| 1 | @ ScummVM Scumm Interpreter
|
|---|
| 2 | @ Copyright (C) 2007 The ScummVM project
|
|---|
| 3 | @
|
|---|
| 4 | @ This program is free software; you can redistribute it and/or
|
|---|
| 5 | @ modify it under the terms of the GNU General Public License
|
|---|
| 6 | @ as published by the Free Software Foundation; either version 2
|
|---|
| 7 | @ of the License, or (at your option) any later version.
|
|---|
| 8 | @
|
|---|
| 9 | @ This program is distributed in the hope that it will be useful,
|
|---|
| 10 | @ but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|---|
| 11 | @ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|---|
| 12 | @ GNU General Public License for more details.
|
|---|
| 13 | @
|
|---|
| 14 | @ You should have received a copy of the GNU General Public License
|
|---|
| 15 | @ along with this program; if not, write to the Free Software
|
|---|
| 16 | @ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
|
|---|
| 17 | @
|
|---|
| 18 | @ $URL: https://scummvm.svn.sourceforge.net/svnroot/scummvm/scummvm/trunk/backends/platform/wince/ARMscaler.s $
|
|---|
| 19 | @ $Id: ARMscaler.s 29306 2007-10-28 18:46:48Z knakos $
|
|---|
| 20 | @
|
|---|
| 21 | @ @author Robin Watts (robin@wss.co.uk)
|
|---|
| 22 |
|
|---|
| 23 | .text
|
|---|
| 24 |
|
|---|
| 25 | .global PocketPCHalfARM
|
|---|
| 26 |
|
|---|
| 27 | @ ARM implementation of PocketPCHalf scaler.
|
|---|
| 28 | @ Scales a width x height block of 16bpp pixels from srcPtr to
|
|---|
| 29 | @ dstPtr. srcPitch and dstPitch identify how to reach subsequent
|
|---|
| 30 | @ lines. redblueMask and round allow for one routine to do both
|
|---|
| 31 | @ 565 and 555 formats.
|
|---|
| 32 | PocketPCHalfARM:
|
|---|
| 33 | @ r0 = srcPtr
|
|---|
| 34 | @ r1 = srcPitch
|
|---|
| 35 | @ r2 = dstPtr
|
|---|
| 36 | @ r3 = dstPitch
|
|---|
| 37 | MOV r12,r13
|
|---|
| 38 | STMFD r13!,{r4-r11,r14}
|
|---|
| 39 | LDMIA r12,{r4-r7}
|
|---|
| 40 | @ r4 = width
|
|---|
| 41 | @ r5 = height
|
|---|
| 42 | @ r6 = redblueMask
|
|---|
| 43 | @ r7 = round
|
|---|
| 44 |
|
|---|
| 45 | SUB r3,r3,r4 @ dstPitch -= width
|
|---|
| 46 | SUBS r5,r5,#2 @ while ((height-=2) >= 0)
|
|---|
| 47 | BLT end
|
|---|
| 48 | height_loop:
|
|---|
| 49 |
|
|---|
| 50 | SUBS r11, r4, #8 @ r11= width_minus_8
|
|---|
| 51 | BLT thin
|
|---|
| 52 |
|
|---|
| 53 | width_loop:
|
|---|
| 54 | @ unroll loop 4 times here
|
|---|
| 55 | LDRH r8,[r0],r1 @ r8 = A = srcPtr[0]
|
|---|
| 56 | LDRH r9,[r0],#2 @ r9 = C = srcPtr[dstPitch]
|
|---|
| 57 | LDRH r12,[r0],-r1 @ r12= D = srcPtr[dstPitch+2]
|
|---|
| 58 | LDRH r14,[r0],#2 @ r14= B = srcPtr[2]
|
|---|
| 59 |
|
|---|
| 60 | ORR r8, r8, r8, LSL #16 @ r8 = b | g | r | b | g | r
|
|---|
| 61 | ORR r9, r9, r9, LSL #16 @ r9 = b | g | r | b | g | r
|
|---|
| 62 | ORR r12,r12,r12,LSL #16 @ r12= b | g | r | b | g | r
|
|---|
| 63 | ORR r14,r14,r14,LSL #16 @ r14= b | g | r | b | g | r
|
|---|
