From 9bba75084b7bde6a6215d616f664d3d2486f4871 Mon Sep 17 00:00:00 2001
From: Sanjay Patel <spatel@rotateright.com>
Date: Thu, 3 Mar 2016 19:19:04 +0000
Subject: [InstCombine] transform bitcasted bitwise logic ops with constants
 (PR26702)

Given that we're not actually reducing the instruction count in the included
regression tests, I think we would call this a canonicalization step.

The motivation comes from the example in PR26702:
https://llvm.org/bugs/show_bug.cgi?id=26702

If we hoist the bitwise logic ahead of the bitcast, the previously unoptimizable
example of:

define <4 x i32> @is_negative(<4 x i32> %x) {
  %lobit = ashr <4 x i32> %x, <i32 31, i32 31, i32 31, i32 31>
  %not = xor <4 x i32> %lobit, <i32 -1, i32 -1, i32 -1, i32 -1>
  %bc = bitcast <4 x i32> %not to <2 x i64>
  %notnot = xor <2 x i64> %bc, <i64 -1, i64 -1>
  %bc2 = bitcast <2 x i64> %notnot to <4 x i32>
  ret <4 x i32> %bc2
}

Simplifies to the expected:

define <4 x i32> @is_negative(<4 x i32> %x) {
  %lobit = ashr <4 x i32> %x, <i32 31, i32 31, i32 31, i32 31>
  ret <4 x i32> %lobit
}

Differential Revision: http://reviews.llvm.org/D17583

llvm-svn: 262645
---
 .../Transforms/InstCombine/InstCombineAndOrXor.cpp | 35 +++++++++++++++++-----
 1 file changed, 28 insertions(+), 7 deletions(-)

(limited to 'llvm/lib/Transforms')

diff --git a/llvm/lib/Transforms/InstCombine/InstCombineAndOrXor.cpp b/llvm/lib/Transforms/InstCombine/InstCombineAndOrXor.cpp
index d19a0226fbc..4a6e99c3cdb 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineAndOrXor.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineAndOrXor.cpp
@@ -1251,21 +1251,42 @@ Instruction *InstCombiner::foldCastedBitwiseLogic(BinaryOperator &I) {
 
   Value *Op0 = I.getOperand(0), *Op1 = I.getOperand(1);
   CastInst *Cast0 = dyn_cast<CastInst>(Op0);
+  if (!Cast0)
+    return nullptr;
+
+  // This must be a cast from an integer or integer vector source type to allow
+  // transformation of the logic operation to the source type.
+  Type *DestTy = I.getType();
+  Type *SrcTy = Cast0->getSrcTy();
+  if (!SrcTy->isIntOrIntVectorTy())
+    return nullptr;
+
+  // If one operand is a bitcast and the other is a constant, move the logic
+  // operation ahead of the bitcast. That is, do the logic operation in the
+  // original type. This can eliminate useless bitcasts and allow normal
+  // combines that would otherwise be impeded by the bitcast. Canonicalization
+  // ensures that if there is a constant operand, it will be the second operand.
+  Value *BC = nullptr;
+  Constant *C = nullptr;
+  if ((match(Op0, m_BitCast(m_Value(BC))) && match(Op1, m_Constant(C)))) {
+    // A bitcast of a constant will be removed.
+    Value *NewConstant = Builder->CreateBitCast(C, SrcTy);
+    Value *NewOp = Builder->CreateBinOp(LogicOpc, BC, NewConstant, I.getName());
+    return CastInst::CreateBitOrPointerCast(NewOp, DestTy);
+  }
+
   CastInst *Cast1 = dyn_cast<CastInst>(Op1);
-  if (!Cast0 || !Cast1)
+  if (!Cast1)
     return nullptr;
 
-  // The casts must be of the same type, and this must be a cast from an integer
-  // or integer vector source type.
+  // Both operands of the logic operation are casts. The casts must be of the
+  // same type for reduction.
   auto CastOpcode = Cast0->getOpcode();
-  Type *SrcTy = Cast0->getSrcTy();
-  if ((CastOpcode != Cast1->getOpcode()) || (SrcTy != Cast1->getSrcTy()) ||
-      !SrcTy->isIntOrIntVectorTy())
+  if (CastOpcode != Cast1->getOpcode() || SrcTy != Cast1->getSrcTy())
     return nullptr;
 
   Value *Cast0Src = Cast0->getOperand(0);
   Value *Cast1Src = Cast1->getOperand(0);
-  Type *DestTy = I.getType();
 
   // fold (logic (cast A), (cast B)) -> (cast (logic A, B))
 
-- 
cgit v1.2.3