ref: a16cd74ba15a43cb2e13284938c8b0c51bfbf3af
parent: 62400028e22b3544eac09724afe45f3cd55766a1
parent: 939f64f68efc837a98a5c80913a4bde50b79854f
author: John Koleszar <jkoleszar@google.com>
date: Thu Aug 11 09:01:45 EDT 2011
Merge remote branch 'internal/upstream-experimental' into HEAD Conflicts: vp8/decoder/detokenize.c vp8/decoder/onyxd_if.c vp8/vp8_common.mk Change-Id: Ifca1108186a8bc715da86a44021ee2fa5550b5b8
--- a/.mailmap
+++ b/.mailmap
@@ -2,3 +2,4 @@
Johann Koenig <johannkoenig@google.com>
Tero Rintaluoma <teror@google.com> <tero.rintaluoma@on2.com>
Tom Finegan <tomfinegan@google.com>
+Ralph Giles <giles@xiph.org> <giles@entropywave.com>
--- a/AUTHORS
+++ b/AUTHORS
@@ -4,8 +4,11 @@
Aaron Watry <awatry@gmail.com>
Adrian Grange <agrange@google.com>
Alex Converse <alex.converse@gmail.com>
+Alexis Ballier <aballier@gentoo.org>
+Alok Ahuja <waveletcoeff@gmail.com>
Andoni Morales Alastruey <ylatuya@gmail.com>
Andres Mejia <mcitadel@gmail.com>
+Aron Rosenberg <arosenberg@logitech.com>
Attila Nagy <attilanagy@google.com>
Fabio Pedretti <fabio.ped@libero.it>
Frank Galligan <fgalligan@google.com>
@@ -22,12 +25,15 @@
Jim Bankoski <jimbankoski@google.com>
Johann Koenig <johannkoenig@google.com>
John Koleszar <jkoleszar@google.com>
+Joshua Bleecher Snyder <josh@treelinelabs.com>
Justin Clift <justin@salasaga.org>
Justin Lebar <justin.lebar@gmail.com>
+Lou Quillio <louquillio@google.com>
Luca Barbato <lu_zero@gentoo.org>
Makoto Kato <makoto.kt@gmail.com>
Martin Ettl <ettl.martin78@googlemail.com>
Michael Kohler <michaelkohler@live.com>
+Mike Hommey <mhommey@mozilla.com>
Mikhal Shemer <mikhal@google.com>
Pascal Massimino <pascal.massimino@gmail.com>
Patrik Westin <patrik.westin@gmail.com>
@@ -34,8 +40,14 @@
Paul Wilkins <paulwilkins@google.com>
Pavol Rusnak <stick@gk2.sk>
Philip Jägenstedt <philipj@opera.com>
+Rafael Ávila de Espíndola <rafael.espindola@gmail.com>
+Ralph Giles <giles@xiph.org>
+Ronald S. Bultje <rbultje@google.com>
Scott LaVarnway <slavarnway@google.com>
+Stefan Holmer <holmer@google.com>
+Taekhyun Kim <takim@nvidia.com>
Tero Rintaluoma <teror@google.com>
+Thijs Vermeir <thijsvermeir@gmail.com>
Timothy B. Terriberry <tterribe@xiph.org>
Tom Finegan <tomfinegan@google.com>
Yaowu Xu <yaowu@google.com>
--- a/CHANGELOG
+++ b/CHANGELOG
@@ -1,3 +1,85 @@
+2011-08-02 v0.9.7 "Cayuga"
+ Our third named release, focused on a faster, higher quality, encoder.
+
+ - Upgrading:
+ This release is backwards compatible with Aylesbury (v0.9.5) and
+ Bali (v0.9.6). Users of older releases should refer to the Upgrading
+ notes in this document for that release.
+
+ - Enhancements:
+ Stereo 3D format support for vpxenc
+ Runtime detection of available processor cores.
+ Allow specifying --end-usage by enum name
+ vpxdec: test for frame corruption
+ vpxenc: add quantizer histogram display
+ vpxenc: add rate histogram display
+ Set VPX_FRAME_IS_DROPPABLE
+ update configure for ios sdk 4.3
+ Avoid text relocations in ARM vp8 decoder
+ Generate a vpx.pc file for pkg-config.
+ New ways of passing encoded data between encoder and decoder.
+
+ - Speed:
+ This release includes across-the-board speed improvements to the
+ encoder. On x86, these measure at approximately 11.5% in Best mode,
+ 21.5% in Good mode (speed 0), and 22.5% in Realtime mode (speed 6).
+ On ARM Cortex A9 with Neon extensions, real-time encoding of video
+ telephony content is 35% faster than Bali on single core and 48%
+ faster on multi-core. On the NVidia Tegra2 platform, real time
+ encoding is 40% faster than Bali.
+
+ Decoder speed was not a priority for this release, but improved
+ approximately 8.4% on x86.
+
+ Reduce motion vector search on alt-ref frame.
+ Encoder loopfilter running in its own thread
+ Reworked loopfilter to precalculate more parameters
+ SSE2/SSSE3 optimizations for build_predictors_mbuv{,_s}().
+ Make hor UV predict ~2x faster (73 vs 132 cycles) using SSSE3.
+ Removed redundant checks
+ Reduced structure sizes
+ utilize preload in ARMv6 MC/LPF/Copy routines
+ ARM optimized quantization, dfct, variance, subtract
+ Increase chrow row alignment to 16 bytes.
+ disable trellis optimization for first pass
+ Write SSSE3 sub-pixel filter function
+ Improve SSE2 half-pixel filter funtions
+ Add vp8_sub_pixel_variance16x8_ssse3 function
+ Reduce unnecessary distortion computation
+ Use diamond search to replace full search
+ Preload reference area in sub-pixel motion search (real-time mode)
+
+ - Quality:
+ This release focused primarily on one-pass use cases, including
+ video conferencing. Low latency data rate control was significantly
+ improved, improving streamability over bandwidth constrained links.
+ Added support for error concealment, allowing frames to maintain
+ visual quality in the presence of substantial packet loss.
+
+ Add rc_max_intra_bitrate_pct control
+ Limit size of initial keyframe in one-pass.
+ Improve framerate adaptation
+ Improved 1-pass CBR rate control
+ Improved KF insertion after fades to still.
+ Improved key frame detection.
+ Improved activity masking (lower PSNR impact for same SSIM boost)
+ Improved interaction between GF and ARFs
+ Adding error-concealment to the decoder.
+ Adding support for independent partitions
+ Adjusted rate-distortion constants
+
+
+ - Bug Fixes:
+ Removed firstpass motion map
+ Fix parallel make install
+ Fix multithreaded encoding for 1 MB wide frame
+ Fixed iwalsh_neon build problems with RVDS4.1
+ Fix semaphore emulation, spin-wait intrinsics on Windows
+ Fix build with xcode4 and simplify GLOBAL.
+ Mark ARM asm objects as allowing a non-executable stack.
+ Fix vpxenc encoding incorrect webm file header on big endian
+
+
2011-03-07 v0.9.6 "Bali"
Our second named release, focused on a faster, higher quality, encoder.
--- a/build/make/Makefile
+++ b/build/make/Makefile
@@ -336,6 +336,7 @@
DIST-SRCS-$(CONFIG_MSVS) += build/make/gen_msvs_proj.sh
DIST-SRCS-$(CONFIG_MSVS) += build/make/gen_msvs_sln.sh
DIST-SRCS-$(CONFIG_MSVS) += build/x86-msvs/yasm.rules
+ DIST-SRCS-$(CONFIG_MSVS) += build/x86-msvs/obj_int_extract.bat
DIST-SRCS-$(CONFIG_RVCT) += build/make/armlink_adapter.sh
# Include obj_int_extract if we use offsets from asm_*_offsets
DIST-SRCS-$(ARCH_ARM)$(ARCH_X86)$(ARCH_X86_64) += build/make/obj_int_extract.c
--- a/build/make/configure.sh
+++ b/build/make/configure.sh
@@ -952,6 +952,10 @@
# shared objects
enabled gcc && enabled pic && check_add_cflags -fPIC
+ # Work around longjmp interception on glibc >= 2.11, to improve binary
+ # compatibility. See http://code.google.com/p/webm/issues/detail?id=166
+ enabled linux && check_add_cflags -D_FORTIFY_SOURCE=0
+
# Check for strip utility variant
${STRIP} -V 2>/dev/null | grep GNU >/dev/null && enable gnu_strip
--- a/configure
+++ b/configure
@@ -40,6 +40,7 @@
${toggle_error_concealment} enable this option to get a decoder which is able to conceal losses
${toggle_runtime_cpu_detect} runtime cpu detection
${toggle_shared} shared library support
+ ${toggle_static} static library support
${toggle_small} favor smaller size over speed
${toggle_postproc_visualizer} macro block / block level visualizers
@@ -153,6 +154,7 @@
enable install_bins
enable install_libs
+enable static
enable optimizations
enable fast_unaligned #allow unaligned accesses, if supported by hw
enable md5
@@ -258,6 +260,7 @@
realtime_only
error_concealment
shared
+ static
small
postproc_visualizer
os_support
@@ -302,6 +305,7 @@
realtime_only
error_concealment
shared
+ static
small
postproc_visualizer
experimental
--- a/examples.mk
+++ b/examples.mk
@@ -167,8 +167,10 @@
# Instantiate linker template for all examples.
CODEC_LIB=$(if $(CONFIG_DEBUG_LIBS),vpx_g,vpx)
+CODEC_LIB_SUF=$(if $(CONFIG_SHARED),.so,.a)
$(foreach bin,$(BINS-yes),\
- $(if $(BUILD_OBJS),$(eval $(bin): $(LIB_PATH)/lib$(CODEC_LIB).a))\
+ $(if $(BUILD_OBJS),$(eval $(bin):\
+ $(LIB_PATH)/lib$(CODEC_LIB)$(CODEC_LIB_SUF)))\
$(if $(BUILD_OBJS),$(eval $(call linker_template,$(bin),\
$(call objs,$($(notdir $(bin)).SRCS)) \
-l$(CODEC_LIB) $(addprefix -l,$(CODEC_EXTRA_LIBS))\
--- a/libs.mk
+++ b/libs.mk
@@ -35,6 +35,7 @@
CODEC_SRCS-yes += $(addprefix $(VP8_PREFIX),$(call enabled,VP8_CX_SRCS))
CODEC_EXPORTS-yes += $(addprefix $(VP8_PREFIX),$(VP8_CX_EXPORTS))
CODEC_SRCS-yes += $(VP8_PREFIX)vp8cx.mk vpx/vp8.h vpx/vp8cx.h vpx/vp8e.h
+ CODEC_SRCS-$(ARCH_ARM) += $(VP8_PREFIX)vp8cx_arm.mk
INSTALL-LIBS-yes += include/vpx/vp8.h include/vpx/vp8e.h include/vpx/vp8cx.h
INSTALL_MAPS += include/vpx/% $(SRC_PATH_BARE)/$(VP8_PREFIX)/%
CODEC_DOC_SRCS += vpx/vp8.h vpx/vp8cx.h
@@ -47,6 +48,7 @@
CODEC_SRCS-yes += $(addprefix $(VP8_PREFIX),$(call enabled,VP8_DX_SRCS))
CODEC_EXPORTS-yes += $(addprefix $(VP8_PREFIX),$(VP8_DX_EXPORTS))
CODEC_SRCS-yes += $(VP8_PREFIX)vp8dx.mk vpx/vp8.h vpx/vp8dx.h
+ CODEC_SRCS-$(ARCH_ARM) += $(VP8_PREFIX)vp8dx_arm.mk
INSTALL-LIBS-yes += include/vpx/vp8.h include/vpx/vp8dx.h
INSTALL_MAPS += include/vpx/% $(SRC_PATH_BARE)/$(VP8_PREFIX)/%
CODEC_DOC_SRCS += vpx/vp8.h vpx/vp8dx.h
@@ -89,6 +91,7 @@
CODEC_SRCS-$(BUILD_LIBVPX) += build/make/version.sh
CODEC_SRCS-$(BUILD_LIBVPX) += vpx/vpx_integer.h
+CODEC_SRCS-$(BUILD_LIBVPX) += vpx_ports/asm_offsets.h
CODEC_SRCS-$(BUILD_LIBVPX) += vpx_ports/vpx_timer.h
CODEC_SRCS-$(BUILD_LIBVPX) += vpx_ports/mem.h
CODEC_SRCS-$(BUILD_LIBVPX) += $(BUILD_PFX)vpx_config.c
@@ -100,7 +103,7 @@
CODEC_SRCS-$(BUILD_LIBVPX) += vpx_ports/x86_cpuid.c
endif
CODEC_SRCS-$(ARCH_ARM) += vpx_ports/arm_cpudetect.c
-CODEC_SRCS-$(ARCH_ARM) += $(BUILD_PFX)vpx_config.asm
+CODEC_SRCS-$(ARCH_ARM) += vpx_ports/arm.h
CODEC_EXPORTS-$(BUILD_LIBVPX) += vpx/exports_com
CODEC_EXPORTS-$(CONFIG_ENCODERS) += vpx/exports_enc
CODEC_EXPORTS-$(CONFIG_DECODERS) += vpx/exports_dec
@@ -121,7 +124,7 @@
INSTALL-LIBS-$(CONFIG_SHARED) += $(foreach p,$(VS_PLATFORMS),$(LIBSUBDIR)/$(p)/vpx.exp)
endif
else
-INSTALL-LIBS-yes += $(LIBSUBDIR)/libvpx.a
+INSTALL-LIBS-$(CONFIG_STATIC) += $(LIBSUBDIR)/libvpx.a
INSTALL-LIBS-$(CONFIG_DEBUG_LIBS) += $(LIBSUBDIR)/libvpx_g.a
