ARM is a UK-based company. If they hadn’t dropped out of EU, it’s possible they would have settled on an ARM-based supercomputer design.
Chalk it up to another WIN for Brexit!
ARM was bought by the Japanese, it’s no longer European. RISC-V is the future.
Not just by the Japanese but by Softbank and Son Masayoshi, the guy now doing buddy-buddy photo ops & “Stargate AI” with Trump.
Can anyone knowledgeable tell us if this is feasible, practical, or a good idea?
Yes, yes and yes, but it’ll take a while. It’s a six year project overall.
With tariffs and sanctions, it has become clear that open standards which can’t be controlled by governments are what is needed.
With what’s been happening over the past few years, there will be a lot of interested in this. Recently, I’ve seen lots of news about it, but that could just be the algorithm.
Considering that you can buy some Raspberry Pi micro computers (these are ARM architecture computers) for less than €100 that are performance competitive with a lot of existing hardware; this idea would make a ton of sense for Europe to implement. I think Europe could probably start designing and manufacturing chips locally within 2 to 5 years on the low end 5 to 10 years on the high end.
ARM is proprietary tech owned by Softbank, whose boss Son Masayoshi was last seen cosying up to Trump with the “Stargate” AI consortium.
I love the raspberry pi, but it’s far from being competitive to something like an apple m4, a Qualcomm snapdragon or an am5 chip from AMD.
For its intended purpose it doesn’t need to, but it’s way slower and less power efficient.
deleted by creator
I’m unexpectedly excited and hopeful for risc-v
Regardless of the outcome I just hope this doesn’t lead to more tribalism in software again. The FOSS community needs to stay strong on an international level whenever it comes to hardware integration etc.
I’ll contact the maintainers of all my favorite FOSS programs written in x86 assembler, to ask them to port the software to RISC-V.
Give me something like Talos2 with a full OSS firmware and a performant CPU… and hell, a half-competitive open source graphics core too. It doesn’t need to be peak performance, it needs to be good enough.
I’ve been trying to work with SBC’s for a while for video decoding platforms and just wound up getting stuck on x86 because the ARM situation with weirdo custom kernels for anything useful is just… annoying.
so, I don’t know if the shit hole made anything WORTH copying, but why respect american intellectual property? you know americans don’t respect yours. copy NVIDIA’s CUDA shit, if that’s efficient. fuck em.
The efficiency is not on the API it is on the microarchitecture. The value of copying the API is just to run unmodified software made for CUDA.
There’s also a lot of efficiency in hardware-specific kernels. A generic rocm build vs. one with hand-written kernels (not even for the proper card just a close enough one to have the same instructions) is like a 10x performance drop. That’s on the matrix multiply up to convolve these tensors level, on the layer above that you then have things like smart memory management and scheduling as well as minimising how much work needs to be done in the first place (re-ordering operations so tensors stay small) and stuff.
You can port cuda code to vulkan or opencl – but you’re going to have to reimplement all of that. Just getting the BLAS layer to not suck is a challenge.
China:
Digital Autonomy with RISC-V in Europe
They really tried hard to make an acronym fit…
A bit like SHIELD
Anyone else remember when Phil Schiller bored the Macworld expo to death explaining why RISC was better than CISC?
deleted by creator
