MIPS: DSPr2: Added over_8888_8888 nearest neighbor fast path.

Performance numbers before/after on MIPS-74kc @ 1GHz:

lowlevel-blt-bench results

Referent (before):
        over_8888_8888 =  L1:  19.47  L2:  16.30  M: 11.24 ( 59.69%)  HT:  9.54  VT:  9.29  R:  9.47  RT:  6.24 (  37Kops/s)

Optimized:
        over_8888_8888 =  L1:  43.67  L2:  33.30  M: 16.32 ( 86.65%)  HT: 14.10  VT: 13.78  R: 12.96  RT:  7.85 (  39Kops/s)

4 files changed, 141 insertions, 0 deletions

diff --git a/pixman/pixman-mips-dspr2-asm.S b/pixman/pixman-mips-dspr2-asm.S
index fb612d9..4b8dc22 100644
--- a/pixman/pixman-mips-dspr2-asm.S
+++ b/pixman/pixman-mips-dspr2-asm.S
@@ -3069,6 +3069,67 @@ LEAF_MIPS_DSPR2(pixman_composite_in_n_8_asm_mips)
 
 END(pixman_composite_in_n_8_asm_mips)
 
+LEAF_MIPS_DSPR2(pixman_scaled_nearest_scanline_8888_8888_OVER_asm_mips)
+/*
+ * a0     - dst  (a8r8g8b8)
+ * a1     - src  (a8r8g8b8)
+ * a2     - w
+ * a3     - vx
+ * 16(sp) - unit_x
+ */
+
+    SAVE_REGS_ON_STACK 0, s0, s1, s2, s3
+    lw       t8, 16(sp) /* t8 = unit_x */
+    li       t6, 0x00ff00ff
+    beqz     a2, 3f
+     nop
+    addiu    t1, a2, -1
+    beqz     t1, 2f
+     nop
+1:
+    sra      t0, a3, 16 /* t0 = vx >> 16 */
+    sll      t0, t0, 2  /* t0 = t0 * 4 (a8r8g8b8) */
+    addu     t0, a1, t0
+    lw       t0, 0(t0)  /* t0 = source      (a8r8g8b8) */
+    addu     a3, a3, t8 /* a3 = vx + unit_x */
+
+    sra      t1, a3, 16 /* t0 = vx >> 16 */
+    sll      t1, t1, 2  /* t0 = t0 * 4 (a8r8g8b8) */
+    addu     t1, a1, t1
+    lw       t1, 0(t1)  /* t1 = source      (a8r8g8b8) */
+    addu     a3, a3, t8 /* a3 = vx + unit_x */
+
+    lw       t2, 0(a0)  /* t2 = destination (a8r8g8b8) */
+    lw       t3, 4(a0)  /* t3 = destination (a8r8g8b8) */
+
+    OVER_2x8888_2x8888 t0, t1, t2, t3, t4, t5, t6, t7, t9, s0, s1, s2, s3
+
+    sw       t4, 0(a0)
+    sw       t5, 4(a0)
+    addiu    a2, a2, -2
+    addiu    t1, a2, -1
+    bgtz     t1, 1b
+     addiu   a0, a0, 8
+2:
+    beqz     a2, 3f
+     nop
+    sra      t0, a3, 16 /* t0 = vx >> 16 */
+    sll      t0, t0, 2  /* t0 = t0 * 4 (a8r8g8b8) */
+    addu     t0, a1, t0
+    lw       t0, 0(t0)  /* t0 = source      (a8r8g8b8) */
+    lw       t1, 0(a0)  /* t1 = destination (a8r8g8b8) */
+    addu     a3, a3, t8 /* a3 = vx + unit_x */
+
+    OVER_8888_8888 t0, t1, t2, t6, t4, t5, t3, t7
+
+    sw       t2, 0(a0)
+3:
+    RESTORE_REGS_FROM_STACK 0, s0, s1, s2, s3
+    j        ra
+     nop
+
+END(pixman_scaled_nearest_scanline_8888_8888_OVER_asm_mips)
+
 LEAF_MIPS_DSPR2(pixman_scaled_nearest_scanline_8888_8_0565_OVER_asm_mips)
 /*
  * a0     - dst  (r5g6b5)
diff --git a/pixman/pixman-mips-dspr2-asm.h b/pixman/pixman-mips-dspr2-asm.h
index b330c0f..bc458b6 100644
--- a/pixman/pixman-mips-dspr2-asm.h
+++ b/pixman/pixman-mips-dspr2-asm.h
@@ -587,6 +587,36 @@ LEAF_MIPS32R2(symbol)                                   \
     addu_s.qb          \out_8888, \out_8888, \s_8888
 .endm
 
