Simplify multiplications by vectors whose elements are powers of 2.

Patch by Andrea Di Biagio.

llvm-svn: 183005
This commit is contained in:
Rafael Espindola 2013-05-31 14:27:15 +00:00
parent 1a566ced91
commit 65281bf36e
2 changed files with 454 additions and 14 deletions

View File

@ -95,6 +95,25 @@ static bool MultiplyOverflows(ConstantInt *C1, ConstantInt *C2, bool sign) {
return MulExt.slt(Min) || MulExt.sgt(Max);
}
/// \brief A helper routine of InstCombiner::visitMul().
///
/// If C is a vector of known powers of 2, then this function returns
/// a new vector obtained from C replacing each element with its logBase2.
/// Return a null pointer otherwise.
static Constant *getLogBase2Vector(ConstantDataVector *CV) {
const APInt *IVal;
SmallVector<Constant *, 4> Elts;
for (unsigned I = 0, E = CV->getNumElements(); I != E; ++I) {
Constant *Elt = CV->getElementAsConstant(I);
if (!match(Elt, m_APInt(IVal)) || !IVal->isPowerOf2())
return 0;
Elts.push_back(ConstantInt::get(Elt->getType(), IVal->logBase2()));
}
return ConstantVector::get(Elts);
}
Instruction *InstCombiner::visitMul(BinaryOperator &I) {
bool Changed = SimplifyAssociativeOrCommutative(I);
Value *Op0 = I.getOperand(0), *Op1 = I.getOperand(1);
@ -108,24 +127,37 @@ Instruction *InstCombiner::visitMul(BinaryOperator &I) {
if (match(Op1, m_AllOnes())) // X * -1 == 0 - X
return BinaryOperator::CreateNeg(Op0, I.getName());
if (ConstantInt *CI = dyn_cast<ConstantInt>(Op1)) {
// Also allow combining multiply instructions on vectors.
{
Value *NewOp;
Constant *C1, *C2;
const APInt *IVal;
if (match(&I, m_Mul(m_Shl(m_Value(NewOp), m_Constant(C2)),
m_Constant(C1))) &&
match(C1, m_APInt(IVal)))
// ((X << C1)*C2) == (X * (C2 << C1))
return BinaryOperator::CreateMul(NewOp, ConstantExpr::getShl(C1, C2));
// ((X << C1)*C2) == (X * (C2 << C1))
if (BinaryOperator *SI = dyn_cast<BinaryOperator>(Op0))
if (SI->getOpcode() == Instruction::Shl)
if (Constant *ShOp = dyn_cast<Constant>(SI->getOperand(1)))
return BinaryOperator::CreateMul(SI->getOperand(0),
ConstantExpr::getShl(CI, ShOp));
if (match(&I, m_Mul(m_Value(NewOp), m_Constant(C1)))) {
Constant *NewCst = 0;
if (match(C1, m_APInt(IVal)) && IVal->isPowerOf2())
// Replace X*(2^C) with X << C, where C is either a scalar or a splat.
NewCst = ConstantInt::get(NewOp->getType(), IVal->logBase2());
else if (ConstantDataVector *CV = dyn_cast<ConstantDataVector>(C1))
// Replace X*(2^C) with X << C, where C is a vector of known
// constant powers of 2.
NewCst = getLogBase2Vector(CV);
const APInt &Val = CI->getValue();
if (Val.isPowerOf2()) { // Replace X*(2^C) with X << C
Constant *NewCst = ConstantInt::get(Op0->getType(), Val.logBase2());
BinaryOperator *Shl = BinaryOperator::CreateShl(Op0, NewCst);
if (I.hasNoSignedWrap()) Shl->setHasNoSignedWrap();
if (I.hasNoUnsignedWrap()) Shl->setHasNoUnsignedWrap();
return Shl;
if (NewCst) {
BinaryOperator *Shl = BinaryOperator::CreateShl(NewOp, NewCst);
if (I.hasNoSignedWrap()) Shl->setHasNoSignedWrap();
if (I.hasNoUnsignedWrap()) Shl->setHasNoUnsignedWrap();
return Shl;
}
}
}
if (ConstantInt *CI = dyn_cast<ConstantInt>(Op1)) {
// Canonicalize (X+C1)*CI -> X*CI+C1*CI.
