[M108-LTS] Fix OOB write in BuildHuffmanTable.

M108 merge issues: dec/vp8l_dec.c: - Conflicting checks before ReadHuffmanCodeLengths() return statement; In 114, an assignment follows the check instead of a return. - ReadHuffmanCodes(): Conflict after the changed huffman_tables check, there's an assignment in 114 instead of the setter call. First, BuildHuffmanTable is called to check if the data is valid. If it is and the table is not big enough, more memory is allocated. This will make sure that valid (but unoptimized because of unbalanced codes) streams are still decodable. Bug: chromium:1479274 Change-Id: I31c36dbf3aa78d35ecf38706b50464fd3d375741 (cherry picked from commit 902bc91903)
2025-12-24 22:19:11 +01:00 · 2023-09-12 09:30:11 +00:00
126 changed files with 1493 additions and 2563 deletions
--- a/.cmake-format.py
+++ b/.cmake-format.py
@@ -1,240 +0,0 @@
-# ----------------------------------
-# Options affecting listfile parsing
-# ----------------------------------
-with section("parse"):
-
-  # Specify structure for custom cmake functions
-  additional_commands = { 'foo': { 'flags': ['BAR', 'BAZ'],
-             'kwargs': {'DEPENDS': '*', 'HEADERS': '*', 'SOURCES': '*'}}}
-
-  # Override configurations per-command where available
-  override_spec = {}
-
-  # Specify variable tags.
-  vartags = []
-
-  # Specify property tags.
-  proptags = []
-
-# -----------------------------
-# Options affecting formatting.
-# -----------------------------
-with section("format"):
-
-  # Disable formatting entirely, making cmake-format a no-op
-  disable = False
-
-  # How wide to allow formatted cmake files
-  line_width = 80
-
-  # How many spaces to tab for indent
-  tab_size = 2
-
-  # If true, lines are indented using tab characters (utf-8 0x09) instead of
-  # <tab_size> space characters (utf-8 0x20). In cases where the layout would
-  # require a fractional tab character, the behavior of the  fractional
-  # indentation is governed by <fractional_tab_policy>
-  use_tabchars = False
-
-  # If <use_tabchars> is True, then the value of this variable indicates how
-  # fractional indentions are handled during whitespace replacement. If set to
-  # 'use-space', fractional indentation is left as spaces (utf-8 0x20). If set
-  # to `round-up` fractional indentation is replaced with a single tab character
-  # (utf-8 0x09) effectively shifting the column to the next tabstop
-  fractional_tab_policy = 'use-space'
-
-  # If an argument group contains more than this many sub-groups (parg or kwarg
-  # groups) then force it to a vertical layout.
-  max_subgroups_hwrap = 3
-
-  # If a positional argument group contains more than this many arguments, then
-  # force it to a vertical layout.
-  max_pargs_hwrap = 6
-
-  # If a cmdline positional group consumes more than this many lines without
-  # nesting, then invalidate the layout (and nest)
-  max_rows_cmdline = 2
-
-  # If true, separate flow control names from their parentheses with a space
-  separate_ctrl_name_with_space = False
-
-  # If true, separate function names from parentheses with a space
-  separate_fn_name_with_space = False
-
-  # If a statement is wrapped to more than one line, than dangle the closing
-  # parenthesis on its own line.
-  dangle_parens = False
-
-  # If the trailing parenthesis must be 'dangled' on its on line, then align it
-  # to this reference: `prefix`: the start of the statement,  `prefix-indent`:
-  # the start of the statement, plus one indentation  level, `child`: align to
-  # the column of the arguments
-  dangle_align = 'prefix'
-
-  # If the statement spelling length (including space and parenthesis) is
-  # smaller than this amount, then force reject nested layouts.
-  min_prefix_chars = 4
-
-  # If the statement spelling length (including space and parenthesis) is larger
-  # than the tab width by more than this amount, then force reject un-nested
-  # layouts.
-  max_prefix_chars = 10
-
-  # If a candidate layout is wrapped horizontally but it exceeds this many
-  # lines, then reject the layout.
-  max_lines_hwrap = 2
-
-  # What style line endings to use in the output.
-  line_ending = 'unix'
-
-  # Format command names consistently as 'lower' or 'upper' case
-  command_case = 'canonical'
-
-  # Format keywords consistently as 'lower' or 'upper' case
-  keyword_case = 'unchanged'
-
-  # A list of command names which should always be wrapped
-  always_wrap = []
-
-  # If true, the argument lists which are known to be sortable will be sorted
-  # lexicographicall
-  enable_sort = True
-
-  # If true, the parsers may infer whether or not an argument list is sortable
-  # (without annotation).
-  autosort = False
-
-  # By default, if cmake-format cannot successfully fit everything into the
-  # desired linewidth it will apply the last, most agressive attempt that it
-  # made. If this flag is True, however, cmake-format will print error, exit
-  # with non-zero status code, and write-out nothing
-  require_valid_layout = False
-
-  # A dictionary mapping layout nodes to a list of wrap decisions. See the
-  # documentation for more information.
-  layout_passes = {}
-
-# ------------------------------------------------
-# Options affecting comment reflow and formatting.
-# ------------------------------------------------
-with section("markup"):
-
-  # What character to use for bulleted lists
-  bullet_char = '*'
-
-  # What character to use as punctuation after numerals in an enumerated list
-  enum_char = '.'
-
-  # If comment markup is enabled, don't reflow the first comment block in each
-  # listfile. Use this to preserve formatting of your copyright/license
-  # statements.
-  first_comment_is_literal = True
-
-  # If comment markup is enabled, don't reflow any comment block which matches
-  # this (regex) pattern. Default is `None` (disabled).
-  literal_comment_pattern = None
-
-  # Regular expression to match preformat fences in comments default=
-  # ``r'^\s*([`~]{3}[`~]*)(.*)$'``
-  fence_pattern = '^\\s*([`~]{3}[`~]*)(.*)$'
-
-  # Regular expression to match rulers in comments default=
-  # ``r'^\s*[^\w\s]{3}.*[^\w\s]{3}$'``
-  ruler_pattern = '^\\s*[^\\w\\s]{3}.*[^\\w\\s]{3}$'
-
-  # If a comment line matches starts with this pattern then it is explicitly a
-  # trailing comment for the preceeding argument. Default is '#<'
-  explicit_trailing_pattern = '#<'
-
-  # If a comment line starts with at least this many consecutive hash
-  # characters, then don't lstrip() them off. This allows for lazy hash rulers
-  # where the first hash char is not separated by space
-  hashruler_min_length = 10
-
-  # If true, then insert a space between the first hash char and remaining hash
-  # chars in a hash ruler, and normalize its length to fill the column
-  canonicalize_hashrulers = True
-
-  # enable comment markup parsing and reflow
-  enable_markup = True
-
-# ----------------------------
-# Options affecting the linter
-# ----------------------------
-with section("lint"):
-
-  # a list of lint codes to disable
-  disabled_codes = []
-
-  # regular expression pattern describing valid function names
-  function_pattern = '[0-9a-z_]+'
-
-  # regular expression pattern describing valid macro names
-  macro_pattern = '[0-9A-Z_]+'
-
-  # regular expression pattern describing valid names for variables with global
-  # (cache) scope
-  global_var_pattern = '[A-Z][0-9A-Z_]+'
-
-  # regular expression pattern describing valid names for variables with global
-  # scope (but internal semantic)
-  internal_var_pattern = '_[A-Z][0-9A-Z_]+'
-
-  # regular expression pattern describing valid names for variables with local
-  # scope
-  local_var_pattern = '[a-z][a-z0-9_]+'
-
-  # regular expression pattern describing valid names for privatedirectory
-  # variables
-  private_var_pattern = '_[0-9a-z_]+'
-
-  # regular expression pattern describing valid names for public directory
-  # variables
-  public_var_pattern = '[A-Z][0-9A-Z_]+'
-
-  # regular expression pattern describing valid names for function/macro
-  # arguments and loop variables.
-  argument_var_pattern = '[a-z][a-z0-9_]+'
-
-  # regular expression pattern describing valid names for keywords used in
-  # functions or macros
-  keyword_pattern = '[A-Z][0-9A-Z_]+'
-
-  # In the heuristic for C0201, how many conditionals to match within a loop in
-  # before considering the loop a parser.
-  max_conditionals_custom_parser = 2
-
-  # Require at least this many newlines between statements
-  min_statement_spacing = 1
-
-  # Require no more than this many newlines between statements
-  max_statement_spacing = 2
-  max_returns = 6
-  max_branches = 12
-  max_arguments = 5
-  max_localvars = 15
-  max_statements = 50
-
-# -------------------------------
-# Options affecting file encoding
-# -------------------------------
-with section("encode"):
-
-  # If true, emit the unicode byte-order mark (BOM) at the start of the file
-  emit_byteorder_mark = False
-
-  # Specify the encoding of the input file. Defaults to utf-8
-  input_encoding = 'utf-8'
-
-  # Specify the encoding of the output file. Defaults to utf-8. Note that cmake
-  # only claims to support utf-8 so be careful when using anything else
-  output_encoding = 'utf-8'
-
-# -------------------------------------
-# Miscellaneous configurations options.
-# -------------------------------------
-with section("misc"):
-
-  # A dictionary containing any per-command configuration overrides. Currently
-  # only `command_case` is supported.
-  per_command = {}
--- a/.mailmap
+++ b/.mailmap
@@ -16,4 +16,3 @@ James Zern <jzern@google.com>
 Roberto Alanis <alanisbaez@google.com>
 Brian Ledger <brianpl@google.com>
 Maryla Ustarroz-Calonge <maryla@google.com>
-Yannis Guyon <yguyon@google.com>
--- a/.style.yapf
+++ b/.style.yapf
@@ -1,2 +1,2 @@
 [style]
-based_on_style = yapf
+based_on_style = chromium
--- a/4
+++ b/4
@@ -11,13 +11,11 @@ Contributors:
 - Djordje Pesut (djordje dot pesut at imgtec dot com)
 - Frank Barchard (fbarchard at google dot com)
 - Hui Su (huisu at google dot com)
- H. Vetinari (h dot vetinari at gmx dot com)
 - Ilya Kurdyukov (jpegqs at gmail dot com)
 - Ingvar Stepanyan (rreverser at google dot com)
 - James Zern (jzern at google dot com)
 - Jan Engelhardt (jengelh at medozas dot de)
 - Jehan (jehan at girinstud dot io)
- Jeremy Maitin-Shepard (jbms at google dot com)
 - Johann Koenig (johann dot koenig at duck dot com)
 - Jovan Zelincevic (jovan dot zelincevic at imgtec dot com)
 - Jyrki Alakuijala (jyrki at google dot com)
@@ -32,7 +30,6 @@ Contributors:
 - Mislav Bradac (mislavm at google dot com)
 - Nico Weber (thakis at chromium dot org)
 - Noel Chromium (noel at chromium dot org)
- Nozomi Isozaki (nontan at pixiv dot co dot jp)
 - Oliver Wolff (oliver dot wolff at qt dot io)
 - Owen Rodley (orodley at google dot com)
 - Parag Salasakar (img dot mips1 at gmail dot com)
@@ -48,7 +45,6 @@ Contributors:
 - Somnath Banerjee (somnath dot banerjee at gmail dot com)
 - Sriraman Tallam (tmsriram at google dot com)
 - Tamar Levy (tamar dot levy at intel dot com)
- Thiago Perrotta (tperrotta at google dot com)
 - Timothy Gu (timothygu99 at gmail dot com)
 - Urvang Joshi (urvang at google dot com)
 - Vikas Arora (vikasa at google dot com)
--- a/Android.mk
+++ b/Android.mk
@@ -1,5 +1,3 @@
-# Ignore this file during non-NDK builds.
-ifdef NDK_ROOT
 LOCAL_PATH := $(call my-dir)

 WEBP_CFLAGS := -Wall -DANDROID -DHAVE_MALLOC_H -DHAVE_PTHREAD -DWEBP_USE_THREAD
@@ -37,7 +35,6 @@ endif

 sharpyuv_srcs := \
    sharpyuv/sharpyuv.c \
-    sharpyuv/sharpyuv_cpu.c \
    sharpyuv/sharpyuv_csp.c \
    sharpyuv/sharpyuv_dsp.c \
    sharpyuv/sharpyuv_gamma.c \
@@ -221,7 +218,7 @@ LOCAL_SRC_FILES := \
    $(utils_enc_srcs) \

 LOCAL_CFLAGS := $(WEBP_CFLAGS)
-LOCAL_EXPORT_C_INCLUDES += $(LOCAL_PATH)/src $(LOCAL_PATH)
+LOCAL_EXPORT_C_INCLUDES += $(LOCAL_PATH)/src

 # prefer arm over thumb mode for performance gains
 LOCAL_ARM_MODE := arm
@@ -291,4 +288,3 @@ include $(WEBP_SRC_PATH)/examples/Android.mk
 ifeq ($(USE_CPUFEATURES),yes)
  $(call import-module,android/cpufeatures)
 endif
-endif  # NDK_ROOT
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -6,11 +6,7 @@
 #  in the file PATENTS.  All contributing project authors may
 #  be found in the AUTHORS file in the root of the source tree.