+/*
+ * OVER operation on two a8r8g8b8 source pixels (s1_8888 and s2_8888) and two
+ * a8r8g8b8 destination pixels (d1_8888 and d2_8888). It also requires maskLSR
+ * needed for rounding process. maskLSR must have following value:
+ *   li       maskLSR, 0x00ff00ff
+ */
+.macro OVER_2x8888_2x8888 s1_8888,   \
+                          s2_8888,   \
+                          d1_8888,   \
+                          d2_8888,   \
+                          out1_8888, \
+                          out2_8888, \
+                          maskLSR,   \
+                          scratch1, scratch2, scratch3, \
+                          scratch4, scratch5, scratch6
+    not                    \scratch1,  \s1_8888
+    srl                    \scratch1,  \scratch1,  24
+    not                    \scratch2,  \s2_8888
+    srl                    \scratch2,  \scratch2,  24
+    MIPS_2xUN8x4_MUL_2xUN8 \d1_8888,   \d2_8888, \
+                           \scratch1,  \scratch2,  \
+                           \out1_8888, \out2_8888, \
+                           \maskLSR, \
+                           \scratch3,  \scratch4, \scratch5, \
+                           \scratch6,  \d1_8888,  \d2_8888
+
+    addu_s.qb              \out1_8888, \out1_8888, \s1_8888
+    addu_s.qb              \out2_8888, \out2_8888, \s2_8888
+.endm
+
 .macro MIPS_UN8x4_MUL_UN8_ADD_UN8x4 s_8888,   \
                                     m_8,      \
                                     d_8888,   \
diff --git a/pixman/pixman-mips-dspr2.c b/pixman/pixman-mips-dspr2.c
index 1ea2445..a68c86f 100644
--- a/pixman/pixman-mips-dspr2.c
+++ b/pixman/pixman-mips-dspr2.c
@@ -121,6 +121,9 @@ PIXMAN_MIPS_BIND_FAST_PATH_SRC_MASK_DST (over_0565_8_0565, uint16_t, 1,
 PIXMAN_MIPS_BIND_FAST_PATH_SRC_MASK_DST (over_8888_8888_8888, uint32_t, 1,
                                          uint32_t, 1, uint32_t, 1)
 
+PIXMAN_MIPS_BIND_SCALED_NEAREST_SRC_DST (8888_8888, OVER,
+                                         uint32_t, uint32_t)
+
 PIXMAN_MIPS_BIND_SCALED_BILINEAR_SRC_DST (0, 8888_8888, SRC,
                                           uint32_t, uint32_t)
 PIXMAN_MIPS_BIND_SCALED_BILINEAR_SRC_DST (0, 8888_0565, SRC,
@@ -357,6 +360,11 @@ static const pixman_fast_path_t mips_dspr2_fast_paths[] =
     PIXMAN_STD_FAST_PATH (OVER_REVERSE, solid, null, a8b8g8r8, mips_composite_over_reverse_n_8888),
     PIXMAN_STD_FAST_PATH (IN,           solid, null, a8,       mips_composite_in_n_8),
 
+    PIXMAN_MIPS_SIMPLE_NEAREST_FAST_PATH (OVER, a8r8g8b8, a8r8g8b8, mips_8888_8888),
+    PIXMAN_MIPS_SIMPLE_NEAREST_FAST_PATH (OVER, a8b8g8r8, a8b8g8r8, mips_8888_8888),
+    PIXMAN_MIPS_SIMPLE_NEAREST_FAST_PATH (OVER, a8r8g8b8, x8r8g8b8, mips_8888_8888),
+    PIXMAN_MIPS_SIMPLE_NEAREST_FAST_PATH (OVER, a8b8g8r8, x8b8g8r8, mips_8888_8888),
+
     PIXMAN_MIPS_SIMPLE_NEAREST_A8_MASK_FAST_PATH (OVER, a8r8g8b8, r5g6b5, mips_8888_8_0565),
     PIXMAN_MIPS_SIMPLE_NEAREST_A8_MASK_FAST_PATH (OVER, a8b8g8r8, b5g6r5, mips_8888_8_0565),
 
diff --git a/pixman/pixman-mips-dspr2.h b/pixman/pixman-mips-dspr2.h
index 4ac9ff9..955ed70 100644
--- a/pixman/pixman-mips-dspr2.h
+++ b/pixman/pixman-mips-dspr2.h
@@ -246,6 +246,48 @@ mips_composite_##name (pixman_implementation_t *imp,                     \
     }                                                                    \
 }
 
+/****************************************************************************/
+
+#define PIXMAN_MIPS_BIND_SCALED_NEAREST_SRC_DST(name, op,                    \
+                                                src_type, dst_type)          \
+void                                                                         \
+pixman_scaled_nearest_scanline_##name##_##op##_asm_mips (                    \
+                                                   dst_type *       dst,     \
+                                                   const src_type * src,     \
+                                                   int32_t          w,       \
+                                                   pixman_fixed_t   vx,      \
+                                                   pixman_fixed_t   unit_x); \
+                                                                             \
+static force_inline void                                                     \
+scaled_nearest_scanline_mips_##name##_##op (dst_type *       pd,             \
+                                            const src_type * ps,             \
+                                            int32_t          w,              \
+                                            pixman_fixed_t   vx,             \
+                                            pixman_fixed_t   unit_x,         \
+                                            pixman_fixed_t   max_vx,         \
+                                            pixman_bool_t    zero_src)       \
+{                                                                            \
+    pixman_scaled_nearest_scanline_##name##_##op##_asm_mips (pd, ps, w,      \
+                                                             vx, unit_x);    \
+}                                                                            \
+                                                                             \
+FAST_NEAREST_MAINLOOP (mips_##name##_cover_##op,                             \
+                       scaled_nearest_scanline_mips_##name##_##op,           \
+                       src_type, dst_type, COVER)                            \
+FAST_NEAREST_MAINLOOP (mips_##name##_none_##op,                              \
+                       scaled_nearest_scanline_mips_##name##_##op,           \
+                       src_type, dst_type, NONE)                             \
+FAST_NEAREST_MAINLOOP (mips_##name##_pad_##op,                               \
+                       scaled_nearest_scanline_mips_##name##_##op,           \
+                       src_type, dst_type, PAD)
+
+/* Provide entries for the fast path table */
+#define PIXMAN_MIPS_SIMPLE_NEAREST_FAST_PATH(op,s,d,func)                    \
+    SIMPLE_NEAREST_FAST_PATH_COVER (op,s,d,func),                            \
+    SIMPLE_NEAREST_FAST_PATH_NONE (op,s,d,func),                             \
+    SIMPLE_NEAREST_FAST_PATH_PAD (op,s,d,func)
+
+
 /*****************************************************************************/
 
 #define PIXMAN_MIPS_BIND_SCALED_NEAREST_SRC_A8_DST(flags, name, op,           \