[Power PC] llvm soft float support for ppc32

[spetrovic]

Summary

This is is second in set of patches for soft float support for ppc32, it enables soft float operations. This patch depends on previuos patch ( http://reviews.llvm.org/D13351 ).

[hfinkel]

lib/Target/PowerPC/PPCISelLowering.cpp

71 ↗

(On Diff #37245)

Add a space after 'if'

2948 ↗

(On Diff #37245)

Add a space after 'if'

lib/Target/PowerPC/PPCTargetMachine.cpp

235 ↗

(On Diff #37245)

You've copied this code from the ARM and/or X86 targets, but did not copy the associated FIXME comment above it. Please copy the associated FIXME comment as well.

test/CodeGen/PowerPC/ppcsoftops.ll

50 ↗

(On Diff #37245)

Please remove unnecessary attributes.

[spetrovic]

Comments addressed.

[spetrovic]

ping

[hfinkel]

LGTM.

llvm/trunk/lib/Target/PowerPC/PPC.td

 def DirectivePwr5x: SubtargetFeature<"", "DarwinDirective", "PPC::DIR_PWR5X", "">;
 def DirectivePwr6: SubtargetFeature<"", "DarwinDirective", "PPC::DIR_PWR6", "">;
 def DirectivePwr6x: SubtargetFeature<"", "DarwinDirective", "PPC::DIR_PWR6X", "">;
 def DirectivePwr7: SubtargetFeature<"", "DarwinDirective", "PPC::DIR_PWR7", "">;
 def DirectivePwr8: SubtargetFeature<"", "DarwinDirective", "PPC::DIR_PWR8", "">;
 
 def Feature64Bit     : SubtargetFeature<"64bit","Has64BitSupport", "true",
                                         "Enable 64-bit instructions">;
+def FeatureSoftFloat : SubtargetFeature<"soft-float", "UseSoftFloat", "true",
+                              "Use software emulation for floating point">;                                        
 def Feature64BitRegs : SubtargetFeature<"64bitregs","Use64BitRegs", "true",
                               "Enable 64-bit registers usage for ppc32 [beta]">;
 def FeatureCRBits    : SubtargetFeature<"crbits", "UseCRBits", "true",
                               "Use condition-register bits individually">;
 def FeatureAltivec   : SubtargetFeature<"altivec","HasAltivec", "true",
                                         "Enable Altivec instructions">;
 def FeatureSPE       : SubtargetFeature<"spe","HasSPE", "true",
                                         "Enable SPE instructions">;

llvm/trunk/lib/Target/PowerPC/PPCISelLowering.h

namespace llvm {
   public:
     explicit PPCTargetLowering(const PPCTargetMachine &TM,
                                const PPCSubtarget &STI);
 
     /// getTargetNodeName() - This method returns the name of a target specific
     /// DAG node.
     const char *getTargetNodeName(unsigned Opcode) const override;
 
+    bool useSoftFloat() const override;
+
     MVT getScalarShiftAmountTy(const DataLayout &, EVT) const override {
       return MVT::i32;
     }
 
     bool isCheapToSpeculateCttz() const override {
       return true;
     }
 

llvm/trunk/lib/Target/PowerPC/PPCISelLowering.cpp

 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/ErrorHandling.h"
 #include "llvm/Support/MathExtras.h"
 #include "llvm/Support/raw_ostream.h"
 #include "llvm/Target/TargetOptions.h"
 
 using namespace llvm;
 
-// FIXME: Remove this once soft-float is supported.
-static cl::opt<bool> DisablePPCFloatInVariadic("disable-ppc-float-in-variadic",
-cl::desc("disable saving float registers for va_start on PPC"), cl::Hidden);
-
 static cl::opt<bool> DisablePPCPreinc("disable-ppc-preinc",
 cl::desc("disable preincrement load/store generation on PPC"), cl::Hidden);
 
 static cl::opt<bool> DisableILPPref("disable-ppc-ilp-pref",
 cl::desc("disable setting the node scheduling preference to ILP on PPC"), cl::Hidden);
 
 static cl::opt<bool> DisablePPCUnaligned("disable-ppc-unaligned",
 cl::desc("disable unaligned load/store generation on PPC"), cl::Hidden);
PPCTargetLowering::PPCTargetLowering(const PPCTargetMachine &TM,
 
