Skip to content
GitLab
Select Git revision
  • v1.14.0-linphone default
  • v1.12.0-linphone
  • v1.9.0-linphone
  • v1.7.0-linphone
  • feature/update_to_v1.9.0-linphone
  • feature/uwp_nuget
  • m68-3440
  • m66-3359
  • sandbox/luoyi@google.com/convolve
  • mandarinduck
  • sandbox/wangch@google.com/vp9
  • v1.6.1_linphone
  • linphone-android
  • longtailedduck
  • m56-2924
  • nextgenv2
  • m54-2840
  • sandbox/yaowu@google.com/mergeaom
  • khakicampbell
  • m52-2743
  • v1.9.0
  • v1.9.0-rc1
  • v1.8.2
  • v1.8.1
  • v1.8.0
  • v1.7.0
  • v1.6.1
  • v1.6.0
  • v1.5.0
  • v1.4.0
  • v1.3.0
  • v1.2.0
  • v1.1.0
  • v1.0.0
  • v0.9.7-p1
  • v0.9.7
  • v0.9.6
  • v0.9.5
  • v0.9.2
  • v0.9.1
Find file BlameHistoryPermalink
  • Scott LaVarnway's avatar
    Added vp8_fast_quantize_b_sse2 · d860f685
    Scott LaVarnway authored 
    Moved vp8_fast_quantize_b_sse from quantize_mmx.asm into
quantize_sse2.asm and renamed.  Updated the assembly code to
match the C version.

Change-Id: I1766d9e1ca60e173f65badc0ca0c160c2b51b200
    d860f685
x86_csystemdependent.c 12.38 KiB
1 
/*
2 
 *  Copyright (c) 2010 The WebM project authors. All Rights Reserved.
3 
 *
4 
 *  Use of this source code is governed by a BSD-style license
5 
 *  that can be found in the LICENSE file in the root of the source
6 
 *  tree. An additional intellectual property rights grant can be found
7 
 *  in the file PATENTS.  All contributing project authors may
8 
 *  be found in the AUTHORS file in the root of the source tree.
9 
 */
10
11
12 
#include "vpx_ports/config.h"
13 
#include "vpx_ports/x86.h"
14 
#include "variance.h"
15 
#include "onyx_int.h"
16
17
18 
#if HAVE_MMX
19 
void vp8_short_fdct8x4_mmx(short *input, short *output, int pitch)
20 
{
21 
    vp8_short_fdct4x4_c(input,   output,    pitch);
22 
    vp8_short_fdct4x4_c(input + 4, output + 16, pitch);
23 
}
24
25
26 
int vp8_fast_quantize_b_impl_mmx(short *coeff_ptr, short *zbin_ptr,
27 
                                 short *qcoeff_ptr, short *dequant_ptr,
28 
                                 short *scan_mask, short *round_ptr,
29 
                                 short *quant_ptr, short *dqcoeff_ptr);
30 
void vp8_fast_quantize_b_mmx(BLOCK *b, BLOCKD *d)
31 
{
32 
    short *scan_mask    = vp8_default_zig_zag_mask;//d->scan_order_mask_ptr;
33 
    short *coeff_ptr  = &b->coeff[0];
34 
    short *zbin_ptr   = &b->zbin[0][0];
35 
    short *round_ptr  = &b->round[0][0];
36 
    short *quant_ptr  = &b->quant[0][0];
37 
    short *qcoeff_ptr = d->qcoeff;
38 
    short *dqcoeff_ptr = d->dqcoeff;
39 
    short *dequant_ptr = &d->dequant[0][0];
40
41 
    d->eob = vp8_fast_quantize_b_impl_mmx(
42 
                 coeff_ptr,
43 
                 zbin_ptr,
44 
                 qcoeff_ptr,
45 
                 dequant_ptr,
46 
                 scan_mask,
47
48 
                 round_ptr,
49 
                 quant_ptr,
50 
                 dqcoeff_ptr
51 
             );
52 
}
53
54 
int vp8_mbblock_error_mmx_impl(short *coeff_ptr, short *dcoef_ptr, int dc);
55 
int vp8_mbblock_error_mmx(MACROBLOCK *mb, int dc)
56 
{
57 
    short *coeff_ptr =  mb->block[0].coeff;
58 
    short *dcoef_ptr =  mb->e_mbd.block[0].dqcoeff;
59 
    return vp8_mbblock_error_mmx_impl(coeff_ptr, dcoef_ptr, dc);
60 
}
61
62 
int vp8_mbuverror_mmx_impl(short *s_ptr, short *d_ptr);
63 
int vp8_mbuverror_mmx(MACROBLOCK *mb)
64 
{
65 
    short *s_ptr = &mb->coeff[256];
66 
    short *d_ptr = &mb->e_mbd.dqcoeff[256];
67 
    return vp8_mbuverror_mmx_impl(s_ptr, d_ptr);
68 
}
69
70 
void vp8_subtract_b_mmx_impl(unsigned char *z,  int src_stride,
7172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140
short *diff, unsigned char *predictor, int pitch); void vp8_subtract_b_mmx(BLOCK *be, BLOCKD *bd, int pitch) { unsigned char *z = *(be->base_src) + be->src; unsigned int src_stride = be->src_stride; short *diff = &be->src_diff[0]; unsigned char *predictor = &bd->predictor[0]; vp8_subtract_b_mmx_impl(z, src_stride, diff, predictor, pitch); } #endif #if HAVE_SSE2 void vp8_short_fdct8x4_sse2(short *input, short *output, int pitch) { vp8_short_fdct4x4_sse2(input, output, pitch); vp8_short_fdct4x4_sse2(input + 4, output + 16, pitch); } int vp8_fast_quantize_b_impl_sse2(short *coeff_ptr, short *qcoeff_ptr, short *dequant_ptr, short *scan_mask, short *round_ptr, short *quant_ptr, short *dqcoeff_ptr); void vp8_fast_quantize_b_sse2(BLOCK *b, BLOCKD *d) { short *scan_mask = vp8_default_zig_zag_mask;//d->scan_order_mask_ptr; short *coeff_ptr = &b->coeff[0]; short *round_ptr = &b->round[0][0]; short *quant_ptr = &b->quant[0][0]; short *qcoeff_ptr = d->qcoeff; short *dqcoeff_ptr = d->dqcoeff; short *dequant_ptr = &d->dequant[0][0]; d->eob = vp8_fast_quantize_b_impl_ssse2( coeff_ptr, qcoeff_ptr, dequant_ptr, scan_mask, round_ptr, quant_ptr, dqcoeff_ptr ); } int vp8_regular_quantize_b_impl_sse2(short *coeff_ptr, short *zbin_ptr, short *qcoeff_ptr,short *dequant_ptr, const int *default_zig_zag, short *round_ptr, short *quant_ptr, short *dqcoeff_ptr, unsigned short zbin_oq_value, short *zbin_boost_ptr); void vp8_regular_quantize_b_sse2(BLOCK *b,BLOCKD *d) { short *zbin_boost_ptr = &b->zrun_zbin_boost[0]; short *coeff_ptr = &b->coeff[0]; short *zbin_ptr = &b->zbin[0][0]; short *round_ptr = &b->round[0][0]; short *quant_ptr = &b->quant[0][0]; short *qcoeff_ptr = d->qcoeff; short *dqcoeff_ptr = d->dqcoeff; short *dequant_ptr = &d->dequant[0][0]; short zbin_oq_value = b->zbin_extra; d->eob = vp8_regular_quantize_b_impl_sse2( coeff_ptr, zbin_ptr, qcoeff_ptr,
141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210
