Is it technically possible for Apple to make multi-SOC machine, to get around their system limitation as it is now? Say 4x Ultra instead of one Extreme SOC that is just two Ultras glued together.
Got a tip for us?
Let us know
Become a MacRumors Supporter for $50/year with no ads, ability to filter front page stories, and private forums.
Apple May Not Launch Updated Mac Studio With M2 Ultra Chip Due to Similarity With Upcoming Mac Pro
- Thread starter MacRumors
- Start date
- Sort by reaction score
Overhead...
Ultra chips are just two flawless Max chips fabbed side by side. They were never physically seperated during the fab process. An Extreme would be four flawless Max chips fabbed side by side. That's why there is negligible performance penalties as they're essentially 1 chip.
If the Extreme chip you are thinking about is two Ultra chips connected via logicboard rather than chip to chip directly then you are introducing latency and other electrical overheads that hits raw performance.
Similar to Nvidia SLI tech that very few, if any, computer games support due to the added development complexities relative to number of users who actually have this setup.
Apple's method is somewhat expensive unless they designed a way to cut the Ultra up into independent Max or Pro chips that could be binned based on the possible fab flaws.
To be honest I think it's more likely the Mac Pro gets canned than the Studio - since the Mac Pro's selling points (in its current guise) don't fit the Apple Silicon SOC paradigm.
For most people the Studio already 'is' the Mac Pro.
For most people the Studio already 'is' the Mac Pro.
Apple's, like many other companies, do not attempt to cater to all use case for all price points all the time.
They look at what will do their KPIs and let the competition take up the slack.
Perhaps save the abuse until Apple actually announces something, rather than relying on potentially baseless speculation?
Unfortunately, for a company that is as big as Apple, this is the only way to go to ensure stability and confidence.
Heck, Apple stopped making iPhone mini just because it’s not selling as well as they hoped for, and I assume Apple sold more iPhone minis that Mac Pros.
If I'd had to guess what was coming this Spring, I would have said that the next-gen Mac Studio and new Mac Pro would be launched alongside each other, with the M2 Ultra in both. The clue to the distinction between them is in the feature they already announced here at 27:15 in the Mac Studio launch:
www.youtube.com
The name Jonny gave to their "custom dye interconnect technology" was "Ultrafusion". If it can connect 2 dyes to create M2 Ultra, it can connect multiple dyes (hence the rumours about the M2 Extreme). But if you're going that far, you might as well take the paradigm to its logical extension, and have an M2 Ultra, with 2n more dye "slots" which end-users can fill with (say) 4 different classes of SoCs, each dedicated to augmenting 1) CPU cores, 2) GPU cores 3) RAM or 4) Neural engine.
So the second-gen Mac Studio would have an M2 Ultra, but that's it, it's a generalist machine. Alternatively, the new Mac Pro is for specific applications that need tons of a certain kind of power, but probably don't need that much of anything else. It would have an M2 Ultra, plus a user-definable (but not upgradable/replaceable), set of SoCs which would be unbalanced by themselves, but as an augment to M2 Ultra, make it a crazy powerful/flexible workhorse.
Apple Event — March 8
Watch the special Apple Event to learn about the all-new Mac Studio and Studio Display, new iPad Air, new iPhone SE, and iPhone 13 Pro and iPhone 13 in two n...
www.youtube.com
The name Jonny gave to their "custom dye interconnect technology" was "Ultrafusion". If it can connect 2 dyes to create M2 Ultra, it can connect multiple dyes (hence the rumours about the M2 Extreme). But if you're going that far, you might as well take the paradigm to its logical extension, and have an M2 Ultra, with 2n more dye "slots" which end-users can fill with (say) 4 different classes of SoCs, each dedicated to augmenting 1) CPU cores, 2) GPU cores 3) RAM or 4) Neural engine.
So the second-gen Mac Studio would have an M2 Ultra, but that's it, it's a generalist machine. Alternatively, the new Mac Pro is for specific applications that need tons of a certain kind of power, but probably don't need that much of anything else. It would have an M2 Ultra, plus a user-definable (but not upgradable/replaceable), set of SoCs which would be unbalanced by themselves, but as an augment to M2 Ultra, make it a crazy powerful/flexible workhorse.
My man, you really need to learn read rumors more critically and not just blindly accept them as true.
Last edited:
I don't know if you get news where you live, but there's been a global shortage of semiconductors in the past two years that probably have a lot to do with this.
For example, the PS5 that launched over two years ago is still not in stock because of this.
Apple are great at logistics and have weathered the storm probably better than most, but even they can't walk on water.
