RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-19 02:52:53 +02:00
Code Issues Projects Releases Wiki Activity

[PatternMatch, InstSimplify] allow undef elements when matching vector -0.0

Browse Source 
This is the FP equivalent of D42818. Use it for the few cases in InstSimplify 
with -0.0 folds (that's the only current use of m_NegZero()).

Differential Revision: https://reviews.llvm.org/D43792

llvm-svn: 327307
This commit is contained in:
Sanjay Patel 2018-03-12 18:17:01 +00:00
parent 9ea3b6fb1d
commit b840189aad
2 changed files with 46 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

59
include/llvm/IR/PatternMatch.h
View File

@ -144,20 +144,6 @@ struct match_zero {
/// zero_initializer for vectors and ConstantPointerNull for pointers.
inline match_zero m_Zero() { return match_zero(); }
struct match_neg_zero {
template <typename ITy> bool match(ITy *V) {
if (const auto *C = dyn_cast<Constant>(V))
return C->isNegativeZeroValue();
return false;
}
};
/// Match an arbitrary zero/null constant. This includes
/// zero_initializer for vectors and ConstantPointerNull for pointers. For
/// floating point constants, this will match negative zero but not positive
/// zero
inline match_neg_zero m_NegZero() { return match_neg_zero(); }
struct match_any_zero {
template <typename ITy> bool match(ITy *V) {
if (const auto *C = dyn_cast<Constant>(V))
@ -250,8 +236,9 @@ template <int64_t Val> inline constantint_match<Val> m_ConstantInt() {
return constantint_match<Val>();
}
/// This helper class is used to match scalar and vector constants that satisfy
/// a specified predicate. For vector constants, undefined elements are ignored.
/// This helper class is used to match scalar and vector integer constants that
/// satisfy a specified predicate.
/// For vector constants, undefined elements are ignored.
template <typename Predicate> struct cst_pred_ty : public Predicate {
template <typename ITy> bool match(ITy *V) {
if (const auto *CI = dyn_cast<ConstantInt>(V))
@ -306,6 +293,38 @@ template <typename Predicate> struct api_pred_ty : public Predicate {
}
};
/// This helper class is used to match scalar and vector floating-point
/// constants that satisfy a specified predicate.
/// For vector constants, undefined elements are ignored.
template <typename Predicate> struct cstfp_pred_ty : public Predicate {
template <typename ITy> bool match(ITy *V) {
if (const auto *CF = dyn_cast<ConstantFP>(V))
return this->isValue(CF->getValueAPF());
if (V->getType()->isVectorTy()) {
if (const auto *C = dyn_cast<Constant>(V)) {
if (const auto *CF = dyn_cast_or_null<ConstantFP>(C->getSplatValue()))
return this->isValue(CF->getValueAPF());
// Non-splat vector constant: check each element for a match.
unsigned NumElts = V->getType()->getVectorNumElements();
assert(NumElts != 0 && "Constant vector with no elements?");
for (unsigned i = 0; i != NumElts; ++i) {
Constant *Elt = C->getAggregateElement(i);
if (!Elt)
return false;
if (isa<UndefValue>(Elt))
continue;
auto *CF = dyn_cast<ConstantFP>(Elt);
if (!CF || !this->isValue(CF->getValueAPF()))
return false;
}
return true;
}
}
return false;
}
};
///////////////////////////////////////////////////////////////////////////////
//
// Encapsulate constant value queries for use in templated predicate matchers.
@ -395,6 +414,14 @@ inline cst_pred_ty<is_sign_mask> m_SignMask() {
return cst_pred_ty<is_sign_mask>();
}
struct is_neg_zero {
bool isValue(const APFloat &C) { return C.isNegZero(); }
};
/// Match an FP or FP vector with all -0.0 values.
inline cstfp_pred_ty<is_neg_zero> m_NegZero() {
return cstfp_pred_ty<is_neg_zero>();
}
///////////////////////////////////////////////////////////////////////////////
template <typename Class> struct bind_ty {

10
test/Transforms/InstSimplify/floating-point-arithmetic.ll
View File

@ -3,8 +3,7 @@
define <2 x float> @fsub_negzero_vec_undef_elts(<2 x float> %x) {
; CHECK-LABEL: @fsub_negzero_vec_undef_elts(
; CHECK-NEXT: [[R:%.*]] = fsub nsz <2 x float> [[X:%.*]], <float undef, float -0.000000e+00>
; CHECK-NEXT: ret <2 x float> [[R]]
; CHECK-NEXT: ret <2 x float> [[X:%.*]]
;
%r = fsub nsz <2 x float> %x, <float undef, float -0.0>
ret <2 x float> %r
@ -31,9 +30,7 @@ define <2 x float> @fsub_-0_-0_x_vec(<2 x float> %a) {
define <2 x float> @fsub_-0_-0_x_vec_undef_elts(<2 x float> %a) {
; CHECK-LABEL: @fsub_-0_-0_x_vec_undef_elts(
; CHECK-NEXT: [[T1:%.*]] = fsub <2 x float> <float undef, float -0.000000e+00>, [[A:%.*]]
; CHECK-NEXT: [[RET:%.*]] = fsub <2 x float> <float -0.000000e+00, float undef>, [[T1]]
; CHECK-NEXT: ret <2 x float> [[RET]]
; CHECK-NEXT: ret <2 x float> [[A:%.*]]
;
%t1 = fsub <2 x float> <float undef, float -0.0>, %a
%ret = fsub <2 x float> <float -0.0, float undef>, %t1
@ -84,8 +81,7 @@ define float @fadd_x_n0(float %a) {
define <2 x float> @fadd_x_n0_vec_undef_elt(<2 x float> %a) {
; CHECK-LABEL: @fadd_x_n0_vec_undef_elt(
; CHECK-NEXT: [[RET:%.*]] = fadd <2 x float> [[A:%.*]], <float -0.000000e+00, float undef>
; CHECK-NEXT: ret <2 x float> [[RET]]
; CHECK-NEXT: ret <2 x float> [[A:%.*]]
;
%ret = fadd <2 x float> %a, <float -0.0, float undef>
ret <2 x float> %ret