[llvm] [SLP] The order of store chains needs to consider the size of the values. (PR #101810)

[via llvm-commits]

https://github.com/tcwzxx created https://github.com/llvm/llvm-project/pull/101810

None

>From 2d66d1515050cfe6eccd10f798432dce6e073f2a Mon Sep 17 00:00:00 2001
From: tcwzxx <tcwzxx at gmail.com>
Date: Sat, 3 Aug 2024 19:10:56 +0800
Subject: [PATCH] The order of store chains needs to consider the size of the
 values.

---
 .../Transforms/Vectorize/SLPVectorizer.cpp    |  8 +++++
 .../SLPVectorizer/X86/stores_mix_sizes.ll     | 34 +++++++++++++++++++
 2 files changed, 42 insertions(+)
 create mode 100644 llvm/test/Transforms/SLPVectorizer/X86/stores_mix_sizes.ll

diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
index 8d2ce6bad6af7..97fb6798adcfc 100644
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -19125,6 +19125,14 @@ bool SLPVectorizerPass::vectorizeStoreChains(BoUpSLP &R) {
     if (V->getPointerOperandType()->getTypeID() >
         V2->getPointerOperandType()->getTypeID())
       return false;
+    if (V->getValueOperand()->getType()->getScalarSizeInBits() <
+        V2->getValueOperand()->getType()->getScalarSizeInBits()) {
+      return true;
+    }
+    if (V->getValueOperand()->getType()->getScalarSizeInBits() >
+        V2->getValueOperand()->getType()->getScalarSizeInBits()) {
+      return false;
+    }
     // UndefValues are compatible with all other values.
     if (isa<UndefValue>(V->getValueOperand()) ||
         isa<UndefValue>(V2->getValueOperand()))
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/stores_mix_sizes.ll b/llvm/test/Transforms/SLPVectorizer/X86/stores_mix_sizes.ll
new file mode 100644
index 0000000000000..c571372e40d16
--- /dev/null
+++ b/llvm/test/Transforms/SLPVectorizer/X86/stores_mix_sizes.ll
@@ -0,0 +1,34 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt -S --passes=slp-vectorizer -mtriple=x86_64-unknown-linux < %s | FileCheck %s
+
+define void @test(ptr %p) {
+; CHECK-LABEL: define void @test(
+; CHECK-SAME: ptr [[P:%.*]]) {
+; CHECK-NEXT:  [[ENTRY:.*:]]
+; CHECK-NEXT:    [[IDX1:%.*]] = getelementptr i8, ptr [[P]], i64 1
+; CHECK-NEXT:    [[IDX_64_9:%.*]] = getelementptr i64, ptr [[P]], i64 9
+; CHECK-NEXT:    store i64 1, ptr [[IDX_64_9]], align 8
+; CHECK-NEXT:    store <8 x i8> zeroinitializer, ptr [[IDX1]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %idx1 = getelementptr i8, ptr %p, i64 1
+  store i8 0, ptr %idx1, align 4
+  %idx.64.9 = getelementptr i64, ptr %p, i64 9
+  store i64 1, ptr %idx.64.9, align 8
+  %idx2 = getelementptr i8, ptr %p, i64 2
+  store i8 0, ptr %idx2, align 4
+  %idx3 = getelementptr i8, ptr %p, i64 3
+  store i8 0, ptr %idx3, align 4
+  %idx4 = getelementptr i8, ptr %p, i64 4
+  store i8 0, ptr %idx4, align 4
+  %idx5 = getelementptr i8, ptr %p, i64 5
+  store i8 0, ptr %idx5, align 4
+  %idx6 = getelementptr i8, ptr %p, i64 6
+  store i8 0, ptr %idx6, align 4
+  %idx7 = getelementptr i8, ptr %p, i64 7
+  store i8 0, ptr %idx7, align 4
+  %idx8 = getelementptr i8, ptr %p, i64 8
+  store i8 0, ptr %idx8, align 4
+  ret void
+}