//
// The LLVM Compiler Infrastructure
//
-// This file was developed by the LLVM research group and is distributed under
-// the University of Illinois Open Source License. See LICENSE.TXT for details.
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
//
//===----------------------------------------------------------------------===//
-#include "CodeEmitterGen.h"
#include "CodeGenTarget.h"
-#include "Record.h"
#include "llvm/ADT/StringExtras.h"
+#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
+#include "llvm/TableGen/Record.h"
+#include "llvm/TableGen/TableGenBackend.h"
+#include <map>
+#include <string>
+#include <vector>
using namespace llvm;
-void CodeEmitterGen::reverseBits(std::vector<Record*> &Insts) {
- for (std::vector<Record*>::iterator I = Insts.begin(), E = Insts.end();
- I != E; ++I) {
- Record *R = *I;
- if (R->getName() == "PHI" || R->getName() == "INLINEASM") continue;
+namespace {
+
+class CodeEmitterGen {
+ RecordKeeper &Records;
+public:
+ CodeEmitterGen(RecordKeeper &R) : Records(R) {}
+
+ void run(raw_ostream &o);
+private:
+ int getVariableBit(const std::string &VarName, BitsInit *BI, int bit);
+ std::string getInstructionCase(Record *R, CodeGenTarget &Target);
+ void AddCodeToMergeInOperand(Record *R, BitsInit *BI,
+ const std::string &VarName,
+ unsigned &NumberedOp,
+ std::set<unsigned> &NamedOpIndices,
+ std::string &Case, CodeGenTarget &Target);
+
+};
+
+// If the VarBitInit at position 'bit' matches the specified variable then
+// return the variable bit position. Otherwise return -1.
+int CodeEmitterGen::getVariableBit(const std::string &VarName,
+ BitsInit *BI, int bit) {
+ if (VarBitInit *VBI = dyn_cast<VarBitInit>(BI->getBit(bit))) {
+ if (VarInit *VI = dyn_cast<VarInit>(VBI->getBitVar()))
+ if (VI->getName() == VarName)
+ return VBI->getBitNum();
+ } else if (VarInit *VI = dyn_cast<VarInit>(BI->getBit(bit))) {
+ if (VI->getName() == VarName)
+ return 0;
+ }
+
+ return -1;
+}
+
+void CodeEmitterGen::
+AddCodeToMergeInOperand(Record *R, BitsInit *BI, const std::string &VarName,
+ unsigned &NumberedOp,
+ std::set<unsigned> &NamedOpIndices,
+ std::string &Case, CodeGenTarget &Target) {
+ CodeGenInstruction &CGI = Target.getInstruction(R);
+
+ // Determine if VarName actually contributes to the Inst encoding.
+ int bit = BI->getNumBits()-1;
+
+ // Scan for a bit that this contributed to.
+ for (; bit >= 0; ) {
+ if (getVariableBit(VarName, BI, bit) != -1)
+ break;
- BitsInit *BI = R->getValueAsBitsInit("Inst");
+ --bit;
+ }
+
+ // If we found no bits, ignore this value, otherwise emit the call to get the
+ // operand encoding.
+ if (bit < 0) return;
+
+ // If the operand matches by name, reference according to that
+ // operand number. Non-matching operands are assumed to be in
+ // order.
+ unsigned OpIdx;
+ if (CGI.Operands.hasOperandNamed(VarName, OpIdx)) {
+ // Get the machine operand number for the indicated operand.
+ OpIdx = CGI.Operands[OpIdx].MIOperandNo;
+ assert(!CGI.Operands.isFlatOperandNotEmitted(OpIdx) &&
+ "Explicitly used operand also marked as not emitted!");
+ } else {
+ unsigned NumberOps = CGI.Operands.size();
+ /// If this operand is not supposed to be emitted by the
+ /// generated emitter, skip it.
+ while (NumberedOp < NumberOps &&
+ (CGI.Operands.isFlatOperandNotEmitted(NumberedOp) ||
+ (NamedOpIndices.size() && NamedOpIndices.count(
+ CGI.Operands.getSubOperandNumber(NumberedOp).first)))) {
+ ++NumberedOp;
+
+ if (NumberedOp >= CGI.Operands.back().MIOperandNo +
+ CGI.Operands.back().MINumOperands) {
+ errs() << "Too few operands in record " << R->getName() <<
+ " (no match for variable " << VarName << "):\n";
+ errs() << *R;
+ errs() << '\n';
- unsigned numBits = BI->getNumBits();
- BitsInit *NewBI = new BitsInit(numBits);
- for (unsigned bit = 0, end = numBits / 2; bit != end; ++bit) {
- unsigned bitSwapIdx = numBits - bit - 1;
- Init *OrigBit = BI->getBit(bit);
- Init *BitSwap = BI->getBit(bitSwapIdx);
- NewBI->setBit(bit, BitSwap);
- NewBI->setBit(bitSwapIdx, OrigBit);
+ return;
+ }
+ }
+
+ OpIdx = NumberedOp++;
+ }
+
+ std::pair<unsigned, unsigned> SO = CGI.Operands.getSubOperandNumber(OpIdx);
+ std::string &EncoderMethodName = CGI.Operands[SO.first].EncoderMethodName;
+
+ // If the source operand has a custom encoder, use it. This will
+ // get the encoding for all of the suboperands.
+ if (!EncoderMethodName.empty()) {
+ // A custom encoder has all of the information for the
+ // sub-operands, if there are more than one, so only
+ // query the encoder once per source operand.
+ if (SO.second == 0) {
+ Case += " // op: " + VarName + "\n" +
+ " op = " + EncoderMethodName + "(MI, " + utostr(OpIdx);
+ Case += ", Fixups, STI";
+ Case += ");\n";
}
- if (numBits % 2) {
- unsigned middle = (numBits + 1) / 2;
- NewBI->setBit(middle, BI->getBit(middle));
+ } else {
+ Case += " // op: " + VarName + "\n" +
+ " op = getMachineOpValue(MI, MI.getOperand(" + utostr(OpIdx) + ")";
+ Case += ", Fixups, STI";
+ Case += ");\n";
+ }
+
+ for (; bit >= 0; ) {
+ int varBit = getVariableBit(VarName, BI, bit);
+
+ // If this bit isn't from a variable, skip it.
+ if (varBit == -1) {
+ --bit;
+ continue;
}
- // Update the bits in reversed order so that emitInstrOpBits will get the
- // correct endianness.
- R->getValue("Inst")->setValue(NewBI);
+ // Figure out the consecutive range of bits covered by this operand, in
+ // order to generate better encoding code.
+ int beginInstBit = bit;
+ int beginVarBit = varBit;
+ int N = 1;
+ for (--bit; bit >= 0;) {
+ varBit = getVariableBit(VarName, BI, bit);
+ if (varBit == -1 || varBit != (beginVarBit - N)) break;
+ ++N;
+ --bit;
+ }
+
+ uint64_t opMask = ~(uint64_t)0 >> (64-N);
+ int opShift = beginVarBit - N + 1;
+ opMask <<= opShift;
+ opShift = beginInstBit - beginVarBit;
+
+ if (opShift > 0) {
+ Case += " Value |= (op & UINT64_C(" + utostr(opMask) + ")) << " +
+ itostr(opShift) + ";\n";
+ } else if (opShift < 0) {
+ Case += " Value |= (op & UINT64_C(" + utostr(opMask) + ")) >> " +
+ itostr(-opShift) + ";\n";
+ } else {
+ Case += " Value |= op & UINT64_C(" + utostr(opMask) + ");\n";
+ }
}
}
-// If the VarBitInit at position 'bit' matches the specified variable then
-// return the variable bit position. Otherwise return -1.
-int CodeEmitterGen::getVariableBit(const std::string &VarName,
- BitsInit *BI, int bit) {
- if (VarBitInit *VBI = dynamic_cast<VarBitInit*>(BI->getBit(bit))) {
- TypedInit *TI = VBI->getVariable();
-
- if (VarInit *VI = dynamic_cast<VarInit*>(TI)) {
- if (VI->getName() == VarName) return VBI->getBitNum();
+std::string CodeEmitterGen::getInstructionCase(Record *R,
+ CodeGenTarget &Target) {
+ std::string Case;
+
+ BitsInit *BI = R->getValueAsBitsInit("Inst");
+ const std::vector<RecordVal> &Vals = R->getValues();
+ unsigned NumberedOp = 0;
+
+ std::set<unsigned> NamedOpIndices;
+ // Collect the set of operand indices that might correspond to named
+ // operand, and skip these when assigning operands based on position.
