[Alignment][NFC] Migrate SelectionDAGTargetInfo::EmitTargetCodeForMemset to Align

[gchatelet]

Summary

This patch is part of a series to introduce an Alignment type.
See this thread for context: http://lists.llvm.org/pipermail/llvm-dev/2019-July/133851.html
See this patch for the introduction of the type: https://reviews.llvm.org/D64790

llvm/include/llvm/CodeGen/SelectionDAGTargetInfo.h

public:
   /// This can be used by targets to provide code sequences for cases
   /// that don't fit the target's parameters for simple stores and can be more
   /// efficient than using a library call. This function can return a null
   /// SDValue if the target declines to use custom code and a different
   /// lowering strategy should be used.
   virtual SDValue EmitTargetCodeForMemset(SelectionDAG &DAG, const SDLoc &dl,
                                           SDValue Chain, SDValue Op1,
                                           SDValue Op2, SDValue Op3,
-                                          unsigned Align, bool isVolatile,
+                                          Align Alignment, bool isVolatile,
                                           MachinePointerInfo DstPtrInfo) const {
     return SDValue();
   }
 
   /// Emit target-specific code that performs a memcmp, in cases where that is
   /// faster than a libcall. The first returned SDValue is the result of the
   /// memcmp and the second is the chain. Both SDValues can be null if a normal
   /// libcall should be used.

llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp

if (ConstantSize) {
     if (Result.getNode())
       return Result;
   }
 
   // Then check to see if we should lower the memset with target-specific
   // code. If the target chooses to do this, this is the next best.
   if (TSI) {
     SDValue Result = TSI->EmitTargetCodeForMemset(
-        *this, dl, Chain, Dst, Src, Size, Alignment.value(), isVol, DstPtrInfo);
+        *this, dl, Chain, Dst, Src, Size, Alignment, isVol, DstPtrInfo);
     if (Result.getNode())
       return Result;
   }
 
   checkAddrSpaceIsValidForLibcall(TLI, DstPtrInfo.getAddrSpace());
 
   // Emit a library call.
   TargetLowering::ArgListTy Args;

llvm/lib/Target/AArch64/AArch64SelectionDAGInfo.h

 #include "llvm/CodeGen/SelectionDAGTargetInfo.h"
 
 namespace llvm {
 
 class AArch64SelectionDAGInfo : public SelectionDAGTargetInfo {
 public:
   SDValue EmitTargetCodeForMemset(SelectionDAG &DAG, const SDLoc &dl,
                                   SDValue Chain, SDValue Dst, SDValue Src,
-                                  SDValue Size, unsigned Align, bool isVolatile,
+                                  SDValue Size, Align Alignment,
+                                  bool isVolatile,
                                   MachinePointerInfo DstPtrInfo) const override;
   SDValue EmitTargetCodeForSetTag(SelectionDAG &DAG, const SDLoc &dl,
                                   SDValue Chain, SDValue Op1, SDValue Op2,
                                   MachinePointerInfo DstPtrInfo,
                                   bool ZeroData) const override;
   bool generateFMAsInMachineCombiner(CodeGenOpt::Level OptLevel) const override;
 };
 }
 
 #endif

llvm/lib/Target/AArch64/AArch64SelectionDAGInfo.cpp

 
 #include "AArch64TargetMachine.h"
 using namespace llvm;
 
 #define DEBUG_TYPE "aarch64-selectiondag-info"
 
 SDValue AArch64SelectionDAGInfo::EmitTargetCodeForMemset(
     SelectionDAG &DAG, const SDLoc &dl, SDValue Chain, SDValue Dst, SDValue Src,
-    SDValue Size, unsigned Align, bool isVolatile,
+    SDValue Size, Align Alignment, bool isVolatile,
     MachinePointerInfo DstPtrInfo) const {
   // Check to see if there is a specialized entry-point for memory zeroing.
   ConstantSDNode *V = dyn_cast<ConstantSDNode>(Src);
   ConstantSDNode *SizeValue = dyn_cast<ConstantSDNode>(Size);
   const AArch64Subtarget &STI =
       DAG.getMachineFunction().getSubtarget<AArch64Subtarget>();
   const char *bzeroName = (V && V->isNullValue())
       ? DAG.getTargetLoweringInfo().getLibcallName(RTLIB::BZERO) : nullptr;

llvm/lib/Target/ARM/ARMSelectionDAGInfo.h

EmitTargetCodeForMemmove(SelectionDAG &DAG, const SDLoc &dl, SDValue Chain,
                            SDValue Dst, SDValue Src, SDValue Size,
                            unsigned Align, bool isVolatile,
                            MachinePointerInfo DstPtrInfo,
                            MachinePointerInfo SrcPtrInfo) const override;
 
