Merge commit '6c1e94bd89ae86fbff19677112cadc98490a376b'

.hgtags

@@ -19,3 +19,4 @@ cbeb7d8a4880e4020c4545dd8e498432c3c6cad3 1.6
 e27327f5da35c5feb660360336fdc94bd0afe719 1.8
 1d3b6e448e01ec40b392ef78b7e55a86249fbe68 1.9
 960c9991d0dcf46559c32e070418d3cbb7e8aa2f 2.0
+981e3bfef16a997bce6f46ce1b15631a0e234747 2.1

doc/reST/cli.rst

@@ -662,7 +662,7 @@ the prediction quad-tree.
 	and less frame parallelism as well. Because of this the faster
 	presets use a CU size of 32. Default: 64
 
-.. option:: --min-cu-size <64|32|16|8>
+.. option:: --min-cu-size <32|16|8>
 
 	Minimum CU size (width and height). By using 16 or 32 the encoder
 	will not analyze the cost of CUs below that minimum threshold,
@@ -869,6 +869,24 @@ as the residual quad-tree (RQT).
 	partitions, in which case a TU split is implied and thus the
 	residual quad-tree begins one layer below the CU quad-tree.
 
+.. option:: --limit-tu <0..4>
+
+	Enables early exit from TU depth recursion, for inter coded blocks.
+	Level 1 - decides to recurse to next higher depth based on cost 
+	comparison of full size TU and split TU.
+
+	Level 2 - based on first split subTU's depth, limits recursion of
+	other split subTUs.
+
+	Level 3 - based on the average depth of the co-located and the neighbor
+	CUs' TU depth, limits recursion of the current CU.
+
+	Level 4 - uses the depth of the neighbouring/ co-located CUs TU depth 
+	to limit the 1st subTU depth. The 1st subTU depth is taken as the 
+	limiting depth for the other subTUs.
+
+	Default: 0
+
 .. option:: --nr-intra <integer>, --nr-inter <integer>
 
 	Noise reduction - an adaptive deadzone applied after DCT
@@ -949,13 +967,17 @@ Temporal / motion search options
 	encoder: a star-pattern search followed by an optional radix scan
 	followed by an optional star-search refinement. Full is an
 	exhaustive search; an order of magnitude slower than all other
-	searches but not much better than umh or star.
+	searches but not much better than umh or star. SEA is similar to
+	FULL search; a three step motion search adopted from x264: DC 
+	calculation followed by ADS calculation followed by SAD of the
+	passed motion vector candidates, hence faster than Full search. 
 
 	0. dia
 	1. hex **(default)**
 	2. umh
 	3. star
-	4. full
+	4. sea
+	5. full
 
 .. option:: --subme, -m <0..7>
 
@@ -1153,6 +1175,13 @@ Slice decision options
 	:option:`--scenecut` 0 or :option:`--no-scenecut` disables adaptive
 	I frame placement. Default 40
 
+.. option:: --scenecut-bias <0..100.0>
+
+	This value represents the percentage difference between the inter cost and
+	intra cost of a frame used in scenecut detection. For example, a value of 5 indicates,
+	if the inter cost of a frame is greater than or equal to 95 percent of the intra cost of the frame,
+	then detect this frame as scenecut. Values between 5 and 15 are recommended. Default 5.	
+
 .. option:: --intra-refresh
 
 	Enables Periodic Intra Refresh(PIR) instead of keyframe insertion.
@@ -1304,7 +1333,7 @@ Quality, rate control and rate distortion options
 	slices using param->rc.ipFactor and param->rc.pbFactor unless QP 0
 	is specified, in which case QP 0 is used for all slice types.  Note
 	that QP 0 does not cause lossless encoding, it only disables
-	quantization. Default disabled (CRF)
+	quantization. Default disabled.
 
 	**Range of values:** an integer from 0 to 51
 
@@ -1824,7 +1853,7 @@ Bitstream options
 	enhancement layer. A decoder may chose to drop the enhancement layer 
 	and only decode and display the base layer slices.
 
