Add sign/zero extend

[rkotler]

Summary

Add code which does sign/zero extend.

[rkotler]

Here is an executable test case:

[rkotler]

loadstoreconv.cpp811 BDownload

[dsanders]

I've tried to ignore the bits that aren't supposed to be in this patch but it's possible I've ignored something important. Could you refresh the patch without the noise?

Please make it clear in the summary (and the title) that this is for MIPS FastISel? It won't be obvious to others when you come to commit

Is the testcase loadstoreconv.ll? I think there should also be a simpler test case that is just sign/zero extension by itself.

lib/Target/Mips/MipsFastISel.cpp

90–94

Indentation nit.

249–250

Both signed and zero extensions are supported.

The function name and implementation suggests that only sign extensions are supported. Zero extensions are in EmitIntZExt()

347–348

The same is true for MIPS and the code below looks right but the comment references ARM.

You'll need to run clang-format on the code though

[dsanders]

Is the testcase loadstoreconv.ll?

Disregard this, the test plan said it is. I still think a sign/zero extend only test is sensible though.

[rkotler]

• refresh patch
• add test case

[rkotler]

loadstoreconv.cpp811 BDownload

Executable test case. You can run this and compare results against it being run on x86.

lib/Target/Mips/MipsFastISel.cpp

 private:
   bool EmitLoad(MVT VT, unsigned &ResultReg, Address &Addr,
                 unsigned Alignment = 0);
   bool EmitStore(MVT VT, unsigned SrcReg, Address &Addr,
                  unsigned Alignment = 0);
   bool SelectLoad(const Instruction *I);
   bool SelectRet(const Instruction *I);
   bool SelectStore(const Instruction *I);
+  bool SelectIntExt(const Instruction *I);
+  bool SelectTrunc(const Instruction *I);
 
   bool isTypeLegal(Type *Ty, MVT &VT);
   bool isLoadTypeLegal(Type *Ty, MVT &VT);
 
   unsigned MaterializeFP(const ConstantFP *CFP, MVT VT);
   unsigned MaterializeGV(const GlobalValue *GV, MVT VT);
   unsigned MaterializeInt(const Constant *C, MVT VT);
   unsigned Materialize32BitInt(int64_t Imm, const TargetRegisterClass *RC);
 
+  bool EmitIntZExt(MVT SrcVT, unsigned SrcReg, MVT DestVT, unsigned DestReg);
+
+  bool EmitIntSExt(MVT SrcVT, unsigned SrcReg, MVT DestVT, unsigned DestReg);
+
   // for some reason, this default is not generated by tablegen
   // so we explicitly generate it here.
   //
   unsigned FastEmitInst_riir(uint64_t inst, const TargetRegisterClass *RC,
                              unsigned Op0, bool Op0IsKill, uint64_t imm1,
                              uint64_t imm2, unsigned Op3, bool Op3IsKill) {
     return 0;
   }
 
   MachineInstrBuilder EmitInst(unsigned Opc) {
     return BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(Opc));
   }
 
   MachineInstrBuilder EmitInst(unsigned Opc, unsigned DstReg) {
     return BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DbgLoc, TII.get(Opc),
                    DstReg);
   }
 
   MachineInstrBuilder EmitInstStore(unsigned Opc, unsigned SrcReg,
                                     unsigned MemReg, int64_t MemOffset) {
     return EmitInst(Opc).addReg(SrcReg).addReg(MemReg).addImm(MemOffset);
   }
 
   MachineInstrBuilder EmitInstLoad(unsigned Opc, unsigned DstReg,
-                                      unsigned MemReg, int64_t MemOffset) {
     return EmitInst(Opc, DstReg).addReg(MemReg).addImm(MemOffset);
   }
 
 #include "MipsGenFastISel.inc"
 };
 
 bool MipsFastISel::isTypeLegal(Type *Ty, MVT &VT) {
   EVT evt = TLI.getValueType(Ty, true);
case MVT::f64:
     break;
   default:
     return false;
   }
   EmitInstStore(Opc, SrcReg, Addr.Base.Reg, Addr.Offset);
   return true;
 }
 
+bool MipsFastISel::EmitIntSExt(MVT SrcVT, unsigned SrcReg, MVT DestVT,
+                               unsigned DestReg) {
+  if ((DestVT != MVT::i32) && (DestVT != MVT::i16))
+    return false;
+  switch (SrcVT.SimpleTy) {
+  default:
+    return false;
+  case MVT::i8:
+    EmitInst(Mips::SEB, DestReg).addReg(SrcReg);
+    break;
+  case MVT::i16:
+    EmitInst(Mips::SEH, DestReg).addReg(SrcReg);
+    break;
+  }
+  return true;
+}
+
+bool MipsFastISel::EmitIntZExt(MVT SrcVT, unsigned SrcReg, MVT DestVT,
+                               unsigned DestReg) {
+  switch (SrcVT.SimpleTy) {
+  default:
+    return false;
+  case MVT::i1:
+    EmitInst(Mips::ANDi, DestReg).addReg(SrcReg).addImm(1);
+    break;
+  case MVT::i8:
+    EmitInst(Mips::ANDi, DestReg).addReg(SrcReg).addImm(0xff);
+    break;
+  case MVT::i16:
+    EmitInst(Mips::ANDi, DestReg).addReg(SrcReg).addImm(0xffff);
+    break;
+  }
+  return true;
+}
+
 bool MipsFastISel::SelectLoad(const Instruction *I) {
   // Atomic loads need special handling.
   if (cast<LoadInst>(I)->isAtomic())
     return false;
 