   // Adjust parameters for memset, see RTABI section 4.3.4
   SDValue EmitTargetCodeForMemset(SelectionDAG &DAG, const SDLoc &dl,
                                   SDValue Chain, SDValue Op1, SDValue Op2,
-                                  SDValue Op3, unsigned Align, bool isVolatile,
+                                  SDValue Op3, Align Alignment, bool isVolatile,
                                   MachinePointerInfo DstPtrInfo) const override;
 
   SDValue EmitSpecializedLibcall(SelectionDAG &DAG, const SDLoc &dl,
                                  SDValue Chain, SDValue Dst, SDValue Src,
                                  SDValue Size, unsigned Align,
                                  RTLIB::Libcall LC) const;
 };
 
 }
 
 #endif

llvm/lib/Target/ARM/ARMSelectionDAGInfo.cpp

SDValue ARMSelectionDAGInfo::EmitTargetCodeForMemmove(
     SDValue Size, unsigned Align, bool isVolatile,
     MachinePointerInfo DstPtrInfo, MachinePointerInfo SrcPtrInfo) const {
   return EmitSpecializedLibcall(DAG, dl, Chain, Dst, Src, Size, Align,
                                 RTLIB::MEMMOVE);
 }
 
 SDValue ARMSelectionDAGInfo::EmitTargetCodeForMemset(
     SelectionDAG &DAG, const SDLoc &dl, SDValue Chain, SDValue Dst, SDValue Src,
-    SDValue Size, unsigned Align, bool isVolatile,
+    SDValue Size, Align Alignment, bool isVolatile,
     MachinePointerInfo DstPtrInfo) const {
-  return EmitSpecializedLibcall(DAG, dl, Chain, Dst, Src, Size, Align,
-                                RTLIB::MEMSET);
+  return EmitSpecializedLibcall(DAG, dl, Chain, Dst, Src, Size,
+                                Alignment.value(), RTLIB::MEMSET);
 }

llvm/lib/Target/SystemZ/SystemZSelectionDAGInfo.h

SDValue EmitTargetCodeForMemcpy(SelectionDAG &DAG, const SDLoc &DL,
                                   SDValue Chain, SDValue Dst, SDValue Src,
                                   SDValue Size, unsigned Align, bool IsVolatile,
                                   bool AlwaysInline,
                                   MachinePointerInfo DstPtrInfo,
                                   MachinePointerInfo SrcPtrInfo) const override;
 
   SDValue EmitTargetCodeForMemset(SelectionDAG &DAG, const SDLoc &DL,
                                   SDValue Chain, SDValue Dst, SDValue Byte,
-                                  SDValue Size, unsigned Align, bool IsVolatile,
+                                  SDValue Size, Align Alignment,
+                                  bool IsVolatile,
                                   MachinePointerInfo DstPtrInfo) const override;
 
   std::pair<SDValue, SDValue>
   EmitTargetCodeForMemcmp(SelectionDAG &DAG, const SDLoc &DL, SDValue Chain,
                           SDValue Src1, SDValue Src2, SDValue Size,
                           MachinePointerInfo Op1PtrInfo,
                           MachinePointerInfo Op2PtrInfo) const override;
 

llvm/lib/Target/SystemZ/SystemZSelectionDAGInfo.cpp

for (unsigned I = 1; I < Size; ++I)
     StoreVal |= ByteVal << (I * 8);
   return DAG.getStore(
       Chain, DL, DAG.getConstant(StoreVal, DL, MVT::getIntegerVT(Size * 8)),
       Dst, DstPtrInfo, Align);
 }
 
