this post was submitted on 05 Mar 2025
23 points (100.0% liked)
Technology
38412 readers
411 users here now
A nice place to discuss rumors, happenings, innovations, and challenges in the technology sphere. We also welcome discussions on the intersections of technology and society. If it’s technological news or discussion of technology, it probably belongs here.
Remember the overriding ethos on Beehaw: Be(e) Nice. Each user you encounter here is a person, and should be treated with kindness (even if they’re wrong, or use a Linux distro you don’t like). Personal attacks will not be tolerated.
Subcommunities on Beehaw:
This community's icon was made by Aaron Schneider, under the CC-BY-NC-SA 4.0 license.
founded 3 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
Holy shit.
M3 Ultra chip with 32-core CPU, 80‑core GPU, 32-core Neural Engine, 512 RAM
Still a ton of money, but I'm salivating. M4 is only Max at this point, but now I'm dreaming about what that might become.
I wonder if this will be the game plan going forward, with the Ultra chip lagging by a year. Seems a likely cadence.
That RAM is nice, but core count doesn't say much at this point: there are different cores with different architectures, multithreading, pipelining, caches, speeds, etc.
I'd rather see a TOPS comparison:
Meta is claiming to have 350,000 H100s, to put things into perspective.
I mean, sure, but largely GPU-based TOPS isn't that good a comparison with a CPU+GPU mixture. Most tasks can't be parallelized that well, so comparing TOPS between an APU and a TPU/GPU is not apples to apples (heh).
Agreed, but my point is that stating "x-core CPU, y-core GPU, z-core NPU", is basically non-information.
I'd like to see the TOPS for each of those, instead of a "core count" that tells me nothing about actual performance. Even the TOPS are orientative... but would be a good start.
Agreed! I'm just not sure TOPS is the right metric for a CPU, due to how different the CPU data pipeline is than a GPU. Bubbly/clear instruction streams are one thing, but the majority type of instruction in a calculation also effects how many instructions can be run on each clock cycle pretty significantly, whereas in matrix-optimized silicon its a lot more fair to generalize over a bulk workload.
Generally, I think its fundamentally challenging to generate a generally applicable single number to represent CPU performance across different workloads.
I think the next ultras won’t use the fusion thing and will be just a larger die. (the m4 max does not seem to have the connector) so it might take them a bit to sort it out.