Allow me to add that I don’t quite get the argument that it has to be M2 — I gather there is a technical reason for it, but I think that’s hard to say without knowing a lot more than we do. I find the idea that Apple would design this entire M1 line but not account for the Mac Pro to be absurd.
In terms of naming, I don’t think they will call it the Ultra Pro or Ultra+, they will all be Ultra, just with different core counts. Basically an Ultra is 2 or 4 Max fused together.
It’s pretty clear that they are finished with the M1. Will people please stop making new M1 chips up?
They may use two or even four M1 Ultra chips. They may change their concept of introducing more powerful chips over the year, and have an M2 Ultra for the Mac Pro. We don’t know. But they won’t have a four chip Ultra. John made that pretty clear.
John was introducing the UltraFusion process when he said that. That process may also allow them to connect two Ultras together, much like what you’re suggesting when you say they may use multiple M1 Ultras in the Mac Pro. It’s a plausible technical solution to the problem. That’s the whole point of the “chiplet” approach. I think you’re getting hung up on semantics, although I’ll concede that it was not a live event and everything said was carefully reviewed.
It isn’t hard to imagine how John would introduce the idea, “UltraFusion not only allows us to fuse two M1 Max together and create the M1 Ultra, but it also allows us to connect two M1 Ultras together …”
Look, he made it pretty clear that the Ultra was the last M1 chip. I don’t know why people insist that isn’t true. He didn’t say it had anything to do with Ultra /fusion, or anything else, just that the Ultra was the last. Earlier on, when they announced the Pro and Max versions, they could have said that too, and then popped out the Ultra with the UF connect, and acted as though it was just the same chip.
but they didn’t. And like it or not, that means something. What would have wrong with not saying anything? It’s not semantics. Semantics is something that’s interpretable. A definitive statement is just that.
the other thing thats] you guys are forgetting is that the cost of making these chips increases more than the added area because of increased defects and the risk of unusable chips. The greater percentage of wafer area a chip takes up, the more the cost. It’s a $1,000 upgrade to go from a 48 core Ultra to the 64 core version. And the cheapest Ultra costs more than twice what the Max version costs. So, even if they would do it, this new chip would likely cost at least three times as much. Maybe more. would that be worth it? I’m not so sure.
The good thing is we’ll know soon enough. There’s no way this uncertainty is prolonged past WWDC.
But reading your last paragraph here makes me think you haven’t looked at the mock-up I’ve been referring to, in conjunction with the patent about this packaging tech Apple filed in January. It’s two Ultras stacked on top of each other (back-to-back)—doing so doesn’t change anything about the wafer layout for making the Max/Ultra. That’s why, no matter how it works, it can’t be considered a new chip. Because it’s not. The Max Tech video that someone pointed to is goofy YouTube sensationalism, but the reading of the patent seems accurate.
I would just add that TSMC and others have been talking about and carefully crafting the techniques of silicon-pass-through connectors which is the basis for Apples patent mentioned above. It is not bleeding edge, but just getting into the realm of full scale application. Apples patent appears to be just a clever use of the pass though technology.
I’ll just put this here because I don’t think the Max Tech guy was the origin of the mock-up. Regardless, he has backed away from it. So now he’s on the “M2 Extreme” (4xMax) bandwagon, pretty much what Marvin posted above.
Editing to note that this isn’t a total fantasy, it’s pretty much exactly what some of that patent describes and illustrates (to be clear, though, this image is not from the patent)…
It's amazing that people don't think this is possible. Before the M1 Ultra was announced these same people would've said that it was impossible, too.
It would certainly be challenging to cool such a design.
Allow me to add that I don’t quite get the argument that it has to be M2 — I gather there is a technical reason for it, but I think that’s hard to say without knowing a lot more than we do. I find the idea that Apple would design this entire M1 line but not account for the Mac Pro to be absurd.
In terms of naming, I don’t think they will call it the Ultra Pro or Ultra+, they will all be Ultra, just with different core counts. Basically an Ultra is 2 or 4 Max fused together.
It’s pretty clear that they are finished with the M1. Will people please stop making new M1 chips up?
They may use two or even four M1 Ultra chips. They may change their concept of introducing more powerful chips over the year, and have an M2 Ultra for the Mac Pro. We don’t know. But they won’t have a four chip Ultra. John made that pretty clear.