endif
@@ -177,12 +180,13 @@
else
LIBVPX_OBJS=$(call objs,$(CODEC_SRCS))
OBJS-$(BUILD_LIBVPX) += $(LIBVPX_OBJS)
-LIBS-$(BUILD_LIBVPX) += $(BUILD_PFX)libvpx.a $(BUILD_PFX)libvpx_g.a
+LIBS-$(if $(BUILD_LIBVPX),$(CONFIG_STATIC)) += $(BUILD_PFX)libvpx.a $(BUILD_PFX)libvpx_g.a
$(BUILD_PFX)libvpx_g.a: $(LIBVPX_OBJS)
BUILD_LIBVPX_SO := $(if $(BUILD_LIBVPX),$(CONFIG_SHARED))
LIBVPX_SO := libvpx.so.$(VERSION_MAJOR).$(VERSION_MINOR).$(VERSION_PATCH)
-LIBS-$(BUILD_LIBVPX_SO) += $(BUILD_PFX)$(LIBVPX_SO)
+LIBS-$(BUILD_LIBVPX_SO) += $(BUILD_PFX)$(LIBVPX_SO)\
+ $(notdir $(LIBVPX_SO_SYMLINKS))
$(BUILD_PFX)$(LIBVPX_SO): $(LIBVPX_OBJS) libvpx.ver
$(BUILD_PFX)$(LIBVPX_SO): extralibs += -lm
$(BUILD_PFX)$(LIBVPX_SO): SONAME = libvpx.so.$(VERSION_MAJOR)
@@ -198,10 +202,19 @@
$(qexec)echo "local: *; };" >> $@
CLEAN-OBJS += libvpx.ver
-$(addprefix $(DIST_DIR)/,$(LIBVPX_SO_SYMLINKS)): $(DIST_DIR)/$(LIBSUBDIR)/$(LIBVPX_SO)
- @echo " [LN] $@"
- $(qexec)ln -sf $(LIBVPX_SO) $@
+define libvpx_symlink_template
+$(1): $(2)
+ @echo " [LN] $$@"
+ $(qexec)ln -sf $(LIBVPX_SO) $$@
+endef
+$(eval $(call libvpx_symlink_template,\
+ $(addprefix $(BUILD_PFX),$(notdir $(LIBVPX_SO_SYMLINKS))),\
+ $(BUILD_PFX)$(LIBVPX_SO)))
+$(eval $(call libvpx_symlink_template,\
+ $(addprefix $(DIST_DIR)/,$(LIBVPX_SO_SYMLINKS)),\
+ $(DIST_DIR)/$(LIBSUBDIR)/$(LIBVPX_SO)))
+
INSTALL-LIBS-$(CONFIG_SHARED) += $(LIBVPX_SO_SYMLINKS)
INSTALL-LIBS-$(CONFIG_SHARED) += $(LIBSUBDIR)/$(LIBVPX_SO)
@@ -259,20 +272,20 @@
#
ifeq ($(filter icc gcc,$(TGT_CC)), $(TGT_CC))
- asm_com_offsets.asm: $(VP8_PREFIX)common/asm_com_offsets.c.S
+ $(BUILD_PFX)asm_com_offsets.asm: $(BUILD_PFX)$(VP8_PREFIX)common/asm_com_offsets.c.S
grep EQU $< | tr -d '$$\#' $(ADS2GAS) > $@
- $(VP8_PREFIX)common/asm_com_offsets.c.S: vp8/common/asm_com_offsets.c
- CLEAN-OBJS += asm_com_offsets.asm $(VP8_PREFIX)common/asm_com_offsets.c.S
+ $(BUILD_PFX)$(VP8_PREFIX)common/asm_com_offsets.c.S: $(VP8_PREFIX)common/asm_com_offsets.c
+ CLEAN-OBJS += $(BUILD_PFX)asm_com_offsets.asm $(BUILD_PFX)$(VP8_PREFIX)common/asm_com_offsets.c.S
- asm_enc_offsets.asm: $(VP8_PREFIX)encoder/asm_enc_offsets.c.S
+ $(BUILD_PFX)asm_enc_offsets.asm: $(BUILD_PFX)$(VP8_PREFIX)encoder/asm_enc_offsets.c.S
grep EQU $< | tr -d '$$\#' $(ADS2GAS) > $@
- $(VP8_PREFIX)encoder/asm_enc_offsets.c.S: vp8/encoder/asm_enc_offsets.c
- CLEAN-OBJS += asm_enc_offsets.asm $(VP8_PREFIX)encoder/asm_enc_offsets.c.S
+ $(BUILD_PFX)$(VP8_PREFIX)encoder/asm_enc_offsets.c.S: $(VP8_PREFIX)encoder/asm_enc_offsets.c
+ CLEAN-OBJS += $(BUILD_PFX)asm_enc_offsets.asm $(BUILD_PFX)$(VP8_PREFIX)encoder/asm_enc_offsets.c.S
- asm_dec_offsets.asm: $(VP8_PREFIX)decoder/asm_dec_offsets.c.S
+ $(BUILD_PFX)asm_dec_offsets.asm: $(BUILD_PFX)$(VP8_PREFIX)decoder/asm_dec_offsets.c.S
grep EQU $< | tr -d '$$\#' $(ADS2GAS) > $@
- $(VP8_PREFIX)decoder/asm_dec_offsets.c.S: vp8/decoder/asm_dec_offsets.c
- CLEAN-OBJS += asm_dec_offsets.asm $(VP8_PREFIX)decoder/asm_dec_offsets.c.S
+ $(BUILD_PFX)$(VP8_PREFIX)decoder/asm_dec_offsets.c.S: $(VP8_PREFIX)decoder/asm_dec_offsets.c
+ CLEAN-OBJS += $(BUILD_PFX)asm_dec_offsets.asm $(BUILD_PFX)$(VP8_PREFIX)decoder/asm_dec_offsets.c.S
else
ifeq ($(filter rvct,$(TGT_CC)), $(TGT_CC))
asm_com_offsets.asm: obj_int_extract
--- a/vp8/common/asm_com_offsets.c
+++ b/vp8/common/asm_com_offsets.c
@@ -9,6 +9,8 @@
*/
+#include "vpx_config.h"
+#include "vpx/vpx_codec.h"
#include "vpx_ports/asm_offsets.h"
#include "vpx_scale/yv12config.h"
@@ -25,8 +27,14 @@
DEFINE(yv12_buffer_config_u_buffer, offsetof(YV12_BUFFER_CONFIG, u_buffer));
DEFINE(yv12_buffer_config_v_buffer, offsetof(YV12_BUFFER_CONFIG, v_buffer));
DEFINE(yv12_buffer_config_border, offsetof(YV12_BUFFER_CONFIG, border));
+DEFINE(VP8BORDERINPIXELS_VAL, VP8BORDERINPIXELS);
END
/* add asserts for any offset that is not supported by assembly code */
/* add asserts for any size that is not supported by assembly code */
+
+#if HAVE_ARMV7
+/* vp8_yv12_extend_frame_borders_neon makes several assumptions based on this */
+ct_assert(VP8BORDERINPIXELS_VAL, VP8BORDERINPIXELS == 32)
+#endif
--- a/vp8/common/onyx.h
+++ b/vp8/common/onyx.h
@@ -211,8 +211,8 @@
// receive a frames worth of data caller can assume that a copy of this frame is made
// and not just a copy of the pointer..
- int vp8_receive_raw_frame(VP8_PTR comp, unsigned int frame_flags, YV12_BUFFER_CONFIG *sd, INT64 time_stamp, INT64 end_time_stamp);
- int vp8_get_compressed_data(VP8_PTR comp, unsigned int *frame_flags, unsigned long *size, unsigned char *dest, INT64 *time_stamp, INT64 *time_end, int flush);
+ int vp8_receive_raw_frame(VP8_PTR comp, unsigned int frame_flags, YV12_BUFFER_CONFIG *sd, int64_t time_stamp, int64_t end_time_stamp);
+ int vp8_get_compressed_data(VP8_PTR comp, unsigned int *frame_flags, unsigned long *size, unsigned char *dest, int64_t *time_stamp, int64_t *time_end, int flush);
int vp8_get_preview_raw_frame(VP8_PTR comp, YV12_BUFFER_CONFIG *dest, vp8_ppflags_t *flags);
int vp8_use_as_reference(VP8_PTR comp, int ref_frame_flags);
--- a/vp8/common/onyxc_int.h
+++ b/vp8/common/onyxc_int.h
@@ -19,7 +19,9 @@
#include "entropy.h"
#include "idct.h"
#include "recon.h"
+#if CONFIG_POSTPROC
#include "postproc.h"
+#endif
/*#ifdef PACKET_TESTING*/
#include "header.h"
@@ -78,7 +80,9 @@
vp8_recon_rtcd_vtable_t recon;
vp8_subpix_rtcd_vtable_t subpix;
vp8_loopfilter_rtcd_vtable_t loopfilter;
+#if CONFIG_POSTPROC
vp8_postproc_rtcd_vtable_t postproc;
+#endif
int flags;
#else
int unused;
@@ -205,7 +209,9 @@
#if CONFIG_MULTITHREAD
int processor_core_count;
#endif
+#if CONFIG_POSTPROC
struct postproc_state postproc_state;
+#endif
} VP8_COMMON;
#endif
--- a/vp8/common/onyxd.h
+++ b/vp8/common/onyxd.h
@@ -54,8 +54,8 @@
int vp8dx_get_setting(VP8D_PTR comp, VP8D_SETTING oxst);
- int vp8dx_receive_compressed_data(VP8D_PTR comp, unsigned long size, const unsigned char *dest, INT64 time_stamp);
- int vp8dx_get_raw_frame(VP8D_PTR comp, YV12_BUFFER_CONFIG *sd, INT64 *time_stamp, INT64 *time_end_stamp, vp8_ppflags_t *flags);
+ int vp8dx_receive_compressed_data(VP8D_PTR comp, unsigned long size, const unsigned char *dest, int64_t time_stamp);
+ int vp8dx_get_raw_frame(VP8D_PTR comp, YV12_BUFFER_CONFIG *sd, int64_t *time_stamp, int64_t *time_end_stamp, vp8_ppflags_t *flags);
vpx_codec_err_t vp8dx_get_reference(VP8D_PTR comp, VP8_REFFRAME ref_frame_flag, YV12_BUFFER_CONFIG *sd);
vpx_codec_err_t vp8dx_set_reference(VP8D_PTR comp, VP8_REFFRAME ref_frame_flag, YV12_BUFFER_CONFIG *sd);
--- a/vp8/decoder/arm/arm_dsystemdependent.c
+++ b/vp8/decoder/arm/arm_dsystemdependent.c
@@ -13,7 +13,6 @@
#include "vpx_ports/arm.h"
#include "vp8/common/blockd.h"
#include "vp8/common/pragmas.h"
-#include "vp8/common/postproc.h"
#include "vp8/decoder/dequantize.h"
#include "vp8/decoder/onyxd_int.h"
--- a/vp8/decoder/detokenize.c
+++ b/vp8/decoder/detokenize.c
@@ -83,7 +83,6 @@
{ 129, 130, 133, 140, 153, 177, 196, 230, 243, 254, 254, 0 };
#endif
-
void vp8_reset_mb_tokens_context(MACROBLOCKD *x)
{
/* Clear entropy contexts for Y2 blocks */
--- a/vp8/decoder/onyxd_if.c
+++ b/vp8/decoder/onyxd_if.c
@@ -244,8 +244,8 @@
/*For ARM NEON, d8-d15 are callee-saved registers, and need to be saved by us.*/
#if HAVE_ARMV7
-extern void vp8_push_neon(INT64 *store);
-extern void vp8_pop_neon(INT64 *store);
+extern void vp8_push_neon(int64_t *store);
+extern void vp8_pop_neon(int64_t *store);
#endif
static int get_free_fb (VP8_COMMON *cm)
@@ -344,10 +344,10 @@
}
*/
-int vp8dx_receive_compressed_data(VP8D_PTR ptr, unsigned long size, const unsigned char *source, INT64 time_stamp)
+int vp8dx_receive_compressed_data(VP8D_PTR ptr, unsigned long size, const unsigned char *source, int64_t time_stamp)
{
#if HAVE_ARMV7
- INT64 dx_store_reg[8];
+ int64_t dx_store_reg[8];
#endif
VP8D_COMP *pbi = (VP8D_COMP *) ptr;
VP8_COMMON *cm = &pbi->common;
@@ -554,9 +554,9 @@
#if 0
{
int i;
- INT64 earliest_time = pbi->dr[0].time_stamp;
- INT64 latest_time = pbi->dr[0].time_stamp;
- INT64 time_diff = 0;
+ int64_t earliest_time = pbi->dr[0].time_stamp;
+ int64_t latest_time = pbi->dr[0].time_stamp;
+ int64_t time_diff = 0;
int bytes = 0;
pbi->dr[pbi->common.current_video_frame&0xf].size = pbi->bc.pos + pbi->bc2.pos + 4;;
@@ -596,7 +596,7 @@
pbi->common.error.setjmp = 0;
return retcode;
}
-int vp8dx_get_raw_frame(VP8D_PTR ptr, YV12_BUFFER_CONFIG *sd, INT64 *time_stamp, INT64 *time_end_stamp, vp8_ppflags_t *flags)
+int vp8dx_get_raw_frame(VP8D_PTR ptr, YV12_BUFFER_CONFIG *sd, int64_t *time_stamp, int64_t *time_end_stamp, vp8_ppflags_t *flags)
{
int ret = -1;
VP8D_COMP *pbi = (VP8D_COMP *) ptr;
--- a/vp8/decoder/onyxd_int.h
+++ b/vp8/decoder/onyxd_int.h
@@ -40,7 +40,7 @@
typedef struct
{
- INT64 time_stamp;
+ int64_t time_stamp;
int size;
} DATARATE;
@@ -121,7 +121,7 @@
#endif
vp8_reader *mbc;
- INT64 last_time_stamp;
+ int64_t last_time_stamp;
int ready_for_new_data;
DATARATE dr[16];
--- a/vp8/encoder/encodeframe.c
+++ b/vp8/encoder/encodeframe.c
@@ -336,7 +336,7 @@
// Calculate an "average" mb activity value for the frame
#define ACT_MEDIAN 0
-static void calc_av_activity( VP8_COMP *cpi, INT64 activity_sum )
+static void calc_av_activity( VP8_COMP *cpi, int64_t activity_sum )
{
#if ACT_MEDIAN
// Find median: Simple n^2 algorithm for experimentation
@@ -404,9 +404,9 @@
VP8_COMMON *const cm = & cpi->common;
int mb_row, mb_col;
- INT64 act;
- INT64 a;
- INT64 b;
+ int64_t act;
+ int64_t a;
+ int64_t b;
#if OUTPUT_NORM_ACT_STATS
FILE *f = fopen("norm_act.stt", "a");
@@ -470,7 +470,7 @@
int mb_row, mb_col;
unsigned int mb_activity;
- INT64 activity_sum = 0;
+ int64_t activity_sum = 0;
// for each macroblock row in image
for (mb_row = 0; mb_row < cm->mb_rows; mb_row++)
@@ -537,15 +537,15 @@
x->errorperbit = x->rdmult * 100 /(110 * x->rddiv);
x->errorperbit += (x->errorperbit==0);
#else
- INT64 a;
- INT64 b;
- INT64 act = *(x->mb_activity_ptr);
+ int64_t a;
+ int64_t b;
+ int64_t act = *(x->mb_activity_ptr);
// Apply the masking to the RD multiplier.
