source/common/x86/pixel-util.h

   1 /*****************************************************************************
   2  * Copyright (C) 2013 x265 project
   3  *
   4  * Authors: Steve Borho <steve@borho.org>
   5  *
   6  * This program is free software; you can redistribute it and/or modify
   7  * it under the terms of the GNU General Public License as published by
   8  * the Free Software Foundation; either version 2 of the License, or
   9  * (at your option) any later version.
  10  *
  11  * This program is distributed in the hope that it will be useful,
  12  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  13  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  14  * GNU General Public License for more details.
  15  *
  16  * You should have received a copy of the GNU General Public License
  17  * along with this program; if not, write to the Free Software
  18  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02111, USA.
  19  *
  20  * This program is also available under a commercial proprietary license.
  21  * For more information, contact us at license @ x265.com.
  22  *****************************************************************************/
  23
  24 #ifndef X265_PIXEL_UTIL_H
  25 #define X265_PIXEL_UTIL_H
  26
  27 void x265_calcRecons4_sse2(pixel* pred, int16_t* residual, int16_t* reconqt, pixel *reconipred, int stride, int strideqt, int strideipred);
  28 void x265_calcRecons8_sse2(pixel* pred, int16_t* residual, int16_t* reconqt, pixel *reconipred, int stride, int strideqt, int strideipred);
  29 void x265_calcRecons16_sse2(pixel* pred, int16_t* residual, int16_t* reconqt, pixel *reconipred, int stride, int strideqt, int strideipred);
  30 void x265_calcRecons32_sse2(pixel* pred, int16_t* residual, int16_t* reconqt, pixel *reconipred, int stride, int strideqt, int strideipred);
  31 void x265_calcRecons16_sse4(pixel* pred, int16_t* residual, int16_t* reconqt, pixel *reconipred, int stride, int strideqt, int strideipred);
  32 void x265_calcRecons32_sse4(pixel* pred, int16_t* residual, int16_t* reconqt, pixel *reconipred, int stride, int strideqt, int strideipred);
  33
  34 void x265_getResidual4_sse2(pixel *fenc, pixel *pred, int16_t *residual, intptr_t stride);
  35 void x265_getResidual8_sse2(pixel *fenc, pixel *pred, int16_t *residual, intptr_t stride);
  36 void x265_getResidual16_sse2(pixel *fenc, pixel *pred, int16_t *residual, intptr_t stride);
  37 void x265_getResidual16_sse4(pixel *fenc, pixel *pred, int16_t *residual, intptr_t stride);
  38 void x265_getResidual32_sse2(pixel *fenc, pixel *pred, int16_t *residual, intptr_t stride);
  39 void x265_getResidual32_sse4(pixel *fenc, pixel *pred, int16_t *residual, intptr_t stride);
  40
  41 void x265_transpose4_sse2(pixel *dest, pixel *src, intptr_t stride);
  42 void x265_transpose8_sse2(pixel *dest, pixel *src, intptr_t stride);
  43 void x265_transpose16_sse2(pixel *dest, pixel *src, intptr_t stride);
  44 void x265_transpose32_sse2(pixel *dest, pixel *src, intptr_t stride);
  45 void x265_transpose64_sse2(pixel *dest, pixel *src, intptr_t stride);
  46
  47 void x265_transpose8_avx2(pixel *dest, pixel *src, intptr_t stride);
  48 void x265_transpose16_avx2(pixel *dest, pixel *src, intptr_t stride);
  49 void x265_transpose32_avx2(pixel *dest, pixel *src, intptr_t stride);
  50 void x265_transpose64_avx2(pixel *dest, pixel *src, intptr_t stride);
  51
  52 uint32_t x265_quant_sse4(int32_t *coef, int32_t *quantCoeff, int32_t *deltaU, int16_t *qCoef, int qBits, int add, int numCoeff);
  53 uint32_t x265_quant_avx2(int32_t *coef, int32_t *quantCoeff, int32_t *deltaU, int16_t *qCoef, int qBits, int add, int numCoeff);
  54 uint32_t x265_nquant_sse4(int32_t *coef, int32_t *quantCoeff, int16_t *qCoef, int qBits, int add, int numCoeff);
  55 uint32_t x265_nquant_avx2(int32_t *coef, int32_t *quantCoeff, int16_t *qCoef, int qBits, int add, int numCoeff);
  56 void x265_dequant_normal_sse4(const int16_t* quantCoef, int32_t* coef, int num, int scale, int shift);
