[llvm] r247269 - [ADT] Rewrite the StringRef::find implementation to be simpler, clearer,

[Chandler Carruth via llvm-commits]

Author: chandlerc
Date: Thu Sep 10 06:17:49 2015
New Revision: 247269

URL: http://llvm.org/viewvc/llvm-project?rev=247269&view=rev
Log:
[ADT] Rewrite the StringRef::find implementation to be simpler, clearer,
and tremendously less reliant on the optimizer to fix things.

The code is always necessarily looking for the entire length of the
string when doing the equality tests in this find implementation, but it
previously was needlessly re-checking the size each time among other
annoyances.

By writing this so simply an ddirectly in terms of memcmp, it also is
about 8x faster in a debug build, which in turn makes FileCheck about 2x
faster in 'ninja check-llvm'. This saves about 8% of the time for
FileCheck-heavy parts of the test suite like the x86 backend tests.

Modified:
    llvm/trunk/lib/Support/StringRef.cpp

Modified: llvm/trunk/lib/Support/StringRef.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Support/StringRef.cpp?rev=247269&r1=247268&r2=247269&view=diff
==============================================================================
--- llvm/trunk/lib/Support/StringRef.cpp (original)
+++ llvm/trunk/lib/Support/StringRef.cpp Thu Sep 10 06:17:49 2015
@@ -140,37 +140,44 @@ std::string StringRef::upper() const {
 /// \return - The index of the first occurrence of \arg Str, or npos if not
 /// found.
 size_t StringRef::find(StringRef Str, size_t From) const {
+  if (From > Length)
+    return npos;
+
+  const char *Needle = Str.data();
   size_t N = Str.size();
-  if (N > Length)
+  if (N == 0)
+    return From;
+
+  size_t Size = Length - From;
+  if (Size < N)
     return npos;
 
+  const char *Start = Data + From;
+  const char *Stop = Start + (Size - N + 1);
+
   // For short haystacks or unsupported needles fall back to the naive algorithm
-  if (Length < 16 || N > 255 || N == 0) {
-    for (size_t e = Length - N + 1, i = std::min(From, e); i != e; ++i)
-      if (substr(i, N).equals(Str))
-        return i;
+  if (Size < 16 || N > 255) {
+    do {
+      if (std::memcmp(Start, Needle, N) == 0)
+        return Start - Data;
+      ++Start;
+    } while (Start < Stop);
     return npos;
   }
 
-  if (From >= Length)
-    return npos;
-
   // Build the bad char heuristic table, with uint8_t to reduce cache thrashing.
   uint8_t BadCharSkip[256];
   std::memset(BadCharSkip, N, 256);
   for (unsigned i = 0; i != N-1; ++i)
     BadCharSkip[(uint8_t)Str[i]] = N-1-i;
 
-  unsigned Len = Length-From, Pos = From;
-  while (Len >= N) {
-    if (substr(Pos, N).equals(Str)) // See if this is the correct substring.
-      return Pos;
+  do {
+    if (std::memcmp(Start, Needle, N) == 0)
+      return Start - Data;
 
     // Otherwise skip the appropriate number of bytes.
-    uint8_t Skip = BadCharSkip[(uint8_t)(*this)[Pos+N-1]];
-    Len -= Skip;
-    Pos += Skip;
-  }
+    Start += BadCharSkip[(uint8_t)Start[N-1]];
+  } while (Start < Stop);
 
   return npos;
 }