From ce08735c06515225f4de6cd9cd1d4858c2be034d Mon Sep 17 00:00:00 2001
From: Adrian Johnson <ajohnson@redneon.com>
Date: Fri, 31 Oct 2014 22:43:32 +1030
Subject: [PATCH] Improve performance of cpu_to_be32 and be32_to_cpu

By switching to the more common form, gcc and clang emit a single
bswap instruction and truetype subsetting of large fonts runs about
15% faster.
---
 src/cairoint.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/cairoint.h b/src/cairoint.h
index 07ced422d..5bca00389 100644
--- a/src/cairoint.h
+++ b/src/cairoint.h
@@ -229,7 +229,7 @@ be16_to_cpu(uint16_t v)
 static inline uint32_t cairo_const
 cpu_to_be32(uint32_t v)
 {
-    return (cpu_to_be16 (v) << 16) | cpu_to_be16 (v >> 16);
+    return (v >> 24) | ((v >> 8) & 0xff00) | ((v << 8) & 0xff0000) | (v << 24);
 }
 
 static inline uint32_t cairo_const