Just ahead of Halloween, Apple is set to unveil the M3 chip line, new MacBook Pros and an updated iMac at a “Scary Fast”-themed event. Also: The company prepares a total overhaul of AirPods; prices for TV+ and other Apple services go up; and the TV app is getting a revamp later this year.
Did they ever lose them?
Depends on what you are measuring/bragging about.
Efficiency is the one that’s still a win for Apple. But raw power has been surpassed by Intel and AMD. Also Apple’s GPU was already surpassed last year with Snapdragon 8 gen 2, and even more with the gen 3.
Plus the upcoming Qualcomm’s chip may be comparable in power efficiency, they claimed 30% less power use at the same performance as the M2 Max. So M3 would need to be much better in that sense to still have bragging rights next year.
Basically, significantly different story from when the M1 released where the gap was bigger. The others are catching up fast.
What’s your source for that?
Searching for benchmark scores on the Snapdragon 8 gen 3 turned up this:
https://www.notebookcheck.net/Snapdragon-8cx-Gen-3-vs-Apple-M2-ARM-based-ThinkPad-X13s-Geekbench-records-show-generational-improvement-but-still-years-behind-Apple-silicon.629767.0.html
And even that article was from before the M2 Pro and Max CPUs came out…
The one that I said could compete with the M series is their upcoming X Elite platform with the Oryon CPU. Here’s a thread from a few days ago about it.
As for the GPU side for which I used the Snapdragon 8 gen 3, you can look the Geekerwan review here.
Qualcomm’s power/efficiency graph was for single core, which seems disingenuous to compare it to the M2 Max, which has the same single core performance as the M2.
This was a bit misleading by Qualcomm. What they didn’t show was the power draw at peak multi-core compared to Apple Silicon. Why? It appears that the Snapdragon X Elite uses twice the amount of power as the M2 Max in for example Cinebench 2024 at approximately the same performance, making the power draw comparable to the M2 Ultra.
And thats relying on things being ‘just benchmarks’.
In real world usage on apple devices you’ve got typically far more performant libraries for the average dev, you’ve got far superior ML, especially on M series chips you’ve got things like the AMX which make a lot of operations desirable for ML literally twice as performant as the competition in many tasks. Fat memory bandwidth helps too of course.
Theres a lot up apple’s sleeves from being so vertically integrated, and I think as per usual it will continue to reflect in the real world experience of users and developers.
Yeah, like someone else replied, they were using the M2 Max for single core instead of the M2. Which obviously paints things in their favor.
I hate all companies doing that. Just like when Apple compares to “the Intel powered Macs” or vs the “best selling PC” (which obviously is gonna be worse) and that stuff.
Obviously it’s all complex. It’s not all lineal. Power draw can be fine for most tasks and then be super high on the top end (kind of like the A17 which is power hungry with those P cores) and that could be fine or not depending on what you need.
We have to wait for the reviews once it’s out. That’s why I wasn’t asserting what they said, just left it at what they claimed and what they could achieve.
On reference Linux build by the way…
Nope, and Qualcomm isn’t changing that either. Not based on chips years away.