-	If used with a fixed GOP (:option:`b-adapt` 0) and :option:`bframes`
+	If used with a fixed GOP (:option:`--b-adapt` 0) and :option:`--bframes`
 	3 then the two layers evenly split the frame rate, with a cadence of
 	PbBbP. You probably also want :option:`--no-scenecut` and a keyframe
 	interval that is a multiple of 4.
@@ -1833,15 +1862,29 @@ Bitstream options
 
   Maximum of the picture order count. Default 8
 
-.. option:: --discard-sei
+.. option:: --[no-]vui-timing-info
 
-  Discard SEI messages generated from the final bitstream. HDR-related SEI
-  messages are always dumped, immaterial of this option. Default disabled.
-
-.. option:: --discard-vui
+	Emit VUI timing info in bitstream. Default enabled.
+
+.. option:: --[no-]vui-hrd-info
+
+	Emit VUI HRD info in  bitstream. Default enabled when
+	:option:`--hrd` is enabled.
+
+.. option:: --[no-]opt-qp-pps
+
+	Optimize QP in PPS (instead of default value of 26) based on the QP values
+	observed in last GOP. Default enabled.
+
+.. option:: --[no-]opt-ref-list-length-pps
+
+	Optimize L0 and L1 ref list length in PPS (instead of default value of 0)
+	based on the lengths observed in the last GOP. Default enabled.
+
+.. option:: --[no-]multi-pass-opt-rps
+
+	Enable storing commonly used RPS in SPS in multi pass mode. Default disabled.
 
-	Discard optional VUI information (timing, HRD info) from the
-	bitstream. Default disabled.
 
 Debugging options
 =================

doc/reST/index.rst

@@ -9,3 +9,4 @@ x265 Documentation
    threading
    presets
    lossless
+   releasenotes

doc/reST/releasenotes.rst

@@ -0,0 +1,141 @@
+*************
+Release Notes
+*************
+
+Version 2.2
+===========
+
+Release date - 26th December, 2016.
+
+Encoder enhancements
+--------------------
+1. Enhancements to TU selection algorithm with early-outs for improved speed; use :option:`--limit-tu` to exercise.
+2. New motion search method SEA (Successive Elimination Algorithm) supported now as :option: `--me` 4
+3. Bit-stream optimizations to improve fields in PPS and SPS for bit-rate savings through :option:`--[no-]opt-qp-pps`, :option:`--[no-]opt-ref-list-length-pps`, and :option:`--[no-]multi-pass-opt-rps`.
+4. Enabled using VBV constraints when encoding without WPP.
+5. All param options dumped in SEI packet in bitstream when info selected.
+6. x265 now supports POWERPC-based systems. Several key functions also have optimized ALTIVEC kernels.
+
+API changes
+-----------
+1. Options to disable SEI and optional-VUI messages from bitstream made more descriptive.
+2. New option :option:`--scenecut-bias` to enable controlling bias to mark scene-cuts via cli.
+3. Support mono and mono16 color spaces for y4m input.
+4. :option:`--min-cu-size` of 64 no-longer supported for reasons of visual quality (was crashing earlier anyways.)
+5. API for CSV now expects version string for better integration of x265 into other applications.
+
+Bug fixes
+---------
+1. Several fixes to slice-based encoding.
+2. :option:`--log2-max-poc-lsb`'s range limited according to HEVC spec.
+3. Restrict MVs to within legal boundaries when encoding.
+
+Version 2.1
+===========
+
+Release date - 27th September, 2016
+
+Encoder enhancements
+--------------------
+1. Support for qg-size of 8
+2. Support for inserting non-IDR I-frames at scenecuts and when running with settings for fixed-GOP (min-keyint = max-keyint)
+3. Experimental support for slice-parallelism.
+
+API changes
+-----------
+1. Encode user-define SEI messages passed in through x265_picture object.
+2. Disable SEI and VUI messages from the bitstream
+3. Specify qpmin and qpmax
+4. Control number of bits to encode POC.
+
+Bug fixes
+---------
+1. QP fluctuation fix for first B-frame in mini-GOP for 2-pass encoding with tune-grain.
+2. Assembly fix for crashes in 32-bit from dct_sse4.
+3. Threadpool creation fix in windows platform.
+
+Version 2.0
+===========
+
+Release date - 13th July, 2016
+
+New Features
+------------
+
+1. uhd-bd: Enable Ultra-HD Bluray support
+2. rskip: Enables skipping recursion to analyze lower CU sizes using heuristics at different rd-levels. Provides good visual quality gains at the highest quality presets. 
+3. rc-grain: Enables a new ratecontrol mode specifically for grainy content. Strictly prevents QP oscillations within and between frames to avoid grain fluctuations.
+4. tune grain: A fully refactored and improved option to encode film grain content including QP control as well as analysis options.
+5. asm: ARM assembly is now enabled by default, native or cross compiled builds supported on armv6 and later systems.
+
+API and Key Behaviour Changes
+-----------------------------
+
+1. x265_rc_stats added to x265_picture, containing all RC decision points for that frame
+2. PTL: high tier is now allowed by default, chosen only if necessary
+3. multi-pass: First pass now uses slow-firstpass by default, enabling better RC decisions in future passes 
+4. pools: fix behaviour on multi-socketed Windows systems, provide more flexibility in determining thread and pool counts
+5. ABR: improve bits allocation in the first few frames, abr reset, vbv and cutree improved
+
+Misc
+----
+1. An SSIM calculation bug was corrected
+
+Version 1.9
+===========
+
+Release date - 29th January, 2016
+
+New Features
+------------
+
+1. Quant offsets: This feature allows block level quantization offsets to be specified for every frame. An API-only feature.
+2. --intra-refresh: Keyframes can be replaced by a moving column of intra blocks in non-keyframes.
+3. --limit-modes: Intelligently restricts mode analysis. 
+4. --max-luma and --min-luma for luma clipping, optional for HDR use-cases
+5. Emergency denoising is now enabled by default in very low bitrate, VBV encodes
+
+API Changes
+-----------
+
+1. x265_frame_stats returns many additional fields: maxCLL, maxFALL, residual energy, scenecut  and latency logging
+2. --qpfile now supports frametype 'K"
+3. x265 now allows CRF ratecontrol in pass N (N greater than or equal to 2)
+4. Chroma subsampling format YUV 4:0:0 is now fully supported and tested
+
+Presets and Performance
+-----------------------
+
+1. Recently added features lookahead-slices, limit-modes, limit-refs have been enabled by default for applicable presets.
+2. The default psy-rd strength has been increased to 2.0
+3. Multi-socket machines now use a single pool of threads that can work cross-socket.
+
+Version 1.8
+===========
+
+Release date - 10th August, 2015
+
+API Changes
+-----------
+1. Experimental support for Main12 is now enabled. Partial assembly support exists. 
+2. Main12 and Intra/Still picture profiles are now supported. Still picture profile is detected based on x265_param::totalFrames.
+3. Three classes of encoding statistics are now available through the API. 
+a) x265_stats - contains encoding statistics, available through x265_encoder_get_stats()
+b) x265_frame_stats and x265_cu_stats - contains frame encoding statistics, available through recon x265_picture
+4. --csv
+a) x265_encoder_log() is now deprecated
+b) x265_param::csvfn is also deprecated
+5. --log-level now controls only console logging, frame level console logging has been removed.
+6. Support added for new color transfer characteristic ARIB STD-B67
+
+New Features
+------------
+1. limit-refs: This feature limits the references analysed for individual CUS. Provides a nice tradeoff between efficiency and performance.
+2. aq-mode 3: A new aq-mode that provides additional biasing for low-light conditions.
+3. An improved scene cut detection logic that allows ratecontrol to manage visual quality at fade-ins and fade-outs better.
+
+Preset and Tune Options
+-----------------------
+
+1. tune grain: Increases psyRdoq strength to 10.0, and rdoq-level to 2.
+2. qg-size: Default value changed to 32.

