From dd96d3b9d4d6a6999d3b198659c57991351605ac Mon Sep 17 00:00:00 2001
From: Ran Benita <ran234@gmail.com>
Date: Sat, 25 Mar 2017 18:01:38 +0300
Subject: [PATCH] Speed up apply_mask()

This function is the most speed-critical in the library. In profiles,
this optimization reduces it from ~75% of the profile to ~55%.

I have tried several approaches, but didn't manage to improve on this
one (LLVM already unrolls the loop here). Though I'm sure it is possible.
---
 src/protocol/frame/frame.rs | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/src/protocol/frame/frame.rs b/src/protocol/frame/frame.rs
index 3719e25..de9ef59 100644
--- a/src/protocol/frame/frame.rs
+++ b/src/protocol/frame/frame.rs
@@ -14,9 +14,8 @@ use error::{Error, Result};
 use super::coding::{OpCode, Control, Data, CloseCode};
 
 fn apply_mask(buf: &mut [u8], mask: &[u8; 4]) {
-    let iter = buf.iter_mut().zip(mask.iter().cycle());
-    for (byte, &key) in iter {
-        *byte ^= key
+    for (i, byte) in buf.iter_mut().enumerate() {
+        *byte ^= mask[i & 3];
     }
 }