Add StringRef::compare_numeric and use it to sort TableGen register records.

This means that our Registers are now ordered R7, R8, R9, R10, R12, ...
Not R1, R10, R11, R12, R2, R3, ...

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@104745 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/ADT/StringRef.h

@@ -128,6 +128,10 @@ namespace llvm {
     /// compare_lower - Compare two strings, ignoring case.
     int compare_lower(StringRef RHS) const;
 
+    /// compare_numeric - Compare two strings, treating sequences of digits as
+    /// numbers.
+    int compare_numeric(StringRef RHS) const;
+
     /// \brief Determine the edit distance between this string and another 
     /// string.
     ///

lib/Support/StringRef.cpp

@@ -23,6 +23,10 @@ static char ascii_tolower(char x) {
   return x;
 }
 
+static bool ascii_isdigit(char x) {
+  return x >= '0' && x <= '9';
+}
+
 /// compare_lower - Compare strings, ignoring case.
 int StringRef::compare_lower(StringRef RHS) const {
   for (size_t I = 0, E = min(Length, RHS.Length); I != E; ++I) {
@@ -37,6 +41,30 @@ int StringRef::compare_lower(StringRef RHS) const {
   return Length < RHS.Length ? -1 : 1;
 }
 
+/// compare_numeric - Compare strings, handle embedded numbers.
+int StringRef::compare_numeric(StringRef RHS) const {
+  for (size_t I = 0, E = min(Length, RHS.Length); I != E; ++I) {
+    if (Data[I] == RHS.Data[I])
+      continue;
+    if (ascii_isdigit(Data[I]) && ascii_isdigit(RHS.Data[I])) {
+      // The longer sequence of numbers is larger. This doesn't really handle
+      // prefixed zeros well.
+      for (size_t J = I+1; J != E+1; ++J) {
+        bool ld = J < Length && ascii_isdigit(Data[J]);
+        bool rd = J < RHS.Length && ascii_isdigit(RHS.Data[J]);
+        if (ld != rd)
+          return rd ? -1 : 1;
+        if (!rd)
+          break;
+      }
+    }
+    return Data[I] < RHS.Data[I] ? -1 : 1;
+  }
+  if (Length == RHS.Length)
+        return 0;
+  return Length < RHS.Length ? -1 : 1;
+}
+
 // Compute the edit distance between the two given strings.
 unsigned StringRef::edit_distance(llvm::StringRef Other, 
                                   bool AllowReplacements) {

lib/Target/X86/SSEDomainFix.cpp

@@ -155,9 +155,7 @@ char SSEDomainFixPass::ID = 0;
 /// Translate TRI register number to an index into our smaller tables of
 /// interesting registers. Return -1 for boring registers.
 int SSEDomainFixPass::RegIndex(unsigned reg) {
-  // Registers are sorted lexicographically.
-  // We just need them to be consecutive, ordering doesn't matter.
-  assert(X86::XMM9 == X86::XMM0+NumRegs-1 && "Unexpected sort");
+  assert(X86::XMM15 == X86::XMM0+NumRegs-1 && "Unexpected sort");
   reg -= X86::XMM0;
   return reg < NumRegs ? (int) reg : -1;
 }

unittests/ADT/StringRefTest.cpp

@@ -53,6 +53,17 @@ TEST(StringRefTest, StringOps) {
   EXPECT_EQ( 1, StringRef("aab").compare("aaa"));
   EXPECT_EQ(-1, StringRef("aab").compare("aabb"));
   EXPECT_EQ( 1, StringRef("aab").compare("aa"));
+
+  EXPECT_EQ(-1, StringRef("aab").compare_numeric("aad"));
+  EXPECT_EQ( 0, StringRef("aab").compare_numeric("aab"));
+  EXPECT_EQ( 1, StringRef("aab").compare_numeric("aaa"));
+  EXPECT_EQ(-1, StringRef("aab").compare_numeric("aabb"));
+  EXPECT_EQ( 1, StringRef("aab").compare_numeric("aa"));
+  EXPECT_EQ(-1, StringRef("1").compare_numeric("10"));
+  EXPECT_EQ( 0, StringRef("10").compare_numeric("10"));
+  EXPECT_EQ( 0, StringRef("10a").compare_numeric("10a"));
+  EXPECT_EQ( 1, StringRef("2").compare_numeric("1"));
+  EXPECT_EQ( 0, StringRef("llvm_v1i64_ty").compare_numeric("llvm_v1i64_ty"));
 }
 
 TEST(StringRefTest, Operators) {

utils/TableGen/CodeGenTarget.cpp

@@ -159,6 +159,7 @@ void CodeGenTarget::ReadRegisters() const {
   std::vector<Record*> Regs = Records.getAllDerivedDefinitions("Register");
   if (Regs.empty())
     throw std::string("No 'Register' subclasses defined!");
+  std::sort(Regs.begin(), Regs.end(), LessRecord());
 
   Registers.reserve(Regs.size());
   Registers.assign(Regs.begin(), Regs.end());
@@ -175,6 +176,7 @@ const std::string &CodeGenRegister::getName() const {
 
 void CodeGenTarget::ReadSubRegIndices() const {
   SubRegIndices = Records.getAllDerivedDefinitions("SubRegIndex");
+  std::sort(SubRegIndices.begin(), SubRegIndices.end(), LessRecord());
 }
 
 void CodeGenTarget::ReadRegisterClasses() const {

utils/TableGen/Record.h

@@ -1461,7 +1461,7 @@ public:
 ///
 struct LessRecord {
   bool operator()(const Record *Rec1, const Record *Rec2) const {
-    return Rec1->getName() < Rec2->getName();
+    return StringRef(Rec1->getName()).compare_numeric(Rec2->getName()) < 0;
   }
 };