diff options
Diffstat (limited to 'pixman/pixman/pixman-mips-dspr2-asm.S')
-rw-r--r-- | pixman/pixman/pixman-mips-dspr2-asm.S | 219 |
1 files changed, 219 insertions, 0 deletions
diff --git a/pixman/pixman/pixman-mips-dspr2-asm.S b/pixman/pixman/pixman-mips-dspr2-asm.S index f1087a776..6a0fc1803 100644 --- a/pixman/pixman/pixman-mips-dspr2-asm.S +++ b/pixman/pixman/pixman-mips-dspr2-asm.S @@ -308,3 +308,222 @@ LEAF_MIPS_DSPR2(pixman_composite_src_x888_8888_asm_mips) nop END(pixman_composite_src_x888_8888_asm_mips) + +LEAF_MIPS_DSPR2(pixman_composite_over_n_8888_8888_ca_asm_mips) +/* + * a0 - dst (a8r8g8b8) + * a1 - src (32bit constant) + * a2 - mask (a8r8g8b8) + * a3 - w + */ + + SAVE_REGS_ON_STACK 16, s0, s1, s2, s3, s4, s5, s6, s7 + beqz a3, 4f + nop + li t6, 0xff + addiu t7, zero, -1 /* t7 = 0xffffffff */ + srl t8, a1, 24 /* t8 = srca */ + li t9, 0x00ff00ff + addiu t1, a3, -1 + beqz t1, 3f /* last pixel */ + nop + beq t8, t6, 2f /* if (srca == 0xff) */ + nop +1: + /* a1 = src */ + lw t0, 0(a2) /* t0 = mask */ + lw t1, 4(a2) /* t1 = mask */ + or t2, t0, t1 + beqz t2, 12f /* if (t0 == 0) && (t1 == 0) */ + addiu a2, a2, 8 + and t3, t0, t1 + move s0, t8 /* s0 = srca */ + move s1, t8 /* s1 = srca */ + move t4, a1 /* t4 = src */ + move t5, a1 /* t5 = src */ + lw t2, 0(a0) /* t2 = dst */ + beq t3, t7, 11f /* if (t0 == 0xffffffff) && (t1 == 0xffffffff) */ + lw t3, 4(a0) /* t0 = dst */ + MIPS_2xUN8x4_MUL_2xUN8x4 a1, a1, t0, t1, t4, t5, t9, s0, s1, s2, s3, s4, s5 + MIPS_2xUN8x4_MUL_2xUN8 t0, t1, t8, t8, s0, s1, t9, s2, s3, s4, s5, s6, s7 +11: + not s0, s0 + not s1, s1 + MIPS_2xUN8x4_MUL_2xUN8x4 t2, t3, s0, s1, s2, s3, t9, t0, t1, s4, s5, s6, s7 + addu_s.qb t0, t4, s2 + addu_s.qb t1, t5, s3 + sw t0, 0(a0) + sw t1, 4(a0) +12: + addiu a3, a3, -2 + addiu t1, a3, -1 + bgtz t1, 1b + addiu a0, a0, 8 + b 3f + nop +2: + /* a1 = src */ + lw t0, 0(a2) /* t0 = mask */ + lw t1, 4(a2) /* t1 = mask */ + or t2, t0, t1 + beqz t2, 22f /* if (t0 == 0) & (t1 == 0) */ + addiu a2, a2, 8 + and t2, t0, t1 + move s0, a1 + beq t2, t7, 21f /* if (t0 == 0xffffffff) && (t1 == 0xffffffff) */ + move s1, a1 + lw t2, 0(a0) /* t2 = dst */ + lw t3, 4(a0) /* t3 = dst */ + MIPS_2xUN8x4_MUL_2xUN8x4 a1, a1, t0, t1, t4, t5, t9, s0, s1, s2, s3, s4, s5 + not t0, t0 + not t1, t1 + MIPS_2xUN8x4_MUL_2xUN8x4 t2, t3, t0, t1, s0, s1, t9, s2, s3, s4, s5, s6, s7 + addu_s.qb s0, t4, s0 + addu_s.qb s1, t5, s1 +21: + sw s0, 0(a0) + sw s1, 4(a0) +22: + addiu a3, a3, -2 + addiu t1, a3, -1 + bgtz t1, 2b + addiu a0, a0, 8 +3: + blez a3, 4f + nop + /* a1 = src */ + lw t1, 0(a2) /* t1 = mask */ + beqz t1, 4f + nop + move s0, t8 /* s0 = srca */ + move t2, a1 /* t2 = src */ + beq t1, t7, 31f + lw t0, 0(a0) /* t0 = dst */ + + MIPS_UN8x4_MUL_UN8x4 a1, t1, t2, t9, t3, t4, t5, t6 + MIPS_UN8x4_MUL_UN8 t1, t8, s0, t9, t3, t4, t5 +31: + not s0, s0 + MIPS_UN8x4_MUL_UN8x4 t0, s0, t3, t9, t4, t5, t6, t1 + addu_s.qb t0, t2, t3 + sw t0, 0(a0) +4: + RESTORE_REGS_FROM_STACK 