Patch 14 (#22)

* Update README.md

* Patch 13 (#13)

* Update README.md

* Patch 12 (#11)

* Update README.md

* Patch 13 (#10)

* Update README.md

* Patch 12 (#9)

* Update memchr.cpp

* Patch 10 (#6)

* Optimize string functions

* Update string_utils.h

* Update memrchr.cpp

* Patch 11 (#8)

* Update README.md

* Patch 10 (#5)

* Update CMakeLists.txt

* Patch 9 (#4)

* Update strchr.cpp

* Add explicit cast (#3)

We need to have the most efficient c++ casting

* Update strchr.cpp

* Update CMakeLists.txt

* Update strrchr.cpp

* Update README.md

* Update string_utils.h

* Update string_utils.h

* Update memchr.cpp

* Update README.md

* Update string_utils.h

* Update README.md

* Update README.md

* Update memcpy.cpp

* Update memmove.cpp

* Update memmove.cpp

* Update strcpy.cpp

* Update strcpy.cpp

* Update strcpy.cpp

* Update memcpy.cpp

* Update memmove.cpp

* Update memmove.cpp

* Update memcpy.cpp

* Update memmove.cpp

* Update README.md

* Update memmove.cpp

* Update strcpy.cpp

* Update strcpy.cpp

* Update memmove.cpp

* Update strcpy.cpp

* Update strcpy.cpp

* Update memmove.cpp

* Fix

* Fix

* Update elements.h

* Update elements.h

Co-authored-by: Radical Dweamer <83354299+RadiD234@users.noreply.github.com>

libc/src/string/memchr.cpp

@@ -17,7 +17,8 @@ namespace __llvm_libc {
 // TODO: Look at performance benefits of comparing words.
 LLVM_LIBC_FUNCTION(void *, memchr, (const void *src, int c, size_t n)) {
   return internal::find_first_character(
-      reinterpret_cast<const unsigned char *>(src), c, n);
+      reinterpret_cast<const unsigned char *>(src),
+      static_cast<unsigned char>(c), n);
 }
 
 } // namespace __llvm_libc

libc/src/string/memcpy.cpp

@@ -30,8 +30,8 @@ namespace __llvm_libc {
 //   implementation parameters.
 // - As compilers and processors get better, the generated code is improved
 //   with little change on the code side.
-static void memcpy_impl(char *__restrict dst, const char *__restrict src,
-                        size_t count) {
+static void memcpy_impl(unsigned char *__restrict dst,
+                        const unsigned char *__restrict src, size_t count) {
   // Use scalar strategies (_1, _2, _3 ...)
   using namespace __llvm_libc::scalar;
 
@@ -61,8 +61,8 @@ static void memcpy_impl(char *__restrict dst, const char *__restrict src,
 LLVM_LIBC_FUNCTION(void *, memcpy,
                    (void *__restrict dst, const void *__restrict src,
                     size_t size)) {
-  memcpy_impl(reinterpret_cast<char *>(dst),
-              reinterpret_cast<const char *>(src), size);
+  memcpy_impl(reinterpret_cast<unsigned char *>(dst),
+              reinterpret_cast<const unsigned char *>(src), size);
   return dst;
 }
 

libc/src/string/memmove.cpp

@@ -15,22 +15,23 @@
 
 namespace __llvm_libc {
 
-static inline void move_byte_forward(char *dest_m, const char *src_m,
-                                     size_t count) {
+static inline void move_byte_forward(unsigned char *dest_m,
+                                     const unsigned char *src_m, size_t count) {
   for (size_t offset = 0; count; --count, ++offset)
     dest_m[offset] = src_m[offset];
 }
 
-static inline void move_byte_backward(char *dest_m, const char *src_m,
+static inline void move_byte_backward(unsigned char *dest_m,
+                                      const unsigned char *src_m,
                                       size_t count) {
   for (size_t offset = count - 1; count; --count, --offset)
     dest_m[offset] = src_m[offset];
 }
 
 LLVM_LIBC_FUNCTION(void *, memmove,
                    (void *dest, const void *src, size_t count)) {
-  char *dest_c = reinterpret_cast<char *>(dest);
-  const char *src_c = reinterpret_cast<const char *>(src);
+  unsigned char *dest_c = reinterpret_cast<unsigned char *>(dest);
+  const unsigned char *src_c = reinterpret_cast<const unsigned char *>(src);
 