   // On PPC32/64, arguments smaller than 4/8 bytes are extended, so all
   // arguments are at least 4/8 bytes aligned.
   bool isPPC64 = Subtarget.isPPC64();
   setMinStackArgumentAlignment(isPPC64 ? 8:4);
 
   // Set up the register classes.
   addRegisterClass(MVT::i32, &PPC::GPRCRegClass);
+  if (!Subtarget.useSoftFloat()) {
     addRegisterClass(MVT::f32, &PPC::F4RCRegClass);
     addRegisterClass(MVT::f64, &PPC::F8RCRegClass);
+  }
 
   // PowerPC has an i16 but no i8 (or i1) SEXTLOAD
   for (MVT VT : MVT::integer_valuetypes()) {
     setLoadExtAction(ISD::SEXTLOAD, VT, MVT::i1, Promote);
     setLoadExtAction(ISD::SEXTLOAD, VT, MVT::i8, Expand);
   }
 
   setTruncStoreAction(MVT::f64, MVT::f32, Expand);
unsigned PPCTargetLowering::getByValTypeAlignment(Type *Ty,
   // 16byte and wider vectors are passed on 16byte boundary.
   // The rest is 8 on PPC64 and 4 on PPC32 boundary.
   unsigned Align = Subtarget.isPPC64() ? 8 : 4;
   if (Subtarget.hasAltivec() || Subtarget.hasQPX())
     getMaxByValAlign(Ty, Align, Subtarget.hasQPX() ? 32 : 16);
   return Align;
 }
 
+bool PPCTargetLowering::useSoftFloat() const {
+  return Subtarget.useSoftFloat();
+}
+
 const char *PPCTargetLowering::getTargetNodeName(unsigned Opcode) const {
   switch ((PPCISD::NodeType)Opcode) {
   case PPCISD::FIRST_NUMBER:    break;
   case PPCISD::FSEL:            return "PPCISD::FSEL";
   case PPCISD::FCFID:           return "PPCISD::FCFID";
   case PPCISD::FCFIDU:          return "PPCISD::FCFIDU";
   case PPCISD::FCFIDS:          return "PPCISD::FCFIDS";
   case PPCISD::FCFIDUS:         return "PPCISD::FCFIDUS";
if (isVarArg) {
     };
     const unsigned NumGPArgRegs = array_lengthof(GPArgRegs);
 
     static const MCPhysReg FPArgRegs[] = {
       PPC::F1, PPC::F2, PPC::F3, PPC::F4, PPC::F5, PPC::F6, PPC::F7,
       PPC::F8
     };
     unsigned NumFPArgRegs = array_lengthof(FPArgRegs);
-    if (DisablePPCFloatInVariadic)
+
+    if (Subtarget.useSoftFloat())
        NumFPArgRegs = 0;
 
     FuncInfo->setVarArgsNumGPR(CCInfo.getFirstUnallocated(GPArgRegs));
     FuncInfo->setVarArgsNumFPR(CCInfo.getFirstUnallocated(FPArgRegs));
 
     // Make room for NumGPArgRegs and NumFPArgRegs.
     int Depth = NumGPArgRegs * PtrVT.getSizeInBits()/8 +
                 NumFPArgRegs * MVT(MVT::f64).getSizeInBits()/8;
 

llvm/trunk/lib/Target/PowerPC/PPCSubtarget.h

protected:
   /// Which cpu directive was used.
   unsigned DarwinDirective;
 
   /// Used by the ISel to turn in optimizations for POWER4-derived architectures
   bool HasMFOCRF;
   bool Has64BitSupport;
   bool Use64BitRegs;
   bool UseCRBits;
+  bool UseSoftFloat;
   bool IsPPC64;
   bool HasAltivec;
   bool HasSPE;
   bool HasQPX;
   bool HasVSX;
   bool HasP8Vector;
   bool HasP8Altivec;
   bool HasP8Crypto;

 public:
   /// isPPC64 - Return true if we are generating code for 64-bit pointer mode.
   ///
   bool isPPC64() const;
 
