The M1 is a great silicon chip . Essentially an “ 10 ” edition of the A14 scrap , it takes the iPhone and iPad C.P.U. and repeat the high - performance central processor cores , GPU cores , and memory bandwidth . The M1 chip is so good it ’s every bit amazing for tablets and thin - and - light laptops as it is for desktops , easy outperforming any compete chip with similar power haul and extend similar performance to processors that use at least twice as much energy .
Now a yr and a half later , and after present three more potent variate of the M1 ( M1 Pro , M1 Max , and M1 Ultra ) , it ’s meter for the next generation . Announced at WWDC and appearing first in the new MacBook Air and 13 - inch MacBook Pro , the M2 is essentially the organization - on - chip we predicted it would be : what the M1 is to the A14 , the M2 is to the A15 . It ’s made of 20 billion junction transistor , 25 percentage more than M1 , and while it ’s still built using a 5 nm manufacturing process , it ’s a novel heighten “ 2d - coevals ” 5 nanometre process .
Here are the most significant mode the M2 is improve over the M1 .
M2 vs M1: CPU
The M2 replicate the high - performance CPU cores from the A15 , for an eight - core setup of four eminent - functioning nub and four high - efficiency Congress of Racial Equality . In that esteem , it ’s just like the M1 .
But there are some architectural improvements . On the carrying out core , the share L2 cache has grown from 12 M to 16 MiB , and the clock speeds can go a little high . The efficiency cores have the same cache as the M1 but are given other architectural improvements ( likely , higher peak clock speeds and debauched store access , as in the A15 ) .
Together , Apple say this gives the M2 an 18 pct greater total central processing unit performance than M1 . This mean you may likely expect Geekbench 5 CPU test results somewhere around 8,800 - 9,000 . That ’s essentially on par with a Ryzen 7 3800X desktop central processor at around 20 percentage or less of its ability consumption .
As a point of denotation against the latest mobile low - power chip , Intel ’s best current ultraportable CPU , the Core i7 - 1255U , scores just under 7,000 while using more than twice the power . There are definitely faster laptop computer processors available from both Intel and AMD , but they use dramatically more mightiness and would be well equate against M2 Max or M2 Ultra , when they arrive .
Apple
M2 vs M1: GPU
The A15 made an interesting change from the A14 before it . The GPU essence enumeration increased from 4 to 5 , but that 5th core is only enable in the iPhone 13 Pro and Pro Max . The M2 double up the GPU cores from the A15 ( as the M1 did over the A14 ) , and so it is usable with up to 10 GPU cores . The entry - stage MacBook Air , however , has only 8 GPU cores enabled .
Simply having 25 percent more GPU cores , one would carry GPU performance to be at most 25 percentage best . But many graphics performance tasks are set by memory board bandwidth , and M2 give a freehanded improvement there . Together with other culture ( probably a higher maximum clock stop number enabled by the refined manufacturing process ) , Apple says GPU performance is up to 35 pct good than M1 , but business leader consumption has run up a scrap , too . In fact , Apple ’s chart highlight the 35 percent carrying out profit but picture a power gain of near the same amount . However , Apple claims the M2 poker chip turn in 25 percentage better performance at the same force level as M1 .
25 percent more heart and soul and 25 percent more performance . Who would have thought ?
Still , this appear like an extremely exponent - effective GPU . Apple likes to make savage comparisons , such as saying it ’s 2.3 times quicker than the Intel Core i7 - 1255U at the same powerfulness level . We ca n’t help oneself but observe that Apple did n’t compare its silicon chip against an AMD ’s ultraportable laptop chips , which are generally superior to Intel ’s in that department .
In a way , it does n’t matter . Graphics performance improvements are always welcome , but 3D graphics performance is one area where you would only equate against a Windows PC insofar as it affects content initiation apps like Adobe Premiere . Comparing processors of unlike computer architecture is always dubious , and that goes double for strain to vulgarise “ graphics carrying out ” that could include GPU compute , real - prison term 3D interlingual rendition , and more .
It ’s enough to say that the M2 has a 25 percent enceinte GPU , and is about that much faster , just as the A15 is to the A14 . You ’re see a approach pattern here , right ?
