[ad_1]
Mac with Apple’s own processor. What kind of finish will the processor have?
I was also paying attention to the Mac itself, but if you were looking for “the meaning of making it unique,” that attention would inevitably turn to processor performance. And the actually announced product further complements the Apple Silicon = Apple M1 chip for Mac.
Apple has announced that it will double the performance of both the CPU and the GPU when the power consumption is set at 10 watts, with the phrase “compared to the latest laptops.” As for the CPU, “the same performance as the maximum performance of the latest laptop” can be demonstrated with 25% power for the CPU and 33% for the GPU.
This latest laptop is a laptop with Intel Core i7-1165G7, the latest model using 11th Gen Intel Core and Xe graphics architecture. If your claim is accurate, they will have a significant advantage over other laptops in terms of performance by power consumption.
The MacBook Air, MacBook Pro and Mac mini announced this time look the same as the previous model, isn’t it because it makes you feel the overwhelming difference to the Intel version? It is a difference that makes me think. Even though they’re all housed in the same case, the MacBook Air performs higher than the Intel version without a cooling fan. Even MacBook Pros and Mac mini equipped with a cooling fan have the scalability that the difference is not closed. If I had changed the design, it would not have been so different.
Now, let’s dive into testing each product in the actual machine review, but let’s focus on the “M1” here and think about what this SoC will bring to the Mac.
Why M1 is not A14X Bionic
As I did so, I thought that the first Mac would have an A14X Bionic, an improved version of the A14 Bionic with more CPU and GPU cores. However, a chip called “M1” has appeared. Perhaps the name A14X will be used for the iPad Pro, but there is actually a reason for the name M1 to be used.
Ie “M1 is not an extended version of A14 Bionic”. The M1 is Apple’s latest reconfigured and reorganized circuitry for Mac. Of course, the latest circuits (components) developed by Apple are usually the same as those developed with the A14 Bionic. High-performance core and high-efficiency core, 16-core neural engine, GPU core, ISP, etc. have the same design, but M1 has 4 equal high-performance cores and 8 GPU cores, each in A14 Bionic On the other hand, it has doubled and the memory bandwidth has doubled as the GPU core has doubled. This area is similar to the relationship between A12 Bionic and A12Z Bionic.
But Macs also require features that iPhones and iPads don’t. One of them is virtualization, and M1 adds the function to run a virtual computer (it is not x86 processor virtualization, however, the instruction set is ARM). The GPU architecture is the same, but it supports more texture formats. This will be important to support PC games etc. Similarly, the Thunderbolt 3 / USB 4 interface is not included in the A14 Bionic.
In other words, we made the best use of the design developed for the iPhone / iPad and used it as a component, but not all, but all the necessary elements for Mac were put into the same die. It is not clear if the M1 will be used as-is when the iPad Pro model is changed in the future, or if the A14X Bionic will be manufactured separately, but in any case, it is incorrect that the M1 is a dedicated processor with exclusive elements of Mac. Absent.
Dynamically changing performance with thermal design. M1 has only “one” specification
All three Macs featured this time around are equipped with M1s, but the specs are unique, except for the entry-level MacBook Air, which has a limited number of GPU cores. The one installed on all models is the M1, and the operating clock frequency is not listed there. This is because the maximum operating clock frequencies are all the same (since it is not open to the public, it cannot be known except by measuring it with a real machine). To be precise, the frequency range of the operating clock is the same.
As with the latest 11th Gen Intel Core, the dynamically running clock changes based on the cooling performance and operating environment (temperature, etc.) of the M1-equipped system and the operating state of the application. In other words, the M1 itself is the same whether it’s a slim, fanless MacBook Air or a desktop mini-type Mac mini, and the instantaneous power can be considered to be almost the same. However, if you have a game or application that is multithreaded, has a full core, and runs the GPU at full capacity, then it is better to have a Mac mini with a lot of cooling capacity.
