Tag Archives: Apple Silicon

Apple Silicon M1 Series vs. M2 Comparison!

Apple just launched the M2 – their second-generation M-series system-on-a-chip (SoC) for Mac computers!

Let’s compare the new M2 against the last-generation M1 series SoCs!

 

Apple Silicon M1 vs. M2 Comparison

On 6 June 2022, Apple unveiled their second-generation M-series system-on-a-chip (SoC) for Mac computers – the Apple Silicon M2!

Built on an improved 5 nm process technology, the Apple M2 has 20 billion transistors – 25% more transistors than the M1.

All those transistors allow the Apple M2 to deliver better performance than the last-generation M1 :

  • Faster Performance cores with a larger cache
  • 18% faster CPU performance
  • 35% more powerful GPU at max. power
  • 40% faster Neural Engine
  • 50% more memory bandwidth
  • up to 24 GB of unified memory
  • a new image signal processor (ISP) for better image noise reduction

The new M2 no doubt offers a significant boost in performance and capabilities over the M1.

On top of that, it partially addressed the limited Unified Memory capacity offered by the M1, by offering a 24 MB option.

The new M2 will debut in the 2022 MacBook Air, and the updated 13-inch MacBook Pro 2022 laptops.

To give you a better idea of how they compare, here is our direct comparison b between the Apple M1 and the Apple M2 :

Specifications M1 M2 Difference
Fab Tech 5nm (N5) 5 nm (N5P)
Transistor
Count
16 billion 20 billion +25%
Die Size 120 mm² NA
CPU Cores
(Performance)
4 x Firestorm
@ 3.2 GHz
4 x Avalanche cores
@ NA GHz
CPU Cores
(Efficiency)
4 x Icestorm cores
@ 2.06 GHz
4 Blizzard cores
@ NA GHz
L2 Cache P-core : 12 MB
E-core : 4 MB
P-core : 16 MB
E-core : 4 MB
P-core : +33%
SLC 16 MB 32 MB +100%
GPU Cores 7 / 8 cores
1278 MHz
8 / 10 cores
NA MHz
+1 / +2 cores
Neural Engine 16 cores
(11 TOPS)
16 cores
(15.8 TOPS)
+44%
Memory Options 8 GB / 16 GB 8 GB / 16 GB / 24 GB
Memory Type LPDDR4X LPDDR5
Memory Speed 2133 MHz 3200 MHz +50%
Memory Bus 128-bit 128-bit
Memory
Bandwidth
68.2 GB/s 102.4 GB/s 50%

 

Apple Silicon M1 Series vs. M2 Comparison

While the M2 may offer significant improvements over the M1, Apple has been careful in not letting it cannibalise sales of the higher-performing M1 Pro, M1 Max and M1 Ultra chips.

Even without testing the new M2, its specifications show that it slots in between the M1 and the M1 Pro.

  • M2 has 8 cores like M1, with 2-4 fewer Performance cores than the M1 Pro.
  • Its Performance cores have L2 cache size of 16 MB, right between M1 (8 MB) and M1 Pro (24 MB).
  • Its 8-10 GPU core count is right between M1 (7-8 cores) and M1 Pro (14-16 cores).
  • Its maximum Unified Memory option is 24 GB, right between M1 (16 GB) and M1 Pro (32 GB).
  • It retains the M1’s narrower 128-bit memory bus, but uses the M1 Pro’s faster LPDDR5 memory.

To show you what I mean, here is a table I created comparing the key specifications of the M1 series against the new M2 :

Specifications M1 M1 Pro M1 Max M1 Ultra M2
Fab Tech 5nm (N5) 5 nm (N5P)
Transistor Count 16 billion 33.7 billion 57 billion 114 billion 20 billion
Die Size 120 mm² 245 mm² 432 mm² 864 mm² NA
CPU Cores
(Performance)
4 cores
(Firestorm)
3.2 GHz
6 / 8 cores
(Firestorm)
3.23 GHz
8 cores
(Firestorm)
3.23 GHz
16 cores
(Firestorm)
3.23 GHz
4 cores
(Avalanche)
NA GHz
CPU Cores
(Efficiency)
4 cores
(Icestorm)
2.06 GHz
2 cores
(Icestorm)
2.06 GHz
2 cores
(Icestorm)
2.06 GHz
4 cores
(Icestorm)
2.06 GHz
4 cores
(Blizzard)
NA GHz
L2 Cache P-core : 12 MB
E-core : 4 MB
P-core : 24 MB
E-core : 4 MB
P-core : 48 MB
E-core : 8 MB
P-core : 16 MB
E-core : 4 MB
SLC 16 MB 32 MB 64 MB 128 MB 32 MB
GPU Cores 7 / 8 cores
1278 MHz
14 / 16 cores
1296 MHz
24 / 32 cores
1296 MHz
48 / 64 cores
1296 MHz
8 / 10 cores
NA MHz
Neural Engine 16 cores 32 cores 16 cores
Memory Options 8 / 16 GB 16 / 32 GB 32 / 64 GB 64 / 128 GB 8 / 16 / 24 GB
Memory Type LPDDR4X LPDDR5
Memory Speed 2133 MHz 3200 MHz
Memory Bus 128-bit 256-bit 512-bit 1024-bit 128-bit
Memory
Bandwidth
68.2 GB/s 204.8 GB/s 409.6 GB/s 819.2 GB/s 102.4 GB/s

 

Please Support My Work!