-if(APPLE)
-  cmake_minimum_required(VERSION 3.17)
-else()
-  cmake_minimum_required(VERSION 3.7)
-endif()
+cmake_minimum_required(VERSION 3.7)

 if(POLICY CMP0072)
  cmake_policy(SET CMP0072 NEW)
@@ -54,9 +50,9 @@ set_property(CACHE WEBP_BITTRACE PROPERTY STRINGS 0 1 2)

 if(WEBP_LINK_STATIC)
  if(WIN32)
-    set(CMAKE_FIND_LIBRARY_SUFFIXES .lib .a ${CMAKE_FIND_LIBRARY_SUFFIXES})
+    SET(CMAKE_FIND_LIBRARY_SUFFIXES .lib .a ${CMAKE_FIND_LIBRARY_SUFFIXES})
  else()
-    set(CMAKE_FIND_LIBRARY_SUFFIXES .a ${CMAKE_FIND_LIBRARY_SUFFIXES})
+    SET(CMAKE_FIND_LIBRARY_SUFFIXES .a ${CMAKE_FIND_LIBRARY_SUFFIXES})
  endif()
  set(CMAKE_POSITION_INDEPENDENT_CODE ON)
  # vwebp does not compile on Ubuntu with static libraries so disabling it for
@@ -82,42 +78,23 @@ if(WEBP_BUILD_WEBP_JS)
  set(WEBP_USE_THREAD OFF)

  if(WEBP_ENABLE_SIMD)
-    message(NOTICE
-            "wasm2js does not support SIMD, disabling webp.js generation.")
+    message("wasm2js does not support SIMD, disabling webp.js generation.")
  endif()
 endif()

-set(SHARPYUV_DEP_LIBRARIES)
-set(SHARPYUV_DEP_INCLUDE_DIRS)
 set(WEBP_DEP_LIBRARIES)
 set(WEBP_DEP_INCLUDE_DIRS)

 if(NOT CMAKE_BUILD_TYPE)
  set(CMAKE_BUILD_TYPE "Release"
      CACHE STRING "Build type: Release, Debug, MinSizeRel or RelWithDebInfo"
-            FORCE)
+      FORCE)
 endif()

 # Include dependencies.
-if(WEBP_BUILD_ANIM_UTILS
-   OR WEBP_BUILD_CWEBP
-   OR WEBP_BUILD_DWEBP
-   OR WEBP_BUILD_EXTRAS
-   OR WEBP_BUILD_GIF2WEBP
-   OR WEBP_BUILD_IMG2WEBP)
-  set(WEBP_FIND_IMG_LIBS TRUE)
-else()
-  set(WEBP_FIND_IMG_LIBS FALSE)
-endif()
 include(cmake/deps.cmake)
 include(GNUInstallDirs)

-if(BUILD_SHARED_LIBS AND NOT DEFINED CMAKE_INSTALL_RPATH)
-  # Set the rpath to match autoconf/libtool behavior. Note this must be set
-  # before target creation.
-  set(CMAKE_INSTALL_RPATH "${CMAKE_INSTALL_PREFIX}/${CMAKE_INSTALL_LIBDIR}")
-endif()
-
 # ##############################################################################
 # Options.
 if(WEBP_ENABLE_SWAP_16BIT_CSP)
@@ -133,50 +110,26 @@ if(WEBP_UNICODE)
  add_definitions(-DUNICODE -D_UNICODE)
 endif()

-if(MSVC AND BUILD_SHARED_LIBS)
-  add_definitions(-DWEBP_DLL)
-endif()
-
-# pkg-config variables used by *.pc.in.
 set(prefix ${CMAKE_INSTALL_PREFIX})
-set(exec_prefix "\${prefix}")
-if(IS_ABSOLUTE "${CMAKE_INSTALL_LIBDIR}")
-  set(libdir "${CMAKE_INSTALL_LIBDIR}")
-else()
-  set(libdir "\${exec_prefix}/${CMAKE_INSTALL_LIBDIR}")
-endif()
-if(IS_ABSOLUTE "${CMAKE_INSTALL_INCLUDEDIR}")
-  set(includedir "${CMAKE_INSTALL_INCLUDEDIR}")
-else()
-  set(includedir "\${prefix}/${CMAKE_INSTALL_INCLUDEDIR}")
-endif()
+set(exec_prefix "\$\{prefix\}")
+set(libdir "\$\{prefix\}/lib")
+set(includedir "\$\{prefix\}/include")
 set(PTHREAD_LIBS ${CMAKE_THREAD_LIBS_INIT})
 set(INSTALLED_LIBRARIES)

-if(MSVC)
-  # match the naming convention used by nmake
-  set(webp_libname_prefix "lib")
-  set(CMAKE_SHARED_LIBRARY_PREFIX "${webp_libname_prefix}")
-  set(CMAKE_IMPORT_LIBRARY_PREFIX "${webp_libname_prefix}")
-  set(CMAKE_STATIC_LIBRARY_PREFIX "${webp_libname_prefix}")
-endif()
-
 set(CMAKE_C_VISIBILITY_PRESET hidden)

 # ##############################################################################
 # Android only.
 if(ANDROID)
  include_directories(${ANDROID_NDK}/sources/android/cpufeatures)
-  add_library(cpufeatures-webp STATIC
+  add_library(cpufeatures STATIC
              ${ANDROID_NDK}/sources/android/cpufeatures/cpu-features.c)
-  list(APPEND INSTALLED_LIBRARIES cpufeatures-webp)
-  target_link_libraries(cpufeatures-webp dl)
-  set(SHARPYUV_DEP_LIBRARIES ${SHARPYUV_DEP_LIBRARIES} cpufeatures-webp)
-  set(WEBP_DEP_LIBRARIES ${WEBP_DEP_LIBRARIES} cpufeatures-webp)
-  set(cpufeatures_include_dir ${ANDROID_NDK}/sources/android/cpufeatures)
-  set(SHARPYUV_DEP_INCLUDE_DIRS ${SHARPYUV_DEP_INCLUDE_DIRS}
-                                ${cpufeatures_include_dir})
-  set(WEBP_DEP_INCLUDE_DIRS ${WEBP_DEP_INCLUDE_DIRS} ${cpufeatures_include_dir})
+  list(APPEND INSTALLED_LIBRARIES cpufeatures)
+  target_link_libraries(cpufeatures dl)
+  set(WEBP_DEP_LIBRARIES ${WEBP_DEP_LIBRARIES} cpufeatures)
+  set(WEBP_DEP_INCLUDE_DIRS ${WEBP_DEP_INCLUDE_DIRS}
+      ${ANDROID_NDK}/sources/android/cpufeatures)
  add_definitions(-DHAVE_CPU_FEATURES_H=1)
  set(HAVE_CPU_FEATURES_H 1)
 else()
@@ -185,7 +138,7 @@ endif()

 function(configure_pkg_config FILE)
  configure_file("${CMAKE_CURRENT_SOURCE_DIR}/${FILE}.in"
-                 "${CMAKE_CURRENT_BINARY_DIR}/${FILE}" @ONLY)
+                 "${CMAKE_CURRENT_BINARY_DIR}/${FILE}")

  if(HAVE_MATH_LIBRARY)
    # MSVC doesn't have libm
@@ -194,8 +147,10 @@ function(configure_pkg_config FILE)
    file(WRITE ${CMAKE_CURRENT_BINARY_DIR}/${FILE} ${data})
  endif()

-  install(FILES "${CMAKE_CURRENT_BINARY_DIR}/${FILE}"
-          DESTINATION ${CMAKE_INSTALL_LIBDIR}/pkgconfig)
+  install(
+    FILES "${CMAKE_CURRENT_BINARY_DIR}/${FILE}"
+    DESTINATION ${CMAKE_INSTALL_LIBDIR}/pkgconfig
+  )
 endfunction()

 # ##############################################################################
@@ -205,15 +160,23 @@ endfunction()
 # E.g.: libimagedec_la_SOURCES  = image_dec.c image_dec.h
 function(parse_Makefile_am FOLDER VAR SRC_REGEX)
  file(READ ${FOLDER}/Makefile.am MAKEFILE_AM)
-  string(REGEX MATCHALL "${SRC_REGEX}_SOURCES[ ]*\\+?=[ ]+[0-9a-z\\._ ]*"
-               FILES_PER_LINE ${MAKEFILE_AM})
+  string(REGEX MATCHALL
+               "${SRC_REGEX}_SOURCES[ ]*\\+?=[ ]+[0-9a-z\\._ ]*"
+               FILES_PER_LINE
+               ${MAKEFILE_AM})
  set(SRCS ${${VAR}})
  foreach(FILES ${FILES_PER_LINE})
    string(FIND ${FILES} "=" OFFSET)
    math(EXPR OFFSET "${OFFSET} + 2")
-    string(SUBSTRING ${FILES} ${OFFSET} -1 FILES)
+    string(SUBSTRING ${FILES}
+                     ${OFFSET}
+                     -1
+                     FILES)
    if(FILES)
-      string(REGEX MATCHALL "[0-9a-z\\._]+" FILES ${FILES})
+      string(REGEX MATCHALL
+                   "[0-9a-z\\._]+"
+                   FILES
+                   ${FILES})
      foreach(FILE ${FILES})
        list(APPEND SRCS ${FOLDER}/${FILE})
      endforeach()
@@ -242,17 +205,175 @@ endforeach()

 # Generate the config.h file.
 configure_file(${CMAKE_CURRENT_LIST_DIR}/cmake/config.h.in
-               ${CMAKE_CURRENT_BINARY_DIR}/src/webp/config.h @ONLY)
+               ${CMAKE_CURRENT_BINARY_DIR}/src/webp/config.h)
 add_definitions(-DHAVE_CONFIG_H)

