[Pixman] [PATCH 3/3] mmx: add x8f8g8b8 fetcher

[Matt Turner]

Loongson:
   add_x888_x888 =  L1:  29.36  L2:  27.81  M: 14.05 ( 38.74%)  HT: 12.45  VT: 11.78  R: 11.52  RT:  7.23 (  75Kops/s)
   add_x888_x888 =  L1:  36.06  L2:  34.55  M: 14.81 ( 41.03%)  HT: 14.01  VT: 13.41  R: 13.06  RT:  9.06 (  90Kops/s)

 src_x888_8_x888 =  L1:  21.92  L2:  20.15  M: 13.35 ( 41.42%)  HT: 11.70  VT: 10.95  R: 10.53  RT:  6.18 (  65Kops/s)
 src_x888_8_x888 =  L1:  25.43  L2:  23.51  M: 14.12 ( 44.00%)  HT: 13.14  VT: 12.50  R: 11.86  RT:  7.49 (  76Kops/s)

over_x888_8_0565 =  L1:  10.64  L2:  10.17  M:  7.74 ( 21.35%)  HT:  6.83  VT:  6.55  R:  6.34  RT:  4.03 (  46Kops/s)
over_x888_8_0565 =  L1:  11.41  L2:  10.97  M:  8.07 ( 22.36%)  HT:  7.42  VT:  7.18  R:  6.92  RT:  4.62 (  52Kops/s)

ARM/iwMMXt:
   add_x888_x888 =  L1:  22.10  L2:  18.93  M: 13.48 ( 32.29%)  HT: 11.32  VT: 10.64  R: 10.36  RT:  6.51 (  61Kops/s)
   add_x888_x888 =  L1:  24.26  L2:  20.83  M: 14.52 ( 35.64%)  HT: 12.66  VT: 12.98  R: 11.34  RT:  7.69 (  72Kops/s)

 src_x888_8_x888 =  L1:  19.33  L2:  17.66  M: 14.26 ( 38.43%)  HT: 11.53  VT: 10.83  R: 10.57  RT:  6.12 (  58Kops/s)
 src_x888_8_x888 =  L1:  21.23  L2:  19.60  M: 15.41 ( 42.55%)  HT: 12.66  VT: 13.30  R: 11.55  RT:  7.32 (  67Kops/s)

over_x888_8_0565 =  L1:   8.15  L2:   7.56  M:  6.50 ( 15.58%)  HT:  5.73  VT:  5.49  R:  5.50  RT:  3.53 (  38Kops/s)
over_x888_8_0565 =  L1:   8.35  L2:   7.85  M:  6.68 ( 16.40%)  HT:  6.12  VT:  5.97  R:  5.78  RT:  4.03 (  43Kops/s)
---
 pixman/pixman-mmx.c |   42 ++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 42 insertions(+), 0 deletions(-)

diff --git a/pixman/pixman-mmx.c b/pixman/pixman-mmx.c
index c127f4a..7511216 100644
--- a/pixman/pixman-mmx.c
+++ b/pixman/pixman-mmx.c
@@ -3210,6 +3210,47 @@ mmx_composite_over_x888_8_8888 (pixman_implementation_t *imp,
 }
 
 static uint32_t *
+mmx_fetch_x8r8g8b8 (pixman_iter_t *iter, const uint32_t *mask)
+{
+    int w = iter->width;
+    uint32_t *dst = iter->buffer;
+    uint32_t *src = (uint32_t *)iter->bits;
+
+    iter->bits += iter->stride;
+
+    while (w && ((unsigned long)dst) & 7)
+    {
+	*dst++ = (*src++) | 0xff000000;
+	w--;
+    }
+
+    while (w >= 8)
+    {
+	__m64 vsrc1 = ldq_u ((__m64 *)(src + 0));
+	__m64 vsrc2 = ldq_u ((__m64 *)(src + 2));
+	__m64 vsrc3 = ldq_u ((__m64 *)(src + 4));
+	__m64 vsrc4 = ldq_u ((__m64 *)(src + 6));
+
+	*(__m64 *)(dst + 0) = _mm_or_si64 (vsrc1, MC (ff000000));
+	*(__m64 *)(dst + 2) = _mm_or_si64 (vsrc2, MC (ff000000));
+	*(__m64 *)(dst + 4) = _mm_or_si64 (vsrc3, MC (ff000000));
+	*(__m64 *)(dst + 6) = _mm_or_si64 (vsrc4, MC (ff000000));
+
+	dst += 8;
+	src += 8;
+	w -= 8;
+    }
+
+    while (w)
+    {
+	*dst++ = (*src++) | 0xff000000;
+	w--;
+    }
+
+    return iter->buffer;
+}
+
+static uint32_t *
 mmx_fetch_r5g6b5 (pixman_iter_t *iter, const uint32_t *mask)
 {
     int w = iter->width;
@@ -3307,6 +3348,7 @@ typedef struct
 
 static const fetcher_info_t fetchers[] =
 {
+    { PIXMAN_x8r8g8b8,		mmx_fetch_x8r8g8b8 },
     { PIXMAN_r5g6b5,		mmx_fetch_r5g6b5 },
     { PIXMAN_a8,		mmx_fetch_a8 },
     { PIXMAN_null }
-- 
1.7.3.4