a = act + (2*cpi->activity_avg);
b = (2*act) + cpi->activity_avg;
- x->rdmult = (unsigned int)(((INT64)x->rdmult*b + (a>>1))/a);
+ x->rdmult = (unsigned int)(((int64_t)x->rdmult*b + (a>>1))/a);
x->errorperbit = x->rdmult * 100 /(110 * x->rddiv);
x->errorperbit += (x->errorperbit==0);
#endif
@@ -1444,9 +1444,9 @@
#if USE_ACT_INDEX
x->act_zbin_adj = *(x->mb_activity_ptr);
#else
- INT64 a;
- INT64 b;
- INT64 act = *(x->mb_activity_ptr);
+ int64_t a;
+ int64_t b;
+ int64_t act = *(x->mb_activity_ptr);
// Apply the masking to the RD multiplier.
a = act + 4*cpi->activity_avg;
@@ -1453,9 +1453,9 @@
b = 4*act + cpi->activity_avg;
if ( act > cpi->activity_avg )
- x->act_zbin_adj = (int)(((INT64)b + (a>>1))/a) - 1;
+ x->act_zbin_adj = (int)(((int64_t)b + (a>>1))/a) - 1;
else
- x->act_zbin_adj = 1 - (int)(((INT64)a + (b>>1))/b);
+ x->act_zbin_adj = 1 - (int)(((int64_t)a + (b>>1))/b);
#endif
}
--- a/vp8/encoder/firstpass.c
+++ b/vp8/encoder/firstpass.c
@@ -530,8 +530,8 @@
YV12_BUFFER_CONFIG *gld_yv12 = &cm->yv12_fb[cm->gld_fb_idx];
int recon_y_stride = lst_yv12->y_stride;
int recon_uv_stride = lst_yv12->uv_stride;
- long long intra_error = 0;
- long long coded_error = 0;
+ int64_t intra_error = 0;
+ int64_t coded_error = 0;
int sum_mvr = 0, sum_mvc = 0;
int sum_mvr_abs = 0, sum_mvc_abs = 0;
@@ -620,7 +620,7 @@
this_error += intrapenalty;
// Cumulative intra error total
- intra_error += (long long)this_error;
+ intra_error += (int64_t)this_error;
// Set up limit values for motion vectors to prevent them extending outside the UMV borders
x->mv_col_min = -((mb_col * 16) + (VP8BORDERINPIXELS - 16));
@@ -757,7 +757,7 @@
}
}
- coded_error += (long long)this_error;
+ coded_error += (int64_t)this_error;
// adjust to the next column of macroblocks
x->src.y_buffer += 16;
@@ -1219,8 +1219,8 @@
cpi->twopass.total_coded_error_left = cpi->twopass.total_stats->coded_error;
cpi->twopass.start_tot_err_left = cpi->twopass.total_error_left;
- //cpi->twopass.bits_left = (long long)(cpi->twopass.total_stats->count * cpi->oxcf.target_bandwidth / DOUBLE_DIVIDE_CHECK((double)cpi->oxcf.frame_rate));
- //cpi->twopass.bits_left -= (long long)(cpi->twopass.total_stats->count * two_pass_min_rate / DOUBLE_DIVIDE_CHECK((double)cpi->oxcf.frame_rate));
+ //cpi->twopass.bits_left = (int64_t)(cpi->twopass.total_stats->count * cpi->oxcf.target_bandwidth / DOUBLE_DIVIDE_CHECK((double)cpi->oxcf.frame_rate));
+ //cpi->twopass.bits_left -= (int64_t)(cpi->twopass.total_stats->count * two_pass_min_rate / DOUBLE_DIVIDE_CHECK((double)cpi->oxcf.frame_rate));
// each frame can have a different duration, as the frame rate in the source
// isn't guaranteed to be constant. The frame rate prior to the first frame
@@ -1230,8 +1230,8 @@
vp8_new_frame_rate(cpi, 10000000.0 * cpi->twopass.total_stats->count / cpi->twopass.total_stats->duration);
cpi->output_frame_rate = cpi->oxcf.frame_rate;
- cpi->twopass.bits_left = (long long)(cpi->twopass.total_stats->duration * cpi->oxcf.target_bandwidth / 10000000.0) ;
- cpi->twopass.bits_left -= (long long)(cpi->twopass.total_stats->duration * two_pass_min_rate / 10000000.0);
+ cpi->twopass.bits_left = (int64_t)(cpi->twopass.total_stats->duration * cpi->oxcf.target_bandwidth / 10000000.0) ;
+ cpi->twopass.bits_left -= (int64_t)(cpi->twopass.total_stats->duration * two_pass_min_rate / 10000000.0);
cpi->twopass.clip_bits_total = cpi->twopass.bits_left;
// Calculate a minimum intra value to be used in determining the IIratio
@@ -2671,16 +2671,16 @@
int max_bits = frame_max_bits(cpi);
// Maximum bits for the kf group
- long long max_grp_bits;
+ int64_t max_grp_bits;
// Default allocation based on bits left and relative
// complexity of the section
- cpi->twopass.kf_group_bits = (long long)( cpi->twopass.bits_left *
+ cpi->twopass.kf_group_bits = (int64_t)( cpi->twopass.bits_left *
( kf_group_err /
cpi->twopass.modified_error_left ));
// Clip based on maximum per frame rate defined by the user.
- max_grp_bits = (long long)max_bits * (long long)cpi->twopass.frames_to_key;
+ max_grp_bits = (int64_t)max_bits * (int64_t)cpi->twopass.frames_to_key;
if (cpi->twopass.kf_group_bits > max_grp_bits)
cpi->twopass.kf_group_bits = max_grp_bits;
@@ -2697,19 +2697,19 @@
int high_water_mark = (opt_buffer_lvl +
cpi->oxcf.maximum_buffer_size) >> 1;
- long long av_group_bits;
+ int64_t av_group_bits;
// Av bits per frame * number of frames
- av_group_bits = (long long)cpi->av_per_frame_bandwidth *
- (long long)cpi->twopass.frames_to_key;
+ av_group_bits = (int64_t)cpi->av_per_frame_bandwidth *
+ (int64_t)cpi->twopass.frames_to_key;
// We are at or above the maximum.
if (cpi->buffer_level >= high_water_mark)
{
- long long min_group_bits;
+ int64_t min_group_bits;
min_group_bits = av_group_bits +
- (long long)(buffer_lvl -
+ (int64_t)(buffer_lvl -
high_water_mark);
if (cpi->twopass.kf_group_bits < min_group_bits)
@@ -2718,11 +2718,11 @@
// We are above optimal but below the maximum
else if (cpi->twopass.kf_group_bits < av_group_bits)
{
- long long bits_below_av = av_group_bits -
+ int64_t bits_below_av = av_group_bits -
cpi->twopass.kf_group_bits;
cpi->twopass.kf_group_bits +=
- (long long)((double)bits_below_av *
+ (int64_t)((double)bits_below_av *
(double)(buffer_lvl - opt_buffer_lvl) /
(double)(high_water_mark - opt_buffer_lvl));
}
@@ -3043,8 +3043,8 @@
}
else
{
- long long clip_bits = (long long)(cpi->twopass.total_stats->count * cpi->oxcf.target_bandwidth / DOUBLE_DIVIDE_CHECK((double)cpi->oxcf.frame_rate));
- long long over_spend = cpi->oxcf.starting_buffer_level - cpi->buffer_level;
+ int64_t clip_bits = (int64_t)(cpi->twopass.total_stats->count * cpi->oxcf.target_bandwidth / DOUBLE_DIVIDE_CHECK((double)cpi->oxcf.frame_rate));
+ int64_t over_spend = cpi->oxcf.starting_buffer_level - cpi->buffer_level;
if ((last_kf_resampled && (kf_q > cpi->worst_quality)) || // If triggered last time the threshold for triggering again is reduced
((kf_q > cpi->worst_quality) && // Projected Q higher than allowed and ...
--- a/vp8/encoder/mcomp.c
+++ b/vp8/encoder/mcomp.c
@@ -15,6 +15,7 @@
#include <stdio.h>
#include <limits.h>
#include <math.h>
+#include "vp8/common/findnearmv.h"
#ifdef ENTROPY_STATS
static int mv_ref_ct [31] [4] [2];
@@ -342,13 +343,27 @@
int bestmse = INT_MAX;
int_mv startmv;
int_mv this_mv;
- unsigned char *y = *(d->base_pre) + d->pre + (bestmv->as_mv.row) * d->pre_stride + bestmv->as_mv.col;
unsigned char *z = (*(b->base_src) + b->src);
int left, right, up, down, diag;
unsigned int sse;
int whichdir ;
int thismse;
+ int y_stride;
+#if ARCH_X86 || ARCH_X86_64
+ MACROBLOCKD *xd = &x->e_mbd;
+ unsigned char *y0 = *(d->base_pre) + d->pre + (bestmv->as_mv.row) * d->pre_stride + bestmv->as_mv.col;
+ unsigned char *y;
+
+ y_stride = 32;
+ /* Copy 18 rows x 32 cols area to intermediate buffer before searching. */
+ vfp->copymem(y0 - 1 - d->pre_stride, d->pre_stride, xd->y_buf, y_stride, 18);
+ y = xd->y_buf + y_stride + 1;
+#else
+ unsigned char *y = *(d->base_pre) + d->pre + (bestmv->as_mv.row) * d->pre_stride + bestmv->as_mv.col;
+ y_stride = d->pre_stride;
+#endif
+
// central mv
bestmv->as_mv.row <<= 3;
bestmv->as_mv.col <<= 3;
@@ -355,7 +370,7 @@
startmv = *bestmv;
// calculate central point error
- bestmse = vfp->vf(y, d->pre_stride, z, b->src_stride, sse1);
+ bestmse = vfp->vf(y, y_stride, z, b->src_stride, sse1);
*distortion = bestmse;
bestmse += mv_err_cost(bestmv, ref_mv, mvcost, error_per_bit);
@@ -362,7 +377,7 @@
// go left then right and check error
this_mv.as_mv.row = startmv.as_mv.row;
this_mv.as_mv.col = ((startmv.as_mv.col - 8) | 4);
- thismse = vfp->svf_halfpix_h(y - 1, d->pre_stride, z, b->src_stride, &sse);
+ thismse = vfp->svf_halfpix_h(y - 1, y_stride, z, b->src_stride, &sse);
left = thismse + mv_err_cost(&this_mv, ref_mv, mvcost, error_per_bit);
if (left < bestmse)
@@ -374,7 +389,7 @@
}
this_mv.as_mv.col += 8;
- thismse = vfp->svf_halfpix_h(y, d->pre_stride, z, b->src_stride, &sse);
+ thismse = vfp->svf_halfpix_h(y, y_stride, z, b->src_stride, &sse);
right = thismse + mv_err_cost(&this_mv, ref_mv, mvcost, error_per_bit);
if (right < bestmse)
@@ -388,7 +403,7 @@
// go up then down and check error
this_mv.as_mv.col = startmv.as_mv.col;
this_mv.as_mv.row = ((startmv.as_mv.row - 8) | 4);
- thismse = vfp->svf_halfpix_v(y - d->pre_stride, d->pre_stride, z, b->src_stride, &sse);
+ thismse = vfp->svf_halfpix_v(y - y_stride, y_stride, z, b->src_stride, &sse);
up = thismse + mv_err_cost(&this_mv, ref_mv, mvcost, error_per_bit);
if (up < bestmse)
@@ -400,7 +415,7 @@
}
this_mv.as_mv.row += 8;
- thismse = vfp->svf_halfpix_v(y, d->pre_stride, z, b->src_stride, &sse);
+ thismse = vfp->svf_halfpix_v(y, y_stride, z, b->src_stride, &sse);
down = thismse + mv_err_cost(&this_mv, ref_mv, mvcost, error_per_bit);
if (down < bestmse)
@@ -423,23 +438,23 @@
case 0:
this_mv.as_mv.col = (this_mv.as_mv.col - 8) | 4;
this_mv.as_mv.row = (this_mv.as_mv.row - 8) | 4;
- thismse = vfp->svf_halfpix_hv(y - 1 - d->pre_stride, d->pre_stride, z, b->src_stride, &sse);
+ thismse = vfp->svf_halfpix_hv(y - 1 - y_stride, y_stride, z, b->src_stride, &sse);
break;
case 1:
this_mv.as_mv.col += 4;
this_mv.as_mv.row = (this_mv.as_mv.row - 8) | 4;
- thismse = vfp->svf_halfpix_hv(y - d->pre_stride, d->pre_stride, z, b->src_stride, &sse);
+ thismse = vfp->svf_halfpix_hv(y - y_stride, y_stride, z, b->src_stride, &sse);
break;
case 2:
this_mv.as_mv.col = (this_mv.as_mv.col - 8) | 4;
this_mv.as_mv.row += 4;
- thismse = vfp->svf_halfpix_hv(y - 1, d->pre_stride, z, b->src_stride, &sse);
+ thismse = vfp->svf_halfpix_hv(y - 1, y_stride, z, b->src_stride, &sse);
break;
case 3:
default:
this_mv.as_mv.col += 4;
this_mv.as_mv.row += 4;
- thismse = vfp->svf_halfpix_hv(y, d->pre_stride, z, b->src_stride, &sse);
+ thismse = vfp->svf_halfpix_hv(y, y_stride, z, b->src_stride, &sse);
break;
}
@@ -458,7 +473,7 @@
// time to check quarter pels.
