From eb7b162ea06091a1bc8b976ae43ee62783dc9fef Mon Sep 17 00:00:00 2001
From: Joseph Huber <huberjn@outlook.com>
Date: Tue, 2 Sep 2025 06:11:06 -0500
Subject:  [libc] Implement generic SIMD helper 'simd.h' and implement strlen 
 (#152605)

Summary:
This PR introduces a new 'simd.h' header that implements an interface
similar to the proposed `stdx::simd` in C++. However, we instead wrap
around the LLVM internal type. This makes heavy use of the clang vector
extensions and boolean vectors, instead using primitive vector types
instead of a class (many benefits to this).

I use this interface to implement a generic strlen implementation, but
propse we use this for math. Right now this requires a feature only
introduced in clang-22.
---
 libc/src/string/CMakeLists.txt                     |  1 +
 .../string/memory_utils/generic/inline_strlen.h    | 53 ++++++++++++++++++++++
 libc/src/string/string_utils.h                     |  6 ++-
 3 files changed, 58 insertions(+), 2 deletions(-)
 create mode 100644 libc/src/string/memory_utils/generic/inline_strlen.h

(limited to 'libc/src/string')

diff --git a/libc/src/string/CMakeLists.txt b/libc/src/string/CMakeLists.txt
index 809decfbe5f0..5c9f622d4439 100644
--- a/libc/src/string/CMakeLists.txt
+++ b/libc/src/string/CMakeLists.txt
@@ -20,6 +20,7 @@ add_header_library(
     libc.hdr.stdint_proxy
     libc.src.__support.CPP.bitset
     libc.src.__support.CPP.type_traits
+    libc.src.__support.CPP.simd
     libc.src.__support.common
   ${string_config_options}
 )
diff --git a/libc/src/string/memory_utils/generic/inline_strlen.h b/libc/src/string/memory_utils/generic/inline_strlen.h
new file mode 100644
index 000000000000..111da35b85ee
--- /dev/null
+++ b/libc/src/string/memory_utils/generic/inline_strlen.h
@@ -0,0 +1,53 @@
+//===-- Strlen for generic SIMD types -------------------------------------===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_LIBC_SRC_STRING_MEMORY_UTILS_GENERIC_INLINE_STRLEN_H
+#define LLVM_LIBC_SRC_STRING_MEMORY_UTILS_GENERIC_INLINE_STRLEN_H
+
+#include "src/__support/CPP/simd.h"
+#include "src/__support/common.h"
+
+namespace LIBC_NAMESPACE_DECL {
+namespace internal {
+
+// Exploit the underlying integer representation to do a variable shift.
+LIBC_INLINE constexpr cpp::simd_mask<char> shift_mask(cpp::simd_mask<char> m,
+                                                      size_t shift) {
+  using bitmask_ty = cpp::internal::get_as_integer_type_t<cpp::simd_mask<char>>;
+  bitmask_ty r = cpp::bit_cast<bitmask_ty>(m) >> shift;
+  return cpp::bit_cast<cpp::simd_mask<char>>(r);
+}
+
+[[clang::no_sanitize("address")]] LIBC_INLINE size_t
+string_length(const char *src) {
+  constexpr cpp::simd<char> null_byte = cpp::splat('\0');
+
+  size_t alignment = alignof(cpp::simd<char>);
+  const cpp::simd<char> *aligned = reinterpret_cast<const cpp::simd<char> *>(
+      __builtin_align_down(src, alignment));
+
+  cpp::simd<char> chars = cpp::load_aligned<cpp::simd<char>>(aligned);
+  cpp::simd_mask<char> mask = cpp::simd_cast<bool>(chars == null_byte);
+  size_t offset = src - reinterpret_cast<const char *>(aligned);
+  if (cpp::any_of(shift_mask(mask, offset)))
+    return cpp::find_first_set(shift_mask(mask, offset));
+
+  for (;;) {
+    cpp::simd<char> chars = cpp::load_aligned<cpp::simd<char>>(++aligned);
+    cpp::simd_mask<char> mask = cpp::simd_cast<bool>(chars == null_byte);
+    if (cpp::any_of(mask))
+      return (reinterpret_cast<const char *>(aligned) - src) +
+             cpp::find_first_set(mask);
+  }
+}
+} // namespace internal
+
+namespace string_length_impl = internal;
+} // namespace LIBC_NAMESPACE_DECL
+
+#endif // LLVM_LIBC_SRC_STRING_MEMORY_UTILS_GENERIC_INLINE_STRLEN_H
diff --git a/libc/src/string/string_utils.h b/libc/src/string/string_utils.h
index ce461581b9d9..26e9adde0d66 100644
--- a/libc/src/string/string_utils.h
+++ b/libc/src/string/string_utils.h
@@ -23,14 +23,16 @@
 #include "src/__support/macros/optimization.h" // LIBC_UNLIKELY
 
 #if defined(LIBC_COPT_STRING_UNSAFE_WIDE_READ)
-#if defined(LIBC_TARGET_ARCH_IS_X86)
+#if LIBC_HAS_VECTOR_TYPE
+#include "src/string/memory_utils/generic/inline_strlen.h"
+#elif defined(LIBC_TARGET_ARCH_IS_X86)
 #include "src/string/memory_utils/x86_64/inline_strlen.h"
 #elif defined(LIBC_TARGET_ARCH_IS_AARCH64) && defined(__ARM_NEON)
 #include "src/string/memory_utils/aarch64/inline_strlen.h"
 #else
 namespace string_length_impl = LIBC_NAMESPACE::wide_read;
 #endif
-#endif
+#endif // defined(LIBC_COPT_STRING_UNSAFE_WIDE_READ)
 
 namespace LIBC_NAMESPACE_DECL {
 namespace internal {
-- 
cgit v1.2.3