Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

MacBook Pro M1X benchmarks have leaked

tomsguide.com

Post reply on HN
Print view View original

111–120 of 141 posts

Re: MacBook Pro M1X benchmarks have leaked

#111

Post by sudosysgen »

8fingerlouie wrote: post #110
sudosysgen wrote: post #72

Earlier quoted context omitted.

Is it able to use 26.5W while using both GPU and CPU without degrading performance? The answer is no. 26.5W is only for the CPU. If you also need to use GPU then it throttles or consumes more.

It has a maximum power consumption of 39W, with an idle consumption of 6.8W. Both measured “on wall”, so including ram, storage and everything else. Compare it to the previous (Intel) generation that uses 20W idle and 122W under load, while not matching the M1 in neither CPU nor GPU performance. https://support.apple.com/en-us/HT201897

This does not address wether the GPU throttles in high CPU usage scenarios.

That being said, RAM and storage is pretty negligible. LPDDR4/X uses around 0.2-0.5w, and around 0.1-0.05w for storage.

There is also no reason to compare to Intel. The competition for Macs aren't older macs - newer macs are always going to be better than older macs. The competition is to what they could have been if they went for AMD, and to other computers of similar form-factors.

In both cases, you're comparing to AMD, not Intel.

Re: MacBook Pro M1X benchmarks have leaked

#112

Post by sudosysgen »

rbanffy wrote: post #108
sudosysgen wrote: post #70

Earlier quoted context omitted.

AMD still generally outpertforms Apple Silicon despite larger lithographies, so I don't really see it.

> AMD still generally outperforms Apple Silicon despite larger lithographies The single-core benchmarks I saw put the M1 against CPUs with amd64 cores running SMT (which is fair - SMT extracts about 20% of extra parallelism of an amd64 workload, something the M1 does using a humongous reorder buffer on a single thread) with the AMD (and latest Intel) parts showing a slight advantage. They do so, however, at a much hi…

They have a much higher TDP because you are comparing PC parts that are not optimized for power consumption. Their uncore is made using power-inefficient lithographies to save on cost and contribute a ton to power usage.

They also have a lot more cores.

Per high-performance core, M1 macs are tied or less efficient depending on the workload.

Re: MacBook Pro M1X benchmarks have leaked

#113

Post by totalZero »

coldtea wrote: post #65
windexh8er wrote: post #6

Earlier quoted context omitted.

The other thing is RAM. Apple still has delusions of gimping it's buyers into 16/32GB for "Pro" level machines. I'd probably buy a 16" MBP with this chip if I could get it with socketed 64/128GB. But Apple's going to solder it to the board and charge a premium even if they did.

> The other thing is RAM. Apple still has delusions of gimping it's buyers into 16/32GB for "Pro" level machines. I'm pretty sure Apple knows what machines it sells, including to video and audio pros, and knows how many of them buy the 32GB options where they're available (in Intel). Besides "Pro" is just a branding, not a class of machines designed for specific tasks with any specific guarantees. Up until now, "pros…

> "Pro" is just a branding, not a class of machines designed for specific tasks with any specific guarantees.

I agree, and to be fair, there are plenty of professional use cases that are totally serviceable with one external monitor and 16GB of RAM. Not every professional is a YouTuber or big data engineer.

I can't speak for anyone else, but I do like it when the name of a product actually means something, because it gives me confidence in the honesty of the vendor.

Re: MacBook Pro M1X benchmarks have leaked

#114

Post by sudosysgen »

tengbretson wrote: post #85
sudosysgen wrote: post #69

Earlier quoted context omitted.

There is no Macbook with AMD processor because Apple didn't want to make it. Intel is not the leader for 5+ years now.

Let's not get ahead of ourselves. In the notebook space they've been the industry leader for less than 12 months.

This is not the case. The very first Zen laptop parts were far ahead of Intel.

Re: MacBook Pro M1X benchmarks have leaked

#115

Post by Kirby64 »

alexellisuk wrote: post #56

I was surprised how well the 5800X holds up to the new M1 and M1X. Given the boost I felt with my MBA M1, I thought my NUC8i7HVK felt sluggish in comparison and was considering a new PC build - or moving off a "Linux Desktop" to M1X if it was dramatically better than incumbent desktop processors. Seems like I can keep Linux and build a 5800X, and have > 32GB RAM to boot. For those happy with MacOS as a daily drive, t…

Given the TDP difference between the 5800X and this supposed M1X, it's not really fair though, is it?

5800X is a 105W TDP, the M1X claims to be a 45W TDP.

If you scale by TDP, the M1X is over 2x faster in multicore bench.

M1X: 321 score/watt 5800X: 146 score/watt

Re: MacBook Pro M1X benchmarks have leaked

#116

Post by rbanffy »

sudosysgen wrote: post #112
rbanffy wrote: post #108

Earlier quoted context omitted.

