2 files changed, 49 insertions, 1 deletions
diff --git a/clang/lib/AST/ByteCode/InterpBuiltin.cpp b/clang/lib/AST/ByteCode/InterpBuiltin.cpp
index 5f0a77c..b69f360 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*");
@@ -3818,6 +3846,21 @@ bool InterpretBuiltin(InterpState &S, CodePtr OpPC, const CallExpr *Call,
           return F;
         });
 
+  case X86::BI__builtin_ia32_vpmadd52luq128:
+  case X86::BI__builtin_ia32_vpmadd52luq256:
+  case X86::BI__builtin_ia32_vpmadd52luq512:
+    return interp__builtin_elementwise_triop(
+        S, OpPC, Call, [](const APSInt &A, const APSInt &B, const APSInt &C) {
+          return A + (B.trunc(52) * C.trunc(52)).zext(64);
+        });
+  case X86::BI__builtin_ia32_vpmadd52huq128:
+  case X86::BI__builtin_ia32_vpmadd52huq256:
+  case X86::BI__builtin_ia32_vpmadd52huq512:
+    return interp__builtin_elementwise_triop(
+        S, OpPC, Call, [](const APSInt &A, const APSInt &B, const APSInt &C) {
+          return A + llvm::APIntOps::mulhu(B.trunc(52), C.trunc(52)).zext(64);
+        });
+
   case X86::BI__builtin_ia32_vpshldd128:
   case X86::BI__builtin_ia32_vpshldd256:
   case X86::BI__builtin_ia32_vpshldd512:
@@ -3928,6 +3971,11 @@ 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:
diff --git a/clang/lib/AST/ByteCode/InterpState.h b/clang/lib/AST/ByteCode/InterpState.h
index a13244b..e2e4d5c 100644
--- a/clang/lib/AST/ByteCode/InterpState.h
+++ b/clang/lib/AST/ByteCode/InterpState.h
@@ -114,7 +114,7 @@ public:
       Alloc = std::make_unique<DynamicAllocator>();
     }
 
-    return *Alloc.get();
+    return *Alloc;
   }
 
   /// Diagnose any dynamic allocations that haven't been freed yet.