[llvm] [LV] Introduce the EVLIVSimplify Pass for EVL-vectorized loops (PR #91796)

[Min-Yih Hsu via llvm-commits]

================
@@ -0,0 +1,282 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 4
+; RUN: opt -S -mtriple=riscv64 -mattr='+v' --passes='loop(evl-iv-simplify)' < %s | FileCheck %s
+; RUN: opt -S -mtriple=riscv64 -mattr='+v' --passes='loop(evl-iv-simplify),function(simplifycfg,dce)' < %s | FileCheck %s --check-prefix=LOOP-DEL
+
+define void @simple(ptr noalias %a, ptr noalias %b, ptr noalias %c, i64 %N) {
----------------
mshockwave wrote:

I've tried to simplify it by only using only a single vp.load rather than two.

https://github.com/llvm/llvm-project/pull/91796