alt Hacker NewsOn a related note, I was reading yesterday that apparently the real bottleneck for Chinese production of AI accelerators is HBM production, not processors or ASML equipment.
The lack of ASML EUV machines certainly hurts, and pushing DUV so hard results in abysmal yields of good chips, but you can compensate by running more wafers or making smaller chips, and the net result is that Huawei's Ascend production volume is limited by CXMT's HBM capacity not processor dies.
The problem is that HBM manufacture requires many steps (die thinning, via drilling, plating, alignment) where the equipment used by everyone else (Samsung, SK Hynix, Micron) is also blocked by sanctions, so the Chinese are having to develop all of this themselves too, which they have, but yields are currently low, even when using shorter HBM stacks.
Replies
Tokens per second is almost entirely memory bandwidth at inference time, training obviously needs more compute but you can add more chips for that.
China should invest in an analog inference chip. It's a hail mary but why not.
Huawei uses their own non-standard HBM called HiZQ probably not produced by CXMT.
I read HBM yields are 25-30% (vs 80-90%) making them 3 to 5 times as expensive. They are 4-5 years behind, that probably means 1-2 in Chinese time.
The only thing the West is achieving here is that sooner or later China will be able to compete on their own terms rather than ours. It may buy some time but the end result is very predictable.