Switch to exponential interpolation between presets.

[x264] / common / quant.c

diff --git a/common/quant.c b/common/quant.c
index 2fa1521d7378cbebfa0328761980236520922378..312f7cd9101d95047ec17c9cdd00951ce6d6ead6 100644 (file)
--- a/common/quant.c
+++ b/common/quant.c
@@ -1,12 +1,12 @@
 /*****************************************************************************
  * quant.c: quantization and level-run
  *****************************************************************************
- * Copyright (C) 2005-2013 x264 project
+ * Copyright (C) 2005-2016 x264 project
  *
  * Authors: Loren Merritt <lorenm@u.washington.edu>
  *          Fiona Glaser <fiona@x264.com>
  *          Christian Heine <sennindemokrit@gmx.net>
- *          Henrik Gramner <hengar-6@student.ltu.se>
+ *          Henrik Gramner <henrik@gramner.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -37,6 +37,12 @@
 #if ARCH_ARM
 #   include "arm/quant.h"
 #endif
+#if ARCH_AARCH64
+#   include "aarch64/quant.h"
+#endif
+#if ARCH_MIPS
+#   include "mips/quant.h"
+#endif
 
 #define QUANT_ONE( coef, mf, f ) \
 { \
@@ -480,6 +486,8 @@ void x264_quant_init( x264_t *h, int cpu, x264_quant_function_t *pf )
         pf->dequant_4x4 = x264_dequant_4x4_sse2;
         pf->dequant_8x8 = x264_dequant_8x8_sse2;
         pf->dequant_4x4_dc = x264_dequant_4x4dc_sse2;
+        pf->idct_dequant_2x4_dc = x264_idct_dequant_2x4_dc_sse2;
+        pf->idct_dequant_2x4_dconly = x264_idct_dequant_2x4_dconly_sse2;
         pf->denoise_dct = x264_denoise_dct_sse2;
         pf->decimate_score15 = x264_decimate_score15_sse2;
         pf->decimate_score16 = x264_decimate_score16_sse2;
@@ -526,6 +534,8 @@ void x264_quant_init( x264_t *h, int cpu, x264_quant_function_t *pf )
     }
     if( cpu&X264_CPU_AVX )
     {
+        pf->idct_dequant_2x4_dc = x264_idct_dequant_2x4_dc_avx;
+        pf->idct_dequant_2x4_dconly = x264_idct_dequant_2x4_dconly_avx;
         pf->denoise_dct = x264_denoise_dct_avx;
     }
     if( cpu&X264_CPU_XOP )
@@ -545,7 +555,10 @@ void x264_quant_init( x264_t *h, int cpu, x264_quant_function_t *pf )
         pf->quant_4x4x4 = x264_quant_4x4x4_avx2;
         pf->dequant_4x4 = x264_dequant_4x4_avx2;
         pf->dequant_8x8 = x264_dequant_8x8_avx2;
+        pf->dequant_4x4_dc = x264_dequant_4x4dc_avx2;
         pf->denoise_dct = x264_denoise_dct_avx2;
+        if( cpu&X264_CPU_LZCNT )
+            pf->coeff_last[DCT_LUMA_8x8] = x264_coeff_last64_avx2_lzcnt;
     }
 #endif // HAVE_MMX
 #else // !HIGH_BIT_DEPTH
@@ -554,9 +567,6 @@ void x264_quant_init( x264_t *h, int cpu, x264_quant_function_t *pf )
     if( cpu&X264_CPU_MMX )
     {
 #if ARCH_X86
-        pf->quant_4x4 = x264_quant_4x4_mmx;
-        pf->quant_4x4x4 = x264_quant_4x4x4_mmx;
-        pf->quant_8x8 = x264_quant_8x8_mmx;
         pf->dequant_4x4 = x264_dequant_4x4_mmx;
         pf->dequant_4x4_dc = x264_dequant_4x4dc_mmx2;
         pf->dequant_8x8 = x264_dequant_8x8_mmx;
@@ -573,6 +583,8 @@ void x264_quant_init( x264_t *h, int cpu, x264_quant_function_t *pf )
     {
         pf->quant_2x2_dc = x264_quant_2x2_dc_mmx2;
 #if ARCH_X86
+        pf->quant_4x4 = x264_quant_4x4_mmx2;
+        pf->quant_8x8 = x264_quant_8x8_mmx2;
         pf->quant_4x4_dc = x264_quant_4x4_dc_mmx2;
         pf->decimate_score15 = x264_decimate_score15_mmx2;
         pf->decimate_score16 = x264_decimate_score16_mmx2;
@@ -610,6 +622,8 @@ void x264_quant_init( x264_t *h, int cpu, x264_quant_function_t *pf )
             pf->dequant_4x4 = x264_dequant_4x4_flat16_sse2;
             pf->dequant_8x8 = x264_dequant_8x8_flat16_sse2;
         }
+        pf->idct_dequant_2x4_dc = x264_idct_dequant_2x4_dc_sse2;
+        pf->idct_dequant_2x4_dconly = x264_idct_dequant_2x4_dconly_sse2;
         pf->optimize_chroma_2x2_dc = x264_optimize_chroma_2x2_dc_sse2;
         pf->denoise_dct = x264_denoise_dct_sse2;
         pf->decimate_score15 = x264_decimate_score15_sse2;
@@ -672,6 +686,8 @@ void x264_quant_init( x264_t *h, int cpu, x264_quant_function_t *pf )
             pf->dequant_4x4 = x264_dequant_4x4_avx;
             pf->dequant_8x8 = x264_dequant_8x8_avx;
         }
+        pf->idct_dequant_2x4_dc = x264_idct_dequant_2x4_dc_avx;
+        pf->idct_dequant_2x4_dconly = x264_idct_dequant_2x4_dconly_avx;
         pf->optimize_chroma_2x2_dc = x264_optimize_chroma_2x2_dc_avx;
         pf->denoise_dct = x264_denoise_dct_avx;
     }
@@ -691,10 +707,9 @@ void x264_quant_init( x264_t *h, int cpu, x264_quant_function_t *pf )
         pf->quant_4x4_dc = x264_quant_4x4_dc_avx2;
         pf->quant_8x8 = x264_quant_8x8_avx2;
         pf->quant_4x4x4 = x264_quant_4x4x4_avx2;
-        if( cpu&X264_CPU_LZCNT )
-            pf->coeff_last[DCT_LUMA_8x8] = x264_coeff_last64_avx2_lzcnt;
         pf->dequant_4x4 = x264_dequant_4x4_avx2;
         pf->dequant_8x8 = x264_dequant_8x8_avx2;
+        pf->dequant_4x4_dc = x264_dequant_4x4dc_avx2;
         if( h->param.i_cqm_preset == X264_CQM_FLAT )
         {
             pf->dequant_4x4 = x264_dequant_4x4_flat16_avx2;
@@ -704,6 +719,7 @@ void x264_quant_init( x264_t *h, int cpu, x264_quant_function_t *pf )
         pf->denoise_dct = x264_denoise_dct_avx2;
         if( cpu&X264_CPU_LZCNT )
         {
+            pf->coeff_last[DCT_LUMA_8x8] = x264_coeff_last64_avx2_lzcnt;
             pf->coeff_level_run[ DCT_LUMA_AC] = x264_coeff_level_run15_avx2_lzcnt;
             pf->coeff_level_run[DCT_LUMA_4x4] = x264_coeff_level_run16_avx2_lzcnt;
         }
@@ -711,7 +727,8 @@ void x264_quant_init( x264_t *h, int cpu, x264_quant_function_t *pf )
 #endif // HAVE_MMX
 