if (bestmv->as_mv.row < startmv.as_mv.row)
- y -= d->pre_stride;
+ y -= y_stride;
if (bestmv->as_mv.col < startmv.as_mv.col)
y--;
@@ -473,12 +488,12 @@
if (startmv.as_mv.col & 7)
{
this_mv.as_mv.col = startmv.as_mv.col - 2;
- thismse = vfp->svf(y, d->pre_stride, this_mv.as_mv.col & 7, this_mv.as_mv.row & 7, z, b->src_stride, &sse);
+ thismse = vfp->svf(y, y_stride, this_mv.as_mv.col & 7, this_mv.as_mv.row & 7, z, b->src_stride, &sse);
}
else
{
this_mv.as_mv.col = (startmv.as_mv.col - 8) | 6;
- thismse = vfp->svf(y - 1, d->pre_stride, 6, this_mv.as_mv.row & 7, z, b->src_stride, &sse);
+ thismse = vfp->svf(y - 1, y_stride, 6, this_mv.as_mv.row & 7, z, b->src_stride, &sse);
}
left = thismse + mv_err_cost(&this_mv, ref_mv, mvcost, error_per_bit);
@@ -492,7 +507,7 @@
}
this_mv.as_mv.col += 4;
- thismse = vfp->svf(y, d->pre_stride, this_mv.as_mv.col & 7, this_mv.as_mv.row & 7, z, b->src_stride, &sse);
+ thismse = vfp->svf(y, y_stride, this_mv.as_mv.col & 7, this_mv.as_mv.row & 7, z, b->src_stride, &sse);
right = thismse + mv_err_cost(&this_mv, ref_mv, mvcost, error_per_bit);
if (right < bestmse)
@@ -509,12 +524,12 @@
if (startmv.as_mv.row & 7)
{
this_mv.as_mv.row = startmv.as_mv.row - 2;
- thismse = vfp->svf(y, d->pre_stride, this_mv.as_mv.col & 7, this_mv.as_mv.row & 7, z, b->src_stride, &sse);
+ thismse = vfp->svf(y, y_stride, this_mv.as_mv.col & 7, this_mv.as_mv.row & 7, z, b->src_stride, &sse);
}
else
{
this_mv.as_mv.row = (startmv.as_mv.row - 8) | 6;
- thismse = vfp->svf(y - d->pre_stride, d->pre_stride, this_mv.as_mv.col & 7, 6, z, b->src_stride, &sse);
+ thismse = vfp->svf(y - y_stride, y_stride, this_mv.as_mv.col & 7, 6, z, b->src_stride, &sse);
}
up = thismse + mv_err_cost(&this_mv, ref_mv, mvcost, error_per_bit);
@@ -528,7 +543,7 @@
}
this_mv.as_mv.row += 4;
- thismse = vfp->svf(y, d->pre_stride, this_mv.as_mv.col & 7, this_mv.as_mv.row & 7, z, b->src_stride, &sse);
+ thismse = vfp->svf(y, y_stride, this_mv.as_mv.col & 7, this_mv.as_mv.row & 7, z, b->src_stride, &sse);
down = thismse + mv_err_cost(&this_mv, ref_mv, mvcost, error_per_bit);
if (down < bestmse)
@@ -558,12 +573,12 @@
if (startmv.as_mv.col & 7)
{
this_mv.as_mv.col -= 2;
- thismse = vfp->svf(y, d->pre_stride, this_mv.as_mv.col & 7, this_mv.as_mv.row & 7, z, b->src_stride, &sse);
+ thismse = vfp->svf(y, y_stride, this_mv.as_mv.col & 7, this_mv.as_mv.row & 7, z, b->src_stride, &sse);
}
else
{
this_mv.as_mv.col = (startmv.as_mv.col - 8) | 6;
- thismse = vfp->svf(y - 1, d->pre_stride, 6, this_mv.as_mv.row & 7, z, b->src_stride, &sse);;
+ thismse = vfp->svf(y - 1, y_stride, 6, this_mv.as_mv.row & 7, z, b->src_stride, &sse);;
}
}
else
@@ -573,12 +588,12 @@
if (startmv.as_mv.col & 7)
{
this_mv.as_mv.col -= 2;
- thismse = vfp->svf(y - d->pre_stride, d->pre_stride, this_mv.as_mv.col & 7, 6, z, b->src_stride, &sse);
+ thismse = vfp->svf(y - y_stride, y_stride, this_mv.as_mv.col & 7, 6, z, b->src_stride, &sse);
}
else
{
this_mv.as_mv.col = (startmv.as_mv.col - 8) | 6;
- thismse = vfp->svf(y - d->pre_stride - 1, d->pre_stride, 6, 6, z, b->src_stride, &sse);
+ thismse = vfp->svf(y - y_stride - 1, y_stride, 6, 6, z, b->src_stride, &sse);
}
}
@@ -589,12 +604,12 @@
if (startmv.as_mv.row & 7)
{
this_mv.as_mv.row -= 2;
- thismse = vfp->svf(y, d->pre_stride, this_mv.as_mv.col & 7, this_mv.as_mv.row & 7, z, b->src_stride, &sse);
+ thismse = vfp->svf(y, y_stride, this_mv.as_mv.col & 7, this_mv.as_mv.row & 7, z, b->src_stride, &sse);
}
else
{
this_mv.as_mv.row = (startmv.as_mv.row - 8) | 6;
- thismse = vfp->svf(y - d->pre_stride, d->pre_stride, this_mv.as_mv.col & 7, 6, z, b->src_stride, &sse);
+ thismse = vfp->svf(y - y_stride, y_stride, this_mv.as_mv.col & 7, 6, z, b->src_stride, &sse);
}
break;
@@ -604,12 +619,12 @@
if (startmv.as_mv.col & 7)
{
this_mv.as_mv.col -= 2;
- thismse = vfp->svf(y, d->pre_stride, this_mv.as_mv.col & 7, this_mv.as_mv.row & 7, z, b->src_stride, &sse);
+ thismse = vfp->svf(y, y_stride, this_mv.as_mv.col & 7, this_mv.as_mv.row & 7, z, b->src_stride, &sse);
}
else
{
this_mv.as_mv.col = (startmv.as_mv.col - 8) | 6;
- thismse = vfp->svf(y - 1, d->pre_stride, 6, this_mv.as_mv.row & 7, z, b->src_stride, &sse);
+ thismse = vfp->svf(y - 1, y_stride, 6, this_mv.as_mv.row & 7, z, b->src_stride, &sse);
}
break;
@@ -616,7 +631,7 @@
case 3:
this_mv.as_mv.col += 2;
this_mv.as_mv.row += 2;
- thismse = vfp->svf(y, d->pre_stride, this_mv.as_mv.col & 7, this_mv.as_mv.row & 7, z, b->src_stride, &sse);
+ thismse = vfp->svf(y, y_stride, this_mv.as_mv.col & 7, this_mv.as_mv.row & 7, z, b->src_stride, &sse);
break;
}
@@ -633,7 +648,7 @@
return bestmse;
}
-int vp8_find_best_half_pixel_step(MACROBLOCK *mb, BLOCK *b, BLOCKD *d,
+int vp8_find_best_half_pixel_step(MACROBLOCK *x, BLOCK *b, BLOCKD *d,
int_mv *bestmv, int_mv *ref_mv,
int error_per_bit,
const vp8_variance_fn_ptr_t *vfp,
@@ -643,12 +658,27 @@
int bestmse = INT_MAX;
int_mv startmv;
int_mv this_mv;
- unsigned char *y = *(d->base_pre) + d->pre + (bestmv->as_mv.row) * d->pre_stride + bestmv->as_mv.col;
unsigned char *z = (*(b->base_src) + b->src);
int left, right, up, down, diag;
unsigned int sse;
+ int whichdir ;
int thismse;
+ int y_stride;
+#if ARCH_X86 || ARCH_X86_64
+ MACROBLOCKD *xd = &x->e_mbd;
+ unsigned char *y0 = *(d->base_pre) + d->pre + (bestmv->as_mv.row) * d->pre_stride + bestmv->as_mv.col;
+ unsigned char *y;
+
+ y_stride = 32;
+ /* Copy 18 rows x 32 cols area to intermediate buffer before searching. */
+ vfp->copymem(y0 - 1 - d->pre_stride, d->pre_stride, xd->y_buf, y_stride, 18);
+ y = xd->y_buf + y_stride + 1;
+#else
+ unsigned char *y = *(d->base_pre) + d->pre + (bestmv->as_mv.row) * d->pre_stride + bestmv->as_mv.col;
+ y_stride = d->pre_stride;
+#endif
+
// central mv
bestmv->as_mv.row <<= 3;
bestmv->as_mv.col <<= 3;
@@ -655,7 +685,7 @@
startmv = *bestmv;
// calculate central point error
- bestmse = vfp->vf(y, d->pre_stride, z, b->src_stride, sse1);
+ bestmse = vfp->vf(y, y_stride, z, b->src_stride, sse1);
*distortion = bestmse;
bestmse += mv_err_cost(bestmv, ref_mv, mvcost, error_per_bit);
@@ -662,7 +692,7 @@
// go left then right and check error
this_mv.as_mv.row = startmv.as_mv.row;
this_mv.as_mv.col = ((startmv.as_mv.col - 8) | 4);
- thismse = vfp->svf_halfpix_h(y - 1, d->pre_stride, z, b->src_stride, &sse);
+ thismse = vfp->svf_halfpix_h(y - 1, y_stride, z, b->src_stride, &sse);
left = thismse + mv_err_cost(&this_mv, ref_mv, mvcost, error_per_bit);
if (left < bestmse)
@@ -674,7 +704,7 @@
}
this_mv.as_mv.col += 8;
- thismse = vfp->svf_halfpix_h(y, d->pre_stride, z, b->src_stride, &sse);
+ thismse = vfp->svf_halfpix_h(y, y_stride, z, b->src_stride, &sse);
right = thismse + mv_err_cost(&this_mv, ref_mv, mvcost, error_per_bit);
if (right < bestmse)
@@ -688,7 +718,7 @@
// go up then down and check error
this_mv.as_mv.col = startmv.as_mv.col;
this_mv.as_mv.row = ((startmv.as_mv.row - 8) | 4);
- thismse = vfp->svf_halfpix_v(y - d->pre_stride, d->pre_stride, z, b->src_stride, &sse);
+ thismse = vfp->svf_halfpix_v(y - y_stride, y_stride, z, b->src_stride, &sse);
up = thismse + mv_err_cost(&this_mv, ref_mv, mvcost, error_per_bit);
if (up < bestmse)
@@ -700,7 +730,7 @@
}
this_mv.as_mv.row += 8;
- thismse = vfp->svf_halfpix_v(y, d->pre_stride, z, b->src_stride, &sse);
+ thismse = vfp->svf_halfpix_v(y, y_stride, z, b->src_stride, &sse);
down = thismse + mv_err_cost(&this_mv, ref_mv, mvcost, error_per_bit);
if (down < bestmse)
@@ -711,8 +741,6 @@
*sse1 = sse;
}
- // somewhat strangely not doing all the diagonals for half pel is slower than doing them.
