Re:Google's First Tensor Processing Unit: Architecture
by KeplerBoy on Tuesday March 26, 2024 @04:07AM
(#39825245)
That's just C. If you're accessing your arrays out of bounds it's going to segfault. hopefully.
Can't blame CUDA for that one.
Re:Google's First Tensor Processing Unit: Architecture
by otabdeveloper4 on Tuesday March 26, 2024 @06:02AM
(#39825973)
I'm talking about the compiler segfaulting, not the end-user code.
Re:Google's First Tensor Processing Unit: Architecture
by Culonavirus on Tuesday March 26, 2024 @04:52AM
(#39825548)
Skill issue.
Re:Google's First Tensor Processing Unit: Architecture
by otabdeveloper4 on Tuesday March 26, 2024 @06:01AM
(#39825963)
No, CUDA's botched gcc implementation segfaulting due to compiler errors during compilation is not a "skill issue".
(Well, a skill issue of whoever is patching gcc on Nvidia's end, I guess.)
NVidia's software is the only reason I'm not using GPU's for ML tasks and likely never will.