Last edited:
Looks like the ugly as sin studio is not long for this world
I for one won't miss it
Worst designed mac ever imo , just abysmal
I for one won't miss it
Worst designed mac ever imo , just abysmal
Nope I mean the Ultra Studio basic configuration 20 core CPU / 48 core GPU, 64gb RAM
You’re right that it took them longer than expected. However, they might have been burned considering how badly the Cube failed back in the day.
Apple stopped doing business with Nvdia because of recalls and leaked proprietary data.
So their sole GPU supplier is AMD.
In future I hope Mac apps improve on Apple Silicon hardware.
Let’s be fair this is totally something Apple will 100% do, so it may as well be fact. I don’t expect a Mac Studio update until next year. Don’t expect Apple to actually give consumers decent choices at the present time under Tim Cook.
Mac Pro trash can with no update for 4-5 years.
iMac update anyone? Doesn’t even have Pro or Max variations of the M1
The reason why Apple has the efficiency edge is mainly due to Apple having an edge in terms of the node they use, the PDN (power delivery network) tech, and packaging.
Their ARM cores are actually more complex than the x86 competitors; significantly wider and with larger resources for out of order and speculation. Most people assume there is some kind of "magic" that makes ARM better that x86, but that is not the case. The ISA has little impact on overall power consumption given the same microarchitectural resources.
Apple uses their larger/more complex cores to their advantage, by running them at a slower clock rate. While allowing them to do more work per clock cycle. This allows them to operate on the frequency/power sweet spot for their process. One has to note that power consumption increases significantly (way higher than linear) the higher the frequency.
Here is where the PDN technology comes into play. Apple uses the most advanced technology to distribute power to keep all the functional units feed, which requires the ability to supply a lot of instantaneous power. To do so, Apple uses a 3D stacked architecture of 2 dies; one for the logic, and another one on top (or bottom depending where you look at it) to distribute the power. In contrast, almost every one else has to use the same die to do logic and distribute power.
The irony is that a simpler/smaller ARM core would have to be clocked faster in order to compete with Intel/AMD cores. And it would end up consuming the same high power.
Apple also has a very good SoC design. Meaning that they integrate most of the system on a single die; the CPUs, the GPU, the NPU (AI accelerator), the Codec (video processing), the camera block, I/O (USB, WiFi, ethernet, PCIe/TB, etc), and the memory controller.
For some stuff like AI and video encoding, having custom silicon handling it is far far more efficient than running it on a general purpose code.
Lastly, it also comes to packaging. Apple not only integrates the SoC in a single die, but it has the memory chips on the same package. This allows them to use low power mobile DDR chips, and since they are on package it also reduces significantly all the power that having the memory transactions run through the system's PCB externally would consume.
So it's a combination of Apple using a single package where Intel/AMD laptops require multiple through their PCBs to support the same functionality. As well as Apple having access to better overall fabrication technology for that single package that AMD/Intel have for theirs.
The trend seems to be that it is becoming more efficient for mobile vendors to scale up their products into laptops, than it is for desktop vendors to scale down their products into laptops.
There is also a key difference in business models: Apple is a system's vendor. Meaning that they sell the finished product, not just the processors. So they can use several parts from the vertical process to subsidize others. In this case, Apple can afford to make very good SoCs because they don't sell those chips elsewhere, meaning that they are not as pressured to make them "cheap" in terms of area for example. Since they're going to recoup the profit from elsewhere in the product.
In contrast; AMD and Intel sell their processors to OEMs, so they only get profit from the processor not the finished system. So they have to prioritize cost, by optimizing their designs for Area first and then focus on power. This is why both AMD and Intel use smaller cores, which allows them for smaller dies. But which have to be clocked faster in order to compete in performance, unfortunately that also increases power.
This is probably they key difference; Apple can afford the larger design that is more power efficient for the same performance. Whereas AMD/Intel have to aim for the smaller design that is less power efficient for the same performance.
Their ARM cores are actually more complex than the x86 competitors; significantly wider and with larger resources for out of order and speculation. Most people assume there is some kind of "magic" that makes ARM better that x86, but that is not the case. The ISA has little impact on overall power consumption given the same microarchitectural resources.
Apple uses their larger/more complex cores to their advantage, by running them at a slower clock rate. While allowing them to do more work per clock cycle. This allows them to operate on the frequency/power sweet spot for their process. One has to note that power consumption increases significantly (way higher than linear) the higher the frequency.
Here is where the PDN technology comes into play. Apple uses the most advanced technology to distribute power to keep all the functional units feed, which requires the ability to supply a lot of instantaneous power. To do so, Apple uses a 3D stacked architecture of 2 dies; one for the logic, and another one on top (or bottom depending where you look at it) to distribute the power. In contrast, almost every one else has to use the same die to do logic and distribute power.
The irony is that a simpler/smaller ARM core would have to be clocked faster in order to compete with Intel/AMD cores. And it would end up consuming the same high power.
