[TableGen] Efficiency improvements for encoding HwMode collection. (#82902)

Currently the DecoderEmitter spends a fair amount of cycles performing
repeated linear walks over the entire instruction list. This patch
eliminates one such walk during HwMode collection for EncodingInfos.

The eliminated traversal visits every instruction and then every
EncodingInfos entry for that instruction merely to collect all
referenced HwModes. That information already happens to be present in
the HwModeSelects created during the one-time construction of
CodeGenHwModes. We instead traverse the HwModeSelects, collecting each
one referenced as an encoding select. This set is a small constant in
size and does not generally grow with the size of the instruction set.

Author: nvjle

llvm/utils/TableGen/CodeGenHwModes.h

@@ -53,6 +53,9 @@ struct CodeGenHwModes {
     return Modes[Id - 1];
   }
   const HwModeSelect &getHwModeSelect(Record *R) const;
+  const std::map<Record *, HwModeSelect> &getHwModeSelects() const {
+    return ModeSelects;
+  }
   unsigned getNumModeIds() const { return Modes.size() + 1; }
   void dump() const;
 

llvm/utils/TableGen/DecoderEmitter.cpp

@@ -22,6 +22,7 @@
 #include "llvm/ADT/CachedHashString.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/SetVector.h"
+#include "llvm/ADT/SmallBitVector.h"
 #include "llvm/ADT/SmallString.h"
 #include "llvm/ADT/Statistic.h"
 #include "llvm/ADT/StringExtras.h"
@@ -2448,6 +2449,22 @@ static void emitCheck(formatted_raw_ostream &OS) {
      << "}\n\n";
 }
 
+// Collect all HwModes referenced by the target for encoding purposes,
+// returning a vector of corresponding names.
+static void
+collectHwModesReferencedForEncodings(const CodeGenHwModes &HWM,
+                                     std::vector<StringRef> &Names) {
+  SmallBitVector BV(HWM.getNumModeIds());
+  for (const auto &MS : HWM.getHwModeSelects()) {
+    for (const HwModeSelect::PairType &P : MS.second.Items) {
+      if (P.second->isSubClassOf("InstructionEncoding"))
+        BV.set(P.first);
+    }
+  }
+  transform(BV.set_bits(), std::back_inserter(Names),
+            [&HWM](const int &M) { return HWM.getMode(M).Name; });
+}
+
 // Emits disassembler code for instruction decoding.
 void DecoderEmitter::run(raw_ostream &o) {
   formatted_raw_ostream OS(o);
@@ -2469,37 +2486,25 @@ void DecoderEmitter::run(raw_ostream &o) {
   Target.reverseBitsForLittleEndianEncoding();
 
   // Parameterize the decoders based on namespace and instruction width.
-  std::set<StringRef> HwModeNames;
-  const auto &NumberedInstructions = Target.getInstructionsByEnumValue();
-  NumberedEncodings.reserve(NumberedInstructions.size());
-  // First, collect all HwModes referenced by the target.
-  for (const auto &NumberedInstruction : NumberedInstructions) {
-    if (const RecordVal *RV =
-            NumberedInstruction->TheDef->getValue("EncodingInfos")) {
-      if (auto *DI = dyn_cast_or_null<DefInit>(RV->getValue())) {
-        const CodeGenHwModes &HWM = Target.getHwModes();
-        EncodingInfoByHwMode EBM(DI->getDef(), HWM);
-        for (auto &KV : EBM)
-          HwModeNames.insert(HWM.getMode(KV.first).Name);
-      }
-    }
-  }
 
+  // First, collect all encoding-related HwModes referenced by the target.
   // If HwModeNames is empty, add the empty string so we always have one HwMode.
+  const CodeGenHwModes &HWM = Target.getHwModes();
+  std::vector<StringRef> HwModeNames;
+  collectHwModesReferencedForEncodings(HWM, HwModeNames);
   if (HwModeNames.empty())
-    HwModeNames.insert("");
+    HwModeNames.push_back("");
 
+  const auto &NumberedInstructions = Target.getInstructionsByEnumValue();
+  NumberedEncodings.reserve(NumberedInstructions.size());
   for (const auto &NumberedInstruction : NumberedInstructions) {
     if (const RecordVal *RV =
             NumberedInstruction->TheDef->getValue("EncodingInfos")) {
       if (DefInit *DI = dyn_cast_or_null<DefInit>(RV->getValue())) {
-        const CodeGenHwModes &HWM = Target.getHwModes();
         EncodingInfoByHwMode EBM(DI->getDef(), HWM);
-        for (auto &KV : EBM) {
+        for (auto &KV : EBM)
           NumberedEncodings.emplace_back(KV.second, NumberedInstruction,
                                          HWM.getMode(KV.first).Name);
-          HwModeNames.insert(HWM.getMode(KV.first).Name);
-        }
         continue;
       }
     }