aboutsummaryrefslogtreecommitdiff
path: root/clang/lib/AST
diff options
context:
space:
mode:
Diffstat (limited to 'clang/lib/AST')
-rw-r--r--clang/lib/AST/ByteCode/Compiler.cpp11
-rw-r--r--clang/lib/AST/ByteCode/Compiler.h17
-rw-r--r--clang/lib/AST/ByteCode/InterpBuiltin.cpp245
-rw-r--r--clang/lib/AST/ExprConstant.cpp315
4 files changed, 287 insertions, 301 deletions
diff --git a/clang/lib/AST/ByteCode/Compiler.cpp b/clang/lib/AST/ByteCode/Compiler.cpp
index f68422c..1243380 100644
--- a/clang/lib/AST/ByteCode/Compiler.cpp
+++ b/clang/lib/AST/ByteCode/Compiler.cpp
@@ -5432,8 +5432,7 @@ bool Compiler<Emitter>::VisitCXXThisExpr(const CXXThisExpr *E) {
unsigned EndIndex = 0;
// Find the init list.
for (StartIndex = InitStack.size() - 1; StartIndex > 0; --StartIndex) {
- if (InitStack[StartIndex].Kind == InitLink::K_InitList ||
- InitStack[StartIndex].Kind == InitLink::K_This) {
+ if (InitStack[StartIndex].Kind == InitLink::K_DIE) {
EndIndex = StartIndex;
--StartIndex;
break;
@@ -5446,7 +5445,8 @@ bool Compiler<Emitter>::VisitCXXThisExpr(const CXXThisExpr *E) {
continue;
if (InitStack[StartIndex].Kind != InitLink::K_Field &&
- InitStack[StartIndex].Kind != InitLink::K_Elem)
+ InitStack[StartIndex].Kind != InitLink::K_Elem &&
+ InitStack[StartIndex].Kind != InitLink::K_DIE)
break;
}
@@ -5457,7 +5457,8 @@ bool Compiler<Emitter>::VisitCXXThisExpr(const CXXThisExpr *E) {
// Emit the instructions.
for (unsigned I = StartIndex; I != (EndIndex + 1); ++I) {
- if (InitStack[I].Kind == InitLink::K_InitList)
+ if (InitStack[I].Kind == InitLink::K_InitList ||
+ InitStack[I].Kind == InitLink::K_DIE)
continue;
if (!InitStack[I].template emit<Emitter>(this, E))
return false;
@@ -6328,8 +6329,8 @@ bool Compiler<Emitter>::compileConstructor(const CXXConstructorDecl *Ctor) {
unsigned FirstLinkOffset =
R->getField(cast<FieldDecl>(IFD->chain()[0]))->Offset;
- InitStackScope<Emitter> ISS(this, isa<CXXDefaultInitExpr>(InitExpr));
InitLinkScope<Emitter> ILS(this, InitLink::Field(FirstLinkOffset));
+ InitStackScope<Emitter> ISS(this, isa<CXXDefaultInitExpr>(InitExpr));
if (!emitFieldInitializer(NestedField, NestedFieldOffset, InitExpr,
IsUnion))
return false;
diff --git a/clang/lib/AST/ByteCode/Compiler.h b/clang/lib/AST/ByteCode/Compiler.h
index 5c46f75..0c6cab9 100644
--- a/clang/lib/AST/ByteCode/Compiler.h
+++ b/clang/lib/AST/ByteCode/Compiler.h
@@ -52,12 +52,14 @@ public:
K_Decl = 3,
K_Elem = 5,
K_RVO = 6,
- K_InitList = 7
+ K_InitList = 7,
+ K_DIE = 8,
};
static InitLink This() { return InitLink{K_This}; }
static InitLink InitList() { return InitLink{K_InitList}; }
static InitLink RVO() { return InitLink{K_RVO}; }
+ static InitLink DIE() { return InitLink{K_DIE}; }
static InitLink Field(unsigned Offset) {
InitLink IL{K_Field};
IL.Offset = Offset;
@@ -668,22 +670,29 @@ public:
~InitLinkScope() { this->Ctx->InitStack.pop_back(); }
-private:
+public:
Compiler<Emitter> *Ctx;
};
template <class Emitter> class InitStackScope final {
public:
InitStackScope(Compiler<Emitter> *Ctx, bool Active)
- : Ctx(Ctx), OldValue(Ctx->InitStackActive) {
+ : Ctx(Ctx), OldValue(Ctx->InitStackActive), Active(Active) {
