[x86] Teach the X86 backend to print shuffle comments for PSHUFB

instructions which happen to have a constant mask.

Currently, this only handles a very narrow set of cases, but those
happen to be the cases that I care about for testing shuffles sanely.
This is a bit trickier than other shuffle instructions because we're
decoding constants out of the constant pool. The current MC layer makes
it completely impossible to inspect a constant pool entry, so we have to
do it at the MI level and attach the comment to the streamer on its way
out. So no joy for disassembling, but it does make test cases and asm
dumps *much* nicer.

Sorry for no test cases, but it didn't really seem that valuable to go
trolling through existing old test cases and updating them. I'll have
lots of testing of this in the upcoming patch for SSSE3 emission in the
new vector shuffle lowering code paths.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@213986 91177308-0d34-0410-b5e6-96231b3b80d8

lib/Target/X86/Utils/X86ShuffleDecode.cpp

@@ -13,6 +13,7 @@
 //===----------------------------------------------------------------------===//
 
 #include "X86ShuffleDecode.h"
+#include "llvm/IR/Constants.h"
 #include "llvm/CodeGen/MachineValueType.h"
 
 //===----------------------------------------------------------------------===//
@@ -207,6 +208,38 @@ void DecodeVPERM2X128Mask(MVT VT, unsigned Imm,
   }
 }
 
+/// \brief Decode PSHUFB masks stored in an LLVM Constant.
+void DecodePSHUFBMask(const ConstantDataSequential *C,
+                      SmallVectorImpl<int> &ShuffleMask) {
+  Type *MaskTy = C->getType();
+  assert(MaskTy->isVectorTy() && "Expected a vector constant mask!");
+  Type *EltTy = MaskTy->getVectorElementType();
+  assert(EltTy->isIntegerTy(8) && "Expected i8 constant mask elements!");
+  int NumElements = MaskTy->getVectorNumElements();
+  // FIXME: Add support for AVX-512.
+  assert((NumElements == 16 || NumElements == 32) &&
+         "Only 128-bit and 256-bit vectors supported!");
+  assert((unsigned)NumElements == C->getNumElements() &&
+         "Constant mask has a different number of elements!");
+
+  ShuffleMask.reserve(NumElements);
+  for (int i = 0; i < NumElements; ++i) {
+    // For AVX vectors with 32 bytes the base of the shuffle is the half of the
+    // vector we're inside.
+    int Base = i < 16 ? 0 : 16;
+    uint64_t Element = C->getElementAsInteger(i);
+    // If the high bit (7) of the byte is set, the element is zeroed.
+    if (Element & (1 << 7))
+      ShuffleMask.push_back(SM_SentinelZero);
+    else {
+      int Index = Base + Element;
+      assert((Index >= 0 && Index < NumElements) ||
+             "Out of bounds shuffle index for pshub instruction!");
+      ShuffleMask.push_back(Index);
+    }
+  }
+}
+
 /// DecodeVPERMMask - this decodes the shuffle masks for VPERMQ/VPERMPD.
 /// No VT provided since it only works on 256-bit, 4 element vectors.
 void DecodeVPERMMask(unsigned Imm, SmallVectorImpl<int> &ShuffleMask) {

lib/Target/X86/Utils/X86ShuffleDecode.h

@@ -22,6 +22,7 @@
 //===----------------------------------------------------------------------===//
 
 namespace llvm {
+class ConstantDataSequential;
 class MVT;
 
 enum {
@@ -59,6 +60,8 @@ void DecodeUNPCKHMask(MVT VT, SmallVectorImpl<int> &ShuffleMask);
 /// different datatypes and vector widths.
 void DecodeUNPCKLMask(MVT VT, SmallVectorImpl<int> &ShuffleMask);
 