{ Value *X; ConstantInt *C1;
if (Op0->hasOneUse() &&

View File

@ -0,0 +1,408 @@
; RUN: opt < %s -instcombine -S | FileCheck %s
; Check that instcombine rewrites multiply by a vector
; of known constant power-of-2 elements with vector shift.
define <4 x i8> @Zero_i8(<4 x i8> %InVec) {
entry:
%mul = mul <4 x i8> %InVec, <i8 0, i8 0, i8 0, i8 0>
ret <4 x i8> %mul
}
; CHECK: @Zero_i8
; CHECK: ret <4 x i8> zeroinitializer
define <4 x i8> @Identity_i8(<4 x i8> %InVec) {
entry:
%mul = mul <4 x i8> %InVec, <i8 1, i8 1, i8 1, i8 1>
ret <4 x i8> %mul
}
; CHECK: @Identity_i8
; CHECK: ret <4 x i8> %InVec
define <4 x i8> @AddToSelf_i8(<4 x i8> %InVec) {
entry:
%mul = mul <4 x i8> %InVec, <i8 2, i8 2, i8 2, i8 2>
ret <4 x i8> %mul
}
; CHECK: @AddToSelf_i8
; CHECK: shl <4 x i8> %InVec, <i8 1, i8 1, i8 1, i8 1>
; CHECK: ret
define <4 x i8> @SplatPow2Test1_i8(<4 x i8> %InVec) {
entry:
%mul = mul <4 x i8> %InVec, <i8 4, i8 4, i8 4, i8 4>
ret <4 x i8> %mul
}
; CHECK: @SplatPow2Test1_i8
; CHECK: shl <4 x i8> %InVec, <i8 2, i8 2, i8 2, i8 2>
; CHECK: ret
define <4 x i8> @SplatPow2Test2_i8(<4 x i8> %InVec) {
entry:
%mul = mul <4 x i8> %InVec, <i8 8, i8 8, i8 8, i8 8>
ret <4 x i8> %mul
}
; CHECK: @SplatPow2Test2_i8
; CHECK: shl <4 x i8> %InVec, <i8 3, i8 3, i8 3, i8 3>
; CHECK: ret
define <4 x i8> @MulTest1_i8(<4 x i8> %InVec) {
entry:
%mul = mul <4 x i8> %InVec, <i8 1, i8 2, i8 4, i8 8>
ret <4 x i8> %mul
}
; CHECK: @MulTest1_i8
; CHECK: shl <4 x i8> %InVec, <i8 0, i8 1, i8 2, i8 3>
; CHECK: ret
define <4 x i8> @MulTest2_i8(<4 x i8> %InVec) {
entry:
%mul = mul <4 x i8> %InVec, <i8 3, i8 3, i8 3, i8 3>
ret <4 x i8> %mul
}
; CHECK: @MulTest2_i8
; CHECK: mul <4 x i8> %InVec, <i8 3, i8 3, i8 3, i8 3>
; CHECK: ret
define <4 x i8> @MulTest3_i8(<4 x i8> %InVec) {
entry:
%mul = mul <4 x i8> %InVec, <i8 4, i8 4, i8 2, i8 2>
ret <4 x i8> %mul
}
; CHECK: @MulTest3_i8
; CHECK: shl <4 x i8> %InVec, <i8 2, i8 2, i8 1, i8 1>
; CHECK: ret
define <4 x i8> @MulTest4_i8(<4 x i8> %InVec) {
entry:
%mul = mul <4 x i8> %InVec, <i8 4, i8 4, i8 0, i8 1>
ret <4 x i8> %mul
}
; CHECK: @MulTest4_i8
; CHECK: mul <4 x i8> %InVec, <i8 4, i8 4, i8 0, i8 1>
; CHECK: ret
define <4 x i16> @Zero_i16(<4 x i16> %InVec) {
entry:
%mul = mul <4 x i16> %InVec, <i16 0, i16 0, i16 0, i16 0>
ret <4 x i16> %mul
}
; CHECK: @Zero_i16
; CHECK: ret <4 x i16> zeroinitializer
define <4 x i16> @Identity_i16(<4 x i16> %InVec) {