Given the current processor situation, where performance is dominated by power, such a configuration is quite conceivable. However, from a different point of view, it can be said that this use is only possible because Apple is a company that develops and sells personal computer systems.
CPU vendors like Intel have so far selected the finished chips, rated their performance, and sold them at different prices for each range. However, for Apple, which sells only the final product, it does not make much sense to create a price list based on such selection, but it is more natural that the performance changes depending on the design.
High performance and restrictions due to shared memory SoC
By the way, the reason the M1 is energy efficient and high-performance is that it features the integrated system chip (SoC) architecture that has been perfected in the iPhone. In the SoC for iPhone, we have advanced in the internal development of the processing circuit to be incorporated, and we have improved the perfection of the architecture of the system in which the processing circuits for different purposes share the same memory and operate cooperatively. Shared Memory Architecture (UMA) is extremely efficient to run the CPU, GPU, and processor dedicated to the machine learning model (Neural Engine) inference algorithm in parallel.
Especially when the GPU is used for general purposes, it is inefficient to load the data into video memory, process it, and bring it back to memory to reflect the output processed by the GPU. Processors that are good at each are better off being able to access the same data such as CPU at one time, GPU at another time, Neural Engine at another time, and ISP at another time. It will be clear which is more efficient if several experts process the information around the same table or if the processing is done through the exchange of emails.
Good efficiency means that it is also advantageous in terms of energy consumption. The goodness of the design itself and the detailed power management feature introduced in the A13 generation may have been successful, but UMA should also contribute to the reduction in power consumption. The advantage of UMA may be that when the processing capacity is improved by increasing the number of cores, the performance can be increased according to the number of cores simply by increasing the interconnect band within the SoC.
However, there are restrictions because it is UMA. That is the installed memory capacity. The memory band shared by each processing circuit must be large enough for UMA to function well. The reason M1 bundles DRAM in the form of SIP (System In Packet) is presumed to be to maximize memory bandwidth.
Reasons to switch to Apple Silicon from the low-end side
In other words, main memory can only be installed insofar as it can be installed in the same package, so this time the economically reasonable line would have been up to 16GB. It seems that increasing the capacity of the main memory will be indispensable to see if the Apple M processor will be used in high-end products in the future.
Similarly, integrating the I / O interface on the chip is an advantage, but it can also be a weakness. The M1 only supports two Thunderbolt 3 / USB 4 ports. It incorporates an interface inside the M1, but is expected to have up to two channels of support. The concept of consolidating most of the system into a single package is advantageous in terms of performance, power consumption, safety, etc., but on the other hand, the obstacles to creating a large system are high.
For this reason, Apple has completely migrated the MacBook Air to the M1, but the MacBook Pro is only a lower model (3×2 Thunderbolt port model) than the 13-inch model. The Mac mini will also be sold alongside an Intel-equipped model with 4 Thunderbolt 3 ports.
There are also differences in the maximum memory and SSD capacity that can be installed. If it’s just plain CPU / GPU performance, considering the significance of installing Neural Engine, it seems like it’s okay to move on to Apple Silicon more boldly, but part of the line, more specifically, in order from the lowest spec. This is because there are restrictions on the expandability of the system in all respects, not just CPU / GPU performance.
Apple says it will take two years to renew its line, and there is no doubt that it will be some time before the Mac Pro is replaced.
Related article:
Apple Silicon MacBook Air announced Fanless design with multiple times performance, first equipped with M1 chip
Announcing the new MacBook Pro. Equipped with Apple’s silicone “M1”, it drives up to 20 hours with several times the performance
New Mac mini announced. CPU performance up to 3 times, graphics up to 6 times with Apple Silicon M1
The next macOS “Big Sur” will be released on November 13. Unleash the power of Macs with M1 chips
Compare MacBook Pro / Air with Apple Silicon M1 with Intel model. Air pays attention to the number of GPU cores
Apple Silicon Mac mini vs Intel Core Mac mini spec comparison. Affordable prices and high processing power are sold.
[ad_2]
