[InstCombine] Avoid folding `select(umin(X, Y), X)` with min/max values in false arm (#143020)llvmorg-20.1.8release/20.x

Fixes https://github.com/llvm/llvm-project/issues/139050.

This patch adds a check to avoid folding min/max reduction into select, which may block loop vectorization.

The issue is that the following snippet:
```
declare i8 @llvm.umin.i8(i8, i8)

define i8 @masked_min_fold_bug(i8 %acc, i8 %val, i8 %mask) {
; CHECK-LABEL: @masked_min_fold_bug(
; CHECK:       %cond = icmp eq i8 %mask, 0
; CHECK:       %masked_val = select i1 %cond, i8 %val, i8 255
; CHECK:       call i8 @llvm.umin.i8(i8 %acc, i8 %masked_val)
;
  %cond = icmp eq i8 %mask, 0
  %masked_val = select i1 %cond, i8 %val, i8 255
  %res = call i8 @llvm.umin.i8(i8 %acc, i8 %masked_val)
  ret i8 %res
}
```

is being optimized to the following code, which can not be vectorized
later.
```
declare i8 @llvm.umin.i8(i8, i8) #0

define i8 @masked_min_fold_bug(i8 %acc, i8 %val, i8 %mask) {
  %cond = icmp eq i8 %mask, 0
  %1 = call i8 @llvm.umin.i8(i8 %acc, i8 %val)
  %res = select i1 %cond, i8 %1, i8 %acc
  ret i8 %res
}

attributes #0 = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }
```

Expected:
```
declare i8 @llvm.umin.i8(i8, i8) #0

define i8 @masked_min_fold_bug(i8 %acc, i8 %val, i8 %mask) {
  %cond = icmp eq i8 %mask, 0
  %masked_val = select i1 %cond, i8 %val, i8 -1
  %res = call i8 @llvm.umin.i8(i8 %acc, i8 %masked_val)
  ret i8 %res
}

attributes #0 = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }
```

https://godbolt.org/z/cYMheKE5r
(cherry picked from commit 07fa6d1d90c714fa269529c3e5004a063d814c4a)

1 files changed, 9 insertions, 0 deletions

diff --git a/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp b/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp
index a64c188..0f5e867 100644
--- a/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp
@@ -1697,6 +1697,15 @@ Instruction *InstCombinerImpl::FoldOpIntoSelect(Instruction &Op, SelectInst *SI,
   if (SI->getType()->isIntOrIntVectorTy(1))
     return nullptr;
 
+  // Avoid breaking min/max reduction pattern,
+  // which is necessary for vectorization later.
+  if (isa<MinMaxIntrinsic>(&Op))
+    for (Value *IntrinOp : Op.operands())
+      if (auto *PN = dyn_cast<PHINode>(IntrinOp))
+        for (Value *PhiOp : PN->operands())
+          if (PhiOp == &Op)
+            return nullptr;
+
   // Test if a FCmpInst instruction is used exclusively by a select as
   // part of a minimum or maximum operation. If so, refrain from doing
   // any other folding. This helps out other analyses which understand