Skip to content

[InstCombine] Inverse is.fpclass mask operand, when profitable #121378

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
Closed

[InstCombine] Inverse is.fpclass mask operand, when profitable #121378

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
52 changes: 43 additions & 9 deletions llvm/lib/Transforms/InstCombine/InstCombineAndOrXor.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1522,9 +1522,21 @@ Value *InstCombinerImpl::foldLogicOfFCmps(FCmpInst *LHS, FCmpInst *RHS,
if (ClassValLHS == ClassValRHS) {
unsigned CombinedMask = IsAnd ? (ClassMaskLHS & ClassMaskRHS)
: (ClassMaskLHS | ClassMaskRHS);
return Builder.CreateIntrinsic(
Intrinsic::is_fpclass, {ClassValLHS->getType()},
{ClassValLHS, Builder.getInt32(CombinedMask)});
unsigned InverseCombinedMask = ~CombinedMask & fcAllFlags;

// If the number of bits set in the combined mask is greater than the
// number of the unset bits, it is more efficient to use the inverse
// mask and invert the result.
bool IsInverse = popcount(CombinedMask) > popcount(InverseCombinedMask);
auto *MaskVal =
Builder.getInt32(IsInverse ? InverseCombinedMask : CombinedMask);

auto *II = Builder.CreateIntrinsic(Intrinsic::is_fpclass,
{ClassValLHS->getType()},
{ClassValLHS, MaskVal});
if (IsInverse)
return Builder.CreateNot(II);
return II;
}
}
}
Expand Down Expand Up @@ -1610,10 +1622,25 @@ Instruction *InstCombinerImpl::foldLogicOfIsFPClass(BinaryOperator &BO,
bool IsRHSClass =
match(Op1, m_OneUse(m_Intrinsic<Intrinsic::is_fpclass>(
m_Value(ClassVal1), m_ConstantInt(ClassMask1))));
if ((((IsLHSClass || matchIsFPClassLikeFCmp(Op0, ClassVal0, ClassMask0)) &&
(IsRHSClass || matchIsFPClassLikeFCmp(Op1, ClassVal1, ClassMask1)))) &&

bool IsLHSInverseClass =
match(Op0, m_OneUse(m_Not(m_OneUse(m_Intrinsic<Intrinsic::is_fpclass>(
m_Value(ClassVal0), m_ConstantInt(ClassMask0))))));
bool IsRHSInverseClass =
match(Op1, m_OneUse(m_Not(m_OneUse(m_Intrinsic<Intrinsic::is_fpclass>(
m_Value(ClassVal1), m_ConstantInt(ClassMask1))))));

if ((((IsLHSClass || IsLHSInverseClass ||
matchIsFPClassLikeFCmp(Op0, ClassVal0, ClassMask0)) &&
(IsRHSClass || IsRHSInverseClass ||
matchIsFPClassLikeFCmp(Op1, ClassVal1, ClassMask1)))) &&
ClassVal0 == ClassVal1) {
unsigned NewClassMask;
if (IsLHSInverseClass)
ClassMask0 = ~ClassMask0 & fcAllFlags;
if (IsRHSInverseClass)
ClassMask1 = ~ClassMask1 & fcAllFlags;

switch (BO.getOpcode()) {
case Instruction::And:
NewClassMask = ClassMask0 & ClassMask1;
Expand Down Expand Up @@ -4651,10 +4678,17 @@ Instruction *InstCombinerImpl::foldNot(BinaryOperator &I) {

if (II->getIntrinsicID() == Intrinsic::is_fpclass) {
ConstantInt *ClassMask = cast<ConstantInt>(II->getArgOperand(1));
II->setArgOperand(
1, ConstantInt::get(ClassMask->getType(),
~ClassMask->getZExtValue() & fcAllFlags));
return replaceInstUsesWith(I, II);
auto ClassMaskValue = ClassMask->getZExtValue();
auto InverseMaskValue = ~ClassMaskValue & fcAllFlags;

