[PATCH] D18662: [GVN] Fix handling of sub-byte types in big-endian mode

[Ulrich Weigand via llvm-commits]

This revision was automatically updated to reflect the committed changes.
Closed by commit rL265684: [GVN] Fix handling of sub-byte types in big-endian mode (authored by uweigand).

Changed prior to commit:
  http://reviews.llvm.org/D18662?vs=52251&id=52929#toc

Repository:
  rL LLVM

http://reviews.llvm.org/D18662

Files:
  llvm/trunk/lib/Transforms/Scalar/GVN.cpp
  llvm/trunk/test/Transforms/GVN/big-endian.ll

Index: llvm/trunk/test/Transforms/GVN/big-endian.ll
===================================================================
--- llvm/trunk/test/Transforms/GVN/big-endian.ll
+++ llvm/trunk/test/Transforms/GVN/big-endian.ll
@@ -0,0 +1,40 @@
+; RUN: opt -gvn -S < %s | FileCheck %s
+
+target datalayout = "E-m:e-i64:64-n32:64"                                                                                         
+target triple = "powerpc64-unknown-linux-gnu"                                                                                     
+
+;; Make sure we use correct bit shift based on storage size for
+;; loads reusing a load value.
+define i64 @test1({ i1, i8 }* %predA, { i1, i8 }* %predB) {
+; CHECK-LABEL: @test1
+; CHECK: [[V1:%.*]] = load i16, i16* %{{.*}}
+; CHECK: [[V2:%.*]] = lshr i16 [[V1]], 8
+; CHECK: trunc i16 [[V2]] to i1
+
+  %valueLoadA.fca.0.gep = getelementptr inbounds { i1, i8 }, { i1, i8 }* %predA, i64 0, i32 0
+  %valueLoadA.fca.0.load = load i1, i1* %valueLoadA.fca.0.gep, align 8
+  %valueLoadB.fca.0.gep = getelementptr inbounds { i1, i8 }, { i1, i8 }* %predB, i64 0, i32 0
+  %valueLoadB.fca.0.load = load i1, i1* %valueLoadB.fca.0.gep, align 8
+  %isTrue = and i1 %valueLoadA.fca.0.load, %valueLoadB.fca.0.load
+  %valueLoadA.fca.1.gep = getelementptr inbounds { i1, i8 }, { i1, i8 }* %predA, i64 0, i32 1
+  %valueLoadA.fca.1.load = load i8, i8* %valueLoadA.fca.1.gep, align 1
+  %isNotNullA = icmp ne i8 %valueLoadA.fca.1.load, 0
+  %valueLoadB.fca.1.gep = getelementptr inbounds { i1, i8 }, { i1, i8 }* %predB, i64 0, i32 1
+  %valueLoadB.fca.1.load = load i8, i8* %valueLoadB.fca.1.gep, align 1
+  %isNotNullB = icmp ne i8 %valueLoadB.fca.1.load, 0
+  %isNotNull = and i1 %isNotNullA, %isNotNullB
+  %isTrueAndNotNull = and i1 %isTrue, %isNotNull
+  %ret = zext i1 %isTrueAndNotNull to i64
+  ret i64 %ret
+}
+
+;; And likewise for loads reusing a store value.
+define i1 @test2(i8 %V, i8* %P) {
+; CHECK-LABEL: @test2
+; CHECK-NOT: lshr
+  store i8 %V, i8* %P
+  %P2 = bitcast i8* %P to i1*
+  %A = load i1, i1* %P2
+  ret i1 %A
+}
+
Index: llvm/trunk/lib/Transforms/Scalar/GVN.cpp
===================================================================
--- llvm/trunk/lib/Transforms/Scalar/GVN.cpp
+++ llvm/trunk/lib/Transforms/Scalar/GVN.cpp
@@ -775,7 +775,9 @@
   // If this is a big-endian system, we need to shift the value down to the low
   // bits so that a truncate will work.
   if (DL.isBigEndian()) {
-    StoredVal = IRB.CreateLShr(StoredVal, StoreSize - LoadSize, "tmp");
+    uint64_t ShiftAmt = DL.getTypeStoreSizeInBits(StoredValTy) -
+                        DL.getTypeStoreSizeInBits(LoadedTy);
+    StoredVal = IRB.CreateLShr(StoredVal, ShiftAmt, "tmp");
   }
 
   // Truncate the integer to the right size now.
@@ -1056,8 +1058,7 @@
     // system, we need to shift down to get the relevant bits.
     Value *RV = NewLoad;
     if (DL.isBigEndian())
-      RV = Builder.CreateLShr(RV,
-                    NewLoadSize*8-SrcVal->getType()->getPrimitiveSizeInBits());
+      RV = Builder.CreateLShr(RV, (NewLoadSize - SrcValSize) * 8);
     RV = Builder.CreateTrunc(RV, SrcVal->getType());
     SrcVal->replaceAllUsesWith(RV);
 


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D18662.52929.patch
Type: text/x-patch
Size: 3186 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20160407/c790b034/attachment.bin>