Ctx->InitStackActive = Active;
+ if (Active)
+ Ctx->InitStack.push_back(InitLink::DIE());
}
- ~InitStackScope() { this->Ctx->InitStackActive = OldValue; }
+ ~InitStackScope() {
+ this->Ctx->InitStackActive = OldValue;
+ if (Active)
+ Ctx->InitStack.pop_back();
+ }
private:
Compiler<Emitter> *Ctx;
bool OldValue;
+ bool Active;
};
} // namespace interp
diff --git a/clang/lib/AST/ByteCode/InterpBuiltin.cpp b/clang/lib/AST/ByteCode/InterpBuiltin.cpp
index 0ef130c..6c7b2f5 100644
--- a/clang/lib/AST/ByteCode/InterpBuiltin.cpp
+++ b/clang/lib/AST/ByteCode/InterpBuiltin.cpp
@@ -2841,76 +2841,6 @@ static bool interp__builtin_blend(InterpState &S, CodePtr OpPC,
return true;
}
-static bool interp__builtin_ia32_pshufb(InterpState &S, CodePtr OpPC,
- const CallExpr *Call) {
- assert(Call->getNumArgs() == 2 && "masked forms handled via select*");
- const Pointer &Control = S.Stk.pop<Pointer>();
- const Pointer &Src = S.Stk.pop<Pointer>();
- const Pointer &Dst = S.Stk.peek<Pointer>();
-
- unsigned NumElems = Dst.getNumElems();
- assert(NumElems == Control.getNumElems());
- assert(NumElems == Dst.getNumElems());
-
- for (unsigned Idx = 0; Idx != NumElems; ++Idx) {
- uint8_t Ctlb = static_cast<uint8_t>(Control.elem<int8_t>(Idx));
-
- if (Ctlb & 0x80) {
- Dst.elem<int8_t>(Idx) = 0;
- } else {
- unsigned LaneBase = (Idx / 16) * 16;
- unsigned SrcOffset = Ctlb & 0x0F;
- unsigned SrcIdx = LaneBase + SrcOffset;
-
- Dst.elem<int8_t>(Idx) = Src.elem<int8_t>(SrcIdx);
- }
- }
- Dst.initializeAllElements();
- return true;
-}
-
-static bool interp__builtin_ia32_pshuf(InterpState &S, CodePtr OpPC,
- const CallExpr *Call, bool IsShufHW) {
- assert(Call->getNumArgs() == 2 && "masked forms handled via select*");
- APSInt ControlImm = popToAPSInt(S, Call->getArg(1));
- const Pointer &Src = S.Stk.pop<Pointer>();
- const Pointer &Dst = S.Stk.peek<Pointer>();
-
- unsigned NumElems = Dst.getNumElems();
- PrimType ElemT = Dst.getFieldDesc()->getPrimType();
-
- unsigned ElemBits = static_cast<unsigned>(primSize(ElemT) * 8);
- if (ElemBits != 16 && ElemBits != 32)
- return false;
-
- unsigned LaneElts = 128u / ElemBits;
- assert(LaneElts && (NumElems % LaneElts == 0));
-
- uint8_t Ctl = static_cast<uint8_t>(ControlImm.getZExtValue());
-
- for (unsigned Idx = 0; Idx != NumElems; Idx++) {
- unsigned LaneBase = (Idx / LaneElts) * LaneElts;
- unsigned LaneIdx = Idx % LaneElts;
- unsigned SrcIdx = Idx;
- unsigned Sel = (Ctl >> (2 * (LaneIdx & 0x3))) & 0x3;
- if (ElemBits == 32) {
- SrcIdx = LaneBase + Sel;
- } else {
- constexpr unsigned HalfSize = 4;
- bool InHigh = LaneIdx >= HalfSize;
- if (!IsShufHW && !InHigh) {
- SrcIdx = LaneBase + Sel;
- } else if (IsShufHW && InHigh) {
- SrcIdx = LaneBase + HalfSize + Sel;
- }
- }
-
- INT_TYPE_SWITCH_NO_BOOL(ElemT, { Dst.elem<T>(Idx) = Src.elem<T>(SrcIdx); });
- }
- Dst.initializeAllElements();
- return true;
-}
-
static bool interp__builtin_ia32_test_op(
InterpState &S, CodePtr OpPC, const CallExpr *Call,
llvm::function_ref<bool(const APInt &A, const APInt &B)> Fn) {
@@ -3377,61 +3307,46 @@ static bool interp__builtin_ia32_vpconflict(InterpState &S, CodePtr OpPC,
return true;
}
