Nvidia GB10's Memory Subsystem, from the CPU Side

gessha 10 minutes ago | parent | next [-]

What’s stopping Mediatek from putting some of those cores in a laptop/desktop CPU package? Is it the infrastructure around it? OEM support? All of the above?

▲

freeqaz 5 hours ago | parent | prev | next [-]

I assume that the author here is testing against one of these boxes, right? https://marketplace.nvidia.com/en-us/enterprise/personal-ai-...

Are these considered a good deal at $3-4k? What's the software support like on them? I've got 2x 3090s and I'm curious how this compares.

	▲	wmf 3 hours ago \| parent \| next [-]
		DGX Spark vs. Strix Halo vs. M4 Max is hotly debated. You can find plenty of HN discussions and YouTube videos about it.
	▲	lifestyleguru 42 minutes ago \| parent \| prev [-]
		> https://marketplace.nvidia.com/en-us/enterprise/personal-ai-... In Europe these cost 5k EUR. I guess I'm not buying computer ever again and hopefully the 10 years old ones I have will never die.

▲

Neywiny 12 hours ago | parent | prev | next [-]

I don't understand on one of the later graphs the core to core latency for strix halo goes out to 32 cores but he says only has 16 cores?

▲

wtallis 11 hours ago | parent [-]

AMD's cores have SMT, allowing them to run two threads at a time and appear to the OS and its scheduler as two logical cores despite being implemented as a single physical core.

▲

Neywiny 11 hours ago | parent [-]

What pattern in the data shows that's what's being measured? I would expect to see basically 0 latency between adjacent "cores" then since L1 is shared per thread?

	▲	monocasa 10 hours ago \| parent [-]
		Co resident threads might not get any speed up here since coherency instructions are functionally operations on the L2 cache.

▲

saagarjha an hour ago | parent | prev [-]

Kind of an odd choice to have clusters that are so different