diff options
Diffstat (limited to 'vp9/common/vp9_idctllm.c')
-rw-r--r-- | vp9/common/vp9_idctllm.c | 1153 |
1 files changed, 229 insertions, 924 deletions
diff --git a/vp9/common/vp9_idctllm.c b/vp9/common/vp9_idctllm.c index 2f847dc78..4ac18ae4a 100644 --- a/vp9/common/vp9_idctllm.c +++ b/vp9/common/vp9_idctllm.c @@ -298,122 +298,7 @@ void vp9_ihtllm_c(const int16_t *input, int16_t *output, int pitch, } } -void vp9_short_inv_walsh4x4_c(int16_t *input, int16_t *output) { - int i; - int a1, b1, c1, d1; - int16_t *ip = input; - int16_t *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])); - - op[0] = (a1 + b1 + 1) >> 1; - op[1] = (c1 + d1) >> 1; - op[2] = (a1 - b1) >> 1; - op[3] = (d1 - c1) >> 1; - - ip += 4; - op += 4; - } - - ip = output; - 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 + 1) >> 1; - op[4] = (c1 + d1) >> 1; - op[8] = (a1 - b1) >> 1; - op[12] = (d1 - c1) >> 1; - ip++; - op++; - } -} - -void vp9_short_inv_walsh4x4_1_c(int16_t *in, int16_t *out) { - int i; - int16_t tmp[4]; - int16_t *ip = in; - int16_t *op = tmp; - - op[0] = (ip[0] + 1) >> 1; - op[1] = op[2] = op[3] = (ip[0] >> 1); - - ip = tmp; - op = out; - for (i = 0; i < 4; i++) { - op[0] = (ip[0] + 1) >> 1; - op[4] = op[8] = op[12] = (ip[0] >> 1); - ip++; - op++; - } -} - #if CONFIG_LOSSLESS -void vp9_short_inv_walsh4x4_lossless_c(int16_t *input, int16_t *output) { - int i; - int a1, b1, c1, d1; - int16_t *ip = input; - int16_t *op = output; - - for (i = 0; i < 4; i++) { - a1 = ((ip[0] + ip[3])) >> Y2_WHT_UPSCALE_FACTOR; - b1 = ((ip[1] + ip[2])) >> Y2_WHT_UPSCALE_FACTOR; - c1 = ((ip[1] - ip[2])) >> Y2_WHT_UPSCALE_FACTOR; - d1 = ((ip[0] - ip[3])) >> Y2_WHT_UPSCALE_FACTOR; - - op[0] = (a1 + b1 + 1) >> 1; - op[1] = (c1 + d1) >> 1; - op[2] = (a1 - b1) >> 1; - op[3] = (d1 - c1) >> 1; - - ip += 4; - op += 4; - } - - ip = output; - 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 + 1) >> 1) << Y2_WHT_UPSCALE_FACTOR; - op[4] = ((c1 + d1) >> 1) << Y2_WHT_UPSCALE_FACTOR; - op[8] = ((a1 - b1) >> 1) << Y2_WHT_UPSCALE_FACTOR; - op[12] = ((d1 - c1) >> 1) << Y2_WHT_UPSCALE_FACTOR; - - ip++; - op++; - } -} - -void vp9_short_inv_walsh4x4_1_lossless_c(int16_t *in, int16_t *out) { - int i; - int16_t tmp[4]; - int16_t *ip = in; - int16_t *op = tmp; - - op[0] = ((ip[0] >> Y2_WHT_UPSCALE_FACTOR) + 1) >> 1; - op[1] = op[2] = op[3] = ((ip[0] >> Y2_WHT_UPSCALE_FACTOR) >> 1); - - ip = tmp; - op = out; - for (i = 0; i < 4; i++) { - op[0] = ((ip[0] + 1) >> 1) << Y2_WHT_UPSCALE_FACTOR; - op[4] = op[8] = op[12] = ((ip[0] >> 1)) << Y2_WHT_UPSCALE_FACTOR; - ip++; - op++; - } -} - void vp9_short_inv_walsh4x4_x8_c(int16_t *input, int16_t *output, int pitch) { int i; int a1, b1, c1, d1; @@ -476,12 +361,13 @@ void vp9_short_inv_walsh4x4_1_x8_c(int16_t *in, int16_t *out, int pitch) { } } -void vp9_dc_only_inv_walsh_add_c(short input_dc, uint8_t *pred_ptr, +void vp9_dc_only_inv_walsh_add_c(int input_dc, uint8_t *pred_ptr, uint8_t *dst_ptr, int pitch, int stride) { int r, c; - short tmp[16]; - vp9_short_inv_walsh4x4_1_x8_c(&input_dc, tmp, 4 << 1); + int16_t dc = input_dc; + int16_t tmp[16]; + vp9_short_inv_walsh4x4_1_x8_c(&dc, tmp, 4 << 1); for (r = 0; r < 4; r++) { for (c = 0; c < 4; c++) { @@ -912,20 +798,6 @@ void vp9_short_idct1_8x8_c(int16_t *input, int16_t *output) { *output = (out + 16) >> 5; } -void vp9_short_ihaar2x2_c(int16_t *input, int16_t *output, int pitch) { - int i; - int16_t *ip = input; // 0, 1, 4, 8 - int16_t *op = output; - for (i = 0; i < 16; i++) { - op[i] = 0; - } - - op[0] = (ip[0] + ip[1] + ip[4] + ip[8] + 1) >> 1; - op[1] = (ip[0] - ip[1] + ip[4] - ip[8]) >> 1; - op[4] = (ip[0] + ip[1] - ip[4] - ip[8]) >> 1; - op[8] = (ip[0] - ip[1] - ip[4] + ip[8]) >> 1; -} - void idct16_1d(int16_t *input, int16_t *output) { int16_t step1[16], step2[16]; int temp1, temp2; @@ -1114,6 +986,231 @@ void vp9_short_idct16x16_c(int16_t *input, int16_t *output, int pitch) { } } +#if CONFIG_INTHT16X16 +void iadst16_1d(int16_t *input, int16_t *output) { + int x0, x1, x2, x3, x4, x5, x6, x7, x8, x9, x10, x11, x12, x13, x14, x15; + int s0, s1, s2, s3, s4, s5, s6, s7, s8, s9, s10, s11, s12, s13, s14, s15; + + x0 = input[15]; + x1 = input[0]; + x2 = input[13]; + x3 = input[2]; + x4 = input[11]; + x5 = input[4]; + x6 = input[9]; + x7 = input[6]; + x8 = input[7]; + x9 = input[8]; + x10 = input[5]; + x11 = input[10]; + x12 = input[3]; + x13 = input[12]; + x14 = input[1]; + x15 = input[14]; + + if (!