mmx: add a8 fetcher

oprofile of xfce4-terminal-a1
210535    9.0407  libpixman-1.so.0.25.3    fetch_scanline_a8
144802    6.0054  libpixman-1.so.0.25.3    mmx_fetch_a8

Loongson:
       add_8_8_8 =  L1:  17.98  L2:  17.28  M: 14.28 ( 19.79%)  HT: 11.11  VT: 10.38  R:  9.97  RT:  5.14 (  55Kops/s)
       add_8_8_8 =  L1:  20.44  L2:  19.65  M: 15.62 ( 21.53%)  HT: 12.86  VT: 11.98  R: 11.32  RT:  6.13 (  64Kops/s)

 src_8888_8_0565 =  L1:  19.97  L2:  18.59  M: 13.42 ( 32.55%)  HT: 11.46  VT: 10.78  R: 10.33  RT:  5.87 (  61Kops/s)
 src_8888_8_0565 =  L1:  21.16  L2:  19.68  M: 13.94 ( 33.64%)  HT: 12.31  VT: 11.52  R: 11.02  RT:  6.54 (  68Kops/s)

 src_x888_8_x888 =  L1:  20.54  L2:  18.88  M: 13.07 ( 40.74%)  HT: 11.05  VT: 10.36  R: 10.02  RT:  5.68 (  60Kops/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)

over_x888_8_0565 =  L1:  10.32  L2:   9.85  M:  7.63 ( 21.13%)  HT:  6.56  VT:  6.30  R:  6.12  RT:  3.80 (  43Kops/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)

ARM/iwMMXt:
       add_8_8_8 =  L1:  13.10  L2:  11.67  M: 10.74 ( 13.46%)  HT:  8.62  VT:  8.15  R:  7.94  RT:  4.39 (  44Kops/s)
       add_8_8_8 =  L1:  13.81  L2:  12.79  M: 11.63 ( 13.93%)  HT:  9.33  VT:  9.20  R:  9.04  RT:  5.43 (  52Kops/s)

 src_8888_8_0565 =  L1:  16.62  L2:  15.07  M: 12.52 ( 27.46%)  HT: 10.07  VT: 10.17  R:  9.95  RT:  5.64 (  54Kops/s)
 src_8888_8_0565 =  L1:  16.84  L2:  16.11  M: 13.22 ( 27.71%)  HT: 11.74  VT: 10.90  R: 10.80  RT:  6.66 (  62Kops/s)

 src_x888_8_x888 =  L1:  17.49  L2:  16.22  M: 13.73 ( 38.73%)  HT: 10.10  VT: 10.33  R:  9.55  RT:  5.21 (  52Kops/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)

over_x888_8_0565 =  L1:   7.57  L2:   7.29  M:  6.37 ( 15.97%)  HT:  5.53  VT:  5.33  R:  5.21  RT:  3.22 (  35Kops/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)

2 files changed, 68 insertions, 0 deletions

diff --git a/pixman/loongson-mmintrin.h b/pixman/loongson-mmintrin.h
index 508366c4..76ae8920 100644
--- a/pixman/loongson-mmintrin.h
+++ b/pixman/loongson-mmintrin.h
@@ -183,6 +183,17 @@ _mm_unpackhi_pi8 (__m64 __m1, __m64 __m2)
 }
 
 extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_unpackhi_pi16 (__m64 __m1, __m64 __m2)
+{
+	__m64 ret;
+	asm("punpckhhw %0, %1, %2\n\t"
+	   : "=f" (ret)
+	   : "f" (__m1), "f" (__m2)
+	);
+	return ret;
+}
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_unpacklo_pi8 (__m64 __m1, __m64 __m2)
 {
 	__m64 ret;
@@ -207,6 +218,17 @@ _mm_unpacklo_pi8_f (__m32 __m1, __m64 __m2)
 }
 
 extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_unpacklo_pi16 (__m64 __m1, __m64 __m2)
+{
+	__m64 ret;
+	asm("punpcklhw %0, %1, %2\n\t"
+	   : "=f" (ret)
+	   : "f" (__m1), "f" (__m2)
+	);
+	return ret;
+}
+
+extern __inline __m64 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _mm_xor_si64 (__m64 __m1, __m64 __m2)
 {
 	__m64 ret;
diff --git a/pixman/pixman-mmx.c b/pixman/pixman-mmx.c
index 80aa59d8..98fb84e2 100644
--- a/pixman/pixman-mmx.c
+++ b/pixman/pixman-mmx.c
@@ -3243,6 +3243,51 @@ mmx_fetch_r5g6b5 (pixman_iter_t *iter, const uint32_t *mask)
     return iter->buffer;
 }
 
+static uint32_t *
+mmx_fetch_a8 (pixman_iter_t *iter, const uint32_t *mask)
+{
+    int w = iter->width;
+    uint32_t *dst = iter->buffer;
+    uint8_t *src = iter->bits;
+
+    iter->bits += iter->stride;
+
+    while (w && (((unsigned long)dst) & 15))
+    {
+        *dst++ = *(src++) << 24;
+        w--;
+    }
+
+    while (w >= 8)
+    {
+	__m64 mm0 = ldq_u ((__m64 *)src);
+
+	__m64 mm1 = _mm_unpacklo_pi8  (_mm_setzero_si64(), mm0);
+	__m64 mm2 = _mm_unpackhi_pi8  (_mm_setzero_si64(), mm0);
+	__m64 mm3 = _mm_unpacklo_pi16 (_mm_setzero_si64(), mm1);
+	__m64 mm4 = _mm_unpackhi_pi16 (_mm_setzero_si64(), mm1);
+	__m64 mm5 = _mm_unpacklo_pi16 (_mm_setzero_si64(), mm2);
+	__m64 mm6 = _mm_unpackhi_pi16 (_mm_setzero_si64(), mm2);
+
+	*(__m64 *)(dst + 0) = mm3;
+	*(__m64 *)(dst + 2) = mm4;
+	*(__m64 *)(dst + 4) = mm5;
+	*(__m64 *)(dst + 6) = mm6;
+
+	dst += 8;
+	src += 8;
+	w -= 8;
+    }
+
+    while (w)
+    {
+	*dst++ = *(src++) << 24;
+	w--;
+    }
+
+    return iter->buffer;
+}
+
 typedef struct
 {
     pixman_format_code_t	format;
@@ -3252,6 +3297,7 @@ typedef struct
 static const fetcher_info_t fetchers[] =
 {
     { PIXMAN_r5g6b5,		mmx_fetch_r5g6b5 },
+    { PIXMAN_a8,		mmx_fetch_a8 },
     { PIXMAN_null }
 };