Add numeric extend, trunctate to mips fast-isel

[rkotler]

Summary

Add numeric extend, trunctate to mips fast-isel

Reactivates D4827

[rkotler]

• Merge branch 'master' into reed-bug-04
• in progress
• Merge branch 'fast-isel-16' into reed-bug-04
• Merge branch 'master' into reed-bug-04
• in progress
• in progress
• in progress
• Merge branch 'master' into reed-bug-04
• test update
• test update
• test update
• test update
• format
• format

1. Updating D5251: Add numeric extend, trunctate to mips fast-isel #
2. Enter a brief description of the changes included in this update.
3. The first line is used as subject, next lines as comment. #
4. If you intended to create a new revision, use:
5. $ arc diff --create

Update patch to handler Mips32/r1

[rkotler]

• make sure test for mips32r1

1. Updating D5251: Add numeric extend, trunctate to mips fast-isel #
2. Enter a brief description of the changes included in this update.
3. The first line is used as subject, next lines as comment. #
4. If you intended to create a new revision, use:
5. $ arc diff --create

Add an extra test for mips32r1

[dsanders]

It will LGTM with a nit, the CHECK-LABEL change, and mcrosiers review comments from the original review (D4827) handled.

There's one additional change from the original review that I'd like you to make but it's no longer a hard requirement.

Add numeric extend, trunctate to mips fast-isel

Reactivates D4827

Will be updating patch to fix issues previously reported.

Just a quick reminder that 'arc commit' will use this text as-is in the commit message. You'll need to edit the revision to drop the last two lines of the summary or commit with svn.

On a similar note, you seem to have arcanist instructions in the description of your two updates.

lib/Target/Mips/MipsFastISel.cpp

257–267

Per my original comments in D4827, I'd prefer this to be calculated rather than special cased for each type. However, you've handled the most important point of those comments (MIPS32r1 support) so while I'd appreciate it using 'ShiftAmt = GPRSize - SrcVT.getSizeInBits()' and a separate if-statement. I'm not going to make that a hard requirement.

Likewise for the ZExt cases.

295–296

Coding standard nit: return after else.

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

31

Copy/pasted from D4827:
Use CHECK-LABEL so that FileCheck divides the file into independent sections. Likewise for the other function labels below.

[rkotler]

• make suggested changes. still need to run test-suite before commit

[rkotler]

• clang format

1. Updating D5251: Add numeric extend, trunctate to mips fast-isel #

reformat MipsFastISel.cpp using clang format

[rkotler]

Closed by commit rL218681 (authored by @rkotler).

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 SelectFPExt(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);
+  bool EmitIntSExt32r1(MVT SrcVT, unsigned SrcReg, MVT DestVT,
+                       unsigned DestReg);
+  bool EmitIntSExt32r2(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;
   }
case MVT::f64:
     break;
   default:
     return false;
   }
   EmitInstStore(Opc, SrcReg, Addr.Base.Reg, Addr.Offset);
   return true;
 }
 
+bool MipsFastISel::EmitIntSExt32r1(MVT SrcVT, unsigned SrcReg, MVT DestVT,
+                                   unsigned DestReg) {
+  unsigned ShiftAmt;
+  switch (SrcVT.SimpleTy) {
+  default:
+    return false;
+  case MVT::i8:
+    ShiftAmt = 24;
+    break;
+  case MVT::i16:
+    ShiftAmt = 16;
+    break;
+  }
+  unsigned TempReg = createResultReg(&Mips::GPR32RegClass);
+  EmitInst(Mips::SLL, TempReg).addReg(SrcReg).addImm(ShiftAmt);
+  EmitInst(Mips::SRA, DestReg).addReg(TempReg).addImm(ShiftAmt);
+  return true;
+}
+
+bool MipsFastISel::EmitIntSExt32r2(MVT SrcVT, unsigned SrcReg, MVT DestVT,
+                                   unsigned DestReg) {
+  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::EmitIntSExt(MVT SrcVT, unsigned SrcReg, MVT DestVT,
+                               unsigned DestReg) {
+  if ((DestVT != MVT::i32) && (DestVT != MVT::i16))
+    return false;
+  if (Subtarget->hasMips32r2())
+    return EmitIntSExt32r2(SrcVT, SrcReg, DestVT, DestReg);
+  else
+    return EmitIntSExt32r1(SrcVT, SrcReg, DestVT, DestReg);
+}
+
+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;
 }
 
