[Pixman] [PATCH 9/9] MIPS: DSPr2: Added rpixbuf fast path.

[Nemanja Lukic]

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

lowlevel-blt-bench results

Referent (before):
       rpixbuf =  L1:  14.63  L2:  13.55  M:  9.91 ( 79.53%)  HT:  8.47  VT:  8.32  R:  8.17  RT:  4.90 (  33Kops/s)

Optimized:
       rpixbuf =  L1:  45.69  L2:  37.30  M: 17.24 (138.31%)  HT: 15.66  VT: 14.88  R: 13.97  RT:  8.38 (  44Kops/s)
---
 pixman/pixman-mips-dspr2-asm.S |   59 ++++++++++++++++++++++++++++++++++++++++
 pixman/pixman-mips-dspr2.c     |    4 +++
 2 files changed, 63 insertions(+), 0 deletions(-)

diff --git a/pixman/pixman-mips-dspr2-asm.S b/pixman/pixman-mips-dspr2-asm.S
index 973b0e4..866e93e 100644
--- a/pixman/pixman-mips-dspr2-asm.S
+++ b/pixman/pixman-mips-dspr2-asm.S
@@ -761,6 +761,65 @@ LEAF_MIPS_DSPR2(pixman_composite_src_pixbuf_8888_asm_mips)
 
 END(pixman_composite_src_pixbuf_8888_asm_mips)
 
+LEAF_MIPS_DSPR2(pixman_composite_src_rpixbuf_8888_asm_mips)
+/*
+ * a0 - dst  (a8r8g8b8)
+ * a1 - src  (a8r8g8b8)
+ * a2 - w
+ */
+
+    SAVE_REGS_ON_STACK 0, v0
+    li       v0, 0x00ff00ff
+
+    beqz     a2, 3f
+     nop
+    addiu    t1, a2, -1
+    beqz     t1, 2f
+     nop
+1:
+    lw       t0, 0(a1)
+    lw       t1, 4(a1)
+    addiu    a1, a1, 8
+    addiu    a2, a2, -2
+    srl      t2, t0, 24
+    srl      t3, t1, 24
+
+    MIPS_2xUN8x4_MUL_2xUN8 t0, t1, t2, t3, t0, t1, v0, t4, t5, t6, t7, t8, t9
+
+    sll      t0, t0, 8
+    sll      t1, t1, 8
+    andi     t2, t2, 0xff
+    andi     t3, t3, 0xff
+    or       t0, t0, t2
+    or       t1, t1, t3
+    rotr     t0, t0, 8
+    rotr     t1, t1, 8
+    sw       t0, 0(a0)
+    sw       t1, 4(a0)
+
+    addiu    t2, a2, -1
+    bgtz     t2, 1b
+     addiu   a0, a0, 8
+2:
+    beqz     a2, 3f
+     nop
+    lw       t0, 0(a1)
+    srl      t1, t0, 24
+
+    MIPS_UN8x4_MUL_UN8 t0, t1, t0, v0, t3, t4, t5
+
+    sll      t0, t0, 8
+    andi     t1, t1, 0xff
+    or       t0, t0, t1
+    rotr     t0, t0, 8
+    sw       t0, 0(a0)
+3:
+    RESTORE_REGS_FROM_STACK 0, v0
+    j        ra
+     nop
+
+END(pixman_composite_src_rpixbuf_8888_asm_mips)
+
 LEAF_MIPS_DSPR2(pixman_composite_src_n_8_8888_asm_mips)
 /*
  * a0 - dst  (a8r8g8b8)
diff --git a/pixman/pixman-mips-dspr2.c b/pixman/pixman-mips-dspr2.c
index 2c2f515..e10c9df 100644
--- a/pixman/pixman-mips-dspr2.c
+++ b/pixman/pixman-mips-dspr2.c
@@ -56,6 +56,8 @@ PIXMAN_MIPS_BIND_FAST_PATH_SRC_DST (0, src_0888_0565_rev,
 #endif
 PIXMAN_MIPS_BIND_FAST_PATH_SRC_DST (0, src_pixbuf_8888,
                                     uint32_t, 1, uint32_t, 1)
+PIXMAN_MIPS_BIND_FAST_PATH_SRC_DST (0, src_rpixbuf_8888,
+                                    uint32_t, 1, uint32_t, 1)
 PIXMAN_MIPS_BIND_FAST_PATH_SRC_DST (0, over_8888_8888,
                                     uint32_t, 1, uint32_t, 1)
 PIXMAN_MIPS_BIND_FAST_PATH_SRC_DST (0, over_8888_0565,
@@ -302,6 +304,8 @@ static const pixman_fast_path_t mips_dspr2_fast_paths[] =
     PIXMAN_STD_FAST_PATH (SRC, b8g8r8,   null, r5g6b5,   mips_composite_src_0888_0565_rev),
 #endif
     PIXMAN_STD_FAST_PATH (SRC, pixbuf,   pixbuf,  a8r8g8b8, mips_composite_src_pixbuf_8888),
+    PIXMAN_STD_FAST_PATH (SRC, pixbuf,   pixbuf,  a8b8g8r8, mips_composite_src_rpixbuf_8888),
+    PIXMAN_STD_FAST_PATH (SRC, rpixbuf,  rpixbuf, a8r8g8b8, mips_composite_src_rpixbuf_8888),
     PIXMAN_STD_FAST_PATH (SRC, rpixbuf,  rpixbuf, a8b8g8r8, mips_composite_src_pixbuf_8888),
     PIXMAN_STD_FAST_PATH (SRC, solid,    a8,   a8r8g8b8, mips_composite_src_n_8_8888),
     PIXMAN_STD_FAST_PATH (SRC, solid,    a8,   x8r8g8b8, mips_composite_src_n_8_8888),
-- 
1.7.3