   // Verify we have a legal type before going any further.
   MVT VT;
   if (!isLoadTypeLegal(I->getType(), VT))
if (!FuncInfo.CanLowerReturn)
     return false;
   if (Ret->getNumOperands() > 0) {
     return false;
   }
   EmitInst(Mips::RetRA);
   return true;
 }
 
+bool MipsFastISel::SelectIntExt(const Instruction *I) {
+  Type *DestTy = I->getType();
+  Value *Src = I->getOperand(0);
+  Type *SrcTy = Src->getType();
+
+  bool isZExt = isa<ZExtInst>(I);
+  unsigned SrcReg = getRegForValue(Src);
+  if (!SrcReg)
+    return false;
+
+  EVT SrcEVT, DestEVT;
+  SrcEVT = TLI.getValueType(SrcTy, true);
+  DestEVT = TLI.getValueType(DestTy, true);
+  if (!SrcEVT.isSimple())
+    return false;
+  if (!DestEVT.isSimple())
+    return false;
+
+  MVT SrcVT = SrcEVT.getSimpleVT();
+  MVT DestVT = DestEVT.getSimpleVT();
+  unsigned ResultReg = createResultReg(&Mips::GPR32RegClass);
+
+  if (isZExt) {
+    if (!EmitIntZExt(SrcVT, SrcReg, DestVT, ResultReg))
+      return false;
+  } else {
+    if (!EmitIntSExt(SrcVT, SrcReg, DestVT, ResultReg))
+      return false;
+  }
+  UpdateValueMap(I, ResultReg);
+  return true;
+}
+
+bool MipsFastISel::SelectTrunc(const Instruction *I) {
+  // The high bits for a type smaller than the register size are assumed to be
+  // undefined.
+  Value *Op = I->getOperand(0);
+
+  EVT SrcVT, DestVT;
+  SrcVT = TLI.getValueType(Op->getType(), true);
+  DestVT = TLI.getValueType(I->getType(), true);
+
+  if (SrcVT != MVT::i32 && SrcVT != MVT::i16 && SrcVT != MVT::i8)
+    return false;
+  if (DestVT != MVT::i16 && DestVT != MVT::i8 && DestVT != MVT::i1)
+    return false;
+
+  unsigned SrcReg = getRegForValue(Op);
+  if (!SrcReg)
+    return false;
+
+  // Because the high bits are undefined, a truncate doesn't generate
+  // any code.
+  UpdateValueMap(I, SrcReg);
+  return true;
+}
+
 bool MipsFastISel::TargetSelectInstruction(const Instruction *I) {
   if (!TargetSupported)
     return false;
   switch (I->getOpcode()) {
   default:
     break;
   case Instruction::Load:
     return SelectLoad(I);
   case Instruction::Store:
     return SelectStore(I);
   case Instruction::Ret:
     return SelectRet(I);
+  case Instruction::Trunc:
+    return SelectTrunc(I);
+  case Instruction::ZExt:
+  case Instruction::SExt:
+    return SelectIntExt(I);
   }
   return false;
 }
 }
 
 unsigned MipsFastISel::MaterializeFP(const ConstantFP *CFP, MVT VT) {
   int64_t Imm = CFP->getValueAPF().bitcastToAPInt().getZExtValue();
   if (VT == MVT::f32) {