 SDValue SystemZSelectionDAGInfo::EmitTargetCodeForMemset(
     SelectionDAG &DAG, const SDLoc &DL, SDValue Chain, SDValue Dst,
-    SDValue Byte, SDValue Size, unsigned Align, bool IsVolatile,
+    SDValue Byte, SDValue Size, Align Alignment, bool IsVolatile,
     MachinePointerInfo DstPtrInfo) const {
   EVT PtrVT = Dst.getValueType();
 
   if (IsVolatile)
     return SDValue();
 
   if (auto *CSize = dyn_cast<ConstantSDNode>(Size)) {
     uint64_t Bytes = CSize->getZExtValue();
     if (Bytes == 0)
       return SDValue();
     if (auto *CByte = dyn_cast<ConstantSDNode>(Byte)) {
       // Handle cases that can be done using at most two of
       // MVI, MVHI, MVHHI and MVGHI.  The latter two can only be
       // used if ByteVal is all zeros or all ones; in other casees,
       // we can move at most 2 halfwords.
       uint64_t ByteVal = CByte->getZExtValue();
       if (ByteVal == 0 || ByteVal == 255 ?
           Bytes <= 16 && countPopulation(Bytes) <= 2 :
           Bytes <= 4) {
         unsigned Size1 = Bytes == 16 ? 8 : 1 << findLastSet(Bytes);
         unsigned Size2 = Bytes - Size1;
         SDValue Chain1 = memsetStore(DAG, DL, Chain, Dst, ByteVal, Size1,
-                                     Align, DstPtrInfo);
+                                     Alignment.value(), DstPtrInfo);
         if (Size2 == 0)
           return Chain1;
         Dst = DAG.getNode(ISD::ADD, DL, PtrVT, Dst,
                           DAG.getConstant(Size1, DL, PtrVT));
         DstPtrInfo = DstPtrInfo.getWithOffset(Size1);
-        SDValue Chain2 = memsetStore(DAG, DL, Chain, Dst, ByteVal, Size2,
-                                     std::min(Align, Size1), DstPtrInfo);
+        SDValue Chain2 = memsetStore(
+            DAG, DL, Chain, Dst, ByteVal, Size2,
+            std::min((unsigned)Alignment.value(), Size1), DstPtrInfo);
         return DAG.getNode(ISD::TokenFactor, DL, MVT::Other, Chain1, Chain2);
       }
     } else {
       // Handle one and two bytes using STC.
       if (Bytes <= 2) {
-        SDValue Chain1 = DAG.getStore(Chain, DL, Byte, Dst, DstPtrInfo, Align);
+        SDValue Chain1 =
+            DAG.getStore(Chain, DL, Byte, Dst, DstPtrInfo, Alignment);
         if (Bytes == 1)
           return Chain1;
         SDValue Dst2 = DAG.getNode(ISD::ADD, DL, PtrVT, Dst,
                                    DAG.getConstant(1, DL, PtrVT));
         SDValue Chain2 =
             DAG.getStore(Chain, DL, Byte, Dst2, DstPtrInfo.getWithOffset(1),
                          /* Alignment = */ 1);
         return DAG.getNode(ISD::TokenFactor, DL, MVT::Other, Chain1, Chain2);
       }
     }
     assert(Bytes >= 2 && "Should have dealt with 0- and 1-byte cases already");
 
     // Handle the special case of a memset of 0, which can use XC.
     auto *CByte = dyn_cast<ConstantSDNode>(Byte);
     if (CByte && CByte->getZExtValue() == 0)
       return emitMemMem(DAG, DL, SystemZISD::XC, SystemZISD::XC_LOOP,
                         Chain, Dst, Dst, Bytes);
 
     // Copy the byte to the first location and then use MVC to copy
     // it to the rest.
-    Chain = DAG.getStore(Chain, DL, Byte, Dst, DstPtrInfo, Align);
+    Chain = DAG.getStore(Chain, DL, Byte, Dst, DstPtrInfo, Alignment);
     SDValue DstPlus1 = DAG.getNode(ISD::ADD, DL, PtrVT, Dst,
                                    DAG.getConstant(1, DL, PtrVT));
     return emitMemMem(DAG, DL, SystemZISD::MVC, SystemZISD::MVC_LOOP,
                       Chain, DstPlus1, Dst, Bytes - 1);
   }
   return SDValue();
 }
 

