[llvm] [DAG][RISCV] Use vp_reduce_* when widening illegal types for reductions (PR #105455)

[Luke Lau via llvm-commits]

https://github.com/lukel97 approved this pull request.

LGTM with nits

> We could slide the vector operand up by one, and insert the padding via a vslide1up. We don't currently pattern match this, but we could. This form would arguably be better iff the surrounding code wanted VL=4. This patch will force a VL toggle in that case instead.

My mental model is that a VL toggle is always going to be cheaper than any other regular permutation/arithmetic instruction, in which case this patch would be preferable.

https://github.com/llvm/llvm-project/pull/105455