Neural Engine
{{Short description|AI acceleration processor series by Apple}}
{{Multiple issues|
{{rough translation|date=January 2024}}
{{Primary sources|date=December 2023}}
}}
Neural Engine is a series of AI accelerators designed for machine learning by Apple. The first SoC including Neural Engine is Apple A11 Bionic for iPhone 8, 8 Plus and iPhone X introduced in 2017.{{Cite web |last=Butts |first=Jeff |date=2023-02-16 |title=What Is the Apple Neural Engine and What Does It Do? |url=https://www.macobserver.com/tips/deep-dive/what-is-apple-neural-engine/ |access-date=2023-12-26 |website=The Mac Observer |language=en-US}} Since then, all Apple A series SoCs have Neural Engine. In 2020, Apple introduced the Apple M1 for Mac{{Cite press release |title=Apple unleashes M1 |url=https://www.apple.com/newsroom/2020/11/apple-unleashes-m1/ |access-date=2023-12-26 |website=Apple Newsroom |language=en-US}} and all Apple M series SoCs have Neural Engine.{{Cite press release |title=Introducing M1 Pro and M1 Max: the most powerful chips Apple has ever built |url=https://www.apple.com/newsroom/2021/10/introducing-m1-pro-and-m1-max-the-most-powerful-chips-apple-has-ever-built/ |access-date=2023-12-26 |website=Apple Newsroom |language=en-US}}{{Cite press release |title=Apple unveils M2 with breakthrough performance and capabilities |url=https://www.apple.com/newsroom/2022/06/apple-unveils-m2-with-breakthrough-performance-and-capabilities/ |access-date=2023-12-26 |website=Apple Newsroom |language=en-US}}{{Cite press release |title=Apple unveils M2 Pro and M2 Max: next-generation chips for next-level workflows |url=https://www.apple.com/newsroom/2023/01/apple-unveils-m2-pro-and-m2-max-next-generation-chips-for-next-level-workflows/ |access-date=2023-12-26 |website=Apple Newsroom |language=en-US}}{{Cite press release |title=Apple unveils M3, M3 Pro, and M3 Max, the most advanced chips for a personal computer |url=https://www.apple.com/newsroom/2023/10/apple-unveils-m3-m3-pro-and-m3-max-the-most-advanced-chips-for-a-personal-computer/ |access-date=2023-12-26 |website=Apple Newsroom |language=en-US}}{{cite press release |title=Apple introduces M4 chip |url=https://www.apple.com/newsroom/2024/05/apple-introduces-m4-chip/ |website=Apple Newsroom |access-date=7 May 2024}}
Apple has stated the Neural Engine in the M4 can perform 38 trillion operations per second (TOPS), an improvement over the 18 TOPS in the M3.{{cite news |author1=Andrew Cunningham |title=Apple announces M4 with more CPU cores and AI focus, just months after M3 |url=https://arstechnica.com/apple/2024/05/apple-announces-m4-with-more-cpu-cores-and-ai-focus-just-months-after-m3/ |access-date=8 May 2024 |work=ArsTechnica |date=7 May 2024 |quote=Apple says the M4 runs up to 38 trillion operations per second (TOPS) […] The M3's Neural Engine is only capable of 18 TOPS}}
Applications
The Neural Engine is used for real-time AI-driven applications such as Face ID, Siri, and augmented reality (AR). It also handles computational photography features, including Smart HDR and Night Mode, by processing vast amounts of sensor data for real-time image enhancements.{{Cite web|title=Neural Engine AI Basics|url=https://www.aionlinecourse.com/ai-basics/neural-engine|website=AI Online Course|access-date=26 December 2023}}
Energy efficiency and privacy
The Neural Engine also provides high energy efficiency, allowing real-time AI tasks to be performed with minimal battery consumption.{{citation needed|date=October 2024}} Its on-device processing ensures that sensitive tasks such as facial recognition and voice commands are handled locally, enhancing privacy by keeping user data secure.
Developer tools
The Neural Engine is fully integrated with Apple's Core ML framework, which allows developers to run machine learning models on-device. This integration supports applications like object recognition, natural language processing, and gesture detection.