-static bool interp__builtin_x86_byteshift(
- InterpState &S, CodePtr OpPC, const CallExpr *Call, unsigned ID,
- llvm::function_ref<APInt(const Pointer &, unsigned Lane, unsigned I,
- unsigned Shift)>
- Fn) {
- assert(Call->getNumArgs() == 2);
-
- APSInt ImmAPS = popToAPSInt(S, Call->getArg(1));
- uint64_t Shift = ImmAPS.getZExtValue() & 0xff;
-
- const Pointer &Src = S.Stk.pop<Pointer>();
- if (!Src.getFieldDesc()->isPrimitiveArray())
- return false;
-
- unsigned NumElems = Src.getNumElems();
- const Pointer &Dst = S.Stk.peek<Pointer>();
- PrimType ElemT = Src.getFieldDesc()->getPrimType();
-
- for (unsigned Lane = 0; Lane != NumElems; Lane += 16) {
- for (unsigned I = 0; I != 16; ++I) {
- unsigned Base = Lane + I;
- APSInt Result = APSInt(Fn(Src, Lane, I, Shift));
- INT_TYPE_SWITCH_NO_BOOL(ElemT,
- { Dst.elem<T>(Base) = static_cast<T>(Result); });
- }
- }
-
- Dst.initializeAllElements();
-
- return true;
-}
-
static bool interp__builtin_ia32_shuffle_generic(
InterpState &S, CodePtr OpPC, const CallExpr *Call,
llvm::function_ref<std::pair<unsigned, int>(unsigned, unsigned)>
GetSourceIndex) {
- assert(Call->getNumArgs() == 3);
+ assert(Call->getNumArgs() == 2 || Call->getNumArgs() == 3);
unsigned ShuffleMask = 0;
Pointer A, MaskVector, B;
-
- QualType Arg2Type = Call->getArg(2)->getType();
bool IsVectorMask = false;
- if (Arg2Type->isVectorType()) {
- IsVectorMask = true;
- B = S.Stk.pop<Pointer>();
- MaskVector = S.Stk.pop<Pointer>();
- A = S.Stk.pop<Pointer>();
- } else if (Arg2Type->isIntegerType()) {
- ShuffleMask = popToAPSInt(S, Call->getArg(2)).getZExtValue();
- B = S.Stk.pop<Pointer>();
- A = S.Stk.pop<Pointer>();
+ bool IsSingleOperand = (Call->getNumArgs() == 2);
+
+ if (IsSingleOperand) {
+ QualType MaskType = Call->getArg(1)->getType();
+ if (MaskType->isVectorType()) {
+ IsVectorMask = true;
+ MaskVector = S.Stk.pop<Pointer>();
+ A = S.Stk.pop<Pointer>();
+ B = A;
+ } else if (MaskType->isIntegerType()) {
+ ShuffleMask = popToAPSInt(S, Call->getArg(1)).getZExtValue();
+ A = S.Stk.pop<Pointer>();
+ B = A;
+ } else {
+ return false;
+ }
} else {
- return false;
+ QualType Arg2Type = Call->getArg(2)->getType();
+ if (Arg2Type->isVectorType()) {
+ IsVectorMask = true;
+ B = S.Stk.pop<Pointer>();
+ MaskVector = S.Stk.pop<Pointer>();
+ A = S.Stk.pop<Pointer>();
+ } else if (Arg2Type->isIntegerType()) {
+ ShuffleMask = popToAPSInt(S, Call->getArg(2)).getZExtValue();
+ B = S.Stk.pop<Pointer>();
+ A = S.Stk.pop<Pointer>();
+ } else {
+ return false;
+ }
}
QualType Arg0Type = Call->getArg(0)->getType();
@@ -3455,6 +3370,7 @@ static bool interp__builtin_ia32_shuffle_generic(
ShuffleMask = static_cast<unsigned>(MaskVector.elem<T>(DstIdx));
});
}
+
auto [SrcVecIdx, SrcIdx] = GetSourceIndex(DstIdx, ShuffleMask);
if (SrcIdx < 0) {
@@ -4555,22 +4471,58 @@ bool InterpretBuiltin(InterpState &S, CodePtr OpPC, const CallExpr *Call,
case X86::BI__builtin_ia32_pshufb128:
case X86::BI__builtin_ia32_pshufb256:
case X86::BI__builtin_ia32_pshufb512:
- return interp__builtin_ia32_pshufb(S, OpPC, Call);
+ return interp__builtin_ia32_shuffle_generic(
+ S, OpPC, Call, [](unsigned DstIdx, unsigned ShuffleMask) {
