Re:Nvidia releases open-source GPU kernel modules
by kllrnohj on Wednesday May 11, 2022 @08:03PM
(#31347602)
> the PC platform has yet to see a proper APU
Wat. AMD literally invented the term 'APU' and has been shipping them since 2011. Fully unified CPU+GPU memory since 2014's Kavari. That's full cache coherent CPU & GPU along with the GPU using the same shared virtual pageable memory as the CPU.
The M1 didn't add anything new to the mix.
Re:Nvidia releases open-source GPU kernel modules
by SemanticStrengh on Wednesday May 11, 2022 @08:18PM
(#31347696)
It's a spectrum. I don't think that cache coherency was useable by developers/compilers. The two only ways I know (HMM and HSA) are niche, used by nobody.
GPGPU compute would GREATLY benefit from programs that can share memory between cpu and gou without having to do needless high latency round-trips and copies.
So they failed in practice.
They never did a CPU addressable HBM interposer (despite having invented HBM) unlike what I believe is the M1.
Re:Nvidia releases open-source GPU kernel modules
by eru on Wednesday May 11, 2022 @09:07PM
(#31348009)
> An unrelated but very underrated is the egpu. Egpus are external to the pc unlike a dgpu. So you can buy a thin laptop, connect it via Thunderbolt to a rtx 3080 and enjoy faster gpu performance than allowed on any laptop on the market, and enjoy a thin lightweight, silent laptop the rest of the time. Disclaimer Thunderbolt is still a moderate limiting factor in reaching peak performance.
Not just for laptops: this sounds also a bit like what the Switch dock could have been.
(And in some sense, it reminds me of Super FX chip for the SNES.)
An unrelated but very underrated is the egpu. Egpus are external to the pc unlike a dgpu. So you can buy a thin laptop, connect it via Thunderbolt to a rtx 3080 and enjoy faster gpu performance than allowed on any laptop on the market, and enjoy a thin lightweight, silent laptop the rest of the time. Disclaimer Thunderbolt is still a moderate limiting factor in reaching peak performance.