John was introducing the UltraFusion process when he said that. That process may also allow them to connect two Ultras together, much like what you’re suggesting when you say they may use multiple M1 Ultras in the Mac Pro. It’s a plausible technical solution to the problem. That’s the whole point of the “chiplet” approach. I think you’re getting hung up on semantics, although I’ll concede that it was not a live event and everything said was carefully reviewed.
It isn’t hard to imagine how John would introduce the idea, “UltraFusion not only allows us to fuse two M1 Max together and create the M1 Ultra, but it also allows us to connect two M1 Ultras together …”
Look, he made it pretty clear that the Ultra was the last M1 chip. I don’t know why people insist that isn’t true. He didn’t say it had anything to do with Ultra /fusion, or anything else, just that the Ultra was the last. Earlier on, when they announced the Pro and Max versions, they could have said that too, and then popped out the Ultra with the UF connect, and acted as though it was just the same chip.
but they didn’t. And like it or not, that means something. What would have wrong with not saying anything? It’s not semantics. Semantics is something that’s interpretable. A definitive statement is just that.
the other thing thats] you guys are forgetting is that the cost of making these chips increases more than the added area because of increased defects and the risk of unusable chips. The greater percentage of wafer area a chip takes up, the more the cost. It’s a $1,000 upgrade to go from a 48 core Ultra to the 64 core version. And the cheapest Ultra costs more than twice what the Max version costs. So, even if they would do it, this new chip would likely cost at least three times as much. Maybe more. would that be worth it? I’m not so sure.
The good thing is we’ll know soon enough. There’s no way this uncertainty is prolonged past WWDC.
But reading your last paragraph here makes me think you haven’t looked at the mock-up I’ve been referring to, in conjunction with the patent about this packaging tech Apple filed in January. It’s two Ultras stacked on top of each other (back-to-back)—doing so doesn’t change anything about the wafer layout for making the Max/Ultra. That’s why, no matter how it works, it can’t be considered a new chip. Because it’s not. The Max Tech video that someone pointed to is goofy YouTube sensationalism, but the reading of the patent seems accurate.
I would just add that TSMC and others have been talking about and carefully crafting the techniques of silicon-pass-through connectors which is the basis for Apples patent mentioned above. It is not bleeding edge, but just getting into the realm of full scale application. Apples patent appears to be just a clever use of the pass though technology.
I’ll just put this here because I don’t think the Max Tech guy was the origin of the mock-up. Regardless, he has backed away from it. So now he’s on the “M2 Extreme” (4xMax) bandwagon, pretty much what Marvin posted above.
Editing to note that this isn’t a total fantasy, it’s pretty much exactly what some of that patent describes and illustrates (to be clear, though, this image is not from the patent)…
Wouldn't the connecting die in this case need some switch logic or does each SOC have a half bandwidth connection to 2 out of 3 others in the stack?
Allow me to add that I don’t quite get the argument that it has to be M2 — I gather there is a technical reason for it, but I think that’s hard to say without knowing a lot more than we do. I find the idea that Apple would design this entire M1 line but not account for the Mac Pro to be absurd.
In terms of naming, I don’t think they will call it the Ultra Pro or Ultra+, they will all be Ultra, just with different core counts. Basically an Ultra is 2 or 4 Max fused together.
It’s pretty clear that they are finished with the M1. Will people please stop making new M1 chips up?
They may use two or even four M1 Ultra chips. They may change their concept of introducing more powerful chips over the year, and have an M2 Ultra for the Mac Pro. We don’t know. But they won’t have a four chip Ultra. John made that pretty clear.
So what do we make of the myriad rumors going way back of the Jade 4C-Die alongside those of the Jade 2C-Die which came to fruition with the M1 Ultra? It seems unlikely that was a very similar codename for a next gen 4x SoC design. The Ternus comment of course complicates all this, so did they maybe test that design at one point and decide to skip it this gen for some reason? Certainly possible, but it seems like it'd be a disappointment for many if the Mac Pro tops out with the same top end as the Studio. I feel like there's gotta be another trick up their sleeve.
Well, they could use two chips. People seem to think that Apple has come out with a more advanced connector than Intel’s, and AMD’s versions, and that’s it for Apple. They can’t possibly think of a faster way of connecting two chips together on a mobo. Why would people think that?
