[CLANG] Full support of complex multiplication and division.

clang/docs/UsersManual.rst

@@ -1847,19 +1847,33 @@ floating point semantic models: precise (the default), strict, and fast.
    * ``16`` - Forces ``_Float16`` operations to be emitted without using excess
      precision arithmetic.
 
-.. option:: -fcx-limited-range:
-
-   This option enables the naive mathematical formulas for complex division and
-   multiplication with no NaN checking of results. The default is
-   ``-fno-cx-limited-range``, but this option is enabled by the ``-ffast-math``
-   option.
-
-.. option:: -fcx-fortran-rules:
-
-   This option enables the naive mathematical formulas for complex
-   multiplication and enables application of Smith's algorithm for complex
-   division. See SMITH, R. L. Algorithm 116: Complex division. Commun.
-   ACM 5, 8 (1962). The default is ``-fno-cx-fortran-rules``.
+.. option:: -fcomplex-arithmetic=<value>:
+
+   This option specifies the implementation for complex multiplication and division.
+
+   Valid values are: ``basic``, ``improved``, ``full`` and ``promoted``.
+
+   * ``basic`` Implementation of complex division and multiplication using
+     algebraic formulas at source precision. No special handling to avoid
+     overflow. NaN and infinite and  values are not handled.
+   * ``improved`` Implementation of complex division using the Smith algorithm at
+     source precision. Smith's algorithm for complex division.
+     See SMITH, R. L. Algorithm 116: Complex division. Commun. ACM 5, 8 (1962).
+     This value offers improved handling for overflow in intermediate calculations,
+     but overflow may occur. NaN and infinite and  values are not handled in some
+     cases.
+   * ``full``  Implementation of complex division and multiplication using a
+     call to runtime library functions (generally the case, but the BE might
+     sometimes replace the library call if it knows enough about the potential
+     range of the inputs). Overflow and non-finite values are handled by the
+     library implementation.
+   * ``promoted`` Implementation of complex division using algebraic formulas at
+     higher precision. Overflow is handled. Non-finite values are handled in some
+     cases. If the target hardware does not have native support for a higher precision
+     data type, an implementation for the complex operation will be used to provide
+     improved guards against intermediate overflow, but overflow and underflow may
+     still occur in some cases. NaN and infinite and  values are not handled.
+     This is the default value.
 
 .. _floating-point-environment:
 

clang/include/clang/Basic/LangOptions.h

@@ -396,7 +396,41 @@ class LangOptionsBase {
     IncompleteOnly = 3,
   };
 
-  enum ComplexRangeKind { CX_Full, CX_Limited, CX_Fortran, CX_None };
+  /// Controls the various implementations for complex multiplication and
+  // division.
+  enum ComplexRangeKind {
+    /// Implementation of complex division and multiplication using a call to
+    ///  runtime library functions(generally the case, but the BE might
+    /// sometimes replace the library call if it knows enough about the
+    /// potential range of the inputs). Overflow and non -finite values are
+    /// handled by the library implementation.
+    CX_Full,
+
+    /// Implementation of complex division using the Smith algorithm at
+    /// source precision. Smith's algorithm for complex division.
+    /// See SMITH, R. L. Algorithm 116: Complex division. Commun. ACM 5, 8
+    /// (1962). This value offers improved handling for overflow in intermediate
+    /// calculations, but overflow may occur. NaN and infinite and  values are
+    /// not handled in some cases.
+    CX_Improved,
+
+    /// Implementation of complex division using algebraic formulas at
+    /// higher precision. Overflow is handled. Non-finite values are handled in
+    /// some cases. If the target hardware does not have native support for a
+    /// higher precision data type, an implementation for the complex operation
+    /// will be used to provide improved guards against intermediate overflow,
+    /// but overflow and underflow may still occur in some cases. NaN and
+    /// infinite and  values are not handled. This is the default value.
+    CX_Promoted,
+
+    /// Implementation of complex division and multiplication using
+    /// algebraic formulas at source precision.No special handling to avoid
+    /// overflow.NaN and infinite and values are not handled.
+    CX_Basic,
+
+    /// No range rule is enabled.
+    CX_None
+  };
 
