Specialize strlen for x86_64.

src/mem/impls.rs

@@ -279,3 +279,13 @@ pub unsafe fn compare_bytes(s1: *const u8, s2: *const u8, n: usize) -> i32 {
     }
     0
 }
+
+#[inline(always)]
+pub unsafe fn c_string_length(mut s: *const core::ffi::c_char) -> usize {
+    let mut n = 0;
+    while *s != 0 {
+        n += 1;
+        s = s.add(1);
+    }
+    n
+}

src/mem/mod.rs

@@ -63,13 +63,7 @@ intrinsics! {
     #[mem_builtin]
     #[cfg_attr(not(all(target_os = "windows", target_env = "gnu")), linkage = "weak")]
     pub unsafe extern "C" fn strlen(s: *const core::ffi::c_char) -> usize {
-        let mut n = 0;
-        let mut s = s;
-        while *s != 0 {
-            n += 1;
-            s = s.offset(1);
-        }
-        n
+        impls::c_string_length(s)
     }
 }
 

src/mem/x86_64.rs

@@ -173,6 +173,35 @@ pub unsafe fn compare_bytes(a: *const u8, b: *const u8, n: usize) -> i32 {
     c16(a.cast(), b.cast(), n)
 }
 
+#[inline(always)]
+pub unsafe fn c_string_length(s: *const core::ffi::c_char) -> usize {
+    let mut n: usize;
+
+    asm!(
+        // search for a zero byte
+        "xor al, al",
+
+        // unbounded memory region
+        "xor rcx, rcx",
+        "not rcx",
+
+        // forward direction
+        "cld",
+
+        // perform search
+        "repne scasb",
+
+        // extract length
+        "not rcx",
+        "dec rcx",
+        inout("rdi") s => _,
+        out("rcx") n,
+        options(nostack),
+    );
+
+    n
+}
+
 /// Determine optimal parameters for a `rep` instruction.
 fn rep_param(dest: *mut u8, mut count: usize) -> (usize, usize, usize) {
     // Unaligned writes are still slow on modern processors, so align the destination address.