I just watched MacBreak weekly. Gurman was on it, and was talking about this very thing. He did mention a possibility of a four chip solution, but he thought it was likely to be an M2 thing - if Apple did it. That would be more likely, I think. It’s also possible, as you say, they tested it and it proved deficient, at least, for now. Not everything scales up linearly. Take multi cpu core chips. They never perform as all of the cores would indicate, including Apple’s chips.
Welp, there are still rumors a-floating of stacked Ultras as a possibility, in which case it wouldn't be a new chip, it'd be dual-Ultras. This was covered on this week's ATP rounding up the rumors, and I think it's likely that's the trick up the sleeve.
Allow me to add that I don’t quite get the argument that it has to be M2 — I gather there is a technical reason for it, but I think that’s hard to say without knowing a lot more than we do. I find the idea that Apple would design this entire M1 line but not account for the Mac Pro to be absurd.
In terms of naming, I don’t think they will call it the Ultra Pro or Ultra+, they will all be Ultra, just with different core counts. Basically an Ultra is 2 or 4 Max fused together.
It’s pretty clear that they are finished with the M1. Will people please stop making new M1 chips up?
They may use two or even four M1 Ultra chips. They may change their concept of introducing more powerful chips over the year, and have an M2 Ultra for the Mac Pro. We don’t know. But they won’t have a four chip Ultra. John made that pretty clear.
John was introducing the UltraFusion process when he said that. That process may also allow them to connect two Ultras together, much like what you’re suggesting when you say they may use multiple M1 Ultras in the Mac Pro. It’s a plausible technical solution to the problem. That’s the whole point of the “chiplet” approach. I think you’re getting hung up on semantics, although I’ll concede that it was not a live event and everything said was carefully reviewed.
It isn’t hard to imagine how John would introduce the idea, “UltraFusion not only allows us to fuse two M1 Max together and create the M1 Ultra, but it also allows us to connect two M1 Ultras together …”
Look, he made it pretty clear that the Ultra was the last M1 chip. I don’t know why people insist that isn’t true. He didn’t say it had anything to do with Ultra /fusion, or anything else, just that the Ultra was the last. Earlier on, when they announced the Pro and Max versions, they could have said that too, and then popped out the Ultra with the UF connect, and acted as though it was just the same chip.
but they didn’t. And like it or not, that means something. What would have wrong with not saying anything? It’s not semantics. Semantics is something that’s interpretable. A definitive statement is just that.
the other thing thats] you guys are forgetting is that the cost of making these chips increases more than the added area because of increased defects and the risk of unusable chips. The greater percentage of wafer area a chip takes up, the more the cost. It’s a $1,000 upgrade to go from a 48 core Ultra to the 64 core version. And the cheapest Ultra costs more than twice what the Max version costs. So, even if they would do it, this new chip would likely cost at least three times as much. Maybe more. would that be worth it? I’m not so sure.
The good thing is we’ll know soon enough. There’s no way this uncertainty is prolonged past WWDC.
But reading your last paragraph here makes me think you haven’t looked at the mock-up I’ve been referring to, in conjunction with the patent about this packaging tech Apple filed in January. It’s two Ultras stacked on top of each other (back-to-back)—doing so doesn’t change anything about the wafer layout for making the Max/Ultra. That’s why, no matter how it works, it can’t be considered a new chip. Because it’s not. The Max Tech video that someone pointed to is goofy YouTube sensationalism, but the reading of the patent seems accurate.
I would just add that TSMC and others have been talking about and carefully crafting the techniques of silicon-pass-through connectors which is the basis for Apples patent mentioned above. It is not bleeding edge, but just getting into the realm of full scale application. Apples patent appears to be just a clever use of the pass though technology.
I’ll just put this here because I don’t think the Max Tech guy was the origin of the mock-up. Regardless, he has backed away from it. So now he’s on the “M2 Extreme” (4xMax) bandwagon, pretty much what Marvin posted above.
Editing to note that this isn’t a total fantasy, it’s pretty much exactly what some of that patent describes and illustrates (to be clear, though, this image is not from the patent)…
It's amazing that people don't think this is possible. Before the M1 Ultra was announced these same people would've said that it was impossible, too.
It would certainly be challenging to cool such a design.
Would it? In a twice larger Mac Pro case, with a larger heat sink and larger fan system than the Studio? Seems like something Apple could figure out.
