vpx/vp8/common/generic/systemdependent.c
Yaowu Xu ca6b85aa4e add 8x8 intra prediction modes
Patch 1 to Patch 3 is an initial implementation of 8x8 intra prediction
modes, here are with the following assumptions:
a. 8x8 has 4 prediction modes DC, H, V and TM
b. UV 4x4 block use the same mode as corresponding 8x8 area
c. i8x8 modes are enabled for key frame only for now
Patch 4:
d. removed debug code from previous patches
Patch 5:
e. added stats code to collect entropy stats and further cleaned up
Patch 6:
f. changed mode stats code to collect finer stats of modes
Patch 7:
g. normalized i8x8 modes distribution to total at 256 (8bits).
Patch 8:
h. fixed a bug in decoder and removed debug printf output.
Patch 9:
i. more cleanups to address paul's comment
Patch 10:
j. messy rebase/merges to bring the commit up to date.

Tests on HD clips encoded with all key frame showing consistent gain
on all clips and all metrics:~0.5%(psnr) and 0.6%(ssim):
http://www.corp.google.com/~yaowu/no_crawl/i8x8hd_allkey_fixedq.html

To build and test, configure with:
--enable-experimental --enable-i8x8

Change-Id: I9813fe07ae48cab5fdb5d904bca022514ad01e7f
2011-09-16 15:55:19 -07:00

167 lines
5.4 KiB
C

/*
* 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.
*/
#include "vpx_ports/config.h"
#include "vp8/common/g_common.h"
#include "vp8/common/subpixel.h"
#include "vp8/common/loopfilter.h"
#include "vp8/common/recon.h"
#include "vp8/common/idct.h"
#include "vp8/common/onyxc_int.h"
#if CONFIG_MULTITHREAD
#if HAVE_UNISTD_H
#include <unistd.h>
#elif defined(_WIN32)
#include <windows.h>
typedef void (WINAPI *PGNSI)(LPSYSTEM_INFO);
#endif
#endif
extern void vp8_arch_x86_common_init(VP8_COMMON *ctx);
extern void vp8_arch_arm_common_init(VP8_COMMON *ctx);
#if CONFIG_MULTITHREAD
static int get_cpu_count()
{
int core_count = 16;
#if HAVE_UNISTD_H
#if defined(_SC_NPROCESSORS_ONLN)
core_count = sysconf(_SC_NPROCESSORS_ONLN);
#elif defined(_SC_NPROC_ONLN)
core_count = sysconf(_SC_NPROC_ONLN);
#endif
#elif defined(_WIN32)
{
PGNSI pGNSI;
SYSTEM_INFO sysinfo;
/* Call GetNativeSystemInfo if supported or
* GetSystemInfo otherwise. */
pGNSI = (PGNSI) GetProcAddress(
GetModuleHandle(TEXT("kernel32.dll")), "GetNativeSystemInfo");
if (pGNSI != NULL)
pGNSI(&sysinfo);
else
GetSystemInfo(&sysinfo);
core_count = sysinfo.dwNumberOfProcessors;
}
#else
/* other platforms */
#endif
return core_count > 0 ? core_count : 1;
}
#endif
void vp8_machine_specific_config(VP8_COMMON *ctx)
{
#if CONFIG_RUNTIME_CPU_DETECT
VP8_COMMON_RTCD *rtcd = &ctx->rtcd;
rtcd->idct.idct1 = vp8_short_idct4x4llm_1_c;
rtcd->idct.idct16 = vp8_short_idct4x4llm_c;
rtcd->idct.idct1_scalar_add = vp8_dc_only_idct_add_c;
rtcd->idct.iwalsh1 = vp8_short_inv_walsh4x4_1_c;
rtcd->idct.iwalsh16 = vp8_short_inv_walsh4x4_c;
#if CONFIG_T8X8
rtcd->idct.idct8 = vp8_short_idct8x8_c;
rtcd->idct.idct8_1 = vp8_short_idct8x8_1_c;
