[llvm] [LLVM][MC][DecoderEmitter] Add support to specialize decoder per bitwidth (PR #154865)

[Rahul Joshi via llvm-commits]

================
@@ -2499,57 +2533,90 @@ 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 an 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;
+  // Map of (bitwidth, namespace, hwmode) tuple to encoding IDs.
+  // Its organized as a nested map, with the (namespace, hwmode) as the key for
+  // the inner map and bitwidth as the key for the outer map. We use std::map
+  // for deterministic iteration order so that the code emitted is also
+  // deterministic.
+  using InnerKeyTy = std::pair<StringRef, unsigned>;
+  using InnerMapTy = std::map<InnerKeyTy, std::vector<unsigned>>;
+  std::map<unsigned, InnerMapTy> EncMap;
+
   for (const auto &[HwModeID, EncodingIDs] : EncodingIDsByHwMode) {
     for (unsigned EncodingID : EncodingIDs) {
       const InstructionEncoding &Encoding = Encodings[EncodingID];
       const Record *EncodingDef = Encoding.getRecord();
----------------
jurahul wrote:

Fixed.

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