[llvm] [LLVM][MC] Add support to cull inactive decoders in decoder emitter (PR #154865)

[Sergei Barannikov via llvm-commits]

================
@@ -2528,59 +2535,114 @@ namespace {
 )";
 
   // Do extra bookkeeping for variable-length encodings.
-  std::vector<unsigned> InstrLen;
   bool IsVarLenInst = Target.hasVariableLengthEncodings();
   unsigned MaxInstLen = 0;
   if (IsVarLenInst) {
-    InstrLen.resize(Target.getInstructions().size(), 0);
+    std::vector<unsigned> InstrLen(Target.getInstructions().size(), 0);
     for (const InstructionEncoding &Encoding : Encodings) {
       MaxInstLen = std::max(MaxInstLen, Encoding.getBitWidth());
       InstrLen[Target.getInstrIntValue(Encoding.getInstruction()->TheDef)] =
           Encoding.getBitWidth();
     }
+
+    // For variable instruction, we emit a instruction length table to let the
+    // decoder know how long the instructions are. You can see example usage in
+    // M68k's disassembler.
+    emitInstrLenTable(OS, InstrLen);
   }
 
   // Map of (namespace, hwmode, size) tuple to encoding IDs.
-  std::map<std::tuple<StringRef, unsigned, unsigned>, std::vector<unsigned>>
-      EncMap;
+  using EncMapTy = std::map<std::tuple<StringRef, unsigned, unsigned>,
+                            std::vector<unsigned>>;
+  EncMapTy EncMap;
+
+  // The set of valid instruction bitwidths for this target.
+  SmallSet<unsigned, 4> InstrBitwidths;
   for (const auto &[HwModeID, EncodingIDs] : EncodingIDsByHwMode) {
     for (unsigned EncodingID : EncodingIDs) {
       const InstructionEncoding &Encoding = Encodings[EncodingID];
       const Record *EncodingDef = Encoding.getRecord();
       unsigned Size = EncodingDef->getValueAsInt("Size");
       StringRef DecoderNamespace =
           EncodingDef->getValueAsString("DecoderNamespace");
+      const unsigned BitWidth = IsVarLenInst ? MaxInstLen : 8 * Size;
+      InstrBitwidths.insert(BitWidth);
       EncMap[{DecoderNamespace, HwModeID, Size}].push_back(EncodingID);
----------------
s-barannikov wrote:

Use the bitwidth (instead of size) as a part of the key to avoid `MaxInstLen : 8 * Size` in every place we extract the size?

https://github.com/llvm/llvm-project/pull/154865