diff options
| author | Nemanja Lukic <nemanja.lukic@rt-rk.com> | 2013-04-15 19:33:01 +0200 |
|---|---|---|
| committer | Søren Sandmann Pedersen <ssp@redhat.com> | 2013-04-30 15:38:43 -0400 |
| commit | c6a6fbdcd3ef18f733ff7ad11d5fafac384744cd (patch) | |
| tree | d8ad5cb686f300a21ae747337d5ab7b4f50d964d | |
| parent | f69335d5292310dc18f2f84d462430137a771976 (diff) | |
MIPS: DSPr2: Added pixbuf fast path.
Performance numbers before/after on MIPS-74kc @ 1GHz:
lowlevel-blt-bench results
Referent (before):
pixbuf = L1: 18.18 L2: 16.47 M: 13.36 (107.27%) HT: 10.16 VT: 10.07 R: 9.84 RT: 5.54 ( 35Kops/s)
Optimized:
pixbuf = L1: 43.54 L2: 36.02 M: 17.08 (137.09%) HT: 15.58 VT: 14.85 R: 13.87 RT: 8.38 ( 44Kops/s)
| -rw-r--r-- | pixman/pixman-mips-dspr2-asm.S | 62 | ||||
| -rw-r--r-- | pixman/pixman-mips-dspr2.c | 4 |
2 files changed, 66 insertions, 0 deletions
diff --git a/pixman/pixman-mips-dspr2-asm.S b/pixman/pixman-mips-dspr2-asm.S index 3a4d9140..973b0e46 100644 --- a/pixman/pixman-mips-dspr2-asm.S +++ b/pixman/pixman-mips-dspr2-asm.S @@ -699,6 +699,68 @@ LEAF_MIPS_DSPR2(pixman_composite_src_0888_0565_rev_asm_mips) END(pixman_composite_src_0888_0565_rev_asm_mips) #endif +LEAF_MIPS_DSPR2(pixman_composite_src_pixbuf_8888_asm_mips) +/* + * a0 - dst (a8b8g8r8) + * 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 + wsbh t0, t0 + wsbh t1, t1 + rotr t0, t0, 16 + rotr t1, t1, 16 + 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 + wsbh t0, t0 + rotr t0, t0, 16 + sw t0, 0(a0) +3: + RESTORE_REGS_FROM_STACK 0, v0 + j ra + nop + +END(pixman_composite_src_pixbuf_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 19499213..2c2f5155 100644 --- a/pixman/pixman-mips-dspr2.c +++ b/pixman/pixman-mips-dspr2.c @@ -54,6 +54,8 @@ PIXMAN_MIPS_BIND_FAST_PATH_SRC_DST (0, src_0888_8888_rev, PIXMAN_MIPS_BIND_FAST_PATH_SRC_DST (0, src_0888_0565_rev, uint8_t, 3, uint16_t, 1) #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, over_8888_8888, uint32_t, 1, uint32_t, 1) PIXMAN_MIPS_BIND_FAST_PATH_SRC_DST (0, over_8888_0565, @@ -299,6 +301,8 @@ static const pixman_fast_path_t mips_dspr2_fast_paths[] = PIXMAN_STD_FAST_PATH (SRC, b8g8r8, null, x8r8g8b8, mips_composite_src_0888_8888_rev), 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, 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), PIXMAN_STD_FAST_PATH (SRC, solid, a8, a8b8g8r8, mips_composite_src_n_8_8888), |