/*****************************************************************************
* quant.c: quantization and level-run
*****************************************************************************
- * Copyright (C) 2005-2011 x264 project
+ * Copyright (C) 2005-2014 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
#if ARCH_ARM
# include "arm/quant.h"
#endif
+#if ARCH_AARCH64
+# include "aarch64/quant.h"
+#endif
#define QUANT_ONE( coef, mf, f ) \
{ \
return !!nz;
}
+static int quant_4x4x4( dctcoef dct[4][16], udctcoef mf[16], udctcoef bias[16] )
+{
+ int nza = 0;
+ for( int j = 0; j < 4; j++ )
+ {
+ int nz = 0;
+ for( int i = 0; i < 16; i++ )
+ QUANT_ONE( dct[j][i], mf[i], bias[i] );
+ nza |= (!!nz)<<j;
+ }
+ return nza;
+}
+
static int quant_4x4_dc( dctcoef dct[16], int mf, int bias )
{
int nz = 0;
{\
int i_last = runlevel->last = x264_coeff_last##num(dct);\
int i_total = 0;\
+ int mask = 0;\
do\
{\
- int r = 0;\
- runlevel->level[i_total] = dct[i_last];\
- while( --i_last >= 0 && dct[i_last] == 0 )\
- r++;\
- runlevel->run[i_total++] = r;\
+ runlevel->level[i_total++] = dct[i_last];\
+ mask |= 1 << (i_last);\
+ while( --i_last >= 0 && dct[i_last] == 0 );\
} while( i_last >= 0 );\
+ runlevel->mask = mask;\
return i_total;\
}
level_run(15)
level_run(16)
+#if ARCH_X86_64
+#define INIT_TRELLIS(cpu)\
+ pf->trellis_cabac_4x4 = x264_trellis_cabac_4x4_##cpu;\
+ pf->trellis_cabac_8x8 = x264_trellis_cabac_8x8_##cpu;\
+ pf->trellis_cabac_4x4_psy = x264_trellis_cabac_4x4_psy_##cpu;\
+ pf->trellis_cabac_8x8_psy = x264_trellis_cabac_8x8_psy_##cpu;\
+ pf->trellis_cabac_dc = x264_trellis_cabac_dc_##cpu;\
+ pf->trellis_cabac_chroma_422_dc = x264_trellis_cabac_chroma_422_dc_##cpu;
+#else
+#define INIT_TRELLIS(...)
+#endif
+
void x264_quant_init( x264_t *h, int cpu, x264_quant_function_t *pf )
{
pf->quant_8x8 = quant_8x8;
pf->quant_4x4 = quant_4x4;
+ pf->quant_4x4x4 = quant_4x4x4;
pf->quant_4x4_dc = quant_4x4_dc;
pf->quant_2x2_dc = quant_2x2_dc;
#if HIGH_BIT_DEPTH
#if HAVE_MMX
+ INIT_TRELLIS( sse2 );
if( cpu&X264_CPU_MMX2 )
{
#if ARCH_X86
pf->denoise_dct = x264_denoise_dct_mmx;
pf->decimate_score15 = x264_decimate_score15_mmx2;
pf->decimate_score16 = x264_decimate_score16_mmx2;
- if( cpu&X264_CPU_SLOW_CTZ )
- {
- pf->decimate_score15 = x264_decimate_score15_mmx2_slowctz;
- pf->decimate_score16 = x264_decimate_score16_mmx2_slowctz;
- }
pf->decimate_score64 = x264_decimate_score64_mmx2;
- pf->coeff_last4 = x264_coeff_last4_mmx2;
+ pf->coeff_last8 = x264_coeff_last8_mmx2;
pf->coeff_last[ DCT_LUMA_AC] = x264_coeff_last15_mmx2;
pf->coeff_last[ DCT_LUMA_4x4] = x264_coeff_last16_mmx2;
pf->coeff_last[ DCT_LUMA_8x8] = x264_coeff_last64_mmx2;