+ uint8_t Ctlb = static_cast<uint8_t>(ShuffleMask);
+ if (Ctlb & 0x80)
+ return std::make_pair(0, -1);
+
+ unsigned LaneBase = (DstIdx / 16) * 16;
+ unsigned SrcOffset = Ctlb & 0x0F;
+ unsigned SrcIdx = LaneBase + SrcOffset;
+ return std::make_pair(0, static_cast<int>(SrcIdx));
+ });
case X86::BI__builtin_ia32_pshuflw:
case X86::BI__builtin_ia32_pshuflw256:
case X86::BI__builtin_ia32_pshuflw512:
- return interp__builtin_ia32_pshuf(S, OpPC, Call, false);
+ return interp__builtin_ia32_shuffle_generic(
+ S, OpPC, Call, [](unsigned DstIdx, unsigned ShuffleMask) {
+ unsigned LaneBase = (DstIdx / 8) * 8;
+ unsigned LaneIdx = DstIdx % 8;
+ if (LaneIdx < 4) {
+ unsigned Sel = (ShuffleMask >> (2 * LaneIdx)) & 0x3;
+ return std::make_pair(0, static_cast<int>(LaneBase + Sel));
+ }
+
+ return std::make_pair(0, static_cast<int>(DstIdx));
+ });
case X86::BI__builtin_ia32_pshufhw:
case X86::BI__builtin_ia32_pshufhw256:
case X86::BI__builtin_ia32_pshufhw512:
- return interp__builtin_ia32_pshuf(S, OpPC, Call, true);
+ return interp__builtin_ia32_shuffle_generic(
+ S, OpPC, Call, [](unsigned DstIdx, unsigned ShuffleMask) {
+ unsigned LaneBase = (DstIdx / 8) * 8;
+ unsigned LaneIdx = DstIdx % 8;
+ if (LaneIdx >= 4) {
+ unsigned Sel = (ShuffleMask >> (2 * (LaneIdx - 4))) & 0x3;
+ return std::make_pair(0, static_cast<int>(LaneBase + 4 + Sel));
+ }
+
+ return std::make_pair(0, static_cast<int>(DstIdx));
+ });
case X86::BI__builtin_ia32_pshufd:
case X86::BI__builtin_ia32_pshufd256:
case X86::BI__builtin_ia32_pshufd512:
- return interp__builtin_ia32_pshuf(S, OpPC, Call, false);
+ return interp__builtin_ia32_shuffle_generic(
+ S, OpPC, Call, [](unsigned DstIdx, unsigned ShuffleMask) {
+ unsigned LaneBase = (DstIdx / 4) * 4;
+ unsigned LaneIdx = DstIdx % 4;
+ unsigned Sel = (ShuffleMask >> (2 * LaneIdx)) & 0x3;
+ return std::make_pair(0, static_cast<int>(LaneBase + Sel));
+ });
case X86::BI__builtin_ia32_kandqi:
case X86::BI__builtin_ia32_kandhi:
@@ -4728,13 +4680,16 @@ bool InterpretBuiltin(InterpState &S, CodePtr OpPC, const CallExpr *Call,
// The lane width is hardcoded to 16 to match the SIMD register size,
// but the algorithm processes one byte per iteration,
// so APInt(8, ...) is correct and intentional.
- return interp__builtin_x86_byteshift(
- S, OpPC, Call, BuiltinID,
- [](const Pointer &Src, unsigned Lane, unsigned I, unsigned Shift) {
- if (I < Shift) {
- return APInt(8, 0);
- }
- return APInt(8, Src.elem<uint8_t>(Lane + I - Shift));
+ return interp__builtin_ia32_shuffle_generic(
+ S, OpPC, Call,
+ [](unsigned DstIdx, unsigned Shift) -> std::pair<unsigned, int> {
+ unsigned LaneBase = (DstIdx / 16) * 16;
+ unsigned LaneIdx = DstIdx % 16;
+ if (LaneIdx < Shift)
+ return std::make_pair(0, -1);
+
+ return std::make_pair(0,
+ static_cast<int>(LaneBase + LaneIdx - Shift));
});
case X86::BI__builtin_ia32_psrldqi128_byteshift:
@@ -4744,14 +4699,40 @@ bool InterpretBuiltin(InterpState &S, CodePtr OpPC, const CallExpr *Call,
// The lane width is hardcoded to 16 to match the SIMD register size,
// but the algorithm processes one byte per iteration,
// so APInt(8, ...) is correct and intentional.