It's amazing that people don't think this is possible. Before the M1 Ultra was announced these same people would've said that it was impossible, too.
The surprise about the Ultra wasn’t that it wasn’t physically possible, it was that Apple had planned it in from early in their design process, and made the economics and thermals work. Impressive planning, execution and secrecy.
The stacked chips are physically MUCH harder in terms of design, thermals, assembly and packaging. We haven’t seen anything like this with devices this size and power. And even “just” a four way crossbar at this scale (in just two dimensions, without stacking) would be an impressive piece of work. If the Ultra warrants being called a “new chip”, then a four way device of any sort sure as shit would deserve that status as well. So unless they flat out lied about no more M1 chips coming, this isn’t going to happen.
It may happen someday (these technologies are being researched, and used in various places), I just don’t think we will see it with the M1 line nor this year.
Allow me to add that I don’t quite get the argument that it has to be M2 — I gather there is a technical reason for it, but I think that’s hard to say without knowing a lot more than we do. I find the idea that Apple would design this entire M1 line but not account for the Mac Pro to be absurd.
In terms of naming, I don’t think they will call it the Ultra Pro or Ultra+, they will all be Ultra, just with different core counts. Basically an Ultra is 2 or 4 Max fused together.
It’s pretty clear that they are finished with the M1. Will people please stop making new M1 chips up?
They may use two or even four M1 Ultra chips. They may change their concept of introducing more powerful chips over the year, and have an M2 Ultra for the Mac Pro. We don’t know. But they won’t have a four chip Ultra. John made that pretty clear.
John was introducing the UltraFusion process when he said that. That process may also allow them to connect two Ultras together, much like what you’re suggesting when you say they may use multiple M1 Ultras in the Mac Pro. It’s a plausible technical solution to the problem. That’s the whole point of the “chiplet” approach. I think you’re getting hung up on semantics, although I’ll concede that it was not a live event and everything said was carefully reviewed.
It isn’t hard to imagine how John would introduce the idea, “UltraFusion not only allows us to fuse two M1 Max together and create the M1 Ultra, but it also allows us to connect two M1 Ultras together …”
Look, he made it pretty clear that the Ultra was the last M1 chip. I don’t know why people insist that isn’t true. He didn’t say it had anything to do with Ultra /fusion, or anything else, just that the Ultra was the last. Earlier on, when they announced the Pro and Max versions, they could have said that too, and then popped out the Ultra with the UF connect, and acted as though it was just the same chip.
but they didn’t. And like it or not, that means something. What would have wrong with not saying anything? It’s not semantics. Semantics is something that’s interpretable. A definitive statement is just that.
the other thing thats] you guys are forgetting is that the cost of making these chips increases more than the added area because of increased defects and the risk of unusable chips. The greater percentage of wafer area a chip takes up, the more the cost. It’s a $1,000 upgrade to go from a 48 core Ultra to the 64 core version. And the cheapest Ultra costs more than twice what the Max version costs. So, even if they would do it, this new chip would likely cost at least three times as much. Maybe more. would that be worth it? I’m not so sure.
The good thing is we’ll know soon enough. There’s no way this uncertainty is prolonged past WWDC.
But reading your last paragraph here makes me think you haven’t looked at the mock-up I’ve been referring to, in conjunction with the patent about this packaging tech Apple filed in January. It’s two Ultras stacked on top of each other (back-to-back)—doing so doesn’t change anything about the wafer layout for making the Max/Ultra. That’s why, no matter how it works, it can’t be considered a new chip. Because it’s not. The Max Tech video that someone pointed to is goofy YouTube sensationalism, but the reading of the patent seems accurate.
I would just add that TSMC and others have been talking about and carefully crafting the techniques of silicon-pass-through connectors which is the basis for Apples patent mentioned above. It is not bleeding edge, but just getting into the realm of full scale application. Apples patent appears to be just a clever use of the pass though technology.
I’ll just put this here because I don’t think the Max Tech guy was the origin of the mock-up. Regardless, he has backed away from it. So now he’s on the “M2 Extreme” (4xMax) bandwagon, pretty much what Marvin posted above.
Editing to note that this isn’t a total fantasy, it’s pretty much exactly what some of that patent describes and illustrates (to be clear, though, this image is not from the patent)…
It's amazing that people don't think this is possible. Before the M1 Ultra was announced these same people would've said that it was impossible, too.