+ pf->coeff_level_run8 = x264_coeff_level_run8_mmx2;
pf->coeff_level_run[ DCT_LUMA_AC] = x264_coeff_level_run15_mmx2;
pf->coeff_level_run[ DCT_LUMA_4x4] = x264_coeff_level_run16_mmx2;
#endif
+ pf->coeff_last4 = x264_coeff_last4_mmx2;
pf->coeff_level_run4 = x264_coeff_level_run4_mmx2;
if( cpu&X264_CPU_LZCNT )
pf->coeff_level_run4 = x264_coeff_level_run4_mmx2_lzcnt;
if( cpu&X264_CPU_SSE2 )
{
pf->quant_4x4 = x264_quant_4x4_sse2;
+ pf->quant_4x4x4 = x264_quant_4x4x4_sse2;
pf->quant_8x8 = x264_quant_8x8_sse2;
pf->quant_2x2_dc = x264_quant_2x2_dc_sse2;
pf->quant_4x4_dc = x264_quant_4x4_dc_sse2;
pf->decimate_score15 = x264_decimate_score15_sse2;
pf->decimate_score16 = x264_decimate_score16_sse2;
pf->decimate_score64 = x264_decimate_score64_sse2;
- if( cpu&X264_CPU_SLOW_CTZ )
- {
- pf->decimate_score15 = x264_decimate_score15_sse2_slowctz;
- pf->decimate_score16 = x264_decimate_score16_sse2_slowctz;
- }
+ pf->coeff_last8 = x264_coeff_last8_sse2;
pf->coeff_last[ DCT_LUMA_AC] = x264_coeff_last15_sse2;
pf->coeff_last[DCT_LUMA_4x4] = x264_coeff_last16_sse2;
pf->coeff_last[DCT_LUMA_8x8] = x264_coeff_last64_sse2;
+ pf->coeff_level_run8 = x264_coeff_level_run8_sse2;
pf->coeff_level_run[ DCT_LUMA_AC] = x264_coeff_level_run15_sse2;
pf->coeff_level_run[DCT_LUMA_4x4] = x264_coeff_level_run16_sse2;
if( cpu&X264_CPU_LZCNT )
{
pf->coeff_last4 = x264_coeff_last4_mmx2_lzcnt;
+ pf->coeff_last8 = x264_coeff_last8_sse2_lzcnt;
pf->coeff_last[ DCT_LUMA_AC] = x264_coeff_last15_sse2_lzcnt;
pf->coeff_last[DCT_LUMA_4x4] = x264_coeff_last16_sse2_lzcnt;
pf->coeff_last[DCT_LUMA_8x8] = x264_coeff_last64_sse2_lzcnt;
+ pf->coeff_level_run8 = x264_coeff_level_run8_sse2_lzcnt;
pf->coeff_level_run[ DCT_LUMA_AC] = x264_coeff_level_run15_sse2_lzcnt;
pf->coeff_level_run[DCT_LUMA_4x4] = x264_coeff_level_run16_sse2_lzcnt;
}
if( cpu&X264_CPU_SSSE3 )
{
pf->quant_4x4 = x264_quant_4x4_ssse3;
+ pf->quant_4x4x4 = x264_quant_4x4x4_ssse3;
pf->quant_8x8 = x264_quant_8x8_ssse3;
pf->quant_2x2_dc = x264_quant_2x2_dc_ssse3;
pf->quant_4x4_dc = x264_quant_4x4_dc_ssse3;
pf->denoise_dct = x264_denoise_dct_ssse3;
pf->decimate_score15 = x264_decimate_score15_ssse3;
pf->decimate_score16 = x264_decimate_score16_ssse3;
- if( cpu&X264_CPU_SLOW_CTZ )
- {
- pf->decimate_score15 = x264_decimate_score15_ssse3_slowctz;
- pf->decimate_score16 = x264_decimate_score16_ssse3_slowctz;
- }
pf->decimate_score64 = x264_decimate_score64_ssse3;
+ INIT_TRELLIS( ssse3 );
}
if( cpu&X264_CPU_SSE4 )
{
pf->quant_2x2_dc = x264_quant_2x2_dc_sse4;
pf->quant_4x4_dc = x264_quant_4x4_dc_sse4;
pf->quant_4x4 = x264_quant_4x4_sse4;
+ pf->quant_4x4x4 = x264_quant_4x4x4_sse4;
pf->quant_8x8 = x264_quant_8x8_sse4;
}
