[Pixman] [PATCH 6/6] Faster fetch for the C variant of r5g6b5 src/dest iterator

[Siarhei Siamashka]

Processing two pixels at once is used to reduce the number of
arithmetic operations.

The speedup relative to the generic fetch_scanline_r5g6b5() from
"pixman-access.c" (pixman was compiled with gcc 4.7.2):

    MIPS 74K        480MHz  :  20.32 MPix/s ->  26.47 MPix/s
    ARM11           700MHz  :  34.95 MPix/s ->  38.22 MPix/s
    ARM Cortex-A8  1000MHz  :  87.44 MPix/s -> 100.92 MPix/s
    ARM Cortex-A9  1700MHz  : 150.95 MPix/s -> 158.13 MPix/s
    ARM Cortex-A15 1700MHz  : 148.91 MPix/s -> 155.42 MPix/s
    IBM Cell PPU   3200MHz  :  75.29 MPix/s ->  98.33 MPix/s
    Intel Core i7  2800MHz  : 257.02 MPix/s -> 376.93 MPix/s

That's the performance for C code (SIMD and assembly optimizations
are disabled via PIXMAN_DISABLE environment variable).
---
 pixman/pixman-fast-path.c |   31 ++++++++++++++++++++++++++++++-
 1 files changed, 30 insertions(+), 1 deletions(-)

diff --git a/pixman/pixman-fast-path.c b/pixman/pixman-fast-path.c
index 4aa6d73..696aca9 100644
--- a/pixman/pixman-fast-path.c
+++ b/pixman/pixman-fast-path.c
@@ -2176,11 +2176,40 @@ fast_fetch_r5g6b5 (pixman_iter_t *iter, const uint32_t 
*mask)
 
     iter->bits += iter->stride;
 
-    while (w > 0)
+    /* Align the source buffer at 4 bytes boundary */
+    if (w > 0 && ((uintptr_t)src & 3))
     {
        *dst++ = convert_0565_to_8888 (*src++);
        w--;
     }
+    /* Process two pixels per iteration */
+    while ((w -= 2) >= 0)
+    {
+       uint32_t sr, sb, sg, t0, t1;
+       uint32_t s = *(const uint32_t *)src;
+       src += 2;
+       sr = (s >> 8) & 0x00F800F8;
+       sb = (s << 3) & 0x00F800F8;
+       sg = (s >> 3) & 0x00FC00FC;
+       sr |= sr >> 5;
+       sb |= sb >> 5;
+       sg |= sg >> 6;
+       t0 = ((sr << 16) & 0x00FF0000) | ((sg << 8) & 0x0000FF00) |
+            (sb & 0xFF) | 0xFF000000;
+       t1 = (sr & 0x00FF0000) | ((sg >> 8) & 0x0000FF00) |
+            (sb >> 16) | 0xFF000000;
+#ifdef WORDS_BIGENDIAN
+       *dst++ = t1;
+       *dst++ = t0;
+#else
+       *dst++ = t0;
+       *dst++ = t1;
+#endif
+    }
+    if (w & 1)
+    {
+       *dst = convert_0565_to_8888 (*src);
+    }
 
     return iter->buffer;
 }
-- 
1.7.8.6

_______________________________________________
Pixman mailing list
Pixman@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/pixman