entry:
%mul = mul <4 x i16> %InVec, <i16 1, i16 1, i16 1, i16 1>
ret <4 x i16> %mul
}
; CHECK: @Identity_i16
; CHECK: ret <4 x i16> %InVec
define <4 x i16> @AddToSelf_i16(<4 x i16> %InVec) {
entry:
%mul = mul <4 x i16> %InVec, <i16 2, i16 2, i16 2, i16 2>
ret <4 x i16> %mul
}
; CHECK: @AddToSelf_i16
; CHECK: shl <4 x i16> %InVec, <i16 1, i16 1, i16 1, i16 1>
; CHECK: ret
define <4 x i16> @SplatPow2Test1_i16(<4 x i16> %InVec) {
entry:
%mul = mul <4 x i16> %InVec, <i16 4, i16 4, i16 4, i16 4>
ret <4 x i16> %mul
}
; CHECK: @SplatPow2Test1_i16
; CHECK: shl <4 x i16> %InVec, <i16 2, i16 2, i16 2, i16 2>
; CHECK: ret
define <4 x i16> @SplatPow2Test2_i16(<4 x i16> %InVec) {
entry:
%mul = mul <4 x i16> %InVec, <i16 8, i16 8, i16 8, i16 8>
ret <4 x i16> %mul
}
; CHECK: @SplatPow2Test2_i16
; CHECK: shl <4 x i16> %InVec, <i16 3, i16 3, i16 3, i16 3>
; CHECK: ret
define <4 x i16> @MulTest1_i16(<4 x i16> %InVec) {
entry:
%mul = mul <4 x i16> %InVec, <i16 1, i16 2, i16 4, i16 8>
ret <4 x i16> %mul
}
; CHECK: @MulTest1_i16
; CHECK: shl <4 x i16> %InVec, <i16 0, i16 1, i16 2, i16 3>
; CHECK: ret
define <4 x i16> @MulTest2_i16(<4 x i16> %InVec) {
entry:
%mul = mul <4 x i16> %InVec, <i16 3, i16 3, i16 3, i16 3>
ret <4 x i16> %mul
}
; CHECK: @MulTest2_i16
; CHECK: mul <4 x i16> %InVec, <i16 3, i16 3, i16 3, i16 3>
; CHECK: ret
define <4 x i16> @MulTest3_i16(<4 x i16> %InVec) {
entry:
%mul = mul <4 x i16> %InVec, <i16 4, i16 4, i16 2, i16 2>
ret <4 x i16> %mul
}
; CHECK: @MulTest3_i16
; CHECK: shl <4 x i16> %InVec, <i16 2, i16 2, i16 1, i16 1>
; CHECK: ret
define <4 x i16> @MulTest4_i16(<4 x i16> %InVec) {
entry:
%mul = mul <4 x i16> %InVec, <i16 4, i16 4, i16 0, i16 2>
ret <4 x i16> %mul
}
; CHECK: @MulTest4_i16
; CHECK: mul <4 x i16> %InVec, <i16 4, i16 4, i16 0, i16 2>
; CHECK: ret
define <4 x i32> @Zero_i32(<4 x i32> %InVec) {
entry:
%mul = mul <4 x i32> %InVec, <i32 0, i32 0, i32 0, i32 0>
ret <4 x i32> %mul
}
; CHECK: @Zero_i32
; CHECK: ret <4 x i32> zeroinitializer
define <4 x i32> @Identity_i32(<4 x i32> %InVec) {
entry:
%mul = mul <4 x i32> %InVec, <i32 1, i32 1, i32 1, i32 1>
ret <4 x i32> %mul
}
; CHECK: @Identity_i32
; CHECK: ret <4 x i32> %InVec
define <4 x i32> @AddToSelf_i32(<4 x i32> %InVec) {
entry:
%mul = mul <4 x i32> %InVec, <i32 2, i32 2, i32 2, i32 2>
ret <4 x i32> %mul
}
; CHECK: @AddToSelf_i32
; CHECK: shl <4 x i32> %InVec, <i32 1, i32 1, i32 1, i32 1>
