In a WIRED interview, Om Malik met Apple’s marketing chief Phil Schiller and chipmaker Anand Shimpi to discuss the A13 Bionic chip featured in the new iPhone 11, iPhone 11 Pro and iPhone 11 Pro Max.
First of all, Malik provides an overview of the A13 chip specifications and performance improvements:
- 8.5 billion transistors, an increase of about 23 per cent compared to the 6.9 billion transistors on the A12 chip
- Six-core CPU: two high-performance 2.66 GHz cores called Lightning and four efficient Thunder cores
- The quad-core graphics processor, an image processor designed by Apple and an octa-core neural engine for machine learning capable of performing trillions of operations per second
- Up to 20 per cent increase in performance of all major components, including CPU, GPU and neural engine
- Up to 30 per cent more energy-efficient than the A12 chip
Schiller told Malik that one of the biggest examples of performance enhancements this year is voice synthesis on the iPhone.
“We have improved our iOS 13 speech synthesis features so that there is much more natural language processing, and everything is done with machine learning and the neural engine,” explained Schiller.
Shimpi noted that during the design of its A-series chips, Apple focuses on performance and efficiency.
“We talk about performances very publicly. But the reality is that we see them as performance per watt. We consider it as energy efficiency and if you build an efficient design, you also happen to build a performance design. “
The article finds that Apple’s chipmaking team will study how apps are used on iOS devices to optimize future chip designs.
“For applications that do not require additional performance, you can perform last year’s performance and do it at a much lower power,” said Shimpi.
Also, machine learning plays an important role in A13 chip, helping to manage battery life and optimize the performance, according to Schiller.
“Machine learning did not exist ten years ago. Now it is always in operation. “