1 files changed, 71 insertions, 68 deletions

diff --git a/clang/lib/AST/ByteCode/InterpBuiltin.cpp b/clang/lib/AST/ByteCode/InterpBuiltin.cpp
index 1eea813..922d679 100644
--- a/clang/lib/AST/ByteCode/InterpBuiltin.cpp
+++ b/clang/lib/AST/ByteCode/InterpBuiltin.cpp
@@ -678,30 +678,6 @@ static bool interp__builtin_popcount(InterpState &S, CodePtr OpPC,
   return true;
 }
 
-static bool interp__builtin_parity(InterpState &S, CodePtr OpPC,
-                                   const InterpFrame *Frame,
-                                   const CallExpr *Call) {
-  APSInt Val = popToAPSInt(S, Call->getArg(0));
-  pushInteger(S, Val.popcount() % 2, Call->getType());
-  return true;
-}
-
-static bool interp__builtin_clrsb(InterpState &S, CodePtr OpPC,
-                                  const InterpFrame *Frame,
-                                  const CallExpr *Call) {
-  APSInt Val = popToAPSInt(S, Call->getArg(0));
-  pushInteger(S, Val.getBitWidth() - Val.getSignificantBits(), Call->getType());
-  return true;
-}
-
-static bool interp__builtin_bitreverse(InterpState &S, CodePtr OpPC,
-                                       const InterpFrame *Frame,
-                                       const CallExpr *Call) {
-  APSInt Val = popToAPSInt(S, Call->getArg(0));
-  pushInteger(S, Val.reverseBits(), Call->getType());
-  return true;
-}
-
 static bool interp__builtin_classify_type(InterpState &S, CodePtr OpPC,
                                           const InterpFrame *Frame,
                                           const CallExpr *Call) {
@@ -736,16 +712,6 @@ static bool interp__builtin_expect(InterpState &S, CodePtr OpPC,
   return true;
 }
 
-static bool interp__builtin_ffs(InterpState &S, CodePtr OpPC,
-                                const InterpFrame *Frame,
-                                const CallExpr *Call) {
-  APSInt Value = popToAPSInt(S, Call->getArg(0));
-
-  uint64_t N = Value.countr_zero();
-  pushInteger(S, N == Value.getBitWidth() ? 0 : N + 1, Call->getType());
-  return true;
-}
-
 static bool interp__builtin_addressof(InterpState &S, CodePtr OpPC,
                                       const InterpFrame *Frame,
                                       const CallExpr *Call) {
@@ -2583,9 +2549,11 @@ static bool interp__builtin_elementwise_maxmin(InterpState &S, CodePtr OpPC,
   return true;
 }
 
-static bool interp__builtin_ia32_pmul(InterpState &S, CodePtr OpPC,
-                                      const CallExpr *Call,
-                                      unsigned BuiltinID) {
+static bool interp__builtin_ia32_pmul(
+    InterpState &S, CodePtr OpPC, const CallExpr *Call,
+    llvm::function_ref<APInt(const APSInt &, const APSInt &, const APSInt &,
+                             const APSInt &)>
+        Fn) {
   assert(Call->getArg(0)->getType()->isVectorType() &&
          Call->getArg(1)->getType()->isVectorType());
   const Pointer &RHS = S.Stk.pop<Pointer>();
@@ -2594,35 +2562,23 @@ static bool interp__builtin_ia32_pmul(InterpState &S, CodePtr OpPC,
 
   const auto *VT = Call->getArg(0)->getType()->castAs<VectorType>();
   PrimType ElemT = *S.getContext().classify(VT->getElementType());
-  unsigned SourceLen = VT->getNumElements();
+  unsigned NumElems = VT->getNumElements();
+  const auto *DestVT = Call->getType()->castAs<VectorType>();
+  PrimType DestElemT = *S.getContext().classify(DestVT->getElementType());
+  bool DestUnsigned = Call->getType()->isUnsignedIntegerOrEnumerationType();
 