-#if 0
// now check 1 more diagonal -
whichdir = (left < right ? 0 : 1) + (up < down ? 0 : 2);
this_mv = startmv;
@@ -720,39 +748,28 @@
switch (whichdir)
{
case 0:
- this_mv.col = (this_mv.col - 8) | 4;
- this_mv.row = (this_mv.row - 8) | 4;
- diag = vfp->svf(y - 1 - d->pre_stride, d->pre_stride, 4, 4, z, b->src_stride, &sse);
+ this_mv.as_mv.col = (this_mv.as_mv.col - 8) | 4;
+ this_mv.as_mv.row = (this_mv.as_mv.row - 8) | 4;
+ thismse = vfp->svf_halfpix_hv(y - 1 - y_stride, y_stride, z, b->src_stride, &sse);
break;
case 1:
- this_mv.col += 4;
- this_mv.row = (this_mv.row - 8) | 4;
- diag = vfp->svf(y - d->pre_stride, d->pre_stride, 4, 4, z, b->src_stride, &sse);
+ this_mv.as_mv.col += 4;
+ this_mv.as_mv.row = (this_mv.as_mv.row - 8) | 4;
+ thismse = vfp->svf_halfpix_hv(y - y_stride, y_stride, z, b->src_stride, &sse);
break;
case 2:
- this_mv.col = (this_mv.col - 8) | 4;
- this_mv.row += 4;
- diag = vfp->svf(y - 1, d->pre_stride, 4, 4, z, b->src_stride, &sse);
+ this_mv.as_mv.col = (this_mv.as_mv.col - 8) | 4;
+ this_mv.as_mv.row += 4;
+ thismse = vfp->svf_halfpix_hv(y - 1, y_stride, z, b->src_stride, &sse);
break;
case 3:
- this_mv.col += 4;
- this_mv.row += 4;
- diag = vfp->svf(y, d->pre_stride, 4, 4, z, b->src_stride, &sse);
+ default:
+ this_mv.as_mv.col += 4;
+ this_mv.as_mv.row += 4;
+ thismse = vfp->svf_halfpix_hv(y, y_stride, z, b->src_stride, &sse);
break;
}
- diag += mv_err_cost(&this_mv, ref_mv, mvcost, error_per_bit);
-
- if (diag < bestmse)
- {
- *bestmv = this_mv;
- bestmse = diag;
- }
-
-#else
- this_mv.as_mv.col = (this_mv.as_mv.col - 8) | 4;
- this_mv.as_mv.row = (this_mv.as_mv.row - 8) | 4;
- thismse = vfp->svf_halfpix_hv(y - 1 - d->pre_stride, d->pre_stride, z, b->src_stride, &sse);
diag = thismse + mv_err_cost(&this_mv, ref_mv, mvcost, error_per_bit);
if (diag < bestmse)
@@ -763,44 +780,6 @@
*sse1 = sse;
}
- this_mv.as_mv.col += 8;
- thismse = vfp->svf_halfpix_hv(y - d->pre_stride, d->pre_stride, z, b->src_stride, &sse);
- diag = thismse + mv_err_cost(&this_mv, ref_mv, mvcost, error_per_bit);
-
- if (diag < bestmse)
- {
- *bestmv = this_mv;
- bestmse = diag;
- *distortion = thismse;
- *sse1 = sse;
- }
-
- this_mv.as_mv.col = (this_mv.as_mv.col - 8) | 4;
- this_mv.as_mv.row = startmv.as_mv.row + 4;
- thismse = vfp->svf_halfpix_hv(y - 1, d->pre_stride, z, b->src_stride, &sse);
- diag = thismse + mv_err_cost(&this_mv, ref_mv, mvcost, error_per_bit);
-
- if (diag < bestmse)
- {
- *bestmv = this_mv;
- bestmse = diag;
- *distortion = thismse;
- *sse1 = sse;
- }
-
- this_mv.as_mv.col += 8;
- thismse = vfp->svf_halfpix_hv(y, d->pre_stride, z, b->src_stride, &sse);
- diag = thismse + mv_err_cost(&this_mv, ref_mv, mvcost, error_per_bit);
-
- if (diag < bestmse)
- {
- *bestmv = this_mv;
- bestmse = diag;
- *distortion = thismse;
- *sse1 = sse;
- }
-
-#endif
return bestmse;
}
@@ -866,7 +845,7 @@
unsigned char *what = (*(b->base_src) + b->src);
int what_stride = b->src_stride;
int in_what_stride = d->pre_stride;
- int br = ref_mv->as_mv.row, bc = ref_mv->as_mv.col;
+ int br, bc;
int_mv this_mv;
unsigned int bestsad = 0x7fffffff;
unsigned int thissad;
@@ -880,6 +859,11 @@
fcenter_mv.as_mv.row = center_mv->as_mv.row >> 3;
fcenter_mv.as_mv.col = center_mv->as_mv.col >> 3;
+ // adjust ref_mv to make sure it is within MV range
+ vp8_clamp_mv(ref_mv, x->mv_col_min, x->mv_col_max, x->mv_row_min, x->mv_row_max);
+ br = ref_mv->as_mv.row;
+ bc = ref_mv->as_mv.col;
+
// Work out the start point for the search
base_offset = (unsigned char *)(*(d->base_pre) + d->pre);
this_offset = base_offset + (br * (d->pre_stride)) + bc;
@@ -1043,8 +1027,8 @@
int best_site = 0;
int last_site = 0;
- int ref_row = ref_mv->as_mv.row;
- int ref_col = ref_mv->as_mv.col;
+ int ref_row;
+ int ref_col;
int this_row_offset;
int this_col_offset;
search_site *ss;
@@ -1057,8 +1041,10 @@
fcenter_mv.as_mv.row = center_mv->as_mv.row >> 3;
fcenter_mv.as_mv.col = center_mv->as_mv.col >> 3;
+ vp8_clamp_mv(ref_mv, x->mv_col_min, x->mv_col_max, x->mv_row_min, x->mv_row_max);
+ ref_row = ref_mv->as_mv.row;
+ ref_col = ref_mv->as_mv.col;
*num00 = 0;
-
best_mv->as_mv.row = ref_row;
best_mv->as_mv.col = ref_col;
@@ -1162,8 +1148,8 @@
int best_site = 0;
int last_site = 0;
- int ref_row = ref_mv->as_mv.row;
- int ref_col = ref_mv->as_mv.col;
+ int ref_row;
+ int ref_col;
int this_row_offset;
int this_col_offset;
search_site *ss;
@@ -1176,6 +1162,9 @@
fcenter_mv.as_mv.row = center_mv->as_mv.row >> 3;
fcenter_mv.as_mv.col = center_mv->as_mv.col >> 3;
+ vp8_clamp_mv(ref_mv, x->mv_col_min, x->mv_col_max, x->mv_row_min, x->mv_row_max);
+ ref_row = ref_mv->as_mv.row;
+ ref_col = ref_mv->as_mv.col;
*num00 = 0;
best_mv->as_mv.row = ref_row;
best_mv->as_mv.col = ref_col;
--- a/vp8/encoder/onyx_if.c
+++ b/vp8/encoder/onyx_if.c
@@ -9,6 +9,7 @@
*/
+#include "vpx_config.h"
#include "vp8/common/onyxc_int.h"
#include "onyx_int.h"
#include "vp8/common/systemdependent.h"
@@ -24,7 +25,9 @@
#include "segmentation.h"
#include "vp8/common/g_common.h"
#include "vpx_scale/yv12extend.h"
+#if CONFIG_POSTPROC
#include "vp8/common/postproc.h"
+#endif
#include "vpx_mem/vpx_mem.h"
#include "vp8/common/swapyv12buffer.h"
#include "vp8/common/threading.h"
@@ -2729,6 +2732,8 @@
cpi->Source = &cpi->scaled_source;
#endif
}
+ else
+ cpi->Source = sd;
}
@@ -3340,7 +3345,7 @@
static void update_buffer_level(VP8_COMP *cpi)
{
- long long tmp;
+ int64_t tmp;
/* Update the buffered average bitrate.
*
@@ -3410,7 +3415,7 @@
*/
if(cpi->total_actual_bits > cpi->oxcf.starting_buffer_level)
{
- tmp = (long long)cpi->buffered_av_per_frame_bandwidth
+ tmp = (int64_t)cpi->buffered_av_per_frame_bandwidth
* cpi->oxcf.maximum_buffer_size
/ cpi->av_per_frame_bandwidth;
cpi->buffer_level = cpi->oxcf.maximum_buffer_size
@@ -3428,7 +3433,7 @@
*/
if(cpi->total_actual_bits > cpi->oxcf.starting_buffer_level)
{
- long long decayed_overshoot;
+ int64_t decayed_overshoot;
decayed_overshoot = cpi->accumulated_overshoot;
decayed_overshoot *= (cpi->oxcf.maximum_buffer_size
@@ -4796,7 +4801,7 @@
{
double two_pass_min_rate = (double)(cpi->oxcf.target_bandwidth
*cpi->oxcf.two_pass_vbrmin_section / 100);
- cpi->twopass.bits_left += (long long)(two_pass_min_rate / cpi->oxcf.frame_rate);
+ cpi->twopass.bits_left += (int64_t)(two_pass_min_rate / cpi->oxcf.frame_rate);
}
}
#endif
@@ -4803,15 +4808,15 @@
//For ARM NEON, d8-d15 are callee-saved registers, and need to be saved by us.
#if HAVE_ARMV7
-extern void vp8_push_neon(INT64 *store);
-extern void vp8_pop_neon(INT64 *store);
+extern void vp8_push_neon(int64_t *store);
+extern void vp8_pop_neon(int64_t *store);
#endif
-int vp8_receive_raw_frame(VP8_PTR ptr, unsigned int frame_flags, YV12_BUFFER_CONFIG *sd, INT64 time_stamp, INT64 end_time)
+int vp8_receive_raw_frame(VP8_PTR ptr, unsigned int frame_flags, YV12_BUFFER_CONFIG *sd, int64_t time_stamp, int64_t end_time)
{
#if HAVE_ARMV7
- INT64 store_reg[8];
+ int64_t store_reg[8];
#endif
VP8_COMP *cpi = (VP8_COMP *) ptr;
VP8_COMMON *cm = &cpi->common;
@@ -4862,10 +4867,10 @@
}
-int vp8_get_compressed_data(VP8_PTR ptr, unsigned int *frame_flags, unsigned long *size, unsigned char *dest, INT64 *time_stamp, INT64 *time_end, int flush)
+int vp8_get_compressed_data(VP8_PTR ptr, unsigned int *frame_flags, unsigned long *size, unsigned char *dest, int64_t *time_stamp, int64_t *time_end, int flush)
{
#if HAVE_ARMV7
- INT64 store_reg[8];
+ int64_t store_reg[8];
#endif
VP8_COMP *cpi = (VP8_COMP *) ptr;
VP8_COMMON *cm = &cpi->common;
@@ -4972,7 +4977,7 @@
// adjust frame rates based on timestamps given
if (!cm->refresh_alt_ref_frame)
{
- long long this_duration;
+ int64_t this_duration;
int step = 0;
if (cpi->source->ts_start == cpi->first_time_stamp_ever)
@@ -4982,7 +4987,7 @@
}
else
{
- long long last_duration;
+ int64_t last_duration;
this_duration = cpi->source->ts_end - cpi->last_end_time_stamp_seen;
last_duration = cpi->last_end_time_stamp_seen
@@ -5158,7 +5163,7 @@
int y_samples = orig->y_height * orig->y_width ;
int uv_samples = orig->uv_height * orig->uv_width ;
int t_samples = y_samples + 2 * uv_samples;
- long long sq_error;
+ int64_t sq_error;
ye = calc_plane_error(orig->y_buffer, orig->y_stride,
recon->y_buffer, recon->y_stride, orig->y_width, orig->y_height,
--- a/vp8/encoder/onyx_int.h
+++ b/vp8/encoder/onyx_int.h
@@ -321,10 +321,10 @@
CODING_CONTEXT coding_context;
// Rate targetting variables
- long long prediction_error;
- long long last_prediction_error;
- long long intra_error;
- long long last_intra_error;
+ int64_t prediction_error;
+ int64_t last_prediction_error;
+ int64_t intra_error;
+ int64_t last_intra_error;
int this_frame_target;
int projected_frame_size;
@@ -347,7 +347,7 @@
int baseline_gf_interval;
int active_arnr_frames; // <= cpi->oxcf.arnr_max_frames
- INT64 key_frame_count;
+ int64_t key_frame_count;
int prior_key_frame_distance[KEY_FRAME_CONTEXT];
int per_frame_bandwidth; // Current section per frame bandwidth target
int av_per_frame_bandwidth; // Average frame size target for clip
@@ -358,9 +358,9 @@
int inter_frame_target;
double output_frame_rate;
- long long last_time_stamp_seen;
- long long last_end_time_stamp_seen;
- long long first_time_stamp_ever;
+ int64_t last_time_stamp_seen;
+ int64_t last_end_time_stamp_seen;
+ int64_t first_time_stamp_ever;
int ni_av_qi;
int ni_tot_qi;
@@ -371,7 +371,7 @@
int zbin_mode_boost;
int zbin_mode_boost_enabled;
- INT64 total_byte_count;
+ int64_t total_byte_count;
int buffered_mode;
@@ -384,7 +384,7 @@
int long_rolling_target_bits;
int long_rolling_actual_bits;
- long long total_actual_bits;
+ int64_t total_actual_bits;
int total_target_vs_actual; // debug stats
int worst_quality;
@@ -541,8 +541,8 @@
FIRSTPASS_STATS *this_frame_stats;
FIRSTPASS_STATS *stats_in, *stats_in_end, *stats_in_start;
int first_pass_done;
- long long bits_left;
- long long clip_bits_total;
+ int64_t bits_left;
+ int64_t clip_bits_total;
double avg_iiratio;
double modified_error_total;
double modified_error_used;
@@ -562,10 +562,10 @@
int gf_group_error_left; // Remaining error from uncoded frames in a gf group. Two pass use only
// Projected total bits available for a key frame group of frames
- long long kf_group_bits;
+ int64_t kf_group_bits;
// Error score of frames still to be coded in kf group
- long long kf_group_error_left;
+ int64_t kf_group_error_left;
int gf_group_bits; // Projected Bits available for a group of frames including 1 GF or ARF
int gf_bits; // Bits for the golden frame or ARF - 2 pass only
--- a/vp8/encoder/pickinter.c
+++ b/vp8/encoder/pickinter.c
@@ -669,8 +669,6 @@
mvp_full.as_mv.col = mvp.as_mv.col>>3;
mvp_full.as_mv.row = mvp.as_mv.row>>3;
- /* adjust mvp to make sure it is within MV range */
- vp8_clamp_mv(&mvp_full, col_min, col_max, row_min, row_max);
}else
{
mvp.as_int = best_ref_mv.as_int;
--- a/vp8/encoder/picklpf.c
+++ b/vp8/encoder/picklpf.c
@@ -161,7 +161,7 @@
if (cm->sharpness_level != cm->last_sharpness_level)
{
vp8_loop_filter_update_sharpness(&cm->lf_info, cm->sharpness_level);
- cm->last_sharpness_level = cm->last_sharpness_level;
+ cm->last_sharpness_level = cm->sharpness_level;
}
// Start the search at the previous frame filter level unless it is now out of range.
