In an interview with Wired, Apple’s Phil Schiller and Anand Shimpi from Platform Architecture have spoken at length and revealed quirks and features about the new A13 Bionic chip. It is no secret that every year, Apple makes its new chip faster and more efficient. Apple has a clear advantage when it comes to hardware performance since it owns the entire vertical stack.
Apple’s new chip is powered by 8.5 billion transistors. Furthermore, it comes equipped with six CPU cores including two high-performance cores at 2.66GHz and four cores meant for efficiency. That apart, the A13 is backed by highly capable machine learning accelerators.
On the performance front, A13 Bionic chip is faster and is yet 30 percent more efficient than its predecessor. In terms of battery backup, the A13 Bionic chip has contributed to an extra five hours per day on new iPhones. As mentioned earlier, Apple owns the entire vertical stack including software, hardware, and the chip design. This has helped Apple add new augmented reality capabilities like Deep Fusion and Night Mode.
Emphasis on Performance per watt
Performance is the cornerstone of any chipset and Apple’s A13 Bionic is no difference. “We talk about performance a lot publicly,” Shimpi says, “but the reality is, we view it as performance per watt. We look at it as energy efficiency, and if you build an efficient design, you also happen to build a performance design.”
Shimpi and Shiller explained that CPU team studies app usage patterns on IOS and uses the data to arrive at better CPU designs. Shimpi further adds that “For applications that don’t need the additional performance, you can run at the performance of last year’s and just do it at a much lower power.”
In the interview, both Shiller and Shimpi walk us through the importance of performance-per-watt rules that are applied to machine learning and graphics processing functions. Developers within Apple collaborate with each other and devise a more efficient way of doing things.
For example, if a developer working on the iPhone’s camera software sees a lot of utilisation of the GPU, then she can work with a GPU architect to figure out a better way of doing things. This leads to a more efficient design for future graphics chips.
Apple Vs Others
Apple is apparently using a different mechanism to delegate work to various parts of the chip. This helps the A13 Bionic to conserve battery power.
In a typical smartphone chip, parts of the chip are turned on to do particular tasks. Think of it as turning on the power for an entire neighborhood for them to eat dinner and watch Game of Thrones, then turning the power off, then switching on the power for another neighborhood that wants to play videogames”
With the A13, think of doing the same on-and-off approach, but on a single home basis. Fewer electrons go to waste.
Furthermore, Schiller talks about how Machine learning is always running and helps in managing your battery life or improving overall performance.[via Wired]