AnandTech delved deep into the new M2 chip announced yesterday, focusing in particular on the performance of the M1 chip against the M2. These chips are available in the all-new MacBook Air and in an updated version of the initial 13-inch MacBook Pro.
The site says that while Apple has been as restrained as ever when it comes to chip specifics (such as clock speed), we already know a lot …
M1 vs. M2 chip: Similar to A14 vs. A15
AnandTech’s Ryan Smith says the overall upgrade looks similar to that of the A14 to A15 chip.
From a high level, there have been a limited number of changes to the M2 – or at least as many as Apple wants to reveal at the moment – with a focus on several critical areas compared to the bonus that was the original M1 SoC. Although all this is in advance or before further revelations from Apple, or get practical time with the hardware itself, the M2 looks a lot like a derivative of the A15 SoC, similar to how the M1 was derived from the A14. As a result, at first glance, the M1 to M2 superstructure looks quite similar to the A14 to A15 superstructure.
Apple said the M2 chip is based on a “second-generation 5nm process”, which almost certainly means TSMC’s 5NP process. This increases the performance without increasing the density of the transistor and this is supported by the main illustration showing that the M2 chip is physically larger than the M1 (image above).
M1 vs. M2 in numbers
Smith helpfully gathered all the data that Apple shared in a comparison chart.
Effective cores are more powerful
AnandTech suggests that a key difference between the M1 and M2 chips is that the latter has more powerful efficiency cores.
The M2 retains the configuration of Apple’s 4 performance plus 4 performance. Apple does not disclose which generation of processor cores is used here, but based on performance and time expectations, there is every reason to believe that these are the cores of Avalanche and Blizzard, which were first introduced on the A15 […]
Avalanche offers only modest productivity gains as Apple invests most of its improvements in improving overall energy efficiency […]
Based on what we’ve already seen on the A15, this major update in this generation is at the heart of performance. Blizzard’s processor cores are increasingly behaving like not-so-small cores, offering relatively high performance and a much broader backend design than we see with other Arm performance cores.
35% faster GPU, but at the cost of power
Overall, the M2 GPU looks more energy efficient – but if you want to use the full power, then it will use more power than the M1.
Apple advertises two figures for M2 GPU performance. At iso power (~ 12W), M2 should provide 25% faster GPU performance than M1. However, the M2’s GPU may, for better or worse, also draw more power than the M1’s GPU. At its full power of 15 watts, Apple says it can provide 35% more performance.
Importantly, the main M2 chip receives support for Apple’s ProRes and ProRes RAW codecs, which are only available for the Pro, Max and Ultra versions of the M1.
50% more memory bandwidth
Another thing that the base M2 occupies from the more powerful versions of the M1 chip is the support for LPDDR5 memory, as opposed to LPDDR4 for the base M1. This gives the chip about 50% more memory bandwidth, which will definitely help GPU performance.
No I / O improvements
Smith says the specifications provided by Apple for USB and other I / O protocols seem unchanged from the M1. Apple has said nothing about the PCIe capabilities of the M2, so that’s likely to remain the same.
As always with the AnandTech tracks, it’s worth reading in full.
FTC: We use automated affiliates to earn revenue. More ▼.
Check out 9to5Mac on YouTube for more Apple news:
Add Comment