Intel claims new i9 is faster than M1 Max

Most people I've seen use laptops near chargers, or at least within 2 hours of the nearest charging opportunity. Sometimes people travel and need more, but I don't think it's that common to need eight hours of charge at maximum performance.

Don't get me wrong, the M1 is an engineering marvel and as Apple's competitors move to a similar node size I hope they too will get these power usage benefits some way or another, but I don't think the average consumer needs all the features the M1 offers.

If Intel can come up with a laptop that's faster than the M1 at two thirds the price with the only downside being that you only get four hours of battery out of it with all cores clocked to their limit, then I don't see why most people who need the horsepower would pay extra for the M1, especially with its restrictions on what operating systems it can run comfortably. The impressive efficiency of the M1 simply isn't that pressing a matter for most people.

I hope Intel is right, and I hope they beat Apple. We've seen AMD overtake Intel and then saw their innovations slow to a crawl while they were ahead. Apple might end up doing the very same if there is no competition in this space. If Intel, AMD or Qualcom produce a chip even better than the M1, we can all only stand to gain from this.

https://www.anandtech.com/show/17024/apple-m1-max-performanc...

Here are some power, prices, and other things can be viewed here about them.

https://ark.intel.com/content/www/us/en/ark/compare.html?pro...

Its impressive, but:

Generally, take Intel's marketing material with a grain of salt. They're notorious for exaggerating, cherry-picking, and out-right lying in marketing materials.

Related to that: While both the M1 Max & 12900HK have on-board iGPUs, the M1 Max has an especially powerful GPU for its class; one of the best iGPUs ever produced. That's going to contribute massively to package power draw, which is what they're measuring on the X-axis; if the Xe G7 can't compete, then these graphs are disingenuous to the overall experience some customers would be looking for (alternatively, other customers will be going dGPU anyway, so it doesn't matter).

Related to that: Its unclear from the chart whether this is per-core relative perf or entire package and multithreaded perf. I'm guessing the latter, due to the size of that x-axis arc and because its roughly where we'd expect a 12th gen 14/20 configuration to land; that's an obscene amount of threads for mobile, far outpacing the 10/10 in M1 Max. In fact, I'd argue: if this is a multithread test, a 40% increase in cores w/ a 100% increase in SMT threads only arriving at a miniscule (~5%?) jump in perf at similar power draw is average, not good. The single-core perf, even on their high-draw cores under load, may be rather poor; so its end-of-day effectiveness may be very workload dependent.

Overall, I'm hopeful the real-world performance matches the expectations they've set, and I'm bullish on Intel's strategy. Chip manufacturing is hard, but TSMC is becoming a bottleneck for both Apple & AMD. Hyper-optimizing large processes may work out for them; but the proof will be in the pudding.

I'm a bit skeptical this is true

2. This is from witeken. A Well known Intel "supporter".

AlderLake is good, but claiming it offer more Pref / Watt than Apple's M1 Max on a node that is generation behind would require some independent testing to verify . Because all the data known so far doesn't seems to suggest this. Especially in the case of Single Core Performance.

[1] The metric used is the geometric mean of an "n-copy" SPECrate run of the C/C++ integer benchmarks in SPEC CPU 2017. You can find the M1 SPECrate 2017 results here

https://www.anandtech.com/show/16252/mac-mini-apple-m1-teste...

Currently using the M1 mini as a display head with VSCode connected to the PC over Thunderbolt, as a backend. Seems like the best of worlds. M1 Pro is probably going to get sold.

I think a lot of the Apple efficiency gains also come from the all-in SoC design (i.e. memory etc. all in the same chip). I guess Intel is trying to make the same play here but I'm sceptical they'll have as much success in the near term simply because they're reliant on OEMs to pretty much redesign their products around that so it could be several years before all the manufacturers cycle their product lines around. Not to mention many PC fans _like_ the fact they can upgrade the RAM in their laptops SODIMM slots.

The 12900k (desktop) pushes an obscene 8p+8e 16c/24t design. Compare this to M1 Max's 8p+2e 10c/10t. M1's per-core perf lead, if it even exists, won't overcome that.

And yeah, its an obscene miss if one overlooks that the 12900k can draw 250 watts, versus M1 Max's ~50w (?). But Apple sells desktops too; they're loved by the Pros Apple spent years neglecting.

There are rumors that Apple is prepping a "M1 Duo" or "M1 Quad" variant of M1 Max for an upcoming Mac Pro. But the wild part is two-fold: First, a "Duo" variant (16p+4e 20c/20t) still may not match the 12900k, and while a "Quad" variant would surpass it (32p+8e 40c/40t), we'd be talking about 12900k levels of power draw anyway. And arguably a chip like that shouldn't be compared to i9; it should be compared to the Xeons its replacing in the Mac Pro.

Apple's M1 is an obscene chip; but I'm fearful of expectations going forward. Pros were exuberant when it was announced, because it was an indication that Apple has started Caring about them after over a decade of being neglected. But if Apple continues the pattern they started with M1 by waiting a year or more to sieve the iPhone core architecture each year all the way down to a proper high-end part, its not obvious to me that pros are better off. The issues Pros were facing on Apple hardware, up to this point, were really Intel's fault (and Apple's ability to integrate Intel's chips in an effective manner); but AMD forced Intel into high gear, and now to some degree, for pros, it feels like we're re-living the same story again. Apple in-housing their chips does not fix their perpetual de-prioritization of pro workloads; if anything it exasperates it, because now we're at the bottom of the totem pole for Apple's chip production monopoly each year, rather than at least hoping Intel could service us.

Makes for a good marketing slide. Does not say a whole lot about the whole package, or every other workload besides this one that laptops might run. Say for example, single thread power efficiency, or anything that needs a GPU and won't drain the battery in 30 minutes.

They also threw out the ability to say "If your company/tasks don't work with MacOS, you can always dual-boot full-fat Windows."

They have to be betting that their platform is still big and compelling enough to keep bringing in users and developers to replace anything they lose to the x86-64 abandonment.

I tend to think that there's no real magic secret to ARM for low power, it's more that we've spent the last 20 years optimizing them for low-power devices while x86 was traditionally performance-at-all-cost.

It’s not hard to outperform an M1 Max. Just use a ton of cores and high frequencies.

But that uses a ton of battery and puts off a ton of heat.

That’s my favorite thing about my M1 Mac. It has no fan, doesn’t get hot, has TONS of battery, and still performs well.

If Intel can match/beat Apple at similar power/thermal levels THATS an achievement.