+// Attempt to fast-select a floating-point extend instruction.
+bool MipsFastISel::SelectFPExt(const Instruction *I) {
+  Value *Src = I->getOperand(0);
+  EVT SrcVT = TLI.getValueType(Src->getType(), true);
+  EVT DestVT = TLI.getValueType(I->getType(), true);
+
+  if (SrcVT != MVT::f32 || DestVT != MVT::f64)
+    return false;
+
+  unsigned SrcReg =
+      getRegForValue(Src); // his must be a 32 bit floating point register class
+                           // maybe we should handle this differently
+  if (!SrcReg)
+    return false;
+
+  unsigned DestReg = createResultReg(&Mips::AFGR64RegClass);
+  EmitInst(Mips::CVT_D32_S, DestReg).addReg(SrcReg);
+  updateValueMap(I, DestReg);
+  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::fastSelectInstruction(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);
+  case Instruction::FPExt:
+    return SelectFPExt(I);
   }
   return false;
 }
-}
 
 unsigned MipsFastISel::MaterializeFP(const ConstantFP *CFP, MVT VT) {
   int64_t Imm = CFP->getValueAPF().bitcastToAPInt().getZExtValue();
   if (VT == MVT::f32) {
     const TargetRegisterClass *RC = &Mips::FGR32RegClass;
     unsigned DestReg = createResultReg(RC);
     unsigned TempReg = Materialize32BitInt(Imm, &Mips::GPR32RegClass);
     EmitInst(Mips::MTC1, DestReg).addReg(TempReg);
if (Lo) {
     unsigned TmpReg = createResultReg(RC);
     EmitInst(Mips::LUi, TmpReg).addImm(Hi);
     EmitInst(Mips::ORi, ResultReg).addReg(TmpReg).addImm(Lo);
   } else {
     EmitInst(Mips::LUi, ResultReg).addImm(Hi);
   }
   return ResultReg;
 }
+}
 
 namespace llvm {
 FastISel *Mips::createFastISel(FunctionLoweringInfo &funcInfo,
                                const TargetLibraryInfo *libInfo) {
   return new MipsFastISel(funcInfo, libInfo);
 }
 }

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

+; RUN: llc -march=mipsel -relocation-model=pic -O0 -mips-fast-isel -fast-isel-abort -mcpu=mips32r2 \
+; RUN:     < %s | FileCheck %s
+
+@f = global float 0x40147E6B80000000, align 4
+@d_f = common global double 0.000000e+00, align 8
+@.str = private unnamed_addr constant [6 x i8] c"%f  \0A\00", align 1
+
+; Function Attrs: nounwind
+define void @dv() #0 {
+entry:
+  %0 = load float* @f, align 4
+  %conv = fpext float %0 to double
+; CHECK: cvt.d.s  $f{{[0-9]+}}, $f{{[0-9]+}}
+  store double %conv, double* @d_f, align 8
+  ret void
+}
+
+
+attributes #1 = { nounwind }

