[clang][PowerPC] Add flag to enable compatibility with GNU for comple…

…x arguments

Fixes : #56023

https://godbolt.org/z/1bsW1sKMs

newFlag : -fcomplex-ppc-gnu-abi

GNU uses GPRs for complex parameters and return values storing for PowerPC-32bit,
which can be enabled which above flag.
Intent of this patch is to make clang compatible with GNU libraries of complex.

clang/include/clang/Basic/CodeGenOptions.def

@@ -225,6 +225,8 @@ CODEGENOPT(MCDCCoverage , 1, 0) ///< Enable MC/DC code coverage criteria.
 
   /// If -fpcc-struct-return or -freg-struct-return is specified.
 ENUM_CODEGENOPT(StructReturnConvention, StructReturnConventionKind, 2, SRCK_Default)
+  /// If -fcomplex-ppc-gnu-abi is specified on ppc32.
+ENUM_CODEGENOPT(ComplexInRegABI, ComplexArgumentConventionKind, 2, CMPLX_OnStack)
 
 CODEGENOPT(RelaxAll          , 1, 0) ///< Relax all machine code instructions.
 CODEGENOPT(RelaxedAliasing   , 1, 0) ///< Set when -fno-strict-aliasing is enabled.

clang/include/clang/Basic/CodeGenOptions.h

@@ -78,6 +78,12 @@ class CodeGenOptions : public CodeGenOptionsBase {
     SRCK_InRegs    // Small structs in registers (-freg-struct-return).
   };
 
+  enum ComplexArgumentConventionKind {
+    CMPLX_OnStack,
+    CMPLX_InGPR, // If -fcomplex-ppc-gnu-abi is specified on ppc32
+    CMPLX_InFPR
+  };
+
   enum ProfileInstrKind {
     ProfileNone,       // Profile instrumentation is turned off.
     ProfileClangInstr, // Clang instrumentation to generate execution counts

clang/include/clang/Driver/Options.td

@@ -2577,6 +2577,10 @@ def ffp_contract : Joined<["-"], "ffp-contract=">, Group<f_Group>,
   HelpText<"Form fused FP ops (e.g. FMAs)">,
   Values<"fast,on,off,fast-honor-pragmas">;
 
+def fcomplex_ppc_gnu_abi : Flag<["-"], "fcomplex-ppc-gnu-abi">, Group<f_Group>, Visibility<[ClangOption, CC1Option]>,
+  DocBrief<"Follow the GNU ABI, pass Complex values in GPRs instead of the stack for PowerPC-32">,
+  HelpText<"Pass Complex values in GPR instead of stack for PowerPC-32">;
+
 defm strict_float_cast_overflow : BoolFOption<"strict-float-cast-overflow",
   CodeGenOpts<"StrictFloatCastOverflow">, DefaultTrue,
   NegFlag<SetFalse, [], [ClangOption, CC1Option],

clang/lib/CodeGen/Targets/PPC.cpp

@@ -330,8 +330,12 @@ namespace {
 class PPC32_SVR4_ABIInfo : public DefaultABIInfo {
   bool IsSoftFloatABI;
   bool IsRetSmallStructInRegABI;
+  // Size of GPR in bits.
+  static const unsigned RegLen = 32;
+  static const int ArgGPRsNum = 8;
 
   CharUnits getParamTypeAlignment(QualType Ty) const;
+  ABIArgInfo handleComplex(uint64_t &TypeSize) const;
 
 public:
   PPC32_SVR4_ABIInfo(CodeGen::CodeGenTypes &CGT, bool SoftFloatABI,
@@ -340,12 +344,17 @@ class PPC32_SVR4_ABIInfo : public DefaultABIInfo {
         IsRetSmallStructInRegABI(RetSmallStructInRegABI) {}
 
   ABIArgInfo classifyReturnType(QualType RetTy) const;
+  ABIArgInfo classifyArgumentType(QualType Ty, int &ArgGPRsLeft) const;
 
   void computeInfo(CGFunctionInfo &FI) const override {
+
     if (!getCXXABI().classifyReturnType(FI))
       FI.getReturnInfo() = classifyReturnType(FI.getReturnType());
+
+    int ArgGPRsLeft = ArgGPRsNum;
+
     for (auto &I : FI.arguments())
-      I.info = classifyArgumentType(I.type);
+      I.info = classifyArgumentType(I.type, ArgGPRsLeft);
   }
 
