Discussion Apple Silicon SoC thread

[Eug]

M1
5 nm
Unified memory architecture - LP-DDR4
16 billion transistors

8-core CPU

4 high-performance cores
192 KB instruction cache
128 KB data cache
Shared 12 MB L2 cache

4 high-efficiency cores
128 KB instruction cache
64 KB data cache
Shared 4 MB L2 cache
(Apple claims the 4 high-effiency cores alone perform like a dual-core Intel MacBook Air)

8-core iGPU (but there is a 7-core variant, likely with one inactive core)
128 execution units
Up to 24576 concurrent threads
2.6 Teraflops
82 Gigatexels/s
41 gigapixels/s

16-core neural engine
Secure Enclave
USB 4

Products:
$999 ($899 edu) 13" MacBook Air (fanless) - 18 hour video playback battery life
$699 Mac mini (with fan)
$1299 ($1199 edu) 13" MacBook Pro (with fan) - 20 hour video playback battery life

Memory options 8 GB and 16 GB. No 32 GB option (unless you go Intel).

It should be noted that the M1 chip in these three Macs is the same (aside from GPU core number). Basically, Apple is taking the same approach which these chips as they do the iPhones and iPads. Just one SKU (excluding the X variants), which is the same across all iDevices (aside from maybe slight clock speed differences occasionally).

EDIT:



M1 Pro 8-core CPU (6+2), 14-core GPU
M1 Pro 10-core CPU (8+2), 14-core GPU
M1 Pro 10-core CPU (8+2), 16-core GPU
M1 Max 10-core CPU (8+2), 24-core GPU
M1 Max 10-core CPU (8+2), 32-core GPU

M1 Pro and M1 Max discussion here:

Page 78 - Discussion - Apple Silicon SoC thread

Page 78 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

forums.anandtech.com

M1 Ultra discussion here:

Page 109 - Discussion - Apple Silicon SoC thread

Page 109 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

forums.anandtech.com

M2 discussion here:

Page 127 - Discussion - Apple Silicon SoC thread

Page 127 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

forums.anandtech.com

Second Generation 5 nm
Unified memory architecture - LPDDR5, up to 24 GB and 100 GB/s
20 billion transistors

8-core CPU

4 high-performance cores
192 KB instruction cache
128 KB data cache
Shared 16 MB L2 cache

4 high-efficiency cores
128 KB instruction cache
64 KB data cache
Shared 4 MB L2 cache

10-core iGPU (but there is an 8-core variant)
3.6 Teraflops

16-core neural engine
Secure Enclave
USB 4

Hardware acceleration for 8K h.264, h.264, ProRes

M3 Family discussion here:

Page 215 - Discussion - Apple Silicon SoC thread

Page 215 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

forums.anandtech.com

M4 Family discussion here:

Page 263 - Discussion - Apple Silicon SoC thread

Page 263 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

forums.anandtech.com

M5 Family discussion here:

Page 431 - Discussion - Apple Silicon SoC thread

Page 431 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

forums.anandtech.com

 

[Jan Olšan]

That 9% is for total PC shipments, not laptops.

As far as notebooks go, there was a switch from Arm to x86 at some point, so pre-2020 data should be considered with care.

Of course, but given the weight of notebooks (70 %) in the PC mix, it's impossible to have 17% laptop share with 9% overall share.

 

[oak8292]

Of course, but given the weight of notebooks (70 %) in the PC mix, it's impossible to have 17% laptop share with 9% overall share.

Be careful with the definition of a ‘laptop’. This varies among the reporters and there isn’t a bright line between tablets and laptops. Where does a Microsoft tablet fit? Where does an iPad Pro fit? Where does a Chromebook fit.

 

[Nothingness]

Of course, but given the weight of notebooks (70 %) in the PC mix, it's impossible to have 17% laptop share with 9% overall share.

Obtaining data is so difficult, this is all I could find (OK, didn't look very long) and to say the least it's hard to know what laptop vs desktop is

But yeah I agree the 17% looks too high. It's somewhere between 9 and 17, both bounds being excluded.

 

[Mopetar]

They've always talked about "long term" supply agreements, six months is not long term to me so I'd question their wording if that was really the case.

For electronics manufacturing six months is practically an eternity in today's world. Everything is designed around a Just In Time philosophy where nothing is kept around any longer than necessary to save on warehousing costs.

When everything is running smoothly this works great, but as we saw during COVID it's easily disrupted. Even the f it weren't, anything beyond six months has too much uncertainty to reliably plan around unless you manufacture all of your own components on existing production lines.

Most of the time not having to have a warehouse full of memory sitting on shelves because the SoC, screens, or some other component got delayed for a few months is more valuable than eating added costs due to market fluctuations. Even those aren't really a problem if everyone has to eat them at the same time or they can just be passed on to consumers.

 

[oak8292]

For electronics manufacturing six months is practically an eternity in today's world. Everything is designed around a Just In Time philosophy where nothing is kept around any longer than necessary to save on warehousing costs.

When everything is running smoothly this works great, but as we saw during COVID it's easily disrupted. Even the f it weren't, anything beyond six months has too much uncertainty to reliably plan around unless you manufacture all of your own components on existing production lines.

Most of the time not having to have a warehouse full of memory sitting on shelves because the SoC, screens, or some other component got delayed for a few months is more valuable than eating added costs due to market fluctuations. Even those aren't really a problem if everyone has to eat them at the same time or they can just be passed on to consumers.

This was the practice that was essential with Moore’s Law due to obsolescence. It is good practice even without obsolescence. However, it is less essential as performance differences decrease. If Compaq or Apple were caught with a warehouse full of computers in a downturn it wouldn’t be an existential crisis.

If Micron has a lot of DDR4 in a warehouse it is increasing in value at this point versus decreasing. Memory and Moore’s Law was a killer as bits typically decrease in value so rapidly.

The market for old electronics may have a renaissance here in 2026 as they were built with ‘cheap’ parts.

 

[Doug S]

For electronics manufacturing six months is practically an eternity in today's world. Everything is designed around a Just In Time philosophy where nothing is kept around any longer than necessary to save on warehousing costs.

When everything is running smoothly this works great, but as we saw during COVID it's easily disrupted. Even the f it weren't, anything beyond six months has too much uncertainty to reliably plan around unless you manufacture all of your own components on existing production lines.

Most of the time not having to have a warehouse full of memory sitting on shelves because the SoC, screens, or some other component got delayed for a few months is more valuable than eating added costs due to market fluctuations. Even those aren't really a problem if everyone has to eat them at the same time or they can just be passed on to consumers.

Apple wouldn't be buying two years worth of memory for immediate delivery, they'd have it delivered over time! They couldn't have it delivered up front even if they wanted to fill up a giant warehouse, because Micron et al wouldn't have enough to ship them two years worth all at once. The reason Apple started doing these multiyear contracts was to guarantee supply. e.g. back when the iPod switched from 1.8" HDDs to flash, they got prepaid deals with multiple suppliers that amounted to nearly all the NAND capacity at first. Even ignoring black swans like Covid and the AI bubble, having guaranteed supply at a guaranteed price makes costing for upcoming products much easier. Cook is an operations guy, after all, this is the kind of stuff he nerds out over (there was an interview not long after he became CEO where a good chunk of it was him doing exactly that lol)

It also helps a bit with getting better terms. Saying "we want this two year deal and we'll pay for everything up front and you ship it as we need it" is gonna get you better pricing than if you do a two year deal and you pay over time. Especially in capital intensive industries like DRAM/NAND (and merchant foundries like TSMC) having that cash up front so you aren't relying on lines of credit for building out future capacity saves Micron/TSMC/etc. money and makes their financials look better (although prepaid orders show up as a liability on the balance sheet just like a line of credit does, it is evaluated much more positively by Wall Street)

I suppose the one downside is that you won't necessarily get as good of pricing during periods where prices are rapidly falling as might if you bought it in smaller quantities, but Apple isn't exactly pricing their RAM/NAND upgrades at thin margins so they don't care about that. They don't want lowest possible price, they want a long term predictable price. Since DRAM/NAND is always sort of a boom/bust cycle with prices that trend down I imagine some of that low term downward price trend gets built into the contracts, just like a contract being signed now would have the upward spike built into it.

The other thing with long term contracts is that you are probably going to trail the market tech wise, and that's proven very true for Apple as they always lag a bit on LPDDR technology.

 

[fkoehler]

Most of the time not having to have a warehouse full of memory sitting on shelves because the SoC, screens, or some other component got delayed for a few months is more valuable than eating added costs due to market fluctuations.

Can't disagree that this is how companies ran until Covid made an impact.
Now with RAM?

Any CEO in the future who tries to use this an excuse is likely to get dinged hard as his Stock price gets hammered and investors scream for his head.

