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.
M1 Max Quadro Mac Pro Leaks - The Alder Lake KILLER! 🤯
- Thread starter Adarna
- Start date
- Sort by reaction score
Apple has a very long history of 20%-on-average year-over-year single core performance increases. Why should that stop suddenly?
(Update: I don’t have specint2006 scores for A15, but it looks like specint2017 shows a 12.5% improvement over A14).
The claim that Apple has an insurmountable lead for effectively the forseeable future. It reminds me of the claims made in the G4 and G5 era.
Claiming that both Intel and AMD will not possibly have anything to compete with something that won't be released for years is a bit much.
Ok. They certainly have an lead for the next several years. Intel is about 3 years behind if you scale by power budget. And nothing from the x86 camp will compete unless Apple stumbles, because Arm is an inherent advantage. It’s possible that some other Arm vendor competes (or some other RISC design), but nobody is in the ballpark right now.
Apple is now in complete control of their CPU and GPUs, just like their mobile A series. Apple no longer has to rely on Intel's release roadmap which has been crap.
So is claiming that they will. They are years behind right now, and nothing they do can overcome the penalty caused by variable length instructions and convoluted addressing modes. The only way an x86-64 design could compete with an Apple design in performance/watt is to be fabbed on a smaller node. (Or for Apple to stumble and release a bad design for some reason)
QualComm is going to enter the PC market with their Arm processors. That will be interesting. I think we are starting a transformative period in the PC market.
I’m aware. And I’m sure their new PC chips will be just as competitive in the PC market in terms of performance/watt as their mobile chips are competitive against the A-series chips
Our newer systems use Epyc chips for that reason. I'm far more interested in performance than performance/watt.
For a desktop system that is not in a small package. But who would have imagined putting a high performance CPU and GPU in a laptop that could run solely on battery and not sound like a jet engine.
Zen4 and 5 looks promising, since we're talking about unreleased products like A17.
I just referenced the A17 because Apple has shown that they can do a yearly cadence. Does AMD do a yearly cadence for their processors?
AMD is far more likely to execute to its roadmap than is Intel.
Of course, as someone who designed CPUs for AMD, I wouldn’t bet on AMD executing forever.
Fewer than 1. The M1 Max is a much larger chip using a newer process.
Of course, the actual price of a chip has little to do with its manufacturing costs.
A64FX is hardly a "high performance ARM chip"... we don't have exact benchmarks but M1 Firestorm is probably at least 2.5x faster than A64FX cores, and probably more than that. Fugaku's performance comes from the fact that it has gazzilion of those cores. And of course, A64FX is a highly specialized chip, designed for parallel throughput on certain scientific workloads. Not something you would put in a general-purpose computer at any rate.
what i am afraid of is the less publicised fact that M1 has a quite big drop of performance (30%) if you use the unified arhitecture under load, I mean memory + GPU + CPU under real load at the same time.
Otherwise i believe it will be like this:
probably, all Apple lineup will get M1 refreshes it just makes sense in business.
MacBook Airs will get some M1 Pros, Mac Minis also but probably not the M1 Max although it can fit in there. early/mid next year. Imac Pros can come back with M1 Pro and M1 Maxes in late 2022.
The new in 2022 Nov, Mac Pro will get the M1 Pro Max chip with 20/40/60/80 core options and memory respectively 128/256/384/512 GPU the same scaling with the cores.
I dont think there will be for example M2 next year (2022), Apple will max out M1 and then in late 2023 M2 maybe.
Otherwise i believe it will be like this:
probably, all Apple lineup will get M1 refreshes it just makes sense in business.
MacBook Airs will get some M1 Pros, Mac Minis also but probably not the M1 Max although it can fit in there. early/mid next year. Imac Pros can come back with M1 Pro and M1 Maxes in late 2022.
The new in 2022 Nov, Mac Pro will get the M1 Pro Max chip with 20/40/60/80 core options and memory respectively 128/256/384/512 GPU the same scaling with the cores.
I dont think there will be for example M2 next year (2022), Apple will max out M1 and then in late 2023 M2 maybe.
It almost feels like Apple manages this in this way so every year has the 20%. Even to the point of withholding performance gains so the next year is guaranteed the same 20%.
This is hardly surprising. The system has finite amount of resources (thermal, memory bandwidth etc.) so if you push it you will see diminishing returns. It makes little sense to optimize the system for such a case since these kind of workloads simply do not exist in the real world (aside from stress testing). By the way, other systems have the same behavior (almost every high-end laptop will throttle if you push the CPU abs the GPU simultaneously).
That said, I am sure that Apples professional systems will do much better in this kind of stress test, especially M1 Max which has many more resources than the base consumer N1.
I would think the lower memory bandwidth provided by the LPDDR4 was the issue...?
I think that they wanted to do a one-year cadence but the supply-chain problems pushed out their schedules.
If the M2-series low-end / entry-level SoCs get LPDDR5, I wonder if the Mn Pro/Max Dual/Quad SoCs (SiPs / MCMs) might move to LPDDR5X...?