dequant_ptr, vp8_default_zig_zag1d, round_ptr, quant_ptr, dqcoeff_ptr, zbin_oq_value, zbin_boost_ptr ); } int vp8_mbblock_error_xmm_impl(short *coeff_ptr, short *dcoef_ptr, int dc); int vp8_mbblock_error_xmm(MACROBLOCK *mb, int dc) { short *coeff_ptr = mb->block[0].coeff; short *dcoef_ptr = mb->e_mbd.block[0].dqcoeff; return vp8_mbblock_error_xmm_impl(coeff_ptr, dcoef_ptr, dc); } int vp8_mbuverror_xmm_impl(short *s_ptr, short *d_ptr); int vp8_mbuverror_xmm(MACROBLOCK *mb) { short *s_ptr = &mb->coeff[256]; short *d_ptr = &mb->e_mbd.dqcoeff[256]; return vp8_mbuverror_xmm_impl(s_ptr, d_ptr); } #endif void vp8_arch_x86_encoder_init(VP8_COMP *cpi) { #if CONFIG_RUNTIME_CPU_DETECT int flags = x86_simd_caps(); int mmx_enabled = flags & HAS_MMX; int xmm_enabled = flags & HAS_SSE; int wmt_enabled = flags & HAS_SSE2; int SSE3Enabled = flags & HAS_SSE3; int SSSE3Enabled = flags & HAS_SSSE3; /* Note: * * This platform can be built without runtime CPU detection as well. If * you modify any of the function mappings present in this file, be sure * to also update them in static mapings (<arch>/filename_<arch>.h) */ /* Override default functions with fastest ones for this CPU. */ #if HAVE_MMX if (mmx_enabled) { cpi->rtcd.variance.sad16x16 = vp8_sad16x16_mmx; cpi->rtcd.variance.sad16x8 = vp8_sad16x8_mmx; cpi->rtcd.variance.sad8x16 = vp8_sad8x16_mmx; cpi->rtcd.variance.sad8x8 = vp8_sad8x8_mmx; cpi->rtcd.variance.sad4x4 = vp8_sad4x4_mmx; cpi->rtcd.variance.var4x4 = vp8_variance4x4_mmx; cpi->rtcd.variance.var8x8 = vp8_variance8x8_mmx; cpi->rtcd.variance.var8x16 = vp8_variance8x16_mmx; cpi->rtcd.variance.var16x8 = vp8_variance16x8_mmx; cpi->rtcd.variance.var16x16 = vp8_variance16x16_mmx; cpi->rtcd.variance.subpixvar4x4 = vp8_sub_pixel_variance4x4_mmx; cpi->rtcd.variance.subpixvar8x8 = vp8_sub_pixel_variance8x8_mmx; cpi->rtcd.variance.subpixvar8x16 = vp8_sub_pixel_variance8x16_mmx; cpi->rtcd.variance.subpixvar16x8 = vp8_sub_pixel_variance16x8_mmx; cpi->rtcd.variance.subpixvar16x16 = vp8_sub_pixel_variance16x16_mmx; cpi->rtcd.variance.subpixmse16x16 = vp8_sub_pixel_mse16x16_mmx;
211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280
cpi->rtcd.variance.mse16x16 = vp8_mse16x16_mmx; cpi->rtcd.variance.getmbss = vp8_get_mb_ss_mmx; cpi->rtcd.variance.get16x16prederror = vp8_get16x16pred_error_mmx; cpi->rtcd.variance.get8x8var = vp8_get8x8var_mmx; cpi->rtcd.variance.get16x16var = vp8_get16x16var_mmx; cpi->rtcd.variance.get4x4sse_cs = vp8_get4x4sse_cs_mmx; #if 0 // new fdct cpi->rtcd.fdct.short4x4 = vp8_short_fdct4x4_mmx; cpi->rtcd.fdct.short8x4 = vp8_short_fdct8x4_mmx; cpi->rtcd.fdct.fast4x4 = vp8_short_fdct4x4_mmx; cpi->rtcd.fdct.fast8x4 = vp8_short_fdct8x4_mmx; #else cpi->rtcd.fdct.short4x4 = vp8_short_fdct4x4_c; cpi->rtcd.fdct.short8x4 = vp8_short_fdct8x4_c; cpi->rtcd.fdct.fast4x4 = vp8_short_fdct4x4_c; cpi->rtcd.fdct.fast8x4 = vp8_short_fdct8x4_c; #endif cpi->rtcd.fdct.walsh_short4x4 = vp8_short_walsh4x4_c; cpi->rtcd.encodemb.berr = vp8_block_error_mmx; cpi->rtcd.encodemb.mberr = vp8_mbblock_error_mmx; cpi->rtcd.encodemb.mbuverr = vp8_mbuverror_mmx; cpi->rtcd.encodemb.subb = vp8_subtract_b_mmx; cpi->rtcd.encodemb.submby = vp8_subtract_mby_mmx; cpi->rtcd.encodemb.submbuv = vp8_subtract_mbuv_mmx; /*cpi->rtcd.quantize.fastquantb = vp8_fast_quantize_b_mmx;*/ } #endif #if HAVE_SSE2 if (wmt_enabled) { cpi->rtcd.variance.sad16x16 = vp8_sad16x16_wmt; cpi->rtcd.variance.sad16x8 = vp8_sad16x8_wmt; cpi->rtcd.variance.sad8x16 = vp8_sad8x16_wmt; cpi->rtcd.variance.sad8x8 = vp8_sad8x8_wmt; cpi->rtcd.variance.sad4x4 = vp8_sad4x4_wmt; cpi->rtcd.variance.var4x4 = vp8_variance4x4_wmt; cpi->rtcd.variance.var8x8 = vp8_variance8x8_wmt; cpi->rtcd.variance.var8x16 = vp8_variance8x16_wmt; cpi->rtcd.variance.var16x8 = vp8_variance16x8_wmt; cpi->rtcd.variance.var16x16 = vp8_variance16x16_wmt; cpi->rtcd.variance.subpixvar4x4 = vp8_sub_pixel_variance4x4_wmt; cpi->rtcd.variance.subpixvar8x8 = vp8_sub_pixel_variance8x8_wmt; cpi->rtcd.variance.subpixvar8x16 = vp8_sub_pixel_variance8x16_wmt; cpi->rtcd.variance.subpixvar16x8 = vp8_sub_pixel_variance16x8_wmt; cpi->rtcd.variance.subpixvar16x16 = vp8_sub_pixel_variance16x16_wmt; cpi->rtcd.variance.subpixmse16x16 = vp8_sub_pixel_mse16x16_wmt; cpi->rtcd.variance.mse16x16 = vp8_mse16x16_wmt; cpi->rtcd.variance.getmbss = vp8_get_mb_ss_sse2; cpi->rtcd.variance.get16x16prederror = vp8_get16x16pred_error_sse2; cpi->rtcd.variance.get8x8var = vp8_get8x8var_sse2; cpi->rtcd.variance.get16x16var = vp8_get16x16var_sse2; /* cpi->rtcd.variance.get4x4sse_cs not implemented for wmt */; cpi->rtcd.fdct.short4x4 = vp8_short_fdct4x4_sse2; cpi->rtcd.fdct.short8x4 = vp8_short_fdct8x4_sse2; cpi->rtcd.fdct.fast4x4 = vp8_short_fdct4x4_sse2; cpi->rtcd.fdct.fast8x4 = vp8_short_fdct8x4_sse2; cpi->rtcd.fdct.walsh_short4x4 = vp8_short_walsh4x4_c ;
281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326
cpi->rtcd.encodemb.berr = vp8_block_error_xmm; cpi->rtcd.encodemb.mberr = vp8_mbblock_error_xmm; cpi->rtcd.encodemb.mbuverr = vp8_mbuverror_xmm; /* cpi->rtcd.encodemb.sub* not implemented for wmt */ /*cpi->rtcd.quantize.quantb = vp8_regular_quantize_b_sse2;*/ cpi->rtcd.quantize.fastquantb = vp8_fast_quantize_b_sse2; } #endif #if HAVE_SSE3 if (SSE3Enabled) { cpi->rtcd.variance.sad16x16 = vp8_sad16x16_sse3; cpi->rtcd.variance.sad16x16x3 = vp8_sad16x16x3_sse3; cpi->rtcd.variance.sad16x8x3 = vp8_sad16x8x3_sse3; cpi->rtcd.variance.sad8x16x3 = vp8_sad8x16x3_sse3; cpi->rtcd.variance.sad8x8x3 = vp8_sad8x8x3_sse3; cpi->rtcd.variance.sad4x4x3 = vp8_sad4x4x3_sse3; cpi->rtcd.search.full_search = vp8_full_search_sadx3; cpi->rtcd.variance.sad16x16x4d = vp8_sad16x16x4d_sse3; cpi->rtcd.variance.sad16x8x4d = vp8_sad16x8x4d_sse3; cpi->rtcd.variance.sad8x16x4d = vp8_sad8x16x4d_sse3; cpi->rtcd.variance.sad8x8x4d = vp8_sad8x8x4d_sse3; cpi->rtcd.variance.sad4x4x4d = vp8_sad4x4x4d_sse3; cpi->rtcd.search.diamond_search = vp8_diamond_search_sadx4; } #endif #if HAVE_SSSE3 if (SSSE3Enabled) { cpi->rtcd.variance.sad16x16x3 = vp8_sad16x16x3_ssse3; cpi->rtcd.variance.sad16x8x3 = vp8_sad16x8x3_ssse3; } #endif #endif }