[Pixman] [PATCH v2 04/11] vmx: implement fast path composite_over_8888_8888

[Oded Gabbay]

Copied impl. from sse2 file and edited to use vmx functions

It was benchmarked against commid id 2be523b from pixman/master

POWER8, 16 cores, 3.4GHz, ppc64le :

reference memcpy speed = 27036.4MB/s (6759.1MP/s for 32bpp fills)

                Before           After           Change
              ---------------------------------------------
L1              129.47          1054.62         +714.57%
L2              138.31          1011.02         +630.98%
M               139.99          1008.65         +620.52%
HT              122.11          468.45          +283.63%
VT              121.06          532.21          +339.62%
R               108.48          240.5           +121.70%
RT              77.87           116.7           +49.87%
Kops/s          758             981             +29.42%

Signed-off-by: Oded Gabbay <oded.gabbay at gmail.com>
Acked-by: Siarhei Siamashka <siarhei.siamashka at gmail.com>
---
 pixman/pixman-vmx.c | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/pixman/pixman-vmx.c b/pixman/pixman-vmx.c
index 61fdb80..9eae31c 100644
--- a/pixman/pixman-vmx.c
+++ b/pixman/pixman-vmx.c
@@ -2688,8 +2688,38 @@ vmx_fill (pixman_implementation_t *imp,
     return TRUE;
 }
 
+static void
+vmx_composite_over_8888_8888 (pixman_implementation_t *imp,
+                               pixman_composite_info_t *info)
+{
+    PIXMAN_COMPOSITE_ARGS (info);
+    int dst_stride, src_stride;
+    uint32_t    *dst_line, *dst;
+    uint32_t    *src_line, *src;
+
+    PIXMAN_IMAGE_GET_LINE (
+    dest_image, dest_x, dest_y, uint32_t, dst_stride, dst_line, 1);
+    PIXMAN_IMAGE_GET_LINE (
+    src_image, src_x, src_y, uint32_t, src_stride, src_line, 1);
+
+    dst = dst_line;
+    src = src_line;
+
+    while (height--)
+    {
+        vmx_combine_over_u (imp, op, dst, src, NULL, width);
+
+        dst += dst_stride;
+        src += src_stride;
+    }
+}
+
 static const pixman_fast_path_t vmx_fast_paths[] =
 {
+    PIXMAN_STD_FAST_PATH (OVER, a8r8g8b8, null, a8r8g8b8, vmx_composite_over_8888_8888),
+    PIXMAN_STD_FAST_PATH (OVER, a8r8g8b8, null, x8r8g8b8, vmx_composite_over_8888_8888),
+    PIXMAN_STD_FAST_PATH (OVER, a8b8g8r8, null, a8b8g8r8, vmx_composite_over_8888_8888),
+    PIXMAN_STD_FAST_PATH (OVER, a8b8g8r8, null, x8b8g8r8, vmx_composite_over_8888_8888),
     {   PIXMAN_OP_NONE	},
 };
 
-- 
2.4.3