Benchmarks show that Intel's Alder Lake chips aren't M1 Max killers
New benchmark tests confirm that the Alder Lake Core i9 processor features significant performance gains compared to its predecessor, but the flagship Intel chip is still not going to unseat the M1 Max as an overall package.
Apple's M1 chip series
Intel had previously claimed that its Core i9 processor beat out Apple's most powerful M1 Max chip. But although recent PCWorld benchmarks analyzed by Macworld confirm significant gains in performance, there are a few key caveats.
The Core i9-12900HK processor in an MSI GE76 Raider, for example, had an average Geekbench 5 multi-core score of 12,707, about 4% faster than the M1 Max. The difference is well within the margin of error for Geekbench testing.
Apple's M1 Max achieved a single-core Geekbench 5 score of 1,774. The Alder Lake chip had a score of 1,838, about 3.5% faster. Again, that's within the margin of error and basically a tie between the two chips.
Although OpenCL graphics benchmark testing showed a much more dramatic difference in graphical performance, it's important to keep in mind that PCWorld tested laptops with pricey discrete GPUs.
Now, the caveats. For one, the PC benchmarks are all for high-end laptops that cost much more than an Apple device. PCWorld's test device retails for $3,999, about 1.5x as much as the 14-inch MacBook Pro with M1 Max chip that performed nearly as well. It's not presently clear what the MSI model without the Nvidia 3080 GPU will cost.
The biggest difference is power efficiency. The GE76 Raider achieved about 6 hours of offline video playback in PCWorld testing. That's significantly lower than the MacBook Pro's 17 hours. As far as power draw from a wall outlet, the Alder Lake chip was consistently in the 100-watt range and spiked as high as 140 watts. AnandTech testing of the M1 Max found that its draw wa about 39.7 watts.
Anecdotally, from users that AppleInsider has spoken to, the fans are very loud in every operating condition, worsening when compared to the M1 Pro under load.
In other words, the Alder Lake chips are impressive for Intel processors. However, when you compare them to the power efficiency and cost effectiveness of Apple's M1 series, any performance advantages look much less significant.
Read on AppleInsider
Apple's M1 chip series
Intel had previously claimed that its Core i9 processor beat out Apple's most powerful M1 Max chip. But although recent PCWorld benchmarks analyzed by Macworld confirm significant gains in performance, there are a few key caveats.
The Core i9-12900HK processor in an MSI GE76 Raider, for example, had an average Geekbench 5 multi-core score of 12,707, about 4% faster than the M1 Max. The difference is well within the margin of error for Geekbench testing.
Apple's M1 Max achieved a single-core Geekbench 5 score of 1,774. The Alder Lake chip had a score of 1,838, about 3.5% faster. Again, that's within the margin of error and basically a tie between the two chips.
Although OpenCL graphics benchmark testing showed a much more dramatic difference in graphical performance, it's important to keep in mind that PCWorld tested laptops with pricey discrete GPUs.
Now, the caveats. For one, the PC benchmarks are all for high-end laptops that cost much more than an Apple device. PCWorld's test device retails for $3,999, about 1.5x as much as the 14-inch MacBook Pro with M1 Max chip that performed nearly as well. It's not presently clear what the MSI model without the Nvidia 3080 GPU will cost.
The biggest difference is power efficiency. The GE76 Raider achieved about 6 hours of offline video playback in PCWorld testing. That's significantly lower than the MacBook Pro's 17 hours. As far as power draw from a wall outlet, the Alder Lake chip was consistently in the 100-watt range and spiked as high as 140 watts. AnandTech testing of the M1 Max found that its draw wa about 39.7 watts.
Anecdotally, from users that AppleInsider has spoken to, the fans are very loud in every operating condition, worsening when compared to the M1 Pro under load.
In other words, the Alder Lake chips are impressive for Intel processors. However, when you compare them to the power efficiency and cost effectiveness of Apple's M1 series, any performance advantages look much less significant.
Read on AppleInsider
Comments
Odds that PC cultists will now stop braying about the "Apple tax" and that Mac users are mindless sheep overpaying for underperforming computers: < 0.