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
+; RUN: llc -march=mipsel -relocation-model=pic -O0 -mips-fast-isel -fast-isel-abort -mcpu=mips32 \
+; RUN:     < %s | FileCheck %s
+; RUN: llc -march=mipsel -relocation-model=pic -O0 -mips-fast-isel -fast-isel-abort -mcpu=mips32r2 \
+; RUN:     < %s | FileCheck %s -check-prefix=mips32r2
+; RUN: llc -march=mipsel -relocation-model=pic -O0 -mips-fast-isel -fast-isel-abort -mcpu=mips32 \
+; RUN:     < %s | FileCheck %s -check-prefix=mips32
+
+@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()  {
+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  $[[REG1:[0-9]+]], 0(${{[0-9]+}})
+; CHECK:  andi  $[[REG2:[0-9]+]], $[[REG1]], 1
+; CHECK:  sb  $[[REG2]], 0(${{[0-9]+}})
+
+
+
+  ret void
+; CHECK:   .end  _Z3b_iv
+}
+
+; Function Attrs: nounwind
+define void @_Z4uc_iv()  {
+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  $[[REG1:[0-9]+]], 0(${{[0-9]+}})
+; CHECK:  andi  ${{[0-9]+}}, $[[REG1]], 255
+
+  store i32 %conv1, i32* @j, align 4
+  ret void
+; CHECK:  .end  _Z4uc_iv
+
+}
+
+; Function Attrs: nounwind
+define void @_Z4sc_iv()  {
+entry:
+; mips32r2:  .ent  _Z4sc_iv
+; mips32:  .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
+; mips32r2:  lbu  $[[REG1:[0-9]+]], 0(${{[0-9]+}})
+; mips32r2:  seb  ${{[0-9]+}}, $[[REG1]]
+; mips32:  lbu  $[[REG1:[0-9]+]], 0(${{[0-9]+}})
+; mips32:    sll  $[[REG2:[0-9]+]], $[[REG1]], 24
+; mips32:    sra  ${{[0-9]+}}, $[[REG2]], 24
+
+  ret void
+; CHECK:  .end  _Z4sc_iv
+}
+
+; Function Attrs: nounwind
+define void @_Z4us_iv()  {
+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  $[[REG1:[0-9]+]], 0(${{[0-9]+}})
+; CHECK:  andi  ${{[0-9]+}}, $[[REG1]], 65535
+; CHECK:  .end  _Z4us_iv
+}
+
+; Function Attrs: nounwind
+define void @_Z4ss_iv()  {
+entry:
+; mips32r2:  .ent  _Z4ss_iv
+; mips32:  .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
+; mips32r2:  lhu  $[[REG1:[0-9]+]], 0(${{[0-9]+}})
+; mips32r2:  seh  ${{[0-9]+}}, $[[REG1]]
+; mips32:    lhu  $[[REG1:[0-9]+]], 0(${{[0-9]+}})
+; mips32:    sll  $[[REG2:[0-9]+]], $[[REG1]], 16
+; mips32:    sra  ${{[0-9]+}}, $[[REG2]], 16
+
+  ret void
+; CHECK:  .end  _Z4ss_iv
+}
+
+; Function Attrs: nounwind
+define void @_Z4b_ssv()  {
+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  $[[REG1:[0-9]+]], 0(${{[0-9]+}})
+; CHECK:  andi  ${{[0-9]+}}, $[[REG1]], 1
+; CHECK:  .end  _Z4b_ssv
+}
+
+; Function Attrs: nounwind
+define void @_Z5uc_ssv()  {
+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  $[[REG1:[0-9]+]], 0(${{[0-9]+}})
+; CHECK:  andi  ${{[0-9]+}}, $[[REG1]], 255
+
+  store i16 %conv1, i16* @ssj, align 2
+  ret void
+; CHECK:  .end  _Z5uc_ssv
+}
+
+; Function Attrs: nounwind
+define void @_Z5sc_ssv()  {
+entry:
+; mips32r2:  .ent  _Z5sc_ssv
+; mips32:  .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
+; mips32r2:  lbu  $[[REG1:[0-9]+]], 0(${{[0-9]+}})
+; mips32r2:  seb  ${{[0-9]+}}, $[[REG1]]
+; mips32:  lbu  $[[REG1:[0-9]+]], 0(${{[0-9]+}})
+; mips32:    sll  $[[REG2:[0-9]+]], $[[REG1]], 24
+; mips32:    sra  ${{[0-9]+}}, $[[REG2]], 24
+
+  ret void
+; CHECK:  .end  _Z5sc_ssv
+}
+