diff options
Diffstat (limited to 'clang/lib/AST/ByteCode/InterpBuiltin.cpp')
| -rw-r--r-- | clang/lib/AST/ByteCode/InterpBuiltin.cpp | 68 |
1 files changed, 67 insertions, 1 deletions
diff --git a/clang/lib/AST/ByteCode/InterpBuiltin.cpp b/clang/lib/AST/ByteCode/InterpBuiltin.cpp index 2d3cb6a..a0d2c76 100644 --- a/clang/lib/AST/ByteCode/InterpBuiltin.cpp +++ b/clang/lib/AST/ByteCode/InterpBuiltin.cpp @@ -2790,6 +2790,34 @@ 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*"); @@ -3073,6 +3101,33 @@ static bool interp__builtin_vec_set(InterpState &S, CodePtr OpPC, return true; } +static bool interp__builtin_ia32_vpconflict(InterpState &S, CodePtr OpPC, + const CallExpr *Call) { + assert(Call->getNumArgs() == 1); + + QualType Arg0Type = Call->getArg(0)->getType(); + const auto *VecT = Arg0Type->castAs<VectorType>(); + PrimType ElemT = *S.getContext().classify(VecT->getElementType()); + unsigned NumElems = VecT->getNumElements(); + bool DestUnsigned = Call->getType()->isUnsignedIntegerOrEnumerationType(); + const Pointer &Src = S.Stk.pop<Pointer>(); + const Pointer &Dst = S.Stk.peek<Pointer>(); + + for (unsigned I = 0; I != NumElems; ++I) { + INT_TYPE_SWITCH_NO_BOOL(ElemT, { + APSInt ElemI = Src.elem<T>(I).toAPSInt(); + APInt ConflictMask(ElemI.getBitWidth(), 0); + for (unsigned J = 0; J != I; ++J) { + APSInt ElemJ = Src.elem<T>(J).toAPSInt(); + ConflictMask.setBitVal(J, ElemI == ElemJ); + } + Dst.elem<T>(I) = static_cast<T>(APSInt(ConflictMask, DestUnsigned)); + }); + } + Dst.initializeAllElements(); + return true; +} + bool InterpretBuiltin(InterpState &S, CodePtr OpPC, const CallExpr *Call, uint32_t BuiltinID) { if (!S.getASTContext().BuiltinInfo.isConstantEvaluated(BuiltinID)) @@ -3863,7 +3918,13 @@ bool InterpretBuiltin(InterpState &S, CodePtr OpPC, const CallExpr *Call, [](const APSInt &Lo, const APSInt &Hi, const APSInt &Amt) { return llvm::APIntOps::fshr(Hi, Lo, Amt); }); - + case X86::BI__builtin_ia32_vpconflictsi_128: + case X86::BI__builtin_ia32_vpconflictsi_256: + case X86::BI__builtin_ia32_vpconflictsi_512: + case X86::BI__builtin_ia32_vpconflictdi_128: + case X86::BI__builtin_ia32_vpconflictdi_256: + case X86::BI__builtin_ia32_vpconflictdi_512: + return interp__builtin_ia32_vpconflict(S, OpPC, Call); case clang::X86::BI__builtin_ia32_blendpd: case clang::X86::BI__builtin_ia32_blendpd256: case clang::X86::BI__builtin_ia32_blendps: @@ -3943,6 +4004,11 @@ bool InterpretBuiltin(InterpState &S, CodePtr OpPC, const CallExpr *Call, case X86::BI__builtin_ia32_selectpd_512: return interp__builtin_select(S, OpPC, 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); + case X86::BI__builtin_ia32_pshuflw: case X86::BI__builtin_ia32_pshuflw256: case X86::BI__builtin_ia32_pshuflw512: |