Speed up SipHasher128.

The current code in `SipHasher128::short_write` is inefficient. It uses
`u8to64_le` (which is complex and slow) to extract just the right number of
bytes of the input into a u64 and pad the result with zeroes. It then
left-shifts that value in order to bitwise-OR it with `self.tail`.

For example, imagine we have a u32 input 0xIIHH_GGFF and only need three bytes
to fill up `self.tail`. The current code uses `u8to64_le` to construct
0x0000_0000_00HH_GGFF, which is just 0xIIHH_GGFF with the 0xII removed and
zero-extended to a u64. The code then left-shifts that value by five bytes --
discarding the 0x00 byte that replaced the 0xII byte! -- to give
0xHHGG_FF00_0000_0000. It then then ORs that value with self.tail.

There's a much simpler way to do it: zero-extend to u64 first, then left shift.
E.g. 0xIIHH_GGFF is zero-extended to 0x0000_0000_IIHH_GGFF, and then
left-shifted to 0xHHGG_FF00_0000_0000. We don't have to take time to exclude
the unneeded 0xII byte, because it just gets shifted out anyway! It also avoids
multiple occurrences of `unsafe`.

There's a similar story with the setting of `self.tail` at the method's end.
The current code uses `u8to64_le` to extract the remaining part of the input,
but the same effect can be achieved more quickly with a right shift on the
zero-extended input.

This commit changes `SipHasher128` to use the simpler shift-based approach. The
code is also smaller, which means that `short_write` is now inlined where
previously it wasn't, which makes things faster again. This gives big
speed-ups for all incremental builds, especially "baseline" incremental
builds.

src/librustc_data_structures/sip128.rs

@@ -4,7 +4,6 @@ use std::cmp;
 use std::hash::Hasher;
 use std::mem;
 use std::ptr;
-use std::slice;
 
 #[cfg(test)]
 mod tests;
@@ -122,42 +121,55 @@ impl SipHasher128 {
         self.state.v1 ^= 0xee;
     }
 
-    // Specialized write function that is only valid for buffers with len <= 8.
-    // It's used to force inlining of write_u8 and write_usize, those would normally be inlined
-    // except for composite types (that includes slices and str hashing because of delimiter).
-    // Without this extra push the compiler is very reluctant to inline delimiter writes,
-    // degrading performance substantially for the most common use cases.
+    // Specialized write function for values with size <= 8.
     #[inline]
-    fn short_write(&mut self, msg: &[u8]) {
-        debug_assert!(msg.len() <= 8);
-        let length = msg.len();
-        self.length += length;
+    fn short_write<T>(&mut self, _x: T, x: u64) {
+        let size = mem::size_of::<T>();
+        self.length += size;
+
+        // The original number must be zero-extended, not sign-extended.
+        debug_assert!(if size < 8 { x >> (8 * size) == 0 } else { true });
 
+        // The number of bytes needed to fill `self.tail`.
         let needed = 8 - self.ntail;
-        let fill = cmp::min(length, needed);
-        if fill == 8 {
-            self.tail = unsafe { load_int_le!(msg, 0, u64) };
-        } else {
-            self.tail |= unsafe { u8to64_le(msg, 0, fill) } << (8 * self.ntail);
-            if length < needed {
-                self.ntail += length;
-                return;
-            }
+
+        // Imagine that `self.tail` is 0x0000_00EE_DDCC_BBAA, `self.ntail`
+        // is 5, and therefore `needed` is 3.
+        //
+        // - Scenario 1, `self.write_u8(0xFF)`: we have already zero-extended
+        //   the input to 0x0000_0000_0000_00FF. We now left-shift it five
+        //   bytes, giving 0x0000_FF00_0000_0000. We then bitwise-OR that value
+        //   into `self.tail`, resulting in 0x0000_FFEE_DDCC_BBAA.
+        //   (Zero-extension of the original input is critical in this scenario
+        //   because we don't want the high two bytes of `self.tail` to be
+        //   touched by the bitwise-OR.) `self.tail` is not yet full, so we
+        //   return early, after updating `self.ntail` to 6.
+        //
+        // - Scenario 2, `self.write_u32(0xIIHH_GGFF)`: we have zero-extended the
+        //   input to 0x0000_0000_IIHH_GGFF. We now left-shift it five bytes,
+        //   giving 0xHHGG_FF00_0000_0000. We then bitwise-OR that value into
+        //   `self.tail`, resulting in 0xHHGG_FFEE_DDCC_BBAA. `self.tail` is
+        //   now full, and we can use it to update `self.state`.
+        //
+        self.tail |= x << (8 * self.ntail);
+        if size < needed {
+            self.ntail += size;
+            return;
         }
+
+        // `self.tail` is full, process it.
         self.state.v3 ^= self.tail;
         Sip24Rounds::c_rounds(&mut self.state);
         self.state.v0 ^= self.tail;
 
-        // Buffered tail is now flushed, process new input.
-        self.ntail = length - needed;
-        self.tail = unsafe { u8to64_le(msg, needed, self.ntail) };
-    }
-
-    #[inline(always)]
-    fn short_write_gen<T>(&mut self, x: T) {
-        let bytes =
-            unsafe { slice::from_raw_parts(&x as *const T as *const u8, mem::size_of::<T>()) };
-        self.short_write(bytes);
+        // Continuing scenario 2: we have one byte left over from the input. We
+        // set `self.ntail` to 1 and `self.tail` to `(0x0000_0000_IIHH_GGFF >>
+        // 8*3)`, which is 0x0000_0000_0000_00II.
+        //
+        // The `if` is needed to avoid shifting by 64 bits, which Rust
+        // complains about.
+        self.ntail = size - needed;
+        self.tail = if needed < 8 { x >> (8 * needed) } else { 0 };
     }
 
     #[inline]
@@ -182,52 +194,52 @@ impl SipHasher128 {
 impl Hasher for SipHasher128 {
     #[inline]
     fn write_u8(&mut self, i: u8) {
-        self.short_write_gen(i);
+        self.short_write(i, i as u64);
     }
 
     #[inline]
     fn write_u16(&mut self, i: u16) {
-        self.short_write_gen(i);
+        self.short_write(i, i as u64);
     }
 
     #[inline]
     fn write_u32(&mut self, i: u32) {
-        self.short_write_gen(i);
+        self.short_write(i, i as u64);
     }
 
     #[inline]
     fn write_u64(&mut self, i: u64) {
-        self.short_write_gen(i);
+        self.short_write(i, i as u64);
     }
 
     #[inline]
     fn write_usize(&mut self, i: usize) {
-        self.short_write_gen(i);
+        self.short_write(i, i as u64);
     }
 
     #[inline]
     fn write_i8(&mut self, i: i8) {
-        self.short_write_gen(i);
+        self.short_write(i, i as u8 as u64);
     }
 
     #[inline]
     fn write_i16(&mut self, i: i16) {
-        self.short_write_gen(i);
+        self.short_write(i, i as u16 as u64);
     }
 
     #[inline]
     fn write_i32(&mut self, i: i32) {
-        self.short_write_gen(i);
+        self.short_write(i, i as u32 as u64);
     }
 
     #[inline]
     fn write_i64(&mut self, i: i64) {
-        self.short_write_gen(i);
+        self.short_write(i, i as i64 as u64);
     }
 
     #[inline]
     fn write_isize(&mut self, i: isize) {
-        self.short_write_gen(i);
+        self.short_write(i, i as usize as u64);
     }
 
     #[inline]