[CIR][X86] Implement lowering for AVX512 mask builtins

clang/lib/CIR/CodeGen/CIRGenBuiltinX86.cpp

@@ -90,6 +90,37 @@ static mlir::Value getMaskVecValue(CIRGenFunction &cgf, const CallExpr *expr,
   return maskVec;
 }
 
+static mlir::Value emitX86MaskAddLogic(CIRGenFunction &cgf,
+                                       const CallExpr *expr,
+                                       const std::string &intrinsicName,
+                                       SmallVectorImpl<mlir::Value> &ops) {
+  CIRGenBuilderTy &builder = cgf.getBuilder();
+  auto intTy = cast<cir::IntType>(ops[0].getType());
+  unsigned numElts = intTy.getWidth();
+  mlir::Value lhsVec = getMaskVecValue(cgf, expr, ops[0], numElts);
+  mlir::Value rhsVec = getMaskVecValue(cgf, expr, ops[1], numElts);
+  mlir::Type vecTy = lhsVec.getType();
+  mlir::Value resVec = emitIntrinsicCallOp(cgf, expr, intrinsicName, vecTy,
+                                           mlir::ValueRange{lhsVec, rhsVec});
+  return builder.createBitcast(resVec, ops[0].getType());
+}
+
+static mlir::Value emitX86MaskLogic(CIRGenFunction &cgf, const CallExpr *expr,
+                                    cir::BinOpKind binOpKind,
+                                    SmallVectorImpl<mlir::Value> &ops,
+                                    bool invertLHS = false) {
+  CIRGenBuilderTy &builder = cgf.getBuilder();
+  unsigned numElts = cast<cir::IntType>(ops[0].getType()).getWidth();
+  mlir::Value lhs = getMaskVecValue(cgf, expr, ops[0], numElts);
+  mlir::Value rhs = getMaskVecValue(cgf, expr, ops[1], numElts);
+
+  if (invertLHS)
+    lhs = builder.createNot(lhs);
+  return builder.createBitcast(
+      builder.createBinop(cgf.getLoc(expr->getExprLoc()), lhs, binOpKind, rhs),
+      ops[0].getType());
+}
+
 mlir::Value CIRGenFunction::emitX86BuiltinExpr(unsigned builtinID,
                                                const CallExpr *expr) {
   if (builtinID == Builtin::BI__builtin_cpu_is) {
@@ -743,38 +774,64 @@ mlir::Value CIRGenFunction::emitX86BuiltinExpr(unsigned builtinID,
   case X86::BI__builtin_ia32_ktestzsi:
   case X86::BI__builtin_ia32_ktestcdi:
   case X86::BI__builtin_ia32_ktestzdi:
+    cgm.errorNYI(expr->getSourceRange(),
+                 std::string("unimplemented X86 builtin call: ") +
+                     getContext().BuiltinInfo.getName(builtinID));
+    return {};
   case X86::BI__builtin_ia32_kaddqi:
+    return emitX86MaskAddLogic(*this, expr, "x86.avx512.kadd.b", ops);
   case X86::BI__builtin_ia32_kaddhi:
+    return emitX86MaskAddLogic(*this, expr, "x86.avx512.kadd.w", ops);
   case X86::BI__builtin_ia32_kaddsi:
+    return emitX86MaskAddLogic(*this, expr, "x86.avx512.kadd.d", ops);
   case X86::BI__builtin_ia32_kadddi:
+    return emitX86MaskAddLogic(*this, expr, "x86.avx512.kadd.q", ops);
   case X86::BI__builtin_ia32_kandqi:
   case X86::BI__builtin_ia32_kandhi:
   case X86::BI__builtin_ia32_kandsi:
   case X86::BI__builtin_ia32_kanddi:
+    return emitX86MaskLogic(*this, expr, cir::BinOpKind::And, ops);
   case X86::BI__builtin_ia32_kandnqi:
   case X86::BI__builtin_ia32_kandnhi:
   case X86::BI__builtin_ia32_kandnsi:
   case X86::BI__builtin_ia32_kandndi:
+    return emitX86MaskLogic(*this, expr, cir::BinOpKind::And, ops, true);
   case X86::BI__builtin_ia32_korqi:
   case X86::BI__builtin_ia32_korhi:
   case X86::BI__builtin_ia32_korsi:
   case X86::BI__builtin_ia32_kordi:
+    return emitX86MaskLogic(*this, expr, cir::BinOpKind::Or, ops);
   case X86::BI__builtin_ia32_kxnorqi:
   case X86::BI__builtin_ia32_kxnorhi:
   case X86::BI__builtin_ia32_kxnorsi:
   case X86::BI__builtin_ia32_kxnordi:
+    return emitX86MaskLogic(*this, expr, cir::BinOpKind::Xor, ops, true);
   case X86::BI__builtin_ia32_kxorqi:
   case X86::BI__builtin_ia32_kxorhi:
   case X86::BI__builtin_ia32_kxorsi:
   case X86::BI__builtin_ia32_kxordi:
+    return emitX86MaskLogic(*this, expr, cir::BinOpKind::Xor, ops);
   case X86::BI__builtin_ia32_knotqi:
   case X86::BI__builtin_ia32_knothi:
   case X86::BI__builtin_ia32_knotsi:
-  case X86::BI__builtin_ia32_knotdi:
+  case X86::BI__builtin_ia32_knotdi: {
+    cir::IntType intTy = cast<cir::IntType>(ops[0].getType());
+    unsigned numElts = intTy.getWidth();
+    mlir::Value resVec = getMaskVecValue(*this, expr, ops[0], numElts);
+    return builder.createBitcast(builder.createNot(resVec), ops[0].getType());
+  }
   case X86::BI__builtin_ia32_kmovb:
   case X86::BI__builtin_ia32_kmovw:
   case X86::BI__builtin_ia32_kmovd:
-  case X86::BI__builtin_ia32_kmovq:
+  case X86::BI__builtin_ia32_kmovq: {
+    // Bitcast to vXi1 type and then back to integer. This gets the mask
+    // register type into the IR, but might be optimized out depending on
+    // what's around it.
+    cir::IntType intTy = cast<cir::IntType>(ops[0].getType());
+    unsigned numElts = intTy.getWidth();
+    mlir::Value resVec = getMaskVecValue(*this, expr, ops[0], numElts);
+    return builder.createBitcast(resVec, ops[0].getType());
+  }
   case X86::BI__builtin_ia32_kunpckdi:
   case X86::BI__builtin_ia32_kunpcksi:
   case X86::BI__builtin_ia32_kunpckhi: