ref: e6ad9ab02c9914182fec83b9170c5bc86baf4102
parent: d15e1da4940f813311035c3ed101a9c69f15b527
author: Yaowu Xu <yaowu@google.com>
date: Thu Feb 7 06:51:23 EST 2013
move dct/idct constants to a header file also removed some un-unsed functions. Change-Id: Ie363bcc8d94441d054137d2ef7c4fe59f56027e5
--- /dev/null
+++ b/vp9/common/vp9_idct.h
@@ -1,0 +1,58 @@
+/*
+ * Copyright (c) 2010 The WebM project authors. All Rights Reserved.
+ *
+ * Use of this source code is governed by a BSD-style license
+ * that can be found in the LICENSE file in the root of the source
+ * tree. An additional intellectual property rights grant can be found
+ * in the file PATENTS. All contributing project authors may
+ * be found in the AUTHORS file in the root of the source tree.
+ */
+
+#ifndef VP9_COMMON_VP9_IDCT_H
+#define VP9_COMMON_VP9_IDCT_H
+
+#include "./vpx_config.h"
+
+// Constants and Macros used by all idct/dct functions
+#define DCT_CONST_BITS 14
+#define DCT_CONST_ROUNDING (1 << (DCT_CONST_BITS - 1))
+// Constants are 16384 * cos(kPi/64) where k = 1 to 31.
+// Note: sin(kPi/64) = cos((32-k)Pi/64)
+static const int cospi_1_64 = 16364;
+static const int cospi_2_64 = 16305;
+static const int cospi_3_64 = 16207;
+static const int cospi_4_64 = 16069;
+static const int cospi_5_64 = 15893;
+static const int cospi_6_64 = 15679;
+static const int cospi_7_64 = 15426;
+static const int cospi_8_64 = 15137;
+static const int cospi_9_64 = 14811;
+static const int cospi_10_64 = 14449;
+static const int cospi_11_64 = 14053;
+static const int cospi_12_64 = 13623;
+static const int cospi_13_64 = 13160;
+static const int cospi_14_64 = 12665;
+static const int cospi_15_64 = 12140;
+static const int cospi_16_64 = 11585;
+static const int cospi_17_64 = 11003;
+static const int cospi_18_64 = 10394;
+static const int cospi_19_64 = 9760;
+static const int cospi_20_64 = 9102;
+static const int cospi_21_64 = 8423;
+static const int cospi_22_64 = 7723;
+static const int cospi_23_64 = 7005;
+static const int cospi_24_64 = 6270;
+static const int cospi_25_64 = 5520;
+static const int cospi_26_64 = 4756;
+static const int cospi_27_64 = 3981;
+static const int cospi_28_64 = 3196;
+static const int cospi_29_64 = 2404;
+static const int cospi_30_64 = 1606;
+static const int cospi_31_64 = 804;
+
+static INLINE int dct_const_round_shift(int input) {+ int rv = (input + DCT_CONST_ROUNDING) >> DCT_CONST_BITS;
+ assert((rv <= INT16_MAX) && (rv >= INT16_MIN));
+ return rv;
+}
+#endif
--- a/vp9/common/vp9_idctllm.c
+++ b/vp9/common/vp9_idctllm.c
@@ -28,6 +28,7 @@
#include "vp9/common/vp9_systemdependent.h"
#include "vp9/common/vp9_blockd.h"
#include "vp9/common/vp9_common.h"
+#include "vp9/common/vp9_idct.h"
@@ -493,50 +494,7 @@
}
#endif
-// Constants and Macros used by all idct functions
-// TODO(Yaowu): move these to a header file as they shared by DCTs and iDCTs
-#define DCT_CONST_BITS 14
-#define DCT_CONST_ROUNDING (1 << (DCT_CONST_BITS - 1))
-// Constants are 16384 * cos(kPi/64) where k = 1 to 31.
