Is anyone else dissapointed in single core performance of the M1 Pro/Max?

[ecrispy]

The new M1 Pro/Max have worse single core perf than the old M1 (in the 13" MBA). This is quite surprising and a bit of a let down. It seems Apple focused primarily on the gpu (and of course the multi core perf is higher).

Why does this matter? Because every single web app, basically every web site you visit, as well as web based apps (such as those built using Electron) use Javascript, which is single threaded and constrained by single core perf. You can see this in Speedometer and other real world web based benchmark scores, where the old MBA beats out the new Macs despite having fewer power cores.

 

[Love-hate 🍏 relationship]

The new M1 Pro/Max have worse single core perf than the old M1 (in the 13" MBA). This is quite surprising and a bit of a let down. It seems Apple focused primarily on the gpu (and of course the multi core perf is higher).

Why does this matter? Because every single web app, basically every web site you visit, as well as web based apps (such as those built using Electron) use Javascript, which is single threaded and constrained by single core perf. You can see this in Speedometer and other real world web based benchmark scores, where the old MBA beats out the new Macs despite having fewer power cores.

speedometer 2.0 ? is this relying on single core only ? cuz i tried the mbp 14 and 16 and they score way higher than the m1

 

[petvas]

Single Core performance is basically identical between M1, M1 Pro and M1 Max.

 

[ecrispy]

speedometer 2.0 ? is this relying on single core only ? cuz i tried the mbp 14 and 16 and they score way higher than the m1

 

[Love-hate 🍏 relationship]

Single Core performance is basically identical between M1, M1 Pro and M1 Max.

and thats disapointing .

 

[Arctic Moose]

I haven’t received mine yet, so cannot comment if it will be noticeable or not, but yeah, I find it mildly surprising and a little annoying that the M1 Pro/Max isn’t clocked higher than the M1 considering the difference in cooling.

 

[petvas]

and thats disapointing .

If you say so. Me and many others disagree. I guess there are many Intel based computers that would fit your needs better.

 

[crazy dave]

I haven’t received mine yet, so cannot comment if it will be noticeable or not, but yeah, it would seem reasonable that the M1 Pro/Max would be clocked higher than the M1.

It’s not. Single core performance should be nearly identical to the M1 - maybe slightly better in memory intensive workloads. The cores are the same - what’s changed is the number of them, the cache sizes, and the memory subsystem feeding them. Interesting that these scores are lower. Definitely worth investigating.

Apple is unlikely to follow AMD and Intel’s model of segregating by clock speed. They have the single core performance they want. What matters then is thermals (sustained performance), and the number of such cores.

 

[Love-hate 🍏 relationship]

thanks .funny i dont get such a high score on my mba m1 ,in fact i reach around 230 ,while on the 14 and 16 i was averaging 280 so...

however i must point out that unless im missing something here,chrome and most modern browser do actually rely on multi threading and multi core ,a LOT . ive read a comment in the video you sent and someone points out that for browsing its likely the chip relies on the efficiency cores more than P cores ,which would explain the lower score on the m1pro . after all the m1 has 4E which equals to 1.3P while the m1pro has only half of that (2E=0,7P)

mind you ,i think the scores on both are actually the same ,not lower.idk what the hell is wrong in this video but again
1)i dont get such high scores on my mba
2)i didnt get such low scores in mbp 14 base and 16

still ,in the best case,they both perform the same ....which is weird for a pro chip indeed

 

[petvas]

Add to that the better GPU. I would suggest the article at Anandtech about the M1 Pro and Max: https://www.anandtech.com/show/17024/apple-m1-max-performance-review

 

[Love-hate 🍏 relationship]

If you say so. Me and many others disagree. I guess there are many Intel based computers that would fit your needs better.

nah bud ,the single core perf is still very high ,higher than most intel chips in fact .im just surprised they didnt clock the m1 pro/max any higher however

 

[Love-hate 🍏 relationship]

Add to that the better GPU. I would suggest the article at Anandtech about the M1 Pro and Max: https://www.anandtech.com/show/17024/apple-m1-max-performance-review

ive read it already .OP isnt saying the new chips are ****,only surprised the single core remains the same nay worse .whats impressive ( but on the other hand its actually pretty boring) is how apple scaled things up so well ,so symmetrical

 

[petvas]

nah bud ,the single core perf is still very high ,higher than most intel chips in fact .im just surprised they didnt clock the m1 pro/max any higher however

This isn't the way Apple thinks about chip design. What Apple achieved is a great performance while at the same time keeping power requirements very low. It's incredible that the new MacBooks have the same performance when used on battery or plugged in.

 

[JMacHack]

The new M1 Pro/Max have worse single core perf than the old M1 (in the 13" MBA). This is quite surprising and a bit of a let down. It seems Apple focused primarily on the gpu (and of course the multi core perf is higher).