16, s0, s1, s2, s3, s4, s5, s6, s7 + j ra + nop + +END(pixman_composite_over_n_8888_8888_ca_asm_mips) + +LEAF_MIPS_DSPR2(pixman_composite_over_n_8888_0565_ca_asm_mips) +/* + * a0 - dst (r5g6b5) + * a1 - src (32bit constant) + * a2 - mask (a8r8g8b8) + * a3 - w + */ + + SAVE_REGS_ON_STACK 20, s0, s1, s2, s3, s4, s5, s6, s7, s8 + beqz a3, 4f + nop + li t5, 0xf800f800 + li t6, 0x07e007e0 + li t7, 0x001F001F + li t9, 0x00ff00ff + + srl t8, a1, 24 /* t8 = srca */ + addiu t1, a3, -1 + beqz t1, 3f /* last pixel */ + nop + li s0, 0xff /* s0 = 0xff */ + addiu s1, zero, -1 /* s1 = 0xffffffff */ + + beq t8, s0, 2f /* if (srca == 0xff) */ + nop +1: + /* a1 = src */ + lw t0, 0(a2) /* t0 = mask */ + lw t1, 4(a2) /* t1 = mask */ + or t2, t0, t1 + beqz t2, 12f /* if (t0 == 0) && (t1 == 0) */ + addiu a2, a2, 8 + and t3, t0, t1 + move t0, t8 + move t1, a1 + lhu t2, 0(a0) /* t2 = dst */ + beq t3, s1, 11f /* if (t0 == 0xffffffff) && (t1 == 0xffffffff) */ + lhu t3, 2(a0) /* t3 = dst */ + MIPS_2xUN8x4_MUL_2xUN8x4 a1, a1, t0, t1, s2, s3, t9, t4, s4, s5, s6, s7, s8 + MIPS_2xUN8x4_MUL_2xUN8 t0, t1, t8, t8, t0, t1, t9, t4, s4, s5, s6, s7, s8 +11: + not t0, t0 + not t1, t1 + CONVERT_2x0565_TO_2x8888 t2, t3, s4, s5, t6, t7, t4, s6, s7, s8 + MIPS_2xUN8x4_MUL_2xUN8x4 s4, s5, t0, t1, s4, s5, t9, t4, s6, s7, s8, t0, t1 + addu_s.qb s2, s2, s4 + addu_s.qb s3, s3, s5 + CONVERT_2x8888_TO_2x0565 s2, s3, t2, t3, t5, t6, t7, s1, s2 + sh t2, 0(a0) + sh t3, 2(a0) +12: + addiu a3, a3, -2 + addiu t1, a3, -1 + bgtz t1, 1b + addiu a0, a0, 4 + b 3f + nop +2: + /* a1 = src */ + lw t0, 0(a2) /* t0 = mask */ + lw t1, 4(a2) /* t1 = mask */ + or t2, t0, t1 + beqz t2, 22f /* if (t0 == 0) & (t1 == 0) */ + addiu a2, a2, 8 + and t3, t0, t1 + move t2, a1 + beq t3, s1, 21f /* if (t0 == 0xffffffff) && (t1 == 0xffffffff) */ + move t3, a1 + lhu t2, 0(a0) /* t2 = dst */ + lhu t3, 2(a0) /* t3 = dst */ + MIPS_2xUN8x4_MUL_2xUN8x4 a1, a1, t0, t1, s2, s3, t9, t4, s4, s5, s6, s7, s8 + not t0, t0 + not t1, t1 + CONVERT_2x0565_TO_2x8888 t2, t3, s4, s5, t6, t7, t4, s6, s7, s8 + MIPS_2xUN8x4_MUL_2xUN8x4 s4, s5, t0, t1, s4, s5, t9, t4, s6, s7, s8, t2, t3 + addu_s.qb t2, s2, s4 + addu_s.qb t3, s3, s5 +21: + CONVERT_2x8888_TO_2x0565 t2, t3, t0, t1, t5, t6, t7, s2, s3 + sh t0, 0(a0) + sh t1, 2(a0) +22: + addiu a3, a3, -2 + addiu t1, a3, -1 + bgtz t1, 2b + addiu a0, a0, 4 +3: + blez a3, 4f + nop + /* a1 = src */ + lw t1, 0(a2) /* t1 = mask */ + beqz t1, 4f + nop + move s0, t8 /* s0 = srca */ + move t2, a1 /* t2 = src */ + beq t1, t7, 31f + lhu t0, 0(a0) /* t0 = dst */ + + MIPS_UN8x4_MUL_UN8x4 a1, t1, t2, t9, t3, t4, t5, t6 + MIPS_UN8x4_MUL_UN8 t1, t8, s0, t9, t3, t4, t5 +31: + not s0, s0 + CONVERT_1x0565_TO_1x8888 t0, s1, s2, s3 + MIPS_UN8x4_MUL_UN8x4 s1, s0, t3, t9, t4, t5, t6, t1 + addu_s.qb t0, t2, t3 + CONVERT_1x8888_TO_1x0565 t0, s1, s2, s3 + sh s1, 0(a0) +4: + RESTORE_REGS_FROM_STACK 20, s0, s1, s2, s3, s4, s5, s6, s7, s8 + j ra + nop + +END(pixman_composite_over_n_8888_0565_ca_asm_mips) |