   // If the distance between src_c and dest_c is equal to or greater
   // than count (integerAbs(src_c - dest_c) >= count), they would not overlap.
@@ -58,7 +59,7 @@ LLVM_LIBC_FUNCTION(void *, memmove,
   // TODO: Optimize `move_byte_xxx(...)` functions.
   if (dest_c < src_c)
     move_byte_forward(dest_c, src_c, count);
-  if (dest_c > src_c)
+  else if (dest_c > src_c)
     move_byte_backward(dest_c, src_c, count);
   return dest;
 }

libc/src/string/memory_utils/elements.h

@@ -29,11 +29,20 @@ template <typename Element>
 void Copy(char *__restrict dst, const char *__restrict src) {
   Element::Copy(dst, src);
 }
+template <typename Element>
+void Copy(unsigned char *__restrict dst, const unsigned char *__restrict src) {
+  Element::Copy(dst, src);
+}
 // Runtime-size copies from 'src' to 'dst'.
 template <typename Element>
 void Copy(char *__restrict dst, const char *__restrict src, size_t size) {
   Element::Copy(dst, src, size);
 }
+template <typename Element>
+void Copy(unsigned char *__restrict dst, const unsigned char *__restrict src,
+          size_t size) {
+  Element::Copy(dst, src, size);
+}
 
 // Fixed-size equality between 'lhs' and 'rhs'.
 template <typename Element> bool Equals(const char *lhs, const char *rhs) {
@@ -124,6 +133,12 @@ template <typename Head, typename... Tail> struct Chained<Head, Tail...> {
     __llvm_libc::Copy<Head>(dst, src);
   }
 
+  static void Copy(unsigned char *__restrict dst,
+                   const unsigned char *__restrict src) {
+    Chained<Tail...>::Copy(dst + Head::kSize, src + Head::kSize);
+    __llvm_libc::Copy<Head>(dst, src);
+  }
+
   static bool Equals(const char *lhs, const char *rhs) {
     if (!__llvm_libc::Equals<Head>(lhs, rhs))
       return false;

libc/src/string/memrchr.cpp

@@ -14,11 +14,10 @@ namespace __llvm_libc {
 
 LLVM_LIBC_FUNCTION(void *, memrchr, (const void *src, int c, size_t n)) {
   const unsigned char *str = reinterpret_cast<const unsigned char *>(src);
-  const unsigned char ch = c;
+  const unsigned char ch = static_cast<unsigned char>(c);
   for (; n != 0; --n) {
-    const unsigned char *s = str + n - 1;
-    if (*s == ch)
-      return const_cast<unsigned char *>(s);
+    if (*(--str) == ch)
+      return const_cast<unsigned char *>(str);
   }
   return nullptr;
 }

libc/src/string/strchr.cpp

@@ -14,12 +14,12 @@ namespace __llvm_libc {
 
 // TODO: Look at performance benefits of comparing words.
 LLVM_LIBC_FUNCTION(char *, strchr, (const char *src, int c)) {
-  unsigned char *str =
-      const_cast<unsigned char *>(reinterpret_cast<const unsigned char *>(src));
-  const unsigned char ch = c;
-  for (; *str && *str != ch; ++str)
-    ;
-  return *str == ch ? reinterpret_cast<char *>(str) : nullptr;
+  const char ch = static_cast<char>(c);
+  for (; *src != ch; ++src)
+    if (*src == '\0')
+      return nullptr;
+
+  return const_cast<char *>(src);
 }
 
 } // namespace __llvm_libc

libc/src/string/strcpy.cpp

@@ -7,17 +7,62 @@
 //===----------------------------------------------------------------------===//
 
 #include "src/string/strcpy.h"
-#include "src/string/memcpy.h"
-#include "src/string/string_utils.h"
-
 #include "src/__support/common.h"
+#include "src/string/memory_utils/elements.h"
+#include "src/string/string_utils.h"
 