+# ##############################################################################
+# Build the webpdecoder library.
+
+# Creates a source file with an unused stub function in $CMAKE_BINARY_DIR and
+# adds it to the specified target. Currently used only with Xcode.
+#
+# See also:
+# https://cmake.org/cmake/help/v3.18/command/add_library.html#object-libraries
+# "Some native build systems (such as Xcode) may not like targets that have
+# only object files, so consider adding at least one real source file to any
+# target that references $<TARGET_OBJECTS:objlib>."
+function(libwebp_add_stub_file TARGET)
+  set(stub_source_dir "${CMAKE_BINARY_DIR}")
+  set(stub_source_file
+      "${stub_source_dir}/libwebp_${TARGET}_stub.c")
+  set(stub_source_code
+      "// Generated file. DO NOT EDIT!\n"
+      "// C source file created for target ${TARGET}.\n"
+      "void libwebp_${TARGET}_stub_function(void)\;\n"
+      "void libwebp_${TARGET}_stub_function(void) {}\n")
+  file(WRITE "${stub_source_file}" ${stub_source_code})
+
+  target_sources(${TARGET} PRIVATE ${stub_source_file})
+endfunction()
+
+parse_makefile_am(${CMAKE_CURRENT_SOURCE_DIR}/sharpyuv "WEBP_SHARPYUV_SRCS"
+                  "")
+add_library(sharpyuv OBJECT ${WEBP_SHARPYUV_SRCS})
+target_include_directories(sharpyuv
+                            PRIVATE ${CMAKE_CURRENT_BINARY_DIR}
+                            ${CMAKE_CURRENT_SOURCE_DIR})
+set_target_properties(
+  sharpyuv
+  PROPERTIES PUBLIC_HEADER "${CMAKE_CURRENT_SOURCE_DIR}/sharpyuv/sharpyuv.h;\
+${CMAKE_CURRENT_SOURCE_DIR}/sharpyuv/sharpyuv_csp.h;\
+${CMAKE_CURRENT_SOURCE_DIR}/src/webp/types.h")
+
+if(MSVC)
+  # avoid security warnings for e.g., fopen() used in the examples.
+  add_definitions(-D_CRT_SECURE_NO_WARNINGS)
+else()
+  add_definitions(-Wall)
+endif()
+include_directories(${WEBP_DEP_INCLUDE_DIRS})
+add_library(webpdecode OBJECT ${WEBP_DEC_SRCS})
+target_include_directories(webpdecode
+                           PRIVATE ${CMAKE_CURRENT_BINARY_DIR}
+                                   ${CMAKE_CURRENT_SOURCE_DIR})
+add_library(webpdspdecode OBJECT ${WEBP_DSP_COMMON_SRCS} ${WEBP_DSP_DEC_SRCS})
+target_include_directories(webpdspdecode
+                           PRIVATE ${CMAKE_CURRENT_BINARY_DIR}
+                                   ${CMAKE_CURRENT_SOURCE_DIR})
+add_library(webputilsdecode
+            OBJECT
+            ${WEBP_UTILS_COMMON_SRCS}
+            ${WEBP_UTILS_DEC_SRCS})
+target_include_directories(webputilsdecode
+                           PRIVATE ${CMAKE_CURRENT_BINARY_DIR}
+                                   ${CMAKE_CURRENT_SOURCE_DIR})
+add_library(webpdecoder
+            $<TARGET_OBJECTS:webpdecode>
+            $<TARGET_OBJECTS:webpdspdecode>
+            $<TARGET_OBJECTS:webputilsdecode>)
+if(XCODE)
+  libwebp_add_stub_file(webpdecoder)
+endif()
+target_link_libraries(webpdecoder ${WEBP_DEP_LIBRARIES})
+target_include_directories(
+  webpdecoder
+  PRIVATE ${CMAKE_CURRENT_BINARY_DIR} ${CMAKE_CURRENT_SOURCE_DIR}
+  INTERFACE $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}>
+            $<INSTALL_INTERFACE:${CMAKE_INSTALL_INCLUDEDIR}>)
+set_target_properties(
+  webpdecoder
+  PROPERTIES PUBLIC_HEADER "${CMAKE_CURRENT_SOURCE_DIR}/src/webp/decode.h;\
+${CMAKE_CURRENT_SOURCE_DIR}/src/webp/types.h")
+
+configure_pkg_config("src/libwebpdecoder.pc")
+
+# Build the webp library.
+add_library(webpencode OBJECT ${WEBP_ENC_SRCS})
+target_include_directories(webpencode
+                           PRIVATE ${CMAKE_CURRENT_BINARY_DIR}
+                                   ${CMAKE_CURRENT_SOURCE_DIR})
+add_library(webpdsp
+            OBJECT
+            ${WEBP_DSP_COMMON_SRCS}
+            ${WEBP_DSP_DEC_SRCS}
+            ${WEBP_DSP_ENC_SRCS})
+target_include_directories(webpdsp
+                           PRIVATE ${CMAKE_CURRENT_BINARY_DIR}
+                                   ${CMAKE_CURRENT_SOURCE_DIR})
+add_library(webputils
+            OBJECT
+            ${WEBP_UTILS_COMMON_SRCS}
+            ${WEBP_UTILS_DEC_SRCS}
+            ${WEBP_UTILS_ENC_SRCS})
+target_include_directories(webputils
+                           PRIVATE ${CMAKE_CURRENT_BINARY_DIR}
+                                   ${CMAKE_CURRENT_SOURCE_DIR})
+add_library(webp
+            $<TARGET_OBJECTS:sharpyuv>
+            $<TARGET_OBJECTS:webpdecode>
+            $<TARGET_OBJECTS:webpdsp>
+            $<TARGET_OBJECTS:webpencode>
+            $<TARGET_OBJECTS:webputils>)
+if(XCODE)
+  libwebp_add_stub_file(webp)
+endif()
+target_link_libraries(webp ${WEBP_DEP_LIBRARIES})
+target_include_directories(
+  webp
+  PRIVATE ${CMAKE_CURRENT_SOURCE_DIR}
+          ${CMAKE_CURRENT_BINARY_DIR}
+  PUBLIC $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/src>
+         $<INSTALL_INTERFACE:include>)
+set_target_properties(
+  webp
+  PROPERTIES PUBLIC_HEADER "${CMAKE_CURRENT_SOURCE_DIR}/src/webp/decode.h;\
+${CMAKE_CURRENT_SOURCE_DIR}/src/webp/encode.h;\
+${CMAKE_CURRENT_SOURCE_DIR}/src/webp/types.h")
+
+# Make sure the OBJECT libraries are built with position independent code (it is
+# not ON by default).
+set_target_properties(sharpyuv
+                      webpdecode
+                      webpdspdecode
+                      webputilsdecode
+                      webpencode
+                      webpdsp
+                      webputils
+                      PROPERTIES POSITION_INDEPENDENT_CODE ON)
+configure_pkg_config("src/libwebp.pc")
+
+# Build the webp demux library.
+add_library(webpdemux ${WEBP_DEMUX_SRCS})
+target_link_libraries(webpdemux webp)
+target_include_directories(webpdemux
+                           PRIVATE ${CMAKE_CURRENT_SOURCE_DIR}
+                                   ${CMAKE_CURRENT_BINARY_DIR}
+                           PUBLIC $<INSTALL_INTERFACE:include>)
+set_target_properties(
+  webpdemux
+  PROPERTIES PUBLIC_HEADER "${CMAKE_CURRENT_SOURCE_DIR}/src/webp/decode.h;\
+${CMAKE_CURRENT_SOURCE_DIR}/src/webp/demux.h;\
+${CMAKE_CURRENT_SOURCE_DIR}/src/webp/mux_types.h;\
+${CMAKE_CURRENT_SOURCE_DIR}/src/webp/types.h")
+
+configure_pkg_config("src/demux/libwebpdemux.pc")
+
 # Set the version numbers.
 macro(set_version FILE TARGET_NAME NAME_IN_MAKEFILE)
-  file(READ ${CMAKE_CURRENT_SOURCE_DIR}/${FILE} SOURCE_FILE)
+  file(READ ${CMAKE_CURRENT_SOURCE_DIR}/src/${FILE} SOURCE_FILE)
  string(REGEX MATCH
-               "${NAME_IN_MAKEFILE}_la_LDFLAGS[^\n]* -version-info [0-9:]+" TMP
+               "${NAME_IN_MAKEFILE}_la_LDFLAGS[^\n]* -version-info [0-9:]+"
+               TMP
               ${SOURCE_FILE})
-  string(REGEX MATCH "[0-9:]+" TMP ${TMP})
-  string(REGEX REPLACE ":" " " LT_VERSION ${TMP})
+  string(REGEX MATCH
+               "[0-9:]+"
+               TMP
+               ${TMP})
+  string(REGEX
+         REPLACE ":"
+                 " "
+                 LT_VERSION
+                 ${TMP})

  # See the libtool docs for more information:
  # https://www.gnu.org/software/libtool/manual/libtool.html#Updating-version-info
@@ -271,164 +392,23 @@ macro(set_version FILE TARGET_NAME NAME_IN_MAKEFILE)

