Apple seems to have its eyes on the road (map) for iPhone processors
TSMC is now Apple’s primary processor manufacturing partner, churning out 7-nanometer (nm) A13 chips for iPhones – and it may be producing 3nm chips for iPhones by 2023.
What’s in a nanometer?
A nanometer is one billionth of a meter. It’s the unit of measurement used to show the distance between the transistors that comprise the processor. The smaller the number of nanometers the higher the number of transistors you can squeeze onto one chip.
Faster processors that are also more energy efficient.
Apple’s chip designs have led the industry for years. It has been developing ARM-based processors since 2007, ramped this up with the A4 and again with its A6 chips and pushed things even further in 2016 with the A10.
The company has achieved significant performance and power efficiency improvements with each iteration:
- The A10 Fusion processor inside the iPhone 7 was the first Apple-designed SOC. It delivered 40% better processor performance and 50% better graphics than the Apple-designed 64-bit A9 chip (used in the iPhone 6S) it replaced.
- Apple achieved a 25% performance boost when it shifted from the 14nm A10 to the 7nm A11.
- Apple’s A12 processors provided significant performance gains over the A11 series in part because they were the first to adopt 7nm process technologies.
- Apple’s existing (7nm) A13 series processors maintain the trend. These deliver 20% more performance and 40% better power efficiency than 2018’s A12.
- You can review performance increases between the A6 and A11.
It’s thought that Apple will migrate to 5nm processors in 2020 following Комментарии и мнения владельцев from TSMC CFO Lora Ho, who revealed his company has become “more aggressive” on the move to manufacture these chips. This means that next year’s A14 processors may be built using 5nm tech, which should deliver similar performance and power efficiency gains.
This should be useful as Apple attempts to handle the new power requirements of 5G solutions as it begins to field them in late 2020.
The future will be better tomorrow
That’s not the end of the road map. TSMC has begun construction of a 3nm fabrication facility at the Southern Taiwan Science and Technology Park, Tainan, Taiwan. This is a huge investment – figures approaching 20 billion are cited – and mass production is expected to begin by late 2022 or early 2023. That’s right on schedule for a follow-up to next year’s anticipated 5nm A14 (if speculation matches reality).
Apple is, after all, one of TSMC’s biggest customers, so it will inevitably be at least interested in what is made there.
What does this tell us?
In a sense, this tells us little new. We only need to look at Apple’s track record to know that it is 100% dedicated to developing and distributing the world’s most advanced processors and to continued improvements in these architectures.
We also know it wants its hardware to offer patented technologies that competitors cannot legitimately copy. It learnrf this the hard way when it failed to win wars against imitators over design patents.
It also confirms that Apple is not working to any random rhythm but retains tight navigation along a clear road map:
- It shows that its path for processor enhancements is solid all the way out to 2023 and beyond.
- It suggests Apple will be able to deliver significant improvements in processors and power efficiency every year until then and beyond.
This also suggests that if Apple’s processor road map remains on course, its wider company mission also remains on track.
What’s the big picture?
It’s pretty clear that Apple’s 64-bit chips are matching – and now almost exceeding – some desktop class processors. That’s got to be significant in terms of Apple’s wider strategy, with iPads and iPhones designed to handle most tasks, and increasingly high-end Macs available to handle more complex tasks.
Will it also prove significant to Apple’s much discussed, but never confirmed (and sometimes denied), wider plan to unify its platforms?
We don’t know for certain, but it makes the unthinkable thinkable, again. How fast will iPhones become before they can completely replace computers?
Please follow me on. or join me in the AppleHolic’s bar grill and Apple Discussions groups on MeWe.
Apple Silicon: The Complete Guide
Since 2020, Apple has been working to transition away from Intel chips, instead using its own Apple silicon chips. Apple’s custom chips are Arm-based and are similar to the A-series chips used in iPhones and iPads, and Apple unveiled the first Apple silicon Macs in November 2020. The second Apple silicon Macs came in 2021, and now the MacBook Air, MacBook Pro, Mac mini, Mac Studio, and iMac lineups all feature machines with M-series chips.
