[llvm] [RISCV][VLOPT] Add support for checkUsers when UserMI is a Single-Width Integer Reduction (PR #120345)

[Luke Lau via llvm-commits]

================
@@ -149,8 +152,11 @@ define i32 @mul_i32(<4 x i32> %a, <4 x i32> %b) {
 ; RV64-NEXT:    vslidedown.vi v10, v9, 2
 ; RV64-NEXT:    vmul.vv v9, v9, v10
 ; RV64-NEXT:    vrgather.vi v10, v8, 1
+; RV64-NEXT:    vsetivli zero, 1, e32, m1, ta, ma
 ; RV64-NEXT:    vmul.vv v8, v8, v10
+; RV64-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
 ; RV64-NEXT:    vrgather.vi v10, v9, 1
+; RV64-NEXT:    vsetivli zero, 1, e32, m1, ta, ma
----------------
lukel97 wrote:

Ah I see. This looks like a regression in the number of vl toggles though. I think the original diff was the optimal solution, i.e. just using vl=4 for every instruction. Is there a plan to get this back after this PR?



https://github.com/llvm/llvm-project/pull/120345