short term single core burst (like in all of them). Desktop chips usually get perfect scaling.
My 3200g has 3.94 MP ratio.
Posted on Reply
#4
Steevo
bonehead123
And so it begins....

waitin to see all the FANBOIS, doomer-gloomers, skeptics, arm-chair analysts etc etc coming out of the woodwork making all sorts of wild, unproven claims, conspiracy theories, etc etc.....
There is nothing so tiring as expectation postponed.

Also, good for Apple, they are aiming at content creation and seem to have built a CPU that does it very well.

I'm interested to see other benchmarks.
Posted on Reply
#5
Aquinus
Resident Wat-man
ShurikN
Was thinking about how that MP ratio of 5x is kinda low considering it's an 8 core cpu.
Probably the part where 4 of the cores are slower low power cores that don't clock as high as the other 4. Honestly, I'm not surprised. The numbers are pretty good to be honest, but that multithreaded score still isn't quite where my 9880H is at, but that's saying something for their low-end chip.
Posted on Reply
#6
ShurikN
Aquinus
Probably the part where 4 of the cores are slower low power cores that don't clock as high as the other 4. Honestly, I'm not surprised. The numbers are pretty good to be honest, but that multithreaded score still isn't quite where my 9880H is at, but that's saying something for their low-end chip.
Ahh yes it has a big.little core arrangement, I forgot about that. Makes sense.
Posted on Reply
#7
Vya Domus
ShurikN
Was thinking about how that MP ratio of 5x is kinda low considering it's an 8 core cpu.
But it is a mobile chip so all core freq must be terribly low compared to short term single core burst (like in all of them). Desktop chips usually get perfect scaling.
My 3200g has 3.94 MP ratio.
4 of the cores are much narrower and likely lower clocked as well. Apple's chip always had terrible MT scaling for that reason, 5x scaling means those cores are dog slow really.

Remember those claims about efficiency and performance per watt ? Yeah, it's because of those small cores.

Oh and they're on 5nm.
Posted on Reply
#8
ebivan
Looks promising.

But didn't Apple promise "3.5 x faster" so i was expecting single core performance somewhere in the 4000-5000 and multicore somewhere high above 20000...??
Posted on Reply
#9
birdie
It's not even about performance per se. In terms of performance per watt Apple M1 is leaps and bounds better than both TGL and Zen 3.
Posted on Reply
#11
AnarchoPrimitiv
birdie
It's not even about performance per se. In terms of performance per watt Apple M1 is leaps and bounds better than both TGL and Zen 3.
some of that is due to node advantage, just as how AMD 7nm is more efficient than intel 14nm
Posted on Reply
#12
theoneandonlymrk
Steevo
wccftech.com/intel-and-amd-x86-mobility-cpus-destroy-apples-m1-in-cinebench-r23-benchmark-results/amp/

Then again this site says different. What's the difference?

Also in the same image when the Intel chip was clocked at 2.8Ghz VS the Apple 3.1Ghz the Intel chip won by 34 points despite running 300Mhz slower per core.
Single core verses multi core.
And on multiple cores the intel and AMD Mobile cores win out easily despite a one or two node advantage for apple.

Hype train derailment in action , fastest mobile CPU my ass.
Posted on Reply
#13
Rahnak
ebivan
Looks promising.

But didn't Apple promise "3.5 x faster" so i was expecting single core performance somewhere in the 4000-5000 and multicore somewhere high above 20000...??
Here's the asterisk on the 3.5x faster performance, straight from Apple:

Testing conducted by Apple in October 2020 using preproduction MacBook Air systems with Apple M1 chip and 8-core GPU, as well as production 1.2GHz quad-core Intel Core i7-based MacBook Air systems, all configured with 16GB RAM and 2TB SSD. Tested with prerelease Final Cut Pro 10.5 using a 55-second clip with 4K Apple ProRes RAW media, at 4096x2160 resolution and 59.94 frames per second, transcoded to Apple ProRes 422. Performance tests are conducted using specific computer systems and reflect the approximate performance of MacBook Air.

A single test. :)
Posted on Reply
#14
Frick
Fishfaced Nincompoop
theoneandonlymrk
Single core verses multi core.
And on multiple cores the intel and AMD Mobile cores win out easily despite a one or two node advantage for apple.

Hype train derailment in action , fastest mobile CPU my ass.
Perf/watt is where the gold (supposedly) is. Being the fastest isn't interesting, it's how fast you can be within a specific power envelope, and these are supposed to really shine there.
Posted on Reply
#15
theoneandonlymrk
Frick
Perf/watt is where the gold (supposedly) is. Being the fastest isn't interesting, it's how fast you can be within a specific power envelope, and these are supposed to really shine there.
Obviously, but then they're not going to replace Those needing more powerful systems like some are implying.
And being the fastest is Exactly what apple reported on being just days ago without proof.
Posted on Reply
#16
dyonoctis
theoneandonlymrk
Single core verses multi core.
And on multiple cores the intel and AMD Mobile cores win out easily despite a one or two node advantage for apple.

Hype train derailment in action , fastest mobile CPU my ass.
For a 10w SoC with an igpu that's fatser than a 1050ti those are still nice numbers. The ryzen 7 5800u might be able to match the single core cpu perf with 15w, but i don't know if rdna2 is going to be as efficient.

