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

Intel claims new i9 is faster than M1 Max

intc.com

Post reply on HN
Print view View original

61–70 of 118 posts

Re: Intel claims new i9 is faster than M1 Max

#61

Post by Zircom »

hamandcheese wrote: post #25
jeroenhd wrote: post #15

Earlier quoted context omitted.

Depending on the workload: does it need to? 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 the…

I am always within 1 minutes of a charger. My i9 MacBook still dies on me all the time. Get to 5% and go to the bathroom? Oops, it died, and I can’t join my next meeting on time. Start a call at 10% battery? Will definitely have to interrupt to go plug in. I want performance and battery.

If you're letting it get to 5% when you're within 1 minute of a charger I don't think a more efficient CPU is gonna help you, you're just gonna end up leaving it off the charger for longer and still find yourself in same exact situations, just postponed a couple extra hours or so than they would've happened.

Re: Intel claims new i9 is faster than M1 Max

#62

Post by ksec »

deepnotderp wrote: post #12

To all the commenters: This is claimed on a power adjusted basis: https://mobile.twitter.com/witeken/status/147844103741682893...

1. This is a slide from Intel. And they dont mention what sort of performance. Edit [1]

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...

Re: Intel claims new i9 is faster than M1 Max

#63

Post by Gigachad »

jeroenhd wrote: post #15
schappim wrote: post #9

But at what thermal, power and monetary price? Edit: @deepnotderp[1] found the power adjusted basis: https://mobile.twitter.com/witeken/status/147844103741682893... [1] https://news.ycombinator.com/item?id=29802359#29803502

Depending on the workload: does it need to? 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 the…

This feels like a cope tbh. People work around poor battery life because that's the only option until recently. I used to feel similarly but since I got my M1 macbook, there have been several times where the excellent battery life have been great.

Recently I was at an airport a few hours before my flight and I ended up just playing games on a food court table. No need to huddle around one of the few seats with power points. Also great to pick up and move to a different room if the current one is noisy without needing to grab your charger as well.

And even in the office, sometimes there will be a multi hour session in a meeting room which is enough to drain everyone's intel macbooks flat.

Re: Intel claims new i9 is faster than M1 Max

#64

Post by mdasen »

Aperocky wrote: post #47
artursapek wrote: post #10

Earlier quoted context omitted.

Exactly. The M1 is awesome not because of raw horsepower, but because of efficiency.

I love my fanless M1 Air primarily because it's fanless. The 14" pro looks great, but can anyone using it tell me whether the fan ever turns on?

I thought that my fan never turned on. I was curious so I installed a fan meter (https://github.com/exelban/stats). If I'm playing a game and running a windows VM, it does sometimes turn on around 2,000 RPMs. I can't hear it even if I put my ear up to the vents.

So, it doesn't seem to turn on almost ever for me. I've had it for over a month and I've never heard it turn on. I've seen it turn on (via the menu-bar monitor) and tried to listen for the fan and just can't hear anything. I'll be using it with the vents covered by a blanket and it doesn't seem to notice.

It's one of the reasons that I love this machine. My 2020 Intel MacBook Pro would run those fans all the time making lots of noise. A web page would randomly start using a lot of CPU and my battery would drain, things would slow down, and the fans would sing their song. The magic of my new M1 Pro machine is that nothing seems to phase it. It's not like I had a crappy old laptop for comparison. I had a 2.4GHz Intel MacBook Pro that was over $2,000.

I was wondering if the fan would go on and it might go on more if you're doing a lot of high-end rendering, but it doesn't for my usage. IntelliJ, Windows VMs, whatever, it mostly stays off and sometimes turns on, but low enough that I can't hear it even with my ear to the vents. It feels magical.

Re: Intel claims new i9 is faster than M1 Max

#65

Post by nerbert »

howdydoo wrote: post #38
carlycue wrote: post #28

Apple has already won. Even if Intel catches up in efficiency, it doesn't matter. Even if they're 30% faster, it doesn't matter. Apple is in charge of their own destiny with Apple Silicon. That's invaluable.

