aboutsummaryrefslogtreecommitdiff
path: root/pixman/pixman/pixman-mips-dspr2-asm.S
diff options
context:
space:
mode:
Diffstat (limited to 'pixman/pixman/pixman-mips-dspr2-asm.S')
-rw-r--r--pixman/pixman/pixman-mips-dspr2-asm.S723
1 files changed, 523 insertions, 200 deletions
diff --git a/pixman/pixman/pixman-mips-dspr2-asm.S b/pixman/pixman/pixman-mips-dspr2-asm.S
index 3adbb2afe..866e93e58 100644
--- a/pixman/pixman/pixman-mips-dspr2-asm.S
+++ b/pixman/pixman/pixman-mips-dspr2-asm.S
@@ -699,6 +699,127 @@ 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_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)
@@ -840,34 +961,35 @@ LEAF_MIPS_DSPR2(pixman_composite_over_n_8888_8888_ca_asm_mips)
* a3 - w
*/
- SAVE_REGS_ON_STACK 8, s0, s1, s2, s3, s4, s5
- beqz a3, 4f
+ beqz a3, 8f
nop
+ SAVE_REGS_ON_STACK 8, s0, s1, s2, s3, s4, s5
+
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 */
+ beqz t1, 4f /* last pixel */
nop
- beq t8, t6, 2f /* if (srca == 0xff) */
- nop
-1:
- /* a1 = src */
+
+0:
lw t0, 0(a2) /* t0 = mask */
lw t1, 4(a2) /* t1 = mask */
+ addiu a3, a3, -2 /* w = w - 2 */
or t2, t0, t1
- beqz t2, 12f /* if (t0 == 0) && (t1 == 0) */
+ beqz t2, 3f /* if (t0 == 0) && (t1 == 0) */
addiu a2, a2, 8
- and t3, t0, t1
- move t4, a1 /* t4 = src */
- move t5, a1 /* t5 = src */
+ and t2, t0, t1
+ beq t2, t7, 1f /* if (t0 == 0xffffffff) && (t1 == 0xffffffff) */
+ nop
+
+//if(ma)
lw t2, 0(a0) /* t2 = dst */
- beq t3, t7, 11f /* if (t0 == 0xffffffff) && (t1 == 0xffffffff) */
- lw t3, 4(a0) /* t3 = dst */
+ lw t3, 4(a0) /* t3 = 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, t0, t1, t9, s0, s1, s2, s3, s4, s5
-11:
not t0, t0
not t1, t1
MIPS_2xUN8x4_MUL_2xUN8x4 t2, t3, t0, t1, t2, t3, t9, s0, s1, s2, s3, s4, s5
@@ -875,62 +997,79 @@ LEAF_MIPS_DSPR2(pixman_composite_over_n_8888_8888_ca_asm_mips)
addu_s.qb t3, t5, t3
sw t2, 0(a0)
sw t3, 4(a0)
-12:
- addiu a3, a3, -2
addiu t1, a3, -1
- bgtz t1, 1b
+ bgtz t1, 0b
addiu a0, a0, 8
- b 3f
+ b 4f
+ nop
+1:
+//if (t0 == 0xffffffff) && (t1 == 0xffffffff):
+ beq t8, t6, 2f /* if (srca == 0xff) */
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 t4, a1
- beq t2, t7, 21f /* if (t0 == 0xffffffff) && (t1 == 0xffffffff) */
- move t5, 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, t2, t3, t9, s0, s1, s2, s3, s4, s5
- addu_s.qb t4, t4, t2
- addu_s.qb t5, t5, t3
-21:
- sw t4, 0(a0)
- sw t5, 4(a0)
-22:
- addiu a3, a3, -2
+ not t0, a1
+ not t1, a1
+ srl t0, t0, 24
+ srl t1, t1, 24
+ MIPS_2xUN8x4_MUL_2xUN8 t2, t3, t0, t1, t2, t3, t9, s0, s1, s2, s3, s4, s5
+ addu_s.qb t2, a1, t2
+ addu_s.qb t3, a1, t3