(x0 | x1 | x2 | x3 | x4 | x5 | x6 | x7 | x8 + | x9 | x10 | x11 | x12 | x13 | x14 | x15)) { + output[0] = output[1] = output[2] = output[3] = output[4] + = output[5] = output[6] = output[7] = output[8] + = output[9] = output[10] = output[11] = output[12] + = output[13] = output[14] = output[15] = 0; + return; + } + + // stage 1 + s0 = x0 * cospi_1_64 + x1 * cospi_31_64; + s1 = x0 * cospi_31_64 - x1 * cospi_1_64; + s2 = x2 * cospi_5_64 + x3 * cospi_27_64; + s3 = x2 * cospi_27_64 - x3 * cospi_5_64; + s4 = x4 * cospi_9_64 + x5 * cospi_23_64; + s5 = x4 * cospi_23_64 - x5 * cospi_9_64; + s6 = x6 * cospi_13_64 + x7 * cospi_19_64; + s7 = x6 * cospi_19_64 - x7 * cospi_13_64; + s8 = x8 * cospi_17_64 + x9 * cospi_15_64; + s9 = x8 * cospi_15_64 - x9 * cospi_17_64; + s10 = x10 * cospi_21_64 + x11 * cospi_11_64; + s11 = x10 * cospi_11_64 - x11 * cospi_21_64; + s12 = x12 * cospi_25_64 + x13 * cospi_7_64; + s13 = x12 * cospi_7_64 - x13 * cospi_25_64; + s14 = x14 * cospi_29_64 + x15 * cospi_3_64; + s15 = x14 * cospi_3_64 - x15 * cospi_29_64; + + x0 = dct_const_round_shift(s0 + s8); + x1 = dct_const_round_shift(s1 + s9); + x2 = dct_const_round_shift(s2 + s10); + x3 = dct_const_round_shift(s3 + s11); + x4 = dct_const_round_shift(s4 + s12); + x5 = dct_const_round_shift(s5 + s13); + x6 = dct_const_round_shift(s6 + s14); + x7 = dct_const_round_shift(s7 + s15); + x8 = dct_const_round_shift(s0 - s8); + x9 = dct_const_round_shift(s1 - s9); + x10 = dct_const_round_shift(s2 - s10); + x11 = dct_const_round_shift(s3 - s11); + x12 = dct_const_round_shift(s4 - s12); + x13 = dct_const_round_shift(s5 - s13); + x14 = dct_const_round_shift(s6 - s14); + x15 = dct_const_round_shift(s7 - s15); + + // stage 2 + s0 = x0; + s1 = x1; + s2 = x2; + s3 = x3; + s4 = x4; + s5 = x5; + s6 = x6; + s7 = x7; + s8 = x8 * cospi_4_64 + x9 * cospi_28_64; + s9 = x8 * cospi_28_64 - x9 * cospi_4_64; + s10 = x10 * cospi_20_64 + x11 * cospi_12_64; + s11 = x10 * cospi_12_64 - x11 * cospi_20_64; + s12 = - x12 * cospi_28_64 + x13 * cospi_4_64; + s13 = x12 * cospi_4_64 + x13 * cospi_28_64; + s14 = - x14 * cospi_12_64 + x15 * cospi_20_64; + s15 = x14 * cospi_20_64 + x15 * cospi_12_64; + + x0 = s0 + s4; + x1 = s1 + s5; + x2 = s2 + s6; + x3 = s3 + s7; + x4 = s0 - s4; + x5 = s1 - s5; + x6 = s2 - s6; + x7 = s3 - s7; + x8 = dct_const_round_shift(s8 + s12); + x9 = dct_const_round_shift(s9 + s13); + x10 = dct_const_round_shift(s10 + s14); + x11 = dct_const_round_shift(s11 + s15); + x12 = dct_const_round_shift(s8 - s12); + x13 = dct_const_round_shift(s9 - s13); + x14 = dct_const_round_shift(s10 - s14); + x15 = dct_const_round_shift(s11 - s15); + + // stage 3 + s0 = x0; + s1 = x1; + s2 = x2; + s3 = x3; + s4 = x4 * cospi_8_64 + x5 * cospi_24_64; + s5 = x4 * cospi_24_64 - x5 * cospi_8_64; + s6 = - x6 * cospi_24_64 + x7 * cospi_8_64; + s7 = x6 * cospi_8_64 + x7 * cospi_24_64; + s8 = x8; + s9 = x9; + s10 = x10; + s11 = x11; + s12 = x12 * cospi_8_64 + x13 * cospi_24_64; + s13 = x12 * cospi_24_64 - x13 * cospi_8_64; + s14 = - x14 * cospi_24_64 + x15 * cospi_8_64; + s15 = x14 * cospi_8_64 + x15 * cospi_24_64; + + x0 = s0 + s2; + x1 = s1 + s3; + x2 = s0 - s2; + x3 = s1 - s3; + x4 = dct_const_round_shift(s4 + s6); + x5 = dct_const_round_shift(s5 + s7); + x6 = dct_const_round_shift(s4 - s6); + x7 = dct_const_round_shift(s5 - s7); + x8 = s8 + s10; + x9 = s9 + s11; + x10 = s8 - s10; + x11 = s9 - s11; + x12 = dct_const_round_shift(s12 + s14); + x13 = dct_const_round_shift(s13 + s15); + x14 = dct_const_round_shift(s12 - s14); + x15 = dct_const_round_shift(s13 - s15); + + // stage 4 + s2 = (- cospi_16_64) * (x2 + x3); + s3 = cospi_16_64 * (x2 - x3); + s6 = cospi_16_64 * (x6 + x7); + s7 = cospi_16_64 * (- x6 + x7); + s10 = cospi_16_64 * (x10 + x11); + s11 = cospi_16_64 * (- x10 + x11); + s14 = (- cospi_16_64) * (x14 + x15); + s15 = cospi_16_64 * (x14 - x15); + + x2 = dct_const_round_shift(s2); + x3 = dct_const_round_shift(s3); + x6 = dct_const_round_shift(s6); + x7 = dct_const_round_shift(s7); + x10 = dct_const_round_shift(s10); + x11 = dct_const_round_shift(s11); + x14 = dct_const_round_shift(s14); + x15 = dct_const_round_shift(s15); + + output[0] = x0; + output[1] = - x8; + output[2] = x12; + output[3] = - x4; + output[4] = x6; + output[5] = x14; + output[6] = x10; + output[7] = x2; + output[8] = x3; + output[9] = x11; + output[10] = x15; + output[11] = x7; + output[12] = x5; + output[13] = - x13; + output[14] = x9; + output[15] = - x1; +} + +void vp9_short_iht16x16_c(int16_t *input, int16_t *output, + int pitch, TX_TYPE tx_type) { + 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]; + + void (*invr)(int16_t*, int16_t*); + void (*invc)(int16_t*, int16_t*); + + switch (tx_type) { + case ADST_ADST: + invc = &iadst16_1d; + invr = &iadst16_1d; + break; + case ADST_DCT: + invc = &iadst16_1d; + invr = &idct16_1d; + break; + case DCT_ADST: + invc = &idct16_1d; + invr = &iadst16_1d; + break; + case DCT_DCT: + invc = &idct16_1d; + invr = &idct16_1d; + break; + default: + assert(0); + } + + // inverse transform row vectors + for (i = 0; i < 16; ++i) { + invr(input, outptr); + input += short_pitch; + outptr += 16; + } + + // inverse transform column vectors + for (i = 0; i < 16; ++i) { + for (j = 0; j < 16; ++j) + temp_in[j] = out[j * 16 + i]; + invc(temp_in, temp_out); + for (j = 0; j < 16; ++j) + output[j * 16 + i] = (temp_out[j] + 32) >> 6; + } +} +#endif + + + void vp9_short_idct10_16x16_c(int16_t *input, int16_t *output, int pitch) { int16_t out[16 * 16]; int16_t *outptr = &out[0]; @@ -1152,8 +1249,6 @@ void vp9_short_idct1_16x16_c(int16_t *input, int16_t *output) { *output = (out + 32) >> 6; } - -#if !CONFIG_DWTDCTHYBRID void idct32_1d(int16_t *input, int16_t *output) { int16_t step1[32], step2[32]; int temp1, temp2; @@ -1521,7 +1616,6 @@ void idct32_1d(int16_t *input, int16_t *output) { output[31] = step1[0] - step1[31]; } - void vp9_short_idct32x32_c(int16_t *input, int16_t *output, int pitch) { int16_t out[32 * 32]; int16_t *outptr = &out[0]; @@ -1554,792 +1648,3 @@ void vp9_short_idct1_32x32_c(int16_t *input, int16_t *output) { out = dct_const_round_shift(tmp); *output = (out + 32) >> 6; } - -#else // !CONFIG_DWTDCTHYBRID - -#if DWT_TYPE == 53 - -// Note: block length must be even for this implementation -static void synthesis_53_row(int length, int16_t *lowpass, int16_t *highpass, - int16_t *x) { - int16_t r, *a, *b; - int n; - - n = length >> 1; - b = highpass; - a = lowpass; - r = *highpass; - while (n--) { - *a++ -= (r + (*b) + 1) >> 1; - r = *b++; - } - - n = length >> 1; - b = highpass; - a = lowpass; - while (--n) { - *x++ = ((r = *a++) + 1) >> 1; - *x++ = *b++ + ((r + (*a) + 2) >> 2); - } - *x++ = ((r = *a) + 1) >> 1; - *x++ = *b + ((r + 1) >> 1); -} - -static void synthesis_53_col(int length, int16_t *lowpass, int16_t *highpass, - int16_t *x) { - int16_t r, *a, *b; - int n; - - n = length >> 1; - b = highpass; - a = lowpass; - r = *highpass; - while (n--) { - *a++ -= (r + (*b) + 1) >> 1; - r = *b++; - } - - n = length >> 1; - b = highpass; - a = lowpass; - while (--n) { - r = *a++; - *x++ = r; - *x++ = ((*b++) << 1) + ((r + (*a) + 1) >> 1); - } - *x++ = *a; - *x++ = ((*b) << 1) + *a; -} - -static void dyadic_synthesize_53(int levels, int width, int height, int16_t *c, - int pitch_c, int16_t *x, int pitch_x) { - int th[16], tw[16], lv, i, j, nh, nw, hh = height, hw = width; - short buffer[2 * DWT_MAX_LENGTH]; - - th[0] = hh; - tw[0] = hw; - for (i = 1; i <= levels; i++) { - th[i] = (th[i - 1] + 1) >> 1; - tw[i] = (tw[i - 1] + 1) >> 1; - } - for (lv = levels - 1; lv >= 0; lv--) { - nh = th[lv]; - nw = tw[lv]; - hh = th[lv + 1]; - hw = tw[lv + 1]; - if ((nh < 2) || (nw < 2)) continue; - for (j = 0; j < nw; j++) { - for (i = 0; i < nh; i++) - buffer[i] = c[i * pitch_c + j]; - synthesis_53_col(nh, buffer, buffer + hh, buffer + nh); - for (i = 0; i < nh; i++) - c[i * pitch_c + j] = buffer[i + nh]; - } - for (i = 0; i < nh; i++) { - memcpy(buffer, &c[i * pitch_c], nw * sizeof(*buffer)); - synthesis_53_row(nw, buffer, buffer + hw, &c[i * pitch_c]); - } - } - for (i = 0; i < height; i++) { - for (j = 0; j < width; j++) { - x[i * pitch_x + j] = c[i * pitch_c + j] >= 0 ? - ((c[i * pitch_c + j] + DWT_PRECISION_RND) >> DWT_PRECISION_BITS) : - -((-c[i * pitch_c + j] + DWT_PRECISION_RND) >> DWT_PRECISION_BITS); - } - } -} - -#elif DWT_TYPE == 26 - -// Note: block length must be even for this implementation -static void synthesis_26_row(int length, int16_t *lowpass, int16_t *highpass, - int16_t *x) { - int16_t r, s, *a, *b; - int i, n = length >> 1; - - if (n >= 4) { - a = lowpass; - b = highpass; - r = *lowpass; - while (--n) { - *b++ += (r - a[1] + 4) >> 3; - r = *a++; - } - *b += (r - *a + 4) >> 3; - } - a = lowpass; - b = highpass; - for (i = length >> 1; i; i--) { - s = *b++; - r = *a++; - *x++ = (r + s + 1) >> 1; - *x++ = (r - s + 1) >> 1; - } -} - -static void synthesis_26_col(int length, int16_t *lowpass, int16_t *highpass, - int16_t *x) { - int16_t r, s, *a, *b; - int i, n = length >> 1; - - if (n >= 4) { - a = lowpass; - b = highpass; - r = *lowpass; - while (--n) { - *b++ += (r - a[1] + 4) >> 3; - r = *a++; - } - *b += (r - *a + 4) >> 3; - } - a = lowpass; - b = highpass; - for (i = length >> 1; i; i--) { - s = *b++; - r = *a++; - *x++ = r + s; - *x++ = r - s; - } -} - -static void dyadic_synthesize_26(int levels, int width, int height, int16_t *c, - int pitch_c, int16_t *x, int pitch_x) { - int th[16], tw[16], lv, i, j, nh, nw, hh = height, hw = width; - int16_t buffer[2 * DWT_MAX_LENGTH]; - - th[0] = hh; - tw[0] = hw; - for (i = 1; i <= levels; i++) { - th[i] = (th[i - 1] + 1) >> 1; - tw[i] = (tw[i - 1] + 1) >> 1; - } - for (lv = levels - 1; lv >= 0; lv--) { - nh = th[lv]; - nw = tw[lv]; - hh = th[lv + 1]; - hw = tw[lv + 1]; - if ((nh < 2) || (nw < 2)) continue; - for (j = 0; j < nw; j++) { - for (i = 0; i < nh; i++) - buffer[i] = c[i * pitch_c + j]; - synthesis_26_col(nh, buffer, buffer + hh, buffer + nh); - for (i = 0; i < nh; i++) - c[i * pitch_c + j] = buffer[i + nh]; - } - for (i = 0; i < nh; i++) { - memcpy(buffer, &c[i * pitch_c], nw * sizeof(*buffer)); - synthesis_26_row(nw, buffer, buffer + hw, &c[i * pitch_c]); - } - } - for (i = 0; i < height; i++) { - for (j = 0; j < width; j++) { - x[i * pitch_x + j] = c[i * pitch_c + j] >= 0 ? - ((c[i * pitch_c + j] + DWT_PRECISION_RND) >> DWT_PRECISION_BITS) : - -((-c[i * pitch_c + j] + DWT_PRECISION_RND) >> DWT_PRECISION_BITS); - } - } -} - -#elif DWT_TYPE == 97 - -static void synthesis_97(int length, double *lowpass, double *highpass, - double *x) { - static const double a_predict1 = -1.586134342; - static const double a_update1 = -0.05298011854; - static const double a_predict2 = 0.8829110762; - static const double a_update2 = 0.4435068522; - static const double s_low = 1.149604398; - static const double s_high = 1/1.149604398; - static const double inv_s_low = 1 / s_low; - static const double inv_s_high = 1 / s_high; - int i; - double y[DWT_MAX_LENGTH]; - // Undo pack and scale - for (i = 0; i < length / 2; i++) { - y[i * 2] = lowpass[i] * inv_s_low; - y[i * 2 + 1] = highpass[i] * inv_s_high; - } - memcpy(x, y, sizeof(*y) * length); - // Undo update 2 - for (i = 2; i < length; i += 2) { - x[i] -= a_update2 * (x[i-1] + x[i+1]); - } - x[0] -= 2 * a_update2 * x[1]; - // Undo predict 2 - for (i = 1; i < length - 2; i += 2) { - x[i] -= a_predict2 * (x[i - 1] + x[i + 1]); - } - x[length - 1] -= 2 * a_predict2 * x[length - 2]; - // Undo update 1 - for (i = 2; i < length; i += 2) { - x[i] -= a_update1 * (x[i - 1] + x[i + 1]); - } - x[0] -= 2 * a_update1 * x[1]; - // Undo predict 1 - for (i = 1; i < length - 2; i += 2) { - x[i] -= a_predict1 * (x[i - 1] + x[i + 1]); - } - x[length - 1] -= 2 * a_predict1 * x[length - 