   // Define simple language options (with no accessors).
 #define LANGOPT(Name, Bits, Default, Description) unsigned Name : Bits;

clang/include/clang/Driver/Options.td

@@ -1039,28 +1039,15 @@ defm offload_uniform_block : BoolFOption<"offload-uniform-block",
   NegFlag<SetFalse, [], [ClangOption, CC1Option], "Don't assume">,
   BothFlags<[], [ClangOption], " that kernels are launched with uniform block sizes (default true for CUDA/HIP and false otherwise)">>;
 
-def fcx_limited_range : Joined<["-"], "fcx-limited-range">,
-  Group<f_Group>, Visibility<[ClangOption, CC1Option]>,
-  HelpText<"Basic algebraic expansions of complex arithmetic operations "
-           "involving are enabled.">;
-
-def fno_cx_limited_range : Joined<["-"], "fno-cx-limited-range">,
-  Group<f_Group>, Visibility<[ClangOption, CC1Option]>,
-  HelpText<"Basic algebraic expansions of complex arithmetic operations "
-           "involving are disabled.">;
-
-def fcx_fortran_rules : Joined<["-"], "fcx-fortran-rules">,
-  Group<f_Group>, Visibility<[ClangOption, CC1Option]>,
-  HelpText<"Range reduction is enabled for complex arithmetic operations.">;
-
-def fno_cx_fortran_rules : Joined<["-"], "fno-cx-fortran-rules">,
-  Group<f_Group>, Visibility<[ClangOption, CC1Option]>,
-  HelpText<"Range reduction is disabled for complex arithmetic operations.">;
+def fcomplex_arithmetic_EQ : Joined<["-"], "fcomplex-arithmetic=">, Group<f_Group>,
+  Visibility<[ClangOption, CC1Option]>,
+  Values<"full,improved,promoted,basic">, NormalizedValuesScope<"LangOptions">,
+  NormalizedValues<["CX_Full", "CX_Improved", "CX_Promoted", "CX_Basic"]>;
 
 def complex_range_EQ : Joined<["-"], "complex-range=">, Group<f_Group>,
   Visibility<[CC1Option]>,
-  Values<"full,limited,fortran">, NormalizedValuesScope<"LangOptions">,
-  NormalizedValues<["CX_Full", "CX_Limited", "CX_Fortran"]>,
+  Values<"full,improved,promoted,basic">, NormalizedValuesScope<"LangOptions">,
+  NormalizedValues<["CX_Full", "CX_Improved", "CX_Promoted", "CX_Basic"]>,
   MarshallingInfoEnum<LangOpts<"ComplexRange">, "CX_Full">;
 
 // OpenCL-only Options

clang/lib/CodeGen/CGExprComplex.cpp

@@ -283,9 +283,48 @@ class ComplexExprEmitter
   ComplexPairTy EmitComplexBinOpLibCall(StringRef LibCallName,
                                         const BinOpInfo &Op);
 
-  QualType getPromotionType(QualType Ty) {
+  QualType HigherPrecisionTypeForComplexArithmetic(QualType ElementType,
+                                                   bool IsDivOpCode) {
+    const TargetInfo &TI = CGF.getContext().getTargetInfo();
+    if (const auto *BT = dyn_cast<BuiltinType>(ElementType)) {
+      switch (BT->getKind()) {
+      case BuiltinType::Kind::Float16:
+      case BuiltinType::Kind::BFloat16: {
+        return CGF.getContext().getComplexType(CGF.getContext().FloatTy);
+      }
+      case BuiltinType::Kind::Float:
+        return CGF.getContext().getComplexType(CGF.getContext().DoubleTy);
+      case BuiltinType::Kind::Double:
+        if (TI.hasLongDoubleType()) {
+          return CGF.getContext().getComplexType(CGF.getContext().LongDoubleTy);
+        } else {
+          return QualType();
+        }
+      case BuiltinType::Kind::LongDouble:
+        if (TI.getTriple().isOSLinux()) {
+          if (TI.hasFloat128Type() && !TI.hasLongDoubleType())
+            return CGF.getContext().getComplexType(CGF.getContext().Float128Ty);
+          else
+            return CGF.getContext().getComplexType(
+                CGF.getContext().LongDoubleTy);
+        }
+        if (TI.getTriple().isOSWindows())
+          return CGF.getContext().getComplexType(CGF.getContext().LongDoubleTy);
+      default:
+        return QualType();
+      }
+    }
+    return QualType();
+  }
+
+  QualType getPromotionType(QualType Ty, bool IsDivOpCode = false) {
     if (auto *CT = Ty->getAs<ComplexType>()) {
       QualType ElementType = CT->getElementType();
+      if (IsDivOpCode && ElementType->isFloatingType() &&
+          CGF.getLangOpts().getComplexRange() ==
+              LangOptions::ComplexRangeKind::CX_Promoted)
+        return HigherPrecisionTypeForComplexArithmetic(ElementType,
+                                                       IsDivOpCode);
       if (ElementType.UseExcessPrecision(CGF.getContext()))
         return CGF.getContext().getComplexType(CGF.getContext().FloatTy);
     }
@@ -296,11 +335,12 @@ class ComplexExprEmitter
 