Expect most industries to return to having something like at least 1QTR worth of inventory in the future. The potential for lost business, stock hammering and business discontinuity makes some warehousing expense a penny save-pound foolish excuse no one will buy.

 

[LightningZ71]

JIT is losing it's luster, but, it's too late for much of the industry as whole supply chains are heavily capacity restricted as manufacturers are loathe to build extra capacity.

 

[name99]

Apple wouldn't be buying two years worth of memory for immediate delivery, they'd have it delivered over time! They couldn't have it delivered up front even if they wanted to fill up a giant warehouse, because Micron et al wouldn't have enough to ship them two years worth all at once. The reason Apple started doing these multiyear contracts was to guarantee supply. e.g. back when the iPod switched from 1.8" HDDs to flash, they got prepaid deals with multiple suppliers that amounted to nearly all the NAND capacity at first. Even ignoring black swans like Covid and the AI bubble, having guaranteed supply at a guaranteed price makes costing for upcoming products much easier. Cook is an operations guy, after all, this is the kind of stuff he nerds out over (there was an interview not long after he became CEO where a good chunk of it was him doing exactly that lol)

It also helps a bit with getting better terms. Saying "we want this two year deal and we'll pay for everything up front and you ship it as we need it" is gonna get you better pricing than if you do a two year deal and you pay over time. Especially in capital intensive industries like DRAM/NAND (and merchant foundries like TSMC) having that cash up front so you aren't relying on lines of credit for building out future capacity saves Micron/TSMC/etc. money and makes their financials look better (although prepaid orders show up as a liability on the balance sheet just like a line of credit does, it is evaluated much more positively by Wall Street)

I suppose the one downside is that you won't necessarily get as good of pricing during periods where prices are rapidly falling as might if you bought it in smaller quantities, but Apple isn't exactly pricing their RAM/NAND upgrades at thin margins so they don't care about that. They don't want lowest possible price, they want a long term predictable price. Since DRAM/NAND is always sort of a boom/bust cycle with prices that trend down I imagine some of that low term downward price trend gets built into the contracts, just like a contract being signed now would have the upward spike built into it.

The other thing with long term contracts is that you are probably going to trail the market tech wise, and that's proven very true for Apple as they always lag a bit on LPDDR technology.

Here's another way to look at this that non-finance people might understand more easily:

Option 1. You pre-arrange contracts for DRAM (and flash, etc) at a fixed price a long time in advance.
That is a fixed price, and the price might go down over the next two years or whatever.

Option 2. You pay the spot DRAM price and buy as you need. This SEEMS like a good idea, especially for high tech items where the price is usually falling.
BUT look at the downside. The downside is not that you pay an extra $10 for some DRAM, it's that you cannot ship an iPhone and thus lose the $400 (or whatever) of profit on that iPhone.
$400>>$10!!!
The fixed-price contract doesn't just avoid price fluctuations; the more important point is that it guarantees you can ship as many iPhones as you need to...

 

[AMDK11]

Of course, but given the weight of notebooks (70 %) in the PC mix, it's impossible to have 17% laptop share with 9% overall share.

Intel is a public company (listed on NASDAQ: INTC) owned mainly by financial institutions, and since 2025, the US government has become a significant investor (approximately $10 billion in investments). Major shareholders include The Vanguard Group, BlackRock, and State Street. In September 2025, Nvidia invested $5 billion in Intel shares.

AMD (Advanced Micro Devices) is a public company listed on the NASDAQ stock exchange, which means that it is owned by shareholders. The largest stake in the company is held by financial institutions, mainly Vanguard Group, BlackRock, and State Street. As of June 30, 2025, institutional investors held approximately 65.45% of the shares, with the remainder held by individual investors.

This is today's info.
Intel investors HAHAHA competition

Now Nvidia:
Shareholder
% of shares
Shares held
Date of notification
Value (in thousands)
The Vanguard Group, Inc. 9.15% 2,223,533,800 09/30/2025 417,290,588
BlackRock, Inc. 7.92% 1,925,473,877 09/30/2025 361,353,682
State Street Global Advisors, Inc. 4.03% 980,029,103 09/30/2025 183,922,062

Qualcomm
Qualcomm Incorporated is a US public company (NASDAQ: QCOM), which means that it is owned by shareholders, mainly large financial institutions. The largest shareholders are Vanguard Group (approx. 10.57% as of March 2025) and BlackRock (approx. 9.44% as of July 2025). Other significant investors include State Street Corp, Geode Capital Management, and Morgan Stanley.