-// Note: sin(kPi/64) = cos((32-k)Pi/64)
-static const int cospi_1_64 = 16364;
-static const int cospi_2_64 = 16305;
-static const int cospi_3_64 = 16207;
-static const int cospi_4_64 = 16069;
-static const int cospi_5_64 = 15893;
-static const int cospi_6_64 = 15679;
-static const int cospi_7_64 = 15426;
-static const int cospi_8_64 = 15137;
-static const int cospi_9_64 = 14811;
-static const int cospi_10_64 = 14449;
-static const int cospi_11_64 = 14053;
-static const int cospi_12_64 = 13623;
-static const int cospi_13_64 = 13160;
-static const int cospi_14_64 = 12665;
-static const int cospi_15_64 = 12140;
-static const int cospi_16_64 = 11585;
-static const int cospi_17_64 = 11003;
-static const int cospi_18_64 = 10394;
-static const int cospi_19_64 = 9760;
-static const int cospi_20_64 = 9102;
-static const int cospi_21_64 = 8423;
-static const int cospi_22_64 = 7723;
-static const int cospi_23_64 = 7005;
-static const int cospi_24_64 = 6270;
-static const int cospi_25_64 = 5520;
-static const int cospi_26_64 = 4756;
-static const int cospi_27_64 = 3981;
-static const int cospi_28_64 = 3196;
-static const int cospi_29_64 = 2404;
-static const int cospi_30_64 = 1606;
-static const int cospi_31_64 = 804;
-static INLINE int dct_const_round_shift(int input) {- int rv = (input + DCT_CONST_ROUNDING) >> DCT_CONST_BITS;
- assert((rv <= INT16_MAX) && (rv >= INT16_MIN));
- return rv;
-}
-
void idct4_1d(int16_t *input, int16_t *output) {int16_t step[4];
int temp1, temp2;
@@ -875,302 +833,6 @@
op[8] = (ip[0] - ip[1] - ip[4] + ip[8]) >> 1;
}
-
-#if 0
-// Keep a really bad float version as reference for now.
-void vp9_short_idct16x16_c(int16_t *input, int16_t *output, int pitch) {-
- vp9_clear_system_state(); // Make it simd safe : __asm emms;
- {- double x;
- const int short_pitch = pitch >> 1;
- int i, j, k, l;
- for (l = 0; l < 16; ++l) {- for (k = 0; k < 16; ++k) {- double s = 0;
- for (i = 0; i < 16; ++i) {- for (j = 0; j < 16; ++j) {- x=cos(PI*j*(l+0.5)/16.0)*cos(PI*i*(k+0.5)/16.0)*input[i*16+j]/32;
- if (i != 0)
- x *= sqrt(2.0);
- if (j != 0)
- x *= sqrt(2.0);
- s += x;
- }
- }
- output[k*short_pitch+l] = (short)round(s);
- }
- }
- }
- vp9_clear_system_state(); // Make it simd safe : __asm emms;
-}
-#endif
-
-#define TEST_INT_16x16_IDCT 1
-#if !TEST_INT_16x16_IDCT
-
-static void butterfly_16x16_idct_1d(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;
-}
-
-// Remove once an int version of iDCT is written
-#if 0
-void reference_16x16_idct_1d(double input[16], double output[16]) {-
- vp9_clear_system_state(); // Make it simd safe : __asm emms;
- {- const double kPi = 3.141592653589793238462643383279502884;
- const double kSqrt2 = 1.414213562373095048801688724209698;
- for (int k = 0; k < 16; k++) {- output[k] = 0.0;
- for (int n = 0; n < 16; n++) {- output[k] += input[n]*cos(kPi*(2*k+1)*n/32.0);
- if (n == 0)
- output[k] = output[k]/kSqrt2;
- }
- }
- }
- vp9_clear_system_state(); // Make it simd safe : __asm emms;
-}
-#endif
-