   /// has64BitSupport - Return true if the selected CPU supports 64-bit
   /// instructions, regardless of whether we are in 32-bit or 64-bit mode.
   bool has64BitSupport() const { return Has64BitSupport; }
+  // useSoftFloat - Return true if soft-float option is turned on.
+  bool useSoftFloat() const { return UseSoftFloat; }
 
   /// use64BitRegs - Return true if in 64-bit mode or if we should use 64-bit
   /// registers in 32-bit mode when possible.  This can only true if
   /// has64BitSupport() returns true.
   bool use64BitRegs() const { return Use64BitRegs; }
 
   /// useCRBits - Return true if we should store and manipulate i1 values in
   /// the individual condition register bits.

llvm/trunk/lib/Target/PowerPC/PPCSubtarget.cpp

 
 void PPCSubtarget::initializeEnvironment() {
   StackAlignment = 16;
   DarwinDirective = PPC::DIR_NONE;
   HasMFOCRF = false;
   Has64BitSupport = false;
   Use64BitRegs = false;
   UseCRBits = false;
+  UseSoftFloat = false;
   HasAltivec = false;
   HasSPE = false;
   HasQPX = false;
   HasVSX = false;
   HasP8Vector = false;
   HasP8Altivec = false;
   HasP8Crypto = false;
   HasFCPSGN = false;

llvm/trunk/lib/Target/PowerPC/PPCTargetMachine.cpp

PPCTargetMachine::getSubtargetImpl(const Function &F) const {
 
   std::string CPU = !CPUAttr.hasAttribute(Attribute::None)
                         ? CPUAttr.getValueAsString().str()
                         : TargetCPU;
   std::string FS = !FSAttr.hasAttribute(Attribute::None)
                        ? FSAttr.getValueAsString().str()
                        : TargetFS;
 
+  // FIXME: This is related to the code below to reset the target options,
+  // we need to know whether or not the soft float flag is set on the
+  // function before we can generate a subtarget. We also need to use
+  // it as a key for the subtarget since that can be the only difference
+  // between two functions.
+  bool SoftFloat =
+    F.hasFnAttribute("use-soft-float") &&
+    F.getFnAttribute("use-soft-float").getValueAsString() == "true";
+  // If the soft float attribute is set on the function turn on the soft float
+  // subtarget feature.
+  if (SoftFloat)
+    FS += FS.empty() ? "+soft-float" : ",+soft-float";
+
   auto &I = SubtargetMap[CPU + FS];
   if (!I) {
     // This needs to be done before we create a new subtarget since any
     // creation will depend on the TM and the code generation flags on the
     // function that reside in TargetOptions.
     resetTargetOptions(F);
     I = llvm::make_unique<PPCSubtarget>(
         TargetTriple, CPU,

llvm/trunk/test/CodeGen/PowerPC/ppcsoftops.ll

+; RUN: llc  -mtriple=powerpc-unknown-linux-gnu -O0 < %s | FileCheck %s
+define double @foo() #0 {
+entry:
+  %a = alloca double, align 8
+  %b = alloca double, align 8
+  %0 = load double, double* %a, align 8
+  %1 = load double, double* %b, align 8
+  %add = fadd double %0, %1
+  ret double %add
+
+  ; CHECK-LABEL:      __adddf3
+}
+
+define double @foo1() #0 {
+entry:
+  %a = alloca double, align 8
+  %b = alloca double, align 8
+  %0 = load double, double* %a, align 8
+  %1 = load double, double* %b, align 8
+  %mul = fmul double %0, %1
+  ret double %mul
+
+  ; CHECK-LABEL:      __muldf3
+}
+
+define double @foo2() #0 {
+entry:
+  %a = alloca double, align 8
+  %b = alloca double, align 8
+  %0 = load double, double* %a, align 8
+  %1 = load double, double* %b, align 8
+  %sub = fsub double %0, %1
+  ret double %sub
+
+  ; CHECK-LABEL:      __subdf3
+}
+
+define double @foo3() #0 {
+entry:
+  %a = alloca double, align 8
+  %b = alloca double, align 8
+  %0 = load double, double* %a, align 8
+  %1 = load double, double* %b, align 8
+  %div = fdiv double %0, %1
+  ret double %div
+
+  ; CHECK-LABEL:      __divdf3
+}
+
+attributes #0 = {"use-soft-float"="true" }