[llvm] r247244 - [ADT] Add a single-character version of the small vector split routine

[Chandler Carruth via llvm-commits]

Author: chandlerc
Date: Thu Sep 10 01:07:03 2015
New Revision: 247244

URL: http://llvm.org/viewvc/llvm-project?rev=247244&view=rev
Log:
[ADT] Add a single-character version of the small vector split routine
on StringRef. Finding and splitting on a single character is
substantially faster than doing it on even a single character StringRef
-- we immediately get to a *very* tuned memchr call this way.

Even nicer, we get to this even in a debug build, shaving 18% off the
runtime of TripleTest.Normalization, helping PR23676 some more.

Modified:
    llvm/trunk/include/llvm/ADT/StringRef.h
    llvm/trunk/lib/Support/StringRef.cpp
    llvm/trunk/lib/Support/Triple.cpp
    llvm/trunk/unittests/ADT/StringRefTest.cpp

Modified: llvm/trunk/include/llvm/ADT/StringRef.h
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/ADT/StringRef.h?rev=247244&r1=247243&r2=247244&view=diff
==============================================================================
--- llvm/trunk/include/llvm/ADT/StringRef.h (original)
+++ llvm/trunk/include/llvm/ADT/StringRef.h Thu Sep 10 01:07:03 2015
@@ -489,6 +489,23 @@ namespace llvm {
                StringRef Separator, int MaxSplit = -1,
                bool KeepEmpty = true) const;
 
+    /// Split into substrings around the occurrences of a separator character.
+    ///
+    /// Each substring is stored in \p A. If \p MaxSplit is >= 0, at most
+    /// \p MaxSplit splits are done and consequently <= \p MaxSplit
+    /// elements are added to A.
+    /// If \p KeepEmpty is false, empty strings are not added to \p A. They
+    /// still count when considering \p MaxSplit
+    /// An useful invariant is that
+    /// Separator.join(A) == *this if MaxSplit == -1 and KeepEmpty == true
+    ///
+    /// \param A - Where to put the substrings.
+    /// \param Separator - The string to split on.
+    /// \param MaxSplit - The maximum number of times the string is split.
+    /// \param KeepEmpty - True if empty substring should be added.
+    void split(SmallVectorImpl<StringRef> &A, char Separator, int MaxSplit = -1,
+               bool KeepEmpty = true) const;
+
     /// Split into two substrings around the last occurrence of a separator
     /// character.
     ///

Modified: llvm/trunk/lib/Support/StringRef.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Support/StringRef.cpp?rev=247244&r1=247243&r2=247244&view=diff
==============================================================================
--- llvm/trunk/lib/Support/StringRef.cpp (original)
+++ llvm/trunk/lib/Support/StringRef.cpp Thu Sep 10 01:07:03 2015
@@ -294,6 +294,26 @@ void StringRef::split(SmallVectorImpl<St
     A.push_back(rest);
 }
 
+void StringRef::split(SmallVectorImpl<StringRef> &A, char Separator,
+                      int MaxSplit, bool KeepEmpty) const {
+  StringRef rest = *this;
+
+  // rest.data() is used to distinguish cases like "a," that splits into
+  // "a" + "" and "a" that splits into "a" + 0.
+  for (int splits = 0;
+       rest.data() != nullptr && (MaxSplit < 0 || splits < MaxSplit);
+       ++splits) {
+    std::pair<StringRef, StringRef> p = rest.split(Separator);
+
+    if (KeepEmpty || p.first.size() != 0)
+      A.push_back(p.first);
+    rest = p.second;
+  }
+  // If we have a tail left, add it.
+  if (rest.data() != nullptr && (rest.size() != 0 || KeepEmpty))
+    A.push_back(rest);
+}
+
 //===----------------------------------------------------------------------===//
 // Helpful Algorithms
 //===----------------------------------------------------------------------===//

Modified: llvm/trunk/lib/Support/Triple.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Support/Triple.cpp?rev=247244&r1=247243&r2=247244&view=diff
==============================================================================
--- llvm/trunk/lib/Support/Triple.cpp (original)
+++ llvm/trunk/lib/Support/Triple.cpp Thu Sep 10 01:07:03 2015
@@ -624,7 +624,7 @@ std::string Triple::normalize(StringRef
 
   // Parse into components.
   SmallVector<StringRef, 4> Components;
-  Str.split(Components, "-");
+  Str.split(Components, '-');
 
   // If the first component corresponds to a known architecture, preferentially
   // use it for the architecture.  If the second component corresponds to a

Modified: llvm/trunk/unittests/ADT/StringRefTest.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/unittests/ADT/StringRefTest.cpp?rev=247244&r1=247243&r2=247244&view=diff
==============================================================================
--- llvm/trunk/unittests/ADT/StringRefTest.cpp (original)
+++ llvm/trunk/unittests/ADT/StringRefTest.cpp Thu Sep 10 01:07:03 2015
@@ -225,6 +225,11 @@ TEST(StringRefTest, Split2) {
   expected.push_back("a"); expected.push_back("b"); expected.push_back("c");
   StringRef("a,,b,c").split(parts, ",", 3, false);
   EXPECT_TRUE(parts == expected);
+
+  expected.clear(); parts.clear();
+  expected.push_back("a"); expected.push_back("b"); expected.push_back("c");
+  StringRef("a,,b,c").split(parts, ',', 3, false);
+  EXPECT_TRUE(parts == expected);
 }
 
 TEST(StringRefTest, Trim) {