if( cpu&X264_CPU_AVX )
{
pf->denoise_dct = x264_denoise_dct_avx;
}
+ if( cpu&X264_CPU_XOP )
+ {
+ pf->dequant_4x4_dc = x264_dequant_4x4dc_xop;
+ if( h->param.i_cqm_preset != X264_CQM_FLAT )
+ {
+ pf->dequant_4x4 = x264_dequant_4x4_xop;
+ pf->dequant_8x8 = x264_dequant_8x8_xop;
+ }
+ }
+ if( cpu&X264_CPU_AVX2 )
+ {
+ pf->quant_4x4 = x264_quant_4x4_avx2;
+ pf->quant_4x4_dc = x264_quant_4x4_dc_avx2;
+ pf->quant_8x8 = x264_quant_8x8_avx2;
+ 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;
+ }
#endif // HAVE_MMX
#else // !HIGH_BIT_DEPTH
#if HAVE_MMX
+ INIT_TRELLIS( sse2 );
if( cpu&X264_CPU_MMX )
{
#if ARCH_X86
- pf->quant_4x4 = x264_quant_4x4_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;
{
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;
- if( cpu&X264_CPU_SLOW_CTZ )
- {
- pf->decimate_score15 = x264_decimate_score15_mmx2_slowctz;
- pf->decimate_score16 = x264_decimate_score16_mmx2_slowctz;
- }
pf->decimate_score64 = x264_decimate_score64_mmx2;
pf->coeff_last[ DCT_LUMA_AC] = x264_coeff_last15_mmx2;
pf->coeff_last[ DCT_LUMA_4x4] = x264_coeff_last16_mmx2;
pf->coeff_level_run[ DCT_LUMA_4x4] = x264_coeff_level_run16_mmx2;
#endif
pf->coeff_last4 = x264_coeff_last4_mmx2;
+ pf->coeff_last8 = x264_coeff_last8_mmx2;
pf->coeff_level_run4 = x264_coeff_level_run4_mmx2;
+ pf->coeff_level_run8 = x264_coeff_level_run8_mmx2;
if( cpu&X264_CPU_LZCNT )
{
pf->coeff_last4 = x264_coeff_last4_mmx2_lzcnt;
+ pf->coeff_last8 = x264_coeff_last8_mmx2_lzcnt;
pf->coeff_level_run4 = x264_coeff_level_run4_mmx2_lzcnt;
+ pf->coeff_level_run8 = x264_coeff_level_run8_mmx2_lzcnt;
}
}
{
pf->quant_4x4_dc = x264_quant_4x4_dc_sse2;
pf->quant_4x4 = x264_quant_4x4_sse2;
+ pf->quant_4x4x4 = x264_quant_4x4x4_sse2;
pf->quant_8x8 = x264_quant_8x8_sse2;
pf->dequant_4x4 = x264_dequant_4x4_sse2;
pf->dequant_4x4_dc = x264_dequant_4x4dc_sse2;
pf->decimate_score15 = x264_decimate_score15_sse2;
pf->decimate_score16 = x264_decimate_score16_sse2;
pf->decimate_score64 = x264_decimate_score64_sse2;
- if( cpu&X264_CPU_SLOW_CTZ )
- {
- pf->decimate_score15 = x264_decimate_score15_sse2_slowctz;
- pf->decimate_score16 = x264_decimate_score16_sse2_slowctz;
- }
pf->coeff_last[ DCT_LUMA_AC] = x264_coeff_last15_sse2;
pf->coeff_last[DCT_LUMA_4x4] = x264_coeff_last16_sse2;
pf->coeff_last[DCT_LUMA_8x8] = x264_coeff_last64_sse2;
pf->quant_2x2_dc = x264_quant_2x2_dc_ssse3;
pf->quant_4x4_dc = x264_quant_4x4_dc_ssse3;
pf->quant_4x4 = x264_quant_4x4_ssse3;
+ pf->quant_4x4x4 = x264_quant_4x4x4_ssse3;
pf->quant_8x8 = x264_quant_8x8_ssse3;
pf->optimize_chroma_2x2_dc = x264_optimize_chroma_2x2_dc_ssse3;
pf->denoise_dct = x264_denoise_dct_ssse3;
pf->decimate_score15 = x264_decimate_score15_ssse3;