It would certainly be challenging to cool such a design.
Would it? In a twice larger Mac Pro case, with a larger heat sink and larger fan system than the Studio? Seems like something Apple could figure out.
I'm not saying they couldn't, but two high performance chip stacked like that (*2) will generate a lot of heat. The M1 Ultra heat sink in the Mac Studio is already very beefy and teardowns are showing heatpipe cooling on both sides. It will be challenging to achieve the same cooling in a double stacked chip.
Allow me to add that I don’t quite get the argument that it has to be M2 — I gather there is a technical reason for it, but I think that’s hard to say without knowing a lot more than we do. I find the idea that Apple would design this entire M1 line but not account for the Mac Pro to be absurd.
In terms of naming, I don’t think they will call it the Ultra Pro or Ultra+, they will all be Ultra, just with different core counts. Basically an Ultra is 2 or 4 Max fused together.
It’s pretty clear that they are finished with the M1. Will people please stop making new M1 chips up?
They may use two or even four M1 Ultra chips. They may change their concept of introducing more powerful chips over the year, and have an M2 Ultra for the Mac Pro. We don’t know. But they won’t have a four chip Ultra. John made that pretty clear.
John was introducing the UltraFusion process when he said that. That process may also allow them to connect two Ultras together, much like what you’re suggesting when you say they may use multiple M1 Ultras in the Mac Pro. It’s a plausible technical solution to the problem. That’s the whole point of the “chiplet” approach. I think you’re getting hung up on semantics, although I’ll concede that it was not a live event and everything said was carefully reviewed.
It isn’t hard to imagine how John would introduce the idea, “UltraFusion not only allows us to fuse two M1 Max together and create the M1 Ultra, but it also allows us to connect two M1 Ultras together …”
Look, he made it pretty clear that the Ultra was the last M1 chip. I don’t know why people insist that isn’t true. He didn’t say it had anything to do with Ultra /fusion, or anything else, just that the Ultra was the last. Earlier on, when they announced the Pro and Max versions, they could have said that too, and then popped out the Ultra with the UF connect, and acted as though it was just the same chip.
but they didn’t. And like it or not, that means something. What would have wrong with not saying anything? It’s not semantics. Semantics is something that’s interpretable. A definitive statement is just that.
the other thing thats] you guys are forgetting is that the cost of making these chips increases more than the added area because of increased defects and the risk of unusable chips. The greater percentage of wafer area a chip takes up, the more the cost. It’s a $1,000 upgrade to go from a 48 core Ultra to the 64 core version. And the cheapest Ultra costs more than twice what the Max version costs. So, even if they would do it, this new chip would likely cost at least three times as much. Maybe more. would that be worth it? I’m not so sure.
The good thing is we’ll know soon enough. There’s no way this uncertainty is prolonged past WWDC.
But reading your last paragraph here makes me think you haven’t looked at the mock-up I’ve been referring to, in conjunction with the patent about this packaging tech Apple filed in January. It’s two Ultras stacked on top of each other (back-to-back)—doing so doesn’t change anything about the wafer layout for making the Max/Ultra. That’s why, no matter how it works, it can’t be considered a new chip. Because it’s not. The Max Tech video that someone pointed to is goofy YouTube sensationalism, but the reading of the patent seems accurate.
I would just add that TSMC and others have been talking about and carefully crafting the techniques of silicon-pass-through connectors which is the basis for Apples patent mentioned above. It is not bleeding edge, but just getting into the realm of full scale application. Apples patent appears to be just a clever use of the pass though technology.
I’ll just put this here because I don’t think the Max Tech guy was the origin of the mock-up. Regardless, he has backed away from it. So now he’s on the “M2 Extreme” (4xMax) bandwagon, pretty much what Marvin posted above.
Editing to note that this isn’t a total fantasy, it’s pretty much exactly what some of that patent describes and illustrates (to be clear, though, this image is not from the patent)…
That illustration may not be possible according to the tear down done by Max?tech done a couple of days ago. It shows the Ultra having heat pipes on both sides of the chip. I’ve said that I can see this working for a while, if Apple had cooling between the chips, at least. It seems that nit inlet would between the chip cooling be required, but cooling on both outsides as well.
Allow me to add that I don’t quite get the argument that it has to be M2 — I gather there is a technical reason for it, but I think that’s hard to say without knowing a lot more than we do. I find the idea that Apple would design this entire M1 line but not account for the Mac Pro to be absurd.