--- a/vp8/encoder/ratectrl.c
+++ b/vp8/encoder/ratectrl.c
@@ -897,9 +897,9 @@
if ( critical_buffer_level >
(cpi->oxcf.optimal_buffer_level >> 2) )
{
- INT64 qadjustment_range =
+ int64_t qadjustment_range =
cpi->worst_quality - cpi->ni_av_qi;
- INT64 above_base =
+ int64_t above_base =
(critical_buffer_level -
(cpi->oxcf.optimal_buffer_level >> 2));
@@ -1163,7 +1163,7 @@
if (cpi->pass==0
&& cpi->common.refresh_golden_frame
&& cpi->oxcf.end_usage == USAGE_STREAM_FROM_SERVER) {
- long long adjust;
+ int64_t adjust;
/*
frames_in_buffer = cpi->oxcf.maximum_buffer_size
--- a/vp8/encoder/rdopt.c
+++ b/vp8/encoder/rdopt.c
@@ -728,7 +728,7 @@
int cost = mb->mbmode_cost [xd->frame_type] [B_PRED];
int distortion = 0;
int tot_rate_y = 0;
- long long total_rd = 0;
+ int64_t total_rd = 0;
ENTROPY_CONTEXT_PLANES t_above, t_left;
ENTROPY_CONTEXT *ta;
ENTROPY_CONTEXT *tl;
@@ -770,11 +770,11 @@
mic->bmi[i].as_mode = best_mode;
- if(total_rd >= (long long)best_rd)
+ if(total_rd >= (int64_t)best_rd)
break;
}
- if(total_rd >= (long long)best_rd)
+ if(total_rd >= (int64_t)best_rd)
return INT_MAX;
*Rate = cost;
@@ -1244,6 +1244,9 @@
// Should we do a full search (best quality only)
if ((cpi->compressor_speed == 0) && (bestsme >> sseshift) > 4000)
{
+ /* Check if mvp_full is within the range. */
+ vp8_clamp_mv(&mvp_full, x->mv_col_min, x->mv_col_max, x->mv_row_min, x->mv_row_max);
+
thissme = cpi->full_search_sad(x, c, e, &mvp_full,
sadpb, 16, v_fn_ptr,
x->mvcost, bsi->ref_mv);
@@ -2078,9 +2081,6 @@
mvp_full.as_mv.col = mvp.as_mv.col>>3;
mvp_full.as_mv.row = mvp.as_mv.row>>3;
-
- /* adjust mvp to make sure it is within MV range */
- vp8_clamp_mv(&mvp_full, col_min, col_max, row_min, row_max);
// Get intersection of UMV window and valid MV window to reduce # of checks in diamond search.
if (x->mv_col_min < col_min )
--- a/vp8/encoder/ssim.c
+++ b/vp8/encoder/ssim.c
@@ -73,8 +73,8 @@
}
}
-const static long long cc1 = 26634; // (64^2*(.01*255)^2
-const static long long cc2 = 239708; // (64^2*(.03*255)^2
+const static int64_t cc1 = 26634; // (64^2*(.01*255)^2
+const static int64_t cc2 = 239708; // (64^2*(.03*255)^2
static double similarity
(
@@ -86,19 +86,19 @@
int count
)
{
- long long ssim_n, ssim_d;
- long long c1, c2;
+ int64_t ssim_n, ssim_d;
+ int64_t c1, c2;
//scale the constants by number of pixels
c1 = (cc1*count*count)>>12;
c2 = (cc2*count*count)>>12;
- ssim_n = (2*sum_s*sum_r+ c1)*((long long) 2*count*sum_sxr-
- (long long) 2*sum_s*sum_r+c2);
+ ssim_n = (2*sum_s*sum_r+ c1)*((int64_t) 2*count*sum_sxr-
+ (int64_t) 2*sum_s*sum_r+c2);
ssim_d = (sum_s*sum_s +sum_r*sum_r+c1)*
- ((long long)count*sum_sq_s-(long long)sum_s*sum_s +
- (long long)count*sum_sq_r-(long long) sum_r*sum_r +c2) ;
+ ((int64_t)count*sum_sq_s-(int64_t)sum_s*sum_s +
+ (int64_t)count*sum_sq_r-(int64_t) sum_r*sum_r +c2) ;
return ssim_n * 1.0 / ssim_d;
}
@@ -124,11 +124,11 @@
const vp8_variance_rtcd_vtable_t *rtcd)
{
unsigned long sum_s=0,sum_r=0,sum_sq_s=0,sum_sq_r=0,sum_sxr=0;
- long long ssim3;
- long long ssim_n1,ssim_n2;
- long long ssim_d1,ssim_d2;
- long long ssim_t1,ssim_t2;
- long long c1, c2;
+ int64_t ssim3;
+ int64_t ssim_n1,ssim_n2;
+ int64_t ssim_d1,ssim_d2;
+ int64_t ssim_t1,ssim_t2;
+ int64_t c1, c2;
// normalize by 256/64
c1 = cc1*16;
@@ -137,12 +137,12 @@
rtcd->ssimpf(s, sp, r, rp, &sum_s, &sum_r, &sum_sq_s, &sum_sq_r, &sum_sxr);
ssim_n1 = (2*sum_s*sum_r+ c1);
- ssim_n2 =((long long) 2*256*sum_sxr-(long long) 2*sum_s*sum_r+c2);
+ ssim_n2 =((int64_t) 2*256*sum_sxr-(int64_t) 2*sum_s*sum_r+c2);
- ssim_d1 =((long long)sum_s*sum_s +(long long)sum_r*sum_r+c1);
+ ssim_d1 =((int64_t)sum_s*sum_s +(int64_t)sum_r*sum_r+c1);
- ssim_d2 = (256 * (long long) sum_sq_s-(long long) sum_s*sum_s +
- (long long) 256*sum_sq_r-(long long) sum_r*sum_r +c2) ;
+ ssim_d2 = (256 * (int64_t) sum_sq_s-(int64_t) sum_s*sum_s +
+ (int64_t) 256*sum_sq_r-(int64_t) sum_r*sum_r +c2) ;
ssim_t1 = 256 - 256 * ssim_n1 / ssim_d1;
ssim_t2 = 256 - 256 * ssim_n2 / ssim_d2;
--- a/vp8/encoder/temporal_filter.c
+++ b/vp8/encoder/temporal_filter.c
@@ -24,7 +24,6 @@
#include "segmentation.h"
#include "vp8/common/g_common.h"
#include "vpx_scale/yv12extend.h"
-#include "vp8/common/postproc.h"
#include "vpx_mem/vpx_mem.h"
#include "vp8/common/swapyv12buffer.h"
#include "vp8/common/threading.h"
--- a/vp8/vp8_common.mk
+++ b/vp8/vp8_common.mk
@@ -15,6 +15,7 @@
VP8_COMMON_SRCS-yes += common/onyx.h
VP8_COMMON_SRCS-yes += common/onyxd.h
VP8_COMMON_SRCS-yes += common/alloccommon.c
+VP8_COMMON_SRCS-yes += common/asm_com_offsets.c
VP8_COMMON_SRCS-yes += common/blockd.c
VP8_COMMON_SRCS-yes += common/coefupdateprobs.h
VP8_COMMON_SRCS-yes += common/debugmodes.c
@@ -101,7 +102,6 @@
endif
# common (c)
-VP8_COMMON_SRCS-$(ARCH_ARM) += common/asm_com_offsets.c
ifeq ($(CONFIG_CSM),yes)
VP8_COMMON_SRCS-yes += common/maskingmv.c
VP8_COMMON_SRCS-$(HAVE_SSE3) += common/x86/mask_sse3.asm
@@ -108,12 +108,15 @@
endif
VP8_COMMON_SRCS-$(ARCH_ARM) += common/arm/arm_systemdependent.c
-
VP8_COMMON_SRCS-$(ARCH_ARM) += common/arm/bilinearfilter_arm.c
VP8_COMMON_SRCS-$(ARCH_ARM) += common/arm/bilinearfilter_arm.h
VP8_COMMON_SRCS-$(ARCH_ARM) += common/arm/filter_arm.c
+VP8_COMMON_SRCS-$(ARCH_ARM) += common/arm/idct_arm.h
VP8_COMMON_SRCS-$(ARCH_ARM) += common/arm/loopfilter_arm.c
+VP8_COMMON_SRCS-$(ARCH_ARM) += common/arm/loopfilter_arm.h
+VP8_COMMON_SRCS-$(ARCH_ARM) += common/arm/recon_arm.h
VP8_COMMON_SRCS-$(ARCH_ARM) += common/arm/reconintra_arm.c
+VP8_COMMON_SRCS-$(ARCH_ARM) += common/arm/subpixel_arm.h
# common (armv6)
VP8_COMMON_SRCS-$(HAVE_ARMV6) += common/arm/armv6/bilinearfilter_v6$(ASM)
--- a/vp8/vp8_cx_iface.c
+++ b/vp8/vp8_cx_iface.c
@@ -40,6 +40,7 @@
unsigned int experimental;
vp8e_tuning tuning;
unsigned int cq_level; /* constrained quality level */
+ unsigned int rc_max_intra_bitrate_pct;
};
@@ -73,6 +74,7 @@
0, /* experimental mode */
0, /* tuning*/
10, /* cq_level */
+ 0, /* rc_max_intra_bitrate_pct */
}
}
};
@@ -308,7 +310,7 @@
}
oxcf->target_bandwidth = cfg.rc_target_bitrate;
- oxcf->rc_max_intra_bitrate_pct = cfg.rc_max_intra_bitrate_pct;
+ oxcf->rc_max_intra_bitrate_pct = vp8_cfg.rc_max_intra_bitrate_pct;
oxcf->best_allowed_q = cfg.rc_min_quantizer;
oxcf->worst_allowed_q = cfg.rc_max_quantizer;
@@ -465,6 +467,7 @@
MAP(VP8E_SET_ARNR_TYPE , xcfg.arnr_type);
MAP(VP8E_SET_TUNING, xcfg.tuning);
MAP(VP8E_SET_CQ_LEVEL, xcfg.cq_level);
+ MAP(VP8E_SET_MAX_INTRA_BITRATE_PCT, xcfg.rc_max_intra_bitrate_pct);
}
@@ -745,7 +748,7 @@
{
unsigned int lib_flags;
YV12_BUFFER_CONFIG sd;
- INT64 dst_time_stamp, dst_end_time_stamp;
+ int64_t dst_time_stamp, dst_end_time_stamp;
unsigned long size, cx_data_sz;
unsigned char *cx_data;
@@ -1107,6 +1110,7 @@
{VP8E_SET_ARNR_TYPE , set_param},
{VP8E_SET_TUNING, set_param},
{VP8E_SET_CQ_LEVEL, set_param},
+ {VP8E_SET_MAX_INTRA_BITRATE_PCT, set_param},
{ -1, NULL},
};
@@ -1139,7 +1143,6 @@
{0}, /* rc_twopass_stats_in */
#endif
256, /* rc_target_bandwidth */
- 0, /* rc_max_intra_bitrate_pct */
4, /* rc_min_quantizer */
63, /* rc_max_quantizer */
100, /* rc_undershoot_pct */
--- a/vp8/vp8_dx_iface.c
+++ b/vp8/vp8_dx_iface.c
@@ -427,7 +427,7 @@
if (!res && ctx->pbi)
{
YV12_BUFFER_CONFIG sd;
- INT64 time_stamp = 0, time_end_stamp = 0;
+ int64_t time_stamp = 0, time_end_stamp = 0;
vp8_ppflags_t flags = {0};
if (ctx->base.init_flags & VPX_CODEC_USE_POSTPROC)
--- a/vp8/vp8cx_arm.mk
+++ b/vp8/vp8cx_arm.mk
@@ -15,9 +15,12 @@
# encoder
VP8_CX_SRCS-$(ARCH_ARM) += encoder/arm/arm_csystemdependent.c
-VP8_CX_SRCS-$(ARCH_ARM) += encoder/arm/quantize_arm.c
-VP8_CX_SRCS-$(ARCH_ARM) += encoder/arm/picklpf_arm.c
VP8_CX_SRCS-$(ARCH_ARM) += encoder/arm/dct_arm.c
+VP8_CX_SRCS-$(ARCH_ARM) += encoder/arm/dct_arm.h
+VP8_CX_SRCS-$(ARCH_ARM) += encoder/arm/encodemb_arm.h
+VP8_CX_SRCS-$(ARCH_ARM) += encoder/arm/picklpf_arm.c
+VP8_CX_SRCS-$(ARCH_ARM) += encoder/arm/quantize_arm.c
+VP8_CX_SRCS-$(ARCH_ARM) += encoder/arm/quantize_arm.h
VP8_CX_SRCS-$(ARCH_ARM) += encoder/arm/variance_arm.c
VP8_CX_SRCS-$(ARCH_ARM) += encoder/arm/variance_arm.h
--- a/vp8/vp8dx.mk
+++ b/vp8/vp8dx.mk
@@ -48,6 +48,7 @@
#INCLUDES += common
#INCLUDES += decoder
+VP8_DX_SRCS-yes += decoder/asm_dec_offsets.c
VP8_DX_SRCS-yes += decoder/dboolhuff.c
VP8_DX_SRCS-yes += decoder/decodemv.c
VP8_DX_SRCS-yes += decoder/decodframe.c
--- a/vp8/vp8dx_arm.mk
+++ b/vp8/vp8dx_arm.mk
@@ -12,9 +12,8 @@
#VP8_DX_SRCS list is modified according to different platforms.
VP8_DX_SRCS-$(ARCH_ARM) += decoder/arm/arm_dsystemdependent.c
-VP8_CX_SRCS-$(ARCH_ARM) += decoder/asm_dec_offsets.c
-
VP8_DX_SRCS-$(ARCH_ARM) += decoder/arm/dequantize_arm.c
+VP8_DX_SRCS-$(ARCH_ARM) += decoder/arm/dequantize_arm.h
#File list for armv6
VP8_DX_SRCS-$(HAVE_ARMV6) += decoder/arm/armv6/dequant_dc_idct_v6$(ASM)
--- a/vpx/vp8cx.h
+++ b/vpx/vp8cx.h
@@ -174,6 +174,20 @@
* \note Valid range: 0..63
*/
VP8E_SET_CQ_LEVEL,
+
+ /*!\brief Max data rate for Intra frames
+ *
+ * This value controls additional clamping on the maximum size of a
+ * keyframe. It is expressed as a percentage of the average
+ * per-frame bitrate, with the special (and default) value 0 meaning
+ * unlimited, or no additional clamping beyond the codec's built-in
+ * algorithm.