llvm/lib/Target/WebAssembly/WebAssemblySelectionDAGInfo.h

SDValue EmitTargetCodeForMemcpy(SelectionDAG &DAG, const SDLoc &dl,
                                   MachinePointerInfo SrcPtrInfo) const override;
   SDValue EmitTargetCodeForMemmove(SelectionDAG &DAG, const SDLoc &dl,
                                    SDValue Chain, SDValue Op1, SDValue Op2,
                                    SDValue Op3, unsigned Align, bool isVolatile,
                                    MachinePointerInfo DstPtrInfo,
                                    MachinePointerInfo SrcPtrInfo) const override;
   SDValue EmitTargetCodeForMemset(SelectionDAG &DAG, const SDLoc &DL,
                                   SDValue Chain, SDValue Op1, SDValue Op2,
-                                  SDValue Op3, unsigned Align, bool IsVolatile,
+                                  SDValue Op3, Align Alignment, bool IsVolatile,
                                   MachinePointerInfo DstPtrInfo) const override;
 };
 
 } // end namespace llvm
 
 #endif

llvm/lib/Target/WebAssembly/WebAssemblySelectionDAGInfo.cpp

SDValue WebAssemblySelectionDAGInfo::EmitTargetCodeForMemmove(
     MachinePointerInfo DstPtrInfo, MachinePointerInfo SrcPtrInfo) const {
   return EmitTargetCodeForMemcpy(DAG, DL, Chain, Op1, Op2, Op3, Align,
                                  IsVolatile, false, DstPtrInfo,
                                  SrcPtrInfo);
 }
 
 SDValue WebAssemblySelectionDAGInfo::EmitTargetCodeForMemset(
     SelectionDAG &DAG, const SDLoc &DL, SDValue Chain, SDValue Dst, SDValue Val,
-    SDValue Size, unsigned Align, bool IsVolatile,
+    SDValue Size, Align Alignment, bool IsVolatile,
     MachinePointerInfo DstPtrInfo) const {
   if (!DAG.getMachineFunction()
            .getSubtarget<WebAssemblySubtarget>()
            .hasBulkMemory())
     return SDValue();
 
   SDValue MemIdx = DAG.getConstant(0, DL, MVT::i32);
   // Only low byte matters for val argument, so anyext the i8
   return DAG.getNode(WebAssemblyISD::MEMORY_FILL, DL, MVT::Other, Chain, MemIdx,
                      Dst, DAG.getAnyExtOrTrunc(Val, DL, MVT::i32),
                      DAG.getZExtOrTrunc(Size, DL, MVT::i32));
 }

llvm/lib/Target/X86/X86SelectionDAGInfo.h

class X86SelectionDAGInfo : public SelectionDAGTargetInfo {
   bool isBaseRegConflictPossible(SelectionDAG &DAG,
                                  ArrayRef<MCPhysReg> ClobberSet) const;
 
 public:
   explicit X86SelectionDAGInfo() = default;
 
   SDValue EmitTargetCodeForMemset(SelectionDAG &DAG, const SDLoc &dl,
                                   SDValue Chain, SDValue Dst, SDValue Src,
-                                  SDValue Size, unsigned Align, bool isVolatile,
+                                  SDValue Size, Align Alignment,
+                                  bool isVolatile,
                                   MachinePointerInfo DstPtrInfo) const override;
 
   SDValue EmitTargetCodeForMemcpy(SelectionDAG &DAG, const SDLoc &dl,
                                   SDValue Chain, SDValue Dst, SDValue Src,
                                   SDValue Size, unsigned Align, bool isVolatile,
                                   bool AlwaysInline,
                                   MachinePointerInfo DstPtrInfo,
                                   MachinePointerInfo SrcPtrInfo) const override;
 };
 
 }
 
 #endif

llvm/lib/Target/X86/X86SelectionDAGInfo.cpp

bool X86SelectionDAGInfo::isBaseRegConflictPossible(
   for (unsigned R : ClobberSet)
     if (BaseReg == R)
       return true;
   return false;
 }
 
 SDValue X86SelectionDAGInfo::EmitTargetCodeForMemset(
     SelectionDAG &DAG, const SDLoc &dl, SDValue Chain, SDValue Dst, SDValue Val,
-    SDValue Size, unsigned Align, bool isVolatile,
+    SDValue Size, Align Alignment, bool isVolatile,
     MachinePointerInfo DstPtrInfo) const {
   ConstantSDNode *ConstantSize = dyn_cast<ConstantSDNode>(Size);
   const X86Subtarget &Subtarget =
       DAG.getMachineFunction().getSubtarget<X86Subtarget>();
 