   Address EmitVAArg(CodeGenFunction &CGF, Address VAListAddr,
@@ -396,12 +405,80 @@ CharUnits PPC32_SVR4_ABIInfo::getParamTypeAlignment(QualType Ty) const {
   return CharUnits::fromQuantity(4);
 }
 
+ABIArgInfo PPC32_SVR4_ABIInfo::handleComplex(uint64_t &TypeSize) const {
+  llvm::Type *ElemTy;
+  unsigned RegsNeeded; // Registers Needed for Complex.
+
+  // Choice of using llvm::Type::getInt64Ty(getVMContext()) for complex
+  // single-precision floats is based on the ABI ATR-PASS-COMPLEX-IN-GPRS
+  // specification. According to the specification:
+  // - For complex single-precision floats: If the register (gr) is even, it's
+  // incremented by one, and the lower-addressed word of the argument is loaded
+  // into gr, while the higher-addressed word is loaded into gr + 1. Then, gr is
+  // incremented by 2.
+  // - For complex double-precision floats: The words of the argument are loaded
+  // in memory-address order into gr, gr + 1, gr + 2, and gr + 3, with gr being
+  // incremented by 4. Thus, to maintain even alignment and adhere to the ABI
+  // specification, llvm::Type::getInt64Ty(getVMContext()) is used when TypeSize
+  // is 64. Powerpc backend handles this alignment requirement. Specifically,
+  // you can refer to the CC_PPC32_SVR4_Custom_AlignArgRegs method from
+  // PPCCallingconvention.cpp. For more context, refer to the previous
+  // discussion: https://reviews.llvm.org/D146942 and the related LLVM pull
+  // request: #77732
+
+  if (TypeSize == 64) {
+    ElemTy = llvm::Type::getInt64Ty(getVMContext());
+    RegsNeeded = 1;
+  } else {
+    ElemTy = llvm::Type::getInt32Ty(getVMContext());
+    RegsNeeded = TypeSize >> 5;
+  }
+  return ABIArgInfo::getDirect(llvm::ArrayType::get(ElemTy, RegsNeeded));
+}
+
+ABIArgInfo PPC32_SVR4_ABIInfo::classifyArgumentType(QualType Ty,
+                                                    int &ArgGPRsLeft) const {
+  Ty = useFirstFieldIfTransparentUnion(Ty);
+
+  if (!(getCodeGenOpts().getComplexInRegABI() == CodeGenOptions::CMPLX_InGPR) ||
+      !ArgGPRsLeft)
+    return DefaultABIInfo::classifyArgumentType(Ty);
+
+  assert(ArgGPRsLeft >= 0 && "Arg GPR must be large or equal than zero");
+  ASTContext &Context = getContext();
+  uint64_t TypeSize = Context.getTypeSize(Ty);
+
+  if (Ty->isAnyComplexType()) {
+    // If gr is even set gr = gr + 1 for TypeSize=64.
+    if (TypeSize == 64 && ArgGPRsLeft % 2 == 1)
+      --ArgGPRsLeft;
+
+    if (TypeSize <= RegLen * ArgGPRsLeft) {
+      ArgGPRsLeft -= TypeSize / RegLen;
+      return handleComplex(TypeSize);
+    }
+  }
+
+  // Records with non-trivial destructors/copy-constructors should not be
+  // passed by value.
+  if (isAggregateTypeForABI(Ty))
+    --ArgGPRsLeft;
+  else if (!Ty->isFloatingType() || (Ty->isFloatingType() && IsSoftFloatABI)) {
+    // For other primitive types.
+    if (TypeSize == 64 && ArgGPRsLeft % 2 == 1)
+      --ArgGPRsLeft; // If gr is even set gr = gr + 1 for TypeSize=64.
+    if (TypeSize <= ArgGPRsLeft * RegLen)
+      ArgGPRsLeft -= TypeSize / RegLen;
+  }
+
+  return DefaultABIInfo::classifyArgumentType(Ty);
+}
+
 ABIArgInfo PPC32_SVR4_ABIInfo::classifyReturnType(QualType RetTy) const {
-  uint64_t Size;
+  uint64_t Size = getContext().getTypeSize(RetTy);
 