  set_target_properties(
    ${TARGET_NAME}
-    PROPERTIES VERSION ${LT_CURRENT_MINUS_AGE}.${LT_AGE}.${LT_REVISION}
-               SOVERSION ${LT_CURRENT_MINUS_AGE})
-  if(APPLE)
-    # For compatibility, set MACHO_COMPATIBILITY_VERSION and
-    # MACHO_CURRENT_VERSION to match libtool. These properties were introduced
-    # in 3.17:
-    # https://cmake.org/cmake/help/latest/prop_tgt/MACHO_COMPATIBILITY_VERSION.html
-    math(EXPR LIBWEBP_MACHO_COMPATIBILITY_VERSION "${LT_CURRENT} + 1")
-    set_target_properties(
-      ${TARGET_NAME}
-      PROPERTIES MACHO_COMPATIBILITY_VERSION
-                 ${LIBWEBP_MACHO_COMPATIBILITY_VERSION}
-                 MACHO_CURRENT_VERSION
-                 ${LIBWEBP_MACHO_COMPATIBILITY_VERSION}.${LT_REVISION})
-  endif()
+    PROPERTIES VERSION
+               ${LT_CURRENT_MINUS_AGE}.${LT_AGE}.${LT_REVISION}
+               SOVERSION
+               ${LT_CURRENT_MINUS_AGE})
 endmacro()
-
-# ##############################################################################
-# Build the webpdecoder library.
-
-# Creates a source file with an unused stub function in $CMAKE_BINARY_DIR and
-# adds it to the specified target. Currently used only with Xcode.
-#
-# See also:
-# https://cmake.org/cmake/help/v3.18/command/add_library.html#object-libraries
-# "Some native build systems (such as Xcode) may not like targets that have only
-# object files, so consider adding at least one real source file to any target
-# that references $<TARGET_OBJECTS:objlib>."
-function(libwebp_add_stub_file TARGET)
-  set(stub_source_dir "${CMAKE_BINARY_DIR}")
-  set(stub_source_file "${stub_source_dir}/libwebp_${TARGET}_stub.c")
-  set(stub_source_code
-      "// Generated file. DO NOT EDIT!\n"
-      "// C source file created for target ${TARGET}.\n"
-      "void libwebp_${TARGET}_stub_function(void)\;\n"
-      "void libwebp_${TARGET}_stub_function(void) {}\n")
-  file(WRITE "${stub_source_file}" ${stub_source_code})
-
-  target_sources(${TARGET} PRIVATE ${stub_source_file})
-endfunction()
-
-parse_makefile_am(${CMAKE_CURRENT_SOURCE_DIR}/sharpyuv "WEBP_SHARPYUV_SRCS" "")
-add_library(sharpyuv ${WEBP_SHARPYUV_SRCS})
-target_link_libraries(sharpyuv ${SHARPYUV_DEP_LIBRARIES})
-set_version(sharpyuv/Makefile.am sharpyuv sharpyuv)
-target_include_directories(
-  sharpyuv PRIVATE ${CMAKE_CURRENT_BINARY_DIR} ${CMAKE_CURRENT_SOURCE_DIR}
-                   ${CMAKE_CURRENT_SOURCE_DIR}/src)
-set_target_properties(
-  sharpyuv
-  PROPERTIES PUBLIC_HEADER "${CMAKE_CURRENT_SOURCE_DIR}/sharpyuv/sharpyuv.h;\
-${CMAKE_CURRENT_SOURCE_DIR}/sharpyuv/sharpyuv_csp.h")
-configure_pkg_config("sharpyuv/libsharpyuv.pc")
-install(
-  TARGETS sharpyuv
-  EXPORT ${PROJECT_NAME}Targets
-  PUBLIC_HEADER DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}/webp/sharpyuv
-  INCLUDES
-  DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}
-  ${CMAKE_INSTALL_INCLUDEDIR}/webp
-  ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR}
-  LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR}
-  RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR})
-
-if(MSVC)
-  # avoid security warnings for e.g., fopen() used in the examples.
-  add_definitions(-D_CRT_SECURE_NO_WARNINGS)
-else()
-  add_compile_options(-Wall)
-endif()
-include_directories(${WEBP_DEP_INCLUDE_DIRS})
-add_library(webpdecode OBJECT ${WEBP_DEC_SRCS})
-target_include_directories(webpdecode PRIVATE ${CMAKE_CURRENT_BINARY_DIR}
-                                              ${CMAKE_CURRENT_SOURCE_DIR})
-add_library(webpdspdecode OBJECT ${WEBP_DSP_COMMON_SRCS} ${WEBP_DSP_DEC_SRCS})
-target_include_directories(webpdspdecode PRIVATE ${CMAKE_CURRENT_BINARY_DIR}
-                                                 ${CMAKE_CURRENT_SOURCE_DIR})
-add_library(webputilsdecode OBJECT ${WEBP_UTILS_COMMON_SRCS}
-                                   ${WEBP_UTILS_DEC_SRCS})
-target_include_directories(webputilsdecode PRIVATE ${CMAKE_CURRENT_BINARY_DIR}
-                                                   ${CMAKE_CURRENT_SOURCE_DIR})
-add_library(
-  webpdecoder $<TARGET_OBJECTS:webpdecode> $<TARGET_OBJECTS:webpdspdecode>
-              $<TARGET_OBJECTS:webputilsdecode>)
-if(XCODE)
-  libwebp_add_stub_file(webpdecoder)
-endif()
-target_link_libraries(webpdecoder ${WEBP_DEP_LIBRARIES})
-target_include_directories(
-  webpdecoder PRIVATE ${CMAKE_CURRENT_BINARY_DIR} ${CMAKE_CURRENT_SOURCE_DIR}
-  INTERFACE $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}>
-            $<INSTALL_INTERFACE:${CMAKE_INSTALL_INCLUDEDIR}>)
-set_target_properties(
-  webpdecoder
-  PROPERTIES PUBLIC_HEADER "${CMAKE_CURRENT_SOURCE_DIR}/src/webp/decode.h;\
-${CMAKE_CURRENT_SOURCE_DIR}/src/webp/types.h")
-
-configure_pkg_config("src/libwebpdecoder.pc")
-
-# Build the webp library.
-add_library(webpencode OBJECT ${WEBP_ENC_SRCS})
-target_include_directories(
-  webpencode PRIVATE ${CMAKE_CURRENT_BINARY_DIR} ${CMAKE_CURRENT_SOURCE_DIR}
-                     ${CMAKE_CURRENT_SOURCE_DIR}/src)
-add_library(webpdsp OBJECT ${WEBP_DSP_COMMON_SRCS} ${WEBP_DSP_DEC_SRCS}
-                           ${WEBP_DSP_ENC_SRCS})
-target_include_directories(webpdsp PRIVATE ${CMAKE_CURRENT_BINARY_DIR}
-                                           ${CMAKE_CURRENT_SOURCE_DIR})
-add_library(webputils OBJECT ${WEBP_UTILS_COMMON_SRCS} ${WEBP_UTILS_DEC_SRCS}
-                             ${WEBP_UTILS_ENC_SRCS})
-target_include_directories(webputils PRIVATE ${CMAKE_CURRENT_BINARY_DIR}
-                                             ${CMAKE_CURRENT_SOURCE_DIR})
-add_library(webp $<TARGET_OBJECTS:webpdecode> $<TARGET_OBJECTS:webpdsp>
-                 $<TARGET_OBJECTS:webpencode> $<TARGET_OBJECTS:webputils>)
-target_link_libraries(webp sharpyuv)
-if(XCODE)
-  libwebp_add_stub_file(webp)
-endif()
-target_link_libraries(webp ${WEBP_DEP_LIBRARIES})
-target_include_directories(
-  webp PRIVATE ${CMAKE_CURRENT_SOURCE_DIR} ${CMAKE_CURRENT_BINARY_DIR}
-  PUBLIC $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/src>
-         $<INSTALL_INTERFACE:include>)
-set_target_properties(
-  webp
-  PROPERTIES PUBLIC_HEADER "${CMAKE_CURRENT_SOURCE_DIR}/src/webp/decode.h;\
-${CMAKE_CURRENT_SOURCE_DIR}/src/webp/encode.h;\
-${CMAKE_CURRENT_SOURCE_DIR}/src/webp/types.h")
-
-# Make sure the OBJECT libraries are built with position independent code (it is
-# not ON by default).
-set_target_properties(webpdecode webpdspdecode webputilsdecode webpencode
-                      webpdsp webputils PROPERTIES POSITION_INDEPENDENT_CODE ON)
-configure_pkg_config("src/libwebp.pc")
-
-# Build the webp demux library.
-add_library(webpdemux ${WEBP_DEMUX_SRCS})
-target_link_libraries(webpdemux webp)
-target_include_directories(
-  webpdemux PRIVATE ${CMAKE_CURRENT_SOURCE_DIR} ${CMAKE_CURRENT_BINARY_DIR}
-  PUBLIC $<INSTALL_INTERFACE:include>)
-set_target_properties(
-  webpdemux
-  PROPERTIES
-    PUBLIC_HEADER
-    "${CMAKE_CURRENT_SOURCE_DIR}/src/webp/decode.h;\
-${CMAKE_CURRENT_SOURCE_DIR}/src/webp/demux.h;\
-${CMAKE_CURRENT_SOURCE_DIR}/src/webp/mux_types.h;\
-${CMAKE_CURRENT_SOURCE_DIR}/src/webp/types.h")
-
-configure_pkg_config("src/demux/libwebpdemux.pc")
-
-set_version(src/Makefile.am webp webp)
-set_version(src/Makefile.am webpdecoder webpdecoder)
-set_version(src/demux/Makefile.am webpdemux webpdemux)
+set_version(Makefile.am webp webp)
+set_version(Makefile.am webpdecoder webpdecoder)
+set_version(demux/Makefile.am webpdemux webpdemux)
 file(READ ${CMAKE_CURRENT_SOURCE_DIR}/configure.ac CONFIGURE_FILE)
-string(REGEX MATCH "AC_INIT\\([^\n]*\\[[0-9\\.]+\\]" TMP ${CONFIGURE_FILE})
-string(REGEX MATCH "[0-9\\.]+" PROJECT_VERSION ${TMP})
+string(REGEX MATCH
+             "AC_INIT\\([^\n]*\\[[0-9\\.]+\\]"
+             TMP
+             ${CONFIGURE_FILE})
+string(REGEX MATCH
+             "[0-9\\.]+"
+             PROJECT_VERSION
+             ${TMP})

 # Define the libraries to install.
 list(APPEND INSTALLED_LIBRARIES webpdecoder webp webpdemux)
@@ -441,8 +421,10 @@ math(EXPR WEBP_SIMD_FILES_TO_INCLUDE_RANGE
 foreach(I_FILE RANGE ${WEBP_SIMD_FILES_TO_INCLUDE_RANGE})
  list(GET WEBP_SIMD_FILES_TO_INCLUDE ${I_FILE} FILE)
  list(GET WEBP_SIMD_FLAGS_TO_INCLUDE ${I_FILE} SIMD_COMPILE_FLAG)
-  set_source_files_properties(${FILE} PROPERTIES COMPILE_FLAGS
-                                                 ${SIMD_COMPILE_FLAG})
+  set_source_files_properties(${FILE}
+                              PROPERTIES
+                              COMPILE_FLAGS
+                              ${SIMD_COMPILE_FLAG})
 endforeach()

 if(NOT WEBP_BUILD_LIBWEBPMUX)
@@ -474,7 +456,8 @@ if(WEBP_BUILD_ANIM_UTILS
  list(APPEND EXAMPLEUTIL_SRCS ${CMAKE_CURRENT_SOURCE_DIR}/examples/stopwatch.h)
  add_library(exampleutil STATIC ${EXAMPLEUTIL_SRCS})
  target_include_directories(
-    exampleutil PUBLIC $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/src>)
+    exampleutil
+    PUBLIC $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/src>)

  parse_makefile_am(${CMAKE_CURRENT_SOURCE_DIR}/imageio "IMAGEIOUTILS_SRCS"
                    "imageio_util_[^ ]*")
@@ -486,7 +469,10 @@ if(WEBP_BUILD_ANIM_UTILS
  parse_makefile_am(${CMAKE_CURRENT_SOURCE_DIR}/imageio "IMAGEDEC_SRCS"
                    "imagedec_[^ ]*")
  add_library(imagedec STATIC ${IMAGEDEC_SRCS})
-  target_link_libraries(imagedec imageioutil webpdemux webp
+  target_link_libraries(imagedec
+                        imageioutil
+                        webpdemux
+                        webp
                        ${WEBP_DEP_IMG_LIBRARIES})

  # Image-encoding utility library.
@@ -495,10 +481,12 @@ if(WEBP_BUILD_ANIM_UTILS
  add_library(imageenc STATIC ${IMAGEENC_SRCS})
  target_link_libraries(imageenc imageioutil webp)

-  set_property(
-    TARGET exampleutil imageioutil imagedec imageenc
-    PROPERTY INCLUDE_DIRECTORIES ${CMAKE_CURRENT_SOURCE_DIR}/src
-             ${CMAKE_CURRENT_BINARY_DIR}/src)
+  set_property(TARGET exampleutil
+                      imageioutil
+                      imagedec
+                      imageenc
+               PROPERTY INCLUDE_DIRECTORIES ${CMAKE_CURRENT_SOURCE_DIR}/src
+                        ${CMAKE_CURRENT_BINARY_DIR}/src)
 endif()

 if(WEBP_BUILD_DWEBP)
@@ -515,25 +503,24 @@ if(WEBP_BUILD_CWEBP)
  parse_makefile_am(${CMAKE_CURRENT_SOURCE_DIR}/examples "CWEBP_SRCS" "cwebp")
  add_executable(cwebp ${CWEBP_SRCS})
  target_link_libraries(cwebp exampleutil imagedec webp)
-  target_include_directories(cwebp PRIVATE ${CMAKE_CURRENT_BINARY_DIR}/src
-                                           ${CMAKE_CURRENT_SOURCE_DIR})
+  target_include_directories(cwebp PRIVATE ${CMAKE_CURRENT_BINARY_DIR}/src)
  install(TARGETS cwebp RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR})
 endif()

 if(WEBP_BUILD_LIBWEBPMUX)
  parse_makefile_am(${CMAKE_CURRENT_SOURCE_DIR}/src/mux "WEBP_MUX_SRCS" "")
-  add_library(libwebpmux ${WEBP_MUX_SRCS})
-  target_link_libraries(libwebpmux webp)
-  target_include_directories(libwebpmux PRIVATE ${CMAKE_CURRENT_BINARY_DIR}
-                                                ${CMAKE_CURRENT_SOURCE_DIR})
-  set_version(src/mux/Makefile.am libwebpmux webpmux)
-  set_target_properties(
-    libwebpmux
-    PROPERTIES PUBLIC_HEADER "${CMAKE_CURRENT_SOURCE_DIR}/src/webp/mux.h;\
+  add_library(webpmux ${WEBP_MUX_SRCS})
+  target_link_libraries(webpmux webp)
+  target_include_directories(webpmux
+                             PRIVATE ${CMAKE_CURRENT_BINARY_DIR}
+                                     ${CMAKE_CURRENT_SOURCE_DIR})
+  set_version(mux/Makefile.am webpmux webpmux)
+  set_target_properties(webpmux
+                        PROPERTIES PUBLIC_HEADER
+                                   "${CMAKE_CURRENT_SOURCE_DIR}/src/webp/mux.h;\
 ${CMAKE_CURRENT_SOURCE_DIR}/src/webp/mux_types.h;\
 ${CMAKE_CURRENT_SOURCE_DIR}/src/webp/types.h;")
-  set_target_properties(libwebpmux PROPERTIES OUTPUT_NAME webpmux)
-  list(APPEND INSTALLED_LIBRARIES libwebpmux)
+  list(APPEND INSTALLED_LIBRARIES webpmux)
  configure_pkg_config("src/mux/libwebpmux.pc")
 endif()