In terms of naming, I don’t think they will call it the Ultra Pro or Ultra+, they will all be Ultra, just with different core counts. Basically an Ultra is 2 or 4 Max fused together.
It’s pretty clear that they are finished with the M1. Will people please stop making new M1 chips up?
They may use two or even four M1 Ultra chips. They may change their concept of introducing more powerful chips over the year, and have an M2 Ultra for the Mac Pro. We don’t know. But they won’t have a four chip Ultra. John made that pretty clear.
So what do we make of the myriad rumors going way back of the Jade 4C-Die alongside those of the Jade 2C-Die which came to fruition with the M1 Ultra? It seems unlikely that was a very similar codename for a next gen 4x SoC design. The Ternus comment of course complicates all this, so did they maybe test that design at one point and decide to skip it this gen for some reason? Certainly possible, but it seems like it'd be a disappointment for many if the Mac Pro tops out with the same top end as the Studio. I feel like there's gotta be another trick up their sleeve.
Well, they could use two chips. People seem to think that Apple has come out with a more advanced connector than Intel’s, and AMD’s versions, and that’s it for Apple. They can’t possibly think of a faster way of connecting two chips together on a mobo. Why would people think that?
I just watched MacBreak weekly. Gurman was on it, and was talking about this very thing. He did mention a possibility of a four chip solution, but he thought it was likely to be an M2 thing - if Apple did it. That would be more likely, I think. It’s also possible, as you say, they tested it and it proved deficient, at least, for now. Not everything scales up linearly. Take multi cpu core chips. They never perform as all of the cores would indicate, including Apple’s chips.
Welp, there are still rumors a-floating of stacked Ultras as a possibility, in which case it wouldn't be a new chip, it'd be dual-Ultras. This was covered on this week's ATP rounding up the rumors, and I think it's likely that's the trick up the sleeve.
Rumors, rumors. Anyone can make up a rumor, and most are wrong. Even the best known rumors guys are wrong at times, and even change what they say as time goes on.
it’s what I’ve been saying. It would be two chips, not one, as some others are hoping for, though I don’t know why. But right now, anything for M2 is completely up in the air. Is it going to be based in the A15 (disappointing if so), or the upcoming A16. After all pretty much all the work on the A16 is done. Just final tape-out, approval from Apple, then preproduction. Manufacturing of that chip would start around May/June. That’s enough time for an A16 based M2 to come out this year. I would imagine that Apple has been planning the M2 for at least a year already. With the experience with the M1 derivatives, the M2 series could come out more rapidly. End of year? Maybe.
Not sure how the circle of “32+8+128” M1 Max Quad chip rumors is going to be squared, but stacking 2 M1 Ultra chips seems way too sporty, and probably isn’t going to be it.
I’m waiting on them to stack LPDDR chips, which should be much more thermally possible than stacking logic chips, and there’s no hint of that so far. Stacking 60 W logic chips seems way crazier.
Ternus said that the M1 Ultra is the last M1 derived chip. The stacked M1 Ultra “Duo” would represent another M1 derived chip. From this standpoint, I think it is an automatic no-go for the stacked M1 Ultras idea.
So, just based off of this, they will have M2 Max chips that will support stitching/bridging of 4 M2 Max chips. My bet is 4 chips laid flat in a 2x2 format with a silicon interposer switch (or whatever topology) that bridges them together, and fast enough to appear as 1 GPU. The silicon interposer port only goes along 1 side.
Another thing to consider is that I think they will support PCIe slots in the Mac Pro. At least I think so. They will need to add enough PCIe 4.0 lanes to support 6 to 8 slots. There will need to have an edge of the chip to do that. 16 PCIe 4.0 lanes per chip gives them 64 in a quad setup, spread across 8 slots in something like a 16+8+16+8+4+4+4+4 lanes per slot arrangement.
How they ship a Mac Pro by December 2022 with an M2 is going to be interesting to see. Maybe it’s just the initial allotment of M2 Max chips, they won’t need that many for the Mac Pro, before the MBP14/16 are updated in Spring of 2023.
Not sure how the circle of “32+8+128” M1 Max Quad chip rumors is going to be squared, but stacking 2 M1 Ultra chips seems way too sporty, and probably isn’t going to be it.
I’m waiting on them to stack LPDDR chips, which should be much more thermally possible than stacking logic chips, and there’s no hint of that so far. Stacking 60 W logic chips seems way crazier.
Ternus said that the M1 Ultra is the last M1 derived chip. The stacked M1 Ultra “Duo” would represent another M1 derived chip. From this standpoint, I think it is an automatic no-go for the stacked M1 Ultras idea.
So, just based off of this, they will have M2 Max chips that will support stitching/bridging of 4 M2 Max chips. My bet is 4 chips laid flat in a 2x2 format with a silicon interposer switch (or whatever topology) that bridges them together, and fast enough to appear as 1 GPU. The silicon interposer port only goes along 1 side.
Another thing to consider is that I think they will support PCIe slots in the Mac Pro. At least I think so. They will need to add enough PCIe 4.0 lanes to support 6 to 8 slots. There will need to have an edge of the chip to do that. 16 PCIe 4.0 lanes per chip gives them 64 in a quad setup, spread across 8 slots in something like a 16+8+16+8+4+4+4+4 lanes per slot arrangement.
How they ship a Mac Pro by December 2022 with an M2 is going to be interesting to see. Maybe it’s just the initial allotment of M2 Max chips, they won’t need that many for the Mac Pro, before the MBP14/16 are updated in Spring of 2023.
I can go with that. With M2, we have no idea as to what Apple is planning. A faster Ultra Fusion interposer perhaps? Higher memory speeds? There’s actually, even with these speeds, a limitation as to how many cores have access to full memory bandwidth they need at once. Will they go to double size memory packages again? If so, maybe the base M2 will be 16GB/32GB instead of the current 8/16. That would give a Max 128, and an Ultra 256 (or whatever Apple calls them. That way, a Mac Pro could get 256, or possibly 512 for two chips. Would that be enough for most Mac Pro customers?
Could/would Apple enable plug in memory? In theory, that’s very possible if the chips have the lines for it. People should remember that RAM is on the substrate, not on the die. So if they want to they can extend the substrate any way they want. The doubled the height for the Ultra now, so that shows it can be done. After all, it’s really just a specialized circuit board. And Apple has been devising connectors for a long time. They could make sockets for small packages of RAM. Just pop them in. A small hit to latency, but if it doubles or quadruples RAM, it could be worth it.
‘’there are a number of things I can see them doing, but I sure agree that they’re through with the M1 series as far as new chips go.
Allow me to add that I don’t quite get the argument that it has to be M2 — I gather there is a technical reason for it, but I think that’s hard to say without knowing a lot more than we do. I find the idea that Apple would design this entire M1 line but not account for the Mac Pro to be absurd.
In terms of naming, I don’t think they will call it the Ultra Pro or Ultra+, they will all be Ultra, just with different core counts. Basically an Ultra is 2 or 4 Max fused together.
It’s pretty clear that they are finished with the M1. Will people please stop making new M1 chips up?
They may use two or even four M1 Ultra chips. They may change their concept of introducing more powerful chips over the year, and have an M2 Ultra for the Mac Pro. We don’t know. But they won’t have a four chip Ultra. John made that pretty clear.
John was introducing the UltraFusion process when he said that. That process may also allow them to connect two Ultras together, much like what you’re suggesting when you say they may use multiple M1 Ultras in the Mac Pro. It’s a plausible technical solution to the problem. That’s the whole point of the “chiplet” approach. I think you’re getting hung up on semantics, although I’ll concede that it was not a live event and everything said was carefully reviewed.
It isn’t hard to imagine how John would introduce the idea, “UltraFusion not only allows us to fuse two M1 Max together and create the M1 Ultra, but it also allows us to connect two M1 Ultras together …”
Look, he made it pretty clear that the Ultra was the last M1 chip. I don’t know why people insist that isn’t true. He didn’t say it had anything to do with Ultra /fusion, or anything else, just that the Ultra was the last. Earlier on, when they announced the Pro and Max versions, they could have said that too, and then popped out the Ultra with the UF connect, and acted as though it was just the same chip.
but they didn’t. And like it or not, that means something. What would have wrong with not saying anything? It’s not semantics. Semantics is something that’s interpretable. A definitive statement is just that.
the other thing thats] you guys are forgetting is that the cost of making these chips increases more than the added area because of increased defects and the risk of unusable chips. The greater percentage of wafer area a chip takes up, the more the cost. It’s a $1,000 upgrade to go from a 48 core Ultra to the 64 core version. And the cheapest Ultra costs more than twice what the Max version costs. So, even if they would do it, this new chip would likely cost at least three times as much. Maybe more. would that be worth it? I’m not so sure.