+ sw t2, 0(a0)
+ sw t3, 4(a0)
addiu t1, a3, -1
- bgtz t1, 2b
+ bgtz t1, 0b
addiu a0, a0, 8
+ b 4f
+ nop
+2:
+ sw a1, 0(a0)
+ sw a1, 4(a0)
3:
- blez a3, 4f
+ addiu t1, a3, -1
+ bgtz t1, 0b
+ addiu a0, a0, 8
+
+4:
+ beqz a3, 7f
nop
/* a1 = src */
- lw t1, 0(a2) /* t1 = mask */
- beqz t1, 4f
+ lw t0, 0(a2) /* t0 = mask */
+ beqz t0, 7f /* if (t0 == 0) */
nop
- 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, t1, t9, t3, t4, t5
-31:
- not t1, t1
- MIPS_UN8x4_MUL_UN8x4 t0, t1, t0, t9, t3, t4, t5, t6
- addu_s.qb t0, t2, t0
- sw t0, 0(a0)
-4:
+ beq t0, t7, 5f /* if (t0 == 0xffffffff) */
+ nop
+//if(ma)
+ lw t1, 0(a0) /* t1 = dst */
+ MIPS_UN8x4_MUL_UN8x4 a1, t0, t2, t9, t3, t4, t5, s0
+ MIPS_UN8x4_MUL_UN8 t0, t8, t0, t9, t3, t4, t5
+ not t0, t0
+ MIPS_UN8x4_MUL_UN8x4 t1, t0, t1, t9, t3, t4, t5, s0
+ addu_s.qb t1, t2, t1
+ sw t1, 0(a0)
RESTORE_REGS_FROM_STACK 8, s0, s1, s2, s3, s4, s5
j ra
nop
+5:
+//if (t0 == 0xffffffff)
+ beq t8, t6, 6f /* if (srca == 0xff) */
+ nop
+ lw t1, 0(a0) /* t1 = dst */
+ not t0, a1
+ srl t0, t0, 24
+ MIPS_UN8x4_MUL_UN8 t1, t0, t1, t9, t2, t3, t4
+ addu_s.qb t1, a1, t1
+ sw t1, 0(a0)
+ RESTORE_REGS_FROM_STACK 8, s0, s1, s2, s3, s4, s5
+ j ra
+ nop
+6:
+ sw a1, 0(a0)
+7:
+ RESTORE_REGS_FROM_STACK 8, s0, s1, s2, s3, s4, s5
+8:
+ j ra
+ nop
END(pixman_composite_over_n_8888_8888_ca_asm_mips)
@@ -942,106 +1081,126 @@ LEAF_MIPS_DSPR2(pixman_composite_over_n_8888_0565_ca_asm_mips)
* a3 - w
*/
- SAVE_REGS_ON_STACK 20, s0, s1, s2, s3, s4, s5, s6, s7, s8
- beqz a3, 4f
+ beqz a3, 8f
nop
- li t5, 0xf800f800
- li t6, 0x07e007e0
- li t7, 0x001F001F
- li t9, 0x00ff00ff
+ SAVE_REGS_ON_STACK 20, s0, s1, s2, s3, s4, s5, s6, s7, s8
+ li t6, 0xff
+ addiu t7, zero, -1 /* t7 = 0xffffffff */
srl t8, a1, 24 /* t8 = srca */
+ li t9, 0x00ff00ff
+ li s6, 0xf800f800
+ li s7, 0x07e007e0
+ li s8, 0x001F001F
+
addiu t1, a3, -1
- beqz t1, 3f /* last pixel */
+ beqz t1, 4f /* 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 */
+0:
lw t0, 0(a2) /* t0 = mask */
lw t1, 4(a2) /* t1 = mask */
+ addiu a3, a3, -2 /* w = w - 2 */
or t2, t0, t1
- beqz t2, 12f /* if (t0 == 0) && (t1 == 0) */
+ beqz t2, 3f /* if (t0 == 0) && (t1 == 0) */
addiu a2, a2, 8
- and t3, t0, t1
- move s2, a1 /* s2 = src */
- move s3, a1 /* s3 = src */
+ and t2, t0, t1
+ beq t2, t7, 1f /* if (t0 == 0xffffffff) && (t1 == 0xffffffff) */
+ nop
+
+//if(ma)
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:
+ lhu t3, 2(a0) /* t3 = 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, t0, t1, t9, s0, s1, s2, s3, s4, s5
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, s4, s5
