Apple may be considering a much more powerful Mac Pro: here’s what we know


The last few days have been dominated in technological news by the launch of Apple iPhone 13 with a new processor, the Bionic chip A15, with 15 billion transistors, i.e. 27% more than on the A14 from 2020.

It is likely that the bulk of those extra transistors went to the new GPU (graphics processing unit), new AI neural engine and a few other things.

A desktop version of the A15 with higher clock speeds is likely to be rolled out on newer versions of the Macbook Air, Macbook Pro, iMac and Mac Mini later this year with twice the cache (32MB). But what about his Mac Pro workplace?

With more power comes more cache

Well, Apple posted an intriguing job post on September 10, in which it advertised a job posting for a processor. Micro-architect RTL cache based in the United States.

This is the fifth offer published by the Cupertino giant which mentions “CPU Cache” and the third which speaks of multiprocessor systems. So there you go, Apple is planning products that will use two or more processors – and the Mac Pro is the only contender for now.

(Note that Apple may refer to multiple processor families within the same SoC – for example, central processing unit, graphics processing unit, neural processing unit, etc.).

The last job description mentions “Multi-level processor cache subsystem architecture and RTL development for multiprocessor systems” and when it comes to multiple cores and multiple physical processors, how to manage the cache (the super fast memory that acts as the first call port between the processor core and the rest of the system) is crucial.

In other workplace (Embedded Linux Engineers), Apple mentions that the successful candidate will be “part of a very visible team validating complex multidisciplinary systems-on-chip (sic) in a multiprocessor environment for future Apple products.” before adding that they “will develop Linux environment (sic) for next generation Mac products enabling new cutting edge technologies ”.

Apple M1 processor

(Image credit: Apple)

No more cache, a different cache?

We know that the Apple M1’s two high-performance cores have 320KB of combined L1 cache each and share 12MB of L2 cache. The remaining four power efficient cores each have 192KB of combined L2 cache and share a 4MB L2 cache. They do not have an L3 cache as the M1 is essentially modeled after the A14.

However, to boot the Xeon on the Mac Pro, Apple will need to have a different type of processor that has a different cache architecture, a higher clock speed, and can support much more memory than it does. the 16 GB currently offered (and located next to the SoC in a system configuration in a package).

The fact that we’re seeing mentions of multiprocessor rather than the emphasis on multicore leads us to believe that Apple might decide to keep the core count low while increasing performance by adding more processors instead.

More cores would increase the need for an L3 cache. Every heart of the 64 hearts Pro 3995WX Chipper for example has 64K L1, 512K L2 and 256MB L3 shared (4MB each). By the way, that’s barely more than the L1 + L2 cache quota for Apple’s energy-efficient core, which may show the company’s reluctance to add another layer of complexity (that’s i.e. L3 shared cache).

We can therefore end up with a Mac Pro with two hypothetical M2X offering 64 GB of RAM (32 GB each) or four with 128 GB of memory, potentially DDR5. That would cover three of the eight current memory configurations that go up to 1.5TB on the current Xeon-based Mac Pro, but still appear inadequate.

Apple will have to find a trick that allows the M1 successor to take over a lot more system memory if it is to be taken seriously.

No Xserve servers

One thing that is unlikely, however, is that Apple will relaunch the Xserve. server brand to supply rack servers to businesses around the world. It’s been almost 13 years since the last Xserve launched and the market has changed to the point of being unrecognizable. While Dell, HP, and Lenovo are still around, market dynamics have been transformed by hyperscalers such as Google, Facebook, Microsoft, Alibaba, and Amazon.

These are companies with a gargantuan appetite for computing power and aren’t afraid to set the agenda when it comes to what they want (hence the reason AMD and Intel have purchased FPGA companies in recent years). I don’t think Apple wants to compete in this cutthroat, low-margin environment.

However, it wouldn’t be surprising if Apple would follow, well, all the other hyperscalers and launch its own server chips for internal consumption only. After all, with hundreds of millions of iCloud users and plans to become a service giant, it would be in Apple’s best interest to do on the infrastructure side, which it has done on the customer side. .

Reduce dependency on third parties by owning the entire vertical stack and providing its end users with unique features not available elsewhere; a super charged Apple Privacy Relay, ultra-efficient video encoding technology, avideo conferencing tool that works with low bandwidth; pipe (line) dream? Let’s see.


About Author

Leave A Reply