source/CMakeLists.txt

@@ -30,7 +30,7 @@ option(STATIC_LINK_CRT "Statically link C runtime for release builds" OFF)
 mark_as_advanced(FPROFILE_USE FPROFILE_GENERATE NATIVE_BUILD)
 
 # X265_BUILD must be incremented each time the public API is changed
-set(X265_BUILD 95)
+set(X265_BUILD 102)
 configure_file("${PROJECT_SOURCE_DIR}/x265.def.in"
                "${PROJECT_BINARY_DIR}/x265.def")
 configure_file("${PROJECT_SOURCE_DIR}/x265_config.h.in"
@@ -60,6 +60,11 @@ elseif(POWERMATCH GREATER "-1")
     message(STATUS "Detected POWER target processor")
     set(POWER 1)
     add_definitions(-DX265_ARCH_POWER=1)
+    if("${CMAKE_SIZEOF_VOID_P}" MATCHES 8)
+        set(PPC64 1)
+        add_definitions(-DPPC64=1)
+        message(STATUS "Detected POWER PPC64 target processor")
+    endif()
 elseif(ARMMATCH GREATER "-1")
     if(CROSS_COMPILE_ARM)
         message(STATUS "Cross compiling for ARM arch")
@@ -167,6 +172,19 @@ elseif(CLANG)
 elseif(CMAKE_COMPILER_IS_GNUCXX)
     set(GCC 1)
 endif()
+
+if(CC STREQUAL "xlc")
+    message(STATUS "Use XLC compiler")
+    set(XLC 1)
+    set(GCC 0)
+    #set(CMAKE_C_COMPILER "/usr/bin/xlc")
+    #set(CMAKE_CXX_COMPILER "/usr/bin/xlc++")
+    add_definitions(-D__XLC__=1)
+    add_definitions(-O3 -qstrict -qhot -qaltivec)
+    add_definitions(-qinline=level=10 -qpath=IL:/data/video_files/latest.tpo/)
+endif()
+
+
 if(GCC)
     add_definitions(-Wall -Wextra -Wshadow)
     add_definitions(-D__STDC_LIMIT_MACROS=1)
@@ -396,6 +414,22 @@ if(WIN32)
     endif(WINXP_SUPPORT)
 endif()
 