-  PrimType DstElemT = *S.getContext().classify(
-      Call->getType()->castAs<VectorType>()->getElementType());
   unsigned DstElem = 0;
-  for (unsigned I = 0; I != SourceLen; I += 2) {
-    APSInt Elem1;
-    APSInt Elem2;
+  for (unsigned I = 0; I != NumElems; I += 2) {
+    APSInt Result;
     INT_TYPE_SWITCH_NO_BOOL(ElemT, {
-      Elem1 = LHS.elem<T>(I).toAPSInt();
-      Elem2 = RHS.elem<T>(I).toAPSInt();
+      APSInt LoLHS = LHS.elem<T>(I).toAPSInt();
+      APSInt HiLHS = LHS.elem<T>(I + 1).toAPSInt();
+      APSInt LoRHS = RHS.elem<T>(I).toAPSInt();
+      APSInt HiRHS = RHS.elem<T>(I + 1).toAPSInt();
+      Result = APSInt(Fn(LoLHS, HiLHS, LoRHS, HiRHS), DestUnsigned);
     });
 
-    APSInt Result;
-    switch (BuiltinID) {
-    case clang::X86::BI__builtin_ia32_pmuludq128:
-    case clang::X86::BI__builtin_ia32_pmuludq256:
-    case clang::X86::BI__builtin_ia32_pmuludq512:
-      Result = APSInt(llvm::APIntOps::muluExtended(Elem1, Elem2),
-                      /*IsUnsigned=*/true);
-      break;
-    case clang::X86::BI__builtin_ia32_pmuldq128:
-    case clang::X86::BI__builtin_ia32_pmuldq256:
-    case clang::X86::BI__builtin_ia32_pmuldq512:
-      Result = APSInt(llvm::APIntOps::mulsExtended(Elem1, Elem2),
-                      /*IsUnsigned=*/false);
-      break;
-    }
-    INT_TYPE_SWITCH_NO_BOOL(DstElemT,
+    INT_TYPE_SWITCH_NO_BOOL(DestElemT,
                             { Dst.elem<T>(DstElem) = static_cast<T>(Result); });
     ++DstElem;
   }
@@ -3158,18 +3114,25 @@ bool InterpretBuiltin(InterpState &S, CodePtr OpPC, const CallExpr *Call,
   case Builtin::BI__builtin_parity:
   case Builtin::BI__builtin_parityl:
   case Builtin::BI__builtin_parityll:
-    return interp__builtin_parity(S, OpPC, Frame, Call);
-
+    return interp__builtin_elementwise_int_unaryop(
+        S, OpPC, Call, [](const APSInt &Val) -> APInt {
+          return APInt(Val.getBitWidth(), Val.popcount() % 2);
+        });
   case Builtin::BI__builtin_clrsb:
   case Builtin::BI__builtin_clrsbl:
   case Builtin::BI__builtin_clrsbll:
-    return interp__builtin_clrsb(S, OpPC, Frame, Call);
-
+    return interp__builtin_elementwise_int_unaryop(
+        S, OpPC, Call, [](const APSInt &Val) -> APInt {
+          return APInt(Val.getBitWidth(),
+                       Val.getBitWidth() - Val.getSignificantBits());
+        });
   case Builtin::BI__builtin_bitreverse8:
   case Builtin::BI__builtin_bitreverse16:
   case Builtin::BI__builtin_bitreverse32:
   case Builtin::BI__builtin_bitreverse64:
-    return interp__builtin_bitreverse(S, OpPC, Frame, Call);
+    return interp__builtin_elementwise_int_unaryop(
+        S, OpPC, Call,
+        [](const APSInt &Val) -> APInt { return Val.reverseBits(); });
 