-void vp9_short_idct16x16_c(int16_t *input, int16_t *output, int pitch) {-
- 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(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(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);
- }
- vp9_clear_system_state(); // Make it simd safe : __asm emms;
-}
-
-#else
-
void idct16_1d(int16_t *input, int16_t *output) {int16_t step1[16], step2[16];
int temp1, temp2;
@@ -1396,7 +1058,7 @@
out = dct_const_round_shift(tmp);
*output = (out + 32) >> 6;
}
-#endif
+
#if !CONFIG_DWTDCTHYBRID
void idct32_1d(int16_t *input, int16_t *output) {--- a/vp9/encoder/vp9_dct.c
+++ b/vp9/encoder/vp9_dct.c
@@ -15,6 +15,7 @@
#include "vp9/common/vp9_systemdependent.h"
#include "vp9/common/vp9_blockd.h"
+#include "vp9/common/vp9_idct.h"
// TODO: these transforms can be converted into integer forms to reduce
// the complexity
@@ -782,49 +783,6 @@
im += tx_dim; // 16
op += tx_dim;
}
-}
-// Constants and Macros used by all idct functions
-// TODO(Yaowu): move these to a header file as they shared by DCTs and iDCTs
-#define DCT_CONST_BITS 14
-#define DCT_CONST_ROUNDING (1 << (DCT_CONST_BITS - 1))
-// Constants are 16384 * cos(kPi/64) where k = 1 to 31.
-// Note: sin(kPi/64) = cos((32-k)Pi/64)
-static const int cospi_1_64 = 16364;
-static const int cospi_2_64 = 16305;
-static const int cospi_3_64 = 16207;
-static const int cospi_4_64 = 16069;
-static const int cospi_5_64 = 15893;
-static const int cospi_6_64 = 15679;
-static const int cospi_7_64 = 15426;
-static const int cospi_8_64 = 15137;
-static const int cospi_9_64 = 14811;
-static const int cospi_10_64 = 14449;
-static const int cospi_11_64 = 14053;
-static const int cospi_12_64 = 13623;
-static const int cospi_13_64 = 13160;
-static const int cospi_14_64 = 12665;
-static const int cospi_15_64 = 12140;
-static const int cospi_16_64 = 11585;
-static const int cospi_17_64 = 11003;
-static const int cospi_18_64 = 10394;
-static const int cospi_19_64 = 9760;
-static const int cospi_20_64 = 9102;
-static const int cospi_21_64 = 8423;
-static const int cospi_22_64 = 7723;
-static const int cospi_23_64 = 7005;
-static const int cospi_24_64 = 6270;
-static const int cospi_25_64 = 5520;
-static const int cospi_26_64 = 4756;
-static const int cospi_27_64 = 3981;
-static const int cospi_28_64 = 3196;
-static const int cospi_29_64 = 2404;
-static const int cospi_30_64 = 1606;
-static const int cospi_31_64 = 804;
-
-static INLINE int dct_const_round_shift(int input) {- int rv = (input + DCT_CONST_ROUNDING) >> DCT_CONST_BITS;
- assert((rv <= INT16_MAX) && (rv >= INT16_MIN));
- return rv;
}
static void fdct4_1d(int16_t *input, int16_t *output) {--- a/vp9/vp9_common.mk
+++ b/vp9/vp9_common.mk
@@ -36,6 +36,7 @@
VP9_COMMON_SRCS-yes += common/vp9_extend.h
VP9_COMMON_SRCS-yes += common/vp9_findnearmv.h
VP9_COMMON_SRCS-yes += common/vp9_header.h
+VP9_COMMON_SRCS-yes += common/vp9_idct.h
VP9_COMMON_SRCS-yes += common/vp9_invtrans.h
VP9_COMMON_SRCS-yes += common/vp9_loopfilter.h
VP9_COMMON_SRCS-yes += common/vp9_modecont.h
--
⑨