+ if (Target.getInstructionSet()->
+ getValueAsBit("noNamedPositionallyEncodedOperands")) {
+ CodeGenInstruction &CGI = Target.getInstruction(R);
+ for (unsigned i = 0, e = Vals.size(); i != e; ++i) {
+ unsigned OpIdx;
+ if (!CGI.Operands.hasOperandNamed(Vals[i].getName(), OpIdx))
+ continue;
+
+ NamedOpIndices.insert(OpIdx);
}
}
-
- return -1;
-}
+ // Loop over all of the fields in the instruction, determining which are the
+ // operands to the instruction.
+ for (unsigned i = 0, e = Vals.size(); i != e; ++i) {
+ // Ignore fixed fields in the record, we're looking for values like:
+ // bits<5> RST = { ?, ?, ?, ?, ? };
+ if (Vals[i].getPrefix() || Vals[i].getValue()->isComplete())
+ continue;
+
+ AddCodeToMergeInOperand(R, BI, Vals[i].getName(), NumberedOp,
+ NamedOpIndices, Case, Target);
+ }
+
+ std::string PostEmitter = R->getValueAsString("PostEncoderMethod");
+ if (!PostEmitter.empty()) {
+ Case += " Value = " + PostEmitter + "(MI, Value";
+ Case += ", STI";
+ Case += ");\n";
+ }
+
+ return Case;
+}
-void CodeEmitterGen::run(std::ostream &o) {
- CodeGenTarget Target;
+void CodeEmitterGen::run(raw_ostream &o) {
+ CodeGenTarget Target(Records);
std::vector<Record*> Insts = Records.getAllDerivedDefinitions("Instruction");
-
+
// For little-endian instruction bit encodings, reverse the bit order
- if (Target.isLittleEndianEncoding()) reverseBits(Insts);
+ Target.reverseBitsForLittleEndianEncoding();
- EmitSourceFileHeader("Machine Code Emitter", o);
- std::string Namespace = Insts[0]->getValueAsString("Namespace") + "::";
-
- std::vector<const CodeGenInstruction*> NumberedInstructions;
- Target.getInstructionsByEnumValue(NumberedInstructions);
+ const std::vector<const CodeGenInstruction*> &NumberedInstructions =
+ Target.getInstructionsByEnumValue();
// Emit function declaration
- o << "unsigned " << Target.getName() << "CodeEmitter::"
- << "getBinaryCodeForInstr(MachineInstr &MI) {\n";
+ o << "uint64_t " << Target.getName();
+ o << "MCCodeEmitter::getBinaryCodeForInstr(const MCInst &MI,\n"
+ << " SmallVectorImpl<MCFixup> &Fixups,\n"
+ << " const MCSubtargetInfo &STI) const {\n";
// Emit instruction base values
- o << " static const unsigned InstBits[] = {\n";
- for (std::vector<const CodeGenInstruction*>::iterator
+ o << " static const uint64_t InstBits[] = {\n";
+ for (std::vector<const CodeGenInstruction*>::const_iterator
IN = NumberedInstructions.begin(),
EN = NumberedInstructions.end();
IN != EN; ++IN) {
const CodeGenInstruction *CGI = *IN;
Record *R = CGI->TheDef;
-
- if (IN != NumberedInstructions.begin()) o << ",\n";
-
- if (R->getName() == "PHI" || R->getName() == "INLINEASM") {
- o << " 0U";
+
+ if (R->getValueAsString("Namespace") == "TargetOpcode" ||
+ R->getValueAsBit("isPseudo")) {
+ o << " UINT64_C(0),\n";
continue;
}
-
+
BitsInit *BI = R->getValueAsBitsInit("Inst");
- // Start by filling in fixed values...
- unsigned Value = 0;
+ // Start by filling in fixed values.
+ uint64_t Value = 0;
for (unsigned i = 0, e = BI->getNumBits(); i != e; ++i) {
- if (BitInit *B = dynamic_cast<BitInit*>(BI->getBit(e-i-1))) {
- Value |= B->getValue() << (e-i-1);
- }
+ if (BitInit *B = dyn_cast<BitInit>(BI->getBit(e-i-1)))
+ Value |= (uint64_t)B->getValue() << (e-i-1);
}
- o << " " << Value << "U";
+ o << " UINT64_C(" << Value << ")," << '\t' << "// " << R->getName() << "\n";
}
- o << "\n };\n";
-
+ o << " UINT64_C(0)\n };\n";
+
// Map to accumulate all the cases.
std::map<std::string, std::vector<std::string> > CaseMap;
-
+
// Construct all cases statement for each opcode
for (std::vector<Record*>::iterator IC = Insts.begin(), EC = Insts.end();
IC != EC; ++IC) {
Record *R = *IC;
- const std::string &InstName = R->getName();
- std::string Case("");
-
- if (InstName == "PHI" || InstName == "INLINEASM") continue;
-
- BitsInit *BI = R->getValueAsBitsInit("Inst");
- const std::vector<RecordVal> &Vals = R->getValues();
-
- // Loop over all of the fields in the instruction, determining which are the
- // operands to the instruction.
