[PATCH] D74311: [CodeGen] Fix the computation of the alignment of split stores.

[Clement Courbet via Phabricator via llvm-commits]

courbet updated this revision to Diff 243529.
courbet added a comment.

Improve documentation as suggested during the review.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D74311/new/

https://reviews.llvm.org/D74311

Files:
  llvm/lib/CodeGen/CodeGenPrepare.cpp
  llvm/test/CodeGen/X86/split-store-unaligned.ll


Index: llvm/test/CodeGen/X86/split-store-unaligned.ll
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/X86/split-store-unaligned.ll
@@ -0,0 +1,51 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -codegenprepare -mtriple=x86_64-unknown-unknown -force-split-store -S < %s | FileCheck %s
+
+target datalayout = "e-m:x-p:32:32-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:32-n8:16:32-a:0:32-S32"
+target triple = "i686-w64-windows-gnu"
+
+define void @split_store_align1(float %x, i64* %p) {
+; CHECK-LABEL: @split_store_align1(
+; CHECK-NEXT:    [[B:%.*]] = bitcast float [[X:%.*]] to i32
+; CHECK-NEXT:    [[Z:%.*]] = zext i32 0 to i64
+; CHECK-NEXT:    [[S:%.*]] = shl nuw nsw i64 [[Z]], 32
+; CHECK-NEXT:    [[Z2:%.*]] = zext i32 [[B]] to i64
+; CHECK-NEXT:    [[O:%.*]] = or i64 [[S]], [[Z2]]
+; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i64* [[P:%.*]] to i32*
+; CHECK-NEXT:    store i32 [[B]], i32* [[TMP1]], align 1
+; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i64* [[P]] to i32*
+; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr i32, i32* [[TMP2]], i32 1
+; CHECK-NEXT:    store i32 0, i32* [[TMP3]], align 1
+; CHECK-NEXT:    ret void
+;
+  %b = bitcast float %x to i32
+  %z = zext i32 0 to i64
+  %s = shl nuw nsw i64 %z, 32
+  %z2 = zext i32 %b to i64
+  %o = or i64 %s, %z2
+  store i64 %o, i64* %p, align 1
+  ret void
+}
+
+define void @split_store_align2(float %x, i64* %p) {
+; CHECK-LABEL: @split_store_align2(
+; CHECK-NEXT:    [[B:%.*]] = bitcast float [[X:%.*]] to i32
+; CHECK-NEXT:    [[Z:%.*]] = zext i32 0 to i64
+; CHECK-NEXT:    [[S:%.*]] = shl nuw nsw i64 [[Z]], 32
+; CHECK-NEXT:    [[Z2:%.*]] = zext i32 [[B]] to i64
+; CHECK-NEXT:    [[O:%.*]] = or i64 [[S]], [[Z2]]
+; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i64* [[P:%.*]] to i32*
+; CHECK-NEXT:    store i32 [[B]], i32* [[TMP1]], align 2
+; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i64* [[P]] to i32*
+; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr i32, i32* [[TMP2]], i32 1
+; CHECK-NEXT:    store i32 0, i32* [[TMP3]], align 2
+; CHECK-NEXT:    ret void
+;
+  %b = bitcast float %x to i32
+  %z = zext i32 0 to i64
+  %s = shl nuw nsw i64 %z, 32
+  %z2 = zext i32 %b to i64
+  %o = or i64 %s, %z2
+  store i64 %o, i64* %p, align 2
+  ret void
+}
Index: llvm/lib/CodeGen/CodeGenPrepare.cpp
===================================================================
--- llvm/lib/CodeGen/CodeGenPrepare.cpp
+++ llvm/lib/CodeGen/CodeGenPrepare.cpp
@@ -6868,8 +6868,14 @@
       Addr = Builder.CreateGEP(
           SplitStoreType, Addr,
           ConstantInt::get(Type::getInt32Ty(SI.getContext()), 1));
-    Builder.CreateAlignedStore(V, Addr,
-                               Upper ? SI.getAlign() / 2 : SI.getAlign());
+    MaybeAlign Alignment = SI.getAlign();
+    if (Upper && Alignment) {
+      // When splitting store in half, the lower half will retain the
+      // alignment of the original wider store, regardless of whether
+      // it was over-aligned or not, while other will require adjustment.
+      Alignment = commonAlignment(Alignment, HalfValBitSize / 8);
+    }
+    Builder.CreateAlignedStore(V, Addr, Alignment);
   };
 
   CreateSplitStore(LValue, false);


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D74311.243529.patch
Type: text/x-patch
Size: 3234 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200210/f1e52f1e/attachment-0001.bin>