@@ -543,7 +530,11 @@ if(WEBP_BUILD_GIF2WEBP)
  parse_makefile_am(${CMAKE_CURRENT_SOURCE_DIR}/examples "GIF2WEBP_SRCS"
                    "gif2webp")
  add_executable(gif2webp ${GIF2WEBP_SRCS})
-  target_link_libraries(gif2webp exampleutil imageioutil webp libwebpmux
+  target_link_libraries(gif2webp
+                        exampleutil
+                        imageioutil
+                        webp
+                        webpmux
                        ${WEBP_DEP_GIF_LIBRARIES})
  target_include_directories(gif2webp PRIVATE ${CMAKE_CURRENT_BINARY_DIR}/src)
  install(TARGETS gif2webp RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR})
@@ -555,10 +546,13 @@ if(WEBP_BUILD_IMG2WEBP)
  parse_makefile_am(${CMAKE_CURRENT_SOURCE_DIR}/examples "IMG2WEBP_SRCS"
                    "img2webp")
  add_executable(img2webp ${IMG2WEBP_SRCS})
-  target_link_libraries(img2webp exampleutil imagedec imageioutil webp
-                        libwebpmux)
-  target_include_directories(img2webp PRIVATE ${CMAKE_CURRENT_BINARY_DIR}/src
-                                              ${CMAKE_CURRENT_SOURCE_DIR})
+  target_link_libraries(img2webp
+                        exampleutil
+                        imagedec
+                        imageioutil
+                        webp
+                        webpmux)
+  target_include_directories(img2webp PRIVATE ${CMAKE_CURRENT_BINARY_DIR}/src)
  install(TARGETS img2webp RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR})
 endif()

@@ -569,17 +563,17 @@ if(WEBP_BUILD_VWEBP)
    include_directories(${WEBP_DEP_IMG_INCLUDE_DIRS})
    parse_makefile_am(${CMAKE_CURRENT_SOURCE_DIR}/examples "VWEBP_SRCS" "vwebp")
    add_executable(vwebp ${VWEBP_SRCS})
-    target_link_libraries(
-      vwebp
-      ${OPENGL_LIBRARIES}
-      exampleutil
-      GLUT::GLUT
-      imageioutil
-      webp
-      webpdemux)
-    target_include_directories(
-      vwebp PRIVATE ${GLUT_INCLUDE_DIR} ${CMAKE_CURRENT_BINARY_DIR}/src
-                    ${OPENGL_INCLUDE_DIR})
+    target_link_libraries(vwebp
+                          ${OPENGL_LIBRARIES}
+                          exampleutil
+                          ${GLUT_glut_LIBRARY}
+                          imageioutil
+                          webp
+                          webpdemux)
+    target_include_directories(vwebp
+                               PRIVATE ${GLUT_INCLUDE_DIR}
+                                       ${CMAKE_CURRENT_BINARY_DIR}/src
+                                       ${OPENGL_INCLUDE_DIR})
    install(TARGETS vwebp RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR})
    if(${CMAKE_SYSTEM_NAME} STREQUAL "Darwin")
      check_c_compiler_flag("-Wno-deprecated-declarations" HAS_NO_DEPRECATED)
@@ -597,8 +591,9 @@ if(WEBP_BUILD_WEBPINFO)
                    "webpinfo")
  add_executable(webpinfo ${WEBPINFO_SRCS})
  target_link_libraries(webpinfo exampleutil imageioutil)
-  target_include_directories(webpinfo PRIVATE ${CMAKE_CURRENT_BINARY_DIR}/src
-                                              ${CMAKE_CURRENT_SOURCE_DIR}/src)
+  target_include_directories(webpinfo
+                             PRIVATE ${CMAKE_CURRENT_BINARY_DIR}/src
+                                     ${CMAKE_CURRENT_SOURCE_DIR}/src)
  install(TARGETS webpinfo RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR})
 endif()

@@ -606,10 +601,12 @@ if(WEBP_BUILD_WEBPMUX)
  # webpmux
  parse_makefile_am(${CMAKE_CURRENT_SOURCE_DIR}/examples "WEBPMUX_SRCS"
                    "webpmux")
-  add_executable(webpmux ${WEBPMUX_SRCS})
-  target_link_libraries(webpmux exampleutil imageioutil libwebpmux webp)
-  target_include_directories(webpmux PRIVATE ${CMAKE_CURRENT_BINARY_DIR}/src)
-  install(TARGETS webpmux RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR})
+  add_executable(webpmux_app ${WEBPMUX_SRCS})
+  set_target_properties(webpmux_app PROPERTIES OUTPUT_NAME webpmux)
+  target_link_libraries(webpmux_app exampleutil imageioutil webpmux webp)
+  target_include_directories(webpmux_app
+                             PRIVATE ${CMAKE_CURRENT_BINARY_DIR}/src)
+  install(TARGETS webpmux_app RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR})
 endif()

 if(WEBP_BUILD_EXTRAS)
@@ -621,46 +618,41 @@ if(WEBP_BUILD_EXTRAS)

  # libextras
  add_library(extras STATIC ${WEBP_EXTRAS_SRCS})
-  target_include_directories(
-    extras PRIVATE ${CMAKE_CURRENT_BINARY_DIR} ${CMAKE_CURRENT_SOURCE_DIR}
-                   ${CMAKE_CURRENT_SOURCE_DIR}/src)
+  target_include_directories(extras
+                             PRIVATE ${CMAKE_CURRENT_BINARY_DIR}
+                             ${CMAKE_CURRENT_SOURCE_DIR}
+                             ${CMAKE_CURRENT_SOURCE_DIR}/src)

  # get_disto
  add_executable(get_disto ${GET_DISTO_SRCS})
  target_link_libraries(get_disto imagedec)
-  target_include_directories(get_disto PRIVATE ${CMAKE_CURRENT_SOURCE_DIR}
-                                               ${CMAKE_CURRENT_BINARY_DIR}/src)
+  target_include_directories(get_disto
+                             PRIVATE ${CMAKE_CURRENT_SOURCE_DIR}
+                                     ${CMAKE_CURRENT_BINARY_DIR}/src)

  # webp_quality
  add_executable(webp_quality ${WEBP_QUALITY_SRCS})
  target_link_libraries(webp_quality exampleutil imagedec extras)
-  target_include_directories(webp_quality PRIVATE ${CMAKE_CURRENT_SOURCE_DIR}
-                                                  ${CMAKE_CURRENT_BINARY_DIR})
+  target_include_directories(webp_quality
+                             PRIVATE ${CMAKE_CURRENT_SOURCE_DIR}
+                                     ${CMAKE_CURRENT_BINARY_DIR})

  # vwebp_sdl
  find_package(SDL)
  if(WEBP_BUILD_VWEBP AND SDL_FOUND)
    add_executable(vwebp_sdl ${VWEBP_SDL_SRCS})
    target_link_libraries(vwebp_sdl ${SDL_LIBRARY} imageioutil webp)
-    target_include_directories(
-      vwebp_sdl PRIVATE ${CMAKE_CURRENT_SOURCE_DIR} ${CMAKE_CURRENT_BINARY_DIR}
-                        ${CMAKE_CURRENT_BINARY_DIR}/src ${SDL_INCLUDE_DIR})
+    target_include_directories(vwebp_sdl
+                               PRIVATE ${CMAKE_CURRENT_SOURCE_DIR}
+                                       ${CMAKE_CURRENT_BINARY_DIR}
+                                       ${CMAKE_CURRENT_BINARY_DIR}/src
+                                       ${SDL_INCLUDE_DIR})
    set(WEBP_HAVE_SDL 1)
    target_compile_definitions(vwebp_sdl PUBLIC WEBP_HAVE_SDL)
  endif()
 endif()

 if(WEBP_BUILD_WEBP_JS)
-  # The default stack size changed from 5MB to 64KB in 3.1.27. See
-  # https://crbug.com/webp/614.
-  if(EMSCRIPTEN_VERSION VERSION_GREATER_EQUAL "3.1.27")
-    # TOTAL_STACK size was renamed to STACK_SIZE in 3.1.27. The old name was
-    # kept for compatibility, but prefer the new one in case it is removed in
-    # the future.
-    set(emscripten_stack_size "-sSTACK_SIZE=5MB")
-  else()
-    set(emscripten_stack_size "-sTOTAL_STACK=5MB")
-  endif()
  # wasm2js does not support SIMD.
  if(NOT WEBP_ENABLE_SIMD)
    # JavaScript version
@@ -670,9 +662,9 @@ if(WEBP_BUILD_WEBP_JS)
    set(WEBP_HAVE_SDL 1)
    set_target_properties(
      webp_js
-      PROPERTIES LINK_FLAGS "-sWASM=0 ${emscripten_stack_size} \
-         -sEXPORTED_FUNCTIONS=_WebPToSDL -sINVOKE_RUN=0 \
-         -sEXPORTED_RUNTIME_METHODS=cwrap")
+      PROPERTIES LINK_FLAGS "-s WASM=0 \
+         -s EXPORTED_FUNCTIONS='[\"_WebpToSDL\"]' -s INVOKE_RUN=0 \
+         -s EXPORTED_RUNTIME_METHODS='[\"cwrap\"]'")
    set_target_properties(webp_js PROPERTIES OUTPUT_NAME webp)
    target_compile_definitions(webp_js PUBLIC EMSCRIPTEN WEBP_HAVE_SDL)
  endif()
@@ -683,9 +675,9 @@ if(WEBP_BUILD_WEBP_JS)
  target_include_directories(webp_wasm PRIVATE ${CMAKE_CURRENT_BINARY_DIR})
  set_target_properties(
    webp_wasm
-    PROPERTIES LINK_FLAGS "-sWASM=1 ${emscripten_stack_size} \
-       -sEXPORTED_FUNCTIONS=_WebPToSDL -sINVOKE_RUN=0 \
-       -sEXPORTED_RUNTIME_METHODS=cwrap")
+    PROPERTIES LINK_FLAGS "-s WASM=1 \
+       -s EXPORTED_FUNCTIONS='[\"_WebpToSDL\"]' -s INVOKE_RUN=0 \
+       -s EXPORTED_RUNTIME_METHODS='[\"cwrap\"]'")
  target_compile_definitions(webp_wasm PUBLIC EMSCRIPTEN WEBP_HAVE_SDL)

  target_compile_definitions(webpdspdecode PUBLIC EMSCRIPTEN)
@@ -697,15 +689,14 @@ if(WEBP_BUILD_ANIM_UTILS)
  parse_makefile_am(${CMAKE_CURRENT_SOURCE_DIR}/examples "ANIM_DIFF_SRCS"
                    "anim_diff")
  add_executable(anim_diff ${ANIM_DIFF_SRCS})
-  target_link_libraries(
-    anim_diff
-    exampleutil
-    imagedec
-    imageenc
-    imageioutil
-    webp
-    webpdemux
-    ${WEBP_DEP_GIF_LIBRARIES})
+  target_link_libraries(anim_diff
+                        exampleutil
+                        imagedec
+                        imageenc
+                        imageioutil
+                        webp
+                        webpdemux
+                        ${WEBP_DEP_GIF_LIBRARIES})
  target_include_directories(anim_diff PRIVATE ${CMAKE_CURRENT_BINARY_DIR}/src)