| 64 | AND r8, r8, r6 @ r8 = 0 | g | 0 | b | 0 | r
|
|---|
| 65 | AND r9, r9, r6 @ r9 = 0 | g | 0 | b | 0 | r
|
|---|
| 66 | AND r12,r12,r6 @ r12= 0 | g | 0 | b | 0 | r
|
|---|
| 67 | AND r14,r14,r6 @ r14= 0 | g | 0 | b | 0 | r
|
|---|
| 68 | ADD r8, r8, r9
|
|---|
| 69 | ADD r8, r8, r12
|
|---|
| 70 | ADD r8, r8, r14
|
|---|
| 71 | ADD r8, r8, r7 @ r8 = summed pixels + rounding
|
|---|
| 72 | AND r8, r6, r8, LSR #2 @ r8 = 0 | g | 0 | b | 0 | r
|
|---|
| 73 | ORR r10,r8, r8, LSR #16 @ r10= 0 | g | 0 | b | g | r
|
|---|
| 74 |
|
|---|
| 75 | LDRH r8,[r0],r1 @ r8 = A = srcPtr[0]
|
|---|
| 76 | LDRH r9,[r0],#2 @ r9 = C = srcPtr[dstPitch]
|
|---|
| 77 | LDRH r12,[r0],-r1 @ r12= D = srcPtr[dstPitch+2]
|
|---|
| 78 | LDRH r14,[r0],#2 @ r14= B = srcPtr[2]
|
|---|
| 79 |
|
|---|
| 80 | STRH r10,[r2],#2 @ *dstPtr++
|
|---|
| 81 |
|
|---|
| 82 | ORR r8, r8, r8, LSL #16 @ r8 = b | g | r | b | g | r
|
|---|
| 83 | ORR r9, r9, r9, LSL #16 @ r9 = b | g | r | b | g | r
|
|---|
| 84 | ORR r12,r12,r12,LSL #16 @ r12= b | g | r | b | g | r
|
|---|
| 85 | ORR r14,r14,r14,LSL #16 @ r14= b | g | r | b | g | r
|
|---|
| 86 | AND r8, r8, r6 @ r8 = 0 | g | 0 | b | 0 | r
|
|---|
| 87 | AND r9, r9, r6 @ r9 = 0 | g | 0 | b | 0 | r
|
|---|
| 88 | AND r12,r12,r6 @ r12= 0 | g | 0 | b | 0 | r
|
|---|
| 89 | AND r14,r14,r6 @ r14= 0 | g | 0 | b | 0 | r
|
|---|
| 90 | ADD r8, r8, r9
|
|---|
| 91 | ADD r8, r8, r12
|
|---|
| 92 | ADD r8, r8, r14
|
|---|
| 93 | ADD r8, r8, r7 @ r8 = summed pixels + rounding
|
|---|
| 94 | AND r8, r6, r8, LSR #2 @ r8 = 0 | g | 0 | b | 0 | r
|
|---|
| 95 | ORR r10,r8, r8, LSR #16 @ r10= 0 | g | 0 | b | g | r
|
|---|
| 96 |
|
|---|
| 97 | LDRH r8,[r0],r1 @ r8 = A = srcPtr[0]
|
|---|
| 98 | LDRH r9,[r0],#2 @ r9 = C = srcPtr[dstPitch]
|
|---|
| 99 | LDRH r12,[r0],-r1 @ r12= D = srcPtr[dstPitch+2]
|
|---|
| 100 | LDRH r14,[r0],#2 @ r14= B = srcPtr[2]
|
|---|
| 101 |
|
|---|
| 102 | STRH r10,[r2],#2 @ *dstPtr++
|
|---|
| 103 |
|
|---|
| 104 | ORR r8, r8, r8, LSL #16 @ r8 = b | g | r | b | g | r
|
|---|
| 105 | ORR r9, r9, r9, LSL #16 @ r9 = b | g | r | b | g | r
|
|---|
| 106 | ORR r12,r12,r12,LSL #16 @ r12= b | g | r | b | g | r
|
|---|
| 107 | ORR r14,r14,r14,LSL #16 @ r14= b | g | r | b | g | r
|
|---|
| 108 | AND r8, r8, r6 @ r8 = 0 | g | 0 | b | 0 | r
|
|---|
| 109 | AND r9, r9, r6 @ r9 = 0 | g | 0 | b | 0 | r
|
|---|
| 110 | AND r12,r12,r6 @ r12= 0 | g | 0 | b | 0 | r
|
|---|
| 111 | AND r14,r14,r6 @ r14= 0 | g | 0 | b | 0 | r
|
|---|
| 112 | ADD r8, r8, r9
|
|---|
| 113 | ADD r8, r8, r12
|
|---|
| 114 | ADD r8, r8, r14
|
|---|
| 115 | ADD r8, r8, r7 @ r8 = summed pixels + rounding
|
|---|
| 116 | AND r8, r6, r8, LSR #2 @ r8 = 0 | g | 0 | b | 0 | r
|
|---|
| 117 | ORR r10,r8, r8, LSR #16 @ r10= 0 | g | 0 | b | g | r
|
|---|
| 118 |
|
|---|
| 119 | LDRH r8,[r0],r1 @ r8 = A = srcPtr[0]
|
|---|
| 120 | LDRH r9,[r0],#2 @ r9 = C = srcPtr[dstPitch]
|
|---|
| 121 | LDRH r12,[r0],-r1 @ r12= D = srcPtr[dstPitch+2]
