From 4626faf1e75ab229552d626db07c18e122971096 Mon Sep 17 00:00:00 2001 From: Yunqing Wang Date: Thu, 1 Nov 2012 09:04:28 -0700 Subject: [PATCH] Convert 16x16 dct/idct to integer forms Converted vp9_short_fdct16x16_c and vp9_short_idct16x16_c to integer versions. Change-Id: Ie3ec985a890ac0f4f4f5818e6f0122e00c8af69f --- vp9/common/idctllm.c | 234 +++++++++++++++++++++++++++++++++++++++++++++++++++ vp9/encoder/dct.c | 224 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 458 insertions(+) diff --git a/vp9/common/idctllm.c b/vp9/common/idctllm.c index becb6ef..4b0ac55 100644 --- a/vp9/common/idctllm.c +++ b/vp9/common/idctllm.c @@ -1013,6 +1013,8 @@ void vp9_short_idct16x16_c(short *input, short *output, int pitch) { } #endif +#define TEST_INT_16x16_IDCT 1 +#if !TEST_INT_16x16_IDCT static const double C1 = 0.995184726672197; static const double C2 = 0.98078528040323; static const double C3 = 0.956940335732209; @@ -1273,3 +1275,235 @@ void vp9_short_idct16x16_c(short *input, short *output, int pitch) { } vp9_clear_system_state(); // Make it simd safe : __asm emms; } + +#else +static const int16_t C1 = 16305; +static const int16_t C2 = 16069; +static const int16_t C3 = 15679; +static const int16_t C4 = 15137; +static const int16_t C5 = 14449; +static const int16_t C6 = 13623; +static const int16_t C7 = 12665; +static const int16_t C8 = 11585; +static const int16_t C9 = 10394; +static const int16_t C10 = 9102; +static const int16_t C11 = 7723; +static const int16_t C12 = 6270; +static const int16_t C13 = 4756; +static const int16_t C14 = 3196; +static const int16_t C15 = 1606; + +#define INITIAL_SHIFT 2 +#define INITIAL_ROUNDING (1 << (INITIAL_SHIFT - 1)) +#define RIGHT_SHIFT 14 +#define RIGHT_ROUNDING (1 << (RIGHT_SHIFT - 1)) + +static void butterfly_16x16_idct_1d(int16_t input[16], int16_t output[16], + int last_shift_bits) { + int16_t step[16]; + int intermediate[16]; + int temp1, temp2; + + int step1_shift = RIGHT_SHIFT + INITIAL_SHIFT; + int step1_rounding = 1 << (step1_shift - 1); + int last_rounding = 0; + + if (last_shift_bits > 0) + last_rounding = 1 << (last_shift_bits - 1); + + // step 1 and 2 + step[ 0] = (input[0] + input[8] + INITIAL_ROUNDING) >> INITIAL_SHIFT; + step[ 1] = (input[0] - input[8] + INITIAL_ROUNDING) >> INITIAL_SHIFT; + + temp1 = input[4] * C12; + temp2 = input[12] * C4; + temp1 = (temp1 - temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + temp1 *= C8; + step[ 2] = (2 * (temp1) + step1_rounding) >> step1_shift; + + temp1 = input[4] * C4; + temp2 = input[12] * C12; + temp1 = (temp1 + temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + temp1 *= C8; + step[ 3] = (2 * (temp1) + step1_rounding) >> step1_shift; + + temp1 = input[2] * C8; + temp1 = (2 * (temp1) + RIGHT_ROUNDING) >> RIGHT_SHIFT; + temp2 = input[6] + input[10]; + step[ 4] = (temp1 + temp2 + INITIAL_ROUNDING) >> INITIAL_SHIFT; + step[ 5] = (temp1 - temp2 + INITIAL_ROUNDING) >> INITIAL_SHIFT; + + temp1 = input[14] * C8; + temp1 = (2 * (temp1) + RIGHT_ROUNDING) >> RIGHT_SHIFT; + temp2 = input[6] - input[10]; + step[ 6] = (temp2 - temp1 + INITIAL_ROUNDING) >> INITIAL_SHIFT; + step[ 7] = (temp2 + temp1 + INITIAL_ROUNDING) >> INITIAL_SHIFT; + + // for odd input + temp1 = input[3] * C12; + temp2 = input[13] * C4; + temp1 = (temp1 + temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + temp1 *= C8; + intermediate[ 8] = (2 * (temp1) + RIGHT_ROUNDING) >> RIGHT_SHIFT; + + temp1 = input[3] * C4; + temp2 = input[13] * C12; + temp2 = (temp2 - temp1 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + temp2 *= C8; + intermediate[ 9] = (2 * (temp2) + RIGHT_ROUNDING) >> RIGHT_SHIFT; + + intermediate[10] = (2 * (input[9] * C8) + RIGHT_ROUNDING) >> RIGHT_SHIFT; + intermediate[11] = input[15] - input[1]; + intermediate[12] = input[15] + input[1]; + intermediate[13] = (2 * (input[7] * C8) + RIGHT_ROUNDING) >> RIGHT_SHIFT; + + temp1 = input[11] * C12; + temp2 = input[5] * C4; + temp2 = (temp2 - temp1 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + temp2 *= C8; + intermediate[14] = (2 * (temp2) + RIGHT_ROUNDING) >> RIGHT_SHIFT; + + temp1 = input[11] * C4; + temp2 = input[5] * C12; + temp1 = (temp1 + temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + temp1 *= C8; + intermediate[15] = (2 * (temp1) + RIGHT_ROUNDING) >> RIGHT_SHIFT; + + step[ 8] = (intermediate[ 8] + intermediate[14] + INITIAL_ROUNDING) + >> INITIAL_SHIFT; + step[ 9] = (intermediate[ 9] + intermediate[15] + INITIAL_ROUNDING) + >> INITIAL_SHIFT; + step[10] = (intermediate[10] + intermediate[11] + INITIAL_ROUNDING) + >> INITIAL_SHIFT; + step[11] = (intermediate[10] - intermediate[11] + INITIAL_ROUNDING) + >> INITIAL_SHIFT; + step[12] = (intermediate[12] + intermediate[13] + INITIAL_ROUNDING) + >> INITIAL_SHIFT; + step[13] = (intermediate[12] - intermediate[13] + INITIAL_ROUNDING) + >> INITIAL_SHIFT; + step[14] = (intermediate[ 8] - intermediate[14] + INITIAL_ROUNDING) + >> INITIAL_SHIFT; + step[15] = (intermediate[ 9] - intermediate[15] + INITIAL_ROUNDING) + >> INITIAL_SHIFT; + + // step 3 + output[0] = step[ 0] + step[ 3]; + output[1] = step[ 1] + step[ 2]; + output[2] = step[ 1] - step[ 2]; + output[3] = step[ 0] - step[ 3]; + + temp1 = step[ 4] * C14; + temp2 = step[ 7] * C2; + output[4] = (temp1 - temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + + temp1 = step[ 4] * C2; + temp2 = step[ 7] * C14; + output[7] = (temp1 + temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + + temp1 = step[ 5] * C10; + temp2 = step[ 6] * C6; + output[5] = (temp1 - temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + + temp1 = step[ 5] * C6; + temp2 = step[ 6] * C10; + output[6] = (temp1 + temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + + output[8] = step[ 8] + step[11]; + output[9] = step[ 9] + step[10]; + output[10] = step[ 9] - step[10]; + output[11] = step[ 8] - step[11]; + output[12] = step[12] + step[15]; + output[13] = step[13] + step[14]; + output[14] = step[13] - step[14]; + output[15] = step[12] - step[15]; + + // output 4 + step[ 0] = output[0] + output[7]; + step[ 1] = output[1] + output[6]; + step[ 2] = output[2] + output[5]; + step[ 3] = output[3] + output[4]; + step[ 4] = output[3] - output[4]; + step[ 5] = output[2] - output[5]; + step[ 6] = output[1] - output[6]; + step[ 7] = output[0] - output[7]; + + temp1 = output[8] * C7; + temp2 = output[15] * C9; + step[ 8] = (temp1 - temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + + temp1 = output[9] * C11; + temp2 = output[14] * C5; + step[ 9] = (temp1 + temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + + temp1 = output[10] * C3; + temp2 = output[13] * C13; + step[10] = (temp1 - temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + + temp1 = output[11] * C15; + temp2 = output[12] * C1; + step[11] = (temp1 + temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + + temp1 = output[11] * C1; + temp2 = output[12] * C15; + step[12] = (temp2 - temp1 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + + temp1 = output[10] * C13; + temp2 = output[13] * C3; + step[13] = (temp1 + temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + + temp1 = output[9] * C5; + temp2 = output[14] * C11; + step[14] = (temp2 - temp1 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + + temp1 = output[8] * C9; + temp2 = output[15] * C7; + step[15] = (temp1 + temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + + // step 5 + output[0] = (step[0] + step[15] + last_rounding) >> last_shift_bits; + output[1] = (step[1] + step[14] + last_rounding) >> last_shift_bits; + output[2] = (step[2] + step[13] + last_rounding) >> last_shift_bits; + output[3] = (step[3] + step[12] + last_rounding) >> last_shift_bits; + output[4] = (step[4] + step[11] + last_rounding) >> last_shift_bits; + output[5] = (step[5] + step[10] + last_rounding) >> last_shift_bits; + output[6] = (step[6] + step[ 9] + last_rounding) >> last_shift_bits; + output[7] = (step[7] + step[ 8] + last_rounding) >> last_shift_bits; + + output[15] = (step[0] - step[15] + last_rounding) >> last_shift_bits; + output[14] = (step[1] - step[14] + last_rounding) >> last_shift_bits; + output[13] = (step[2] - step[13] + last_rounding) >> last_shift_bits; + output[12] = (step[3] - step[12] + last_rounding) >> last_shift_bits; + output[11] = (step[4] - step[11] + last_rounding) >> last_shift_bits; + output[10] = (step[5] - step[10] + last_rounding) >> last_shift_bits; + output[9] = (step[6] - step[ 9] + last_rounding) >> last_shift_bits; + output[8] = (step[7] - step[ 8] + last_rounding) >> last_shift_bits; +} + +void vp9_short_idct16x16_c(int16_t *input, int16_t *output, int pitch) { + int16_t out[16 * 16]; + int16_t *outptr = &out[0]; + const int short_pitch = pitch >> 1; + int i, j; + int16_t temp_in[16], temp_out[16]; + + // First transform rows + for (i = 0; i < 16; ++i) { + butterfly_16x16_idct_1d(input, outptr, 0); + input += short_pitch; + outptr += 16; + } + + // Then transform columns + for (i = 0; i < 16; ++i) { + for (j = 0; j < 16; ++j) + temp_in[j] = out[j * 16 + i]; + butterfly_16x16_idct_1d(temp_in, temp_out, 3); + for (j = 0; j < 16; ++j) + output[j * 16 + i] = temp_out[j]; + } +} +#undef INITIAL_SHIFT +#undef INITIAL_ROUNDING +#undef RIGHT_SHIFT +#undef RIGHT_ROUNDING +#endif diff --git a/vp9/encoder/dct.c b/vp9/encoder/dct.c index 5e56b4e..5be2d76 100644 --- a/vp9/encoder/dct.c +++ b/vp9/encoder/dct.c @@ -901,6 +901,8 @@ void vp9_short_walsh8x4_x8_c(short *input, short *output, int pitch) { } #endif +#define TEST_INT_16x16_DCT 1 +#if !TEST_INT_16x16_DCT static const double C1 = 0.995184726672197; static const double C2 = 0.98078528040323; static const double C3 = 0.956940335732209; @@ -1107,3 +1109,225 @@ void vp9_short_fdct16x16_c(short *input, short *out, int pitch) { } vp9_clear_system_state(); // Make it simd safe : __asm emms; } + +#else +static const int16_t C1 = 