+ CONVERT_2x0565_TO_2x8888 t2, t3, t2, t3, s7, s8, s0, s1, s2, s3
+ MIPS_2xUN8x4_MUL_2xUN8x4 t2, t3, t0, t1, t2, t3, t9, s0, s1, s2, s3, s4, s5
+ addu_s.qb t2, t4, t2
+ addu_s.qb t3, t5, t3
+ CONVERT_2x8888_TO_2x0565 t2, t3, t2, t3, s6, s7, s8, s0, s1
sh t2, 0(a0)
sh t3, 2(a0)
-12:
- addiu a3, a3, -2
addiu t1, a3, -1
- bgtz t1, 1b
+ bgtz t1, 0b
addiu a0, a0, 4
- b 3f
+ b 4f
+ nop
+1:
+//if (t0 == 0xffffffff) && (t1 == 0xffffffff):
+ beq t8, t6, 2f /* if (srca == 0xff) */
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
+ not t0, a1
+ not t1, a1
+ srl t0, t0, 24
+ srl t1, t1, 24
+ CONVERT_2x0565_TO_2x8888 t2, t3, t2, t3, s7, s8, s0, s1, s2, s3
+ MIPS_2xUN8x4_MUL_2xUN8 t2, t3, t0, t1, t2, t3, t9, s0, s1, s2, s3, s4, s5
+ addu_s.qb t2, a1, t2
+ addu_s.qb t3, a1, t3
+ CONVERT_2x8888_TO_2x0565 t2, t3, t2, t3, s6, s7, s8, s0, s1
+ sh t2, 0(a0)
+ sh t3, 2(a0)
addiu t1, a3, -1
- bgtz t1, 2b
+ bgtz t1, 0b
addiu a0, a0, 4
+ b 4f
+ nop
+2:
+ CONVERT_1x8888_TO_1x0565 a1, t2, s0, s1
+ sh t2, 0(a0)
+ sh t2, 2(a0)
3:
- blez a3, 4f
+ addiu t1, a3, -1
+ bgtz t1, 0b
+ addiu a0, a0, 4
+
+4:
+ beqz a3, 7f
nop
/* a1 = src */
- lw t1, 0(a2) /* t1 = mask */
- beqz t1, 4f
+ lw t0, 0(a2) /* t0 = mask */
+ beqz t0, 7f /* if (t0 == 0) */
nop
- 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, t1, t9, t3, t4, t5
-31:
- not t1, t1
- CONVERT_1x0565_TO_1x8888 t0, s1, s2, s3
- MIPS_UN8x4_MUL_UN8x4 s1, t1, t3, t9, t4, t5, t6, t7
- 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
+ beq t0, t7, 5f /* if (t0 == 0xffffffff) */
+ nop
+//if(ma)
+ lhu t1, 0(a0) /* t1 = dst */
+ MIPS_UN8x4_MUL_UN8x4 a1, t0, t2, t9, t3, t4, t5, s0
+ MIPS_UN8x4_MUL_UN8 t0, t8, t0, t9, t3, t4, t5
+ not t0, t0
+ CONVERT_1x0565_TO_1x8888 t1, s1, s2, s3
+ MIPS_UN8x4_MUL_UN8x4 s1, t0, s1, t9, t3, t4, t5, s0
+ addu_s.qb s1, t2, s1
+ CONVERT_1x8888_TO_1x0565 s1, t1, s0, s2
+ sh t1, 0(a0)
+ RESTORE_REGS_FROM_STACK 20, s0, s1, s2, s3, s4, s5, s6, s7, s8
+ j ra
+ nop
+5:
+//if (t0 == 0xffffffff)
+ beq t8, t6, 6f /* if (srca == 0xff) */
+ nop
+ lhu t1, 0(a0) /* t1 = dst */
+ not t0, a1
+ srl t0, t0, 24
+ CONVERT_1x0565_TO_1x8888 t1, s1, s2, s3
+ MIPS_UN8x4_MUL_UN8 s1, t0, s1, t9, t2, t3, t4
+ addu_s.qb s1, a1, s1
+ CONVERT_1x8888_TO_1x0565 s1, t1, s0, s2
+ sh t1, 0(a0)
+ RESTORE_REGS_FROM_STACK 20, s0, s1, s2, s3, s4, s5, s6, s7, s8
+ j ra
+ nop
+6:
+ CONVERT_1x8888_TO_1x0565 a1, t1, s0, s2
+ sh t1, 0(a0)
+7:
+ RESTORE_REGS_FROM_STACK 20, s0, s1, s2, s3, s4, s5, s6, s7, s8
+8:
j ra
nop
@@ -2936,101 +3095,265 @@ END(pixman_composite_over_reverse_n_8888_asm_mips)
LEAF_MIPS_DSPR2(pixman_composite_in_n_8_asm_mips)