- return interp__builtin_x86_byteshift(
- S, OpPC, Call, BuiltinID,
- [](const Pointer &Src, unsigned Lane, unsigned I, unsigned Shift) {
- if (I + Shift < 16) {
- return APInt(8, Src.elem<uint8_t>(Lane + I + Shift));
+ return interp__builtin_ia32_shuffle_generic(
+ S, OpPC, Call,
+ [](unsigned DstIdx, unsigned Shift) -> std::pair<unsigned, int> {
+ unsigned LaneBase = (DstIdx / 16) * 16;
+ unsigned LaneIdx = DstIdx % 16;
+ if (LaneIdx + Shift < 16)
+ return std::make_pair(0,
+ static_cast<int>(LaneBase + LaneIdx + Shift));
+
+ return std::make_pair(0, -1);
+ });
+
+ case X86::BI__builtin_ia32_palignr128:
+ case X86::BI__builtin_ia32_palignr256:
+ case X86::BI__builtin_ia32_palignr512:
+ return interp__builtin_ia32_shuffle_generic(
+ S, OpPC, Call, [](unsigned DstIdx, unsigned Shift) {
+ // Default to -1 → zero-fill this destination element
+ unsigned VecIdx = 1;
+ int ElemIdx = -1;
+
+ int Lane = DstIdx / 16;
+ int Offset = DstIdx % 16;
+
+ // Elements come from VecB first, then VecA after the shift boundary
+ unsigned ShiftedIdx = Offset + (Shift & 0xFF);
+ if (ShiftedIdx < 16) { // from VecB
+ ElemIdx = ShiftedIdx + (Lane * 16);
+ } else if (ShiftedIdx < 32) { // from VecA
+ VecIdx = 0;
+ ElemIdx = (ShiftedIdx - 16) + (Lane * 16);
}
- return APInt(8, 0);
+ return std::pair<unsigned, int>{VecIdx, ElemIdx};
});
default:
diff --git a/clang/lib/AST/ExprConstant.cpp b/clang/lib/AST/ExprConstant.cpp
index 972d9fe..1bfea24 100644
--- a/clang/lib/AST/ExprConstant.cpp
+++ b/clang/lib/AST/ExprConstant.cpp
@@ -12090,24 +12090,46 @@ static bool evalShuffleGeneric(
unsigned ShuffleMask = 0;
APValue A, MaskVector, B;
bool IsVectorMask = false;
-
- QualType Arg2Type = Call->getArg(2)->getType();
- if (Arg2Type->isVectorType()) {
- IsVectorMask = true;
- if (!EvaluateAsRValue(Info, Call->getArg(0), A) ||
- !EvaluateAsRValue(Info, Call->getArg(1), MaskVector) ||
- !EvaluateAsRValue(Info, Call->getArg(2), B))
- return false;
- } else if (Arg2Type->isIntegerType()) {
- APSInt MaskImm;
- if (!EvaluateInteger(Call->getArg(2), MaskImm, Info))
- return false;
- ShuffleMask = static_cast<unsigned>(MaskImm.getZExtValue());
- if (!EvaluateAsRValue(Info, Call->getArg(0), A) ||
- !EvaluateAsRValue(Info, Call->getArg(1), B))
+ bool IsSingleOperand = (Call->getNumArgs() == 2);
+
+ if (IsSingleOperand) {
+ QualType MaskType = Call->getArg(1)->getType();
+ if (MaskType->isVectorType()) {
+ IsVectorMask = true;
+ if (!EvaluateAsRValue(Info, Call->getArg(0), A) ||
+ !EvaluateAsRValue(Info, Call->getArg(1), MaskVector))
+ return false;
+ B = A;
+ } else if (MaskType->isIntegerType()) {
+ APSInt MaskImm;
+ if (!EvaluateInteger(Call->getArg(1), MaskImm, Info))
+ return false;
+ ShuffleMask = static_cast<unsigned>(MaskImm.getZExtValue());
+ if (!EvaluateAsRValue(Info, Call->getArg(0), A))
+ return false;
+ B = A;
+ } else {
return false;
+ }
} else {
- return false;
+ QualType Arg2Type = Call->getArg(2)->getType();
+ if (Arg2Type->isVectorType()) {
+ IsVectorMask = true;
+ if (!EvaluateAsRValue(Info, Call->getArg(0), A) ||
+ !EvaluateAsRValue(Info, Call->getArg(1), MaskVector) ||
+ !EvaluateAsRValue(Info, Call->getArg(2), B))
+ return false;
+ } else if (Arg2Type->isIntegerType()) {
+ APSInt MaskImm;
+ if (!EvaluateInteger(Call->getArg(2), MaskImm, Info))
+ return false;
+ ShuffleMask = static_cast<unsigned>(MaskImm.getZExtValue());
