Refactor WIDE_READ to allow finer control over high-performance function selection

libc/cmake/modules/LLVMLibCCompileOptionRules.cmake

@@ -81,9 +81,8 @@ function(_get_compile_options_from_config output_var)
     list(APPEND config_options "-DLIBC_QSORT_IMPL=${LIBC_CONF_QSORT_IMPL}")
   endif()
 
-  if(LIBC_CONF_STRING_UNSAFE_WIDE_READ)
-    list(APPEND config_options "-DLIBC_COPT_STRING_UNSAFE_WIDE_READ")
-  endif()
+  list(APPEND config_options "-DLIBC_COPT_STRING_LENGTH_IMPL=${LIBC_CONF_STRING_LENGTH_IMPL}")
+  list(APPEND config_options "-DLIBC_COPT_FIND_FIRST_CHARACTER_IMPL=${LIBC_CONF_FIND_FIRST_CHARACTER_IMPL}")
 
   if(LIBC_CONF_MEMSET_X86_USE_SOFTWARE_PREFETCHING)
     list(APPEND config_options "-DLIBC_COPT_MEMSET_X86_USE_SOFTWARE_PREFETCHING")

libc/config/config.json

@@ -40,6 +40,7 @@
       "value": false,
       "doc": "Use an alternative printf float implementation based on 320-bit floats"
     },
+
     "LIBC_CONF_PRINTF_DISABLE_FIXED_POINT": {
       "value": false,
       "doc": "Disable printing fixed point values in printf and friends."
@@ -64,9 +65,13 @@
     }
   },
   "string": {
-    "LIBC_CONF_STRING_UNSAFE_WIDE_READ": {
-      "value": false,
-      "doc": "Read more than a byte at a time to perform byte-string operations like strlen."
+    "LIBC_CONF_STRING_LENGTH_IMPL": {
+      "value": "element",
+      "doc": "Selects the implementation for string-length: 'element', 'word', 'clang_vector', or 'arch_vector'."
+    },
+    "LIBC_CONF_FIND_FIRST_CHARACTER_IMPL": {
+      "value": "element",
+      "doc": "Selects the implementation for find-first-character-related functions: 'element', 'word', 'clang_vector', or 'arch_vector'."
     },
     "LIBC_CONF_MEMSET_X86_USE_SOFTWARE_PREFETCHING": {
       "value": false,

libc/config/linux/arm/config.json

@@ -1,7 +1,10 @@
 {
   "string": {
-    "LIBC_CONF_STRING_UNSAFE_WIDE_READ": {
-      "value": false
+    "LIBC_CONF_STRING_LENGTH_IMPL": {
+      "value": "element"
+    }
+    "LIBC_CONF_FIND_FIRST_CHARACTER_IMPL": {
+      "value": "element"
     }
   }
 }

libc/config/linux/config.json

@@ -1,7 +1,10 @@
 {
   "string": {
-    "LIBC_CONF_STRING_UNSAFE_WIDE_READ": {
-      "value": true
+    "LIBC_CONF_STRING_LENGTH_IMPL": {
+      "value": "clang_vector",
+    },
+    "LIBC_CONF_FIND_FIRST_CHARACTER_IMPL": {
+      "value": "word",
     }
   }
 }

libc/config/linux/riscv/config.json

@@ -1,7 +1,10 @@
 {
   "string": {
-    "LIBC_CONF_STRING_UNSAFE_WIDE_READ": {
-      "value": false
+    "LIBC_CONF_STRING_LENGTH_IMPL": {
+      "value": "element"
+    }
+    "LIBC_CONF_FIND_FIRST_CHARACTER_IMPL": {
+      "value": "element"
     }
   }
 }