 #define HANDLEBINOP(OP)                                                        \
   ComplexPairTy VisitBin##OP(const BinaryOperator *E) {                        \
-    QualType promotionTy = getPromotionType(E->getType());                     \
+    QualType promotionTy = getPromotionType(                                   \
+        E->getType(),                                                          \
+        (E->getOpcode() == BinaryOperatorKind::BO_Div) ? true : false);        \
     ComplexPairTy result = EmitBin##OP(EmitBinOps(E, promotionTy));            \
     if (!promotionTy.isNull())                                                 \
-      result =                                                                 \
-          CGF.EmitUnPromotedValue(result, E->getType());                       \
+      result = CGF.EmitUnPromotedValue(result, E->getType());                  \
     return result;                                                             \
   }
 
@@ -790,8 +830,9 @@ ComplexPairTy ComplexExprEmitter::EmitBinMul(const BinOpInfo &Op) {
       ResR = Builder.CreateFSub(AC, BD, "mul_r");
       ResI = Builder.CreateFAdd(AD, BC, "mul_i");
 
-      if (Op.FPFeatures.getComplexRange() == LangOptions::CX_Limited ||
-          Op.FPFeatures.getComplexRange() == LangOptions::CX_Fortran)
+      if (Op.FPFeatures.getComplexRange() == LangOptions::CX_Basic ||
+          Op.FPFeatures.getComplexRange() == LangOptions::CX_Improved ||
+          Op.FPFeatures.getComplexRange() == LangOptions::CX_Promoted)
         return ComplexPairTy(ResR, ResI);
 
       // Emit the test for the real part becoming NaN and create a branch to
@@ -982,9 +1023,10 @@ ComplexPairTy ComplexExprEmitter::EmitBinDiv(const BinOpInfo &Op) {
     llvm::Value *OrigLHSi = LHSi;
     if (!LHSi)
       LHSi = llvm::Constant::getNullValue(RHSi->getType());
-    if (Op.FPFeatures.getComplexRange() == LangOptions::CX_Fortran)
+    if (Op.FPFeatures.getComplexRange() == LangOptions::CX_Improved)
       return EmitRangeReductionDiv(LHSr, LHSi, RHSr, RHSi);
-    else if (Op.FPFeatures.getComplexRange() == LangOptions::CX_Limited)
+    else if (Op.FPFeatures.getComplexRange() == LangOptions::CX_Basic ||
+             Op.FPFeatures.getComplexRange() == LangOptions::CX_Promoted)
       return EmitAlgebraicDiv(LHSr, LHSi, RHSr, RHSi);
     else if (!CGF.getLangOpts().FastMath ||
              // '-ffast-math' is used in the command line but followed by an

clang/lib/Driver/ToolChains/Clang.cpp

@@ -2687,45 +2687,42 @@ static void CollectArgsForIntegratedAssembler(Compilation &C,
   }
 }
 
