armv6: Add four more nearest-scaled-cover fast paths

These complete the set of fast paths where currently pixman-fast-path.c
provides versions that get selected in preference to the armv6-optimised
scanline fetchers/combiners/writeback routines.

Because generation of these fast paths is macroised, the patch required
to add them is fairly simple.

lowlevel-blt-bench -n over_8888_8888:

     Before          After
     Mean   StdDev   Mean   StdDev  Confidence  Change
L1   13.8   0.0      26.5   0.2     100.0%      +91.7%
L2   9.4    0.2      22.9   0.4     100.0%      +142.6%
M    8.6    0.0      23.8   0.0     100.0%      +176.1%
HT   7.4    0.0      14.1   0.1     100.0%      +91.2%
VT   7.3    0.0      13.4   0.1     100.0%      +84.1%
R    7.0    0.0      13.0   0.1     100.0%      +85.9%
RT   4.5    0.1      6.2    0.1     100.0%      +36.6%

affine-bench * 0 0 1 over a8r8g8b8 a8r8g8b8:

     Before          After
     Mean   StdDev   Mean   StdDev  Confidence  Change
0.5  9.4    0.0      28.0   0.0     100.0%      +197.4%
0.75 9.0    0.0      26.1   0.0     100.0%      +190.2%
1.0  8.6    0.0      24.4   0.0     100.0%      +184.6%
1.5  7.9    0.0      21.7   0.0     100.0%      +173.4%
2.0  7.3    0.0      19.6   0.0     100.0%      +166.6%

lowlevel-blt-bench -n src_x888_8888:

     Before          After
     Mean   StdDev   Mean   StdDev  Confidence  Change
L1   108.6  2.0      66.3   0.9     100.0%      -39.0%
L2   32.4   1.5      44.3   2.1     100.0%      +36.8%
M    27.5   0.1      62.0   0.1     100.0%      +125.6%
HT   20.3   0.1      28.7   0.2     100.0%      +41.2%
VT   19.9   0.1      26.7   0.1     100.0%      +34.4%
R    18.6   0.1      25.3   0.2     100.0%      +36.3%
RT   8.7    0.1      9.8    0.2     100.0%      +12.6%

affine-bench * 0 0 1 src x8r8g8b8 a8r8g8b8:

     Before          After
     Mean   StdDev   Mean   StdDev  Confidence  Change
0.5  45.2   0.0      97.2   0.1     100.0%      +115.1%
0.75 35.9   0.1      76.7   0.1     100.0%      +113.9%
1.0  29.6   0.1      61.1   0.1     100.0%      +106.4%
1.5  21.4   0.0      52.7   0.1     100.0%      +145.9%
2.0  16.7   0.0      43.0   0.1     100.0%      +156.9%

lowlevel-blt-bench -n src_8888_0565:

     Before          After
     Mean   StdDev   Mean   StdDev  Confidence  Change
L1   57.2   0.7      43.1   0.4     100.0%      -24.7%
L2   23.0   1.0      32.8   1.0     100.0%      +42.5%
M    24.8   0.0      42.2   0.0     100.0%      +70.0%
HT   18.0   0.1      22.1   0.1     100.0%      +22.5%
VT   17.1   0.1      21.0   0.1     100.0%      +22.5%
R    16.5   0.1      20.0   0.1     100.0%      +21.4%
RT   8.3    0.2      8.4    0.1     95.0%       +1.0%  (insignificant)

affine-bench * 0 0 1 src a8r8g8b8 r5g6b5:

     Before          After
     Mean   StdDev   Mean   StdDev  Confidence  Change
0.5  34.9   0.0      55.3   0.0     100.0%      +58.7%
0.75 29.3   0.0      49.1   0.0     100.0%      +67.4%
1.0  24.8   0.0      42.6   0.1     100.0%      +71.6%
1.5  19.0   0.0      38.2   0.1     100.0%      +100.7%
2.0  15.4   0.0      31.8   0.0     100.0%      +107.1%

lowlevel-blt-bench -n over_8888_0565:

     Before          After
     Mean   StdDev   Mean   StdDev  Confidence  Change
L1   9.8    0.0      15.3   0.1     100.0%      +56.6%
L2   7.4    0.0      14.3   0.2     100.0%      +91.7%
M    7.5    0.0      15.4   0.0     100.0%      +106.0%
HT   6.5    0.0      10.1   0.0     100.0%      +54.5%
VT   6.4    0.0      9.9    0.0     100.0%      +54.6%
R    6.2    0.0      9.5    0.0     100.0%      +52.1%
RT   4.2    0.0      4.6    0.1     100.0%      +9.8%

affine-bench * 0 0 1 over a8r8g8b8 r5g6b5:

     Before          After
     Mean   StdDev   Mean   StdDev  Confidence  Change
0.5  8.0    0.0      17.3   0.0     100.0%      +116.1%
0.75 7.8    0.0      16.5   0.0     100.0%      +112.9%
1.0  7.5    0.0      15.7   0.0     100.0%      +110.5%
1.5  7.0    0.0      14.8   0.0     100.0%      +112.8%
2.0  6.5    0.0      13.7   0.0     100.0%      +111.4%

1 files changed, 17 insertions, 0 deletions

diff --git a/pixman/pixman-arm-simd.c b/pixman/pixman-arm-simd.c
index 5f62ed3..cc946ec 100644
--- a/pixman/pixman-arm-simd.c
+++ b/pixman/pixman-arm-simd.c
@@ -238,7 +238,11 @@ pixman_get_scanline_r5g6b5_nearest_scaled_cover_r5g6b5_asm_armv6(uint32_t
                                                                  const uint16_t *source);
 