  57 void x265_dequant_normal_avx2(const int16_t* quantCoef, int32_t* coef, int num, int scale, int shift);
  58 int x265_count_nonzero_ssse3(const int16_t *quantCoeff, int numCoeff);
  59
  60 void x265_weight_pp_sse4(pixel *src, pixel *dst, intptr_t stride, int width, int height, int w0, int round, int shift, int offset);
  61 void x265_weight_pp_avx2(pixel *src, pixel *dst, intptr_t stride, int width, int height, int w0, int round, int shift, int offset);
  62 void x265_weight_sp_sse4(int16_t *src, pixel *dst, intptr_t srcStride, intptr_t dstStride, int width, int height, int w0, int round, int shift, int offset);
  63
  64 void x265_pixel_ssim_4x4x2_core_mmx2(const uint8_t * pix1, intptr_t stride1,
  65                                      const uint8_t * pix2, intptr_t stride2, int sums[2][4]);
  66 void x265_pixel_ssim_4x4x2_core_sse2(const pixel * pix1, intptr_t stride1,
  67                                      const pixel * pix2, intptr_t stride2, int sums[2][4]);
  68 void x265_pixel_ssim_4x4x2_core_avx(const pixel * pix1, intptr_t stride1,
  69                                     const pixel * pix2, intptr_t stride2, int sums[2][4]);
  70 float x265_pixel_ssim_end4_sse2(int sum0[5][4], int sum1[5][4], int width);
  71 float x265_pixel_ssim_end4_avx(int sum0[5][4], int sum1[5][4], int width);
  72
  73 void x265_scale1D_128to64_ssse3(pixel *, pixel *, intptr_t);
  74 void x265_scale1D_128to64_avx2(pixel *, pixel *, intptr_t);
  75 void x265_scale2D_64to32_ssse3(pixel *, pixel *, intptr_t);
  76
  77 #define SETUP_CHROMA_PIXELSUB_PS_FUNC(W, H, cpu) \
  78     void x265_pixel_sub_ps_ ## W ## x ## H ## cpu(int16_t * dest, intptr_t destride, pixel * src0, pixel * src1, intptr_t srcstride0, intptr_t srcstride1); \
  79     void x265_pixel_add_ps_ ## W ## x ## H ## cpu(pixel * dest, intptr_t destride, pixel * src0, int16_t * scr1, intptr_t srcStride0, intptr_t srcStride1);
  80
  81 #define CHROMA_PIXELSUB_DEF(cpu) \
  82     SETUP_CHROMA_PIXELSUB_PS_FUNC(4, 4, cpu); \
  83     SETUP_CHROMA_PIXELSUB_PS_FUNC(8, 8, cpu); \
  84     SETUP_CHROMA_PIXELSUB_PS_FUNC(16, 16, cpu); \
  85     SETUP_CHROMA_PIXELSUB_PS_FUNC(32, 32, cpu);
  86
  87 #define CHROMA_PIXELSUB_DEF_422(cpu) \
  88     SETUP_CHROMA_PIXELSUB_PS_FUNC(4, 8, cpu); \
  89     SETUP_CHROMA_PIXELSUB_PS_FUNC(8, 16, cpu); \
  90     SETUP_CHROMA_PIXELSUB_PS_FUNC(16, 32, cpu); \
  91     SETUP_CHROMA_PIXELSUB_PS_FUNC(32, 64, cpu);
  92
  93 #define SETUP_LUMA_PIXELSUB_PS_FUNC(W, H, cpu) \
  94     void x265_pixel_sub_ps_ ## W ## x ## H ## cpu(int16_t * dest, intptr_t destride, pixel * src0, pixel * src1, intptr_t srcstride0, intptr_t srcstride1); \
  95     void x265_pixel_add_ps_ ## W ## x ## H ## cpu(pixel * dest, intptr_t destride, pixel * src0, int16_t * scr1, intptr_t srcStride0, intptr_t srcStride1);
  96
  97 #define LUMA_PIXELSUB_DEF(cpu) \
  98     SETUP_LUMA_PIXELSUB_PS_FUNC(8,   8, cpu); \
  99     SETUP_LUMA_PIXELSUB_PS_FUNC(16, 16, cpu); \
 100     SETUP_LUMA_PIXELSUB_PS_FUNC(32, 32, cpu); \
 101     SETUP_LUMA_PIXELSUB_PS_FUNC(64, 64, cpu);
 102
 103 CHROMA_PIXELSUB_DEF(_sse4);
 104 LUMA_PIXELSUB_DEF(_sse4);
 105 CHROMA_PIXELSUB_DEF(_sse2);
 106 LUMA_PIXELSUB_DEF(_sse2);
 107
 108 CHROMA_PIXELSUB_DEF_422(_sse4);
 109 CHROMA_PIXELSUB_DEF_422(_sse2);
 110
 111 #define SETUP_LUMA_PIXELVAR_FUNC(W, H, cpu) \
 112     uint64_t x265_pixel_var_ ## W ## x ## H ## cpu(pixel * pix, intptr_t pixstride);
 113
 114 #define LUMA_PIXELVAR_DEF(cpu) \
 115     SETUP_LUMA_PIXELVAR_FUNC(8,   8, cpu); \
 116     SETUP_LUMA_PIXELVAR_FUNC(16, 16, cpu); \
 117     SETUP_LUMA_PIXELVAR_FUNC(32, 32, cpu); \
 118     SETUP_LUMA_PIXELVAR_FUNC(64, 64, cpu);
 119
 120 LUMA_PIXELVAR_DEF(_sse2);
 121
 122 #undef CHROMA_PIXELSUB_DEF
 123 #undef CHROMA_PIXELSUB_DEF_422
 124 #undef LUMA_PIXELSUB_DEF
 125 #undef LUMA_PIXELVAR_DEF
 126 #undef SETUP_CHROMA_PIXELSUB_PS_FUNC
 127 #undef SETUP_LUMA_PIXELSUB_PS_FUNC
 128 #undef SETUP_LUMA_PIXELVAR_FUNC
 129
 130 #endif // ifndef X265_PIXEL_UTIL_H