+ if (!EvaluateAsRValue(Info, Call->getArg(0), A) ||
+ !EvaluateAsRValue(Info, Call->getArg(1), B))
+ return false;
+ } else {
+ return false;
+ }
}
unsigned NumElts = VT->getNumElements();
@@ -12124,8 +12146,16 @@ static bool evalShuffleGeneric(
if (SrcIdx < 0) {
// Zero out this element
QualType ElemTy = VT->getElementType();
- ResultElements.push_back(
- APValue(APFloat::getZero(Info.Ctx.getFloatTypeSemantics(ElemTy))));
+ if (ElemTy->isRealFloatingType()) {
+ ResultElements.push_back(
+ APValue(APFloat::getZero(Info.Ctx.getFloatTypeSemantics(ElemTy))));
+ } else if (ElemTy->isIntegerType()) {
+ APValue Zero(Info.Ctx.MakeIntValue(0, ElemTy));
+ ResultElements.push_back(APValue(Zero));
+ } else {
+ // Other types of fallback logic
+ ResultElements.push_back(APValue());
+ }
} else {
const APValue &Src = (SrcVecIdx == 0) ? A : B;
ResultElements.push_back(Src.getVectorElt(SrcIdx));
@@ -12136,98 +12166,6 @@ static bool evalShuffleGeneric(
return true;
}
-static bool evalPshufbBuiltin(EvalInfo &Info, const CallExpr *Call,
- APValue &Out) {
- APValue SrcVec, ControlVec;
- if (!EvaluateAsRValue(Info, Call->getArg(0), SrcVec))
- return false;
- if (!EvaluateAsRValue(Info, Call->getArg(1), ControlVec))
- return false;
-
- const auto *VT = Call->getType()->getAs<VectorType>();
- if (!VT)
- return false;
-
- QualType ElemT = VT->getElementType();
- unsigned NumElts = VT->getNumElements();
-
- SmallVector<APValue, 64> ResultElements;
- ResultElements.reserve(NumElts);
-
- for (unsigned Idx = 0; Idx != NumElts; ++Idx) {
- APValue CtlVal = ControlVec.getVectorElt(Idx);
- APSInt CtlByte = CtlVal.getInt();
- uint8_t Ctl = static_cast<uint8_t>(CtlByte.getZExtValue());
-
- if (Ctl & 0x80) {
- APValue Zero(Info.Ctx.MakeIntValue(0, ElemT));
- ResultElements.push_back(Zero);
- } else {
- unsigned LaneBase = (Idx / 16) * 16;
- unsigned SrcOffset = Ctl & 0x0F;
- unsigned SrcIdx = LaneBase + SrcOffset;
-
- ResultElements.push_back(SrcVec.getVectorElt(SrcIdx));
- }
- }
- Out = APValue(ResultElements.data(), ResultElements.size());
- return true;
-}
-
-static bool evalPshufBuiltin(EvalInfo &Info, const CallExpr *Call,
- bool IsShufHW, APValue &Out) {
- APValue Vec;
- APSInt Imm;
- if (!EvaluateAsRValue(Info, Call->getArg(0), Vec))
- return false;
- if (!EvaluateInteger(Call->getArg(1), Imm, Info))
- return false;
-
- const auto *VT = Call->getType()->getAs<VectorType>();
- if (!VT)
- return false;
-
- QualType ElemT = VT->getElementType();
- unsigned ElemBits = Info.Ctx.getTypeSize(ElemT);
- unsigned NumElts = VT->getNumElements();
-
- unsigned LaneBits = 128u;
- unsigned LaneElts = LaneBits / ElemBits;
- if (!LaneElts || (NumElts % LaneElts) != 0)
- return false;
-
- uint8_t Ctl = static_cast<uint8_t>(Imm.getZExtValue());
-
- SmallVector<APValue, 32> ResultElements;
- ResultElements.reserve(NumElts);
-
- for (unsigned Idx = 0; Idx != NumElts; Idx++) {
- unsigned LaneBase = (Idx / LaneElts) * LaneElts;
- unsigned LaneIdx = Idx % LaneElts;
- unsigned SrcIdx = Idx;
- unsigned Sel = (Ctl >> (2 * LaneIdx)) & 0x3;
-
- if (ElemBits == 32) {
- SrcIdx = LaneBase + Sel;
- } else {
- constexpr unsigned HalfSize = 4;
- bool InHigh = LaneIdx >= HalfSize;
- if (!IsShufHW && !InHigh) {
- SrcIdx = LaneBase + Sel;
- } else if (IsShufHW && InHigh) {
- unsigned Rel = LaneIdx - HalfSize;
- Sel = (Ctl >> (2 * Rel)) & 0x3;
- SrcIdx = LaneBase + HalfSize + Sel;
- }
