vmx: implement fast path vmx_composite_over_n_8888implement_vmx_fastpaths

Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>

1 files changed, 71 insertions, 0 deletions

diff --git a/pixman/pixman-vmx.c b/pixman/pixman-vmx.c
index 23bee2f..7fbef83 100644
--- a/pixman/pixman-vmx.c
+++ b/pixman/pixman-vmx.c
@@ -3164,6 +3164,75 @@ vmx_composite_src_x888_8888 (pixman_implementation_t *imp,
 }
 
 static void
+vmx_composite_over_n_8888 (pixman_implementation_t *imp,
+                            pixman_composite_info_t *info)
+{
+    PIXMAN_COMPOSITE_ARGS (info);
+    uint32_t src;
+    uint32_t    *dst_line, *dst, d;
+    int32_t w;
+    int dst_stride;
+    vector unsigned int vmx_src, vmx_alpha;
+    vector unsigned int vmx_dst, vmx_dst_lo, vmx_dst_hi;
+
+    src = _pixman_image_get_solid (imp, src_image, dest_image->bits.format);
+
+    if (src == 0)
+	return;
+
+    PIXMAN_IMAGE_GET_LINE (
+	dest_image, dest_x, dest_y, uint32_t, dst_stride, dst_line, 1);
+
+    vmx_src = expand_pixel_32_1x128 (src);
+    vmx_alpha = expand_alpha_1x128 (vmx_src);
+
+    while (height--)
+    {
+	dst = dst_line;
+
+	dst_line += dst_stride;
+	w = width;
+
+	while (w && (uintptr_t)dst & 15)
+	{
+	    d = *dst;
+	    *dst++ = pack_1x128_32 (over (vmx_src,
+					  vmx_alpha,
+					  unpack_32_1x128 (d)));
+	    w--;
+	}
+
+	while (w >= 4)
+	{
+	    vmx_dst = load_128_aligned(dst);
+
+	    unpack_128_2x128 (vmx_dst, (vector unsigned int) AVV(0),
+			      &vmx_dst_lo, &vmx_dst_hi);
+
+	    over_2x128 (&vmx_src, &vmx_src,
+			&vmx_alpha, &vmx_alpha,
+			&vmx_dst_lo, &vmx_dst_hi);
+
+	    /* rebuild the 4 pixel data and save*/
+	    save_128_aligned (dst, pack_2x128_128 (vmx_dst_lo, vmx_dst_hi));
+
+	    w -= 4;
+	    dst += 4;
+	}
+
+	while (w)
+	{
+	    d = *dst;
+	    *dst++ = pack_1x128_32 (over (vmx_src,
+					  vmx_alpha,
+					  unpack_32_1x128 (d)));
+	    w--;
+	}
+
+    }
+}
+
+static void
 vmx_composite_over_8888_8888 (pixman_implementation_t *imp,
                                pixman_composite_info_t *info)
 {
@@ -3499,6 +3568,8 @@ FAST_NEAREST_MAINLOOP (vmx_8888_8888_normal_OVER,
 static const pixman_fast_path_t vmx_fast_paths[] =
 {
     /* PIXMAN_OP_OVER */
+    PIXMAN_STD_FAST_PATH (OVER, solid, null, a8r8g8b8, vmx_composite_over_n_8888),
+    PIXMAN_STD_FAST_PATH (OVER, solid, null, x8r8g8b8, vmx_composite_over_n_8888),
     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),