> AMD still generally outperforms Apple Silicon despite larger lithographies The single-core benchmarks I saw put the M1 against CPUs with amd64 cores running SMT (which is fair - SMT extracts about 20% of extra parallelism of an amd64 workload, something the M1 does using a humongous reorder buffer on a single thread) with the AMD (and latest Intel) parts showing a slight advantage. They do so, however, at a much hi…

They have a much higher TDP because you are comparing PC parts that are not optimized for power consumption. Their uncore is made using power-inefficient lithographies to save on cost and contribute a ton to power usage. They also have a lot more cores. Per high-performance core, M1 macs are tied or less efficient depending on the workload.

> Per high-performance core, M1 macs are tied or less efficient depending on the workload.

That's not what the benchmarks I see say. AMD's chips with 8 amd64 cores beat the M1, which has 4 big cores and 4 low-power ones. In some benchmarks, the x86 laptop CPUs record higher performance, but at a higher clock and with a higher TDP. I don't have the IPC numbers for either, but with a lot of execution ports, its huge reorder buffer and the less strict memory consistency model, I suspect the IPC to be higher on the M1.

Re: MacBook Pro M1X benchmarks have leaked

#117

Post by gumby »

tonyedgecombe wrote: post #94
gumby wrote: post #83

Earlier quoted context omitted.

There are still a lot of people who need Intel, primarily people doing cloud development and in particular those who aren’t using an interpreted language. I don’t how big this group is as a percentage of Apple customers, but in an absolute sense it’s significant — several $B worth anyway. Also there are people who won’t buy M1 because they are (probably correctly, though I haven’t had any problems) hearing that not e…

They said the transition would be completed within two years. I imagine they have a pretty good idea how many people are using Bootcamp or Windows VM's and have already decided it isn't significant enough to stop them transitioning.

I assumed they meant every Mac in the product line would have an ARM version. I presume a few of the Intel-based SKUs will remain until demand ebbs, but probably not every one (e.g. perhaps only the 16” MBP and the Pro)

Re: MacBook Pro M1X benchmarks have leaked

#118

Post by tonyedgecombe »

gumby wrote: post #117
tonyedgecombe wrote: post #94

Earlier quoted context omitted.

They said the transition would be completed within two years. I imagine they have a pretty good idea how many people are using Bootcamp or Windows VM's and have already decided it isn't significant enough to stop them transitioning.

I assumed they meant every Mac in the product line would have an ARM version. I presume a few of the Intel-based SKUs will remain until demand ebbs, but probably not every one (e.g. perhaps only the 16” MBP and the Pro)

I suspect they won't want Intel hanging around any longer than necessary because it will delay the point where they can stop supporting both architectures in future versions of macOS.

Re: MacBook Pro M1X benchmarks have leaked

#119

Post by faeriechangling »

cromwellian wrote: post #104
8fingerlouie wrote: post #36

Earlier quoted context omitted.

A lot of things will probably beat it at performance, but not at lot of them will beat at GTX 1060 as well as Core i5 performance using only 26.5W of power while doing it. The performance of the M1 is remarkable, but the real killer feature is they managed to push that much performance while reducing power consumption.

That’s great and all but for people who are gamers or doing heavy work with the GPU they’re going to be plugged into power most of the time. I’d rather have a chip that scales to high performance when plugged in and lower GPU performance when I’m on say an airplane or in a cafe, then one whose GPU performance is a half decade behind.

You're bringing up a limitation of the current tech, that it tethers you to a wall, to speak against this new tech. Does a student who has a gap between classes always want to find an outlet somewhere and deal with their computer sounding like it's about to liftoff? Does the video editor offloading some of their workload to GPU always want to find an outlet?

Apple is selling super quiet hypermobile performance here, I see them as occupying a niche with no real competition.

Re: MacBook Pro M1X benchmarks have leaked

#120

Post by washadjeffmad »

totalZero wrote: post #113
coldtea wrote: post #65

Earlier quoted context omitted.

> The other thing is RAM. Apple still has delusions of gimping it's buyers into 16/32GB for "Pro" level machines. I'm pretty sure Apple knows what machines it sells, including to video and audio pros, and knows how many of them buy the 32GB options where they're available (in Intel). Besides "Pro" is just a branding, not a class of machines designed for specific tasks with any specific guarantees. Up until now, "pros…

> "Pro" is just a branding, not a class of machines designed for specific tasks with any specific guarantees. I agree, and to be fair, there are plenty of professional use cases that are totally serviceable with one external monitor and 16GB of RAM. Not every professional is a YouTuber or big data engineer. I can't speak for anyone else, but I do like it when the name of a product actually means something, because it…

Memory latency often has a bigger impact on performance than capacity. Your CPU spends a lot more time waiting around than you'd expect.

With NVMe, I'd rather have 16GB LPDDR4X than 64GB low-JEDEC, high latency DDR3 memory. More RAM is still good in many cases, but it's not vital like it was 15 years ago when you'd end up in swap hell or OOMing constantly over a GB or two.

Post reply on HN