i965/tiled_memcpy: Optimize RGBA -> BGRA swizzle.

Replaces four byte loads and four byte stores with a load, bswap,
rotate, store; or a movbe, rotate, store.

Reviewed-by: Roland Scheidegger <sroland@vmware.com>

diff --git a/src/mesa/drivers/dri/i965/intel_tiled_memcpy.c b/src/mesa/drivers/dri/i965/intel_tiled_memcpy.c
index 0a68751d5d03f10a958957d39beb38ea9b7a7d68..fa5ec75529880da4ff651175bd0a7383adfe33e8 100644 (file)
--- a/src/mesa/drivers/dri/i965/intel_tiled_memcpy.c
+++ b/src/mesa/drivers/dri/i965/intel_tiled_memcpy.c
@@ -56,24 +56,27 @@ static const uint32_t ytile_width = 128;
 static const uint32_t ytile_height = 32;
 static const uint32_t ytile_span = 16;
 
+static inline uint32_t
+ror(uint32_t n, uint32_t d)
+{
+   return (n >> d) | (n << (32 - d));
+}
+
 /**
  * Copy RGBA to BGRA - swap R and B.
  */
 static inline void *
 rgba8_copy(void *dst, const void *src, size_t bytes)
 {
-   uint8_t *d = dst;
-   uint8_t const *s = src;
+   uint32_t *d = dst;
+   uint32_t const *s = src;
 
    assert(bytes % 4 == 0);
 
    while (bytes >= 4) {
-      d[0] = s[2];
-      d[1] = s[1];
-      d[2] = s[0];
-      d[3] = s[3];
-      d += 4;
-      s += 4;
+      *d = ror(__builtin_bswap32(*s), 8);
+      d += 1;
+      s += 1;
       bytes -= 4;
    }
    return dst;