Apple also has a very good SoC design. Meaning that they integrate most of the system on a single die; the CPUs, the GPU, the NPU (AI accelerator), the Codec (video processing), the camera block, I/O (USB, WiFi, ethernet, PCIe/TB, etc), and the memory controller.
For some stuff like AI and video encoding, having custom silicon handling it is far far more efficient than running it on a general purpose code.
Lastly, it also comes to packaging. Apple not only integrates the SoC in a single die, but it has the memory chips on the same package. This allows them to use low power mobile DDR chips, and since they are on package it also reduces significantly all the power that having the memory transactions run through the system's PCB externally would consume.
So it's a combination of Apple using a single package where Intel/AMD laptops require multiple through their PCBs to support the same functionality. As well as Apple having access to better overall fabrication technology for that single package that AMD/Intel have for theirs.
The trend seems to be that it is becoming more efficient for mobile vendors to scale up their products into laptops, than it is for desktop vendors to scale down their products into laptops.
There is also a key difference in business models: Apple is a system's vendor. Meaning that they sell the finished product, not just the processors. So they can use several parts from the vertical process to subsidize others. In this case, Apple can afford to make very good SoCs because they don't sell those chips elsewhere, meaning that they are not as pressured to make them "cheap" in terms of area for example. Since they're going to recoup the profit from elsewhere in the product.
In contrast; AMD and Intel sell their processors to OEMs, so they only get profit from the processor not the finished system. So they have to prioritize cost, by optimizing their designs for Area first and then focus on power. This is why both AMD and Intel use smaller cores, which allows them for smaller dies. But which have to be clocked faster in order to compete in performance, unfortunately that also increases power.
This is probably they key difference; Apple can afford the larger design that is more power efficient for the same performance. Whereas AMD/Intel have to aim for the smaller design that is less power efficient for the same performance.
Sorry beforehand if I'm being ignorant but would it be so terrible for the Mac Studio to come ONLY with a M2 Max flavors whilst the Mac Pro would come ONLY with M2 Ultra? Seems to me the logical and sensible solution for differentiating them, so lineup would look like this:
( Low-end) Mac Mini with M2 and 8GB Ram
( Mid-end）Mac Mini with M2 Pro and a minimum of 16GB ram
(High-end) Mac Studio with M2 Max and a minimum of 32 GB ram
(Highest-end) Mac Pro with M2 Ultra and a minimum of 64 GB ram
Makes sense right? No? Unless I'm stupidly missing something, then Apple should just hire me and pay me the big bucks for coming up with painfully obvious solutions to their ridiculously invented/imaginary problems.
( Low-end) Mac Mini with M2 and 8GB Ram
( Mid-end）Mac Mini with M2 Pro and a minimum of 16GB ram
(High-end) Mac Studio with M2 Max and a minimum of 32 GB ram
(Highest-end) Mac Pro with M2 Ultra and a minimum of 64 GB ram
Makes sense right? No? Unless I'm stupidly missing something, then Apple should just hire me and pay me the big bucks for coming up with painfully obvious solutions to their ridiculously invented/imaginary problems.
I remember in 2017, in the famous interview with some of the execs, Apple admitted that they had designed themselves into a thermal corner or something like that with the 2013 MP. So, have they designed themselves into a "too closed non-expandable computer philosophy" this time around? It seems that the extreme efficiency and the closely connected parts of the design of the Apple Silicon may show its flip side of the coin in that it doesn't (easily) allow expandability such as (high-enough throughput/low-enough latency) RAM, GPU and maybe even SSD? Again, I'm not in the market for a new Mac Pro, but as a music producer and occasional video editor I am interested in the trajectory of Apples Mac line since I'm deeply invested in it. I hope they're able to deliver what the most demanding pros (not me, but probably graphics/memory/storage demanding movie studios) want – since, that's how the entire pro hardware/software ecosystem will be maintained and see further evolving.
Last edited:
I still can't believe they went from beautiful designs (G3, iBook Clamshell) to what we're seeing today. Everything is essentially a Mac Mini, or a thicker Mac Mini, with a separate monitor.
The new 24" iMac was a great reintroduction to that theme. A 27" with a Max would have been incredible.
The new 24" iMac was a great reintroduction to that theme. A 27" with a Max would have been incredible.
It's a tough call maxing out a Mac Mini vs. a base model M1 Max Mac Studio... Pro-sumers probably can't justify the big bump to a Mac Pro all the way up from a Mini, so why not keep this Mac around?
No it doesn’t make sense for the new Apple. Your solution offers clear cut difference between models so consumers have clear choice. The new Apple is about upselling, so there has to be upgrades in between that might nudge you to buy the higher tier models.
FYI, there is a massive thread on running Ventura on unsupported Macs. Might be something in there to help you get current with OS and security updates.