aboutsummaryrefslogtreecommitdiff
path: root/backends/platform/wince/ARMscaler.s
blob: bcd391766578eca4e8d8daf6ee5a851aef989795 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
@ ScummVM Scumm Interpreter
@ Copyright (C) 2007 The ScummVM project
@
@ This program is free software; you can redistribute it and/or
@ modify it under the terms of the GNU General Public License
@ as published by the Free Software Foundation; either version 2
@ of the License, or (at your option) any later version.
@
@ This program is distributed in the hope that it will be useful,
@ but WITHOUT ANY WARRANTY; without even the implied warranty of
@ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
@ GNU General Public License for more details.
@
@ You should have received a copy of the GNU General Public License
@ along with this program; if not, write to the Free Software
@ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
@
@ $URL$
@ $Id$
@
@ @author Robin Watts (robin@wss.co.uk)

	.text

	.global	PocketPCHalfARM

	@ ARM implementation of PocketPCHalf scaler.
	@ Scales a width x height block of 16bpp pixels from srcPtr to
	@ dstPtr. srcPitch and dstPitch identify how to reach subsequent
	@ lines. redblueMask and round allow for one routine to do both
	@ 565 and 555 formats.
PocketPCHalfARM:
	@ r0 = srcPtr
	@ r1 = srcPitch
	@ r2 = dstPtr
	@ r3 = dstPitch
	MOV	r12,r13
	STMFD	r13!,{r4-r11,r14}
	LDMIA	r12,{r4-r7}
	@ r4 = width
	@ r5 = height
	@ r6 = redblueMask
	@ r7 = round

	SUB	r3,r3,r4		@ dstPitch -= width
	SUBS	r5,r5,#2		@ while ((height-=2) >= 0)
	BLT	end
height_loop:

        SUBS	r11, r4, #8		@ r11= width_minus_8
	BLT	thin

width_loop:
	@ unroll loop 4 times here
	LDRH	r8,[r0],r1		@ r8 = A = srcPtr[0]
	LDRH	r9,[r0],#2		@ r9 = C = srcPtr[dstPitch]
	LDRH	r12,[r0],-r1		@ r12= D = srcPtr[dstPitch+2]
	LDRH	r14,[r0],#2		@ r14= B = srcPtr[2]

	ORR	r8, r8, r8, LSL #16	@ r8 = b | g | r | b | g | r
	ORR	r9, r9, r9, LSL #16	@ r9 = b | g | r | b | g | r
	ORR	r12,r12,r12,LSL #16	@ r12= b | g | r | b | g | r
	ORR	r14,r14,r14,LSL #16	@ r14= b | g | r | b | g | r
	AND	r8, r8, r6		@ r8 = 0 | g | 0 | b | 0 | r
	AND	r9, r9, r6		@ r9 = 0 | g | 0 | b | 0 | r
	AND	r12,r12,r6		@ r12= 0 | g | 0 | b | 0 | r
	AND	r14,r14,r6		@ r14= 0 | g | 0 | b | 0 | r
	ADD	r8, r8, r9
	ADD	r8, r8, r12
	ADD	r8, r8, r14
	ADD	r8, r8, r7		@ r8 = summed pixels + rounding
	AND	r8, r6, r8, LSR #2	@ r8 = 0 | g | 0 | b | 0 | r
	ORR	r10,r8, r8, LSR #16	@ r10= 0 | g | 0 | b | g | r

	LDRH	r8,[r0],r1		@ r8 = A = srcPtr[0]
	LDRH	r9,[r0],#2		@ r9 = C = srcPtr[dstPitch]
	LDRH	r12,[r0],-r1		@ r12= D = srcPtr[dstPitch+2]
	LDRH	r14,[r0],#2		@ r14= B = srcPtr[2]

	STRH	r10,[r2],#2		@ *dstPtr++

	ORR	r8, r8, r8, LSL #16	@ r8 = b | g | r | b | g | r
	ORR	r9, r9, r9, LSL #16	@ r9 = b | g | r | b | g | r
	ORR	r12,r12,r12,LSL #16	@ r12= b | g | r | b | g | r
	ORR	r14,r14,r14,LSL #16	@ r14= b | g | r | b | g | r
	AND	r8, r8, r6		@ r8 = 0 | g | 0 | b | 0 | r
	AND	r9, r9, r6		@ r9 = 0 | g | 0 | b | 0 | r
	AND	r12,r12,r6		@ r12= 0 | g | 0 | b | 0 | r
	AND	r14,r14,r6		@ r14= 0 | g | 0 | b | 0 | r
	ADD	r8, r8, r9
	ADD	r8, r8, r12
	ADD	r8, r8, r14
	ADD	r8, r8, r7		@ r8 = summed pixels + rounding
	AND	r8, r6, r8, LSR #2	@ r8 = 0 | g | 0 | b | 0 | r
	ORR	r10,r8, r8, LSR #16	@ r10= 0 | g | 0 | b | g | r

	LDRH	r8,[r0],r1		@ r8 = A = srcPtr[0]
	LDRH	r9,[r0],#2		@ r9 = C = srcPtr[dstPitch]
	LDRH	r12,[r0],-r1		@ r12= D = srcPtr[dstPitch+2]
	LDRH	r14,[r0],#2		@ r14= B = srcPtr[2]

