Apple’s 2021 Mac chips will blow away the fastest PCs

Apple is prepping new Mac chips for introduction as early as 2021 that are aimed at significantly outperforming the fastest PCs.

M1 is the first personal computer chip built using cutting-edge 5-nanometer process technology and is packed with an astounding 16 billion transistors.
Apple’s M1 is the first personal computer chip built using cutting-edge 5-nanometer process technology and is packed with an astounding 16 billion transistors.

Mark Gurman and Ian King for Bloomberg News:

Chip engineers at the Cupertino, California-based technology giant are working on several successors to the M1 custom chip, Apple’s first Mac main processor that debuted in November. If they live up to expectations, they will significantly outpace the performance of the latest machines running Intel chips, according to people familiar with the matter who asked not to be named because the plans aren’t yet public.

The company’s next series of chips, planned for release as early as the spring and later in the fall, are destined to be placed across upgraded versions of the MacBook Pro, both entry-level and high-end iMac desktops, and later a new Mac Pro workstation, the people said.

The road map indicates Apple’s confidence that it can differentiate its products on the strength of its own engineering and is taking decisive steps to design Intel components out of its devices. The next two lines of Apple chips are also planned to be more ambitious than some industry watchers expected for next year…

For its next generation chip targeting MacBook Pro and iMac models, Apple is working on designs with as many as 16 power cores and four efficiency cores, the people said… For higher-end desktop computers, planned for later in 2021 and a new half-sized Mac Pro planned to launch by 2022, Apple is testing a chip design with as many as 32 high-performance cores.

Apple engineers are also developing more ambitious graphics processors. Today’s M1 processors are offered with a custom Apple graphics engine that comes in either 7- or 8-core variations. For its future high-end laptops and mid-range desktops, Apple is testing 16-core and 32-core graphics parts.

MacDailyNews Take: The Revenge of the Mac is upon us!

Even now, with only the first generation M1 released:


  1. I think Apple have the framework to completely revolutionize PCs and dominate the market for a decade. They have invested in acquiring the expertise to develop the most efficient and advanced processors in the world. With the revenues from iOS devices they can fund development of SoC chips far beyond what any other company can do. Apple tried to do this with RISC but whilst it saved the company they could not make major advances due to the ineptitude of IBM.

    We are going to see great things from Apple Silicon and PCs will rapidly evolve over the next few years. The rest of the industry will try to copy but will never make serious money from it.

    1. I have to enthusiastically agreed with your first paragraph.

      Apple is on the verge of something big finally over time blow away Pro PCs and gaming machines and RETAKE the mantle of most powerful PCs they relinquished in the 1990s…

  2. I wonder though, if it’s really practical for Apple to put 16cpu and 32 GPU cores on a chip. That would bake it very large, expensive, and draw a lot of power.

    Conversely, I can see more cores, but I can also see Apple drawing on their long experience in delivering two socket machines. Two 8 CPU and 16 GPU core chips would result in a powerhouse with less power draw concentrated in one chip. That would make it easier to cool, and would lead in much less expensive chips because yield would be higher, as well as chip costs being lower because of size.

    Additionally, we see that with the M1, Apple brought the “fabric” itself out of the chip, and on to the substrate where the chip is soldered. Those lines go to the 128 memory channel dram packages positioned to the right of the chip. That’s called “on package”.

    Every module on the chip is connected through that fabric, the GPUs are. I can imagine that Apple could also bring the GPU off the chip and on to the substrate as they did with the dram. That would have several advantages. One would allow a separate GPU chip to be placed above, to the botto , or to the left of the main chip. Having a separate chip would allow Apple to add 32 cores in a chip that’s no longer than the current main chip, and much thinner in height.

    Two would be that Apple would have about 20% of the chip now holding the GPU, empty. That could be used to expand the number of CPU cores, make them larger, add to the Neural Engine, etc.

    They could add to the two dram packages by stringing the lines out just a bit further on a slightly extended substrate, by maybe just .375 to .500 inch to the right of the two current packages, and adding two more packages. Or, a small socket for one larger package containing two chips, allowing RAM upgrades with special RAM for that small socket.

    Whether Apple will do any of this is speculation on my part, as I haven’t read anything like this anywhere else, except for my own writing, but it’s certainly possible to do.

    1. There was an ArsTechnica article (maybe someone else technical, now I’m not sure) recently about these Apple chips and it seemed to indicate these are much more easily expandable, and would not generate heat like AMD and Intel chips do. So, that may not be much of a concern.

    2. I don’t think dual socket would apply or be beneficial.. for the other reasons you mentioned.. namely the ‘unified memory’ architecture. it sounds like you’d need to go back to a bus to transfer between the sockets losing many of the benefits… I see how it might simplify manufacturing to use the same chips for scaled up solutions, but I don’t see how it would change the power consumption.. but i’m no expert.. There was a good article discussing how this is fundamentally a different architecture here… (although quite technical)

      1. I don’t agree. We do t know what Apple has planned for. But there are a number of ways this can be done. After all, supercomputers use extremely high throughput connections between processors. Remember that these companies use a fabric between elements on the chip which every component goes through. The fabric is an on chip intelligent bus.

        As Apple, brings that bus off chip now (as everyone e does) to connect to RAM on the substrate, they can do it with different parts of the chip, such as the GPU. But it’s very possible that this has been designed to facilitate chip to chip communications as well, as is do r with the Xeons and other multiple chip solutions. Apple has a lot of experience in that area, designing a special but for dual socket G4 designs.

        If these chips are kept close together, or have a large substrate, as some other chip companies have, and are doing, then more than one chip can be on the substrate. Or just have chips mounter very closely, possibly even back to back.

        There is no reason why this can’t be done.

  3. My new MacBook Pro 13 arrived today. But I will not open until X-mas. When my kids get their new iPads Air. And my wife her new iPhone 12 Pro. I am so pleased that Apple could get rid of Intel.

  4. I actually don’t doubt this, I can’t wait to see how they implement all of this. But it also tells me, just as with the transition to OS X and then to Intel, I am going to be waiting awhile to buy a new Mac. As with those other transitions, they need to get the software on board too. A Mac that isn’t running uch is just a piece of furniture. I installed Big Sur and loved it . . . until I saw all that was non-functional yet critical to my work on it. That isn’t Apple’s fault, but it is a thing nonetheless (and I would recommend holding off on Big Sur, snappy and cool as it is, until audio and 3D and even certain utilities are better supported, if that applies to you. I am really beginning to think that outside of coding, the real pros have just left the Mac to rot).

  5. Apple has the incentive, the drive, the opportunity, the money, and likely the inside track to get hints on advanced tech. that it gets from the Pentagon’s still publically undisclosed secret technology that it has collected from crashed UFOs and from tech. exchanges with ETs.

    1. Per UFOs and exchanges with ET’s, I think you are confusing the association with FaceBook. By all appearances, Mark Zuckerberg is a borg. I believe he walked off one of the crashed ships you mentioned. His eyes confirm this.

Reader Feedback

This site uses Akismet to reduce spam. Learn how your comment data is processed.