From a13148a8808d1cc50c97cb2c1411694840a5ddc7 Mon Sep 17 00:00:00 2001
From: Alexey Bataev <a.bataev@outlook.com>
Date: Wed, 20 Dec 2023 06:01:59 -0800
Subject: [SLP]Fix PR75995: drop wrapping flags for resized wrapped binops.

If decided to resize the instruction, need to drop wrapping flags from
the resulting vector instructions to avoid incorrect
optimizations/assumptions later.
Fixes PR75995.
---
 llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp                         | 2 +-
 .../Transforms/SLPVectorizer/X86/minbitwidth-drop-wrapping-flags.ll     | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
index ee92e10..5c325ad 100644
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -11472,7 +11472,7 @@ Value *BoUpSLP::vectorizeTree(TreeEntry *E, bool PostponedPHIs) {
       Value *V = Builder.CreateBinOp(
           static_cast<Instruction::BinaryOps>(E->getOpcode()), LHS,
           RHS);
-      propagateIRFlags(V, E->Scalars, VL0);
+      propagateIRFlags(V, E->Scalars, VL0, !MinBWs.contains(E));
       if (auto *I = dyn_cast<Instruction>(V))
         V = propagateMetadata(I, E->Scalars);
 
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/minbitwidth-drop-wrapping-flags.ll b/llvm/test/Transforms/SLPVectorizer/X86/minbitwidth-drop-wrapping-flags.ll
index 853cf3d..44738aa 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/minbitwidth-drop-wrapping-flags.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/minbitwidth-drop-wrapping-flags.ll
@@ -11,7 +11,7 @@ define i32 @test() {
 ; CHECK-NEXT:    [[TMP3:%.*]] = or <4 x i8> [[TMP1]], zeroinitializer
 ; CHECK-NEXT:    [[TMP4:%.*]] = shufflevector <4 x i8> [[TMP2]], <4 x i8> [[TMP3]], <4 x i32> <i32 0, i32 1, i32 6, i32 7>
 ; CHECK-NEXT:    [[TMP5:%.*]] = zext <4 x i8> [[TMP4]] to <4 x i16>
-; CHECK-NEXT:    [[TMP6:%.*]] = add nuw nsw <4 x i16> [[TMP5]], <i16 -1, i16 0, i16 0, i16 0>
+; CHECK-NEXT:    [[TMP6:%.*]] = add <4 x i16> [[TMP5]], <i16 -1, i16 0, i16 0, i16 0>
 ; CHECK-NEXT:    [[TMP7:%.*]] = call i16 @llvm.vector.reduce.or.v4i16(<4 x i16> [[TMP6]])
 ; CHECK-NEXT:    [[TMP8:%.*]] = zext i16 [[TMP7]] to i32
 ; CHECK-NEXT:    [[TMP9:%.*]] = and i32 [[TMP8]], 65535
-- 
cgit v1.1