+void DecodePSHUFBMask(const ConstantDataSequential *C,
+                      SmallVectorImpl<int> &ShuffleMask);
 
 void DecodeVPERM2X128Mask(MVT VT, unsigned Imm,
                           SmallVectorImpl<int> &ShuffleMask);

lib/Target/X86/X86MCInstLower.cpp

@@ -16,8 +16,11 @@
 #include "X86RegisterInfo.h"
 #include "InstPrinter/X86ATTInstPrinter.h"
 #include "MCTargetDesc/X86BaseInfo.h"
+#include "Utils/X86ShuffleDecode.h"
 #include "llvm/ADT/SmallString.h"
 #include "llvm/CodeGen/MachineFunction.h"
+#include "llvm/CodeGen/MachineConstantPool.h"
+#include "llvm/CodeGen/MachineOperand.h"
 #include "llvm/CodeGen/MachineModuleInfoImpls.h"
 #include "llvm/CodeGen/StackMaps.h"
 #include "llvm/IR/DataLayout.h"
@@ -963,6 +966,83 @@ void X86AsmPrinter::EmitInstruction(const MachineInstr *MI) {
   case X86::SEH_EndPrologue:
     OutStreamer.EmitWinCFIEndProlog();
     return;
+
+  case X86::PSHUFBrm:
+    // Lower PSHUFB normally but add a comment if we can find a constant
+    // shuffle mask. We won't be able to do this at the MC layer because the
+    // mask isn't an immediate.
+    std::string Comment;
+    raw_string_ostream CS(Comment);
+    SmallVector<int, 16> Mask;
+
+    assert(MI->getNumOperands() == 7 &&
+           "Wrong number of operansd for PSHUFBrm");
+    const MachineOperand &DstOp = MI->getOperand(0);
+    const MachineOperand &SrcOp = MI->getOperand(1);
+    const MachineOperand &MaskOp = MI->getOperand(5);
+
+    // Compute the name for a register. This is really goofy because we have
+    // multiple instruction printers that could (in theory) use different
+    // names. Fortunately most people use the ATT style (outside of Windows)
+    // and they actually agree on register naming here. Ultimately, this is
+    // a comment, and so its OK if it isn't perfect.
+    auto GetRegisterName = [](unsigned RegNum) -> StringRef {
+      return X86ATTInstPrinter::getRegisterName(RegNum);
+    };
+
+    StringRef DstName = DstOp.isReg() ? GetRegisterName(DstOp.getReg()) : "mem";
+    StringRef SrcName = SrcOp.isReg() ? GetRegisterName(SrcOp.getReg()) : "mem";
+    CS << DstName << " = ";
+
+    if (MaskOp.isCPI()) {
+      ArrayRef<MachineConstantPoolEntry> Constants =
+          MI->getParent()->getParent()->getConstantPool()->getConstants();
+      const MachineConstantPoolEntry &MaskConstantEntry =
+          Constants[MI->getOperand(5).getIndex()];
+      Type *MaskTy = MaskConstantEntry.getType();
+      if (!MaskConstantEntry.isMachineConstantPoolEntry())
+        if (auto *C = dyn_cast<ConstantDataSequential>(
+                MaskConstantEntry.Val.ConstVal)) {
+          assert(MaskTy == C->getType() &&
+                 "Expected a constant of the same type!");
+
+          DecodePSHUFBMask(C, Mask);
+          assert(Mask.size() == MaskTy->getVectorNumElements() &&
+                 "Shuffle mask has a different size than its type!");
+        }
+    }
+
+    if (!Mask.empty()) {
+      bool NeedComma = false;
+      bool InSrc = false;
+      for (int M : Mask) {
+        // Wrap up any prior entry...
+        if (M == SM_SentinelZero && InSrc) {
+          InSrc = false;
+          CS << "]";
+        }
+        if (NeedComma)
+          CS << ",";
+        else
+          NeedComma = true;
+
+        // Print this shuffle...
+        if (M == SM_SentinelZero) {
+          CS << "zero";
+        } else {
+          if (!InSrc) {
+            InSrc = true;
+            CS << SrcName << "[";
+          }
+          CS << M;
+        }
+      }
+      if (InSrc)
+        CS << "]";
+
+      OutStreamer.AddComment(CS.str());
+    }
+    break;
   }
 
   MCInst TmpInst;