On Wed, Oct 23, 2019 at 4:16 AM Richard Biener <richard.guent...@gmail.com> wrote: > Note I delayed thinking about relaxing the single-vector-size > constraint in the vectorizer until after we're SLP only because > that looked more easily done there. I also remember patches > relaxing this a bit from RISCV folks.
Probably not from us RISC-V folks. I don't know of anyone looking at RISC-V vector support in gcc other than me, and I've only had time for some initial exploration. Jim