 #ifndef NDEBUG
   // If the base register might conflict with our physical registers, bail out.
   const MCPhysReg ClobberSet[] = {X86::RCX, X86::RAX, X86::RDI,
                                   X86::ECX, X86::EAX, X86::EDI};
   assert(!isBaseRegConflictPossible(DAG, ClobberSet));
 #endif
 
   // If to a segment-relative address space, use the default lowering.
   if (DstPtrInfo.getAddrSpace() >= 256)
     return SDValue();
 
   // If not DWORD aligned or size is more than the threshold, call the library.
   // The libc version is likely to be faster for these cases. It can use the
   // address value and run time information about the CPU.
-  if ((Align & 3) != 0 || !ConstantSize ||
+  if (Alignment < Align(4) || !ConstantSize ||
       ConstantSize->getZExtValue() > Subtarget.getMaxInlineSizeThreshold()) {
     // Check to see if there is a specialized entry-point for memory zeroing.
     ConstantSDNode *ValC = dyn_cast<ConstantSDNode>(Val);
 
     if (const char *bzeroName = (ValC && ValC->isNullValue())
         ? DAG.getTargetLoweringInfo().getLibcallName(RTLIB::BZERO)
         : nullptr) {
       const TargetLowering &TLI = DAG.getTargetLoweringInfo();
#endif
   SDValue Count;
   ConstantSDNode *ValC = dyn_cast<ConstantSDNode>(Val);
   unsigned BytesLeft = 0;
   if (ValC) {
     unsigned ValReg;
     uint64_t Val = ValC->getZExtValue() & 255;
 
     // If the value is a constant, then we can potentially use larger sets.
-    switch (Align & 3) {
-    case 2:   // WORD aligned
-      AVT = MVT::i16;
-      ValReg = X86::AX;
-      Val = (Val << 8) | Val;
-      break;
-    case 0:  // DWORD aligned
+    if (Alignment > Align(2)) {
+      // DWORD aligned
       AVT = MVT::i32;
       ValReg = X86::EAX;
       Val = (Val << 8)  | Val;
       Val = (Val << 16) | Val;
-      if (Subtarget.is64Bit() && ((Align & 0x7) == 0)) {  // QWORD aligned
+      if (Subtarget.is64Bit() && Alignment > Align(8)) { // QWORD aligned
         AVT = MVT::i64;
         ValReg = X86::RAX;
         Val = (Val << 32) | Val;
       }
-      break;
-    default:  // Byte aligned
+    } else if (Alignment == Align(2)) {
+      // WORD aligned
+      AVT = MVT::i16;
+      ValReg = X86::AX;
+      Val = (Val << 8) | Val;
+    } else {
+      // Byte aligned
       AVT = MVT::i8;
       ValReg = X86::AL;
       Count = DAG.getIntPtrConstant(SizeVal, dl);
-      break;
     }
 
     if (AVT.bitsGT(MVT::i8)) {
       unsigned UBytes = AVT.getSizeInBits() / 8;
       Count = DAG.getIntPtrConstant(SizeVal / UBytes, dl);
       BytesLeft = SizeVal % UBytes;
     }
 
#endif
   Chain = DAG.getNode(X86ISD::REP_STOS, dl, Tys, Ops);
 
   if (BytesLeft) {
     // Handle the last 1 - 7 bytes.
     unsigned Offset = SizeVal - BytesLeft;
     EVT AddrVT = Dst.getValueType();
     EVT SizeVT = Size.getValueType();
 
-    Chain = DAG.getMemset(Chain, dl,
-                          DAG.getNode(ISD::ADD, dl, AddrVT, Dst,
-                                      DAG.getConstant(Offset, dl, AddrVT)),
-                          Val, DAG.getConstant(BytesLeft, dl, SizeVT),
-                          llvm::Align(Align), isVolatile, false,
-                          DstPtrInfo.getWithOffset(Offset));
+    Chain =
+        DAG.getMemset(Chain, dl,
+                      Val, DAG.getConstant(BytesLeft, dl, SizeVT), Alignment,
+                      isVolatile, false, DstPtrInfo.getWithOffset(Offset));
   }
 
   // TODO: Use a Tokenfactor, as in memcpy, instead of a single chain.
   return Chain;
 }
 
 /// Emit a single REP MOVS{B,W,D,Q} instruction.
 static SDValue emitRepmovs(const X86Subtarget &Subtarget, SelectionDAG &DAG,