6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2024-12-12 13:30:51 +00:00
Code Issues Projects Releases Wiki Activity

LoopVectorize: We don't need an identity element for min/max reductions

Browse Source 
We can just use the initial element that feeds the reduction.

  max(max(x, y), z) == max(max(x,y), max(x,z))

radar://13723044

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@181141 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Arnold Schwaighofer 2013-05-05 01:54:42 +00:00
parent 5c332dbd30
commit c1738fdadd
2 changed files with 22 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

49
lib/Transforms/Vectorize/LoopVectorize.cpp
View File

@ -498,8 +498,7 @@ public:
/// This function returns the identity element (or neutral element) for
/// the operation K.
static Constant *getReductionIdentity(ReductionKind K, Type *Tp,
MinMaxReductionKind MinMaxK);
static Constant *getReductionIdentity(ReductionKind K, Type *Tp);
private:
/// Check if a single basic block loop is vectorizable.
/// At this point we know that this is a loop with a constant trip count
@ -1501,8 +1500,7 @@ InnerLoopVectorizer::createEmptyLoop(LoopVectorizationLegality *Legal) {
/// This function returns the identity element (or neutral element) for
/// the operation K.
Constant*
LoopVectorizationLegality::getReductionIdentity(ReductionKind K, Type *Tp,
MinMaxReductionKind MinMaxK) {
LoopVectorizationLegality::getReductionIdentity(ReductionKind K, Type *Tp) {
switch (K) {
case RK_IntegerXor:
case RK_IntegerAdd:
@ -1521,24 +1519,6 @@ LoopVectorizationLegality::getReductionIdentity(ReductionKind K, Type *Tp,
case RK_FloatAdd:
// Adding zero to a number does not change it.
return ConstantFP::get(Tp, 0.0L);
case RK_IntegerMinMax:
switch(MinMaxK) {
default: llvm_unreachable("Unknown min/max predicate");
case MRK_UIntMin:
return ConstantInt::getAllOnesValue(Tp);
case MRK_UIntMax:
return ConstantInt::get(Tp, 0);
case MRK_SIntMin: {
unsigned BitWidth = Tp->getPrimitiveSizeInBits();
return ConstantInt::get(Tp->getContext(),
APInt::getSignedMaxValue(BitWidth));
}
case LoopVectorizationLegality::MRK_SIntMax: {
unsigned BitWidth = Tp->getPrimitiveSizeInBits();
return ConstantInt::get(Tp->getContext(),
APInt::getSignedMinValue(BitWidth));
}
}
default:
llvm_unreachable("Unknown reduction kind");
}
@ -1761,16 +1741,23 @@ InnerLoopVectorizer::vectorizeLoop(LoopVectorizationLegality *Legal) {
// Find the reduction identity variable. Zero for addition, or, xor,
// one for multiplication, -1 for And.
Constant *Iden =
LoopVectorizationLegality::getReductionIdentity(RdxDesc.Kind,
VecTy->getScalarType(),
RdxDesc.MinMaxKind);
Constant *Identity = ConstantVector::getSplat(VF, Iden);
Value *Identity;
Value *VectorStart;
if (RdxDesc.Kind == LoopVectorizationLegality::RK_IntegerMinMax)
// MinMax reduction have the start value as their identify.
VectorStart = Identity = Builder.CreateVectorSplat(VF, RdxDesc.StartValue,
"minmax.ident");
else {
Constant *Iden =
LoopVectorizationLegality::getReductionIdentity(RdxDesc.Kind,
VecTy->getScalarType());
Identity = ConstantVector::getSplat(VF, Iden);
// This vector is the Identity vector where the first element is the
// incoming scalar reduction.
Value *VectorStart = Builder.CreateInsertElement(Identity,
RdxDesc.StartValue, Zero);
// This vector is the Identity vector where the first element is the
// incoming scalar reduction.
VectorStart = Builder.CreateInsertElement(Identity,
RdxDesc.StartValue, Zero);
}
// Fix the vector-loop phi.
// We created the induction variable so we know that the

5
test/Transforms/LoopVectorize/minmax_reduction.ll
View File

@ -6,8 +6,11 @@ target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f3
; Signed tests.
; Turn this into a max reduction.
; Turn this into a max reduction. Make sure we use a splat to initialize the
; vector for the reduction.
; CHECK: @max_red
; CHECK: %[[VAR:.*]] = insertelement <2 x i32> undef, i32 %max, i32 0
; CHECK: {{.*}} = shufflevector <2 x i32> %[[VAR]], <2 x i32> undef, <2 x i32> zeroinitializer
; CHECK: icmp sgt <2 x i32>
; CHECK: select <2 x i1>
; CHECK: middle.block