  # anim_dump
@@ -713,59 +704,45 @@ if(WEBP_BUILD_ANIM_UTILS)
  parse_makefile_am(${CMAKE_CURRENT_SOURCE_DIR}/examples "ANIM_DUMP_SRCS"
                    "anim_dump")
  add_executable(anim_dump ${ANIM_DUMP_SRCS})
-  target_link_libraries(
-    anim_dump
-    exampleutil
-    imagedec
-    imageenc
-    imageioutil
-    webp
-    webpdemux
-    ${WEBP_DEP_GIF_LIBRARIES})
+  target_link_libraries(anim_dump
+                        exampleutil
+                        imagedec
+                        imageenc
+                        imageioutil
+                        webp
+                        webpdemux
+                        ${WEBP_DEP_GIF_LIBRARIES})
  target_include_directories(anim_dump PRIVATE ${CMAKE_CURRENT_BINARY_DIR}/src)
 endif()

 # Install the different headers and libraries.
-install(
-  TARGETS ${INSTALLED_LIBRARIES}
-  EXPORT ${PROJECT_NAME}Targets
-  PUBLIC_HEADER DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}/webp
-  INCLUDES
-  DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}
-  ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR}
-  LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR}
-  RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR})
+install(TARGETS ${INSTALLED_LIBRARIES}
+        EXPORT ${PROJECT_NAME}Targets
+        PUBLIC_HEADER DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}/webp
+        INCLUDES
+        DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}
+        ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR}
+        LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR}
+        RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR})
 set(ConfigPackageLocation ${CMAKE_INSTALL_DATADIR}/${PROJECT_NAME}/cmake/)
-install(EXPORT ${PROJECT_NAME}Targets NAMESPACE ${PROJECT_NAME}::
+install(EXPORT ${PROJECT_NAME}Targets
+        NAMESPACE ${PROJECT_NAME}::
        DESTINATION ${ConfigPackageLocation})

 # Create the CMake version file.
 include(CMakePackageConfigHelpers)
 write_basic_package_version_file(
  "${CMAKE_CURRENT_BINARY_DIR}/WebPConfigVersion.cmake"
-  VERSION ${PACKAGE_VERSION} COMPATIBILITY AnyNewerVersion)
+  VERSION ${PACKAGE_VERSION}
+  COMPATIBILITY AnyNewerVersion)

 # Create the Config file.
 include(CMakePackageConfigHelpers)
-# Fix libwebpmux reference. The target name libwebpmux is used for compatibility
-# purposes, but the library mentioned in WebPConfig.cmake should be the
-# unprefixed version. Note string(...) can be replaced with list(TRANSFORM ...)
-# if cmake_minimum_required is >= 3.12.
-string(REGEX REPLACE "libwebpmux" "webpmux" INSTALLED_LIBRARIES
-                     "${INSTALLED_LIBRARIES}")
-
-if(MSVC)
-  # For compatibility with nmake, MSVC builds use a custom prefix (lib) that
-  # needs to be included in the library name.
-  string(REGEX REPLACE "[A-Za-z0-9_]+" "${CMAKE_STATIC_LIBRARY_PREFIX}\\0"
-                       INSTALLED_LIBRARIES "${INSTALLED_LIBRARIES}")
-endif()
-
 configure_package_config_file(
  ${CMAKE_CURRENT_SOURCE_DIR}/cmake/WebPConfig.cmake.in
  ${CMAKE_CURRENT_BINARY_DIR}/WebPConfig.cmake
-  INSTALL_DESTINATION ${ConfigPackageLocation}
-  PATH_VARS CMAKE_INSTALL_INCLUDEDIR)
+  INSTALL_DESTINATION
+  ${ConfigPackageLocation})

 # Install the generated CMake files.
 install(FILES "${CMAKE_CURRENT_BINARY_DIR}/WebPConfigVersion.cmake"
@@ -797,6 +774,7 @@ foreach(I_MAN RANGE ${MAN_PAGES_RANGE})
  if(WEBP_BUILD_${EXEC_BUILD})
    list(GET MAN_PAGES ${I_MAN} MAN_PAGE)
    install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/man/${MAN_PAGE}
-            DESTINATION ${CMAKE_INSTALL_MANDIR}/man1 COMPONENT doc)
+            DESTINATION ${CMAKE_INSTALL_MANDIR}/man1
+            COMPONENT doc)
  endif()
 endforeach()
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -19,59 +19,10 @@ again.

 All submissions, including submissions by project members, require review. We
 use a [Gerrit](https://www.gerritcodereview.com) instance hosted at
-https://chromium-review.googlesource.com for this purpose.
-
-## Sending patches
-
-The basic git workflow for modifying libwebp code and sending for review is:
-
-1.  Get the latest version of the repository locally:
-
-    ```sh
-    git clone https://chromium.googlesource.com/webm/libwebp && cd libwebp
-    ```
-
-2.  Copy the commit-msg script into ./git/hooks (this will add an ID to all of
-    your commits):
-
-    ```sh
-    curl -Lo .git/hooks/commit-msg https://chromium-review.googlesource.com/tools/hooks/commit-msg && chmod u+x .git/hooks/commit-msg
-    ```
-
-3.  Modify the local copy of libwebp. Make sure the code
-    [builds successfully](https://chromium.googlesource.com/webm/libwebp/+/HEAD/doc/building.md#cmake).
-
-4.  Choose a short and representative commit message:
-
-    ```sh
-    git commit -a -m "Set commit message here"
-    ```
-
-5.  Send the patch for review:
-
-    ```sh
-    git push https://chromium-review.googlesource.com/webm/libwebp HEAD:refs/for/main
-    ```
-
-    Go to https://chromium-review.googlesource.com to view your patch and
-    request a review from the maintainers.
-
-See the
+https://chromium-review.googlesource.com for this purpose. See the
 [WebM Project page](https://www.webmproject.org/code/contribute/submitting-patches/)
 for additional details.

-## Code Style
-
-The C code style is based on the
-[Google C++ Style Guide](https://google.github.io/styleguide/cppguide.html) and
-`clang-format --style=Google`, though this project doesn't use the tool to
-enforce the formatting.
-
-CMake files are formatted with
-[cmake-format](https://cmake-format.readthedocs.io/en/latest/). `cmake-format
-i` can be used to format individual files, it will use the settings from
-`.cmake-format.py`.
-
 ## Community Guidelines