- unsigned op = 0;
- for (unsigned i = 0, e = Vals.size(); i != e; ++i) {
- if (!Vals[i].getPrefix() && !Vals[i].getValue()->isComplete()) {
- // Is the operand continuous? If so, we can just mask and OR it in
- // instead of doing it bit-by-bit, saving a lot in runtime cost.
- const std::string &VarName = Vals[i].getName();
- bool gotOp = false;
-
- for (int bit = BI->getNumBits()-1; bit >= 0; ) {
- int varBit = getVariableBit(VarName, BI, bit);
-
- if (varBit == -1) {
- --bit;
- } else {
- int beginInstBit = bit;
- int beginVarBit = varBit;
- int N = 1;
-
- for (--bit; bit >= 0;) {
- varBit = getVariableBit(VarName, BI, bit);
- if (varBit == -1 || varBit != (beginVarBit - N)) break;
- ++N;
- --bit;
- }
-
- if (!gotOp) {
- Case += " // op: " + VarName + "\n"
- + " op = getMachineOpValue(MI, MI.getOperand("
- + utostr(op++)
- + "));\n";
- gotOp = true;
-
- // If this is a two-address instruction and we just got the dest
- // op, skip the src op.
- if (op == 1 && Target.getInstruction(InstName).isTwoAddress)
- ++op;
- }
-
- unsigned opMask = (1 << N) - 1;
- int opShift = beginVarBit - N + 1;
- opMask <<= opShift;
- opShift = beginInstBit - beginVarBit;
-
- if (opShift > 0) {
- Case += " Value |= (op & " + utostr(opMask) + "U) << "
- + itostr(opShift) + ";\n";
- } else if (opShift < 0) {
- Case += " Value |= (op & " + utostr(opMask) + "U) >> "
- + itostr(-opShift) + ";\n";
- } else {
- Case += " Value |= op & " + utostr(opMask) + "U;\n";
- }
- }
- }
- }
- }
+ if (R->getValueAsString("Namespace") == "TargetOpcode" ||
+ R->getValueAsBit("isPseudo"))
+ continue;
+ const std::string &InstName = R->getValueAsString("Namespace") + "::"
+ + R->getName();
+ std::string Case = getInstructionCase(R, Target);
- std::vector<std::string> &InstList = CaseMap[Case];
- InstList.push_back(InstName);
+ CaseMap[Case].push_back(InstName);
}
-
// Emit initial function code
o << " const unsigned opcode = MI.getOpcode();\n"
- << " unsigned Value = InstBits[opcode];\n"
- << " unsigned op;\n"
+ << " uint64_t Value = InstBits[opcode];\n"
+ << " uint64_t op = 0;\n"
+ << " (void)op; // suppress warning\n"
<< " switch (opcode) {\n";
// Emit each case statement
for (int i = 0, N = InstList.size(); i < N; i++) {
if (i) o << "\n";
- o << " case " << Namespace << InstList[i] << ":";
+ o << " case " << InstList[i] << ":";
}
o << " {\n";
o << Case;
// Default case: unhandled opcode
o << " default:\n"
- << " std::cerr << \"Not supported instr: \" << MI << \"\\n\";\n"
- << " abort();\n"
+ << " std::string msg;\n"
+ << " raw_string_ostream Msg(msg);\n"
+ << " Msg << \"Not supported instr: \" << MI;\n"
+ << " report_fatal_error(Msg.str());\n"
<< " }\n"
<< " return Value;\n"
<< "}\n\n";
}
+
+} // End anonymous namespace
+
+namespace llvm {
+
+void EmitCodeEmitter(RecordKeeper &RK, raw_ostream &OS) {
+ emitSourceFileHeader("Machine Code Emitter", OS);
+ CodeEmitterGen(RK).run(OS);
+}
+
+} // End llvm namespace