This guide covers everything we know about Apple silicon, Apple‘s plans to transition the entire Mac lineup away from Intel chips, and Apple’s efforts to make it easy for developers to design apps for the new Arm-based Macs.
Apple Silicon Mac Lineup
Apple’s first Macs with Apple silicon chips, the late 2020 MacBook Air, MacBook Pro, Mac mini and the 2021 iPad Pro and iMac all use the M1 chip, which is Apple’s first custom-designed Arm-based chip for Mac. The 2021 14-inch and 16-inch MacBook Pro models use the M1 Pro and M1 Max, upgraded variants of the M1 that are more powerful, and the Mac Studio uses the M1 Ultra, which is twice as powerful as the M1 Max.
M-series chips feature Apple’s first System on a Chip design for the Mac, and it integrates several different components including the CPU, GPU, unified memory architecture (RAM), Neural Engine, Secure Enclave, SSD controller, image signal processor, encode/decode engines, Thunderbolt controller with USB 4 support, and more, all of which power the different features in the Mac.
The M1, M1 Pro, M1 Max, and M1 Ultra chips are the most powerful chips that Apple has created to date, handily beating out much higher-end Intel chips.
The M1 features an 8-core CPU with four high-performance cores and four high-efficiency cores and an 8-core GPU. The M1 Pro features a 10-core CPU with eight high performance cores and two high efficiency cores along with a 16-core GPU (though there is an entry-level version with 8-core CPU and 14-core GPU).
Apple’s high-end M1 Max features a 10-core CPU (the same as the CPU for the M1 Pro) and a 32-core GPU for improved graphics performance. The high=performance cores in the M-series chips are designed to offer the best performance for power-intensive single-threaded tasks, while the high-efficiency cores are available for tasks that don’t require as much power, such as web browsing. This split between high power and high efficiency is what gives the Apple silicon Macs incredible battery life.
The M1 Ultra offers twice the performance of the M1 Max with up to a 20-core CPU and up to a 64-core GPU.
All of the Apple silicon chips have unified memory that’s shared between all chip components to eliminate swapping and improve performance, plus a 16-core Neural Engine and other add-ons like an image signal processor, Secure Enclave for secure booting and Touch ID, and more.
Why Apple Made the Switch
Apple is adopting its own Apple silicon chips to make better Macs. Apple’s chips bring a whole new level of performance with more powerful Macs that are also more energy-efficient. Apple says that its advanced power management capabilities allow for maximized performance paired with better than ever battery life of up to 21 hours. That’s double the battery life of some prior-generation Intel-based Macs.
Apple Silicon Advantage
Apple has years of experience with power-efficient chip design thanks to its work on the iPhone, iPad, and Apple Watch, all of which use custom-designed chips developed by Apple engineers. Apple has made huge gains in processor performance over the years, and its chips are now more than powerful enough to be used in Macs.
Apple aimed to deliver the highest possible performance with the lowest power consumption, a goal that its expertise made it well-suited to achieve. Better performance and efficiency were Apple’s main goals, but there are other reasons that the company decided to transition away from Intel, and that includes all of the custom technologies that are built into Apple silicon to further boost the Mac’s capabilities and make it stand out from the competition.
Deep integration between software and hardware has always made iPhones stand out from other smartphones, and the same is true for the Mac. Apple‘s custom chips provide best-in-class security with the Secure Enclave and high-performance graphics capabilities for pro apps and games, but the true performance gains remain to be seen.
Apple silicon chips are built with Neural Engines and Machine Learning Accelerators to make Macs ideal platforms for machine learning. Other technologies include a high-quality camera processor, performance controller, Secure Enclave and Touch ID, high-performance DRAM, unified memory, and cryptography acceleration.
Many of Apple’s prior Macs used x86 chips from Intel, while its iPhones and some iPads used Arm-based chips. x86 chips and Arm chips like the M1, M1 Pro, and M1 Max are built using different architectures, so the transition from x86 to Arm has taken some effort.
Apple used Intel’s chips in its Mac lineup since 2006 after transitioning away from PowerPC processors, which has meant that Apple was subject to Intel’s release timelines, chip delays, and security issues, which at times, negatively affected Apple’s own device release plans.