; CHECK: ret
define <4 x i32> @SplatPow2Test1_i32(<4 x i32> %InVec) {
entry:
%mul = mul <4 x i32> %InVec, <i32 4, i32 4, i32 4, i32 4>
ret <4 x i32> %mul
}
; CHECK: @SplatPow2Test1_i32
; CHECK: shl <4 x i32> %InVec, <i32 2, i32 2, i32 2, i32 2>
; CHECK: ret
define <4 x i32> @SplatPow2Test2_i32(<4 x i32> %InVec) {
entry:
%mul = mul <4 x i32> %InVec, <i32 8, i32 8, i32 8, i32 8>
ret <4 x i32> %mul
}
; CHECK: @SplatPow2Test2_i32
; CHECK: shl <4 x i32> %InVec, <i32 3, i32 3, i32 3, i32 3>
; CHECK: ret
define <4 x i32> @MulTest1_i32(<4 x i32> %InVec) {
entry:
%mul = mul <4 x i32> %InVec, <i32 1, i32 2, i32 4, i32 8>
ret <4 x i32> %mul
}
; CHECK: @MulTest1_i32
; CHECK: shl <4 x i32> %InVec, <i32 0, i32 1, i32 2, i32 3>
; CHECK: ret
define <4 x i32> @MulTest2_i32(<4 x i32> %InVec) {
entry:
%mul = mul <4 x i32> %InVec, <i32 3, i32 3, i32 3, i32 3>
ret <4 x i32> %mul
}
; CHECK: @MulTest2_i32
; CHECK: mul <4 x i32> %InVec, <i32 3, i32 3, i32 3, i32 3>
; CHECK: ret
define <4 x i32> @MulTest3_i32(<4 x i32> %InVec) {
entry:
%mul = mul <4 x i32> %InVec, <i32 4, i32 4, i32 2, i32 2>
ret <4 x i32> %mul
}
; CHECK: @MulTest3_i32
; CHECK: shl <4 x i32> %InVec, <i32 2, i32 2, i32 1, i32 1>
; CHECK: ret
define <4 x i32> @MulTest4_i32(<4 x i32> %InVec) {
entry:
%mul = mul <4 x i32> %InVec, <i32 4, i32 4, i32 0, i32 1>
ret <4 x i32> %mul
}
; CHECK: @MulTest4_i32
; CHECK: mul <4 x i32> %InVec, <i32 4, i32 4, i32 0, i32 1>
; CHECK: ret
define <4 x i64> @Zero_i64(<4 x i64> %InVec) {
entry:
%mul = mul <4 x i64> %InVec, <i64 0, i64 0, i64 0, i64 0>
ret <4 x i64> %mul
}
; CHECK: @Zero_i64
; CHECK: ret <4 x i64> zeroinitializer
define <4 x i64> @Identity_i64(<4 x i64> %InVec) {
entry:
%mul = mul <4 x i64> %InVec, <i64 1, i64 1, i64 1, i64 1>
ret <4 x i64> %mul
}
; CHECK: @Identity_i64
; CHECK: ret <4 x i64> %InVec
define <4 x i64> @AddToSelf_i64(<4 x i64> %InVec) {
entry:
%mul = mul <4 x i64> %InVec, <i64 2, i64 2, i64 2, i64 2>
ret <4 x i64> %mul
}
; CHECK: @AddToSelf_i64
; CHECK: shl <4 x i64> %InVec, <i64 1, i64 1, i64 1, i64 1>
; CHECK: ret
define <4 x i64> @SplatPow2Test1_i64(<4 x i64> %InVec) {
entry:
%mul = mul <4 x i64> %InVec, <i64 4, i64 4, i64 4, i64 4>
ret <4 x i64> %mul
}
; CHECK: @SplatPow2Test1_i64
; CHECK: shl <4 x i64> %InVec, <i64 2, i64 2, i64 2, i64 2>
; CHECK: ret
define <4 x i64> @SplatPow2Test2_i64(<4 x i64> %InVec) {
entry:
%mul = mul <4 x i64> %InVec, <i64 8, i64 8, i64 8, i64 8>
ret <4 x i64> %mul
}
; CHECK: @SplatPow2Test2_i64
; CHECK: shl <4 x i64> %InVec, <i64 3, i64 3, i64 3, i64 3>
; CHECK: ret
define <4 x i64> @MulTest1_i64(<4 x i64> %InVec) {
entry:
%mul = mul <4 x i64> %InVec, <i64 1, i64 2, i64 4, i64 8>
ret <4 x i64> %mul
}
; CHECK: @MulTest1_i64
; CHECK: shl <4 x i64> %InVec, <i64 0, i64 1, i64 2, i64 3>
; CHECK: ret
define <4 x i64> @MulTest2_i64(<4 x i64> %InVec) {
entry:
%mul = mul <4 x i64> %InVec, <i64 3, i64 3, i64 3, i64 3>
ret <4 x i64> %mul
}
; CHECK: @MulTest2_i64
; CHECK: mul <4 x i64> %InVec, <i64 3, i64 3, i64 3, i64 3>
; CHECK: ret
define <4 x i64> @MulTest3_i64(<4 x i64> %InVec) {
entry:
%mul = mul <4 x i64> %InVec, <i64 4, i64 4, i64 2, i64 2>
ret <4 x i64> %mul
}
; CHECK: @MulTest3_i64
; CHECK: shl <4 x i64> %InVec, <i64 2, i64 2, i64 1, i64 1>
; CHECK: ret
define <4 x i64> @MulTest4_i64(<4 x i64> %InVec) {
entry:
%mul = mul <4 x i64> %InVec, <i64 4, i64 4, i64 0, i64 1>
ret <4 x i64> %mul
}
; CHECK: @MulTest4_i64
; CHECK: mul <4 x i64> %InVec, <i64 4, i64 4, i64 0, i64 1>
; CHECK: ret
; Test also that the following rewriting rule works with vectors
; of integers as well:
; ((X << C1)*C2) == (X * (C2 << C1))
define <4 x i8> @ShiftMulTest1(<4 x i8> %InVec) {
entry:
%shl = shl <4 x i8> %InVec, <i8 2, i8 2, i8 2, i8 2>
%mul = mul <4 x i8> %shl, <i8 3, i8 3, i8 3, i8 3>
ret <4 x i8> %mul
}
; CHECK: @ShiftMulTest1
; CHECK: mul <4 x i8> %InVec, <i8 12, i8 12, i8 12, i8 12>
; CHECK: ret
define <4 x i16> @ShiftMulTest2(<4 x i16> %InVec) {
entry:
%shl = shl <4 x i16> %InVec, <i16 2, i16 2, i16 2, i16 2>
%mul = mul <4 x i16> %shl, <i16 3, i16 3, i16 3, i16 3>
ret <4 x i16> %mul
}
; CHECK: @ShiftMulTest2
; CHECK: mul <4 x i16> %InVec, <i16 12, i16 12, i16 12, i16 12>
; CHECK: ret
define <4 x i32> @ShiftMulTest3(<4 x i32> %InVec) {
entry:
%shl = shl <4 x i32> %InVec, <i32 2, i32 2, i32 2, i32 2>
%mul = mul <4 x i32> %shl, <i32 3, i32 3, i32 3, i32 3>
ret <4 x i32> %mul
}
; CHECK: @ShiftMulTest3
; CHECK: mul <4 x i32> %InVec, <i32 12, i32 12, i32 12, i32 12>
; CHECK: ret
define <4 x i64> @ShiftMulTest4(<4 x i64> %InVec) {
entry:
%shl = shl <4 x i64> %InVec, <i64 2, i64 2, i64 2, i64 2>
%mul = mul <4 x i64> %shl, <i64 3, i64 3, i64 3, i64 3>
ret <4 x i64> %mul
}
; CHECK: @ShiftMulTest4
; CHECK: mul <4 x i64> %InVec, <i64 12, i64 12, i64 12, i64 12>
; CHECK: ret