libc/docs/configure.rst

@@ -58,8 +58,9 @@ to learn about the defaults for your platform and target.
 * **"setjmp" options**
     - ``LIBC_CONF_SETJMP_AARCH64_RESTORE_PLATFORM_REGISTER``: Make setjmp save the value of x18, and longjmp restore it. The AArch64 ABI delegates this register to platform ABIs, which can choose whether to make it caller-saved.
 * **"string" options**
+    - ``LIBC_CONF_FIND_FIRST_CHARACTER_IMPL``: Selects the implementation for find-first-character-related functions: 'element', 'word', 'clang_vector', or 'arch_vector'.
     - ``LIBC_CONF_MEMSET_X86_USE_SOFTWARE_PREFETCHING``: Inserts prefetch for write instructions (PREFETCHW) for memset on x86 to recover performance when hardware prefetcher is disabled.
-    - ``LIBC_CONF_STRING_UNSAFE_WIDE_READ``: Read more than a byte at a time to perform byte-string operations like strlen.
+    - ``LIBC_CONF_STRING_LENGTH_IMPL``: Selects the implementation for string-length: 'element', 'word', 'clang_vector', or 'arch_vector'.
 * **"threads" options**
     - ``LIBC_CONF_THREAD_MODE``: The implementation used for Mutex, acceptable values are LIBC_THREAD_MODE_PLATFORM, LIBC_THREAD_MODE_SINGLE, and LIBC_THREAD_MODE_EXTERNAL.
 * **"time" options**

libc/src/string/memory_utils/aarch64/inline_strlen.h

@@ -16,7 +16,7 @@
 
 namespace LIBC_NAMESPACE_DECL {
 
-namespace neon {
+namespace internal::arch_vector {
 [[maybe_unused]] LIBC_NO_SANITIZE_OOB_ACCESS LIBC_INLINE static size_t
 string_length(const char *src) {
   using Vector __attribute__((may_alias)) = uint8x8_t;
@@ -44,9 +44,7 @@ string_length(const char *src) {
                                  (cpp::countr_zero(cmp) >> 3));
   }
 }
-} // namespace neon
-
-namespace string_length_impl = neon;
+} // namespace internal::arch_vector
 
 } // namespace LIBC_NAMESPACE_DECL
 #endif // __ARM_NEON

libc/src/string/memory_utils/generic/inline_strlen.h

@@ -14,7 +14,7 @@
 #include "src/__support/common.h"
 
 namespace LIBC_NAMESPACE_DECL {
-namespace internal {
+namespace clang_vector {
 
 // Exploit the underlying integer representation to do a variable shift.
 LIBC_INLINE constexpr cpp::simd_mask<char> shift_mask(cpp::simd_mask<char> m,
@@ -46,9 +46,8 @@ LIBC_NO_SANITIZE_OOB_ACCESS LIBC_INLINE size_t string_length(const char *src) {
              cpp::find_first_set(mask);
   }
 }
-} // namespace internal
+} // namespace clang_vector
 
-namespace string_length_impl = internal;
 } // namespace LIBC_NAMESPACE_DECL
 
 #endif // LLVM_LIBC_SRC_STRING_MEMORY_UTILS_GENERIC_INLINE_STRLEN_H

libc/src/string/memory_utils/x86_64/inline_strlen.h

@@ -15,7 +15,8 @@
 
 namespace LIBC_NAMESPACE_DECL {
 
-namespace string_length_internal {
+namespace internal::arch_vector {
+
 // Return a bit-mask with the nth bit set if the nth-byte in block_ptr is zero.
 template <typename Vector, typename Mask>
 LIBC_NO_SANITIZE_OOB_ACCESS LIBC_INLINE static Mask
@@ -92,15 +93,18 @@ namespace avx512 {
 }
 } // namespace avx512
 #endif
-} // namespace string_length_internal
 
+[[maybe_unused]] LIBC_INLINE size_t string_length(const char *src) {
 #if defined(__AVX512F__)
-namespace string_length_impl = string_length_internal::avx512;
+  return avx512::string_length(src);
 #elif defined(__AVX2__)
-namespace string_length_impl = string_length_internal::avx2;
+  return avx2::string_length(src);
 #else
-namespace string_length_impl = string_length_internal::sse2;
+  return sse2::string_length(src);
 #endif
+}
+
+} // namespace internal::arch_vector
 
