Apple Reportedly Worked on Two 'Extreme' Chips

[MacRumors]

Apple once developed "M2 Extreme" and "M3 Extreme" chips for the Mac Pro, but it decided not to release them, according to Bloomberg's Mark Gurman. He first reported on this topic in 2022, and he touched on it again in his Power On newsletter today.

"Extreme" chips would have had twice as many CPU and GPU cores as Apple's "Ultra" chips.

"The idea was to offer twice as many graphics and main processing cores as that chip," he said. "In the past, I've called this proposed processor the 'Extreme' chip, which to me is the most sensible Apple marketing name for something above Ultra."

Apple decided not to release the chips due to concerns over higher production costs and limited demand for the Mac Pro, according to Gurman.

Not only did Apple ultimately scrap the "Extreme" chips, but it discontinued the Mac Pro entirely this year following a 20-year run.

Article Link: Apple Reportedly Worked on Two 'Extreme' Chips

 

[I7guy]

This goes to show how scalable apples’ silicon is.

 

[Rychiar]

For what purpose?

 

[hieranonymous]

The fact that Apple went so far as to develop these chips and then not release them is a massive bummer. They simply didn’t see a market for them, even after all the R&D.

 

[Nik]

These could have gotten the MacPro over $100,000, finally. /s

 

[Madhatter32]

Is this how it goes now?

Base < Pro < Max < Ultra < Extreme < Supercalifragilisticexpialidocious

 

[CarAnalogy]

It makes sense not to release it since that’s only one thing people wanted the Mac Pro for. They removed every other reason to get one.

 

[DavidSchaub]

I still think Quadra would have been a better branding to use instead of Extreme. 🙂

Now that Apple is going full on chiplets, I absolutely could see Apple revisiting the M* Quadra series, post M7.

 

[DavidSchaub]

The fact that Apple went so far as to develop these chips and then not release them is a massive bummer. They simply didn’t see a market for them, even after all the R&D.

Well, we don't know how well they actually performed and scaled. It is possible that they also offered nowhere near 2x the performance of the Ultras.

 

[DavidSchaub]

It makes sense not to release it since that’s only one thing people wanted the Mac Pro for. They removed every other reason to get one.

The reasons for getting them are basically the same as before. Niche work that required:
- lots of fast internal storage
- fast internal networking
- fast I/O boards
- very specific hardware needs.

Apple is likely right to kick those users off the platform. The market wasn't worth it.

 

[boswald]

If they had been released, I wonder how many people would have put Windows on it...

 

[jz0309]

it would have been a very niche product, at an absurd price, so, makes sense not to release this ...

 

[All Taken]

Mac Studio extreme, please.

 

[anthony13]

Extreme?! How about Astonishing? Spectacular? Uncanny? Are we just using X-men team names now?

 

[Bokito]

In the video industry these processors would be very welcome, but I wonder how big this industry is for Apple. I think quite a few people lost faith in Apple’s dedication to high end hardware. The M3 Ultra and M5 Max perform great, but when you really need number-crunching like exporting 4K movies to the highest possible quality per bit every core counts. In that case AMD has offerings for the very high end market that would greatly outperform Apple’s offerings. Thing is that AMD has the server market as well for their processors and that market is way bigger.

I think an extreme wouldn’t make sense for Apple. More graphics power would be welcome and would put Apple on par with Nvidia’s high end offerings, but there is no business case for it. And there is only limited use in Apple’s current customers base for anything above Ultra and that number of (CPU) cores.

 

[The Mercurian]

Extreme?! How about Astonishing? Spectacular? Uncanny? Are we just using X-men team names now?

Can I pre-order a Mac Studio M6 Wolverine please? 😃

 

[963852741]

The reasons for getting them are basically the same as before. Niche work that required:
- lots of fast internal storage
- fast internal networking
- fast I/O boards
- very specific hardware needs.

Apple is likely right to kick those users off the platform. The market wasn't worth it.

Apple never took that market segment seriously.

 

[HVDynamo]

It makes sense not to release it since that’s only one thing people wanted the Mac Pro for. They removed every other reason to get one.

Yeah, they shot themselves in the foot with the Mac Pro. Having upgradable RAM/Storage and expansion slots was the main seller. I wanted one when they talked about the 2019, but once they released it at those prices I noped out. They made it too expensive for a consumer that just wanted an upgradable machine. I understand having the higher tiers for real professionals, but the price for the base model was outrageous for what you got. Then Apple Silicon came along and they squandered it even further.

The Apple Silicon Mac Pro should have had a Modular CPU board, and allowed extra RAM be upgraded by the user beyond the unified memory. You pay for the fixed unified memory on the CPU board, then you can add more that's slower that gets used when the unified memory fills up. Then having plenty of storage bays, and adding support for aftermarket GPU's from AMD/Nvidia would have made the Mac Pro more worth it. The starting price would have been OK, with the modularity allowing you to replace the CPU board separately down the road without having to replace everything else. I would have paid the steep entry price if it meant 4 years later I could upgrade the CPU board from an M2Max to an M5 Max/Ultra, or even bought second hand upgrades from other people upgrading.

I know all that is a pipe dream that never would have happened. But I can dream.

 

[oldmanyoung]

Is this how it goes now?

Base < Pro < Max < Ultra < Extreme < Supercalifragilisticexpialidocious

Ludicrous

 

[Unregistered 4U]

“Thing that never happened totally did happen and I’m the only one that knows it! Keep me employed by believing that I know things!”

There was never a business case for any Extreme. It was a red herring to sort folks out of the supply chain. Considering how bad leaker predictions are these days, they appear to have been wildly successful!

 

[ConfusedChris]

I always wondering how loud the required cooling would have been.

 

[All Taken]

“Thing that never happened totally did happen and I’m the only one that knows it! Keep me employed by believing that I know things!”

There was never a business case for any Extreme. It was a red herring to sort folks out of the supply chain. Considering how bad leaker predictions are these days, they appear to have been wildly successful!

Yeah, idiots. Real people in the know, know it is actually called mega.

 

[keksikuningas]

must be for their own servers since Mac Pro doesn't exist anymore?

 

[CWallace]

Well, we don't know how well they actually performed and scaled. It is possible that they also offered nowhere near 2x the performance of the Ultras.

Agreed. An Ultra is not twice as fast as a Max, so scaling could very well have dropped off even more. I believe it was leaker "MajinBu" who showed what they claimed was a "vertical" UltraFusion connector that would have connected two Ultras along their longitudinal access, but you have to wonder how memory bandwidth and latency would have faired in such a "clover-leaf" configuration with four separate memory controllers (one per Max die).

 

[TVreporter]

Imagine being one of the engineers spending probably years working on those chips and/or the computer itself.

Tim: sorry guys we’re shutting it all down.Don’t fret you still have a job - we’re moving you to Apple Polishing Cloth 2.0!