[llvm] [WIP][RISCV] Tune flag for fast vrgather.vv (PR #124664)

[Petr Penzin via llvm-commits]

================
@@ -490,6 +490,7 @@ def TENSTORRENT_ASCALON_D8 : RISCVProcessorModel<"tt-ascalon-d8",
                                                   FeatureUnalignedScalarMem,
                                                   FeatureUnalignedVectorMem]),
                                                  [TuneNoDefaultUnroll,
+                                                  TuneFastVRGather,
----------------
ppenzin wrote:

Joining with next line would definitely push that past 80 columns, is that OK?

https://github.com/llvm/llvm-project/pull/124664