2]; -} - -static void dyadic_synthesize_97(int levels, int width, int height, int16_t *c, - int pitch_c, int16_t *x, int pitch_x) { - int th[16], tw[16], lv, i, j, nh, nw, hh = height, hw = width; - double buffer[2 * DWT_MAX_LENGTH]; - double y[DWT_MAX_LENGTH * DWT_MAX_LENGTH]; - - th[0] = hh; - tw[0] = hw; - for (i = 1; i <= levels; i++) { - th[i] = (th[i - 1] + 1) >> 1; - tw[i] = (tw[i - 1] + 1) >> 1; - } - for (lv = levels - 1; lv >= 0; lv--) { - nh = th[lv]; - nw = tw[lv]; - hh = th[lv + 1]; - hw = tw[lv + 1]; - if ((nh < 2) || (nw < 2)) continue; - for (j = 0; j < nw; j++) { - for (i = 0; i < nh; i++) - buffer[i] = c[i * pitch_c + j]; - synthesis_97(nh, buffer, buffer + hh, buffer + nh); - for (i = 0; i < nh; i++) - y[i * DWT_MAX_LENGTH + j] = buffer[i + nh]; - } - for (i = 0; i < nh; i++) { - memcpy(buffer, &y[i * DWT_MAX_LENGTH], nw * sizeof(*buffer)); - synthesis_97(nw, buffer, buffer + hw, &y[i * DWT_MAX_LENGTH]); - } - } - for (i = 0; i < height; i++) - for (j = 0; j < width; j++) - x[i * pitch_x + j] = round(y[i * DWT_MAX_LENGTH + j] / - (1 << DWT_PRECISION_BITS)); -} - -#endif // DWT_TYPE - -// TODO(debargha): Implement scaling differently so as not to have to use the -// floating point 16x16 dct -static void butterfly_16x16_idct_1d_f(double input[16], double output[16]) { - static const double C1 = 0.995184726672197; - static const double C2 = 0.98078528040323; - static const double C3 = 0.956940335732209; - static const double C4 = 0.923879532511287; - static const double C5 = 0.881921264348355; - static const double C6 = 0.831469612302545; - static const double C7 = 0.773010453362737; - static const double C8 = 0.707106781186548; - static const double C9 = 0.634393284163646; - static const double C10 = 0.555570233019602; - static const double C11 = 0.471396736825998; - static const double C12 = 0.38268343236509; - static const double C13 = 0.290284677254462; - static const double C14 = 0.195090322016128; - static const double C15 = 0.098017140329561; - - vp9_clear_system_state(); // Make it simd safe : __asm emms; - { - double step[16]; - double intermediate[16]; - double temp1, temp2; - - - // step 1 and 2 - step[ 0] = input[0] + input[8]; - step[ 1] = input[0] - input[8]; - - temp1 = input[4]*C12; - temp2 = input[12]*C4; - - temp1 -= temp2; - temp1 *= C8; - - step[ 2] = 2*(temp1); - - temp1 = input[4]*C4; - temp2 = input[12]*C12; - temp1 += temp2; - temp1 = (temp1); - temp1 *= C8; - step[ 3] = 2*(temp1); - - temp1 = input[2]*C8; - temp1 = 2*(temp1); - temp2 = input[6] + input[10]; - - step[ 4] = temp1 + temp2; - step[ 5] = temp1 - temp2; - - temp1 = input[14]*C8; - temp1 = 2*(temp1); - temp2 = input[6] - input[10]; - - step[ 6] = temp2 - temp1; - step[ 7] = temp2 + temp1; - - // for odd input - temp1 = input[3]*C12; - temp2 = input[13]*C4; - temp1 += temp2; - temp1 = (temp1); - temp1 *= C8; - intermediate[ 8] = 2*(temp1); - - temp1 = input[3]*C4; - temp2 = input[13]*C12; - temp2 -= temp1; - temp2 = (temp2); - temp2 *= C8; - intermediate[ 9] = 2*(temp2); - - intermediate[10] = 2*(input[9]*C8); - intermediate[11] = input[15] - input[1]; - intermediate[12] = input[15] + input[1]; - intermediate[13] = 2*((input[7]*C8)); - - temp1 = input[11]*C12; - temp2 = input[5]*C4; - temp2 -= temp1; - temp2 = (temp2); - temp2 *= C8; - intermediate[14] = 2*(temp2); - - temp1 = input[11]*C4; - temp2 = input[5]*C12; - temp1 += temp2; - temp1 = (temp1); - temp1 *= C8; - intermediate[15] = 2*(temp1); - - step[ 8] = intermediate[ 8] + intermediate[14]; - step[ 9] = intermediate[ 9] + intermediate[15]; - step[10] = intermediate[10] + intermediate[11]; - step[11] = intermediate[10] - intermediate[11]; - step[12] = intermediate[12] + intermediate[13]; - step[13] = intermediate[12] - intermediate[13]; - step[14] = intermediate[ 8] - intermediate[14]; - step[15] = intermediate[ 9] - intermediate[15]; - - // 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; - temp1 -= temp2; - output[4] = (temp1); - - temp1 = step[ 4]*C2; - temp2 = step[ 7]*C14; - temp1 += temp2; - output[7] = (temp1); - - temp1 = step[ 5]*C10; - temp2 = step[ 6]*C6; - temp1 -= temp2; - output[5] = (temp1); - - temp1 = step[ 5]*C6; - temp2 = step[ 6]*C10; - temp1 += temp2; - output[6] = (temp1); - - 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; - temp1 -= temp2; - step[ 8] = (temp1); - - temp1 = output[9]*C11; - temp2 = output[14]*C5; - temp1 += temp2; - step[ 9] = (temp1); - - temp1 = output[10]*C3; - temp2 = output[13]*C13; - temp1 -= temp2; - step[10] = (temp1); - - temp1 = output[11]*C15; - temp2 = output[12]*C1; - temp1 += temp2; - step[11] = (temp1); - - temp1 = output[11]*C1; - temp2 = output[12]*C15; - temp2 -= temp1; - step[12] = (temp2); - - temp1 = output[10]*C13; - temp2 = output[13]*C3; - temp1 += temp2; - step[13] = (temp1); - - temp1 = output[9]*C5; - temp2 = output[14]*C11; - temp2 -= temp1; - step[14] = (temp2); - - temp1 = output[8]*C9; - temp2 = output[15]*C7; - temp1 += temp2; - step[15] = (temp1); - - // step 5 - output[0] = (step[0] + step[15]); - output[1] = (step[1] + step[14]); - output[2] = (step[2] + step[13]); - output[3] = (step[3] + step[12]); - output[4] = (step[4] + step[11]); - output[5] = (step[5] + step[10]); - output[6] = (step[6] + step[ 9]); - output[7] = (step[7] + step[ 8]); - - output[15] = (step[0] - step[15]); - output[14] = (step[1] - step[14]); - output[13] = (step[2] - step[13]); - output[12] = (step[3] - step[12]); - output[11] = (step[4] - step[11]); - output[10] = (step[5] - step[10]); - output[9] = (step[6] - step[ 9]); - output[8] = (step[7] - step[ 8]); - } - vp9_clear_system_state(); // Make it simd safe : __asm emms; -} - -static void vp9_short_idct16x16_c_f(int16_t *input, int16_t *output, int pitch, - int scale) { - vp9_clear_system_state(); // Make it simd safe : __asm emms; - { - double out[16*16], out2[16*16]; - const int short_pitch = pitch >> 1; - int i, j; - // First transform rows - for (i = 0; i < 16; ++i) { - double temp_in[16], temp_out[16]; - for (j = 0; j < 16; ++j) - temp_in[j] = input[j + i*short_pitch]; - butterfly_16x16_idct_1d_f(temp_in, temp_out); - for (j = 0; j < 16; ++j) - out[j + i*16] = temp_out[j]; - } - // Then transform columns - for (i = 0; i < 16; ++i) { - double temp_in[16], temp_out[16]; - for (j = 0; j < 16; ++j) - temp_in[j] = out[j*16 + i]; - butterfly_16x16_idct_1d_f(temp_in, temp_out); - for (j = 0; j < 16; ++j) - out2[j*16 + i] = temp_out[j]; - } - for (i = 0; i < 16*16; ++i) - output[i] = round(out2[i] / (128 >> scale)); - } - vp9_clear_system_state(); // Make it simd safe : __asm emms; -} - -static void idct8_1d_f(double *x) { - int i, j; - double t[8]; - static const double idctmat[64] = { - 0.35355339059327, 0.49039264020162, 0.46193976625564, 0.41573480615127, - 0.35355339059327, 0.2777851165098, 0.19134171618254, 0.097545161008064, - 0.35355339059327, 0.41573480615127, 0.19134171618254, -0.097545161008064, - -0.35355339059327, -0.49039264020161, -0.46193976625564, -0.2777851165098, - 0.35355339059327, 0.2777851165098, -0.19134171618254, -0.49039264020162, - -0.35355339059327, 0.097545161008064, 0.46193976625564, 0.41573480615127, - 0.35355339059327, 0.097545161008063, -0.46193976625564, -0.2777851165098, - 0.35355339059327, 0.41573480615127, -0.19134171618254, -0.49039264020162, - 0.35355339059327, -0.097545161008063, -0.46193976625564, 0.2777851165098, - 0.35355339059327, -0.41573480615127, -0.19134171618255, 0.49039264020162, - 0.35355339059327, -0.2777851165098, -0.19134171618254, 0.49039264020161, - -0.35355339059327, -0.097545161008064, 0.46193976625564, -0.41573480615127, - 0.35355339059327, -0.41573480615127, 0.19134171618254, 0.097545161008065, - -0.35355339059327, 0.49039264020162, -0.46193976625564, 0.2777851165098, - 0.35355339059327, -0.49039264020162, 0.46193976625564, -0.41573480615127, - 0.35355339059327, -0.2777851165098, 0.19134171618255, -0.097545161008064 - }; - for (i = 0; i < 8; ++i) { - t[i] = 0; - for (j = 0; j < 8; ++j) - t[i] += idctmat[i * 8 + j] * x[j]; - } - for (i = 0; i < 8; ++i) { - x[i] = t[i]; - } -} - -static void