[llvm] [RISCV] Support llvm.masked.expandload intrinsic (PR #101954)

[Craig Topper via llvm-commits]

================
@@ -1359,6 +1359,10 @@ def TuneOptimizedZeroStrideLoad
                       "true", "Optimized (perform fewer memory operations)"
                       "zero-stride vector load">;
 
+def TuneOptimizedIndexedLoadStore
+   : SubtargetFeature<"optimized-indexed-load-store", "HasOptimizedIndexedLoadStore",
----------------
topperc wrote:

I'm also happy with only vrgather.vv lowering

https://github.com/llvm/llvm-project/pull/101954