 This project follows
--- a/226
+++ b/226
@@ -1,229 +1,3 @@
-1ace578c update NEWS
-63234c42 bump version to 1.3.2
-2af26267 Fix OOB write in BuildHuffmanTable.
-fd7bb21c update ChangeLog (tag: v1.3.1-rc2, tag: v1.3.1)
-e1adea50 update NEWS
-43393320 enc/*: normalize WebPEncodingSetError() calls
-287fdefe enc/*: add missing WebPEncodingSetError() calls
-c3bd7cff EncodeAlphaInternal: add missing error check
-d49cfbb3 vp8l_enc,WriteImage: add missing error check
-2e5a9ec3 muxread,MuxImageParse: add missing error checks
-ebb6f949 cmake,emscripten: explicitly set stack size
-59a2b1f9 WebPDecodeYUV: check u/v/stride/uv_stride ptrs
-8e965ccb Call png_get_channels() to see if image has alpha
-7f0a3419 update ChangeLog (tag: v1.3.1-rc1)
-bab7efbe update NEWS
-7138bf8f bump version to 1.3.1
-435b4ded update AUTHORS
-47351229 update .mailmap
-ff6c7f4e CONTRIBUTING.md: add C style / cmake-format notes
-dd530437 add .cmake-format.py
-adbe2cb1 cmake,cosmetics: apply cmake-format
-15b36508 doc/webp-container-spec: rm future codec comment
-c369c4bf doc/webp-lossless-bitstream-spec: improve link text
-1de35f47 doc/webp-container-spec: don't use 'currently'
-bb06a16e doc/webp-container-spec: prefer present tense
-9f38b71e doc/webp-lossless-bitstream-spec: prefer present tense
-7acb6b82 doc/webp-container-spec: avoid i.e. & e.g.
-4967e7cd doc/webp-lossless-bitstream-spec: avoid i.e. & e.g.
-e3366659 Merge "Do not find_package image libraries if not needed." into main
-428588ef clarify single leaf node trees and use of canonical prefix coding
-709ec152 Do not find_package image libraries if not needed.
-8dd80ef8 fuzz_utils.h: lower kFuzzPxLimit w/ASan
-8f187b9f Clean message calls in CMake
-cba30078 WebPConfig.cmake.in: use calculated include path
-6cf9a76a Merge "webp-lossless-bitstream-spec: remove use of 'dynamics'" into main
-740943b2 Merge "Specialize and optimize ITransform_SSE2 using do_two" into main
-2d547e24 Compare kFuzzPxLimit to max_num_operations
-ac42dde1 Specialize and optimize ITransform_SSE2 using do_two
-17e0ef1d webp-lossless-bitstream-spec: remove use of 'dynamics'
-ed274371 neon.h,cosmetics: clear a couple lint warnings
-3fb82947 cpu.h,cosmetics: segment defines
-0c496a4f cpu.h: add WEBP_AARCH64
-8151f388 move VP8GetCPUInfo declaration to cpu.c
-916548c2 Make kFuzzPxLimit sanitizer dependent
-4070b271 advanced_api_fuzzer: reduce scaling limit
-761f49c3 Merge "webp-lossless-bitstream-spec: add missing bits to ABNF" into main
-84d04c48 webp-lossless-bitstream-spec: add missing bits to ABNF
-0696e1a7 advanced_api_fuzzer: reduce scaling limit
-93d88aa2 Merge "deps.cmake: remove unneeded header checks" into main
-118e0035 deps.cmake: remove unneeded header checks
-4c3d7018 webp-lossless-bitstream-spec: condense normal-prefix-code
-a6a09b32 webp-lossless-bitstream-spec: fix 2 code typos
-50ac4f7c Merge "cpu.h: enable NEON w/_M_ARM64EC" into main
-4b7d7b4f Add contribution instructions
-0afbd97b cpu.h: enable NEON w/_M_ARM64EC
-349f4353 Merge changes Ibd89e56b,Ic57e7f84,I89096614 into main
-8f7513b7 upsampling_neon.c: fix WEBP_SWAP_16BIT_CSP check
-cbf624b5 advanced_api_fuzzer: reduce scaling limit
-89edfdd1 Skip slow scaling in libwebp advanced_api_fuzzer
-859f19f7 Reduce libwebp advanced_api_fuzzer threshold
-a4f04835 Merge changes Ic389aaa2,I329ccd79 into main
-1275fac8 Makefile.vc: fix img2webp link w/dynamic cfg
-2fe27bb9 img2webp: normalize help output
-24bed3d9 cwebp: reflow -near_lossless help text
-0825faa4 img2webp: add -sharp_yuv/-near_lossless
-d64e6d7d Merge "PaletteSortModifiedZeng: fix leak on error" into main
-0e12a22d Merge "EncodeAlphaInternal: clear result->bw on error" into main
-0edbb6ea PaletteSortModifiedZeng: fix leak on error
-41ffe04e Merge "Update yapf style from "chromium" to "yapf"" into main
-2d9d9265 Update yapf style from "chromium" to "yapf"
-a486d800 EncodeAlphaInternal: clear result->bw on error
-1347a32d Skip big scaled advanced_api_fuzzer
-52b6f067 Fix scaling limit in advanced_api_fuzzer.c
-73618428 Limit scaling in libwebp advanced_api_fuzzer.c
-b54d21a0 Merge "CMakeLists.txt: allow CMAKE_INSTALL_RPATH to be set empty" into main
-31c28db5 libwebp{,demux,mux}.pc.in: Requires -> Requires.private
-d9a505ff CMakeLists.txt: allow CMAKE_INSTALL_RPATH to be set empty
-bdf33d03 Merge tag 'v1.3.0'
-b5577769 update ChangeLog (tag: v1.3.0-rc1, tag: v1.3.0)
-0ba77244 update NEWS
-e763eb1e bump version to 1.3.0
-2a8686fc update AUTHORS
-106a57c1 Merge "*/Android.mk: add a check for NDK_ROOT" into main
-c5e841c4 Merge "extras: WebpToSDL -> WebPToSDL" into main
-dbc30715 Merge "xcframeworkbuild.sh: bump MACOSX_CATALYST_MIN_VERSION" into main
-6fc1a9f9 */Android.mk: add a check for NDK_ROOT
-d3e151fc doc/api.md,webp_js/README.md: Webp -> WebP
-ed92a626 extras: WebpToSDL -> WebPToSDL
-6eb0189b xcframeworkbuild.sh: bump MACOSX_CATALYST_MIN_VERSION
-1d58575b CMake: align .pc variables with autoconf
-e5fe2cfc webp-lossless-bitstream-spec,cosmetics: reflow paragraphs
-0ceeeab9 webp-lossless-bitstream-spec: add amendment note
-607611cd Merge "webp-container-spec: normalize section title case" into main
-f853685e lossless: SUBTRACT_GREEN -> SUBTRACT_GREEN_TRANSFORM
-786497e4 webp-lossless-bitstream-spec: fix inv color txfm description
-c6ac672d webp-lossless-bitstream-spec: fix num_code_lengths check
-b5700efb webp-lossless-bitstream-spec,cosmetics: grammar/capitalization
-d8ed8c11 webp-container-spec: normalize section title case
-52ec0b8f Merge changes Ie975dbb5,Ifc8c93af,I6ca7c5d6,I2e8d66f5,I152477b8 into main
-5097ef62 webp-container-spec,cosmetics: grammar/capitalization
-e3ba2b1f webp-lossless-bitstream-spec,cosmetics: reflow abstract
-1e8e3ded webp-lossless-bitstream-spec: reword abstract re alpha
-017cb6fa webp-container-spec,cosmetics: normalize range syntax
-f6a4684b webp-lossless-bitstream-spec,cosmetics: normalize range syntax
-54ebd5a3 webp-lossless-bitstream-spec: limit dist map lut to 69 cols
-44741f9c webp-lossless-bitstream-spec: fix dist mapping example
-fad0ece7 pnmdec.c: use snprintf instead of sprintf
-3f73e8f7 sharpyuv: add SharpYuvGetVersion()
-ce2f2d66 SharpYuvConvert: fix a race on SharpYuvGetCPUInfo
-a458e308 sharpyuv_dsp.h: restore sharpyuv_cpu.h include
-9ba800a7 Merge changes Id72fbf3b,Ic59d23a2 into main
-979c0ebb sharpyuv: add SharpYuvGetCPUInfo
-8bab09a4 Merge "*.pc.in: rename lib_prefix to webp_libname_prefix" into main
-769387c5 cpu.c,cosmetics: fix a typo
-a02978c2 sharpyuv/Makefile.am+cmake: add missing -lm
-28aedcb9 *.pc.in: rename lib_prefix to webp_libname_prefix
-c42e6d5a configure.ac: export an empty lib_prefix variable
-dfc843aa Merge "*.pc.in: add lib prefix to lib names w/MSVC" into main
-2498209b *.pc.in: add lib prefix to lib names w/MSVC
-ac252b61 Merge "analysis_enc.c: fix a dead store warning" into main
-56944762 analysis_enc.c: fix a dead store warning
-d34f9b99 Merge "webp-lossless-bitstream-spec: convert BNF to ABNF" into main
-dc05b4db Merge changes I96bc063c,I45880467,If9e18e5a,I6ee938e4,I0a410b28, ... into main
-83270c7f webp-container-spec: add prose for rendering process
-73b19b64 webp-container-spec: note reserved fields MUST be ignored
-57101d3f webp-lossless-bitstream-spec: improve 'small' color table stmt
-dfd32e45 webp-container-spec: remove redundant sentence
-8a6185dd doc/webp-*: fix some punctuation, grammar
-72776530 webp-lossless-bitstream-spec: convert BNF to ABNF
-d992bb08 cmake: rename cpufeatures target to cpufeatures-webp
-3ed2b275 webp-container-spec: clarify background color note
-951c292d webp-container-spec: come too late -> out of order
-902dd787 webp-container-spec: prefer hex literals
-a8f6b5ee webp-container-spec: change SHOULD to MUST w/ANIM chunk
-1dc59435 webp-container-spec: add unknown fields MUST be ignored
-280a810f webp-container-spec: make padding byte=0 a MUST
-41f0bf68 webp-container-spec: update note on trailing data
-6bdd36db webp-container-spec: clarify Chunk Size is in bytes
-87e36c48 Merge "webp_js/README.md,cosmetics: reflow some lines" into main
-5b01f321 Merge "Update Windows makefile to build libsharpyuv library." into main
-19b1a71c webp_js/README.md,cosmetics: reflow some lines
-780db756 Update Windows makefile to build libsharpyuv library.
-e407d4b3 CMakeLists.txt: replace GLUT_glut_LIBRARY w/GLUT::GLUT
-abf73d62 Merge "WebPConfig.cmake.in: add find_dependency(Threads)" into main
-25807fb4 Merge "cmake: restore compatibility with cmake < 3.12" into main
-5dbc4bfa WebPConfig.cmake.in: add find_dependency(Threads)
-b2a175dd Merge "Update wasm instructions." into main
-cb90f76b Update wasm instructions.
-02d15258 cmake: restore compatibility with cmake < 3.12
-5ba046e2 CMake: add_definitions -> add_compile_options
-e68765af dsp,neon: use vaddv in a few more places
-e8f83de2 Set libsharpyuv include dir to 'webp' subdirectory.
-15a91ab1 cmake,cosmetics: apply cmake-format
-0dd49d1a CMakeLists.txt: set @ONLY in configure_file() calls
-62b1bfe8 Merge changes I2877e7bb,I777cad70,I15af7d1a,I686e6740,If10538a9, ... into main
-95c8fe5f Merge changes Iecea3603,I9dc228ab into main
-e7c805cf picture_csp_enc.c: remove SafeInitSharpYuv
-6af8845a sharpyuv: prefer webp/types.h
-639619ce cmake: fix dll exports
-782ed48c sharpyuv,SharpYuvInit: add mutex protection when available
-cad0d5ad sharyuv_{neon,sse2}.c: merge WEBP_USE_* sections
-ef70ee06 add a few missing <stddef.h> includes for NULL
-f0f9eda4 sharpyuv.h: remove <inttypes.h>
-9b902cba Merge "picture_csp_enc.c,CheckNonOpaque: rm unneeded local" into main
-9c1d457c cmake/cpu.cmake: remove unused variable
-9ac25bcb CMakeLists.txt,win32: match naming convention used by nmake
-76c353ba picture_csp_enc.c,CheckNonOpaque: rm unneeded local
-5000de54 Merge "cwebp: fix WebPPictureHasTransparency call" into main
-e1729309 Merge "WebPPictureHasTransparency: add missing pointer check" into main
-00ff988a vp8l_enc,AddSingleSubGreen: clear int sanitizer warnings
-e2fecc22 dsp/lossless_enc.c: clear int sanitizer warnings
-129cf9e9 dsp/lossless.c: clear int sanitizer warnings
-ad7d1753 dsp/lossless_enc.c: clear int sanitizer warnings
-5037220e VP8LSubtractGreenFromBlueAndRed_C: clear int sanitizer warnings
-2ee786c7 upsampling_sse2.c: clear int sanitizer warnings
-4cc157d4 ParseOptionalChunks: clear int sanitizer warning
-892cf033 BuildHuffmanTable: clear int sanitizer warning
-3a9a4d45 VP8GetSigned: clear int sanitizer warnings
-704a3d0a dsp/lossless.c: quiet int sanitizer warnings
-1a6c109c WebPPictureHasTransparency: add missing pointer check
-c626e7d5 cwebp: fix WebPPictureHasTransparency call
-866e349c Merge tag 'v1.2.4'
-c170df38 Merge "Create libsharpyuv.a in makefile.unix." into main
-9d7ff74a Create libsharpyuv.a in makefile.unix.
-0d1f1254 update ChangeLog (tag: v1.2.4)
-fcbc2d78 Merge "doc/*.txt: restrict code to 69 columns" into main
-4ad0e189 Merge "webp-container-spec.txt: normalize fourcc spelling" into main
-980d2488 update NEWS
-9fde8127 bump version to 1.2.4
-7a0a9935 doc/*.txt: restrict code to 69 columns
-c040a615 webp-container-spec.txt: normalize fourcc spelling
-aff1c546 dsp,x86: normalize types w/_mm_cvtsi128_si32 calls
-ab540ae0 dsp,x86: normalize types w/_mm_cvtsi32_si128 calls
-8980362e dsp,x86: normalize types w/_mm_set* calls (2)
-e626925c lossless: fix crunch mode w/WEBP_REDUCE_SIZE
-83539239 dsp,x86: normalize types w/_mm_set* calls
-8a4576ce webp-container-spec.txt: replace &amp; with &
-db870881 Merge "webp-container-spec.txt: make reserved 0 values a MUST" into main
-01d7d378 webp-lossless-bitstream-spec: number all sections
-337cf69f webp-lossless-bitstream-spec: mv Nomenclature after Intro
-79be856e Merge changes I7111d1f7,I872cd62c into main
-5b87983a webp-container-spec.txt: make reserved 0 values a MUST
-bd939123 Merge changes I7a25b1a6,I51b2c2a0,I87d0cbcf,I6ec60af6,I0a3fe9dc into main
-04764b56 libwebp.pc: add libsharpyuv to requires
-7deee810 libsharpyuv: add pkg-config file
-1a64a7e6 webp-container-spec.txt: clarify some SHOULDs
-bec2c88a webp-container-spec.txt: move ChunkHeader to terminology
-c9359332 webp-container-spec.txt: clarify 'VP8 '/'XMP ' fourccs
-70fe3063 webp-container-spec.txt: rightsize table entries
-ddbf3f3f webp-container-spec.txt: update 'key words' text
-c151e95b utils.h,WEBP_ALIGN: make bitmask unsigned
-748e92bb add WebPInt32ToMem
-3fe15b67 Merge "Build libsharpyuv as a full installable library." into main
-4f402f34 add WebPMemToInt32
-a3b68c19 Build libsharpyuv as a full installable library.
-b4994eaa CMake: set rpath for shared objects
-94cd7117 Merge "CMake: fix dylib versioning" into main
-e91451b6 Fix the lossless specs a bit more.
-231bdfb7 CMake: fix dylib versioning
-bfad7ab5 CMakeLists.txt: correct libwebpmux name in WebPConfig.cmake
-c2e3fd30 Revert "cmake: fix webpmux lib name for cmake linking"
-7366f7f3 Merge "lossless: fix crunch mode w/WEBP_REDUCE_SIZE" into main
-84163d9d lossless: fix crunch mode w/WEBP_REDUCE_SIZE
-d01c1eb3 webp-lossless-bitstream-spec,cosmetics: normalize capitalization
-8813ca8e Merge tag 'v1.2.3'
-3c4a0fbf update ChangeLog (tag: v1.2.3)
 56a480e8 dsp/cpu.h: add missing extern "C"
 62b45bdd update ChangeLog (tag: v1.2.3-rc1)
 8764ec7a Merge changes Idb037953,Id582e395 into 1.2.3
--- a/Makefile.vc
+++ b/Makefile.vc
@@ -5,7 +5,6 @@ LIBWEBPDECODER_BASENAME = libwebpdecoder
 LIBWEBP_BASENAME = libwebp
 LIBWEBPMUX_BASENAME = libwebpmux
 LIBWEBPDEMUX_BASENAME = libwebpdemux
-LIBSHARPYUV_BASENAME = libsharpyuv

