vp8/common/arm/armv6/copymem16x16_v6.asm

   1 ;
   2 ;  Copyright (c) 2010 The WebM project authors. All Rights Reserved.
   3 ;
   4 ;  Use of this source code is governed by a BSD-style license
   5 ;  that can be found in the LICENSE file in the root of the source
   6 ;  tree. An additional intellectual property rights grant can be found
   7 ;  in the file PATENTS.  All contributing project authors may
   8 ;  be found in the AUTHORS file in the root of the source tree.
   9 ;
  10
  11
  12     EXPORT  |vp8_copy_mem16x16_v6|
  13     ; ARM
  14     ; REQUIRE8
  15     ; PRESERVE8
  16
  17     AREA    Block, CODE, READONLY ; name this block of code
  18 ;void copy_mem16x16_v6( unsigned char *src, int src_stride, unsigned char *dst, int dst_stride)
  19 ;-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
  20 |vp8_copy_mem16x16_v6| PROC
  21     stmdb       sp!, {r4 - r7}
  22     ;push   {r4-r7}
  23
  24     ;preload
  25     pld     [r0]
  26     pld     [r0, r1]
  27     pld     [r0, r1, lsl #1]
  28
  29     ands    r4, r0, #15
  30     beq     copy_mem16x16_fast
  31
  32     ands    r4, r0, #7
  33     beq     copy_mem16x16_8
  34
  35     ands    r4, r0, #3
  36     beq     copy_mem16x16_4
  37
  38     ;copy one byte each time
  39     ldrb    r4, [r0]
  40     ldrb    r5, [r0, #1]
  41     ldrb    r6, [r0, #2]
  42     ldrb    r7, [r0, #3]
  43
  44     mov     r12, #16
  45
  46 copy_mem16x16_1_loop
  47     strb    r4, [r2]
  48     strb    r5, [r2, #1]
  49     strb    r6, [r2, #2]
  50     strb    r7, [r2, #3]
  51
  52     ldrb    r4, [r0, #4]
  53     ldrb    r5, [r0, #5]
  54     ldrb    r6, [r0, #6]
  55     ldrb    r7, [r0, #7]
  56
  57     subs    r12, r12, #1
  58
  59     strb    r4, [r2, #4]
  60     strb    r5, [r2, #5]
  61     strb    r6, [r2, #6]
  62     strb    r7, [r2, #7]
  63
  64     ldrb    r4, [r0, #8]
  65     ldrb    r5, [r0, #9]
  66     ldrb    r6, [r0, #10]
  67     ldrb    r7, [r0, #11]
  68
  69     strb    r4, [r2, #8]
  70     strb    r5, [r2, #9]
  71     strb    r6, [r2, #10]
  72     strb    r7, [r2, #11]
  73
  74     ldrb    r4, [r0, #12]
  75     ldrb    r5, [r0, #13]
  76     ldrb    r6, [r0, #14]
  77     ldrb    r7, [r0, #15]
  78
  79     add     r0, r0, r1
  80
  81     strb    r4, [r2, #12]
  82     strb    r5, [r2, #13]
  83     strb    r6, [r2, #14]
  84     strb    r7, [r2, #15]
  85
  86     add     r2, r2, r3
  87
  88     ldrneb  r4, [r0]
  89     ldrneb  r5, [r0, #1]
  90     ldrneb  r6, [r0, #2]
  91     ldrneb  r7, [r0, #3]
  92
  93     bne     copy_mem16x16_1_loop
  94
  95     ldmia       sp!, {r4 - r7}
  96     ;pop        {r4-r7}
  97     mov     pc, lr
  98
  99 ;copy 4 bytes each time
 100 copy_mem16x16_4
 101     ldr     r4, [r0]
 102     ldr     r5, [r0, #4]
 103     ldr     r6, [r0, #8]
 104     ldr     r7, [r0, #12]
 105
 106     mov     r12, #16
 107
 108 copy_mem16x16_4_loop
 109     subs    r12, r12, #1
 110     add     r0, r0, r1
 111
 112     str     r4, [r2]
 113     str     r5, [r2, #4]
 114     str     r6, [r2, #8]
 115     str     r7, [r2, #12]
 116
 117     add     r2, r2, r3
 118
 119     ldrne   r4, [r0]
 120     ldrne   r5, [r0, #4]
 121     ldrne   r6, [r0, #8]
 122     ldrne   r7, [r0, #12]
 123
 124     bne     copy_mem16x16_4_loop
 125
 126     ldmia       sp!, {r4 - r7}
 127     ;pop        {r4-r7}
 128     mov     pc, lr
 129
 130 ;copy 8 bytes each time
 131 copy_mem16x16_8
 132     sub     r1, r1, #16
 133     sub     r3, r3, #16
 134
 135     mov     r12, #16
 136
 137 copy_mem16x16_8_loop
 138     ldmia   r0!, {r4-r5}
 139     ;ldm        r0, {r4-r5}
 140     ldmia   r0!, {r6-r7}
 141
 142     add     r0, r0, r1
 143
 144     stmia   r2!, {r4-r5}
 145     subs    r12, r12, #1
 146     ;stm        r2, {r4-r5}
 147     stmia   r2!, {r6-r7}
 148
 149     add     r2, r2, r3
 150
 151     bne     copy_mem16x16_8_loop
 152
 153     ldmia       sp!, {r4 - r7}
 154     ;pop        {r4-r7}
 155     mov     pc, lr
 156
 157 ;copy 16 bytes each time
 158 copy_mem16x16_fast
 159     ;sub        r1, r1, #16
 160     ;sub        r3, r3, #16
 161
 162     mov     r12, #16
 163
 164 copy_mem16x16_fast_loop
 165     ldmia   r0, {r4-r7}
 166     ;ldm        r0, {r4-r7}
 167     add     r0, r0, r1
 168
 169     subs    r12, r12, #1
 170     stmia   r2, {r4-r7}
 171     ;stm        r2, {r4-r7}
 172     add     r2, r2, r3
 173
 174     bne     copy_mem16x16_fast_loop
 175
 176     ldmia       sp!, {r4 - r7}
 177     ;pop        {r4-r7}
 178     mov     pc, lr
 179
 180     ENDP  ; |vp8_copy_mem16x16_v6|
 181
 182     END