[Pixman] [PATCH v2 11/11] vmx: implement fast path iterator vmx_fetch_a8

[Oded Gabbay]

no changes were observed when running cairo trimmed benchmarks.

Running "lowlevel-blt-bench src_8_8888" on POWER8, 8 cores,
3.4GHz, RHEL 7.1 ppc64le gave the following results:

reference memcpy speed = 25197.2MB/s (6299.3MP/s for 32bpp fills)

                Before          After           Change
              --------------------------------------------
L1              965.34          3936           +307.73%
L2              942.99          3436.29        +264.40%
M               902.24          2757.77        +205.66%
HT              448.46          784.99         +75.04%
VT              430.05          819.78         +90.62%
R               412.9           717.04         +73.66%
RT              168.93          220.63         +30.60%
Kops/s          1025            1303           +27.12%

It was benchmarked against commid id e2d211a from pixman/master

Siarhei Siamashka reported that on playstation3, it shows the following
results:

== before ==

              src_8_8888 =  L1: 194.37  L2: 198.46  M:155.90 (148.35%)
              HT: 59.18  VT: 36.71  R: 38.93  RT: 12.79 ( 106Kops/s)

== after ==

              src_8_8888 =  L1: 373.96  L2: 391.10  M:245.81 (233.88%)
              HT: 80.81  VT: 44.33  R: 48.10  RT: 14.79 ( 122Kops/s)

Signed-off-by: Oded Gabbay <oded.gabbay at gmail.com>
Acked-by: Siarhei Siamashka <siarhei.siamashka at gmail.com>
---
 pixman/pixman-vmx.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)

diff --git a/pixman/pixman-vmx.c b/pixman/pixman-vmx.c
index ec39c81..3349657 100644
--- a/pixman/pixman-vmx.c
+++ b/pixman/pixman-vmx.c
@@ -3137,6 +3137,49 @@ vmx_fetch_x8r8g8b8 (pixman_iter_t *iter, const uint32_t *mask)
     return iter->buffer;
 }
 
+static uint32_t *
+vmx_fetch_a8 (pixman_iter_t *iter, const uint32_t *mask)
+{
+    int w = iter->width;
+    uint32_t *dst = iter->buffer;
+    uint8_t *src = iter->bits;
+    vector unsigned int vmx0, vmx1, vmx2, vmx3, vmx4, vmx5, vmx6;
+
+    iter->bits += iter->stride;
+
+    while (w && (((uintptr_t)dst) & 15))
+    {
+        *dst++ = *(src++) << 24;
+        w--;
+    }
+
+    while (w >= 16)
+    {
+	vmx0 = load_128_unaligned((uint32_t *) src);
+
+	unpack_128_2x128((vector unsigned int) AVV(0), vmx0, &vmx1, &vmx2);
+	unpack_128_2x128_16((vector unsigned int) AVV(0), vmx1, &vmx3, &vmx4);
+	unpack_128_2x128_16((vector unsigned int) AVV(0), vmx2, &vmx5, &vmx6);
+
+	save_128_aligned(dst, vmx6);
+	save_128_aligned((dst +  4), vmx5);
+	save_128_aligned((dst +  8), vmx4);
+	save_128_aligned((dst + 12), vmx3);
+
+	dst += 16;
+	src += 16;
+	w -= 16;
+    }
+
+    while (w)
+    {
+	*dst++ = *(src++) << 24;
+	w--;
+    }
+
+    return iter->buffer;
+}
+
 #define IMAGE_FLAGS							\
     (FAST_PATH_STANDARD_FLAGS | FAST_PATH_ID_TRANSFORM |		\
      FAST_PATH_BITS_IMAGE | FAST_PATH_SAMPLES_COVER_CLIP_NEAREST)
@@ -3146,6 +3189,9 @@ static const pixman_iter_info_t vmx_iters[] =
     { PIXMAN_x8r8g8b8, IMAGE_FLAGS, ITER_NARROW,
       _pixman_iter_init_bits_stride, vmx_fetch_x8r8g8b8, NULL
     },
+    { PIXMAN_a8, IMAGE_FLAGS, ITER_NARROW,
+      _pixman_iter_init_bits_stride, vmx_fetch_a8, NULL
+    },
     { PIXMAN_null },
 };
 
-- 
2.4.3