[llvm] [NVPTX] Merge consecutive elements while buffering constant vectors with sub-byte datatype. (PR #183628)

[Alex MacLean via llvm-commits]

AlexMaclean wrote:

I wonder if it would be possible to use more of the generic AsmPrinter support here instead of continuing to add complexity and features to the NVPTX-specific constant emission code. It seems like this is a problem that someone has already solved for other targets. 

https://github.com/llvm/llvm-project/pull/183628