// If the number of set bits in the class mask is less than the number of
// set bits in the inverse mask, it's more efficient to keep the "not"
// instruction instead of inverting the class mask.
if (popcount(ClassMaskValue) > popcount(InverseMaskValue)) {
II->setArgOperand(
1, ConstantInt::get(ClassMask->getType(), InverseMaskValue));
return replaceInstUsesWith(I, II);
}
}
}

Expand Down
14 changes: 14 additions & 0 deletions llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1050,6 +1050,20 @@ Instruction *InstCombinerImpl::foldIntrinsicIsFPClass(IntrinsicInst &II) {
if (Mask == Known.KnownFPClasses)
return replaceInstUsesWith(II, ConstantInt::get(II.getType(), true));

// If the number of set bits in the mask is greater than the number of the
// unset bits, it's more efficient to inverse the mask and the intrinsic
// result:
// if.fpclass(x, mask) -> !if.fpclass(x, ~mask)
//
auto InverseMask = ~Mask & fcAllFlags;
if (popcount<unsigned>(Mask) > popcount<unsigned>(InverseMask)) {
auto *NewII =
Builder.CreateIntrinsic(Intrinsic::is_fpclass, {Src0->getType()},
{Src0, Builder.getInt32(InverseMask)});
auto *Not = Builder.CreateNot(NewII);
return replaceInstUsesWith(II, Not);
}

return nullptr;
}

Expand Down
9 changes: 6 additions & 3 deletions llvm/test/Transforms/InstCombine/combine-is.fpclass-and-fcmp.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -189,7 +189,8 @@ define i1 @fcmp_issubnormal_and_class_finite(half %x) {

define i1 @class_inf_or_fcmp_issubnormal(half %x) {
; CHECK-LABEL: @class_inf_or_fcmp_issubnormal(
; CHECK-NEXT: [[OR:%.*]] = call i1 @llvm.is.fpclass.f16(half [[X:%.*]], i32 756)
; CHECK-NEXT: [[TMP1:%.*]] = call i1 @llvm.is.fpclass.f16(half [[X:%.*]], i32 267)
; CHECK-NEXT: [[OR:%.*]] = xor i1 [[TMP1]], true
; CHECK-NEXT: ret i1 [[OR]]
;
%fabs = call half @llvm.fabs.f16(half %x)
Expand Down Expand Up @@ -289,7 +290,8 @@ define i1 @class_normal_or_fcmp_oeq_zero(half %x) {

define i1 @fcmp_ueq_zero_or_class_normal(half %x) {
; CHECK-LABEL: @fcmp_ueq_zero_or_class_normal(
; CHECK-NEXT: [[CLASS:%.*]] = call i1 @llvm.is.fpclass.f16(half [[X:%.*]], i32 363)
; CHECK-NEXT: [[TMP1:%.*]] = call i1 @llvm.is.fpclass.f16(half [[X:%.*]], i32 660)
; CHECK-NEXT: [[CLASS:%.*]] = xor i1 [[TMP1]], true
; CHECK-NEXT: ret i1 [[CLASS]]
;
%ueq.inf = fcmp ueq half %x, 0.0
Expand All @@ -300,7 +302,8 @@ define i1 @fcmp_ueq_zero_or_class_normal(half %x) {

define i1 @class_normal_or_fcmp_ueq_zero(half %x) {
; CHECK-LABEL: @class_normal_or_fcmp_ueq_zero(
; CHECK-NEXT: [[CLASS:%.*]] = call i1 @llvm.is.fpclass.f16(half [[X:%.*]], i32 363)
; CHECK-NEXT: [[TMP1:%.*]] = call i1 @llvm.is.fpclass.f16(half [[X:%.*]], i32 660)
; CHECK-NEXT: [[CLASS:%.*]] = xor i1 [[TMP1]], true
; CHECK-NEXT: ret i1 [[CLASS]]
;
%ueq.inf = fcmp ueq half %x, 0.0
Expand Down
Loading
Loading