Unverified Commit 0a0e06f2 authored by Nikita Popov's avatar Nikita Popov Committed by GitHub
Browse files

[TableGen] Fix prefix detection with anchor (NFC) (#71379) 

instregex uses an optimization, where the constant prefix of the regex
is extracted to perform a binary search first. However, this
optimization currently mainly fails to apply, because most instregex
uses have an explicit ^ anchor, which gets counted as a meta char and
disables the optimization.

Make sure the anchor is skipped when determining the prefix. Also fix an
implementation bug this exposes, where the pick a too long prefix if the
first meta character is a quantifier.

This cuts the time needed to generate files like X86GenInstrInfo.inc by
half.
parent d64d5ea1

llvm/utils/TableGen/CodeGenSchedule.cpp

+19 −1
Original line number Diff line number Diff line
@@ -91,10 +91,25 @@ struct InstRegexOp : public SetTheory::Operator { 
        PrintFatalError(Loc, "instregex requires pattern string: " +

                                 Expr->getAsString());

      StringRef Original = SI->getValue();

      // Drop an explicit ^ anchor to not interfere with prefix search.

      bool HadAnchor = Original.consume_front("^");



      // Extract a prefix that we can binary search on.

      static const char RegexMetachars[] = "()^$|*+?.[]\\{}";

      auto FirstMeta = Original.find_first_of(RegexMetachars);

      if (FirstMeta != StringRef::npos && FirstMeta > 0) {

        // If we have a regex like ABC* we can only use AB as the prefix, as

        // the * acts on C.

        switch (Original[FirstMeta]) {

        case '+':

        case '*':

        case '?':

          --FirstMeta;

          break;

        default:

          break;

        }

      }



      // Look for top-level | or ?. We cannot optimize them to binary search.

      if (removeParens(Original).find_first_of("|?") != std::string::npos)
@@ -106,7 +121,10 @@ struct InstRegexOp : public SetTheory::Operator { 
      if (!PatStr.empty()) {

        // For the rest use a python-style prefix match.

        std::string pat = std::string(PatStr);

        if (pat[0] != '^') {

        // Add ^ anchor. If we had one originally, don't need the group.

        if (HadAnchor) {

          pat.insert(0, "^");

        } else {

          pat.insert(0, "^(");

          pat.insert(pat.end(), ')');

        }