16305; +static const int16_t C2 = 16069; +static const int16_t C3 = 15679; +static const int16_t C4 = 15137; +static const int16_t C5 = 14449; +static const int16_t C6 = 13623; +static const int16_t C7 = 12665; +static const int16_t C8 = 11585; +static const int16_t C9 = 10394; +static const int16_t C10 = 9102; +static const int16_t C11 = 7723; +static const int16_t C12 = 6270; +static const int16_t C13 = 4756; +static const int16_t C14 = 3196; +static const int16_t C15 = 1606; + +#define RIGHT_SHIFT 14 +#define ROUNDING (1 << (RIGHT_SHIFT - 1)) + +static void dct16x16_1d(int16_t input[16], int16_t output[16], + int last_shift_bits) { + int16_t step[16]; + int intermediate[16]; + int temp1, temp2; + int final_shift = RIGHT_SHIFT; + int final_rounding = ROUNDING; + int output_shift = 0; + int output_rounding = 0; + + final_shift += last_shift_bits; + if (final_shift > 0) + final_rounding = 1 << (final_shift - 1); + + output_shift += last_shift_bits; + if (output_shift > 0) + output_rounding = 1 << (output_shift - 1); + + // step 1 + step[ 0] = input[0] + input[15]; + step[ 1] = input[1] + input[14]; + step[ 2] = input[2] + input[13]; + step[ 3] = input[3] + input[12]; + step[ 4] = input[4] + input[11]; + step[ 5] = input[5] + input[10]; + step[ 6] = input[6] + input[ 9]; + step[ 7] = input[7] + input[ 8]; + step[ 8] = input[7] - input[ 8]; + step[ 9] = input[6] - input[ 9]; + step[10] = input[5] - input[10]; + step[11] = input[4] - input[11]; + step[12] = input[3] - input[12]; + step[13] = input[2] - input[13]; + step[14] = input[1] - input[14]; + step[15] = input[0] - input[15]; + + // step 2 + output[0] = step[0] + step[7]; + output[1] = step[1] + step[6]; + output[2] = step[2] + step[5]; + output[3] = step[3] + step[4]; + output[4] = step[3] - step[4]; + output[5] = step[2] - step[5]; + output[6] = step[1] - step[6]; + output[7] = step[0] - step[7]; + + temp1 = step[ 8] * C7; + temp2 = step[15] * C9; + output[ 8] = (temp1 + temp2 + ROUNDING) >> RIGHT_SHIFT; + + temp1 = step[ 9] * C11; + temp2 = step[14] * C5; + output[ 9] = (temp1 - temp2 + ROUNDING) >> RIGHT_SHIFT; + + temp1 = step[10] * C3; + temp2 = step[13] * C13; + output[10] = (temp1 + temp2 + ROUNDING) >> RIGHT_SHIFT; + + temp1 = step[11] * C15; + temp2 = step[12] * C1; + output[11] = (temp1 - temp2 + ROUNDING) >> RIGHT_SHIFT; + + temp1 = step[11] * C1; + temp2 = step[12] * C15; + output[12] = (temp2 + temp1 + ROUNDING) >> RIGHT_SHIFT; + + temp1 = step[10] * C13; + temp2 = step[13] * C3; + output[13] = (temp2 - temp1 + ROUNDING) >> RIGHT_SHIFT; + + temp1 = step[ 9] * C5; + temp2 = step[14] * C11; + output[14] = (temp2 + temp1 + ROUNDING) >> RIGHT_SHIFT; + + temp1 = step[ 8] * C9; + temp2 = step[15] * C7; + output[15] = (temp2 - temp1 + ROUNDING) >> RIGHT_SHIFT; + + // step 3 + step[ 0] = output[0] + output[3]; + step[ 1] = output[1] + output[2]; + step[ 2] = output[1] - output[2]; + step[ 3] = output[0] - output[3]; + + temp1 = output[4] * C14; + temp2 = output[7] * C2; + step[ 4] = (temp1 + temp2 + ROUNDING) >> RIGHT_SHIFT; + + temp1 = output[5] * C10; + temp2 = output[6] * C6; + step[ 5] = (temp1 + temp2 + ROUNDING) >> RIGHT_SHIFT; + + temp1 = output[5] * C6; + temp2 = output[6] * C10; + step[ 6] = (temp2 - temp1 + ROUNDING) >> RIGHT_SHIFT; + + temp1 = output[4] * C2; + temp2 = output[7] * C14; + step[ 7] = (temp2 - temp1 + ROUNDING) >> RIGHT_SHIFT; + + step[ 8] = output[ 8] + output[11]; + step[ 9] = output[ 9] + output[10]; + step[10] = output[ 9] - output[10]; + step[11] = output[ 8] - output[11]; + + step[12] = output[12] + output[15]; + step[13] = output[13] + output[14]; + step[14] = output[13] - output[14]; + step[15] = output[12] - output[15]; + + // step 4 + output[ 0] = (step[ 0] + step[ 1] + output_rounding) >> output_shift; + output[ 8] = (step[ 0] - step[ 1] + output_rounding) >> output_shift; + + temp1 = step[2] * C12; + temp2 = step[3] * C4; + temp1 = (temp1 + temp2 + final_rounding) >> final_shift; + output[ 4] = (2 * (temp1 * C8) + ROUNDING) >> RIGHT_SHIFT; + + temp1 = step[2] * C4; + temp2 = step[3] * C12; + temp1 = (temp2 - temp1 + final_rounding) >> final_shift; + output[12] = (2 * (temp1 * C8) + ROUNDING) >> RIGHT_SHIFT; + + output[ 2] = (2 * ((step[4] + step[ 5]) * C8) + final_rounding) + >> final_shift; + output[14] = (2 * ((step[7] - step[ 6]) * C8) + final_rounding) + >> final_shift; + + temp1 = step[4] - step[5]; + temp2 = step[6] + step[7]; + output[ 6] = (temp1 + temp2 + output_rounding) >> output_shift; + output[10] = (temp1 - temp2 + output_rounding) >> output_shift; + + intermediate[8] = step[8] + step[14]; + intermediate[9] = step[9] + step[15]; + + temp1 = intermediate[8] * C12; + temp2 = intermediate[9] * C4; + temp1 = (temp1 - temp2 + final_rounding) >> final_shift; + output[3] = (2 * (temp1 * C8) + ROUNDING) >> RIGHT_SHIFT; + + temp1 = intermediate[8] * C4; + temp2 = intermediate[9] * C12; + temp1 = (temp2 + temp1 + final_rounding) >> final_shift; + output[13] = (2 * (temp1 * C8) + ROUNDING) >> RIGHT_SHIFT; + + output[ 9] = (2 * ((step[10] + step[11]) * C8) + final_rounding) + >> final_shift; + + intermediate[11] = step[10] - step[11]; + intermediate[12] = step[12] + step[13]; + intermediate[13] = step[12] - step[13]; + intermediate[14] = step[ 8] - step[14]; + intermediate[15] = step[ 9] - step[15]; + + output[15] = (intermediate[11] + intermediate[12] + output_rounding) + >> output_shift; + output[ 1] = -(intermediate[11] - intermediate[12] + output_rounding) + >> output_shift; + + output[ 7] = (2 * (intermediate[13] * C8) + final_rounding) >> final_shift; + + temp1 = intermediate[14] * C12; + temp2 = intermediate[15] * C4; + temp1 = (temp1 - temp2 + final_rounding) >> final_shift; + output[11] = (-2 * (temp1 * C8) + ROUNDING) >> RIGHT_SHIFT; + + temp1 = intermediate[14] * C4; + temp2 = intermediate[15] * C12; + temp1 = (temp2 + temp1 + final_rounding) >> final_shift; + output[ 5] = (2 * (temp1 * C8) + ROUNDING) >> RIGHT_SHIFT; +} + +void vp9_short_fdct16x16_c(int16_t *input, int16_t *out, int pitch) { + int shortpitch = pitch >> 1; + int i, j; + int16_t output[256]; + int16_t *outptr = &output[0]; + + // First transform columns + for (i = 0; i < 16; i++) { + int16_t temp_in[16]; + int16_t temp_out[16]; + for (j = 0; j < 16; j++) + temp_in[j] = input[j * shortpitch + i]; + dct16x16_1d(temp_in, temp_out, 0); + for (j = 0; j < 16; j++) + output[j * 16 + i] = temp_out[j]; + } + + // Then transform rows + for (i = 0; i < 16; ++i) { + dct16x16_1d(outptr, out, 1); + outptr += 16; + out += 16; + } +} +#undef RIGHT_SHIFT +#undef ROUNDING +#endif -- 2.7.4