rtcd->idct.idct1_scalar_add_8x8 = vp8_dc_only_idct_add_8x8_c;
rtcd->idct.ihaar2 = vp8_short_ihaar2x2_c;
rtcd->idct.ihaar2_1 = vp8_short_ihaar2x2_1_c;
#endif
rtcd->recon.copy16x16 = vp8_copy_mem16x16_c;
rtcd->recon.copy8x8 = vp8_copy_mem8x8_c;
rtcd->recon.copy8x4 = vp8_copy_mem8x4_c;
rtcd->recon.recon = vp8_recon_b_c;
#if CONFIG_I8X8
rtcd->recon.recon_uv = vp8_recon_uv_b_c;
#endif
rtcd->recon.recon2 = vp8_recon2b_c;
rtcd->recon.recon4 = vp8_recon4b_c;
rtcd->recon.recon_mb = vp8_recon_mb_c;
rtcd->recon.recon_mby = vp8_recon_mby_c;
rtcd->recon.build_intra_predictors_mby =
vp8_build_intra_predictors_mby;
rtcd->recon.build_intra_predictors_mby_s =
vp8_build_intra_predictors_mby_s;
rtcd->recon.build_intra_predictors_mbuv =
vp8_build_intra_predictors_mbuv;
rtcd->recon.build_intra_predictors_mbuv_s =
vp8_build_intra_predictors_mbuv_s;
rtcd->recon.intra4x4_predict =
vp8_intra4x4_predict;
#if CONFIG_I8X8
rtcd->recon.intra8x8_predict =
vp8_intra8x8_predict;
rtcd->recon.intra_uv4x4_predict =
vp8_intra_uv4x4_predict;
#endif
rtcd->subpix.sixtap16x16 = vp8_sixtap_predict16x16_c;
rtcd->subpix.sixtap8x8 = vp8_sixtap_predict8x8_c;
rtcd->subpix.sixtap8x4 = vp8_sixtap_predict8x4_c;
rtcd->subpix.sixtap4x4 = vp8_sixtap_predict_c;
rtcd->subpix.bilinear16x16 = vp8_bilinear_predict16x16_c;
rtcd->subpix.bilinear8x8 = vp8_bilinear_predict8x8_c;
rtcd->subpix.bilinear8x4 = vp8_bilinear_predict8x4_c;
rtcd->subpix.bilinear4x4 = vp8_bilinear_predict4x4_c;
rtcd->loopfilter.normal_mb_v = vp8_loop_filter_mbv_c;
rtcd->loopfilter.normal_b_v = vp8_loop_filter_bv_c;
rtcd->loopfilter.normal_mb_h = vp8_loop_filter_mbh_c;
rtcd->loopfilter.normal_b_h = vp8_loop_filter_bh_c;
rtcd->loopfilter.simple_mb_v = vp8_loop_filter_simple_vertical_edge_c;
rtcd->loopfilter.simple_b_v = vp8_loop_filter_bvs_c;
rtcd->loopfilter.simple_mb_h = vp8_loop_filter_simple_horizontal_edge_c;
rtcd->loopfilter.simple_b_h = vp8_loop_filter_bhs_c;
#if CONFIG_POSTPROC || (CONFIG_VP8_ENCODER && CONFIG_INTERNAL_STATS)
rtcd->postproc.down = vp8_mbpost_proc_down_c;
rtcd->postproc.across = vp8_mbpost_proc_across_ip_c;
rtcd->postproc.downacross = vp8_post_proc_down_and_across_c;
rtcd->postproc.addnoise = vp8_plane_add_noise_c;
rtcd->postproc.blend_mb_inner = vp8_blend_mb_inner_c;
rtcd->postproc.blend_mb_outer = vp8_blend_mb_outer_c;
rtcd->postproc.blend_b = vp8_blend_b_c;
#endif
#endif
#if ARCH_X86 || ARCH_X86_64
vp8_arch_x86_common_init(ctx);
#endif
#if ARCH_ARM
vp8_arch_arm_common_init(ctx);
#endif
#if CONFIG_EXTEND_QRANGE
rtcd->idct.idct1 = vp8_short_idct4x4llm_1_c;
rtcd->idct.idct16 = vp8_short_idct4x4llm_c;
rtcd->idct.idct1_scalar_add = vp8_dc_only_idct_add_c;
rtcd->idct.iwalsh1 = vp8_short_inv_walsh4x4_1_c;
rtcd->idct.iwalsh16 = vp8_short_inv_walsh4x4_c;
#endif
#if CONFIG_MULTITHREAD
ctx->processor_core_count = get_cpu_count();
#endif /* CONFIG_MULTITHREAD */
}