Apple has cited platform consolidation and performance advantages as reasons for ditching Intel chips, but one former Intel engineer claimed that Intel’s issues with Skylake chips drove Apple to speed up development of its Arm-based chips. There have been rumors about Apple designing its own Mac chips since 2014, so the decision to stop using Intel chips was in the works for a long time.
Swapping to house-made chips lets Apple release updates on its own schedule and with more regular technology improvements, plus Apple is also able to differentiate its devices from competing products with tight integration between software and hardware, similar to its iOS platform and A-series chips.
Common iOS and Mac Architecture
With Apple designing its own chips for iOS devices and Macs, there is a common architecture across all Apple product lines, which makes it easier for developers to write and optimize software that runs on all Apple products.
In fact, apps designed for the iPhone and the iPad can run on Apple silicon natively, and compatible iOS apps can be downloaded from the Mac App Store on an M1 Mac.
Easing the Transition
macOS is equipped with tools to help both developers and Apple customers transition from Intel chips to Apple silicon. All Apple apps, including Apple’s pro apps like Final Cut Pro and Logic Pro, are already running natively on Apple silicon and are available on M1 Macs. Since the launch of Apple silicon Macs, developers big and small have introduced native support.
Developers can use Xcode to get their apps up and running on Apple silicon in just a matter of days, and Apple has developed tools for building new Universal 2 app binaries that work on Intel Macs and Macs built on Apple silicon so developers can still support Intel Macs with a single binary for all users.
Support for Intel Macs
Apple will continue to release software updates for Intel Macs for years after the transition to Apple silicon, so those who purchase Intel-based Macs can expect to receive macOS updates throughout the life of their machines.
Running Intel Apps on Apple silicon
Apple expects most developers to develop native apps quickly, but users can run Intel apps even if those apps haven’t been updated, thanks to Rosetta 2, a translation process that runs in the background and is invisible to the user.
Rosetta 2 translates existing Intel apps so they work on Macs equipped with Apple silicon quickly, seamlessly, and without issues. Apple has demoed Rosetta 2 with apps and games and there’s no difference between running an Intel app on an Intel machine and on an Apple silicon machine. All of the features work and the software is just as quick.
Apple has also introduced new virtualization technologies that will let developers run Linux or tools like Docker. Rosetta 2 does not support virtualization using apps like VMware or Parallels, so it is not possible to run Windows using that method unless the apps are rebuilt for Apple silicon, and it’s not clear if that will happen at this time in regard to licensing.
No Boot Camp
Windows does not operate in Boot Camp mode on Macs that run Apple silicon as Microsoft only licenses Windows 10 on Arm to OEMs and has no current plans make an Arm-based version of Windows freely available.
Apple has also said that it does not plan to support Boot Camp on its future Macs. We’re not direct booting an alternate operating system, Apple software engineering chief Craig Federighi said. Purely virtualization is the route. If, however, Microsoft releases an Arm-based version of Windows that consumers can purchase, things might change.
Apple silicon Macs and Thunderbolt Support
Apple is transitioning away from Intel’s chips in its Mac and is instead opting to use Apple silicon chips, but Apple is continuing to support Intel’s Thunderbolt USB-C standard. The M1 Macs support USB 4 and Thunderbolt 3.
Current Arm-Based Macs
Apple has released the 2020 MacBook Air, 13-inch MacBook Pro, and Mac mini with M1 chips, replacing the low-end machines in those lineups. In 2021, Apple added the M1 iPad Pro models, the M1 iMac, and the M1 Pro and M1 Max MacBook Pro models, and in 2022, Apple added the M1 Ultra Mac Studio, the M2 MacBook Air, and the M2 13-inch MacBook Pro.
Future Arm-Based Macs
Apple is working on updated Apple silicon chips designed for the Mac Pro, 27-inch iMac, and high-end Mac mini, according to Bloomberg.
The Mac mini and iMac could use next-generation M2 Pro and M2 Max chips, and Apple is also working on even higher-powered chips for the Mac Pro. The chip that’s in the works for the Mac Pro will feature two processors that are either twice or four times as powerful as the M1 Max MacBook Pro chip. These chips will feature 20 or 40 computing cores with 16 high-performance or 32 high-performance cores and four or eight high-efficiency cores, along with 64 and 128 core options for graphics.