Support my work through a bank transfer /  PayPal / credit card!

Name : Adrian Wong
Bank Transfer : CIMB 7064555917 (Swift Code : CIBBMYKL)
Credit Card / Paypal : https://paypal.me/techarp

Dr. Adrian Wong has been writing about tech and science since 1997, even publishing a book with Prentice Hall called Breaking Through The BIOS Barrier (ISBN 978-0131455368) while in medical school.

He continues to devote countless hours every day writing about tech, medicine and science, in his pursuit of facts in a post-truth world.

 

Recommended Reading

Go Back To > ComputerTech ARP

 

Support Tech ARP!

Please support us by visiting our sponsors, participating in the Tech ARP Forums, or donating to our fund. Thank you!

macOS Monterey Memory Leak : Solutions You Can Try!

macOS Monterey continues to be plagued by an insidious memory leak problem that Apple does not seem able to fix.

So here are a few workarounds that you can try!

 

macOS Monterey Memory Leak : What’s Going On?

Ever since it was released on 25 October 2021, macOS Monterey has been plaguing users with an insidious memory leak problem.

And even as Christmas approaches, Apple is still unable to fix the problem. Here is what we know so far…

It Gobbles Up Insane Amounts Of Memory

The memory leak quietly eats up insane amounts of memory, creeping up on users without warning.

A single affected app like Firefox can gobble up almost 80 GB of memory. Even a critical macOS process like WindowServer can end up using 24 GB of memory, while the Mail app can use more than 100 GB of memory!

Unless you have been keeping an eye on memory usage, you will only realise this is happening when you get the warning that “Your system has run out of application memory” with a request to Force Quit apps you are not using.

It Appears To Be An OS Issue

This Monterey memory leak affects many different apps with no obvious culprit in sight :

  • Internet browsers like Firefox and Safari
  • Apps like Tweetbot and Final Cut Pro
  • macOS features like Control Center, Mail and Finder
  • macOS processes like WindowsServer

That strongly suggests that it is an operating system issue, and not a bug in any particular app.

It Affects Intel + Apple Silicon Models

This Monterey memory leak problem is not platform-specific, and affects both Intel and Apple Silicon models.

So you are not going to be able to “escape” this memory leak problem by upgrading to the new M1 Pro / Max-powered MacBook Pro laptops.

 

macOS Monterey Memory Leak : Possible Solutions

Unfortunately, Apple still does not seem to be able to plug this insidious macOS Monterey memory leak. So here are some solutions that may work for you…

Revert To Standard Mouse Pointer

One of the new features macOS Monterey is the ability to change the mouse pointer’s size, as well as its outline and fill colours.

However, the developers at Mozilla discovered that using a non-standard mouse pointer in macOS Monterey causes a large memory leak!

This memory leak is not limited to Firefox, but occurs anytime the non-standard mouse pointer changes its look, like when you mouse over a button or a text field.

To fix this, you will need to revert to a standard mouse pointer, and here’s how to do that :

Step 1 : Go to Settings and select Accessibility.

Step 2 : Tap on the Display option, and select the Pointer tab.

Step 3 : Move the Pointer size all the way to the left (Normal).

Step 4 : Click on the Reset button to the right of Pointer outline colour and Pointer fill colour.

Step 5 : Restart your Mac, and fingers crossed – this fixes your Monterey memory leak problem!

Relaunch Finder

If you notice Finder using a prodigious amount of memory, that memory leak happens when you use the Find (⌘ F) feature in to search for files.

The easiest way to prevent this memory leak is to avoid using Finder’s Find feature. Try using the Search option on the upper right corner.

But once you get a Finder memory leak, you must relaunch it to release the leaked memory…

Option A : While in the Finder window, click on the Apple menu. Then press and hold the Shift key and click on Force Quit Finder.

Option B : Click on the Apple menu. Click Force Quit (Command + Option + Escape). Then select Finder and click on Relaunch.

Limit Use Of Control Center

Some users have reported that the Control Center can use upwards of 20GB of RAM, but most users fortunately do not encounter such terrible waste of memory.

This memory leak is easily reproducible – every time you use a control, it uses a little more RAM but does not release it.

Unfortunately, there is no way to release the leaked memory short of restarting the computer. So the best way to avoid this memory leak is to limit the use of Control Center.

Restart Apps Whenever Memory Use Is Too Much

Well, this seems obvious, but I have to throw it in anyway.

If any app, whether it’s Safari or Final Cut Pro starts using way too much memory, just close and reopen it. That should quickly recover the leaked memory.

Of course, this is only a stopgap solution until Apple releases a fix for this truly pesky memory problem in macOS Monterey…

 

Please Support My Work!

Support my work through a bank transfer /  PayPal / credit card!

Name : Adrian Wong
Bank Transfer : CIMB 7064555917 (Swift Code : CIBBMYKL)
Credit Card / Paypal : https://paypal.me/techarp

Dr. Adrian Wong has been writing about tech and science since 1997, even publishing a book with Prentice Hall called Breaking Through The BIOS Barrier (ISBN 978-0131455368) while in medical school.

He continues to devote countless hours every day writing about tech, medicine and science, in his pursuit of facts in a post-truth world.

 

Recommended Reading

Go Back To > Software | Computer | Tech ARP

 

Support Tech ARP!

Please support us by visiting our sponsors, participating in the Tech ARP Forums, or donating to our fund. Thank you!