Last Updated on 17/10/2021 by Hrithik V
Apple unveiled its own performance chip during the last keynote of the year that took place on 10th of November. Along with the M1 chip, Apple introduced MacBook Air, MacBook Pro 13” and Mac Mini.
Before this chip, a Mac needed multiple chips to deliver all of its features like the processor, I/O, security, and memory. With M1, these technologies are combined into a single system on a chip, delivering a new level of integration for more simplicity, more efficiency, and amazing performance. And with incredibly small transistors measured at an atomic scale, M1 is remarkably complex, packing the largest number of transistors they have ever put into a single chip. It’s also the first personal computer chip built using industry‑leading 5‑nanometer process technology.
Unified Memory Architecture
M1 unifies its high‑bandwidth, low‑latency memory into a single pool within a custom package. As a result, all of the technologies in the single system on the chip can access the same data without copying it between multiple pools of memory. This dramatically improves performance and power efficiency. Resulting in snappier video apps, richer and more fluent gaming as well as lightning-fast processing.
CPU Performance Upgrade
The 8‑core CPU in M1 is by far the highest‑performance CPU Apple has ever built. Designed to crush tasks using the least amount of power, M1 features two types of cores: high performance and high efficiency. 4 high-performance cores are created to handle one single heavy task with the goal of optimizing it as well as possible while 4 high-efficiency cores are designed to handle numerous lightweight tasks allowing power cores to optimize the performance.
M1 has an integrated Graphic chip which lets the user get the best of both worlds: better graphic performance and lower power consumption.M1 is capable of executing nearly 25,000 threads at a time with 8 GPU cores. At every power level, M1 delivers significantly higher graphics performance than the very latest PC laptop chip for up to 2x the graphics speed and M1 can match the peak performance of the PC chip while using just a third of the power.
Superior Machine Learning
Apple has designed a 16 core chip known as Neural Engine that is capable of performing 11 trillion operations per second. In addition to an 8 core GPU and machine learning accelerators, M1 is highly optimized for carrying out machine learning tasks.
The first benchmark testing was done by Geekbench. The second benchmark test involving x86 emulation under Rosetta 2 was carried out.
The new Rosetta 2 Geekbench results uploaded show that the M1 chip running on a MacBook Air with 8GB of RAM has single-core and multi-core scores of 1,313 and 5,888 respectively. Since this version of Geekbench is running through Apple’s translation layer Rosetta 2, an impact on performance is to be expected. Rosetta 2 running x86 code appears to be achieving 78%-79% of the performance of native Apple Silicon code.