 } // namespace LIBC_NAMESPACE_DECL
 

libc/src/string/string_optimization.h

@@ -0,0 +1,212 @@
+//===-- String Optimization -------------------------------------*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// Basic implementation and dispatch mechanism for performance-sensitive string-
+// related code.
+//
+//===----------------------------------------------------------------------===//
+
+#include "hdr/limits_macros.h"
+#include "hdr/stdint_proxy.h" // uintptr_t
+#include "hdr/types/size_t.h"
+#include "src/__support/CPP/type_traits.h" // cpp::is_same_v
+
+#if LIBC_HAS_VECTOR_TYPE
+#include "src/string/memory_utils/generic/inline_strlen.h"
+#endif
+#if defined(LIBC_TARGET_ARCH_IS_X86)
+#include "src/string/memory_utils/x86_64/inline_strlen.h"
+#elif defined(LIBC_TARGET_ARCH_IS_AARCH64)
+#include "src/string/memory_utils/aarch64/inline_strlen.h"
+#endif
+
+// Set sensible defaults
+#ifndef LIBC_COPT_STRING_LENGTH_IMPL
+#define LIBC_COPT_STRING_LENGTH_IMPL element
+#endif
+#ifndef LIBC_COPT_FIND_FIRST_CHARACTER_IMPL
+#define LIBC_COPT_STRING_LENGTH_IMPL element
+#endif
+
+namespace LIBC_NAMESPACE_DECL {
+namespace internal {
+
+#if !LIBC_HAS_VECTOR_TYPE
+// Forward any clang vector impls to architecture specific ones
+namespace arch_vector {}
+namespace clang_vector = arch_vector;
+#endif
+
+namespace element {
+// Element-by-element (usually a byte, but wider for wchar) implementations of
+// functions that search for data.  Slow, but easy to understand and analyze.
+
+// Returns the length of a string, denoted by the first occurrence
+// of a null terminator.
+LIBC_INLINE size_t string_length(const char *src) {
+  size_t length;
+  for (length = 0; *src; ++src, ++length)
+    ;
+  return length;
+}
+
+template <typename T> LIBC_INLINE size_t string_length_element(const T *src) {
+  size_t length;
+  for (length = 0; *src; ++src, ++length)
+    ;
+  return length;
+}
+
+LIBC_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;
+}
+} // namespace element
+
+namespace word {
+// Non-vector, implementations of functions that search for data by reading from
+// memory word-by-word.
+
+template <typename Word> LIBC_INLINE constexpr Word repeat_byte(Word byte) {
+  static_assert(CHAR_BIT == 8, "repeat_byte assumes a byte is 8 bits.");
+  constexpr size_t BITS_IN_BYTE = CHAR_BIT;
+  constexpr size_t BYTE_MASK = 0xff;
+  Word result = 0;
+  byte = byte & BYTE_MASK;
+  for (size_t i = 0; i < sizeof(Word); ++i)
+    result = (result << BITS_IN_BYTE) | byte;
+  return result;
+}
+
+// The goal of this function is to take in a block of arbitrary size and return
+// if it has any bytes equal to zero without branching. This is done by
+// transforming the block such that zero bytes become non-zero and non-zero
+// bytes become zero.
+// The first transformation relies on the properties of carrying in arithmetic
+// subtraction. Specifically, if 0x01 is subtracted from a byte that is 0x00,
+// then the result for that byte must be equal to 0xff (or 0xfe if the next byte
+// needs a carry as well).
+// The next transformation is a simple mask. All zero bytes will have the high
+// bit set after the subtraction, so each byte is masked with 0x80. This narrows
+// the set of bytes that result in a non-zero value to only zero bytes and bytes
+// with the high bit and any other bit set.
+// The final transformation masks the result of the previous transformations
+// with the inverse of the original byte. This means that any byte that had the
+// high bit set will no longer have it set, narrowing the list of bytes which
+// result in non-zero values to just the zero byte.
+template <typename Word> LIBC_INLINE constexpr bool has_zeroes(Word block) {
+  constexpr unsigned int LOW_BITS = repeat_byte<Word>(0x01);
+  constexpr Word HIGH_BITS = repeat_byte<Word>(0x80);
+  Word subtracted = block - LOW_BITS;
+  Word inverted = ~block;
+  return (subtracted & inverted & HIGH_BITS) != 0;
