All articles tagged with #neural engine
Apple’s self-driving car effort never shipped, but it spurred the Neural Engine and a lineage of on-device AI hardware—from the iPhone X’s A11 Bionic to the M-series—making Apple a hardware-driven AI player. The company is accelerating the M7 line, skipping M6 variants, with the M7 Ultra expected to power a new server product and upgrade Neural Engine capabilities, including up to 1.5TB RAM.
Apple’s Doug Brooks says the Mac mini (and Mac Studio) are in “incredible demand” for running AI agents locally, as developers favor systems that are always on and under user control. He frames agentic AI as a whole‑chip challenge rather than just a GPU one, powered by Neural Engine and other neural accelerators to enable on‑device AI. Brooks envisions a hybrid future where some workloads run locally while others are offloaded to the cloud for privacy and cost reasons, and cites “transparent AI” features on iPhone/iPad and Mac (like Draw Things and SwingVision) as examples of AI quietly working in the background. The interview underscores Apple’s chip‑and‑software approach to push on‑device AI forward, a trend likely to accelerate after WWDC 2026.
A leaked motherboard image suggests the iPhone 18 Pro will use Wafer-Level Multi-Chip Module (WMCM) packaging for the A20 Pro, relocating DRAM to the side to spread heat and reduce throttling while maintaining high speed. The A20 Pro is also said to feature LPDDR6 memory with a 96-bit bus and a substantially expanded Neural Engine, boosting bandwidth and on-device AI performance. The WMCM approach could enable more chiplet variants and lower production waste. The leak is tied to a hacked Tata iPhone factory, though the image’s provenance remains unconfirmed.
iOS 27, due this fall alongside the iPhone 18 Pro/Max/Fold, is expected to boost battery life through code optimizations, larger battery cells (Pro ~4,252 mAh, Pro Max ~5,088 mAh, Fold rumored 5.5–5.8k mAh), and a more efficient Neural Engine with throttling and smarter background task handling, plus a redesigned 48-hour re-indexing process to reduce post-update drain.
Apple is set to refresh its MacBook Pro lineup with M4 chips, expected to debut in late 2024. The M4 will be built on a 3-nanometer process, focusing on AI capabilities with an upgraded Neural Engine. The entry-level 14-inch MacBook Pro will feature the standard M4 chip, while higher-end models will have M4 Pro and M4 Max chips. No design changes are anticipated, and the launch timeline is estimated for late 2024 to early 2025.
The upcoming iPhone 16 series is rumored to feature a significant upgrade in AI computing cores, potentially increasing the Neural Engine performance to 24 or 32 cores, along with improvements in existing processors. Reports also suggest that generative AI features will be exclusive to the 2024 iPhone series, and Apple is working on using generative AI to accelerate software development. Additionally, design changes related to the updated processor, including a new camera bump arrangement, may enable spatial video recording.
Apple is set to introduce AI features in iOS 18, with some exclusive to the iPhone 16 lineup, making it a compelling upgrade over the iPhone 15. The iPhone 16 models will boast an upgraded Neural Engine with the A18 chip, enhancing their ability to handle AI-centric tasks efficiently. Apple's AI efforts will extend to various apps and system-level operations, potentially revolutionizing Siri and Spotlight Search. While specific details are yet to be confirmed, the iPhone 16 is expected to leverage powerful internals to fully utilize the forthcoming AI features and upgrades.
Apple is rumored to be upgrading the Neural Engine in its upcoming A18 chip for the iPhone 16 lineup to handle the generative AI features expected to debut with iOS 18. The improved Neural Engine with additional cores will enable faster AI and machine learning tasks, potentially allowing for better on-device processing of AI-related features. This upgrade aligns with Apple's focus on developing custom generative AI models and tools, such as Keyframer, and could also enhance Siri's capabilities. Additionally, the company is expected to improve the performance of the Neural Engine on Macs with the forthcoming M4 chips.
Apple is rumored to be enhancing the AI computing power of its upcoming M4 and A18 processors for the iPhone 16, potentially significantly increasing the number of AI computing cores and performance. This aligns with rumors of iOS 18 featuring new AI features, although skepticism is advised due to the source's mixed track record. The more powerful Neural Engine in the iPhone 16 may be aimed at future-proofing and improving the performance of iOS 18's features, while questions remain about whether it will be exclusive to the iPhone 16 Pro's version of the A18 chip.
Apple's upcoming A18 and M4 chips for future iPhone and Mac models are rumored to feature an upgraded Neural Engine with "significantly" more cores, enhancing AI/machine learning performance. iOS 18 is expected to introduce new generative AI features, and the A18 series chips are likely to debut in the iPhone 16 models in September. The upgraded Neural Engine could enable exclusive generative AI features for the iPhone 16. Additionally, most Mac models with Apple silicon chips are equipped with a 16-core Neural Engine, and the first Macs with an M4 chip may be released in late 2024 or early 2025.
Market intelligence company Canalys predicts that Windows PC brands will introduce their own equivalent of Apple's Neural Engine chips into high-end laptops this year, with around 20% of PCs launched in 2022 expected to have their own AI chips. Canalys forecasts that by 2027, over 170 million AI-capable PCs will be shipped, with nearly 60% being deployed in commercial settings. This move signifies a shift towards on-device AI processing in PCs, with potential benefits for productivity, security, and cost management in the commercial sector.
Apple is emphasizing the importance of data security by promoting the idea of keeping personal data out of the cloud. During its recent event, Apple highlighted features in its new A17 Pro System on Chip (SoC) for the iPhone 15 Pro and the S9 System in Package (SiP) for the Apple Watch Series 9 that enhance personal data security by processing information on-device instead of sending it to the cloud. The increased capability of the Neural Engine components in these systems allows for faster and more secure processing of Siri requests and health queries, eliminating the need for roundtrip cloud data movement. By keeping data on the device, Apple aims to provide greater security and faster performance for users, emphasizing that their data is safer on Apple devices.
Apple avoided using the term "AI" during its WWDC keynote event and instead focused on terms like "machine learning" and "ML." Apple's new transformer model in iOS 17 allows sentence-level autocorrections that can finish either a word or an entire sentence when you press the space bar. Apple's on-device AI processing is easy because of a special portion of Apple Silicon chips called the Neural Engine, which is designed to accelerate machine learning applications. Apple also debuted a new app called Journal that allows personal text and image journaling, which uses on-device machine learning to create personalized suggestions of moments to inspire writing.