[llvm] [RISCV][ISel] Remove redundant min/max in saturating truncation (PR #75145)

[via llvm-commits]

sun-jacobi wrote:

> How can you use just vnsrl? vnsrl discards the upper bits without any max or min.

Yes, you are right. 

But if the range created by a pair of max/min operation is precisely the range of the truncation destination, 
then the pair could be removed.

In the below case, `[-128, 127]` is the value range of u8. 
Since we truncate the u16 vector into a u8 vector, removing the max/min won't change the final result, AFAIU. 

https://github.com/llvm/llvm-project/pull/75145