Yes, thank you, this as well to me is the biggest difference (though there are many big differences), especially with regard to a laptop that is expected to do intensive work such as video editing. CPU throttling to deal with heat dissipation is a very real thing that is seldom taken into account by PC cultists desperate to slag off Apple Silicon. Typically they are thinking about gAmInG first and foremost, to the extent that they consider the effects of heat dissipation at all they are either assuming extraordinary cooling solutions or in the case of a laptop, perhaps they are thinking about using it while seated in a meat locker.
Yesterday I was browsing through the Mac laptops on offer in the Apple Refurb Store. IF you're OK with an Intel CPU and IF you only need it for run-of-the-mill tasks rather than serious photo/video/3D work, there were some amazing bargains. In one case, a 2019 MB Pro for around $1800 instead of the original $2800.
But, I consider any Intel-powered Mac a total non-starter for what I need and I suspect that the vast majority of those in the market for a new Mac think so as well. They just seem like a dead-end at this point if you're committed to the Mac platform.
I wish I could think of a reason to justify buying such a machine. I've even given though to how cheap it would have to be to make me bite; the number I arrived at was somewhere in the mid-hundreds. I make my living with my Mac computers and I am accustomed to them having a useful life for my work of at least 10 years. I can't imagine an Intel-powered Mac - especially a laptop - being useful to me for my work much beyond the next five years.
Let me get this economics right - you have to pay 1.5 times more for an intel laptop to perform as well as M1 Max Pro and you have to pay for more electricity because it requires consuming at least twice more power to get similiar performance.
So, in terms of cost-benefit analysis, M1 Max Pro is a clear winner if performance is the main concern. No companies would be in the right mind to pay for those Intel laptops as it would cost them a lot more to buy them and also cost them more in energy usage.
I know I already pointed this out in the comment immediately above yours, but I could not help myself. Right out of the gate, AS has been f'ing killing it and I'm positively giddy about what we'll see in the future. The silver lining for Mac haters is that they'll lose a waist size or two from all the goalpost-moving they'll be doing.
disclaimer: I started working with and on computerized systems in the middle 70's but the only game I play is Toy Blast on my older iPad.
from the Macworld article:
59,774 Apple M1 Max 32 core GPU
143,594 nVidia 3080 Ti
240% faster, presumably not 'within margin of error'
Even more pronounced seem the desktop options (AMD) with the relatively inexpensive nVidia 3060 outperforming passmark scores for many higher priced cards as well as having 12GB VRAM www.bestbuy.com/site/evga-nvidia-geforce-rtx-3060-xc-gaming-12gb-gddr6-pci-express-4-0-graphics-card/6454329.p?skuId=6454329
I understood Apple is working on a 'boost' option which may help, and will presumably also ramp up the power and fan requirements...?
What does an Intel Core i9 do that requires it to be as power inefficient in the same processing circumstances as an AS M1 Max?
I'm assuming the architecture is radically different, but what stops Intel from changing to that architecture?
If you need the power of a nVidia 3080 Ti for your work then yes, perhaps the M1 Max isn't for you. Later this year we should see the AS-powered Mac Pro, I'm willing to wager right now that it's going to compare very favorably to the best Intel+nVidia GPU combos and even beat them out in specific categories of comparison.
Intel's "Core" line was built in part because they were having trouble getting older designs to go faster. They built a new internal architecture which is a lot simpler, then added a sort of translation layer which takes the more complex instructions and breaks them into "micro-operations". That approach has served them well, but there's only so much you can do in hardware without removing instructions and simplifying what the processor offers to software.
ARM is radically simpler than x86.
This gets a little complicated. With Apple's "unified memory", their GPU cores have access to everything in the whole up-to-64-GB of RAM. A lot of non-gaming uses of GPUs involve manipulating huge datasets. If the data you're working with is bigger than can fit in the card's VRAM (12 GB for the 3080, 24 GB for the 3090), you're basically going to be swapping between VRAM and normal RAM. That seriously hurts performance and is why Nvidia has been making their compute-specific cards (Tesla, until that brand was retired in 2020) with 12+ GB per GPU since 2014.
For math across large datasets, the M1 Max can actually beat the RTX 3080 just because it doesn't have to spend so much time shuffling data around.
This is also the idea behind AMD's Radeon Pro SSG (Solid State Graphics). They added a 2 TB NVMe SSD to use as on-card swap space for VRAM. It's meant for video editing and allows you to keep a huge chunk of the video all on the card.