 namespace __llvm_libc {
 
+// Design rationale
+// ================
+//
+// Using a profiler to observe size distributions for calls into libc
+// functions, it was found most operations act on a small number of bytes.
+// This makes it important to favor small sizes.
+//
+// The tests for `count` are in ascending order so the cost of branching is
+// proportional to the cost of copying.
+//
+// The function is written in C++ for several reasons:
+// - The compiler can __see__ the code, this is useful when performing Profile
+//   Guided Optimization as the optimized code can take advantage of branching
+//   probabilities.
+// - It also allows for easier customization and favors testing multiple
+//   implementation parameters.
+// - As compilers and processors get better, the generated code is improved
+//   with little change on the code side.
+static void strcpy_impl(char *__restrict dst, const char *__restrict src,
+                        size_t count) {
+  // Use scalar strategies (_1, _2, _3 ...)
+  using namespace __llvm_libc::scalar;
+
+  if (count == 0)
+    return;
+  if (count == 1)
+    return Copy<_1>(dst, src);
+  if (count == 2)
+    return Copy<_2>(dst, src);
+  if (count == 3)
+    return Copy<_3>(dst, src);
+  if (count == 4)
+    return Copy<_4>(dst, src);
+  if (count < 8)
+    return Copy<HeadTail<_4>>(dst, src, count);
+  if (count < 16)
+    return Copy<HeadTail<_8>>(dst, src, count);
+  if (count < 32)
+    return Copy<HeadTail<_16>>(dst, src, count);
+  if (count < 64)
+    return Copy<HeadTail<_32>>(dst, src, count);
+  if (count < 128)
+    return Copy<HeadTail<_64>>(dst, src, count);
+  return Copy<Align<_32, Arg::Src>::Then<Loop<_32>>>(dst, src, count);
+}
+
 LLVM_LIBC_FUNCTION(char *, strcpy,
                    (char *__restrict dest, const char *__restrict src)) {
-  return reinterpret_cast<char *>(
-      __llvm_libc::memcpy(dest, src, internal::string_length(src) + 1));
+  strcpy_impl(dest, src, internal::string_length(src) + 1);
+  return dest;
 }
 
 } // namespace __llvm_libc

libc/src/string/string_utils.h

@@ -18,30 +18,31 @@ namespace internal {
 // Returns the length of a string, denoted by the first occurrence
 // of a null terminator.
 static inline size_t string_length(const char *src) {
-  size_t length;
-  for (length = 0; *src; ++src, ++length)
+  const char *const initial = src;
+  for (; *src != '\0'; ++src)
     ;
-  return length;
+  return src - initial;
 }
 
 // Returns the first occurrence of 'ch' within the first 'n' characters of
 // 'src'. If 'ch' is not found, returns nullptr.
 static inline void *find_first_character(const unsigned char *src,
                                          unsigned char ch, size_t n) {
-  for (; n && *src != ch; --n, ++src)
-    ;
-  return n ? const_cast<unsigned char *>(src) : nullptr;
+  for (; n != 0; --n, ++src)
+    if (*src == ch)
+      return const_cast<unsigned char *>(src);
+  return nullptr;
 }
 
 // Returns the maximum length span that contains only characters not found in
 // 'segment'. If no characters are found, returns the length of 'src'.
 static inline size_t complementary_span(const char *src, const char *segment) {
-  const char *initial = src;
+  const char *const initial = src;
   cpp::Bitset<256> bitset;
 
-  for (; *segment; ++segment)
+  for (; *segment != '\0'; ++segment)
     bitset.set(*segment);
-  for (; *src && !bitset.test(*src); ++src)
+  for (; *src != '\0' && !bitset.test(*src); ++src)
     ;
   return src - initial;
 }
@@ -59,22 +60,21 @@ static inline char *string_token(char *__restrict src,
                                  const char *__restrict delimiter_string,
                                  char **__restrict saveptr) {
   cpp::Bitset<256> delimiter_set;
-  for (; *delimiter_string; ++delimiter_string)
+  for (; *delimiter_string != '\0'; ++delimiter_string)
     delimiter_set.set(*delimiter_string);
 
   src = src ? src : *saveptr;
-  for (; *src && delimiter_set.test(*src); ++src)
+  for (; *src != '\0' && delimiter_set.test(*src); ++src)
     ;
-  if (!*src) {
+  if (*src == '\0') {
     *saveptr = src;
     return nullptr;
   }
   char *token = src;
-  for (; *src && !delimiter_set.test(*src); ++src)
+  for (; *src != '\0' && !delimiter_set.test(*src); ++src)
     ;
-  if (*src) {
-    *src = '\0';
-    ++src;
+  if (*src != '\0') {
+    *src++ = '\0';
   }
   *saveptr = src;
   return token;

libc/src/string/strrchr.cpp

@@ -13,12 +13,12 @@
 namespace __llvm_libc {
 
 LLVM_LIBC_FUNCTION(char *, strrchr, (const char *src, int c)) {
-  const char ch = c;
+  const char ch = static_cast<char>(c);
   char *last_occurrence = nullptr;
   do {
     if (*src == ch)
       last_occurrence = const_cast<char *>(src);
-  } while (*src++);
+  } while (*src++ != '\0');
   return last_occurrence;
 }