pf->decimate_score16 = x264_decimate_score16_ssse3;
- if( cpu&X264_CPU_SLOW_CTZ )
+ pf->decimate_score64 = x264_decimate_score64_ssse3;
+ INIT_TRELLIS( ssse3 );
+ pf->coeff_level_run4 = x264_coeff_level_run4_ssse3;
+ pf->coeff_level_run8 = x264_coeff_level_run8_ssse3;
+ pf->coeff_level_run[ DCT_LUMA_AC] = x264_coeff_level_run15_ssse3;
+ pf->coeff_level_run[DCT_LUMA_4x4] = x264_coeff_level_run16_ssse3;
+ if( cpu&X264_CPU_LZCNT )
{
- pf->decimate_score15 = x264_decimate_score15_ssse3_slowctz;
- pf->decimate_score16 = x264_decimate_score16_ssse3_slowctz;
+ pf->coeff_level_run4 = x264_coeff_level_run4_ssse3;
+ pf->coeff_level_run8 = x264_coeff_level_run8_ssse3;
+ pf->coeff_level_run[ DCT_LUMA_AC] = x264_coeff_level_run15_ssse3_lzcnt;
+ pf->coeff_level_run[DCT_LUMA_4x4] = x264_coeff_level_run16_ssse3_lzcnt;
}
- pf->decimate_score64 = x264_decimate_score64_ssse3;
}
if( cpu&X264_CPU_SSE4 )
pf->optimize_chroma_2x2_dc = x264_optimize_chroma_2x2_dc_avx;
pf->denoise_dct = x264_denoise_dct_avx;
}
+
+ if( cpu&X264_CPU_XOP )
+ {
+ if( h->param.i_cqm_preset != X264_CQM_FLAT )
+ {
+ pf->dequant_4x4 = x264_dequant_4x4_xop;
+ pf->dequant_8x8 = x264_dequant_8x8_xop;
+ }
+ }
+
+ if( cpu&X264_CPU_AVX2 )
+ {
+ pf->quant_4x4 = x264_quant_4x4_avx2;
+ pf->quant_4x4_dc = x264_quant_4x4_dc_avx2;
+ pf->quant_8x8 = x264_quant_8x8_avx2;
+ 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;
+ if( h->param.i_cqm_preset == X264_CQM_FLAT )
+ {
+ pf->dequant_4x4 = x264_dequant_4x4_flat16_avx2;
+ pf->dequant_8x8 = x264_dequant_8x8_flat16_avx2;
+ }
+ pf->decimate_score64 = x264_decimate_score64_avx2;
+ 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;
+ }
+ }
#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;
#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;
pf->quant_4x4 = x264_quant_4x4_neon;
pf->quant_4x4_dc = x264_quant_4x4_dc_neon;
+ pf->quant_4x4x4 = x264_quant_4x4x4_neon;
pf->quant_8x8 = x264_quant_8x8_neon;
pf->dequant_4x4 = x264_dequant_4x4_neon;
pf->dequant_4x4_dc = x264_dequant_4x4_dc_neon;
pf->coeff_last[DCT_LUMA_8x8] = x264_coeff_last64_neon;
}
#endif
+#if ARCH_AARCH64
+ if( cpu&X264_CPU_ARMV8 )
+ {
+ pf->coeff_last4 = x264_coeff_last4_aarch64;
+ pf->coeff_last8 = x264_coeff_last8_aarch64;
+ }
+ if( cpu&X264_CPU_NEON )
+ {
+ pf->decimate_score15 = x264_decimate_score15_neon;
+ pf->decimate_score16 = x264_decimate_score16_neon;
+ pf->decimate_score64 = x264_decimate_score64_neon;
+ }
+#endif
#endif // HIGH_BIT_DEPTH
pf->coeff_last[DCT_LUMA_DC] = pf->coeff_last[DCT_CHROMAU_DC] = pf->coeff_last[DCT_CHROMAV_DC] =
pf->coeff_last[DCT_CHROMAU_4x4] = pf->coeff_last[DCT_CHROMAV_4x4] = pf->coeff_last[DCT_LUMA_4x4];