vp9_short_idct8x8_c_f(int16_t *coefs, int16_t *block, int pitch, - int scale) { - double X[8 * 8], Y[8]; - int i, j; - int shortpitch = pitch >> 1; - - vp9_clear_system_state(); // Make it simd safe : __asm emms; - { - for (i = 0; i < 8; i++) { - for (j = 0; j < 8; j++) { - X[i * 8 + j] = (double)coefs[i * shortpitch + j]; - } - } - for (i = 0; i < 8; i++) - idct8_1d_f(X + 8 * i); - for (i = 0; i < 8; i++) { - for (j = 0; j < 8; ++j) - Y[j] = X[i + 8 * j]; - idct8_1d_f(Y); - for (j = 0; j < 8; ++j) - X[i + 8 * j] = Y[j]; - } - for (i = 0; i < 8; i++) { - for (j = 0; j < 8; j++) { - block[i * 8 + j] = (int16_t)round(X[i * 8 + j] / (8 >> scale)); - } - } - } - vp9_clear_system_state(); // Make it simd safe : __asm emms; -} - -#define multiply_bits(d, n) ((n) < 0 ? (d) >> (n) : (d) << (n)) - -#if DWTDCT_TYPE == DWTDCT16X16_LEAN - -void vp9_short_idct32x32_c(int16_t *input, int16_t *output, int pitch) { - // assume output is a 32x32 buffer - // Temporary buffer to hold a 16x16 block for 16x16 inverse dct - int16_t buffer[16 * 16]; - // Temporary buffer to hold a 32x32 block for inverse 32x32 dwt - int16_t buffer2[32 * 32]; - // Note: pitch is in bytes, short_pitch is in short units - const int short_pitch = pitch >> 1; - int i, j; - - // TODO(debargha): Implement more efficiently by adding output pitch - // argument to the idct16x16 function - vp9_short_idct16x16_c_f(input, buffer, pitch, - 1 + DWT_PRECISION_BITS); - for (i = 0; i < 16; ++i) { - vpx_memcpy(buffer2 + i * 32, buffer + i * 16, sizeof(*buffer2) * 16); - } - for (i = 0; i < 16; ++i) { - for (j = 16; j < 32; ++j) { - buffer2[i * 32 + j] = - multiply_bits(input[i * short_pitch + j], DWT_PRECISION_BITS - 2); - } - } - for (i = 16; i < 32; ++i) { - for (j = 0; j < 32; ++j) { - buffer2[i * 32 + j] = - multiply_bits(input[i * short_pitch + j], DWT_PRECISION_BITS - 2); - } - } -#if DWT_TYPE == 26 - dyadic_synthesize_26(1, 32, 32, buffer2, 32, output, 32); -#elif DWT_TYPE == 97 - dyadic_synthesize_97(1, 32, 32, buffer2, 32, output, 32); -#elif DWT_TYPE == 53 - dyadic_synthesize_53(1, 32, 32, buffer2, 32, output, 32); -#endif -} - -#elif DWTDCT_TYPE == DWTDCT16X16 - -void vp9_short_idct32x32_c(int16_t *input, int16_t *output, int pitch) { - // assume output is a 32x32 buffer - // Temporary buffer to hold a 16x16 block for 16x16 inverse dct - int16_t buffer[16 * 16]; - // Temporary buffer to hold a 32x32 block for inverse 32x32 dwt - int16_t buffer2[32 * 32]; - // Note: pitch is in bytes, short_pitch is in short units - const int short_pitch = pitch >> 1; - int i, j; - - // TODO(debargha): Implement more efficiently by adding output pitch - // argument to the idct16x16 function - vp9_short_idct16x16_c_f(input, buffer, pitch, - 1 + DWT_PRECISION_BITS); - for (i = 0; i < 16; ++i) { - vpx_memcpy(buffer2 + i * 32, buffer + i * 16, sizeof(*buffer2) * 16); - } - vp9_short_idct16x16_c_f(input + 16, buffer, pitch, - 1 + DWT_PRECISION_BITS); - for (i = 0; i < 16; ++i) { - vpx_memcpy(buffer2 + i * 32 + 16, buffer + i * 16, sizeof(*buffer2) * 16); - } - vp9_short_idct16x16_c_f(input + 16 * short_pitch, buffer, pitch, - 1 + DWT_PRECISION_BITS); - for (i = 0; i < 16; ++i) { - vpx_memcpy(buffer2 + i * 32 + 16 * 32, buffer + i * 16, - sizeof(*buffer2) * 16); - } - vp9_short_idct16x16_c_f(input + 16 * short_pitch + 16, buffer, pitch, - 1 + DWT_PRECISION_BITS); - for (i = 0; i < 16; ++i) { - vpx_memcpy(buffer2 + i * 32 + 16 * 33, buffer + i * 16, - sizeof(*buffer2) * 16); - } -#if DWT_TYPE == 26 - dyadic_synthesize_26(1, 32, 32, buffer2, 32, output, 32); -#elif DWT_TYPE == 97 - dyadic_synthesize_97(1, 32, 32, buffer2, 32, output, 32); -#elif DWT_TYPE == 53 - dyadic_synthesize_53(1, 32, 32, buffer2, 32, output, 32); -#endif -} - -#elif DWTDCT_TYPE == DWTDCT8X8 - -void vp9_short_idct32x32_c(int16_t *input, int16_t *output, int pitch) { - // assume output is a 32x32 buffer - // Temporary buffer to hold a 16x16 block for 16x16 inverse dct - int16_t buffer[8 * 8]; - // Temporary buffer to hold a 32x32 block for inverse 32x32 dwt - int16_t buffer2[32 * 32]; - // Note: pitch is in bytes, short_pitch is in short units - const int short_pitch = pitch >> 1; - int i, j; - - // TODO(debargha): Implement more efficiently by adding output pitch - // argument to the idct16x16 function - vp9_short_idct8x8_c_f(input, buffer, pitch, - 1 + DWT_PRECISION_BITS); - for (i = 0; i < 8; ++i) { - vpx_memcpy(buffer2 + i * 32, buffer + i * 8, sizeof(*buffer2) * 8); - } - vp9_short_idct8x8_c_f(input + 8, buffer, pitch, - 1 + DWT_PRECISION_BITS); - for (i = 0; i < 8; ++i) { - vpx_memcpy(buffer2 + i * 32 + 8, buffer + i * 8, sizeof(*buffer2) * 8); - } - vp9_short_idct8x8_c_f(input + 8 * short_pitch, buffer, pitch, - 1 + DWT_PRECISION_BITS); - for (i = 0; i < 8; ++i) { - vpx_memcpy(buffer2 + i * 32 + 8 * 32, buffer + i * 8, - sizeof(*buffer2) * 8); - } - vp9_short_idct8x8_c_f(input + 8 * short_pitch + 8, buffer, pitch, - 1 + DWT_PRECISION_BITS); - for (i = 0; i < 8; ++i) { - vpx_memcpy(buffer2 + i * 32 + 8 * 33, buffer + i * 8, - sizeof(*buffer2) * 8); - } - for (i = 0; i < 16; ++i) { - for (j = 16; j < 32; ++j) { - buffer2[i * 32 + j] = - multiply_bits(input[i * short_pitch + j], DWT_PRECISION_BITS - 2); - } - } - for (i = 16; i < 32; ++i) { - for (j = 0; j < 32; ++j) { - buffer2[i * 32 + j] = - multiply_bits(input[i * short_pitch + j], DWT_PRECISION_BITS - 2); - } - } -#if DWT_TYPE == 26 - dyadic_synthesize_26(2, 32, 32, buffer2, 32, output, 32); -#elif DWT_TYPE == 97 - dyadic_synthesize_97(2, 32, 32, buffer2, 32, output, 32); -#elif DWT_TYPE == 53 - dyadic_synthesize_53(2, 32, 32, buffer2, 32, output, 32); -#endif -} - -#endif - -#if CONFIG_TX64X64 -void vp9_short_idct64x64_c(int16_t *input, int16_t *output, int pitch) { - // assume output is a 64x64 buffer - // Temporary buffer to hold a 16x16 block for 16x16 inverse dct - int16_t buffer[16 * 16]; - // Temporary buffer to hold a 32x32 block for inverse 32x32 dwt - int16_t buffer2[64 * 64]; - // Note: pitch is in bytes, short_pitch is in short units - const int short_pitch = pitch >> 1; - int i, j; - - // TODO(debargha): Implement more efficiently by adding output pitch - // argument to the idct16x16 function - vp9_short_idct16x16_c_f(input, buffer, pitch, - 2 + DWT_PRECISION_BITS); - for (i = 0; i < 16; ++i) { - vpx_memcpy(buffer2 + i * 64, buffer + i * 16, sizeof(*buffer2) * 16); - } -#if DWTDCT_TYPE == DWTDCT16X16_LEAN - for (i = 0; i < 16; ++i) { - for (j = 16; j < 64; ++j) { - buffer2[i * 64 + j] = - multiply_bits(input[i * short_pitch + j], DWT_PRECISION_BITS - 1); - } - } - for (i = 16; i < 64; ++i) { - for (j = 0; j < 64; ++j) { - buffer2[i * 64 + j] = - multiply_bits(input[i * short_pitch + j], DWT_PRECISION_BITS - 1); - } - } -#elif DWTDCT_TYPE == DWTDCT16X16 - vp9_short_idct16x16_c_f(input + 16, buffer, pitch, - 2 + DWT_PRECISION_BITS); - for (i = 0; i < 16; ++i) { - vpx_memcpy(buffer2 + i * 64 + 16, buffer + i * 16, sizeof(*buffer2) * 16); - } - vp9_short_idct16x16_c_f(input + 16 * short_pitch, buffer, pitch, - 2 + DWT_PRECISION_BITS); - for (i = 0; i < 16; ++i) { - vpx_memcpy(buffer2 + i * 64 + 16 * 64, buffer + i * 16, - sizeof(*buffer2) * 16); - } - vp9_short_idct16x16_c_f(input + 16 * short_pitch + 16, buffer, pitch, - 2 + DWT_PRECISION_BITS); - for (i = 0; i < 16; ++i) { - vpx_memcpy(buffer2 + i * 64 + 16 * 65, buffer + i * 16, - sizeof(*buffer2) * 16); - } - - // Copying and scaling highest bands into buffer2 - for (i = 0; i < 32; ++i) { - for (j = 32; j < 64; ++j) { - buffer2[i * 64 + j] = - multiply_bits(input[i * short_pitch + j], DWT_PRECISION_BITS - 1); - } - } - for (i = 32; i < 64; ++i) { - for (j = 0; j < 64; ++j) { - buffer2[i * 64 + j] = - multiply_bits(input[i * short_pitch + j], DWT_PRECISION_BITS - 1); - } - } -#endif // DWTDCT_TYPE - -#if DWT_TYPE == 26 - dyadic_synthesize_26(2, 64, 64, buffer2, 64, output, 64); -#elif DWT_TYPE == 97 - dyadic_synthesize_97(2, 64, 64, buffer2, 64, output, 64); -#elif DWT_TYPE == 53 - dyadic_synthesize_53(2, 64, 64, buffer2, 64, output, 64); -#endif -} -#endif // CONFIG_TX64X64 -#endif // !CONFIG_DWTDCTHYBRID |