+ *
+ * For example, to allocate no more than 4.5 frames worth of bitrate
+ * to a keyframe, set this to 450.
+ *
+ */
+ VP8E_SET_MAX_INTRA_BITRATE_PCT,
};
/*!\brief vpx 1-D scaling mode
@@ -304,6 +318,9 @@
VPX_CTRL_USE_TYPE(VP8E_GET_LAST_QUANTIZER, int *)
VPX_CTRL_USE_TYPE(VP8E_GET_LAST_QUANTIZER_64, int *)
+
+VPX_CTRL_USE_TYPE(VP8E_SET_MAX_INTRA_BITRATE_PCT, unsigned int)
+
/*! @} - end defgroup vp8_encoder */
#include "vpx_codec_impl_bottom.h"
--- a/vpx/vpx_encoder.h
+++ b/vpx/vpx_encoder.h
@@ -433,21 +433,6 @@
unsigned int rc_target_bitrate;
- /*!\brief Max data rate for Intra frames
- *
- * This value controls additional clamping on the maximum size of a
- * keyframe. It is expressed as a percentage of the average
- * per-frame bitrate, with the special (and default) value 0 meaning
- * unlimited, or no additional clamping beyond the codec's built-in
- * algorithm.
- *
- * For example, to allocate no more than 4.5 frames worth of bitrate
- * to a keyframe, set this to 450.
- *
- */
- unsigned int rc_max_intra_bitrate_pct;
-
-
/*
* quantizer settings
*/
--- a/vpx_scale/arm/neon/vp8_vpxyv12_extendframeborders_neon.asm
+++ b/vpx_scale/arm/neon/vp8_vpxyv12_extendframeborders_neon.asm
@@ -18,42 +18,32 @@
AREA ||.text||, CODE, READONLY, ALIGN=2
;void vp8_yv12_extend_frame_borders_neon (YV12_BUFFER_CONFIG *ybf);
-;Note: this is VP8 function, which has border=32 and 16. Internal y_width and y_height
-; are always multiples of 16.
+; we depend on VP8BORDERINPIXELS being 32
|vp8_yv12_extend_frame_borders_neon| PROC
push {r4 - r10, lr}
vpush {d8 - d15}
- ;Not need to load y_width, since: y_width = y_stride - 2*border
- ldr r3, [r0, #yv12_buffer_config_border]
- ldr r1, [r0, #yv12_buffer_config_y_buffer] ;srcptr1
- ldr r4, [r0, #yv12_buffer_config_y_height]
- ldr lr, [r0, #yv12_buffer_config_y_stride]
+ ; Border = 32
+ ldr r3, [r0, #yv12_buffer_config_y_width] ; plane_width
+ ldr r1, [r0, #yv12_buffer_config_y_buffer] ; src_ptr1
+ ldr r4, [r0, #yv12_buffer_config_y_height] ; plane_height
+ ldr lr, [r0, #yv12_buffer_config_y_stride] ; plane_stride
- cmp r3, #16
- beq b16_extend_frame_borders
+; Border copy for Y plane
+; copy the left and right most columns out
+ add r6, r1, r3 ; dest_ptr2 = src_ptr2 + 1 (src_ptr1 + plane_width)
+ sub r2, r6, #1 ; src_ptr2 = src_ptr1 + plane_width - 1
+ sub r5, r1, #32 ; dest_ptr1 = src_ptr1 - Border
-;=======================
-b32_extend_frame_borders
-;border = 32
-;=======================
-;Border copy for Y plane
-;copy the left and right most columns out
- sub r5, r1, r3 ;destptr1
- add r6, r1, lr
- sub r6, r6, r3, lsl #1 ;destptr2
- sub r2, r6, #1 ;srcptr2
+ mov r12, r4, lsr #2 ; plane_height / 4
- ;Do four rows at one time
- mov r12, r4, lsr #2
-
copy_left_right_y
vld1.8 {d0[], d1[]}, [r1], lr
vld1.8 {d4[], d5[]}, [r2], lr
vld1.8 {d8[], d9[]}, [r1], lr
vld1.8 {d12[], d13[]}, [r2], lr
- vld1.8 {d16[], d17[]}, [r1], lr
+ vld1.8 {d16[], d17[]}, [r1], lr
vld1.8 {d20[], d21[]}, [r2], lr
vld1.8 {d24[], d25[]}, [r1], lr
vld1.8 {d28[], d29[]}, [r2], lr
@@ -81,15 +71,16 @@
bne copy_left_right_y
;Now copy the top and bottom source lines into each line of the respective borders
- ldr r7, [r0, #yv12_buffer_config_y_buffer] ;srcptr1
- mul r8, r3, lr
+ ldr r1, [r0, #yv12_buffer_config_y_buffer] ; y_buffer
+ mul r8, r4, lr ; plane_height * plane_stride
- mov r12, lr, lsr #7
+ ; copy width is plane_stride
+ mov r12, lr, lsr #7 ; plane_stride / 128
- sub r6, r1, r3 ;destptr2
- sub r2, r6, lr ;srcptr2
- sub r1, r7, r3 ;srcptr1
- sub r5, r1, r8 ;destptr1
+ sub r1, r1, #32 ; src_ptr1 = y_buffer - Border
+ add r6, r1, r8 ; dest_ptr2 = src_ptr2 - plane_stride (src_ptr1 + (plane_height * plane_stride))
+ sub r2, r6, lr ; src_ptr2 = src_ptr1 + (plane_height * plane_stride) - plane_stride
+ sub r5, r1, lr, asl #5 ; dest_ptr1 = src_ptr1 - (Border * plane_stride)
copy_top_bottom_y
vld1.8 {q0, q1}, [r1]!
@@ -101,7 +92,7 @@
vld1.8 {q6, q7}, [r1]!
vld1.8 {q14, q15}, [r2]!
- mov r7, r3
+ mov r7, #32 ; Border
top_bottom_32
subs r7, r7, #1
@@ -115,45 +106,42 @@
vst1.8 {q6, q7}, [r5]!
vst1.8 {q14, q15}, [r6]!
- add r5, r5, lr
- sub r5, r5, #128
- add r6, r6, lr
- sub r6, r6, #128
+ add r5, r5, lr ; dest_ptr1 += plane_stride
+ sub r5, r5, #128 ; dest_ptr1 -= 128
+ add r6, r6, lr ; dest_ptr2 += plane_stride
+ sub r6, r6, #128 ; dest_ptr2 -= 128
bne top_bottom_32
- sub r5, r1, r8
- add r6, r2, lr
+ sub r5, r1, lr, asl #5 ; src_ptr1 - (Border* plane_stride)
+ add r6, r2, lr ; src_ptr2 + plane_stride
subs r12, r12, #1
bne copy_top_bottom_y
- mov r7, lr, lsr #4 ;check to see if extra copy is needed
+ mov r7, lr, lsr #4 ; check to see if extra copy is needed
ands r7, r7, #0x7
bne extra_top_bottom_y
end_of_border_copy_y
;Border copy for U, V planes
- ldr r1, [r0, #yv12_buffer_config_u_buffer] ;srcptr1
- mov lr, lr, lsr #1 ;uv_stride
- mov r3, r3, lsr #1 ;border
- mov r4, r4, lsr #1 ;uv_height
- mov r8, r8, lsr #2
+; Border = 16
+ ldr r7, [r0, #yv12_buffer_config_u_buffer] ; src_ptr1
+ ldr lr, [r0, #yv12_buffer_config_uv_stride] ; plane_stride
+ ldr r3, [r0, #yv12_buffer_config_uv_width] ; plane_width
+ ldr r4, [r0, #yv12_buffer_config_uv_height] ; plane_height
mov r10, #2
;copy the left and right most columns out
border_copy_uv
- sub r5, r1, r3 ;destptr1
- add r6, r1, lr
- sub r6, r6, r3, lsl #1 ;destptr2
- sub r2, r6, #1 ;srcptr2
+ mov r1, r7 ; src_ptr1 needs to be saved for second half of loop
+ sub r5, r1, #16 ; dest_ptr1 = src_ptr1 - Border
+ add r6, r1, r3 ; dest_ptr2 = src_ptr2 + 1 (src_ptr1 + plane_width)
+ sub r2, r6, #1 ; src_ptr2 = src_ptr1 + plane_width - 1
- mov r7, r1
+ mov r12, r4, lsr #3 ; plane_height / 8
- ;Do eight rows at one time
- mov r12, r4, lsr #3
-
copy_left_right_uv
vld1.8 {d0[], d1[]}, [r1], lr
vld1.8 {d2[], d3[]}, [r2], lr
@@ -167,7 +155,7 @@
vld1.8 {d18[], d19[]}, [r2], lr
vld1.8 {d20[], d21[]}, [r1], lr
vld1.8 {d22[], d23[]}, [r2], lr
- vld1.8 {d24[], d25[]}, [r1], lr
+ vld1.8 {d24[], d25[]}, [r1], lr
vld1.8 {d26[], d27[]}, [r2], lr
vld1.8 {d28[], d29[]}, [r1], lr
vld1.8 {d30[], d31[]}, [r2], lr
@@ -194,12 +182,14 @@
bne copy_left_right_uv
;Now copy the top and bottom source lines into each line of the respective borders
- mov r12, lr, lsr #6
+ mov r1, r7
+ mul r8, r4, lr ; plane_height * plane_stride
+ mov r12, lr, lsr #6 ; plane_stride / 64
- sub r6, r1, r3 ;destptr2
- sub r2, r6, lr ;srcptr2
- sub r1, r7, r3 ;srcptr1
- sub r5, r1, r8 ;destptr1
+ sub r1, r1, #16 ; src_ptr1 = u_buffer - Border
+ add r6, r1, r8 ; dest_ptr2 = src_ptr2 + plane_stride (src_ptr1 + (plane_height * plane_stride)
+ sub r2, r6, lr ; src_ptr2 = src_ptr1 + (plane_height * plane_stride) - plane_stride
+ sub r5, r1, lr, asl #4 ; dest_ptr1 = src_ptr1 - (Border * plane_stride)
copy_top_bottom_uv
vld1.8 {q0, q1}, [r1]!
@@ -207,7 +197,7 @@
vld1.8 {q2, q3}, [r1]!
vld1.8 {q10, q11}, [r2]!
- mov r7, r3
+ mov r7, #16 ; Border
top_bottom_16
subs r7, r7, #1
@@ -217,26 +207,26 @@
vst1.8 {q2, q3}, [r5]!
vst1.8 {q10, q11}, [r6]!
- add r5, r5, lr
+ add r5, r5, lr ; dest_ptr1 += plane_stride
sub r5, r5, #64
- add r6, r6, lr
+ add r6, r6, lr ; dest_ptr2 += plane_stride
sub r6, r6, #64
bne top_bottom_16
- sub r5, r1, r8
- add r6, r2, lr
+ sub r5, r1, lr, asl #4 ; dest_ptr1 = src_ptr1 - (Border * plane_stride)
+ add r6, r2, lr ; dest_ptr2 = src_ptr2 + plane_stride
subs r12, r12, #1
bne copy_top_bottom_uv
- mov r7, lr, lsr #3 ;check to see if extra copy is needed
+ mov r7, lr, lsr #3 ; check to see if extra copy is needed
ands r7, r7, #0x7
bne extra_top_bottom_uv
end_of_border_copy_uv
subs r10, r10, #1
- ldrne r1, [r0, #yv12_buffer_config_v_buffer] ;srcptr1
+ ldrne r7, [r0, #yv12_buffer_config_v_buffer] ; src_ptr1
bne border_copy_uv
vpop {d8 - d15}
@@ -243,12 +233,11 @@
pop {r4 - r10, pc}
;;;;;;;;;;;;;;;;;;;;;;
-;extra copy part for Y
extra_top_bottom_y
vld1.8 {q0}, [r1]!
vld1.8 {q2}, [r2]!
- mov r9, r3, lsr #3
+ mov r9, #4 ; 32 >> 3
extra_top_bottom_32
subs r9, r9, #1
@@ -271,19 +260,18 @@
vst1.8 {q2}, [r6], lr
bne extra_top_bottom_32
- sub r5, r1, r8
- add r6, r2, lr
+ sub r5, r1, lr, asl #5 ; src_ptr1 - (Border * plane_stride)
+ add r6, r2, lr ; src_ptr2 + plane_stride
subs r7, r7, #1
bne extra_top_bottom_y
b end_of_border_copy_y
-;extra copy part for UV
extra_top_bottom_uv
vld1.8 {d0}, [r1]!
vld1.8 {d8}, [r2]!
- mov r9, r3, lsr #3
+ mov r9, #2 ; 16 >> 3
extra_top_bottom_16
subs r9, r9, #1
@@ -306,283 +294,12 @@
vst1.8 {d8}, [r6], lr
bne extra_top_bottom_16
- sub r5, r1, r8
- add r6, r2, lr
+ sub r5, r1, lr, asl #4 ; src_ptr1 - (Border * plane_stride)
+ add r6, r2, lr ; src_ptr2 + plane_stride
subs r7, r7, #1
bne extra_top_bottom_uv
b end_of_border_copy_uv
-
-
-;=======================
-b16_extend_frame_borders
-;border = 16
-;=======================
-;Border copy for Y plane
-;copy the left and right most columns out
- sub r5, r1, r3 ;destptr1
- add r6, r1, lr
- sub r6, r6, r3, lsl #1 ;destptr2
- sub r2, r6, #1 ;srcptr2
-
- ;Do four rows at one time
- mov r12, r4, lsr #2
-
-copy_left_right_y_b16
- vld1.8 {d0[], d1[]}, [r1], lr
- vld1.8 {d4[], d5[]}, [r2], lr
- vld1.8 {d8[], d9[]}, [r1], lr
- vld1.8 {d12[], d13[]}, [r2], lr
- vld1.8 {d16[], d17[]}, [r1], lr
- vld1.8 {d20[], d21[]}, [r2], lr
- vld1.8 {d24[], d25[]}, [r1], lr
- vld1.8 {d28[], d29[]}, [r2], lr
-
- subs r12, r12, #1
-
- vst1.8 {q0}, [r5], lr
- vst1.8 {q2}, [r6], lr
- vst1.8 {q4}, [r5], lr
- vst1.8 {q6}, [r6], lr
- vst1.8 {q8}, [r5], lr
- vst1.8 {q10}, [r6], lr
- vst1.8 {q12}, [r5], lr
- vst1.8 {q14}, [r6], lr
-
- bne copy_left_right_y_b16
-
-;Now copy the top and bottom source lines into each line of the respective borders
- ldr r7, [r0, #yv12_buffer_config_y_buffer] ;srcptr1
- mul r8, r3, lr
-
- mov r12, lr, lsr #7
-
- sub r6, r1, r3 ;destptr2
- sub r2, r6, lr ;srcptr2
- sub r1, r7, r3 ;srcptr1
- sub r5, r1, r8 ;destptr1
-
-copy_top_bottom_y_b16
- vld1.8 {q0, q1}, [r1]!