(and Apple did said fastest single core for a low power cpu*, the tiger lake can either be a 28w or a 12w part)

Posted on Reply
#17
Vya Domus
dyonoctis
i don't know if rdna2 is going to be as efficient.
RDNA1 is about 50% more efficient than Vega and RDNA2 is 50% more efficient than RDNA2.

Yeah, it's going to be much, much more efficient. Regardless, efficiency in GPUs isn't that impressive because what you can always do is make a really wide and low clocked GPU, which Apple did. Vega iGPUs run at over 2 Ghz, that's actually way, way more impressive than anything else.
Posted on Reply
#18
Endeavour
theoneandonlymrk
Single core verses multi core.
And on multiple cores the intel and AMD Mobile cores win out easily despite a one or two node advantage for apple.

Hype train derailment in action , fastest mobile CPU my ass.
You are forgetting about a couple of things:
- These are low-power CPUs. The new M1 Macbook Air is fanless and runs cooler than the previous Intel chip they used, which btw was way slower.
- The GPU is also very nice. First benchmarks put it above Intel Xe, MX350 and anything that AMD has in that power envelope.

It also has hardware acceleration for many video codecs, apparently the M1 is as fast as a Mac Pro transcoding video.
Clearly a big win for Apple.
Posted on Reply
#19
theoneandonlymrk
dyonoctis
For a 10w SoC with an igpu that's fatser than a 1050ti those are still nice numbers. The ryzen 7 5800u might be able to match the single core cpu perf with 15w, but i don't know if rdna2 is going to be as efficient.

(and Apple did said fastest single core for a low power cpu*, the tiger lake can either be a 28w or a 12w part)


So look at your argument.

"Our high performance core is the world's fastest CPU core"

They have forgotten your caveats.
And I doubt Rdna2 isn't more efficient.

Looking at it your way the M1 can equal the better chips with ONE core but get beat out using multiple cores , hmnn that power limit that's never going away on the latest node precludes them Ever competing on multiple cores and where is software headed.
GPU is unproven and 100% unicorn until we see some comparable in game benches let's see some AAA Cod running on it or fortnite, err hmnn.
Posted on Reply
#20
techisfun
The M1 does appear to have the most efficient cores, as Apple said.

In terms of efficiency, I doubt PC hardware will be able to catch up to Apple Silicon hardware. PC hardware is far less integrated by design, which makes it less efficient.
Posted on Reply
#21
Caring1
techisfun
The M1 does appear to have the most efficient cores, as Apple said.

In terms of efficiency, I doubt PC hardware will be able to catch up to Apple Silicon hardware. PC hardware is far less integrated by design, which makes it less efficient.
Are you saying Apple don't make Personal Computers? :p
Posted on Reply
#22
Chrispy_
If the M1 does anything, it might finally get Microsoft to hurry the hell up and ditch all the legacy crap that is bogging down x86 Windows.

With x86 and Windows playing a chicken-and-egg game, it's never going to become a more streamlined architecture until someone takes the first step. AMD and Intel can't afford to cull features in hardware until they are dropped from the OS, and Microsoft is still unwilling to completely let go of 32-bit OS even in this day and age....
Posted on Reply
#23
theoneandonlymrk
Caring1
Are you saying Apple don't make Personal Computers? :p
"What's a personal computer"

That's a line I remember from an apple advertisement.

They make apple's not PC's.
Posted on Reply
#24
dyonoctis
theoneandonlymrk
So look at your argument.

"Our high performance core is the world's fastest CPU core"

They have forgotten your caveats.
And I doubt Rdna2 isn't more efficient.

Looking at it your way the M1 can equal the better chips with ONE core but get beat out using multiple cores , hmnn that power limit that's never going away on the latest node precludes them Ever competing on multiple cores and where is software headed.
GPU is unproven and 100% unicorn until we see some comparable in game benches let's see some AAA Cod running on it or fortnite, err hmnn.
True. I tend to forget that this isn't a classic 8 core, but 4+4. So there's a bit of "cheating" there. It's a design philosophy that works well for those machine, but AMD already said that they are not interested in an Hybrid design.

Well, on paper AMD got the tech to make a great soc: zen3 core (low power zen 2 was already impressive in it's own right), rdna 2 with the AV1 acceleration...machine learning for the consumer is the thing that they don't do yet, but it's a whole mess on windows (intel with their odd deep link, and nvidia tensor cores are only for "beefy" laptops.) But then there is the software side. Open cl being what it is, cuda is the only thing close to the metal api on windows. Adobe and Nvidia have a love story where AMD is a third wheel at best.
Posted on Reply
#25
Valantar
Impressive, especially considering R23 is a continuous, throttling-inducing load designed to bypass short-term performance boosts. 3.1GHz isn't particularly impressive, though the IPC on show clearly demonstrates that at least in some workloads you can make up for clock speeds through a wider core. AnandTech's recent A14 article does show how Apple is managing some things that current X86 designs aren't even close to in terms of architectural width and caches, so it'll be really interesting to see how this in turn affects future X86 development.

Also, of course, it kind of demonstrates what can happen if you give a chip development company unlimited resources. No wonder they're doing things nobody else can.
Posted on Reply
Add your own comment