Why does this matter? Because every single web app, basically every web site you visit, as well as web based apps (such as those built using Electron) use Javascript, which is single threaded and constrained by single core perf. You can see this in Speedometer and other real world web based benchmark scores, where the old MBA beats out the new Macs despite having fewer power cores.

I recommend Alder Lake(tm) processors by Intel(tm). They are going to be superb with their architecture improvements and node improvements on Intel 7(tm) technology. Furthermore their power efficiency will be increased with their new big.little design using their Intel(tm) Atom(tm) cores. Which are excellent for embedded devices as well!

(Where’s my ****ing paycheck Intel?)

 

[crazy dave]

nah bud ,the single core perf is still very high ,higher than most intel chips in fact .im just surprised they didnt clock the m1 pro/max any higher however

They could’ve but then you start running much more power to achieve that and lose the efficiency of the chip. That’s not Apple’s design philosophy around their SOCs. As I said in my last post, they’re not likely to follow the Intel/AMD model of segregating by MHz as well as cores/memory. They right way to think about it is that everyone gets the best single core. Then it’s a matter of how many more cores, how much more memory, and how big a GPU do you want?

Same with the GPU in fact. Clock speed is unchanged across models - though the M1 Max might ramp up to top speed a touch slower, it still has the same top speed. It just also has more cores. And more memory.

 

[Love-hate 🍏 relationship]

They could’ve but then you start running much more power to achieve that and lose the efficiency of the chip. That’s not Apple’s design philosophy around their SOCs. As I said in my last post, they’re not likely to follow the Intel/AMD model of segregating by MHz as well as cores/memory. They right way to think about it is that everyone gets the best single core. Then it’s a matter of how many more cores, how much more memory, and how big a GPU do you want?

Same with the GPU in fact. Clock speed is unchanged across models - though the M1 Max might ramp up to top speed a touch slower, it still has the same top speed. It just also has more cores. And more memory.

ye,i hear what you and petvas are saying

 

[War833]

Sounds fine to me. No one ever said the pro-line M1s would speed up execution within a single browser tab. I don't think the expectation makes sense: it is still M1.

"Pro" in the name is alluding to "professional" apps and use cases, which will certainly tend to (and need to!) leverage multiple CPU cores and threads.

 

[ecrispy]

Why are people trying to turn this into Intel vs Apple? I'm simply making the point that for certain use cases the older M1 performs better, and that use case happens to be not some trivial benchmark but web performance and single core.

As for 'pro' a MBP should perform better than a MBA in every single category (except portability, size, power draw) no questions asked, not just multi core/gpu.

 

[gpat]

Why are people trying to turn this into Intel vs Apple? I'm simply making the point that for certain use cases the older M1 performs better, and that use case happens to be not some trivial benchmark but web performance and single core.

As for 'pro' a MBP should perform better than a MBA in every single category (except portability, size, power draw) no questions asked, not just multi core/gpu.

The fact is, virtually any application benefits from the multicore performance.
This debate is not even new. When I got my first MBP in 2011, with the Sandy Bridge chips, the 13" had dual-core and the 15" had quad-core CPUs. The single-core performance of the 13" was comparable to the 15" but the latter still was noticeably faster in every use case.

 

[JimmyjamesEU]

Why are people trying to turn this into Intel vs Apple? I'm simply making the point that for certain use cases the older M1 performs better, and that use case happens to be not some trivial benchmark but web performance and single core.

As for 'pro' a MBP should perform better than a MBA in every single category (except portability, size, power draw) no questions asked, not just multi core/gpu.

All the figures I’ve seen show identical ST perf with all M1 chips. Where are you seeing worse numbers?

 

[Adreitz]

As for 'pro' a MBP should perform better than a MBA in every single category (except portability, size, power draw) no questions asked, not just multi core/gpu.

Why? If Apple is able to achieve maximum performance even on a low end chip, would you want them to underclock it or something to provide artificial product differentiation? You are assuming that Apple can provide more single-core performance in this product cycle than they did, but that is a pure assumption.

 

[newellj]

and thats disapointing .

I have a Pentium 5 Windows machine somewhere in the attic that will take care of 125% of your needs.

 

[gotohamish]

I haven’t received mine yet, so cannot comment if it will be noticeable or not, but yeah, I find it mildly surprising and a little annoying that the M1 Pro/Max isn’t clocked higher than the M1 considering the difference in cooling.

I think it's clear that Apple's plan for this chip (and subsequent ones) is not to be judged by clock speed, otherwise we fall into the 1990s Intel bull****. It's clear they've found a better way to design and execute a chip design so expanding upon and exploiting that will be the initial focus of this product.

 

[MauiPa]

Is this a joke thread? The single core performance rocks. I think Intel has 1 chip (@135w/270w-thats a desktop or a really heavy laptop with low battery) that barely, barely, barely, ever so narrowly edges it out. So hard to argue with success

Also a benchmark is only as good as the software measuring it and the persons knowledge of how to properly measure it

 

[yitwail]

I hope everyone who’s disappointed like OP cancels their order so maybe I’ll get mine sooner.