/*
* a0 - dst (a8)
- * a1 - src (a8r8g8b8)
+ * a1 - src (32bit constant)
* a2 - w
*/
- beqz a2, 5f
+ li t9, 0x00ff00ff
+ beqz a2, 3f
nop
-
- SAVE_REGS_ON_STACK 20, s0, s1, s2, s3, s4, s5, s6, s7
- move t7, a1
- srl t5, t7, 24
- replv.ph t5, t5
- srl t9, a2, 2 /* t1 = how many multiples of 4 src pixels */
- beqz t9, 2f /* branch if less than 4 src pixels */
+ srl t7, a2, 2 /* t7 = how many multiples of 4 dst pixels */
+ beqz t7, 1f /* branch if less than 4 src pixels */
nop
-1:
- addiu t9, t9, -1
- addiu a2, a2, -4
+ srl t8, a1, 24
+ replv.ph t8, t8
+
+0:
+ beqz t7, 1f
+ addiu t7, t7, -1
lbu t0, 0(a0)
lbu t1, 1(a0)
lbu t2, 2(a0)
lbu t3, 3(a0)
- muleu_s.ph.qbl s0, t0, t5
- muleu_s.ph.qbr s1, t0, t5
- muleu_s.ph.qbl s2, t1, t5
- muleu_s.ph.qbr s3, t1, t5
- muleu_s.ph.qbl s4, t2, t5
- muleu_s.ph.qbr s5, t2, t5
- muleu_s.ph.qbl s6, t3, t5
- muleu_s.ph.qbr s7, t3, t5
-
- shrl.ph t4, s0, 8
- shrl.ph t6, s1, 8
- shrl.ph t7, s2, 8
- shrl.ph t8, s3, 8
- addq.ph t0, s0, t4
- addq.ph t1, s1, t6
- addq.ph t2, s2, t7
- addq.ph t3, s3, t8
- shra_r.ph t0, t0, 8
- shra_r.ph t1, t1, 8
+ precr_sra.ph.w t1, t0, 0
+ precr_sra.ph.w t3, t2, 0
+ precr.qb.ph t0, t3, t1
+
+ muleu_s.ph.qbl t2, t0, t8
+ muleu_s.ph.qbr t3, t0, t8
+ shra_r.ph t4, t2, 8
+ shra_r.ph t5, t3, 8
+ and t4, t4, t9
+ and t5, t5, t9
+ addq.ph t2, t2, t4
+ addq.ph t3, t3, t5
shra_r.ph t2, t2, 8
shra_r.ph t3, t3, 8
- shrl.ph t4, s4, 8
- shrl.ph t6, s5, 8
- shrl.ph t7, s6, 8
- shrl.ph t8, s7, 8
- addq.ph s0, s4, t4
- addq.ph s1, s5, t6
- addq.ph s2, s6, t7
- addq.ph s3, s7, t8
- shra_r.ph t4, s0, 8
- shra_r.ph t6, s1, 8
- shra_r.ph t7, s2, 8
- shra_r.ph t8, s3, 8
-
- precr.qb.ph s0, t0, t1
- precr.qb.ph s1, t2, t3
- precr.qb.ph s2, t4, t6
- precr.qb.ph s3, t7, t8
+ precr.qb.ph t2, t2, t3
- sb s0, 0(a0)
- sb s1, 1(a0)
- sb s2, 2(a0)
- sb s3, 3(a0)
- bgtz t9, 1b
+ sb t2, 0(a0)
+ srl t2, t2, 8
+ sb t2, 1(a0)
+ srl t2, t2, 8
+ sb t2, 2(a0)
+ srl t2, t2, 8
+ sb t2, 3(a0)
+ addiu a2, a2, -4
+ b 0b
addiu a0, a0, 4
-2:
- beqz a2, 4f
+
+1:
+ beqz a2, 3f
nop
-3:
- lbu t1, 0(a0)
+ srl t8, a1, 24
+2:
+ lbu t0, 0(a0)
+
+ mul t2, t0, t8
+ shra_r.ph t3, t2, 8
+ andi t3, t3, 0x00ff
+ addq.ph t2, t2, t3
+ shra_r.ph t2, t2, 8
- muleu_s.ph.qbl t4, t1, t5
- muleu_s.ph.qbr t7, t1, t5
- shrl.ph t6, t4, 8
- shrl.ph t0, t7, 8
- addq.ph t8, t4, t6
- addq.ph t9, t7, t0
- shra_r.ph t8, t8, 8
- shra_r.ph t9, t9, 8
- precr.qb.ph t2, t8, t9
sb t2, 0(a0)
addiu a2, a2, -1
- bnez a2, 3b
+ bnez a2, 2b
addiu a0, a0, 1
-4:
- RESTORE_REGS_FROM_STACK 20, s0, s1, s2, s3, s4, s5, s6, s7
-5:
+
+3:
j ra
nop