Have questions about Apple’s work on Arm-based Macs or want to offer feedback on this guide? Send us an email here.
iPhone 14 Pro’s A16 Bionic CPU specs details just started to leak
Each new iPhone generation brings a brand new A-series System-in-Chip (SoC) that’s more powerful and energy-efficient than the last. And every new A-series chip has no rival on the Android side, significantly outperforming same-year competitors from Qualcomm and Samsung. The same goes for the iPhone 14. The new handset series will feature Apple’s brand new silicon for mobile devices. But unlike in previous years, the A16 Bionic will reportedly only power the iPhone 14 Pro and iPhone 14 Pro Max.
Tech. Entertainment. Science. Your inbox.
Sign up for the most interesting tech entertainment news out there.
That’s according to various leaks that claim Apple is looking to further differentiate the regular and Pro variants. Putting a different chip in the cheaper iPhone 14 models might do the trick, especially considering that Apple has no real rival from Android.
With that in mind, we have a new leak that gives us early details about the A16 Bionic specs.
Not all iPhone 14 chips are the same
Pick any iPhone launch event and search for the performance segment. You’ll see Apple brag about the capabilities of its newest SoC. Choose one of the newer iPhones and you’ll see Apple bash rivals by claiming that the next best processor in the industry is available from year-old iPhones rather than a current Android flagship handset.
One example is immediately available from this year’s Galaxy S22 benchmarks. The Android handset failed to outperform the 2019 iPhone 11 in some tests. Even more embarrassing is the fact that Samsung was cheating to get those benchmark scores.
With that in mind, the A16 Bionic’s closest competition this year will probably be the A15 Bionic that powers all the iPhone 13 models. And rumors say Apple will use that A15 Bionic for one more year. The SoC will reportedly be found inside the iPhone 14 and iPhone 14 Max, although the handsets will have 6GB of RAM instead of 4GB of RAM like the cheapest iPhone 13 models.
over, rumors say the A15 Bionic in the iPhone 14 models get some mild upgrades. Or it might match the iPhone 13 Pro’s A15. There is a slight difference between the A15 powering the iPhone 13 Pro and the A15 inside the iPhone 13 and 13 mini. The latter has a 4-core GPU, compared to a 5-core GPU on the Pro models.
The A16 Bionic should deliver the biggest SoC upgrades this year, but they’ll supposedly be restricted to the iPhone 14 Pro and Pro Max.
Leaked A16 Bionic specs in the iPhone 14 Pro
A leaker posted a thread on about Apple’s various SoC versions coming this year.
The A16 Bionic is at the top of the list, with well-known leaker ShrimpApplePro claiming the iPhone 14 Pro chip will be a 5nm TSMC creation. That means Apple won’t make the jump to 4nm yet, a node that rivals already use.
Even so, the A16 Bionic should deliver a better CPU and GPU, plus support for LPDDR5 RAM. That last note is of real interest, as it’ll allow Apple to use the fastest possible RAM. Currently, all iPhone 13 models utilize LPDDR4X RAM.
The leaker did not offer any benchmarks for the A16 Bionic, however. It’s unclear what sort of improvements we’re looking at compared to the 2021 SoC.
However, ShrimpApplePro also mentioned the next-gen M-series SoC in the same thread.
The M2 will be a 3nm processor and it might feature a custom ARMv9 chip. The leaker also mentioned the last SoC in the M1 series, which will feature updated Avalanche (high-performance) and Blizzard (energy-efficient) cores.
The A16 Bionic that powers the iPhone 14 Pro should be announced before any new M-series SoCs. Apple will likely launch the new iPhones in September. Any Mac launches the company might have on its calendar for 2022 likely won’t take place before the iPhone 14 press conference.
iPhone coverage: For more iPhone news, visit our iPhone 14 guide.
What Is the Apple Neural Engine and What Does It Do?
When Apple launched the A11 Bionic chip in 2017, it introduced us to a new type of processor, the Neural Engine. The Cupertino-based tech giant promised this new chip would power the algorithms that recognize your face to unlock the iPhone, transfer your facial expressions onto animated emoji and more.
