From 462b73c1fe1f67a62223a3ccf830f02a2571c016 Mon Sep 17 00:00:00 2001
From: Ian Kronquist <iankronquist@gmail.com>
Date: Mon, 30 Sep 2019 09:02:47 -0700
Subject: [PATCH] Implement bcmp (#315)

As of LLVM 9.0, certain calls to memcmp may be converted to bcmp, which I guess
could save a single subtraction on some architectures. [1]

bcmp is just like memcmp except instead of returning the difference between the
two differing bytes, it returns non-zero instead. As such, memcmp is a valid
implementation of bcmp.

If we care about size, bcmp should just call memcmp.
If we care about speed, we can change bcmp to look like this instead:
```rust
pub unsafe extern "C" fn bcmp(s1: *const u8, s2: *const u8, n: usize) -> i32 {
    let mut i = 0;
    while i < n {
        let a = *s1.offset(i as isize);
        let b = *s2.offset(i as isize);
        if a != b {
            return 1;
        }
        i += 1;
    }
    0
}
```

In this PR I do not address any changes which may or may not be needed for arm
aebi as I lack proper test hardware.

[1]: https://releases.llvm.org/9.0.0/docs/ReleaseNotes.html#noteworthy-optimizations
---
 src/mem.rs | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/src/mem.rs b/src/mem.rs
index 76372d9..7b8a37f 100644
--- a/src/mem.rs
+++ b/src/mem.rs
@@ -63,6 +63,11 @@ pub unsafe extern "C" fn memcmp(s1: *const u8, s2: *const u8, n: usize) -> i32 {
     0
 }
 
+#[cfg_attr(all(feature = "mem", not(feature = "mangled-names")), no_mangle)]
+pub unsafe extern "C" fn bcmp(s1: *const u8, s2: *const u8, n: usize) -> i32 {
+    memcmp(s1, s2, n)
+}
+
 // `bytes` must be a multiple of `mem::size_of::<T>()`
 fn memcpy_element_unordered_atomic<T: Copy>(dest: *mut T, src: *const T, bytes: usize) {
     unsafe {