- vld1.8 {q8, q9}, [r2]!
- vld1.8 {q2, q3}, [r1]!
- vld1.8 {q10, q11}, [r2]!
- vld1.8 {q4, q5}, [r1]!
- vld1.8 {q12, q13}, [r2]!
- vld1.8 {q6, q7}, [r1]!
- vld1.8 {q14, q15}, [r2]!
-
- mov r7, r3
-
-top_bottom_16_b16
- subs r7, r7, #1
-
- vst1.8 {q0, q1}, [r5]!
- vst1.8 {q8, q9}, [r6]!
- vst1.8 {q2, q3}, [r5]!
- vst1.8 {q10, q11}, [r6]!
- vst1.8 {q4, q5}, [r5]!
- vst1.8 {q12, q13}, [r6]!
- vst1.8 {q6, q7}, [r5]!
- vst1.8 {q14, q15}, [r6]!
-
- add r5, r5, lr
- sub r5, r5, #128
- add r6, r6, lr
- sub r6, r6, #128
-
- bne top_bottom_16_b16
-
- sub r5, r1, r8
- add r6, r2, lr
-
- subs r12, r12, #1
- bne copy_top_bottom_y_b16
-
- mov r7, lr, lsr #4 ;check to see if extra copy is needed
- ands r7, r7, #0x7
- bne extra_top_bottom_y_b16
-end_of_border_copy_y_b16
-
-;Border copy for U, V planes
- ldr r1, [r0, #yv12_buffer_config_u_buffer] ;srcptr1
- mov lr, lr, lsr #1 ;uv_stride
- mov r3, r3, lsr #1 ;border
- mov r4, r4, lsr #1 ;uv_height
- mov r8, r8, lsr #2
-
- mov r10, #2
-
-;copy the left and right most columns out
-border_copy_uv_b16
- sub r5, r1, r3 ;destptr1
- add r6, r1, lr
- sub r6, r6, r3, lsl #1 ;destptr2
- sub r2, r6, #1 ;srcptr2
-
- mov r7, r1
-
- ;Do eight rows at one time
- mov r12, r4, lsr #3
-
-copy_left_right_uv_b16
- vld1.8 {d0[]}, [r1], lr
- vld1.8 {d2[]}, [r2], lr
- vld1.8 {d4[]}, [r1], lr
- vld1.8 {d6[]}, [r2], lr
- vld1.8 {d8[]}, [r1], lr
- vld1.8 {d10[]}, [r2], lr
- vld1.8 {d12[]}, [r1], lr
- vld1.8 {d14[]}, [r2], lr
- vld1.8 {d16[]}, [r1], lr
- vld1.8 {d18[]}, [r2], lr
- vld1.8 {d20[]}, [r1], lr
- vld1.8 {d22[]}, [r2], lr
- vld1.8 {d24[]}, [r1], lr
- vld1.8 {d26[]}, [r2], lr
- vld1.8 {d28[]}, [r1], lr
- vld1.8 {d30[]}, [r2], lr
-
- subs r12, r12, #1
-
- vst1.8 {d0}, [r5], lr
- vst1.8 {d2}, [r6], lr
- vst1.8 {d4}, [r5], lr
- vst1.8 {d6}, [r6], lr
- vst1.8 {d8}, [r5], lr
- vst1.8 {d10}, [r6], lr
- vst1.8 {d12}, [r5], lr
- vst1.8 {d14}, [r6], lr
- vst1.8 {d16}, [r5], lr
- vst1.8 {d18}, [r6], lr
- vst1.8 {d20}, [r5], lr
- vst1.8 {d22}, [r6], lr
- vst1.8 {d24}, [r5], lr
- vst1.8 {d26}, [r6], lr
- vst1.8 {d28}, [r5], lr
- vst1.8 {d30}, [r6], lr
-
- bne copy_left_right_uv_b16
-
-;Now copy the top and bottom source lines into each line of the respective borders
- mov r12, lr, lsr #6
-
- sub r6, r1, r3 ;destptr2
- sub r2, r6, lr ;srcptr2
- sub r1, r7, r3 ;srcptr1
- sub r5, r1, r8 ;destptr1
-
-copy_top_bottom_uv_b16
- vld1.8 {q0, q1}, [r1]!
- vld1.8 {q8, q9}, [r2]!
- vld1.8 {q2, q3}, [r1]!
- vld1.8 {q10, q11}, [r2]!
-
- mov r7, r3
-
-top_bottom_8_b16
- subs r7, r7, #1
-
- vst1.8 {q0, q1}, [r5]!
- vst1.8 {q8, q9}, [r6]!
- vst1.8 {q2, q3}, [r5]!
- vst1.8 {q10, q11}, [r6]!
-
- add r5, r5, lr
- sub r5, r5, #64
- add r6, r6, lr
- sub r6, r6, #64
-
- bne top_bottom_8_b16
-
- sub r5, r1, r8
- add r6, r2, lr
-
- subs r12, r12, #1
- bne copy_top_bottom_uv_b16
-
- mov r7, lr, lsr #3 ;check to see if extra copy is needed
- ands r7, r7, #0x7
- bne extra_top_bottom_uv_b16
-
-end_of_border_copy_uv_b16
- subs r10, r10, #1
- ldrne r1, [r0, #yv12_buffer_config_v_buffer] ;srcptr1
- bne border_copy_uv_b16
-
- vpop {d8-d15}
- pop {r4 - r10, pc}
-
-;;;;;;;;;;;;;;;;;;;;;;
-;extra copy part for Y
-extra_top_bottom_y_b16
- vld1.8 {q0}, [r1]!
- vld1.8 {q2}, [r2]!
-
- mov r9, r3, lsr #3
-
-extra_top_bottom_16_b16
- subs r9, r9, #1
-
- vst1.8 {q0}, [r5], lr
- vst1.8 {q2}, [r6], lr
- vst1.8 {q0}, [r5], lr
- vst1.8 {q2}, [r6], lr
- vst1.8 {q0}, [r5], lr
- vst1.8 {q2}, [r6], lr
- vst1.8 {q0}, [r5], lr
- vst1.8 {q2}, [r6], lr
- vst1.8 {q0}, [r5], lr
- vst1.8 {q2}, [r6], lr
- vst1.8 {q0}, [r5], lr
- vst1.8 {q2}, [r6], lr
- vst1.8 {q0}, [r5], lr
- vst1.8 {q2}, [r6], lr
- vst1.8 {q0}, [r5], lr
- vst1.8 {q2}, [r6], lr
- bne extra_top_bottom_16_b16
-
- sub r5, r1, r8
- add r6, r2, lr
- subs r7, r7, #1
- bne extra_top_bottom_y_b16
-
- b end_of_border_copy_y_b16
-
-;extra copy part for UV
-extra_top_bottom_uv_b16
- vld1.8 {d0}, [r1]!
- vld1.8 {d8}, [r2]!
-
- mov r9, r3, lsr #3
-
-extra_top_bottom_8_b16
- subs r9, r9, #1
-
- vst1.8 {d0}, [r5], lr
- vst1.8 {d8}, [r6], lr
- vst1.8 {d0}, [r5], lr
- vst1.8 {d8}, [r6], lr
- vst1.8 {d0}, [r5], lr
- vst1.8 {d8}, [r6], lr
- vst1.8 {d0}, [r5], lr
- vst1.8 {d8}, [r6], lr
- vst1.8 {d0}, [r5], lr
- vst1.8 {d8}, [r6], lr
- vst1.8 {d0}, [r5], lr
- vst1.8 {d8}, [r6], lr
- vst1.8 {d0}, [r5], lr
- vst1.8 {d8}, [r6], lr
- vst1.8 {d0}, [r5], lr
- vst1.8 {d8}, [r6], lr
- bne extra_top_bottom_8_b16
-
- sub r5, r1, r8
- add r6, r2, lr
- subs r7, r7, #1
- bne extra_top_bottom_uv_b16
-
- b end_of_border_copy_uv_b16
ENDP
END
--- a/vpxenc.c
+++ b/vpxenc.c
@@ -542,7 +542,7 @@
}
#undef WRITE_BUFFER
-/* Need a fixed size serializer for the track ID. libmkv provdes a 64 bit
+/* Need a fixed size serializer for the track ID. libmkv provides a 64 bit
* one, but not a 32 bit one.
*/
static void Ebml_SerializeUnsigned32(EbmlGlobal *glob, unsigned long class_id, uint64_t ui)
@@ -559,8 +559,8 @@
unsigned long class_id)
{
//todo this is always taking 8 bytes, this may need later optimization
- //this is a key that says lenght unknown
- unsigned long long unknownLen = LITERALU64(0x01FFFFFFFFFFFFFF);
+ //this is a key that says length unknown
+ uint64_t unknownLen = LITERALU64(0x01FFFFFFFFFFFFFF);
Ebml_WriteID(glob, class_id);
*ebmlLoc = ftello(glob->stream);
@@ -975,7 +975,7 @@
static const arg_def_t stereo_mode = ARG_DEF_ENUM(NULL, "stereo-mode", 1,
"Stereo 3D video format", stereo_mode_enum);
static const arg_def_t timebase = ARG_DEF(NULL, "timebase", 1,
- "Stream timebase (frame duration)");
+ "Output timestamp precision (fractional seconds)");
static const arg_def_t error_resilient = ARG_DEF(NULL, "error-resilient", 1,
"Enable error resiliency features");
static const arg_def_t lag_in_frames = ARG_DEF(NULL, "lag-in-frames", 1,
@@ -1020,14 +1020,11 @@
"Client initial buffer size (ms)");
static const arg_def_t buf_optimal_sz = ARG_DEF(NULL, "buf-optimal-sz", 1,
"Client optimal buffer size (ms)");
-static const arg_def_t max_intra_rate_pct = ARG_DEF(NULL, "max-intra-rate", 1,
- "Max I-frame bitrate (pct)");
static const arg_def_t *rc_args[] =
{
&dropframe_thresh, &resize_allowed, &resize_up_thresh, &resize_down_thresh,
&end_usage, &target_bitrate, &min_quantizer, &max_quantizer,
&undershoot_pct, &overshoot_pct, &buf_sz, &buf_initial_sz, &buf_optimal_sz,
- &max_intra_rate_pct,
NULL
};
@@ -1091,12 +1088,14 @@
"Material to favor", tuning_enum);
static const arg_def_t cq_level = ARG_DEF(NULL, "cq-level", 1,
"Constrained Quality Level");
+static const arg_def_t max_intra_rate_pct = ARG_DEF(NULL, "max-intra-rate", 1,
+ "Max I-frame bitrate (pct)");
static const arg_def_t *vp8_args[] =
{
&cpu_used, &auto_altref, &noise_sens, &sharpness, &static_thresh,
&token_parts, &arnr_maxframes, &arnr_strength, &arnr_type,
- &tune_ssim, &cq_level, NULL
+ &tune_ssim, &cq_level, &max_intra_rate_pct, NULL
};
static const int vp8_arg_ctrl_map[] =
{
@@ -1104,7 +1103,7 @@
VP8E_SET_NOISE_SENSITIVITY, VP8E_SET_SHARPNESS, VP8E_SET_STATIC_THRESHOLD,
VP8E_SET_TOKEN_PARTITIONS,
VP8E_SET_ARNR_MAXFRAMES, VP8E_SET_ARNR_STRENGTH , VP8E_SET_ARNR_TYPE,
- VP8E_SET_TUNING, VP8E_SET_CQ_LEVEL, 0
+ VP8E_SET_TUNING, VP8E_SET_CQ_LEVEL, VP8E_SET_MAX_INTRA_BITRATE_PCT, 0
};
#endif
@@ -1131,6 +1130,9 @@
fprintf(stderr, "\nVP8 Specific Options:\n");
arg_show_usage(stdout, vp8_args);
#endif
+ fprintf(stderr, "\nStream timebase (--timebase):\n"
+ " The desired precision of timestamps in the output, expressed\n"
+ " in fractional seconds. Default is 1/1000.\n");
fprintf(stderr, "\n"
"Included encoders:\n"
"\n");
@@ -1169,7 +1171,7 @@
big_bucket = i;
}
- /* If we have too many buckets, merge the smallest with an ajacent
+ /* If we have too many buckets, merge the smallest with an adjacent
* bucket.
*/
while(buckets > max_buckets)
@@ -1640,8 +1642,6 @@
cfg.rc_end_usage = arg_parse_enum_or_int(&arg);
else if (arg_match(&arg, &target_bitrate, argi))
cfg.rc_target_bitrate = arg_parse_uint(&arg);
- else if (arg_match(&arg, &max_intra_rate_pct, argi))
- cfg.rc_max_intra_bitrate_pct = arg_parse_uint(&arg);
else if (arg_match(&arg, &min_quantizer, argi))
cfg.rc_min_quantizer = arg_parse_uint(&arg);
else if (arg_match(&arg, &max_quantizer, argi))