Apple is expected to use TSMC's base 2-nanometer N2 process rather than the newer N2P variant for its upcoming A20 and M6 chips, according to the China Times.


Apple is rumored to launch the A20 chip with new iPhone models in the fall, and the M6 family of Apple silicon chips in redesigned MacBook Pro models featuring OLED displays later this year. The latest report claims that the company will not move to TSMC's most advanced 2-nanometer manufacturing variant for these chip generations.

TSMC's 2-nanometer family marks the company's transition from FinFET transistors to gate-all-around technology, which is intended to improve power efficiency and performance scaling as chip densities increase. TSMC previously said that its base N2 process will enter mass production in 2026, followed by enhanced variants including N2P and A16 in the second half of the year.

N2P is positioned as a higher-performance version of N2, while A16 is designed for high-power and high-complexity chips, particularly for AI applications and data centers. The performance difference between N2 and N2P is expected to be modest. N2P offers roughly a 5% performance gain at the same power level, but comes at a higher manufacturing cost, which helps explain why Apple is expected to remain on N2 for its A- and M-series chips this year.

Competitors including Qualcomm and MediaTek are expected to adopt N2P for their flagship mobile chips in order to reach higher peak clock speeds. TSMC apparently expects the 2-nanometer generation to have a long lifecycle and potentially scale beyond its 3-nanometer family. Companies including AMD, Google, and Amazon are expected to adopt 2-nanometer processes for future CPUs, GPUs, and AI chips.

Supply availability is also thought to be a factor. Demand for 2-nanometer manufacturing has apparently exceeded expectations, with much of the initial N2 capacity already reserved by leading customers such as Apple. This early capacity allocation reduces the need for Apple to move to N2P simply to secure production volume for future A-series and M-series chips.

Crucially, since N2P only begins mass production in the second half of the year, it likely does not leave enough time for Apple to introduce chips made with the newer technology to its devices. N2 chips are already in production.
This article, "Apple Seemingly Avoiding Latest Chip Tech for New iPhones and Macs" first appeared on MacRumors.com

Today marks the fifth anniversary of the Apple silicon chip that replaced Intel chips in Apple's Mac lineup. The first Apple silicon chip, the M1, was unveiled on November 10, 2020. The M1 debuted in the MacBook Air, Mac mini, and 13-inch MacBook Pro.


The ‌M1‌ chip was impressive when it launched, featuring the "world's fastest CPU core" and industry-leading performance per watt, and it's only improved since then. We've had five total generations of Apple silicon chips, with the M5 unveiled in the 14-inch ‌MacBook Pro‌ just last month.

Here's how the M5 measures up to the ‌M1‌, per Apple's M5 specs:

• 6× faster CPU/GPU performance


• 6× faster AI performance


• 7.7× faster AI video processing


• 6.8× faster 3D rendering


• 2.6× faster gaming performance


• 2.1× faster code compiling

Geekbench comparison scores:

• ‌M1‌ single-core - 2,320


• M5 single-core - 4,263


• ‌M1‌ multi-core - 8,175


• M5 multi-core - 17,862


• ‌M1‌ Metal - 33,041


• M5 Metal - 75,637

Both CPU and GPU performance have increased significantly over the past five years, and Apple has boosted AI and gaming performance too with add-ons like hardware-accelerated ray tracing and an ever-improving Neural Engine.

‌M1‌ Chip	M5 Chip
Made with TSMC's 5nm process (N5)	Made TSMC's third-generation 3nm process (N3P)
Based on A14 Bionic Pro chip from iPhone 12	Based on A19 Pro chip from iPhone 17 Pro
8-core CPU, 8-core GPU	10-core CPU, 10-core GPU
3.2 GHz CPU clock speed	4.61 GHz CPU clock speed
No integrated Neural Accelerators	Integrated Neural Accelerator in every GPU core
No ray tracing engine	Third-generation ray tracing engine
No dynamic caching	Second-generation dynamic caching
Support for up to 16GB unified memory	Support for up to 32GB unified memory
68.25 GB/s unified memory bandwidth	153 GB/s unified memory bandwidth

Apple sold Apple silicon Macs alongside Intel Macs for three years, but phased out the final Intel Mac in June 2023 when the 2019 Mac Pro was discontinued. Now all of Apple's devices have Apple chips, and we're even hitting the end of the road for Intel Mac software support. Intel Macs won't get software updates after macOS Tahoe.

Over the next five years, Apple silicon chip technology will continue to evolve. Apple supplier TSMC is already working on 2nm chips that could make an appearance as soon as 2026, offering a 10 to 15 percent speed improvement and a 25 to 30 percent power reduction. 1.4nm chips could follow as soon as 2028 for even more power and efficiency.
This article, "Five Years of Apple Silicon: M1 to M5 Performance Comparison" first appeared on MacRumors.com

Discuss this article in our forums

Apple today announced the M5 chip, its next-generation chip for the MacBook Pro, iPad Pro, and Vision Pro.


From Apple's press release:

Built using third-generation 3-nanometer technology, M5 introduces a next-generation 10-core GPU architecture with a Neural Accelerator in each core, enabling GPU-based AI workloads to run dramatically faster. The GPU also offers enhanced graphics capabilities and third-generation ray tracing that combined deliver a graphics performance that is up to 45 percent higher than M4. M5 features the world's fastest performance core, with up to a 10-core CPU made up of six efficiency cores and up to four performance cores. Together, they deliver up to 15 percent faster multithreaded performance over M4. M5 also features an improved 16-core Neural Engine, a powerful media engine, and a nearly 30 percent increase in unified memory bandwidth to 153GB/s.

The M5's next-generation GPU architecture is optimized for AI tasks. Each of its 10 cores features a dedicated Neural Accelerator, delivering over 4x peak GPU compute compared to the M4. The M5 also includes a third-generation ray-tracing engine, providing up to a 45% graphics uplift in apps using ray tracing.

Apple says the next-generation GPU, enhanced shader cores, second-generation dynamic caching, and third-generation ray-tracing engine on the M5 bring more realistic visuals, faster rendering times, and smoother performance. The faster 16-core Neural Engine also delivers more powerful AI performance with greater energy efficiency.

The M5 chip unified memory bandwidth of 153GB/s, providing a nearly 30% increase over the M4, offering higher multithreaded performance in apps, faster graphics performance, and faster AI performance running models on the Neural Accelerators in the GPU or the Neural Engine. It supports up to 32GB of unified memory.

The new ‌MacBook Pro‌, ‌iPad Pro‌, and Vision Pro with the M5 chip are available to pre-order today.
This article, "Apple Unveils M5 Chip With Next-Generation GPU" first appeared on MacRumors.com

Discuss this article in our forums