When Apple launched its in-house designed system-on-chip (SoC) for the MacBook lineup, it shooked the notebook market. Dubbed as the Apple M1, the chip is fabricated on the Taiwan Semiconductor Manufacturing Company’s (TSMC) 5nm semiconductor node which is one of the most advanced chipmaking techniques in the world.
So, when we are talking about the M1 chip from Apple, it is worth mentioning that the M1 was designed to power Apple’s desktop and notebook computers. But when we compare a high-level look at the chip’s design and compare it to what Tesla Inc’s HW 3.0 computer offers, we find quite a few key possibilities for the two front-runners.
Tesla’s HW 3.0 features roughly six billion transistors per chip and was launched in 2019. It is built on Samsung Electronics’ 14nm manufacturing process is responsible for running software updated to a vehicle from Tesla, to locally determine the state of the world around it.
The HW 3.0 is capable of roughly 74 million Tera-Ops/second (TOPS)/chip, to determine the computing capacity of a neural engine. The chip’s each die is dedicated to its GPU and NPU as opposed to the CPU, which is self-explanatory due to its use-case.
However, Apple’s M1 chip has a larger area dedicated to the CPU and GPU because the main purpose of the chip is to power notebooks instead of an autonomous driving system. However, the octa-core powerhouse GPU on the M1 allows it to breeze past the HW 3.0 when comes to performance. The GPU performance of Apple’s M1 is nearly double of Tesla’s hardware.
Apple’s chip is capable of a peak output of 2.6 TFLOPs (Trillion Floating Point Operations-Per-Second). This means that Apple can design a more powerful chip that is aided by TSMC’s 5nm process which offers higher performance and power efficiency terms over the older 14nm node.
However, Tesla still has access to its already huge database, which contains data compiled from miles of travel. So, if Apple wants to compete with Tesla’s autonomous driving Ai using its very own Project Titan, the Cupertino giant still has a long way to go.
I have one thing to say. Dojo