test/CodeGen/Mips/Fast-ISel/loadstoreconv.ll

+; RUN: llc -march=mipsel -relocation-model=pic -O0 -mips-fast-isel -fast-isel-abort -mcpu=mips32r2 \
+; RUN:     < %s | FileCheck %s
+
+@b2 = global i8 0, align 1
+@b1 = global i8 1, align 1
+@uc1 = global i8 0, align 1
+@uc2 = global i8 -1, align 1
+@sc1 = global i8 -128, align 1
+@sc2 = global i8 127, align 1
+@ss1 = global i16 -32768, align 2
+@ss2 = global i16 32767, align 2
+@us1 = global i16 0, align 2
+@us2 = global i16 -1, align 2
+@ssi = global i16 0, align 2
+@ssj = global i16 0, align 2
+@i = global i32 0, align 4
+@j = global i32 0, align 4
+@.str = private unnamed_addr constant [4 x i8] c"%i\0A\00", align 1
+@.str1 = private unnamed_addr constant [7 x i8] c"%i %i\0A\00", align 1
+
+; Function Attrs: nounwind
+define void @_Z3b_iv() #0 {
+entry:
+; CHECK:  .ent  _Z3b_iv
+  %0 = load i8* @b1, align 1
+  %tobool = trunc i8 %0 to i1
+  %frombool = zext i1 %tobool to i8
+  store i8 %frombool, i8* @b2, align 1
+  %1 = load i8* @b2, align 1
+  %tobool1 = trunc i8 %1 to i1
+  %conv = zext i1 %tobool1 to i32
+  store i32 %conv, i32* @i, align 4
+; CHECK:  lbu ${{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:  andi  ${{[0-9]+}}, ${{[0-9]+}}, 1
+; CHECK:  sb  ${{[0-9]+}}, 0(${{[0-9]+}})
+
+
+
+  ret void
+; CHECK:  .end  _Z3b_iv
+}
+
+; Function Attrs: nounwind
+define void @_Z4uc_iv() #0 {
+entry:
+; CHECK:  .ent  _Z4uc_iv
+
+  %0 = load i8* @uc1, align 1
+  %conv = zext i8 %0 to i32
+  store i32 %conv, i32* @i, align 4
+  %1 = load i8* @uc2, align 1
+  %conv1 = zext i8 %1 to i32
+; CHECK:  lbu ${{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:  andi  ${{[0-9]+}}, ${{[0-9]+}}, 255
+
+  store i32 %conv1, i32* @j, align 4
+  ret void
+; CHECK:  .end  _Z4uc_iv
+
+}
+
+; Function Attrs: nounwind
+define void @_Z4sc_iv() #0 {
+entry:
+; CHECK:  .ent  _Z4sc_iv
+
+  %0 = load i8* @sc1, align 1
+  %conv = sext i8 %0 to i32
+  store i32 %conv, i32* @i, align 4
+  %1 = load i8* @sc2, align 1
+  %conv1 = sext i8 %1 to i32
+  store i32 %conv1, i32* @j, align 4
+; CHECK:  lbu ${{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:  seb ${{[0-9]+}}, ${{[0-9]+}}
+
+  ret void
+; CHECK:  .end  _Z4sc_iv
+}
+
+; Function Attrs: nounwind
+define void @_Z4us_iv() #0 {
+entry:
+; CHECK:  .ent  _Z4us_iv
+  %0 = load i16* @us1, align 2
+  %conv = zext i16 %0 to i32
+  store i32 %conv, i32* @i, align 4
+  %1 = load i16* @us2, align 2
+  %conv1 = zext i16 %1 to i32
+  store i32 %conv1, i32* @j, align 4
+  ret void
+; CHECK:  lhu ${{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:  andi  ${{[0-9]+}}, ${{[0-9]+}}, 65535
+; CHECK:  .end  _Z4us_iv
+}
+
+; Function Attrs: nounwind
+define void @_Z4ss_iv() #0 {
+entry:
+; CHECK:  .ent  _Z4ss_iv
+
+  %0 = load i16* @ss1, align 2
+  %conv = sext i16 %0 to i32
+  store i32 %conv, i32* @i, align 4
+  %1 = load i16* @ss2, align 2
+  %conv1 = sext i16 %1 to i32
+  store i32 %conv1, i32* @j, align 4
+; CHECK:  lhu ${{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:  seh ${{[0-9]+}}, ${{[0-9]+}}
+
+  ret void
+; CHECK:  .end  _Z4ss_iv
+}
+
+; Function Attrs: nounwind
+define void @_Z4b_ssv() #0 {
+entry:
+; CHECK:  .ent  _Z4b_ssv
+  %0 = load i8* @b2, align 1
+  %tobool = trunc i8 %0 to i1
+  %conv = zext i1 %tobool to i16
+  store i16 %conv, i16* @ssi, align 2
+  ret void
+; CHECK:  lbu ${{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:  andi  ${{[0-9]+}}, ${{[0-9]+}}, 1
+; CHECK:  .end  _Z4b_ssv
+}
+
+; Function Attrs: nounwind
+define void @_Z5uc_ssv() #0 {
+entry:
+; CHECK:  .ent  _Z5uc_ssv
+  %0 = load i8* @uc1, align 1
+  %conv = zext i8 %0 to i16
+  store i16 %conv, i16* @ssi, align 2
+  %1 = load i8* @uc2, align 1
+  %conv1 = zext i8 %1 to i16
+; CHECK:  lbu ${{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:  andi  ${{[0-9]+}}, ${{[0-9]+}}, 255
+
+  store i16 %conv1, i16* @ssj, align 2
+  ret void
+; CHECK:  .end  _Z5uc_ssv
+}
+
+; Function Attrs: nounwind
+define void @_Z5sc_ssv() #0 {
+entry:
+; CHECK:  .ent  _Z5sc_ssv
+  %0 = load i8* @sc1, align 1
+  %conv = sext i8 %0 to i16
+  store i16 %conv, i16* @ssi, align 2
+  %1 = load i8* @sc2, align 1
+  %conv1 = sext i8 %1 to i16
+  store i16 %conv1, i16* @ssj, align 2
+; CHECK:  lbu ${{[0-9]+}}, 0(${{[0-9]+}})
+; CHECK:  seb ${{[0-9]+}}, ${{[0-9]+}}
+
+  ret void
+; CHECK:  .end  _Z5sc_ssv
+}
+
+declare i32 @printf(i8*, ...) #1
+
+attributes #0 = { nounwind "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
+attributes #1 = { "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
+