- }
-
- ResultElements.push_back(Vec.getVectorElt(SrcIdx));
- }
-
- Out = APValue(ResultElements.data(), ResultElements.size());
- return true;
-}
-
bool VectorExprEvaluator::VisitCallExpr(const CallExpr *E) {
if (!IsConstantEvaluatedBuiltinCall(E))
return ExprEvaluatorBaseTy::VisitCallExpr(E);
@@ -12993,7 +12931,19 @@ bool VectorExprEvaluator::VisitCallExpr(const CallExpr *E) {
case X86::BI__builtin_ia32_pshufb256:
case X86::BI__builtin_ia32_pshufb512: {
APValue R;
- if (!evalPshufbBuiltin(Info, E, R))
+ if (!evalShuffleGeneric(
+ Info, E, R,
+ [](unsigned DstIdx,
+ unsigned ShuffleMask) -> std::pair<unsigned, int> {
+ uint8_t Ctlb = static_cast<uint8_t>(ShuffleMask);
+ if (Ctlb & 0x80)
+ return std::make_pair(0, -1);
+
+ unsigned LaneBase = (DstIdx / 16) * 16;
+ unsigned SrcOffset = Ctlb & 0x0F;
+ unsigned SrcIdx = LaneBase + SrcOffset;
+ return std::make_pair(0, static_cast<int>(SrcIdx));
+ }))
return false;
return Success(R, E);
}
@@ -13002,7 +12952,21 @@ bool VectorExprEvaluator::VisitCallExpr(const CallExpr *E) {
case X86::BI__builtin_ia32_pshuflw256:
case X86::BI__builtin_ia32_pshuflw512: {
APValue R;
- if (!evalPshufBuiltin(Info, E, false, R))
+ if (!evalShuffleGeneric(
+ Info, E, R,
+ [](unsigned DstIdx, unsigned Mask) -> std::pair<unsigned, int> {
+ constexpr unsigned LaneBits = 128u;
+ constexpr unsigned ElemBits = 16u;
+ constexpr unsigned LaneElts = LaneBits / ElemBits;
+ constexpr unsigned HalfSize = 4;
+ unsigned LaneBase = (DstIdx / LaneElts) * LaneElts;
+ unsigned LaneIdx = DstIdx % LaneElts;
+ if (LaneIdx < HalfSize) {
+ unsigned Sel = (Mask >> (2 * LaneIdx)) & 0x3;
+ return std::make_pair(0, static_cast<int>(LaneBase + Sel));
+ }
+ return std::make_pair(0, static_cast<int>(DstIdx));
+ }))
return false;
return Success(R, E);
}
@@ -13011,7 +12975,23 @@ bool VectorExprEvaluator::VisitCallExpr(const CallExpr *E) {
case X86::BI__builtin_ia32_pshufhw256:
case X86::BI__builtin_ia32_pshufhw512: {
APValue R;
- if (!evalPshufBuiltin(Info, E, true, R))
+ if (!evalShuffleGeneric(
+ Info, E, R,
+ [](unsigned DstIdx, unsigned Mask) -> std::pair<unsigned, int> {
+ constexpr unsigned LaneBits = 128u;
+ constexpr unsigned ElemBits = 16u;
+ constexpr unsigned LaneElts = LaneBits / ElemBits;
+ constexpr unsigned HalfSize = 4;
+ unsigned LaneBase = (DstIdx / LaneElts) * LaneElts;
+ unsigned LaneIdx = DstIdx % LaneElts;
+ if (LaneIdx >= HalfSize) {
+ unsigned Rel = LaneIdx - HalfSize;
+ unsigned Sel = (Mask >> (2 * Rel)) & 0x3;
+ return std::make_pair(
+ 0, static_cast<int>(LaneBase + HalfSize + Sel));
+ }
+ return std::make_pair(0, static_cast<int>(DstIdx));
+ }))
return false;
return Success(R, E);
}
@@ -13020,7 +13000,17 @@ bool VectorExprEvaluator::VisitCallExpr(const CallExpr *E) {
case X86::BI__builtin_ia32_pshufd256:
case X86::BI__builtin_ia32_pshufd512: {
APValue R;
- if (!evalPshufBuiltin(Info, E, false, R))
+ if (!evalShuffleGeneric(
+ Info, E, R,
+ [](unsigned DstIdx, unsigned Mask) -> std::pair<unsigned, int> {
+ constexpr unsigned LaneBits = 128u;
+ constexpr unsigned ElemBits = 32u;
+ constexpr unsigned LaneElts = LaneBits / ElemBits;
+ unsigned LaneBase = (DstIdx / LaneElts) * LaneElts;
+ unsigned LaneIdx = DstIdx % LaneElts;
+ unsigned Sel = (Mask >> (2 * LaneIdx)) & 0x3;
+ return std::make_pair(0, static_cast<int>(LaneBase + Sel));
+ }))
return false;
return Success(R, E);
}
