Overview of the Apple M1 chip architecture

The M1 chip is Apple's first processor for Macs. Since its release in November 2020, it has shaped Apple's product lineup and set a new standard for what consumers can expect from their devices.

Although the world has moved past M1 technology, it's still worth considering the shift it caused in how we think of processor technology for personal computers today. This is because its architecture combines high performance with exceptional energy efficiency.

In this article, you'll understand the M1 chip architecture and how much it changed the world of processors. You'll go through the variations of Apple's M1 chip and understand why it has become so popular.

What is an M1 chip?

The Apple M1 chip is a processor that provides Apple products with better performance and efficiency than the previously used Intel processors. It's able to provide such high-end capabilities due to its ARM-based System on a Chip (SoC) architecture.

The M1 chip combines multiple components, such as the CPU, GPU, Neural Engine, and unified memory, into a single silicon chip. This integration makes it perform better and faster while consuming less power.

One of the standout features of the M1 chip is its Unified Memory Architecture (UMA). This architecture allows the CPU, GPU, and other components to access the same memory pool, reducing the time data moves around different components during processing.

The birth of the M1 chip

To fully understand why Apple developed the M1, it's essential to examine the history of processor architecture and the technological principles that guided its creation.

RISC vs. CISC

Traditionally, processors were built using one of two architectures. Either the Reduced Instruction Set Computer (RISC) or the Complex Instruction Set Computer (CISC).

CISC processors, like those from Intel and AMD, are designed to execute complex instructions directly. These are efficient for certain tasks but often result in greater power consumption and heat generation.

RISC processors, on the other hand, use a simpler instruction set. They require multiple instructions to perform complex tasks but generally achieve greater efficiency and performance.

The role of ARM

Acorn RISC Machine (ARM), as the name suggests, is known for its RISC-based processor designs. This design played a crucial role in the development of the M1 chip.

Previously, Apple had already had success using ARM-based processors on some of its devices (iPhones & iPads), demonstrating the potential for these processors to do exceptionally well.

The ARM Big.LITTLE architecture

A significant innovation in ARM's design philosophy is the big.LITTLE architecture. This is the same architecture that Apple would integrate into its M1 chip. The approach of this architecture involves combining high-performance (big cores) and high-efficiency cores (little cores).

The high-performance cores handle demanding tasks, such as video editing and gaming, while the high-efficiency cores manage less intensive tasks, like web browsing and email. This design allows the chip to switch between cores while providing optimal performance and energy efficiency.

Bringing the M1 to light

The development of the M1 chip resulted from years of research and development.

Apple's engineering teams worked very hard to design a System on a Chip (SoC) that integrated the CPU, GPU, Neural Engine, and more into a single, unified architecture.

This integration was key to achieving the high levels of performance and efficiency that the M1 is known for.

Why is the M1 chip so popular?

Aside from all the features mentioned above and the UMA, the M1 chip stood out for two prominent reasons.

Speed

One defining characteristic of the Apple M1 when it rolled out was its speed compared to its Intel predecessors.

The image below shows the Geekbench 5 benchmark scores for both processors in a MacBook Air.

The M1 processor is approximately two times faster in single-core performance and 2.54 times faster in multi-core performance than the former:

Figure 1: Geekbench 5 scores for MacBook Air with Intel and M1 processors

This difference in speed is due to Apple's design - SoC architecture and eight CPU cores. The high-performance cores handle intensive tasks swiftly, while the high-efficiency cores manage lighter tasks without draining the battery life.

Design

The M1 chip's design is a marvel of engineering. The proximity between all its components allows for faster communication and data transfer.

As part of its design, the M1 is built on a 5-nanometer process, packing 16 billion transistors onto the chip. This dense transistor counts not only boosts performance but also improves power efficiency.

The chip's design also uses a fanless architecture in many devices, contributing to quieter operation and sleeker, thinner form factors.

M1's architecture

As mentioned earlier, the M1 chip architecture combines multiple components on its single SoC. This design aims to reduce the distance data needs to travel and allows for better coordination between components.

Figure 2: M1 Architecture by Fonearena

The Central Processing Unit (CPU) in the M1 chip consists of four high-performance and four high-efficiency cores. The high-performance cores handle demanding tasks, while the high-efficiency cores handle less intensive tasks, focusing on overall power usage.

The Graphics Processing Unit (GPU) within the M1 chip is dedicated to graphics rendering, which is crucial for activities like video playback, photo editing, and gaming. This GPU is designed to deliver powerful graphics performance while consuming minimal power, contributing to the chip's overall efficiency.

As earlier emphasized, one of the key features of the M1 chip is its Unified Memory Architecture (UMA). This shared memory system means that data doesn't need to be copied between different memory areas, which speeds up processing and improves performance.

Additionally, the M1 chip includes a neural engine designed for machine learning tasks. This neural engine can handle up to 11 trillion operations per second, making it highly efficient for AI-related functions like image and speech recognition.

The chip also integrates various other specialized processors, such as an image signal processor for enhancing camera functionality and a storage controller for managing data storage efficiently.

How does all this work together?

Imagine you're using a MacBook Air with an M1 chip, and you decide to run four different processes at the same time. Let's say editing a high-resolution video, browsing the web with multiple tabs open in Safari, syncing your files to iCloud, and listening to music on Apple Music.

