(Image: Apple)It’s not a big industry secret that Apple is working feverishly behind the scenes to excise every trace of Intel silicon from its Mac lineup. The company announced plans to switch from Intel to its own custom chips several years ago, and in 2020 it began the replacement process with the original M1 chip landing at the very bottom of its lineup with the MacBook Air, Mac Mini, and the entry-level 24″ iMac. Next up was the upgraded M1 Pro and Max SoCs, which landed in the company’s revamped 2021 MacBook Pros. This leaves just two models left on the upgrade path: the “big” 27″ iMac, and the pinnacle of power, the Mac Pro, both of which still use Intel processors and AMD discrete GPUs. According to a report, one of those chips will break cover soon; an M1 Max Duo SoC the company plans to drop into an all-new iMac Pro.
As its name implies, the M1 Max Duo will reportedly be two M1 Max chips connected together for double everything the Max chip offers. This translates to a 20-core CPU, and 64-core GPU, along with the ability to boast up to 128GB of RAM. There’s also Mac Pro rumors suggesting an M1 Max Quadro, with a 4x design. This is huge upgrade from the original M1 chip, which has just eight CPU cores and seven GPU cores, along with a maximum of 16GB of memory. The sources of these rumors are twofold: Bloomberg journalist Mark Gurman, and Hector Martin, who is porting Linux to Apple silicon Macs.
Starting with Gurman, who is a noted Apple insider, he pointed out in a recent tweet that Apple is indeed working on taking the M1 Max die and simply multiplying it both 2x and 4x for upcoming desktop chips. In his tweet he writes, “…the new Mac Pro desktop is expected to come in at least two variations: 2X and 4X the number of CPU and GPU cores as the M1 Max. That’s up to 40 CPU cores and 128 GPU cores on the high-end.” This dovetails with info from Mr. Martin, who has been elbow-deep in the MacOS code and reports, “…the macOS drivers have plenty of multi-die references, and the IRQ controller in the M1 Pro/Max is very clearly engineered with a (currently unused) second half for a second die.” If that’s not enough information from you, he adds, “For the technically minded: it’s a second set of config/mask/software-gen/hw-state registers, and the hardware inputs are all idle but you can software-gen IRQs in that block just fine and they get delivered with a die-id of 1 in the top 8 bits of the event register.” If you’re more into the video thing, YouTuber MaxTech goes into significant detail about all of these rumors.
For those of us who are silicon aficionados, it’s been fascinating to watch Apple’s moves in this market, as the M1 chips have upended the notion of what we can expect from a mobile CPU by offering both blistering performance and incredible efficiency; a rare feat indeed. Which is why the prospect of Apple delivering a chip that doesn’t need to go into a mobile device is alluring, as they can theoretically unleash the hounds since they won’t need to worry about power consumption, within reason at least. The bad news, however, is the same tipsters who are offering these tantalizing leaks are also pointing to insane price tags for this much power, with one pointing out the top-end Mac Pro could cost around $50,000. This shouldn’t come as that big of a surprise though, as you can already spend that much money quite easily on the current Xeon-powered Mac Pro tower, even without the $400 wheels.