Apple’s new M1 Pro and M1 Max processors

Post by beebeepka » Mon, Oct 18, 2021, 11:25 PM UTC

dragontamer wrote: post #595

morei wrote: post #544

Earlier quoted context omitted.

L3 is almost never SRAM, it's usually eDRAM and clocked significantly lower than L1 or L2. (SRAM is prohibitively expensive to do at scale due to die area required). Edit: Nope, I'm wrong. It's pretty much only Power that has this.

As far as I'm aware, IBM is one of the few chip-designers who have eDRAM capabilities. IBM has eDRAM on a number of chips in varying capacities, but... its difficult for me to think of Intel, AMD, Apple, ARM, or other chips that have eDRAM of any kind. Intel had one: the eDRAM "Crystalwell" chip, but that is seemingly a one-off and never attempted again. Even then, this was a 2nd die that was "glued" onto the main ch…

Post by andrekandre » Mon, Oct 18, 2021, 11:27 PM UTC

derefr wrote: post #432

bla3 wrote: post #118

Earlier quoted context omitted.

I thought the memory was one of the more interesting bits here. My 2-year-old Intel MBP has 64 GB, and 8 GB of additional memory on the GPU. True, on the M1 Max you don't have to copy back and forth between CPU and GPU thanks to integrated memory, but the new MBP still has less total memory than my 2-year-old Intel MBP. And it seems they just barely managed to get to 64 GiB. The whole processor chip is surrounded by…

> but the new MBP still has less total memory From the perspective of your GPU, that 64GB of main memory attached to your CPU is almost as slow to fetch from as if it were memory on a separate NUMA node, or even pages swapped to an NVMe disk. It may as well not be considered "memory" at all. It's effectively a secondary storage tier. Which means that you can't really do "GPU things" (e.g. working with hugely detailed…

Post by PragmaticPulp » Mon, Oct 18, 2021, 11:29 PM UTC

labby5 wrote: post #639

satya71 wrote: post #440

Earlier quoted context omitted.

Very simple: thermal budget. Chip performance is limited by thermal budget. You just can't spend more than roughly 100W in a single package, without going into very expensive and esoteric cooling mechanisms.

this is mostly wrong. The real issue has always been memory bandwidth. the highest end consumer x86 CPU has about the same memory bandwidth as a dGPU from 10 years ago. The M1 is extremely competitive with modern dGPUs, only a bit behind a 6900 XT.

Post by wmf » Mon, Oct 18, 2021, 11:36 PM UTC

amelius wrote: post #488

PaulKeeble wrote: post #109

Earlier quoted context omitted.

400GB/s available to the CPU cores in a unified memory, that is going to really help certain workloads that are very memory dominant on modern architectures. Both Intel and AMD are solving this with ever increasing L3 cache sizes but just using attached memory in a SOC has vastly higher memory bandwidth potential and probably better latency too especially on work that doesn't fit in ~32MB of L3 cache.

> 400GB/s available to the CPU cores in a unified memory It's not just throughput that counts, but latency. Any numbers to compare there?

Post by willseth » Mon, Oct 18, 2021, 11:39 PM UTC

sulam wrote: post #616

modulusshift wrote: post #555

Earlier quoted context omitted.

macOS Monterey coming out on the 25th has a new Low Power Mode feature that may do just that. That said, these Macs are incredibly efficient for light use, you may already get 24 hrs of battery life with your workload. Not counting screen off time.

Yes, it depends on what you're doing, but if you can watch 21 hours of video, many people will be able to do more than 24 hours of development.