First, let's look at the video editing task. This is a highly demanding process that requires significant computational power. Here, M1's high-performance cores, known as Firestorm, kick into action. Since these cores are optimized for heavy lifting, they will handle the video editing tasks swiftly.

Back to Safari. Some tabs might be running JavaScript-heavy websites or streaming videos. While this task is less demanding than video editing, it still requires a good amount of processing power. The remaining high-performance cores will effectively handle this task without slowing down your video editing.

Now, let's consider the background task of syncing your files to iCloud. This process is less intensive and can be managed by the high-efficiency cores known as Icestorm. These cores are designed for tasks that don't need as much processing power but still need to be completed efficiently. By offloading these lighter tasks to the high-efficiency cores, the M1 chip ensures that the high-performance cores remain focused on more demanding applications.

Finally, you're also listening to music on Apple Music. Streaming music is a relatively light task, and it can be managed alongside other processes without requiring significant computational resources. The high-efficiency cores can handle this task without any issues, ensuring that your music plays smoothly while you work on your other activities.

The M1's unified memory architecture (UMA) further enhances the performance of these concurrent tasks. For example, let's say you need to pull a high-resolution image from your photo library while you're editing the video. The shared memory allows you to retrieve data quickly while reducing latency and improving the overall speed of your workflow.

Variations of M1

The M1 chip family includes several variations designed to cater to performance needs and device types.

These variations include the original M1, the M1 Pro, the M1 Max, and the M1 Ultra. Below is an overview of each variant, how they differ, and the devices they power:

M1

The original M1 chip features an 8-core CPU, an integrated GPU with up to 8 cores, and a 16-core Neural Engine.

The M1 focuses on balancing performance and power efficiency. It's built on a 5-nanometer process and integrates multiple components into a single chip, including the CPU, GPU, and memory.

The M1 chip is used in the MacBook Air, 13-inch MacBook Pro, Mac mini, and 24-inch iMac. It's also found in the iPad Pro, which provides desktop-level performance in a tablet form factor.

M1 Pro

The M1 Pro was announced 11 months (October 2021) after M1. It enhances the original M1 with more cores and higher memory capacity. It features up to a 10-core CPU (eight high-performance cores and two high-efficiency cores) and a GPU with up to 16 cores.

The M1 Pro supports more unified memory (up to 32GB) and higher bandwidth. It also includes additional Thunderbolt controllers for more external device support.

The M1 Pro powers the 14-inch and 16-inch MacBook Pro models, providing significant performance boosts for professional users needing more computational power and memory.

M1 Max

The M1 Max, released in October 2021, is a further step from the M1 Pro. It features the same 10-core CPU but a significantly more powerful GPU with up to 32 cores.

The M1 Max doubles the memory bandwidth of the M1 Pro and supports up to 64GB of unified memory. This makes it ideal for graphics-intensive tasks and workflows that require substantial memory and bandwidth, such as 3D rendering, video editing, and machine learning.

The M1 Max is available in the 14-inch and 16-inch MacBook Pro models and Mac Studio.

M1 Ultra

The M1 Ultra, introduced in March 2022, is the most powerful variant of the M1 family. It essentially combines two M1 Max chips using a technology Apple calls UltraFusion, which connects the two dies with a high-speed interconnect.

The M1 Ultra features up to a 20-core CPU and a GPU with up to 64 cores. It supports up to 128GB of unified memory and offers double the memory bandwidth of the M1 Max, making it an absolute powerhouse for the most demanding professional workloads.

The M1 Ultra is used in the Mac Studio.

Below is a table that summarises all the features of each member of the M1 chip family:

Figure 3: Summary of Properties for the variants of the M1 Chip

Drawbacks of M1

While the M1 chip has received widespread applause for its performance and efficiency, there are two drawbacks that you should be aware of.

Compatibility issues

One of the primary concerns with the M1 chip is compatibility. Since the M1 uses ARM architecture, some older software designed for Intel's x86 architecture doesn't run natively on M1 devices.

Apple has implemented Rosetta 2, a translation layer that allows most Intel-based applications to run on M1 Macs. However, occasional issues with performance or compatibility, particularly with more specialized or legacy software, can still occur.

Limited customization

Devices that use the SoC architecture, like the M1 chip, have limitations in upgrading components.

The RAM and storage are soldered onto the motherboard, making it impossible for you to upgrade these components after purchase.

This can be a limitation if you need more memory or storage capacity in the future.

In the End...

The M1 chip has done amazing things over the years and changed the world of personal computers. Its impeccable SoC architecture, comprising a unified memory architecture (UMA), high-performance and high-efficiency cores, and integrated GPU, set a new standard for what processors could achieve in terms of performance and efficiency.

In addition to the variants of the M1 chip, Apple has gone further in creating more powerful chips for Macs. With the inclusion of M2 and, most recently, M3, they have pushed the barriers of personal computers to another level. All this began with the bold move of transitioning from intel-based x86 architecture Macs to M1 chips.

Like this article? Sign up for our newsletter below and become one of over 1000 subscribers who stay informed on the latest developments in the world of DevOps. Subscribe now!