+}
+
+// Unsigned int is the default size for most processors, and on x86-64 it
+// performs better than larger sizes when the src pointer can't be assumed to
+// be aligned to a word boundary, so it's the size we use for reading the
+// string a block at a time.
+
+LIBC_INLINE size_t string_length(const char *src) {
+  using Word = unsigned int;
+  const char *char_ptr = src;
+  // Step 1: read 1 byte at a time to align to block size
+  for (; reinterpret_cast<uintptr_t>(char_ptr) % sizeof(Word) != 0;
+       ++char_ptr) {
+    if (*char_ptr == '\0')
+      return static_cast<size_t>(char_ptr - src);
+  }
+  // Step 2: read blocks
+  for (const Word *block_ptr = reinterpret_cast<const Word *>(char_ptr);
+       !has_zeroes<Word>(*block_ptr); ++block_ptr) {
+    char_ptr = reinterpret_cast<const char *>(block_ptr);
+  }
+  // Step 3: find the zero in the block
+  for (; *char_ptr != '\0'; ++char_ptr) {
+    ;
+  }
+  return static_cast<size_t>(char_ptr - src);
+}
+
+LIBC_NO_SANITIZE_OOB_ACCESS LIBC_INLINE void *
+find_first_character(const unsigned char *src, unsigned char ch,
+                     size_t max_strlen = cpp::numeric_limits<size_t>::max()) {
+  using Word = unsigned int;
+  const unsigned char *char_ptr = src;
+  size_t cur = 0;
+
+  // If the maximum size of the string is small, the overhead of aligning to a
+  // word boundary and generating a bitmask of the appropriate size may be
+  // greater than the gains from reading larger chunks. Based on some testing,
+  // the crossover point between when it's faster to just read bytewise and read
+  // blocks is somewhere between 16 and 32, so 4 times the size of the block
+  // should be in that range.
+  if (max_strlen < (sizeof(Word) * 4)) {
+    return element::find_first_character(src, ch, max_strlen);
+  }
+  size_t n = max_strlen;
+  // Step 1: read 1 byte at a time to align to block size
+  for (; reinterpret_cast<uintptr_t>(char_ptr) % sizeof(Word) != 0 && cur < n;
+       ++char_ptr, ++cur) {
+    if (*char_ptr == ch)
+      return const_cast<unsigned char *>(char_ptr);
+  }
+
+  const Word ch_mask = repeat_byte<Word>(ch);
+
+  // Step 2: read blocks
+  for (const Word *block_ptr = reinterpret_cast<const Word *>(char_ptr);
+       !has_zeroes<Word>((*block_ptr) ^ ch_mask) && cur < n;
+       ++block_ptr, cur += sizeof(Word)) {
+    char_ptr = reinterpret_cast<const unsigned char *>(block_ptr);
+  }
+
+  // Step 3: find the match in the block
+  for (; *char_ptr != ch && cur < n; ++char_ptr, ++cur) {
+    ;
+  }
+
+  if (*char_ptr != ch || cur >= n)
+    return static_cast<void *>(nullptr);
+
+  return const_cast<unsigned char *>(char_ptr);
+}
+
+} // namespace word
+
+// Dispatch mechanism for implementations of performance-sensitive
+// functions. Always measure, but generally from lower- to higher-performance
+// order:
+//
+// 1. element - read char-by-char or wchar-by-wchar
+// 3. word - read word-by-word
+// 3. clang_vector - read using clang's internal vector types
+// 4. arch_vector - hand-coded per architecture. Possibly in asm, or with
+// intrinsics.
+//
+// The called implemenation is chosen at build-time by setting
+// LIBC_CONF_{FUNC}_IMPL in config.json
+static constexpr auto &string_length_impl =
+    LIBC_COPT_STRING_LENGTH_IMPL::string_length;
+static constexpr auto &find_first_character_impl =
+    LIBC_COPT_FIND_FIRST_CHARACTER_IMPL::find_first_character;
+
+template <typename T> LIBC_INLINE size_t string_length(const T *src) {
+  if constexpr (cpp::is_same_v<T, char>)
+    return string_length_impl(src);
+  return element::string_length_element<T>(src);
+}
+
+// Returns the first occurrence of 'ch' within the first 'n' characters of
+// 'src'. If 'ch' is not found, returns nullptr.
+LIBC_INLINE void *find_first_character(const unsigned char *src,
+                                       unsigned char ch, size_t max_strlen) {
+  return find_first_character_impl(src, ch, max_strlen);
+}