|
|---|
| 122 | LDRH r14,[r0],#2 @ r14= B = srcPtr[2]
|
|---|
| 123 |
|
|---|
| 124 | STRH r10,[r2],#2 @ *dstPtr++
|
|---|
| 125 |
|
|---|
| 126 | ORR r8, r8, r8, LSL #16 @ r8 = b | g | r | b | g | r
|
|---|
| 127 | ORR r9, r9, r9, LSL #16 @ r9 = b | g | r | b | g | r
|
|---|
| 128 | ORR r12,r12,r12,LSL #16 @ r12= b | g | r | b | g | r
|
|---|
| 129 | ORR r14,r14,r14,LSL #16 @ r14= b | g | r | b | g | r
|
|---|
| 130 | AND r8, r8, r6 @ r8 = 0 | g | 0 | b | 0 | r
|
|---|
| 131 | AND r9, r9, r6 @ r9 = 0 | g | 0 | b | 0 | r
|
|---|
| 132 | AND r12,r12,r6 @ r12= 0 | g | 0 | b | 0 | r
|
|---|
| 133 | AND r14,r14,r6 @ r14= 0 | g | 0 | b | 0 | r
|
|---|
| 134 | ADD r8, r8, r9
|
|---|
| 135 | ADD r8, r8, r12
|
|---|
| 136 | ADD r8, r8, r14
|
|---|
| 137 | ADD r8, r8, r7 @ r8 = summed pixels + rounding
|
|---|
| 138 | AND r8, r6, r8, LSR #2 @ r8 = 0 | g | 0 | b | 0 | r
|
|---|
| 139 | ORR r10, r8, r8, LSR #16 @ r8 = 0 | g | 0 | b | g | r
|
|---|
| 140 |
|
|---|
| 141 | STRH r10,[r2],#2 @ *dstPtr++
|
|---|
| 142 |
|
|---|
| 143 | SUBS r11,r11,#8 @ width_minus_8 -= 8
|
|---|
| 144 | BGE width_loop @ (width_minus_8 >= 0) => do 8+ more
|
|---|
| 145 |
|
|---|
| 146 | thin:
|
|---|
| 147 | ADDS r11,r11,#8 @ r11= width
|
|---|
| 148 | BEQ width_end @ if no more left to do, then bail
|
|---|
| 149 | thin_lp:
|
|---|
| 150 | @ single output pixels done in this bit
|
|---|
| 151 | LDRH r8,[r0],r1 @ r8 = A = srcPtr[0]
|
|---|
| 152 | LDRH r9,[r0],#2 @ r9 = C = srcPtr[dstPitch]
|
|---|
| 153 | LDRH r12,[r0],-r1 @ r12= D = srcPtr[dstPitch+2]
|
|---|
| 154 | LDRH r14,[r0],#2 @ r14= B = srcPtr[2]
|
|---|
| 155 |
|
|---|
| 156 | ORR r8, r8, r8, LSL #16 @ r8 = b | g | r | b | g | r
|
|---|
| 157 | ORR r9, r9, r9, LSL #16 @ r9 = b | g | r | b | g | r
|
|---|
| 158 | ORR r12,r12,r12,LSL #16 @ r12= b | g | r | b | g | r
|
|---|
| 159 | ORR r14,r14,r14,LSL #16 @ r14= b | g | r | b | g | r
|
|---|
| 160 | AND r8, r8, r6 @ r8 = 0 | g | 0 | b | 0 | r
|
|---|
| 161 | AND r9, r9, r6 @ r9 = 0 | g | 0 | b | 0 | r
|
|---|
| 162 | AND r12,r12,r6 @ r12= 0 | g | 0 | b | 0 | r
|
|---|
| 163 | AND r14,r14,r6 @ r14= 0 | g | 0 | b | 0 | r
|
|---|
| 164 | ADD r8, r8, r9
|
|---|
| 165 | ADD r8, r8, r12
|
|---|
| 166 | ADD r8, r8, r14
|
|---|
| 167 | ADD r8, r8, r7 @ r8 = summed pixels + rounding
|
|---|
| 168 | AND r8, r6, r8, LSR #2 @ r8 = 0 | g | 0 | b | 0 | r
|
|---|
| 169 | ORR r8, r8, r8, LSR #16 @ r8 = 0 | g | 0 | b | g | r
|
|---|
| 170 |
|
|---|
| 171 | STRH r8,[r2],#2 @ *dstPtr++
|
|---|
| 172 |
|
|---|
| 173 | SUBS r11,r11,#2
|
|---|
| 174 | BGT thin_lp
|
|---|
| 175 | width_end:
|
|---|
| 176 | ADD r2,r2,r3 @ dstPtr += dstPitch
|
|---|
| 177 | ADD r0,r0,r1,LSL #1 @ srcPtr += 2*srcPitch
|
|---|
| 178 | SUB r0,r0,r4,LSL #1 @ srcPtr -= 2*width
|
|---|
| 179 |
|
|---|
| 180 | SUBS r5,r5,#2
|
|---|
| 181 | BGE height_loop
|
|---|
| 182 |
|
|---|
| 183 | end:
|
|---|
| 184 | LDMFD r13!,{r4-r11,PC}
|
|---|