So Apple is the best regardless of which product is better?

Said like that it sounds ridiculous. That being said, if Apple silicon has the same rate of improvement as iPhone processors, Intel's victory is very temporary.

Re: Intel claims new i9 is faster than M1 Max

#67

Post by Gigachad »

PragmaticPulp wrote: post #13

They're specifically talking about the mobile part here. But it's not hard to believe that it will outrun the M1 Max in multithreaded benchmarks, and likely even single-threaded benchmarks. Intel's latest desktop parts are already faster than an M1 Max by a not-insignificant amount, and this is just a lower-power version. Intel's Alder Lake desktop parts are already surprisingly power efficient (ignoring the heavily…

I'm glad power efficiency is really getting a spotlight recently I tested a new AMD build with a ryzen 5 and a few hard drives and it was drawing 70w idle with a headless linux distro running. Some of this can be blamed on the case fans and hard drives, but even without that it doesn't come anywhere close to what a mac mini would draw.

Re: Intel claims new i9 is faster than M1 Max

#68

Post by caconym_ »

jeroenhd wrote: post #15
schappim wrote: post #9

But at what thermal, power and monetary price? Edit: @deepnotderp[1] found the power adjusted basis: https://mobile.twitter.com/witeken/status/147844103741682893... [1] https://news.ycombinator.com/item?id=29802359#29803502

Depending on the workload: does it need to? 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 the…

Heat seems just as big an issue as battery life, if not bigger. Can i9-12900HK-equipped laptops really exist in the same highly convenient size/weight bracket as the new MBPs and make use of all that power without extreme fan noise, extreme chassis heat, and/or extreme thermal throttling? My past experience with Intel mobile CPUs says no, absolutely not.

Honestly, my past experience with Intel mobile CPUs versus my current experience with my new MBP says I will never buy one of the former again, ever, unless it's otherwise a truly special machine or I have no choice.

I will admit that I'm not really the target market for the big, chunky laptops that can make a 75W+ TDP anything but miserable, because I have a desktop machine that still wipes the floor with anything in that segment. The truth about the M1 Pro/Max SoCs is that they won't give you the absolute hottest performance around in CPU or GPU, but they will give you legitimately great performance along with other attributes that are best-in-class taken together, mainly size, weight, battery endurance, and thermals. And those things do matter to a lot of people.

Re: Intel claims new i9 is faster than M1 Max

#69

Post by dghlsakjg »

thebean11 wrote: post #55
Aperocky wrote: post #47

Earlier quoted context omitted.

I love my fanless M1 Air primarily because it's fanless. The 14" pro looks great, but can anyone using it tell me whether the fan ever turns on?

I have the 16" which has slightly better thermals. When it's in clamshell mode and I'm doing heavy stuff (maybe a zoom call + big compilation + running a few local services) I can feel a tiny bit of warm air coming out. Can't hear anything though.

Great to hear!

I have an i7 16" intel and maxing out a single core will spin up the fans in short order. Maxing out multiple cores is kind of absurd how much noise and throttling happens

Re: Intel claims new i9 is faster than M1 Max

#70

Post by Gigachad »

jeffbee wrote: post #44
PragmaticPulp wrote: post #13

They're specifically talking about the mobile part here. But it's not hard to believe that it will outrun the M1 Max in multithreaded benchmarks, and likely even single-threaded benchmarks. Intel's latest desktop parts are already faster than an M1 Max by a not-insignificant amount, and this is just a lower-power version. Intel's Alder Lake desktop parts are already surprisingly power efficient (ignoring the heavily…

I have an M1, M1 Pro, and Core i7-12700K on my desk. The Intel part is the fastest on single and multi-threaded workloads I care about, and it does not come with the rosetta nonsense that makes it difficult to manage your compilers and libs on macOS. It does come with a different kind of nonsense, namely that Linux doesn't know what to do with the efficiency cores of the Intel part, so you have to either disable them…

The M1 is probably the first time a lot of people have had to deal with cross compiling so the tooling kind of sucks right now but I imagine in a few years it will be seamless.
Post reply on HN