 BIND_NEAREST_SCALED_COVER_FAST_PATH_SRC_DST (armv6, src_8888_8888,  SRC,  src,  uint32_t, uint32_t, a8r8g8b8, a8r8g8b8)
+BIND_NEAREST_SCALED_COVER_FAST_PATH_SRC_DST (armv6, src_x888_8888,  SRC,  src,  uint32_t, uint32_t, x8r8g8b8, a8r8g8b8)
+BIND_NEAREST_SCALED_COVER_FAST_PATH_SRC_DST (armv6, src_8888_0565,  SRC,  src,  uint32_t, uint16_t, a8r8g8b8, r5g6b5)
 BIND_NEAREST_SCALED_COVER_FAST_PATH_SRC_DST (armv6, src_0565_0565,  SRC,  src,  uint16_t, uint16_t, r5g6b5,   r5g6b5)
+BIND_NEAREST_SCALED_COVER_FAST_PATH_SRC_DST (armv6, over_8888_8888, OVER, over, uint32_t, uint32_t, a8r8g8b8, a8r8g8b8)
+BIND_NEAREST_SCALED_COVER_FAST_PATH_SRC_DST (armv6, over_8888_0565, OVER, over, uint32_t, uint16_t, a8r8g8b8, r5g6b5)
 
 void
 pixman_composite_src_n_8888_asm_armv6 (int32_t   w,
@@ -457,12 +461,25 @@ static const pixman_fast_path_t arm_simd_fast_paths[] =
     PIXMAN_ARM_NEAREST_SCALED_COVER_SRC_DST_FAST_PATH (armv6, SRC, r5g6b5, r5g6b5, src_0565_0565),
     PIXMAN_ARM_NEAREST_SCALED_COVER_SRC_DST_FAST_PATH (armv6, SRC, b5g6r5, b5g6r5, src_0565_0565),
 
+    PIXMAN_ARM_NEAREST_SCALED_COVER_SRC_DST_FAST_PATH (armv6, SRC, a8r8g8b8, r5g6b5, src_8888_0565),
+    PIXMAN_ARM_NEAREST_SCALED_COVER_SRC_DST_FAST_PATH (armv6, SRC, x8r8g8b8, r5g6b5, src_8888_0565),
+    PIXMAN_ARM_NEAREST_SCALED_COVER_SRC_DST_FAST_PATH (armv6, SRC, a8b8g8r8, b5g6r5, src_8888_0565),
+    PIXMAN_ARM_NEAREST_SCALED_COVER_SRC_DST_FAST_PATH (armv6, SRC, x8b8g8r8, b5g6r5, src_8888_0565),
+    PIXMAN_ARM_NEAREST_SCALED_COVER_SRC_DST_FAST_PATH (armv6, OVER, a8r8g8b8, r5g6b5, over_8888_0565),
+    PIXMAN_ARM_NEAREST_SCALED_COVER_SRC_DST_FAST_PATH (armv6, OVER, a8b8g8r8, b5g6r5, over_8888_0565),
+
     PIXMAN_ARM_NEAREST_SCALED_COVER_SRC_DST_FAST_PATH (armv6, SRC, a8r8g8b8, a8r8g8b8, src_8888_8888),
     PIXMAN_ARM_NEAREST_SCALED_COVER_SRC_DST_FAST_PATH (armv6, SRC, a8r8g8b8, x8r8g8b8, src_8888_8888),
     PIXMAN_ARM_NEAREST_SCALED_COVER_SRC_DST_FAST_PATH (armv6, SRC, x8r8g8b8, x8r8g8b8, src_8888_8888),
     PIXMAN_ARM_NEAREST_SCALED_COVER_SRC_DST_FAST_PATH (armv6, SRC, a8b8g8r8, a8b8g8r8, src_8888_8888),
     PIXMAN_ARM_NEAREST_SCALED_COVER_SRC_DST_FAST_PATH (armv6, SRC, a8b8g8r8, x8b8g8r8, src_8888_8888),
     PIXMAN_ARM_NEAREST_SCALED_COVER_SRC_DST_FAST_PATH (armv6, SRC, x8b8g8r8, x8b8g8r8, src_8888_8888),
+    PIXMAN_ARM_NEAREST_SCALED_COVER_SRC_DST_FAST_PATH (armv6, SRC, x8r8g8b8, a8r8g8b8, src_x888_8888),
+    PIXMAN_ARM_NEAREST_SCALED_COVER_SRC_DST_FAST_PATH (armv6, SRC, x8b8g8r8, a8b8g8r8, src_x888_8888),
+    PIXMAN_ARM_NEAREST_SCALED_COVER_SRC_DST_FAST_PATH (armv6, OVER, a8r8g8b8, a8r8g8b8, over_8888_8888),
+    PIXMAN_ARM_NEAREST_SCALED_COVER_SRC_DST_FAST_PATH (armv6, OVER, a8r8g8b8, x8r8g8b8, over_8888_8888),
+    PIXMAN_ARM_NEAREST_SCALED_COVER_SRC_DST_FAST_PATH (armv6, OVER, a8b8g8r8, a8b8g8r8, over_8888_8888),
+    PIXMAN_ARM_NEAREST_SCALED_COVER_SRC_DST_FAST_PATH (armv6, OVER, a8b8g8r8, x8b8g8r8, over_8888_8888),
 
     SIMPLE_NEAREST_FAST_PATH (SRC, r5g6b5, r5g6b5, armv6_0565_0565),
     SIMPLE_NEAREST_FAST_PATH (SRC, b5g6r5, b5g6r5, armv6_0565_0565),