-static StringRef EnumComplexRangeToStr(LangOptions::ComplexRangeKind Range) {
-  StringRef RangeStr = "";
+static std::string ComplexRangeKindToStr(LangOptions::ComplexRangeKind Range) {
   switch (Range) {
-  case LangOptions::ComplexRangeKind::CX_Limited:
-    return "-fcx-limited-range";
+  case LangOptions::ComplexRangeKind::CX_Full:
+    return "full";
     break;
-  case LangOptions::ComplexRangeKind::CX_Fortran:
-    return "-fcx-fortran-rules";
+  case LangOptions::ComplexRangeKind::CX_Basic:
+    return "basic";
     break;
-  default:
-    return RangeStr;
+  case LangOptions::ComplexRangeKind::CX_Improved:
+    return "improved";
+    break;
+  case LangOptions::ComplexRangeKind::CX_Promoted:
+    return "promoted";
     break;
+  default:
+    return "";
   }
 }
 
+static std::string ComplexArithmeticStr(LangOptions::ComplexRangeKind Range) {
+  return "-fcomplex-arithmetic=" + ComplexRangeKindToStr(Range);
+}
+
 static void EmitComplexRangeDiag(const Driver &D,
                                  LangOptions::ComplexRangeKind Range1,
                                  LangOptions::ComplexRangeKind Range2) {
   if (Range1 != Range2 && Range1 != LangOptions::ComplexRangeKind::CX_None)
     D.Diag(clang::diag::warn_drv_overriding_option)
-        << EnumComplexRangeToStr(Range1) << EnumComplexRangeToStr(Range2);
+        << ComplexArithmeticStr(Range1) << ComplexArithmeticStr(Range2);
 }
 
 static std::string
 RenderComplexRangeOption(LangOptions::ComplexRangeKind Range) {
-  std::string ComplexRangeStr = "-complex-range=";
-  switch (Range) {
-  case LangOptions::ComplexRangeKind::CX_Full:
-    ComplexRangeStr += "full";
-    break;
-  case LangOptions::ComplexRangeKind::CX_Limited:
-    ComplexRangeStr += "limited";
-    break;
-  case LangOptions::ComplexRangeKind::CX_Fortran:
-    ComplexRangeStr += "fortran";
-    break;
-  default:
-    assert(0 && "Unexpected range option");
-  }
+  std::string ComplexRangeStr = ComplexRangeKindToStr(Range);
+  if (!ComplexRangeStr.empty())
+    return "-complex-range=" + ComplexRangeStr;
   return ComplexRangeStr;
 }
 
@@ -2794,7 +2791,7 @@ static void RenderFloatingPointOptions(const ToolChain &TC, const Driver &D,
     FPContract = "fast";
     // ffast-math enables limited range rules for complex multiplication and
     // division.
-    Range = LangOptions::ComplexRangeKind::CX_Limited;
+    Range = LangOptions::ComplexRangeKind::CX_Basic;
     SeenUnsafeMathModeOption = true;
   };
 
@@ -2809,24 +2806,24 @@ static void RenderFloatingPointOptions(const ToolChain &TC, const Driver &D,
     switch (optID) {
     default:
       break;
-    case options::OPT_fcx_limited_range: {
-      EmitComplexRangeDiag(D, Range, LangOptions::ComplexRangeKind::CX_Limited);
-      Range = LangOptions::ComplexRangeKind::CX_Limited;
-      break;
-    }
-    case options::OPT_fno_cx_limited_range:
-      EmitComplexRangeDiag(D, Range, LangOptions::ComplexRangeKind::CX_Full);
-      Range = LangOptions::ComplexRangeKind::CX_Full;
-      break;
-    case options::OPT_fcx_fortran_rules: {
-      EmitComplexRangeDiag(D, Range, LangOptions::ComplexRangeKind::CX_Fortran);
-      Range = LangOptions::ComplexRangeKind::CX_Fortran;
+    case options::OPT_fcomplex_arithmetic_EQ: {
+      LangOptions::ComplexRangeKind RangeVal;
+      StringRef Val = A->getValue();
+      if (Val.equals("full"))
+        RangeVal = LangOptions::ComplexRangeKind::CX_Full;
+      else if (Val.equals("improved"))
+        RangeVal = LangOptions::ComplexRangeKind::CX_Improved;
+      else if (Val.equals("promoted"))
+        RangeVal = LangOptions::ComplexRangeKind::CX_Promoted;
+      else if (Val.equals("basic"))
+        RangeVal = LangOptions::ComplexRangeKind::CX_Basic;
+      else
+        D.Diag(diag::err_drv_unsupported_option_argument)
+            << A->getSpelling() << LangOptions::ComplexRangeKind::CX_None;
+      EmitComplexRangeDiag(D, Range, RangeVal);
+      Range = RangeVal;
       break;
     }
-    case options::OPT_fno_cx_fortran_rules:
-      EmitComplexRangeDiag(D, Range, LangOptions::ComplexRangeKind::CX_Full);
-      Range = LangOptions::ComplexRangeKind::CX_Full;
-      break;
     case options::OPT_ffp_model_EQ: {
       // If -ffp-model= is seen, reset to fno-fast-math
       HonorINFs = true;
@@ -3239,16 +3236,12 @@ static void RenderFloatingPointOptions(const ToolChain &TC, const Driver &D,
 
