651–660 of 855 posts
What are people doing with these CPUs on a desktop ? I'm just watching videos, surfing, and doing some programming -- on a 5 year old Ryzen with 32GB and it seems perfectly fine. For my productivity needs, performance is mostly about I/O speed and so switching to SSD and then NVME was the biggest boost for me (Linux at work). When I get home, it's all about the GPU on my gaming PC (Windows). It's just that CPU just d…
Earlier quoted context omitted.
I suppose given that this is two M1 Max glued together, assuming cooling is a solved problem, the max SOC power consumption just twice as high as usual, plus interconnect overhead. Right? Based on the thermal and power consumption characteristics of previous chips I would not be surprised if say ~120W is the max power draw of this thing. edit: Of course the M1 max only shipped in laptops, so... who knows.
> assuming cooling is a solved problem I’d assume that’s what most of the chonk is about, no? > Based on the thermal and power consumption characteristics of previous chips I would not be surprised if say ~120W is the max power draw of this thing. The Max could be brought up to 90W or so.
I think the GPU claims are interesting. According to the graph's footer, the M1 Ultra was compared to an RTX 3090. If the performance/wattage claims are correct, I'm wondering if the Mac Studio could become an "affordable" personal machine learning workstation (which also won't make the electricity bill skyrocket). If Pytorch becomes stable and easy to use on Apple Silicon [0][1], it could be an appealing choice. [0]…
Earlier quoted context omitted.
Are both cases compiling to the same target architecture? If not, you may well be comparing the relative performance of different compiler backends instead of comparing the performance of your CPUs. (+ now I see it's rust: how parallel is your build, really?)
The target arch doesn’t matter for the change-build-test loop d vs do. All that matters is how fast can you compile your code to test it. If the final x86 production build takes longer it doesn’t matter - that happens on the cloud anyway. Edit: Rust builds are very parallel until linking. No different than any other LLVM build.
It matters when comparing CPU performance, which is what this benchmark is being used for.
Looks like all the people saying "just start fusing those M1 CPU's into bigger ones" were right, that's basically what they did here (fused two M1 Max'es together). And since the presenter mentioned the Mac Pro would come on another day, I wonder if they'll just do 4x M1 Max for that.
>Looks like all the people saying "just start fusing those M1 CPU's into bigger ones" were right, Well they were only correct that Apple managed to hide a whole section of Die Image. ( Which is actually genius ) Otherwise it wouldn't have made any sense. Likely to be using CoWoS from TSMC [1] since the bandwidth numbers fits. But needs further confirmation. [1] https://en.wikichip.org/wiki/tsmc/cowos
I think the GPU claims are interesting. According to the graph's footer, the M1 Ultra was compared to an RTX 3090. If the performance/wattage claims are correct, I'm wondering if the Mac Studio could become an "affordable" personal machine learning workstation (which also won't make the electricity bill skyrocket). If Pytorch becomes stable and easy to use on Apple Silicon [0][1], it could be an appealing choice. [0]…
The GPU claims on the M1 Pro & Max were, let's say, cherry picked to put it nicely. The M1 Ultra claims already look suspicious since the GPU graph tops out at ~120W & the CPU graph tops out at ~60W yet the M1 Studio is rated for 370W continuous power draw. Since you mention ML specifically, looking at some benchmarks out there (like https://tlkh.dev/benchmarking-the-apple-m1-max#heading-gpu & https://wandb.ai/tcapel…
Interested to know what you think a reasonable PSU would be for A machine that was consuming close to 200W for processing...
Earlier quoted context omitted.
> assuming cooling is a solved problem I’d assume that’s what most of the chonk is about, no? > Based on the thermal and power consumption characteristics of previous chips I would not be surprised if say ~120W is the max power draw of this thing. The Max could be brought up to 90W or so.
I wouldn't assume heat is solved as it's been Apples weak point in the past. The cube would crack, g5 iMac's would melt capacitors, MacBooks would burn users' laps.
Earlier quoted context omitted.
I've been saying 4x M1 Max is not a thing and never will be a thing ever since the week I got my M1 Max and saw that the IRQ controller was only instantiated to support 2 dies, but everyone kept parroting that nonsense the Bloomberg reporter said about a 4-die version regardless... Turns out I was right. The Mac Pro chip will be a different thing/die.
Plus they are running out of M1 superlatives. They’ll have to go to M2 to avoid launching M1 Plaid.
Earlier quoted context omitted.
>Looks like all the people saying "just start fusing those M1 CPU's into bigger ones" were right, Well they were only correct that Apple managed to hide a whole section of Die Image. ( Which is actually genius ) Otherwise it wouldn't have made any sense. Likely to be using CoWoS from TSMC [1] since the bandwidth numbers fits. But needs further confirmation. [1] https://en.wikichip.org/wiki/tsmc/cowos
The interconnect area was already known from third-party die photos of the M1 Max https://twitter.com/vadimyuryev/status/1466526403331952644
I wrote about it three months ago.