diff options
Diffstat (limited to 'vp8/common/idctllm.c')
-rw-r--r-- | vp8/common/idctllm.c | 189 |
1 files changed, 189 insertions, 0 deletions
diff --git a/vp8/common/idctllm.c b/vp8/common/idctllm.c new file mode 100644 index 000000000..57cf8584e --- /dev/null +++ b/vp8/common/idctllm.c @@ -0,0 +1,189 @@ +/* + * Copyright (c) 2010 The VP8 project authors. All Rights Reserved. + * + * Use of this source code is governed by a BSD-style license and patent + * grant that can be found in the LICENSE file in the root of the source + * tree. All contributing project authors may be found in the AUTHORS + * file in the root of the source tree. + */ + + +/**************************************************************************** + * Notes: + * + * This implementation makes use of 16 bit fixed point verio of two multiply + * constants: + * 1. sqrt(2) * cos (pi/8) + * 2. sqrt(2) * sin (pi/8) + * Becuase the first constant is bigger than 1, to maintain the same 16 bit + * fixed point precision as the second one, we use a trick of + * x * a = x + x*(a-1) + * so + * x * sqrt(2) * cos (pi/8) = x + x * (sqrt(2) *cos(pi/8)-1). + **************************************************************************/ +static const int cospi8sqrt2minus1 = 20091; +static const int sinpi8sqrt2 = 35468; +static const int rounding = 0; +void vp8_short_idct4x4llm_c(short *input, short *output, int pitch) +{ + int i; + int a1, b1, c1, d1; + + short *ip = input; + short *op = output; + int temp1, temp2; + int shortpitch = pitch >> 1; + + for (i = 0; i < 4; i++) + { + a1 = ip[0] + ip[8]; + b1 = ip[0] - ip[8]; + + temp1 = (ip[4] * sinpi8sqrt2 + rounding) >> 16; + temp2 = ip[12] + ((ip[12] * cospi8sqrt2minus1 + rounding) >> 16); + c1 = temp1 - temp2; + + temp1 = ip[4] + ((ip[4] * cospi8sqrt2minus1 + rounding) >> 16); + temp2 = (ip[12] * sinpi8sqrt2 + rounding) >> 16; + d1 = temp1 + temp2; + + op[shortpitch*0] = a1 + d1; + op[shortpitch*3] = a1 - d1; + + op[shortpitch*1] = b1 + c1; + op[shortpitch*2] = b1 - c1; + + ip++; + op++; + } + + ip = output; + op = output; + + for (i = 0; i < 4; i++) + { + a1 = ip[0] + ip[2]; + b1 = ip[0] - ip[2]; + + temp1 = (ip[1] * sinpi8sqrt2 + rounding) >> 16; + temp2 = ip[3] + ((ip[3] * cospi8sqrt2minus1 + rounding) >> 16); + c1 = temp1 - temp2; + + temp1 = ip[1] + ((ip[1] * cospi8sqrt2minus1 + rounding) >> 16); + temp2 = (ip[3] * sinpi8sqrt2 + rounding) >> 16; + d1 = temp1 + temp2; + + + op[0] = (a1 + d1 + 4) >> 3; + op[3] = (a1 - d1 + 4) >> 3; + + op[1] = (b1 + c1 + 4) >> 3; + op[2] = (b1 - c1 + 4) >> 3; + + ip += shortpitch; + op += shortpitch; + } +} + +void vp8_short_idct4x4llm_1_c(short *input, short *output, int pitch) +{ + int i; + int a1; + short *op = output; + int shortpitch = pitch >> 1; + a1 = ((input[0] + 4) >> 3); + + for (i = 0; i < 4; i++) + { + op[0] = a1; + op[1] = a1; + op[2] = a1; + op[3] = a1; + op += shortpitch; + } +} + + +void vp8_dc_only_idct_c(short input_dc, short *output, int pitch) +{ + int i; + int a1; + short *op = output; + int shortpitch = pitch >> 1; + a1 = ((input_dc + 4) >> 3); + + for (i = 0; i < 4; i++) + { + op[0] = a1; + op[1] = a1; + op[2] = a1; + op[3] = a1; + op += shortpitch; + } +} + +void vp8_short_inv_walsh4x4_c(short *input, short *output) +{ + int i; + int a1, b1, c1, d1; + int a2, b2, c2, d2; + short *ip = input; + short *op = output; + + for (i = 0; i < 4; i++) + { + a1 = ip[0] + ip[12]; + b1 = ip[4] + ip[8]; + c1 = ip[4] - ip[8]; + d1 = ip[0] - ip[12]; + + op[0] = a1 + b1; + op[4] = c1 + d1; + op[8] = a1 - b1; + op[12] = d1 - c1; + ip++; + op++; + } + + ip = output; + op = output; + + for (i = 0; i < 4; i++) + { + a1 = ip[0] + ip[3]; + b1 = ip[1] + ip[2]; + c1 = ip[1] - ip[2]; + d1 = ip[0] - ip[3]; + + a2 = a1 + b1; + b2 = c1 + d1; + c2 = a1 - b1; + d2 = d1 - c1; + + op[0] = (a2 + 3) >> 3; + op[1] = (b2 + 3) >> 3; + op[2] = (c2 + 3) >> 3; + op[3] = (d2 + 3) >> 3; + + ip += 4; + op += 4; + } +} + +void vp8_short_inv_walsh4x4_1_c(short *input, short *output) +{ + int i; + int a1; + short *op = output; + + a1 = ((input[0] + 3) >> 3); + + for (i = 0; i < 4; i++) + { + op[0] = a1; + op[1] = a1; + op[2] = a1; + op[3] = a1; + op += 4; + } +} |