   if (Range != LangOptions::ComplexRangeKind::CX_None)
     ComplexRangeStr = RenderComplexRangeOption(Range);
-  if (!ComplexRangeStr.empty())
+  if (!ComplexRangeStr.empty()) {
     CmdArgs.push_back(Args.MakeArgString(ComplexRangeStr));
-  if (Args.hasArg(options::OPT_fcx_limited_range))
-    CmdArgs.push_back("-fcx-limited-range");
-  if (Args.hasArg(options::OPT_fcx_fortran_rules))
-    CmdArgs.push_back("-fcx-fortran-rules");
-  if (Args.hasArg(options::OPT_fno_cx_limited_range))
-    CmdArgs.push_back("-fno-cx-limited-range");
-  if (Args.hasArg(options::OPT_fno_cx_fortran_rules))
-    CmdArgs.push_back("-fno-cx-fortran-rules");
+    if (Args.hasArg(options::OPT_fcomplex_arithmetic_EQ))
+      CmdArgs.push_back(Args.MakeArgString("-fcomplex-arithmetic=" +
+                                           ComplexRangeKindToStr(Range)));
+  }
 }
 
 static void RenderAnalyzerOptions(const ArgList &Args, ArgStringList &CmdArgs,

clang/lib/Parse/ParsePragma.cpp

@@ -909,15 +909,15 @@ void Parser::HandlePragmaCXLimitedRange() {
   LangOptions::ComplexRangeKind Range;
   switch (OOS) {
   case tok::OOS_ON:
-    Range = LangOptions::CX_Limited;
+    Range = LangOptions::CX_Basic;
     break;
   case tok::OOS_OFF:
     Range = LangOptions::CX_Full;
     break;
   case tok::OOS_DEFAULT:
     // According to ISO C99 standard chapter 7.3.4, the default value
-    // for the pragma is ``off'. -fcx-limited-range and -fcx-fortran-rules
-    // control the default value of these pragmas.
+    // for the pragma is ``off'. -fcomplex-arithmetic controls the default value
+    // of these pragmas.
     Range = getLangOpts().getComplexRange();
     break;
   }

clang/test/CodeGen/complex-math.c

@@ -5,7 +5,7 @@
 // RUN: %clang_cc1 %s -O0 -emit-llvm -triple armv7-none-linux-gnueabi -o - | FileCheck %s --check-prefix=ARM
 // RUN: %clang_cc1 %s -O0 -emit-llvm -triple armv7-none-linux-gnueabihf -o - | FileCheck %s --check-prefix=ARMHF
 // RUN: %clang_cc1 %s -O0 -emit-llvm -triple thumbv7k-apple-watchos2.0 -o - -target-abi aapcs16 | FileCheck %s --check-prefix=ARM7K
-// RUN: %clang_cc1 %s -O0 -emit-llvm -triple aarch64-unknown-unknown -ffast-math -ffp-contract=fast -complex-range=fortran -o - | FileCheck %s --check-prefix=AARCH64-FASTMATH
+// RUN: %clang_cc1 %s -O0 -emit-llvm -triple aarch64-unknown-unknown -ffast-math -ffp-contract=fast -complex-range=improved -o - | FileCheck %s --check-prefix=AARCH64-FASTMATH
 // RUN: %clang_cc1 %s -O0 -emit-llvm -triple spir -o - | FileCheck %s --check-prefix=SPIR
 
 float _Complex add_float_rr(float a, float b) {