No one will die, no one will get hurt, NVIDIA will have high-end products, AMD will be making cheap stuff at the same time, and when Intel ran out of steam, its sister company NVIDIA lent (or rather invested) $5 billion. Intel = AMD = NVIDIA = ARM, one and the same owner

Apple Inc. is a publicly traded corporation, meaning it is owned by its shareholders – millions of individual and institutional investors worldwide. Investment funds such as Vanguard Group (approximately 8.4%) and BlackRock hold the largest stakes, while Warren Buffett (Berkshire Hathaway) is also a significant investor.

ASML Holding NV (ASML)​

BlackRock 7,17%
Vanguard Group 4.47%

TSMC (Taiwan Semiconductor Manufacturing Company) is a public company whose main institutional shareholder is the National Development Fund of Taiwan (Executive Yuan), which holds over 6% of the shares. More than half of the shares are free float, and leading investors include BlackRock.

Microsoft is a publicly traded corporation owned by its shareholders, not a single individual.

The largest shareholders are financial institutions such as BlackRock and Vanguard. Co-founder Bill Gates previously held significant stakes, but his current stake is small (approximately 1.3%), with investment funds controlling the majority.

Major institutional shareholders: BlackRock, Inc. (~7.95%), State Street Corporation (~4.03%).

 

[johnsonwax]

How does gaming in Windows virtualised on Apple processors (and iGPUs) work in practice? Usually alternative GPU providers face huge issues with game compatibility, even Intel has rough time despite their graphics already being in the ecosystem for decades so it wasn't a complete new for game devs. I'm highly skeptical you can just install EGS and Steam and run games like it was a Windows PC with Radeon/GeForce graphics.

What sort of driver does the game running in the Windows VM actually communicate with? Does Apple provide Windows GPU driver with 3D API support? Is there some shim that tries to translate Vulkan and DX11/12 to Metal and tunnels the calls to the macOS host for execution? (IIRC that's how DX12 works in WSL)

I mean, it works pretty well overall. You have WINE as the foundation for the API mappings which has substantial development contributed to by Codeweavers, paid for by subscribers of the Mac Crossover product which packages up WINE quite nicely on the Mac. Behind that you have Rosetta 2 doing the binary translation to Apple Silicon.

AMD and Nvidia patch their drivers to fix problems in games, which creates a bit of inconsistency to performance and stability depending on GPU/driver version you're on - which is why Intel struggles because they need to develop similar driver patches. That's mostly all incorporated in Codeweavers work, which is also pushed out to WINE so at the very least it's all in one place. And Crossover does support DX12.

Game Porting Toolkit is separate from Crossover, but Codeweavers does use Apple's work there. GPT is a bunch of different tools, some diagnostic, etc. but the main one is that it recompiles shaders to Metal not unlike how Rosetta works. It's beneficial to Apple in the sense that it helps them see where Metal doesn't map cleanly onto Vulkan, etc. and where developers like Epic are having trouble maintaining Metal parity in UE5, etc. It's mainly intended for developers to get a port out the door quickly, and then add native support, but it's similarly useful for users to get Windows games running.

In terms of performance, there's a pretty small performance hit overall. For non-GPU constrained games you might even come out ahead, and on GPU constrained games you're mostly taking a hit because Apple's GPUs aren't as strong as traditional gaming GPUs, but it's going to beat the pants off of any integrated GPU in the PC world and a fair number of discrete ones. I'm really interested to see what the M5 Pro/Max put out there given the improvements in the M5, because they could be competitive with top end discrete laptop GPUs and everything but the very top of the line desktop ones.

 

[johnsonwax]

Apple wouldn't be buying two years worth of memory for immediate delivery, they'd have it delivered over time! They couldn't have it delivered up front even if they wanted to fill up a giant warehouse, because Micron et al wouldn't have enough to ship them two years worth all at once. The reason Apple started doing these multiyear contracts was to guarantee supply. e.g. back when the iPod switched from 1.8" HDDs to flash, they got prepaid deals with multiple suppliers that amounted to nearly all the NAND capacity at first. Even ignoring black swans like Covid and the AI bubble, having guaranteed supply at a guaranteed price makes costing for upcoming products much easier. Cook is an operations guy, after all, this is the kind of stuff he nerds out over (there was an interview not long after he became CEO where a good chunk of it was him doing exactly that lol)