@@ -13500,61 +13490,66 @@ bool VectorExprEvaluator::VisitCallExpr(const CallExpr *E) {
case X86::BI__builtin_ia32_pslldqi128_byteshift:
case X86::BI__builtin_ia32_pslldqi256_byteshift:
case X86::BI__builtin_ia32_pslldqi512_byteshift: {
- assert(E->getNumArgs() == 2);
-
- APValue Src;
- APSInt Imm;
- if (!EvaluateAsRValue(Info, E->getArg(0), Src) ||
- !EvaluateInteger(E->getArg(1), Imm, Info))
+ APValue R;
+ if (!evalShuffleGeneric(
+ Info, E, R,
+ [](unsigned DstIdx, unsigned Shift) -> std::pair<unsigned, int> {
+ unsigned LaneBase = (DstIdx / 16) * 16;
+ unsigned LaneIdx = DstIdx % 16;
+ if (LaneIdx < Shift)
+ return std::make_pair(0, -1);
+
+ return std::make_pair(
+ 0, static_cast<int>(LaneBase + LaneIdx - Shift));
+ }))
return false;
-
- unsigned VecLen = Src.getVectorLength();
- unsigned Shift = Imm.getZExtValue() & 0xff;
-
- SmallVector<APValue> ResultElements;
- for (unsigned Lane = 0; Lane != VecLen; Lane += 16) {
- for (unsigned I = 0; I != 16; ++I) {
- if (I < Shift) {
- APSInt Zero(8, /*isUnsigned=*/true);
- Zero = 0;
- ResultElements.push_back(APValue(Zero));
- } else {
- ResultElements.push_back(Src.getVectorElt(Lane + I - Shift));
- }
- }
- }
-
- return Success(APValue(ResultElements.data(), ResultElements.size()), E);
+ return Success(R, E);
}
case X86::BI__builtin_ia32_psrldqi128_byteshift:
case X86::BI__builtin_ia32_psrldqi256_byteshift:
case X86::BI__builtin_ia32_psrldqi512_byteshift: {
- assert(E->getNumArgs() == 2);
-
- APValue Src;
- APSInt Imm;
- if (!EvaluateAsRValue(Info, E->getArg(0), Src) ||
- !EvaluateInteger(E->getArg(1), Imm, Info))
+ APValue R;
+ if (!evalShuffleGeneric(
+ Info, E, R,
+ [](unsigned DstIdx, unsigned Shift) -> std::pair<unsigned, int> {
+ unsigned LaneBase = (DstIdx / 16) * 16;
+ unsigned LaneIdx = DstIdx % 16;
+ if (LaneIdx + Shift < 16)
+ return std::make_pair(
+ 0, static_cast<int>(LaneBase + LaneIdx + Shift));
+
+ return std::make_pair(0, -1);
+ }))
return false;
+ return Success(R, E);
+ }
- unsigned VecLen = Src.getVectorLength();
- unsigned Shift = Imm.getZExtValue() & 0xff;
-
- SmallVector<APValue> ResultElements;
- for (unsigned Lane = 0; Lane != VecLen; Lane += 16) {
- for (unsigned I = 0; I != 16; ++I) {
- if (I + Shift < 16) {
- ResultElements.push_back(Src.getVectorElt(Lane + I + Shift));
- } else {
- APSInt Zero(8, /*isUnsigned=*/true);
- Zero = 0;
- ResultElements.push_back(APValue(Zero));
- }
- }
- }
+ case X86::BI__builtin_ia32_palignr128:
+ case X86::BI__builtin_ia32_palignr256:
+ case X86::BI__builtin_ia32_palignr512: {
+ APValue R;
+ if (!evalShuffleGeneric(Info, E, R, [](unsigned DstIdx, unsigned Shift) {
+ // Default to -1 → zero-fill this destination element
+ unsigned VecIdx = 1;
+ int ElemIdx = -1;
+
+ int Lane = DstIdx / 16;
+ int Offset = DstIdx % 16;
+
+ // Elements come from VecB first, then VecA after the shift boundary
+ unsigned ShiftedIdx = Offset + (Shift & 0xFF);
+ if (ShiftedIdx < 16) { // from VecB
+ ElemIdx = ShiftedIdx + (Lane * 16);
+ } else if (ShiftedIdx < 32) { // from VecA
+ VecIdx = 0;
+ ElemIdx = (ShiftedIdx - 16) + (Lane * 16);
+ }
- return Success(APValue(ResultElements.data(), ResultElements.size()), E);
+ return std::pair<unsigned, int>{VecIdx, ElemIdx};
+ }))
+ return false;
+ return Success(R, E);
}
case X86::BI__builtin_ia32_vpermi2varq128:
case X86::BI__builtin_ia32_vpermi2varpd128: {
generated by cgit v1.1 at 2025-11-12 08:45:35 +0000