vmx: implement fast path vmx_composite_src_x888_8888

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

POWER8, 8 cores, 3.4GHz, RHEL 7.1 ppc64le.
reference memcpy speed = 24764.8MB/s (6191.2MP/s for 32bpp fills)

                Before           After           Change
              ---------------------------------------------
L1              1115.4          5006.49         +348.85%
L2              1112.26         4338.01         +290.02%
M               1110.54         2524.15         +127.29%
HT              745.41          1140.03         +52.94%
VT              749.03          1287.13         +71.84%
R               423.91          547.6           +29.18%
RT              205.79          194.98          -5.25%
Kops/s          1414            1361            -3.75%

cairo trimmed benchmarks :

Speedups
========
t-gnome-system-monitor  1402.62  -> 1212.75 :  1.16x
   t-firefox-asteroids   533.92  ->  474.50 :  1.13x

Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Acked-by: Siarhei Siamashka <siarhei.siamashka@gmail.com>

1 files changed, 60 insertions, 0 deletions

diff --git a/pixman/pixman-vmx.c b/pixman/pixman-vmx.c
index 47393dc..64e9125 100644
--- a/pixman/pixman-vmx.c
+++ b/pixman/pixman-vmx.c
@@ -2689,6 +2689,62 @@ vmx_fill (pixman_implementation_t *imp,
 }
 
 static void
+vmx_composite_src_x888_8888 (pixman_implementation_t *imp,
+			      pixman_composite_info_t *info)
+{
+    PIXMAN_COMPOSITE_ARGS (info);
+    uint32_t    *dst_line, *dst;
+    uint32_t    *src_line, *src;
+    int32_t w;
+    int dst_stride, src_stride;
+
+    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);
+
+    while (height--)
+    {
+	dst = dst_line;
+	dst_line += dst_stride;
+	src = src_line;
+	src_line += src_stride;
+	w = width;
+
+	while (w && (uintptr_t)dst & 15)
+	{
+	    *dst++ = *src++ | 0xff000000;
+	    w--;
+	}
+
+	while (w >= 16)
+	{
+	    vector unsigned int vmx_src1, vmx_src2, vmx_src3, vmx_src4;
+
+	    vmx_src1 = load_128_unaligned (src);
+	    vmx_src2 = load_128_unaligned (src + 4);
+	    vmx_src3 = load_128_unaligned (src + 8);
+	    vmx_src4 = load_128_unaligned (src + 12);
+
+	    save_128_aligned (dst, vec_or (vmx_src1, mask_ff000000));
+	    save_128_aligned (dst + 4, vec_or (vmx_src2, mask_ff000000));
+	    save_128_aligned (dst + 8, vec_or (vmx_src3, mask_ff000000));
+	    save_128_aligned (dst + 12, vec_or (vmx_src4, mask_ff000000));
+
+	    dst += 16;
+	    src += 16;
+	    w -= 16;
+	}
+
+	while (w)
+	{
+	    *dst++ = *src++ | 0xff000000;
+	    w--;
+	}
+    }
+}
+
+static void
 vmx_composite_over_8888_8888 (pixman_implementation_t *imp,
                                pixman_composite_info_t *info)
 {
@@ -2914,6 +2970,10 @@ static const pixman_fast_path_t vmx_fast_paths[] =
     PIXMAN_STD_FAST_PATH (ADD, a8r8g8b8, null, a8r8g8b8, vmx_composite_add_8888_8888),
     PIXMAN_STD_FAST_PATH (ADD, a8b8g8r8, null, a8b8g8r8, vmx_composite_add_8888_8888),
 
+    /* PIXMAN_OP_SRC */
+    PIXMAN_STD_FAST_PATH (SRC, x8r8g8b8, null, a8r8g8b8, vmx_composite_src_x888_8888),
+    PIXMAN_STD_FAST_PATH (SRC, x8b8g8r8, null, a8b8g8r8, vmx_composite_src_x888_8888),
+
     {   PIXMAN_OP_NONE	},
 };