vp8/common/arm/armv6/copymem8x4_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_mem8x4_v6|
  13     ; ARM
  14     ; REQUIRE8
  15     ; PRESERVE8
  16
  17     AREA    Block, CODE, READONLY ; name this block of code
  18 ;void vp8_copy_mem8x4_v6( unsigned char *src, int src_stride, unsigned char *dst, int dst_stride)
  19 ;-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
  20 |vp8_copy_mem8x4_v6| PROC
  21     ;push   {r4-r5}
  22     stmdb  sp!, {r4-r5}
  23
  24     ;preload
  25     pld     [r0]
  26     pld     [r0, r1]
  27     pld     [r0, r1, lsl #1]
  28
  29     ands    r4, r0, #7
  30     beq     copy_mem8x4_fast
  31
  32     ands    r4, r0, #3
  33     beq     copy_mem8x4_4
  34
  35     ;copy 1 byte each time
  36     ldrb    r4, [r0]
  37     ldrb    r5, [r0, #1]
  38
  39     mov     r12, #4
  40
  41 copy_mem8x4_1_loop
  42     strb    r4, [r2]
  43     strb    r5, [r2, #1]
  44
  45     ldrb    r4, [r0, #2]
  46     ldrb    r5, [r0, #3]
  47
  48     subs    r12, r12, #1
  49
  50     strb    r4, [r2, #2]
  51     strb    r5, [r2, #3]
  52
  53     ldrb    r4, [r0, #4]
  54     ldrb    r5, [r0, #5]
  55
  56     strb    r4, [r2, #4]
  57     strb    r5, [r2, #5]
  58
  59     ldrb    r4, [r0, #6]
  60     ldrb    r5, [r0, #7]
  61
  62     add     r0, r0, r1
  63
  64     strb    r4, [r2, #6]
  65     strb    r5, [r2, #7]
  66
  67     add     r2, r2, r3
  68
  69     ldrneb  r4, [r0]
  70     ldrneb  r5, [r0, #1]
  71
  72     bne     copy_mem8x4_1_loop
  73
  74     ldmia       sp!, {r4 - r5}
  75     ;pop        {r4-r5}
  76     mov     pc, lr
  77
  78 ;copy 4 bytes each time
  79 copy_mem8x4_4
  80     ldr     r4, [r0]
  81     ldr     r5, [r0, #4]
  82
  83     mov     r12, #4
  84
  85 copy_mem8x4_4_loop
  86     subs    r12, r12, #1
  87     add     r0, r0, r1
  88
  89     str     r4, [r2]
  90     str     r5, [r2, #4]
  91
  92     add     r2, r2, r3
  93
  94     ldrne   r4, [r0]
  95     ldrne   r5, [r0, #4]
  96
  97     bne     copy_mem8x4_4_loop
  98
  99     ldmia  sp!, {r4-r5}
 100     ;pop        {r4-r5}
 101     mov     pc, lr
 102
 103 ;copy 8 bytes each time
 104 copy_mem8x4_fast
 105     ;sub        r1, r1, #8
 106     ;sub        r3, r3, #8
 107
 108     mov     r12, #4
 109
 110 copy_mem8x4_fast_loop
 111     ldmia   r0, {r4-r5}
 112     ;ldm        r0, {r4-r5}
 113     add     r0, r0, r1
 114
 115     subs    r12, r12, #1
 116     stmia   r2, {r4-r5}
 117     ;stm        r2, {r4-r5}
 118     add     r2, r2, r3
 119
 120     bne     copy_mem8x4_fast_loop
 121
 122     ldmia  sp!, {r4-r5}
 123     ;pop        {r4-r5}
 124     mov     pc, lr
 125
 126     ENDP  ; |vp8_copy_mem8x4_v6|
 127
 128     END