It also helps a bit with getting better terms. Saying "we want this two year deal and we'll pay for everything up front and you ship it as we need it" is gonna get you better pricing than if you do a two year deal and you pay over time. Especially in capital intensive industries like DRAM/NAND (and merchant foundries like TSMC) having that cash up front so you aren't relying on lines of credit for building out future capacity saves Micron/TSMC/etc. money and makes their financials look better (although prepaid orders show up as a liability on the balance sheet just like a line of credit does, it is evaluated much more positively by Wall Street)

I suppose the one downside is that you won't necessarily get as good of pricing during periods where prices are rapidly falling as might if you bought it in smaller quantities, but Apple isn't exactly pricing their RAM/NAND upgrades at thin margins so they don't care about that. They don't want lowest possible price, they want a long term predictable price. Since DRAM/NAND is always sort of a boom/bust cycle with prices that trend down I imagine some of that low term downward price trend gets built into the contracts, just like a contract being signed now would have the upward spike built into it.

The other thing with long term contracts is that you are probably going to trail the market tech wise, and that's proven very true for Apple as they always lag a bit on LPDDR technology.

In order to understand the long term contract dynamics you kind of have to understand how costs accrue and how risk in the industry works. A large player like Apple can sometimes come in and get a good deal because they are going to guarantee a level of spending over a specific period of time. It's a form of risk transferral from the supplier to the customer. Now, the supplier won't want to do that across the board, but if Apple can come in and say 'we will guarantee you enough revenue to cover all of your fixed costs' then your financial state is pretty well guaranteed, and you ask all of the other, smaller customers to cover the marginal costs.

There was a really interesting contract that the USPS entered into with Amazon years ago, before Amazon got into the delivery business themselves. There was a lot of criticism of the contract because it seemed too inexpensive, but USPS is already required to drive to every household in the US. They have almost no marginal cost on driving to an address because they need to anyway. So essentially Amazon was subsidizing the fixed costs of the postal service, and occasionally, when packages required moving to a larger vehicle or splitting routes because there was too much volume, etc. having to incur a marginal cost. Apple has long played that role in the tech industry - their purchases are so reliable over long periods of time that they can leverage that, and if you know that you're going to get a check from Apple in 2027 for x billion dollars, because that contract is already written, that has a significant benefit in terms of your strategic planning. Now, as you note you might lose out when prices are falling, but at Apple's scale they pretty much never get to see that either, because again, high price variability happens at the margins when you have over/underproduced and you either need to clear inventory or you are seeking to tamp down demand in favor of profits. If you overproduced by 10% and are discounting, and Apple is buying 40% of your production, you can't afford to give Apple that discount. You can at most give them ¼ of that discount, so if you are a large enough player, that's not really a dynamic that happens.

For folks in the US, remember back during the egg price spike of 2022? You know who always had eggs, and didn't raise prices? McDonalds - the largest egg buyer in the US. They had long term contracts to buy eggs and they kept reliably buying at the contracted price. It's not like the cost of producing eggs had gone up so much as the supply was outstripped by demand. Those price spikes happened at the margins, with buyers that didn't have long term contracts because if the supply had gone down by 20% and 80% of the market previously was going to outfits with long term contracts, then there was zero supply for the spot market, so price would go to infinity. Apple is large enough for almost everything they do that they can live inside that stable contract space because the scariest thing for a supplier isn't failing to get the high price when things spike, it's failing to meet their fixed costs, and Apple solves that problem for them.

 

[johnsonwax]

JIT is losing it's luster, but, it's too late for much of the industry as whole supply chains are heavily capacity restricted as manufacturers are loathe to build extra capacity.

JIT isn't losing its luster. JIT always favored long term contracting, but that requires, you know, doing work, and knowing what you're doing - things that are anathema to a lot of MBAs. And in the current moment, there is so much idle cash in the economy not knowing where to go, that we've gotten this enormous bubble. If you weren't doing JIT, you'd have the same problem. Worse, you'd have a much slower moving tech industry because you'd have these commitments to outdated tech sitting in your warehouses that you would need to find ways to deal with. When Apple agrees to a long term JIT contract, both parties are happy to swap that LPDDR5 prepurchase agreement for LPDDR6 components if that switch needs to happen midway through the contract. You don't get to do that if you have 2 years of LPDDR5 sitting in a factory. You can't unmake products.