Difference between revisions of "Apple M1"
Jump to navigation
Jump to search
Tags: Mobile web edit, Mobile edit |
|||
(One intermediate revision by the same user not shown) | |||
Line 1: | Line 1: | ||
[[wikipedia:Apple M1]] (November 2020) | [[wikipedia:Apple M1]] (November 2020) | ||
− | * Pro, Max, Ultra | + | * Pro, Max, [[Ultra]] |
Line 11: | Line 11: | ||
* [[MacBook Pro]] 5th generation (13-inch, M1, Nov 2020) | * [[MacBook Pro]] 5th generation (13-inch, M1, Nov 2020) | ||
* [[iMac]] (May 2021) | * [[iMac]] (May 2021) | ||
+ | * [[iPad Air (5th generation)]] | ||
Latest revision as of 21:04, 10 April 2024
wikipedia:Apple M1 (November 2020)
- Pro, Max, Ultra
- 5 nm
- Apple M1 Pro, 32 GB max memory
- Apple M1 Max, 64 GB max memory
- MacBook Air (M1, 2020)
- Mac mini (M1, 2020)
- MacBook Pro 5th generation (13-inch, M1, Nov 2020)
- iMac (May 2021)
- iPad Air (5th generation)
- Dedicated neural network hardware in a 16-core Neural Engine, capable of executing 11 trillion operations per second
- ISP
Initial support for the M1 SoC in the Linux kernel was released on June 27, 2021, with version 5.13
Contents
GPU[edit]
Apple's claim can execute nearly 25,000 threads simultaneously and have a maximum floating point (FP32) performance of 2.6 TFLOPs.
Errata[edit]
The M1 chip has errata given the name "M1RACLES". Two sandboxed applications can exchange data without the system's knowledge by using an unintentionally writable processor register as a covert channel, violating the security model and constituting a minor vulnerability. It was discovered by Héctor Martín Cantero
Related[edit]
- Asahi Linux
- Apple silicon
uname -m
- Apple M2 (June 6, 2022)
- Apple Neural Engine (ANE)
See also[edit]
Advertising: