The A12Z was an iPad chip, (more or less the same as the iPad Pro's 2018 A12X [+ 1 GPU core]). The M1 is the first Mac chip, so...
The CPU possibly, but if you look more closely you'll see that Apple focused mainly on the power of the e-cores [rather than P-cores] and the gains there are more in the 30-35% range, so actually quite good.
I thing it is funny when people praise 30-40 % better gpu but it has 25% more cores, so without those it would not be much better then M1 and we would have 5-10%.
This is just plain false. The entire core architecture is using the newer cores from the A15 Bionic in the M2.
Because if cinebench isn’t efficient on a platform, you can throw all the cores you want at it and you won’t see much improvement. That Just tells you cinebench is leaving performance on the table for both the M1 and M2. There’s a reason it’s one of the few apps not to show much performance increase.
I believe cinebench performance scales very well with the number of threads on Apple Silicon.
I don't know, but I wish people stopped using that tool to measure SSD performance. SSD is all about random read/write, which this tool doesn't measure.
What is that belief based on? The link I provided shows it doesn’t utilise all the available resources. It’s multi-threaded, but under utilises each core.
It hasn't, MR has been suspiciously quiet when it comes to independent reviews. Which means the MBA will throttle so much faster.
Agreed. But can you imagine how hot an MBA will be with the M2?Even when you run the fans at over 7000RPM to drop the CPU temp by 20 degrees C, the machine doesn't run any faster per Max Tech's testing so I don't believe it is correct to say that the M2 thermally throttles.
As with Max Tech's testing of the entire M1 family, it doesn't looks like Apple allows any M series SoC to draw maximum power (as measured by wattage) to run the clock speed at the maximum rated speed, but instead keeps it a few hundred MHz below that maximum both single and multi core.
This seems to be to allow the SoC to run with either no fans or at the minimum speed possible for as long as possible. And with the number of folks on these forums complaining that any fan speed sounds like a box of anvils being dropped next to their ears, it should not be surprising Apple is following this tack.
it cannot be any hotter than 104-105C
It can't, I'm just exaggerating. However, the fact is, the MBA will be hotter for longer and rapid reach that state given the passive arrangement.
The reviewer did state it seems like Apple's fan curve is broken on the M2 as on the M1 is revs correctly. Also, likely the MBP didn't see throttling as the heat pipes were actively taking heat away to the fan fins which even at extremely low speeds helped.
