[InstCombine] change bitwise logic type to eliminate bitcasts

In PR27925:
https://llvm.org/bugs/show_bug.cgi?id=27925

...we proposed adding this fold to eliminate a bitcast. In D20774, there was 
some concern about changing the type of a bitwise op as well as creating 
bitcasts that might not be free for a target. However, if we're strictly 
eliminating an instruction (by limiting this to one-use ops), then we should 
be able to do this in InstCombine.

But we're cautiously restricting the transform for now to vector types to
avoid possible backend problems. A transform to make sure the logic op is
legal for the target should be added to reverse this transform and improve
codegen.

Differential Revision: https://reviews.llvm.org/D26641

llvm-svn: 287707

2 files changed, 68 insertions, 4 deletions

diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
index 8115a8c51ca..c085a31b5cd 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
@@ -1778,6 +1778,46 @@ static Instruction *canonicalizeBitCastExtElt(BitCastInst &BitCast,
   return ExtractElementInst::Create(NewBC, ExtElt->getIndexOperand());
 }
 
+/// Change the type of a bitwise logic operation if we can eliminate a bitcast.
+static Instruction *foldBitCastBitwiseLogic(BitCastInst &BitCast,
+                                            InstCombiner::BuilderTy &Builder) {
+  BinaryOperator *BO;
+  if (!match(BitCast.getOperand(0), m_OneUse(m_BinOp(BO))))
+    return nullptr;
+
+  auto Opcode = BO->getOpcode();
+  if (Opcode != Instruction::And && Opcode != Instruction::Or &&
+      Opcode != Instruction::Xor)
+    return nullptr;
+
+  Type *DestTy = BitCast.getType();
+  if (!DestTy->getScalarType()->isIntegerTy())
+    return nullptr;
+  
+  // FIXME: This transform is restricted to vector types to avoid backend
+  // problems caused by creating potentially illegal operations. If a fix-up is
+  // added to handle that situation, we can remove this check.
+  if (!DestTy->isVectorTy() || !BO->getType()->isVectorTy())
+    return nullptr;
+  
+  Value *X;
+  if (match(BO->getOperand(0), m_OneUse(m_BitCast(m_Value(X)))) &&
+      X->getType() == DestTy && !isa<Constant>(X)) {
+    // bitcast(logic(bitcast(X), Y)) --> logic'(X, bitcast(Y))
+    Value *CastedOp1 = Builder.CreateBitCast(BO->getOperand(1), DestTy);
+    return BinaryOperator::Create(Opcode, X, CastedOp1);
+  }
+
+  if (match(BO->getOperand(1), m_OneUse(m_BitCast(m_Value(X)))) &&
+      X->getType() == DestTy && !isa<Constant>(X)) {
+    // bitcast(logic(Y, bitcast(X))) --> logic'(bitcast(Y), X)
+    Value *CastedOp0 = Builder.CreateBitCast(BO->getOperand(0), DestTy);
+    return BinaryOperator::Create(Opcode, CastedOp0, X);
+  }
+
+  return nullptr;
+}
+
 /// Check if all users of CI are StoreInsts.
 static bool hasStoreUsersOnly(CastInst &CI) {
   for (User *U : CI.users()) {
@@ -2030,6 +2070,9 @@ Instruction *InstCombiner::visitBitCast(BitCastInst &CI) {
   if (Instruction *I = canonicalizeBitCastExtElt(CI, *this, DL))
     return I;
 
+  if (Instruction *I = foldBitCastBitwiseLogic(CI, *Builder))
+    return I;
+
   if (SrcTy->isPointerTy())
     return commonPointerCastTransforms(CI);
   return commonCastTransforms(CI);
diff --git a/llvm/test/Transforms/InstCombine/bitcast.ll b/llvm/test/Transforms/InstCombine/bitcast.ll
index 8d8c25a1095..49cb5618831 100644
--- a/llvm/test/Transforms/InstCombine/bitcast.ll
+++ b/llvm/test/Transforms/InstCombine/bitcast.ll
@@ -74,10 +74,8 @@ define <2 x i32> @or_bitcast_int_to_vec(i64 %a) {
 
 define <4 x i32> @bitcasts_and_bitcast(<4 x i32> %a, <8 x i16> %b) {
 ; CHECK-LABEL: @bitcasts_and_bitcast(
-; CHECK-NEXT:    [[BC1:%.*]] = bitcast <4 x i32> %a to <2 x i64>
-; CHECK-NEXT:    [[BC2:%.*]] = bitcast <8 x i16> %b to <2 x i64>
-; CHECK-NEXT:    [[AND:%.*]] = and <2 x i64> [[BC2]], [[BC1]]
-; CHECK-NEXT:    [[BC3:%.*]] = bitcast <2 x i64> [[AND]] to <4 x i32>
+; CHECK-NEXT:    [[TMP1:%.*]] = bitcast <8 x i16> %b to <4 x i32>
+; CHECK-NEXT:    [[BC3:%.*]] = and <4 x i32> [[TMP1]], %a
 ; CHECK-NEXT:    ret <4 x i32> [[BC3]]
 ;
   %bc1 = bitcast <4 x i32> %a to <2 x i64>
@@ -87,6 +85,27 @@ define <4 x i32> @bitcasts_and_bitcast(<4 x i32> %a, <8 x i16> %b) {
   ret <4 x i32> %bc3
 }
 
+; The destination must have an integer element type.
+; FIXME: We can still eliminate one bitcast in this test by doing the logic op
+; in the type of the input that has an integer element type.
+
+define <4 x float> @bitcasts_and_bitcast_to_fp(<4 x float> %a, <8 x i16> %b) {
+; CHECK-LABEL: @bitcasts_and_bitcast_to_fp(
+; CHECK-NEXT:    [[BC1:%.*]] = bitcast <4 x float> %a to <2 x i64>
+; CHECK-NEXT:    [[BC2:%.*]] = bitcast <8 x i16> %b to <2 x i64>
+; CHECK-NEXT:    [[AND:%.*]] = and <2 x i64> [[BC2]], [[BC1]]
+; CHECK-NEXT:    [[BC3:%.*]] = bitcast <2 x i64> [[AND]] to <4 x float>
+; CHECK-NEXT:    ret <4 x float> [[BC3]]
+;
+  %bc1 = bitcast <4 x float> %a to <2 x i64>
+  %bc2 = bitcast <8 x i16> %b to <2 x i64>
+  %and = and <2 x i64> %bc2, %bc1
+  %bc3 = bitcast <2 x i64> %and to <4 x float>
+  ret <4 x float> %bc3
+}
+
+; FIXME: Transform limited from changing vector op to integer op to avoid codegen problems.
+
 define i128 @bitcast_or_bitcast(i128 %a, <2 x i64> %b) {
 ; CHECK-LABEL: @bitcast_or_bitcast(
 ; CHECK-NEXT:    [[BC1:%.*]] = bitcast i128 %a to <2 x i64>
@@ -100,6 +119,8 @@ define i128 @bitcast_or_bitcast(i128 %a, <2 x i64> %b) {
   ret i128 %bc2
 }
 
+; FIXME: Transform limited from changing integer op to vector op to avoid codegen problems.
+
 define <4 x i32> @bitcast_xor_bitcast(<4 x i32> %a, i128 %b) {
 ; CHECK-LABEL: @bitcast_xor_bitcast(
 ; CHECK-NEXT:    [[BC1:%.*]] = bitcast <4 x i32> %a to i128