Since then, the Neural Engine has become even more capable, powerful and faster. Even so, many people wonder what precisely the Neural Engine is and what it does. Let’s dive in and see what this chip dedicated to AI and machine learning can do.
Apple Neural Engine Kicked Off the Future of AI and
Apple’s Neural Engine is Cupertino’s name for its own neural processing unit (NPU). Such processors are also known as Deep Learning Processors, and handle the algorithms behind AI, augmented reality and machine learning (ML).
The Neural Engine allows Apple to offload certain tasks that the central processing unit (CPU) or graphics processing unit (GPU) used handle.
You see, an NPU can (and is designed to) handle specific tasks much faster and more efficiently than more generalized processors can.
In the early days of AI and machine learning, almost all of the processing fell to the CPU. Later, engineers tasked the GPU to help. These chips aren’t designed with the specific needs of AI or ML algorithms in mind, though.
Enter the NPU
That’s why engineers came up with NPUs such as Apple’s Neural Engine. Engineers design these custom chips specifically to accelerate AI and ML tasks. Whereas manufacturers design a GPU to accelerate graphics tasks, the Neural Engine boosts neural network operations.
Apple, of course, isn’t the only tech company to design neural processing units. Google has its TPU, or Tensor Processing Unit. Samsung has designed its own version of the NPU, as have Intel, Nvidia, Amazon and more.
To put it into perspective, an NPU can accelerate ML computational tasks by as much as 10,000 times the speed of a GPU. They also consume less power in the process, meaning they are both more powerful and more efficient than a GPU for the same job.
Tasks the Apple Neural Engine Takes Responsibility For
It’s time to dive into just what sort of jobs the Neural Engine takes care of. As previously mentioned, every time you use Face ID to unlock your iPhone or iPad, your device uses the Neural Engine. When you send an animated Memoji message, the Neural Engine is interpreting your facial expressions.
That’s just the beginning, though. Cupertino also employs its Neural Engine to help Siri better understand your voice. In the Photos app, when you search for images of a dog, your iPhone does so with ML (hence the Neural Engine.)
Initially, the Neural Engine was off-limits to third-party developers. It couldn’t be used outside of Apple’s own software. In 2018, though, Cupertino released the CoreML API to developers in iOS 11. That’s when things got interesting.
The CoreML API allowed developers to start taking advantage of the Neural Engine. Today, developers can use CoreML to analyze video or classify images and sounds. It’s even able to analyze and classify objects, actions and drawings.
History of Apple’s Neural Engine
Since it first announced the Neural Engine in 2017, Apple has steadily (and exponentially) made the chip more efficient and powerful. The first iteration had two neural cores and could process up to 600 billion operations per second.
The latest M2 Pro and M2 Max SoCs take that capability much, much farther. The Neural Engine in these SoCs have 16 neural cores. They can grind through up to 15.8 trillion operations every second.
Apple’s Neural Engine Version History (Information Credit: Apple Wiki)
Apple has truly molded the iPhone, and now the Mac, experience around its Neural Engine. When your iPhone reads the text in your photos, it’s using the Neural Engine. As Siri figures out you almost always run a specific app at a certain time of the day, that’s the Neural Engine at work.
Since first introducing the Neural Engine, Apple has even embedded its NPU in a task as seemingly mundane as photography. When Apple refers to the image processor making a certain number of calculations or decisions per photo, the Neural Engine is at play.
The Foundation of Apple’s Newest Innovations
The Neural Engine also helps with everything Apple does in AR. Whether it’s allowing the Measure app to give you the dimensions of an object or projecting a 3D model into your environment through the camera’s viewfinder, that’s ML. If it’s ML, chances are the Apple Neural Engine boosts it tremendously.
This means, of course, that Apple’s future innovations hinge on the Neural Engine. When Cupertino finally unleashes its mixed reality headset on the world, the Neural Engine will be a big part of that technology.
Even further, Apple Glass, the rumored augmented reality glasses expected to follow the mixed reality headset, will depend on Machine Learning and the Neural Engine.
So, from the simple act of recognizing your face to unlock your iPhone to helping AR transport you to a different environment, the Neural Engine is at play.
Leave a Reply Cancel reply
You must be logged in to post a comment.