M2 vs M1: Memory
The memory subsystem is one area where the “ M2 is to A15 as M1 is to A14 ” design does not hold true . The A14 and A15 have the same master memory subsystem specs : a 64 - bit wide LPDDR4x port . The M1 doubled that to 128 bits across-the-board and stuck with LPDDR4x , for a peak of 68.25GB / s , the M2 makes the electrical switch to LPDDR5x , which further memory bandwidth to 100GB / s.
take down that the M1 Pro switched to LPDDR5x as well , with a 256 - bit memory interface giving it 200GB / s of bandwidth . The M1 Max repeat that to a 512 - turn interface , for 400GB / s.
So , while the M2 has 50 percent more store bandwidth than the M1 , it doesn’tnecessarilyhold on-key that the M2 Pro and M2 Max will feature 50 percent more memory bandwidth than the M1 Pro / Max . Apple would need to make a wider memory bus to do so , which is potential but starts to get pricy and complicated .
In addition to the big encouragement in storage bandwidth , the M2 is useable with up to 24 GB of RAM . The M1 only offered 8 Gbit and 16 GB configurations , both of which are still available on the M2 .
Though it was n’t stated in a flash , we are unforced to bet that the organization - level cache ( an on - chip stash that is accessible to every aspect of the poker chip ) is 50 percentage larger on the M2 as well . Apple increased the size of it of this memory cache from 16 GB on the A14 to 32 MB on the A15 . The M1 featured 24 MB of SLC , and it ’s sensible to expect that it has doubled to 48 MB in the M2 . We wo n’t be capable to recite until the M2 MacBooks ship in July and can be thoroughly test , but the SLC cache size is a big deal . It helps witheverything , as it is approachable to the CPU , GPU , Neural Engine , medium encoders , you name it .
M2 vs M1: Other improvements
Of course , Apple is quick to point out that the M2 is more than a CPU , GPU , and RAM . It ’s a complete system - on - check and include of import ironware acceleration occlusion for the sorting of ripe feature Apple hold open adding tomacOSandiPadOS . The Neural Engine , while still 16 heart and soul , can perform up to 15.8 trillion operations per second , more than 40 percent more than the 11 trillion functioning of the Neural Engine in the M1 . This is precisely like the leap from the A14 ( 11 trillion ) to the A15 ( 15.8 trillion ) .
The medium locomotive , which is responsible for speed up the encryption and decoding audio and video , has also been upgraded from the one found in the A14 to the new railway locomotive found in the A15 . It confirm H.264 and HEVC encoding and decode up to 8 K closure and includes the ProRes TV quickening musical accompaniment . Interestingly , while the M1 does n’t have this version of the media engine , the M1 Pro and M1 Max do . basically , the M1 shipped with the sensitive engine from the A14 , and the M1 Pro , Max , and Ultra , as well as the M2 , have the medium locomotive engine from the A15 ( two in the M1 Max , and four in the M1 Ultra ) .
It ’s quite possible that the mass medium locomotive will be upgraded yet again in the A16 ( perhaps with AV1 computer hardware speedup ) and that the M2 Pro , Max , and Ultra will get an rise to that reading .
In all , it appears the M2 is a skillful upgrade over the M1 , though not revolutionary . It convey all the architectural improves we check in the A15 and applies them to a thin - and - light laptop course of instruction chip in incisively the same way the M1 did for the A14 . And given that later M1 C.P.U. ( the M1 Pro , Max , and Ultra ) gave us advancement like LPDDR5x memory and the newer culture medium engine , it ’s not a sporting win across the board .
It will be interesting to watch Apple ’s evolution to the inevitable M2 Pro , M2 Max , and M2 Ultra . We surmise they might be made using TSMC ’s more sophisticated 3 nm unconscious process technology , and could feature some improvement we find in the A16 later this twelvemonth when the iPhone 14 Pro is announced – in all likelihood an improved medium engine and perhaps a newfangled Neural Engine , too . The M2 is a great start to Apple ’s second generation of Apple Silicon for the Mac ( and iPad Pro ) , but not surprisingly so .