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_0565_OVER_asm_mips)
+/*
+ * a0 - dst (r5g6b5)
+ * a1 - src (a8r8g8b8)
+ * a2 - w
+ * a3 - vx
+ * 16(sp) - unit_x
+ */
+
+ SAVE_REGS_ON_STACK 24, s0, s1, s2, s3, s4, v0, v1
+ lw t8, 40(sp) /* t8 = unit_x */
+ li t4, 0x00ff00ff
+ li t5, 0xf800f800
+ li t6, 0x07e007e0
+ li t7, 0x001F001F
+ 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 */
+ lhu t2, 0(a0) /* t2 = destination (r5g6b5) */
+ lhu t3, 2(a0) /* t3 = destination (r5g6b5) */
+
+ CONVERT_2x0565_TO_2x8888 t2, t3, v0, v1, t6, t7, s0, s1, s2, s3
+ OVER_2x8888_2x8888 t0, t1, v0, v1, t2, t3, t4, t9, s0, s1, s2, s3, s4
+ CONVERT_2x8888_TO_2x0565 t2, t3, v0, v1, t5, t6, t7, t9, s2
+
+ sh v0, 0(a0)
+ sh v1, 2(a0)
+ addiu a2, a2, -2
+ addiu t1, a2, -1
+ bgtz t1, 1b
+ addiu a0, a0, 4
+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) */
+ lhu t1, 0(a0) /* t1 = destination (r5g6b5) */
+ addu a3, a3, t8 /* a3 = vx + unit_x */
+
+ CONVERT_1x0565_TO_1x8888 t1, t2, t5, t6
+ OVER_8888_8888 t0, t2, t1, t4, t3, t5, t6, t7
+ CONVERT_1x8888_TO_1x0565 t1, t2, t5, t6
+
+ sh t2, 0(a0)
+3:
+ RESTORE_REGS_FROM_STACK 24, s0, s1, s2, s3, s4, v0, v1
+ j ra
+ nop
+
+END(pixman_scaled_nearest_scanline_8888_0565_OVER_asm_mips)
+
+LEAF_MIPS_DSPR2(pixman_scaled_nearest_scanline_0565_8888_SRC_asm_mips)
+/*
+ * a0 - dst (a8r8g8b8)
+ * a1 - src (r5g6b5)
+ * a2 - w
+ * a3 - vx
+ * 16(sp) - unit_x
+ */
+
+ SAVE_REGS_ON_STACK 0, v0
+ beqz a2, 3f
+ nop
+
+ lw v0, 16(sp) /* v0 = unit_x */
+ addiu t1, a2, -1
+ beqz t1, 2f
+ nop
+
+ li t4, 0x07e007e0
+ li t5, 0x001F001F
+1:
+ sra t0, a3, 16 /* t0 = vx >> 16 */
+ sll t0, t0, 1 /* t0 = t0 * 2 ((r5g6b5)) */
+ addu t0, a1, t0
+ lhu t0, 0(t0) /* t0 = source ((r5g6b5)) */
+ addu a3, a3, v0 /* a3 = vx + unit_x */
+ sra t1, a3, 16 /* t1 = vx >> 16 */
+ sll t1, t1, 1 /* t1 = t1 * 2 ((r5g6b5)) */
+ addu t1, a1, t1
+ lhu t1, 0(t1) /* t1 = source ((r5g6b5)) */
+ addu a3, a3, v0 /* a3 = vx + unit_x */
+ addiu a2, a2, -2
+
+ CONVERT_2x0565_TO_2x8888 t0, t1, t2, t3, t4, t5, t6, t7, t8, t9
+
+ sw t2, 0(a0)
+ sw t3, 4(a0)
+
+ addiu t2, a2, -1
+ bgtz t2, 1b
+ addiu a0, a0, 8
+2:
+ beqz a2, 3f
+ nop
+ sra t0, a3, 16 /* t0 = vx >> 16 */
+ sll t0, t0, 1 /* t0 = t0 * 2 ((r5g6b5)) */
+ addu t0, a1, t0
+ lhu t0, 0(t0) /* t0 = source ((r5g6b5)) */
+
+ CONVERT_1x0565_TO_1x8888 t0, t1, t2, t3
+
+ sw t1, 0(a0)
+3:
+ RESTORE_REGS_FROM_STACK 0, v0
+ j ra
+ nop
+
+END(pixman_scaled_nearest_scanline_0565_8888_SRC_asm_mips)
+
LEAF_MIPS_DSPR2(pixman_scaled_nearest_scanline_8888_8_0565_OVER_asm_mips)
/*
* a0 - dst (r5g6b5)
generated by cgit v1.2.3 (git 2.25.1) at 2024-07-05 10:55:10 +0000