	STRH	r10,[r2],#2		@ *dstPtr++

	ORR	r8, r8, r8, LSL #16	@ r8 = b | g | r | b | g | r
	ORR	r9, r9, r9, LSL #16	@ r9 = b | g | r | b | g | r
	ORR	r12,r12,r12,LSL #16	@ r12= b | g | r | b | g | r
	ORR	r14,r14,r14,LSL #16	@ r14= b | g | r | b | g | r
	AND	r8, r8, r6		@ r8 = 0 | g | 0 | b | 0 | r
	AND	r9, r9, r6		@ r9 = 0 | g | 0 | b | 0 | r
	AND	r12,r12,r6		@ r12= 0 | g | 0 | b | 0 | r
	AND	r14,r14,r6		@ r14= 0 | g | 0 | b | 0 | r
	ADD	r8, r8, r9
	ADD	r8, r8, r12
	ADD	r8, r8, r14
	ADD	r8, r8, r7		@ r8 = summed pixels + rounding
	AND	r8, r6, r8, LSR #2	@ r8 = 0 | g | 0 | b | 0 | r
	ORR	r10,r8, r8, LSR #16	@ r10= 0 | g | 0 | b | g | r

	LDRH	r8,[r0],r1		@ r8 = A = srcPtr[0]
	LDRH	r9,[r0],#2		@ r9 = C = srcPtr[dstPitch]
	LDRH	r12,[r0],-r1		@ r12= D = srcPtr[dstPitch+2]
	LDRH	r14,[r0],#2		@ r14= B = srcPtr[2]

	STRH	r10,[r2],#2		@ *dstPtr++

	ORR	r8, r8, r8, LSL #16	@ r8 = b | g | r | b | g | r
	ORR	r9, r9, r9, LSL #16	@ r9 = b | g | r | b | g | r
	ORR	r12,r12,r12,LSL #16	@ r12= b | g | r | b | g | r
	ORR	r14,r14,r14,LSL #16	@ r14= b | g | r | b | g | r
	AND	r8, r8, r6		@ r8 = 0 | g | 0 | b | 0 | r
	AND	r9, r9, r6		@ r9 = 0 | g | 0 | b | 0 | r
	AND	r12,r12,r6		@ r12= 0 | g | 0 | b | 0 | r
	AND	r14,r14,r6		@ r14= 0 | g | 0 | b | 0 | r
	ADD	r8, r8, r9
	ADD	r8, r8, r12
	ADD	r8, r8, r14
	ADD	r8, r8, r7		@ r8 = summed pixels + rounding
	AND	r8, r6, r8, LSR #2	@ r8 = 0 | g | 0 | b | 0 | r
	ORR	r10, r8, r8, LSR #16	@ r8 = 0 | g | 0 | b | g | r

	STRH	r10,[r2],#2		@ *dstPtr++

	SUBS	r11,r11,#8		@ width_minus_8 -= 8
	BGE	width_loop		@ (width_minus_8 >= 0) => do 8+ more

thin:
	ADDS	r11,r11,#8		@ r11= width
	BEQ	width_end		@ if no more left to do, then bail
thin_lp:
	@ single output pixels done in this bit
	LDRH	r8,[r0],r1		@ r8 = A = srcPtr[0]
	LDRH	r9,[r0],#2		@ r9 = C = srcPtr[dstPitch]
	LDRH	r12,[r0],-r1		@ r12= D = srcPtr[dstPitch+2]
	LDRH	r14,[r0],#2		@ r14= B = srcPtr[2]

	ORR	r8, r8, r8, LSL #16	@ r8 = b | g | r | b | g | r
	ORR	r9, r9, r9, LSL #16	@ r9 = b | g | r | b | g | r
	ORR	r12,r12,r12,LSL #16	@ r12= b | g | r | b | g | r
	ORR	r14,r14,r14,LSL #16	@ r14= b | g | r | b | g | r
	AND	r8, r8, r6		@ r8 = 0 | g | 0 | b | 0 | r
	AND	r9, r9, r6		@ r9 = 0 | g | 0 | b | 0 | r
	AND	r12,r12,r6		@ r12= 0 | g | 0 | b | 0 | r
	AND	r14,r14,r6		@ r14= 0 | g | 0 | b | 0 | r
	ADD	r8, r8, r9
	ADD	r8, r8, r12
	ADD	r8, r8, r14
	ADD	r8, r8, r7		@ r8 = summed pixels + rounding
	AND	r8, r6, r8, LSR #2	@ r8 = 0 | g | 0 | b | 0 | r
	ORR	r8, r8, r8, LSR #16	@ r8 = 0 | g | 0 | b | g | r

	STRH	r8,[r2],#2		@ *dstPtr++

	SUBS	r11,r11,#2
	BGT	thin_lp
width_end:
	ADD	r2,r2,r3		@ dstPtr += dstPitch
	ADD	r0,r0,r1,LSL #1		@ srcPtr += 2*srcPitch
	SUB	r0,r0,r4,LSL #1		@ srcPtr -= 2*width

	SUBS	r5,r5,#2
	BGE	height_loop

end:
	LDMFD	r13!,{r4-r11,PC}