   // -msvr4-struct-return puts small aggregates in GPR3 and GPR4.
-  if (isAggregateTypeForABI(RetTy) && IsRetSmallStructInRegABI &&
-      (Size = getContext().getTypeSize(RetTy)) <= 64) {
+  if (isAggregateTypeForABI(RetTy) && IsRetSmallStructInRegABI && Size <= 64) {
     // System V ABI (1995), page 3-22, specified:
     // > A structure or union whose size is less than or equal to 8 bytes
     // > shall be returned in r3 and r4, as if it were first stored in the
@@ -421,6 +498,10 @@ ABIArgInfo PPC32_SVR4_ABIInfo::classifyReturnType(QualType RetTy) const {
     }
   }
 
+  if ((getCodeGenOpts().getComplexInRegABI() == CodeGenOptions::CMPLX_InGPR) &&
+      RetTy->isAnyComplexType())
+    return handleComplex(Size);
+
   return DefaultABIInfo::classifyReturnType(RetTy);
 }
 
@@ -431,11 +512,12 @@ Address PPC32_SVR4_ABIInfo::EmitVAArg(CodeGenFunction &CGF, Address VAList,
   if (getTarget().getTriple().isOSDarwin()) {
     auto TI = getContext().getTypeInfoInChars(Ty);
     TI.Align = getParamTypeAlignment(Ty);
+    int ArgGPRs = ArgGPRsNum;
 
     CharUnits SlotSize = CharUnits::fromQuantity(4);
     return emitVoidPtrVAArg(CGF, VAList, Ty,
-                            classifyArgumentType(Ty).isIndirect(), TI, SlotSize,
-                            /*AllowHigherAlign=*/true);
+                            classifyArgumentType(Ty, ArgGPRs).isIndirect(), TI,
+                            SlotSize, /*AllowHigherAlign=*/true);
   }
 
   const unsigned OverflowLimit = 8;

clang/lib/Driver/ToolChains/Clang.cpp

@@ -5585,6 +5585,15 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
     }
   }
 
+  if (Arg *A = Args.getLastArg(options::OPT_fcomplex_ppc_gnu_abi)) {
+    if (!TC.getTriple().isPPC32() || !TC.getTriple().isOSBinFormatELF()) {
+      D.Diag(diag::err_drv_unsupported_opt_for_target)
+          << A->getSpelling() << RawTriple.str();
+    } else {
+      CmdArgs.push_back("-fcomplex-ppc-gnu-abi");
+    }
+  }
+
   if (Args.hasFlag(options::OPT_mrtd, options::OPT_mno_rtd, false)) {
     if (Triple.getArch() == llvm::Triple::m68k)
       CmdArgs.push_back("-fdefault-calling-conv=rtdcall");

clang/lib/Frontend/CompilerInvocation.cpp

@@ -1651,6 +1651,10 @@ void CompilerInvocationBase::GenerateCodeGenArgs(const CodeGenOptions &Opts,
     GenerateArg(Consumer, Opt);
   }
 
+  if (T.isPPC32() && Opts.ComplexInRegABI == CodeGenOptions::CMPLX_InGPR) {
+    GenerateArg(Consumer, OPT_fcomplex_ppc_gnu_abi);
+  }
+
   if (Opts.EnableAIXExtendedAltivecABI)
     GenerateArg(Consumer, OPT_mabi_EQ_vec_extabi);
 
@@ -2023,6 +2027,10 @@ bool CompilerInvocation::ParseCodeGenArgs(CodeGenOptions &Opts, ArgList &Args,
     }
   }
 
+  if (Args.getLastArg(OPT_fcomplex_ppc_gnu_abi)) {
+    Opts.setComplexInRegABI(CodeGenOptions::CMPLX_InGPR);
+  }
+
   if (Arg *A = Args.getLastArg(OPT_mxcoff_roptr)) {
     if (!T.isOSAIX())
       Diags.Report(diag::err_drv_unsupported_opt_for_target)