+if(POWER)
+    # IBM Power8
+    option(ENABLE_ALTIVEC "Enable ALTIVEC profiling instrumentation" ON)
+    if(ENABLE_ALTIVEC)
+        add_definitions(-DHAVE_ALTIVEC=1 -maltivec -mabi=altivec)
+        add_definitions(-flax-vector-conversions -fpermissive)
+    else()
+        add_definitions(-DHAVE_ALTIVEC=0)
+    endif()
+
+    option(CPU_POWER8 "Enable CPU POWER8 profiling instrumentation" ON)
+    if(CPU_POWER8)
+        add_definitions(-mcpu=power8 -DX265_ARCH_POWER8=1)
+    endif()
+endif()
+
 include(version) # determine X265_VERSION and X265_LATEST_TAG
 include_directories(. common encoder "${PROJECT_BINARY_DIR}")
 

source/common/CMakeLists.txt

@@ -99,6 +99,19 @@ if(ENABLE_ASSEMBLY AND (ARM OR CROSS_COMPILE_ARM))
     source_group(Assembly FILES ${ASM_PRIMITIVES})
 endif(ENABLE_ASSEMBLY AND (ARM OR CROSS_COMPILE_ARM))
 
+if(POWER)
+    set_source_files_properties(version.cpp PROPERTIES COMPILE_FLAGS -DX265_VERSION=${X265_VERSION})
+    if(ENABLE_ALTIVEC)
+        set(ALTIVEC_SRCS pixel_altivec.cpp dct_altivec.cpp ipfilter_altivec.cpp intrapred_altivec.cpp)
+        foreach(SRC ${ALTIVEC_SRCS})
+            set(ALTIVEC_PRIMITIVES ${ALTIVEC_PRIMITIVES} ppc/${SRC})
+        endforeach()
+        source_group(Intrinsics_altivec FILES ${ALTIVEC_PRIMITIVES})
+        set_source_files_properties(${ALTIVEC_PRIMITIVES} PROPERTIES COMPILE_FLAGS "-Wno-unused  -Wno-unknown-pragmas -Wno-maybe-uninitialized")
+    endif()
+endif()
+
+
 # set_target_properties can't do list expansion
 string(REPLACE ";" " " VERSION_FLAGS "${VFLAGS}")
 set_source_files_properties(version.cpp PROPERTIES COMPILE_FLAGS ${VERSION_FLAGS})
@@ -116,7 +129,7 @@ if(WIN32)
 endif(WIN32)
 
 add_library(common OBJECT
-    ${ASM_PRIMITIVES} ${VEC_PRIMITIVES} ${WINXP}
+    ${ASM_PRIMITIVES} ${VEC_PRIMITIVES} ${ALTIVEC_PRIMITIVES} ${WINXP}
     primitives.cpp primitives.h
     pixel.cpp dct.cpp ipfilter.cpp intrapred.cpp loopfilter.cpp
     constants.cpp constants.h

source/common/bitstream.h

@@ -71,6 +71,7 @@ class Bitstream : public BitInterface
     uint32_t getNumberOfWrittenBytes() const { return m_byteOccupancy; }
     uint32_t getNumberOfWrittenBits()  const { return m_byteOccupancy * 8 + m_partialByteBits; }
     const uint8_t* getFIFO() const           { return m_fifo; }
+    void     copyBits(Bitstream* stream)     { m_partialByteBits = stream->m_partialByteBits; m_byteOccupancy = stream->m_byteOccupancy; m_partialByte = stream->m_partialByte; }
 
     void     write(uint32_t val, uint32_t numBits);
     void     writeByte(uint32_t val);