Following an impressive amount of fanfare, Apple has included its new A13 Bionic processor in the upcoming iPhone 11, iPhone 11 Pro, and iPhone 11 Pro Max handsets. The new chip is the fastest processor Apple has ever designed, but is also designed to use far less power.
Representatives claimed that the A13 is the fastest CPU and GPU of any smartphone or tablet, the 64-bit chip’s CPU and GPU performing 20 percent faster than the A12 processor, a variety of elements allowing it to perform over one trillion operations per second, some relating to machine learning.
The A13 is made up of many sections, but the main three are the CPU, GPU, and the Neural Engine. The CPU consists of two performance cores and four efficiency cores, with each used depending on the workload. The GPU contains four Metal-optimized cores, while the Neural Engine contains eight more.
The CPU region features a pair of “Machine Learning Accelerators,” which are used to perform matrix multiplication, which is a calculation frequently used in machine learning. Apple says that the A13 will perform this calculation six times faster than the A12 Bionic.
Load balancing via the chip’s Machine Learning Controller allows machine learning models to be scheduled on the CPU, GPU, and Neural Engine, depending on which would offer the best performance. The controller also does this while balancing the need to stay as efficient as possible, helping reduce the amount of power used.
As the controller takes all the decision-making out of where to process machine learning models at any time away from developers, this also simplifies the process for development.
The A13 Bionic also works to reduce the amount of energy it requires to perform these calculations in the first place. This also helps provide multiple extra hours of battery life for the iPhone 11 Pro, as opposed to typical improvements of an hour.
A fair portion of the reduced power usage comes from Apple’s taking advantage of chip partner TSMC’s commercial processes for creating 7-nanometer chips, described as an “advanced improved 2nd generation 7-nanometer transistor.” This allows Apple to balance performance and power.
With the A13, Apple has also managed 8.5 billion transistors onto the A13, up from 6.9 billion used in the A12.
Aside from the transistors themselves, as well as being more selective over what is used to perform calculations, Apple has also worked on improving the architecture.
In addition, Apple’s architecture utilizes hundreds of voltage domains on the chip, certain sections activating when they’ll be used for processing. This allows the architecture to power down sections of the chip that aren’t being used, reducing how much energy is required.
At an even smaller level, the use of hundreds of thousands of smaller domains allow for granular control over what gets power, ensuring only the smallest amount of logic in the chip is used for a process.
The changes result in overall power changes, such as the CPU’s two performance cores consuming 30 percent less power, the four efficiency cores saving 40 percent, the four GPU cores also saving 40 percent, and the eight Neural Engine cores being 15 percent more power efficient.
Stay tuned for additional details as they become available.
Via AppleInsider