   case Builtin::BI__builtin_classify_type:
     return interp__builtin_classify_type(S, OpPC, Frame, Call);
@@ -3209,7 +3172,11 @@ bool InterpretBuiltin(InterpState &S, CodePtr OpPC, const CallExpr *Call,
   case Builtin::BI__builtin_ffs:
   case Builtin::BI__builtin_ffsl:
   case Builtin::BI__builtin_ffsll:
-    return interp__builtin_ffs(S, OpPC, Frame, Call);
+    return interp__builtin_elementwise_int_unaryop(
+        S, OpPC, Call, [](const APSInt &Val) {
+          return APInt(Val.getBitWidth(),
+                       Val.isZero() ? 0u : Val.countTrailingZeros() + 1u);
+        });
 
   case Builtin::BIaddressof:
   case Builtin::BI__addressof:
@@ -3494,6 +3461,30 @@ bool InterpretBuiltin(InterpState &S, CodePtr OpPC, const CallExpr *Call,
     return interp__builtin_elementwise_int_binop(S, OpPC, Call,
                                                  llvm::APIntOps::avgCeilU);
 
+  case clang::X86::BI__builtin_ia32_pmaddubsw128:
+  case clang::X86::BI__builtin_ia32_pmaddubsw256:
+  case clang::X86::BI__builtin_ia32_pmaddubsw512:
+    return interp__builtin_ia32_pmul(
+        S, OpPC, Call,
+        [](const APSInt &LoLHS, const APSInt &HiLHS, const APSInt &LoRHS,
+           const APSInt &HiRHS) {
+          unsigned BitWidth = 2 * LoLHS.getBitWidth();
+          return (LoLHS.zext(BitWidth) * LoRHS.sext(BitWidth))
+              .sadd_sat((HiLHS.zext(BitWidth) * HiRHS.sext(BitWidth)));
+        });
+
+  case clang::X86::BI__builtin_ia32_pmaddwd128:
+  case clang::X86::BI__builtin_ia32_pmaddwd256:
+  case clang::X86::BI__builtin_ia32_pmaddwd512:
+    return interp__builtin_ia32_pmul(
+        S, OpPC, Call,
+        [](const APSInt &LoLHS, const APSInt &HiLHS, const APSInt &LoRHS,
+           const APSInt &HiRHS) {
+          unsigned BitWidth = 2 * LoLHS.getBitWidth();
+          return (LoLHS.sext(BitWidth) * LoRHS.sext(BitWidth)) +
+                 (HiLHS.sext(BitWidth) * HiRHS.sext(BitWidth));
+        });
+
   case clang::X86::BI__builtin_ia32_pmulhuw128:
   case clang::X86::BI__builtin_ia32_pmulhuw256:
   case clang::X86::BI__builtin_ia32_pmulhuw512:
@@ -3638,10 +3629,22 @@ bool InterpretBuiltin(InterpState &S, CodePtr OpPC, const CallExpr *Call,
   case clang::X86::BI__builtin_ia32_pmuldq128:
   case clang::X86::BI__builtin_ia32_pmuldq256:
   case clang::X86::BI__builtin_ia32_pmuldq512:
+    return interp__builtin_ia32_pmul(
+        S, OpPC, Call,
+        [](const APSInt &LoLHS, const APSInt &HiLHS, const APSInt &LoRHS,
+           const APSInt &HiRHS) {
+          return llvm::APIntOps::mulsExtended(LoLHS, LoRHS);
+        });
+
   case clang::X86::BI__builtin_ia32_pmuludq128:
   case clang::X86::BI__builtin_ia32_pmuludq256:
   case clang::X86::BI__builtin_ia32_pmuludq512:
-    return interp__builtin_ia32_pmul(S, OpPC, Call, BuiltinID);
+    return interp__builtin_ia32_pmul(
+        S, OpPC, Call,
+        [](const APSInt &LoLHS, const APSInt &HiLHS, const APSInt &LoRHS,
+           const APSInt &HiRHS) {
+          return llvm::APIntOps::muluExtended(LoLHS, LoRHS);
+        });
 
   case Builtin::BI__builtin_elementwise_fma:
     return interp__builtin_elementwise_triop_fp(