The good thing is we’ll know soon enough. There’s no way this uncertainty is prolonged past WWDC.
But reading your last paragraph here makes me think you haven’t looked at the mock-up I’ve been referring to, in conjunction with the patent about this packaging tech Apple filed in January. It’s two Ultras stacked on top of each other (back-to-back)—doing so doesn’t change anything about the wafer layout for making the Max/Ultra. That’s why, no matter how it works, it can’t be considered a new chip. Because it’s not. The Max Tech video that someone pointed to is goofy YouTube sensationalism, but the reading of the patent seems accurate.
I would just add that TSMC and others have been talking about and carefully crafting the techniques of silicon-pass-through connectors which is the basis for Apples patent mentioned above. It is not bleeding edge, but just getting into the realm of full scale application. Apples patent appears to be just a clever use of the pass though technology.
I’ll just put this here because I don’t think the Max Tech guy was the origin of the mock-up. Regardless, he has backed away from it. So now he’s on the “M2 Extreme” (4xMax) bandwagon, pretty much what Marvin posted above.
Editing to note that this isn’t a total fantasy, it’s pretty much exactly what some of that patent describes and illustrates (to be clear, though, this image is not from the patent)…
It's amazing that people don't think this is possible. Before the M1 Ultra was announced these same people would've said that it was impossible, too.
It would certainly be challenging to cool such a design.
Would it? In a twice larger Mac Pro case, with a larger heat sink and larger fan system than the Studio? Seems like something Apple could figure out.
I'm not saying they couldn't, but two high performance chip stacked like that (*2) will generate a lot of heat. The M1 Ultra heat sink in the Mac Studio is already very beefy and teardowns are showing heatpipe cooling on both sides. It will be challenging to achieve the same cooling in a double stacked chip.
I didn't know about the heatpipes on both sides — I definitely need to check out the teardown still.
I’m waiting for a video meme where you see a super-long chip, which just goes on and on for a minute until it is presented as the ”Apple M1 200X Ultra” or something.
The opening sequence of "Spaceballs" comes to mind.
Comments
The stacked chips are physically MUCH harder in terms of design, thermals, assembly and packaging. We haven’t seen anything like this with devices this size and power. And even “just” a four way crossbar at this scale (in just two dimensions, without stacking) would be an impressive piece of work. If the Ultra warrants being called a “new chip”, then a four way device of any sort sure as shit would deserve that status as well. So unless they flat out lied about no more M1 chips coming, this isn’t going to happen.
It may happen someday (these technologies are being researched, and used in various places), I just don’t think we will see it with the M1 line nor this year.
it’s what I’ve been saying. It would be two chips, not one, as some others are hoping for, though I don’t know why. But right now, anything for M2 is completely up in the air. Is it going to be based in the A15 (disappointing if so), or the upcoming A16. After all pretty much all the work on the A16 is done. Just final tape-out, approval from Apple, then preproduction. Manufacturing of that chip would start around May/June. That’s enough time for an A16 based M2 to come out this year. I would imagine that Apple has been planning the M2 for at least a year already. With the experience with the M1 derivatives, the M2 series could come out more rapidly. End of year? Maybe.
So, just based off of this, they will have M2 Max chips that will support stitching/bridging of 4 M2 Max chips. My bet is 4 chips laid flat in a 2x2 format with a silicon interposer switch (or whatever topology) that bridges them together, and fast enough to appear as 1 GPU. The silicon interposer port only goes along 1 side.
Could/would Apple enable plug in memory? In theory, that’s very possible if the chips have the lines for it. People should remember that RAM is on the substrate, not on the die. So if they want to they can extend the substrate any way they want. The doubled the height for the Ultra now, so that shows it can be done. After all, it’s really just a specialized circuit board. And Apple has been devising connectors for a long time. They could make sockets for small packages of RAM. Just pop them in. A small hit to latency, but if it doubles or quadruples RAM, it could be worth it.
‘’there are a number of things I can see them doing, but I sure agree that they’re through with the M1 series as far as new chips go.