 #if HAVE_ALTIVEC
-    if( cpu&X264_CPU_ALTIVEC ) {
+    if( cpu&X264_CPU_ALTIVEC )
+    {
         pf->quant_2x2_dc = x264_quant_2x2_dc_altivec;
         pf->quant_4x4_dc = x264_quant_4x4_dc_altivec;
         pf->quant_4x4 = x264_quant_4x4_altivec;
@@ -724,8 +741,12 @@ void x264_quant_init( x264_t *h, int cpu, x264_quant_function_t *pf )
 
 #if HAVE_ARMV6
     if( cpu&X264_CPU_ARMV6 )
+    {
         pf->coeff_last4 = x264_coeff_last4_arm;
-
+        pf->coeff_last8 = x264_coeff_last8_arm;
+    }
+#endif
+#if HAVE_ARMV6 || ARCH_AARCH64
     if( cpu&X264_CPU_NEON )
     {
         pf->quant_2x2_dc   = x264_quant_2x2_dc_neon;
@@ -739,6 +760,39 @@ void x264_quant_init( x264_t *h, int cpu, x264_quant_function_t *pf )
         pf->coeff_last[ DCT_LUMA_AC] = x264_coeff_last15_neon;
         pf->coeff_last[DCT_LUMA_4x4] = x264_coeff_last16_neon;
         pf->coeff_last[DCT_LUMA_8x8] = x264_coeff_last64_neon;
+        pf->denoise_dct = x264_denoise_dct_neon;
+        pf->decimate_score15 = x264_decimate_score15_neon;
+        pf->decimate_score16 = x264_decimate_score16_neon;
+        pf->decimate_score64 = x264_decimate_score64_neon;
+    }
+#endif
+#if ARCH_AARCH64
+    if( cpu&X264_CPU_ARMV8 )
+    {
+        pf->coeff_last4 = x264_coeff_last4_aarch64;
+        pf->coeff_last8 = x264_coeff_last8_aarch64;
+        pf->coeff_level_run4 = x264_coeff_level_run4_aarch64;
+    }
+    if( cpu&X264_CPU_NEON )
+    {
+        pf->coeff_level_run8 = x264_coeff_level_run8_neon;
+        pf->coeff_level_run[  DCT_LUMA_AC] = x264_coeff_level_run15_neon;
+        pf->coeff_level_run[ DCT_LUMA_4x4] = x264_coeff_level_run16_neon;
+    }
+#endif
+
+#if HAVE_MSA
+    if( cpu&X264_CPU_MSA )
+    {
+        pf->quant_4x4      = x264_quant_4x4_msa;
+        pf->quant_4x4_dc   = x264_quant_4x4_dc_msa;
+        pf->quant_4x4x4    = x264_quant_4x4x4_msa;
+        pf->quant_8x8      = x264_quant_8x8_msa;
+        pf->dequant_4x4    = x264_dequant_4x4_msa;
+        pf->dequant_4x4_dc = x264_dequant_4x4_dc_msa;
+        pf->dequant_8x8    = x264_dequant_8x8_msa;
+        pf->coeff_last[DCT_LUMA_4x4] = x264_coeff_last16_msa;
+        pf->coeff_last[DCT_LUMA_8x8] = x264_coeff_last64_msa;
     }
 #endif
 #endif // HIGH_BIT_DEPTH