 !IFNDEF ARCH
 !IF ! [ cl 2>&1 | find "x86" > NUL ]
@@ -97,7 +96,6 @@ LIBWEBPDECODER_BASENAME = $(LIBWEBPDECODER_BASENAME)_debug
 LIBWEBP_BASENAME = $(LIBWEBP_BASENAME)_debug
 LIBWEBPMUX_BASENAME = $(LIBWEBPMUX_BASENAME)_debug
 LIBWEBPDEMUX_BASENAME = $(LIBWEBPDEMUX_BASENAME)_debug
-LIBSHARPYUV_BASENAME = $(LIBSHARPYUV_BASENAME)_debug
 !ELSE IF "$(CFG)" == "release-dynamic"
 CC        = $(CCNODBG)
 RC        = $(RCNODBG)
@@ -111,7 +109,6 @@ LIBWEBPDECODER_BASENAME = $(LIBWEBPDECODER_BASENAME)_debug
 LIBWEBP_BASENAME = $(LIBWEBP_BASENAME)_debug
 LIBWEBPMUX_BASENAME = $(LIBWEBPMUX_BASENAME)_debug
 LIBWEBPDEMUX_BASENAME = $(LIBWEBPDEMUX_BASENAME)_debug
-LIBSHARPYUV_BASENAME = $(LIBSHARPYUV_BASENAME)_debug
 !ENDIF

 !IF "$(STATICLIBBUILD)" == "TRUE"
@@ -121,14 +118,13 @@ LIBWEBPDECODER = $(DIRLIB)\$(LIBWEBPDECODER_BASENAME).lib
 LIBWEBP = $(DIRLIB)\$(LIBWEBP_BASENAME).lib
 LIBWEBPMUX = $(DIRLIB)\$(LIBWEBPMUX_BASENAME).lib
 LIBWEBPDEMUX = $(DIRLIB)\$(LIBWEBPDEMUX_BASENAME).lib
-LIBSHARPYUV = $(DIRLIB)\$(LIBSHARPYUV_BASENAME).lib
 !ELSE IF "$(DLLBUILD)" == "TRUE"
-CC     = $(CC) /I$(DIROBJ) $(RTLIB) /DWEBP_DLL
+DLLINC = webp_dll.h
+CC     = $(CC) /I$(DIROBJ) /FI$(DLLINC) $(RTLIB) /DWEBP_DLL
 LIBWEBPDECODER = $(DIRLIB)\$(LIBWEBPDECODER_BASENAME)_dll.lib
 LIBWEBP = $(DIRLIB)\$(LIBWEBP_BASENAME)_dll.lib
 LIBWEBPMUX = $(DIRLIB)\$(LIBWEBPMUX_BASENAME)_dll.lib
 LIBWEBPDEMUX = $(DIRLIB)\$(LIBWEBPDEMUX_BASENAME)_dll.lib
-LIBSHARPYUV = $(DIRLIB)\$(LIBSHARPYUV_BASENAME)_dll.lib
 LIBWEBP_PDBNAME = $(DIROBJ)\$(LIBWEBP_BASENAME)_dll.pdb
 CFGSET = TRUE
 !ENDIF
@@ -180,7 +176,6 @@ CFLAGS = $(CFLAGS) /D_UNICODE /DUNICODE

 SHARPYUV_OBJS = \
    $(DIROBJ)\sharpyuv\sharpyuv.obj \
-    $(DIROBJ)\sharpyuv\sharpyuv_cpu.obj \
    $(DIROBJ)\sharpyuv\sharpyuv_csp.obj \
    $(DIROBJ)\sharpyuv\sharpyuv_dsp.obj \
    $(DIROBJ)\sharpyuv\sharpyuv_gamma.obj \
@@ -348,13 +343,12 @@ UTILS_ENC_OBJS = \
    $(DIROBJ)\utils\quant_levels_utils.obj \

 LIBWEBPDECODER_OBJS = $(DEC_OBJS) $(DSP_DEC_OBJS) $(UTILS_DEC_OBJS)
-LIBWEBP_OBJS = $(LIBWEBPDECODER_OBJS) $(ENC_OBJS) \
+LIBWEBP_OBJS = $(LIBWEBPDECODER_OBJS) $(SHARPYUV_OBJS) $(ENC_OBJS) \
               $(DSP_ENC_OBJS) $(UTILS_ENC_OBJS) $(DLL_OBJS)
 LIBWEBPMUX_OBJS = $(MUX_OBJS) $(LIBWEBPMUX_OBJS)
 LIBWEBPDEMUX_OBJS = $(DEMUX_OBJS) $(LIBWEBPDEMUX_OBJS)
-LIBSHARPYUV_OBJS = $(SHARPYUV_OBJS)

-OUT_LIBS = $(LIBWEBPDECODER) $(LIBWEBP) $(LIBSHARPYUV)
+OUT_LIBS = $(LIBWEBPDECODER) $(LIBWEBP)
 !IF "$(ARCH)" == "ARM"
 ex: $(OUT_LIBS)
 all: ex
@@ -382,7 +376,7 @@ $(DIRBIN)\anim_dump.exe: $(EX_GIF_DEC_OBJS) $(LIBWEBPDEMUX) $(LIBWEBP)
 $(DIRBIN)\anim_dump.exe: $(IMAGEIO_ENC_OBJS)
 $(DIRBIN)\cwebp.exe: $(DIROBJ)\examples\cwebp.obj $(IMAGEIO_DEC_OBJS)
 $(DIRBIN)\cwebp.exe: $(IMAGEIO_UTIL_OBJS)
-$(DIRBIN)\cwebp.exe: $(LIBWEBPDEMUX) $(LIBSHARPYUV)
+$(DIRBIN)\cwebp.exe: $(LIBWEBPDEMUX)
 $(DIRBIN)\dwebp.exe: $(DIROBJ)\examples\dwebp.obj $(IMAGEIO_DEC_OBJS)
 $(DIRBIN)\dwebp.exe: $(IMAGEIO_ENC_OBJS)
 $(DIRBIN)\dwebp.exe: $(IMAGEIO_UTIL_OBJS)
@@ -400,7 +394,7 @@ $(DIRBIN)\webpmux.exe: $(EX_UTIL_OBJS) $(IMAGEIO_UTIL_OBJS) $(LIBWEBP)
 $(DIRBIN)\img2webp.exe: $(DIROBJ)\examples\img2webp.obj $(LIBWEBPMUX)
 $(DIRBIN)\img2webp.exe: $(IMAGEIO_DEC_OBJS)
 $(DIRBIN)\img2webp.exe: $(EX_UTIL_OBJS) $(IMAGEIO_UTIL_OBJS)
-$(DIRBIN)\img2webp.exe: $(LIBWEBPDEMUX) $(LIBWEBP) $(LIBSHARPYUV)
+$(DIRBIN)\img2webp.exe: $(LIBWEBPDEMUX) $(LIBWEBP)
 $(DIRBIN)\get_disto.exe: $(DIROBJ)\extras\get_disto.obj
 $(DIRBIN)\get_disto.exe: $(IMAGEIO_DEC_OBJS) $(IMAGEIO_UTIL_OBJS)
 $(DIRBIN)\get_disto.exe: $(LIBWEBPDEMUX) $(LIBWEBP)
@@ -423,16 +417,17 @@ $(EX_UTIL_OBJS) $(IMAGEIO_UTIL_OBJS): $(OUTPUT_DIRS)
 $(IMAGEIO_DEC_OBJS) $(IMAGEIO_ENC_OBJS) $(EXTRAS_OBJS): $(OUTPUT_DIRS)
 !ENDIF  # ARCH == ARM

-$(LIBSHARPYUV): $(LIBSHARPYUV_OBJS)
 $(LIBWEBPDECODER): $(LIBWEBPDECODER_OBJS)
-$(LIBWEBP): $(LIBWEBP_OBJS) $(LIBSHARPYUV)
+$(LIBWEBP): $(LIBWEBP_OBJS)
 $(LIBWEBPMUX): $(LIBWEBPMUX_OBJS)
 $(LIBWEBPDEMUX): $(LIBWEBPDEMUX_OBJS)

-$(LIBWEBP_OBJS) $(LIBWEBPMUX_OBJS) $(LIBWEBPDEMUX_OBJS) $(LIBSHARPYUV_OBJS): \
-    $(OUTPUT_DIRS)
+$(LIBWEBP_OBJS) $(LIBWEBPMUX_OBJS) $(LIBWEBPDEMUX_OBJS): $(OUTPUT_DIRS)

 !IF "$(DLLBUILD)" == "TRUE"
+$(LIBWEBP_OBJS) $(LIBWEBPMUX_OBJS) $(LIBWEBPDEMUX_OBJS): \
+    $(DIROBJ)\$(DLLINC)
+
 {$(DIROBJ)}.c{$(DIROBJ)}.obj:
 	$(CC) $(CFLAGS) /Fd$(LIBWEBP_PDBNAME) /Fo$@  $<

@@ -442,20 +437,20 @@ $(LIBWEBP_OBJS) $(LIBWEBPMUX_OBJS) $(LIBWEBPDEMUX_OBJS) $(LIBSHARPYUV_OBJS): \
 	$(RC) /fo$@ $<
 {src\mux}.rc{$(DIROBJ)\mux}.res:
 	$(RC) /fo$@ $<
-{sharpyuv}.rc{$(DIROBJ)\sharpyuv}.res:
-	$(RC) /fo$@ $<

-$(LIBSHARPYUV): $(DIROBJ)\sharpyuv\$(LIBSHARPYUV_BASENAME:_debug=).res
-$(LIBWEBP): $(LIBSHARPYUV) $(DIROBJ)\$(LIBWEBP_BASENAME:_debug=).res
+$(LIBWEBP): $(DIROBJ)\$(LIBWEBP_BASENAME:_debug=).res
 $(LIBWEBPDECODER): $(DIROBJ)\$(LIBWEBPDECODER_BASENAME:_debug=).res
 $(LIBWEBPMUX): $(LIBWEBP) $(DIROBJ)\mux\$(LIBWEBPMUX_BASENAME:_debug=).res
 $(LIBWEBPDEMUX): $(LIBWEBP) $(DIROBJ)\demux\$(LIBWEBPDEMUX_BASENAME:_debug=).res

-$(LIBWEBPDECODER) $(LIBWEBP) $(LIBWEBPMUX) $(LIBWEBPDEMUX) $(LIBSHARPYUV):
+$(LIBWEBPDECODER) $(LIBWEBP) $(LIBWEBPMUX) $(LIBWEBPDEMUX):
 	$(LNKDLL) /out:$(DIRBIN)\$(@B:_dll=.dll) /implib:$@ $(LFLAGS) $**
 	-xcopy $(DIROBJ)\*.pdb $(DIRLIB) /y
+
+clean::
+	@-erase /s $(DIROBJ)\$(DLLINC) 2> NUL
 !ELSE
-$(LIBWEBPDECODER) $(LIBWEBP) $(LIBWEBPMUX) $(LIBWEBPDEMUX) $(LIBSHARPYUV):
+$(LIBWEBPDECODER) $(LIBWEBP) $(LIBWEBPMUX) $(LIBWEBPDEMUX):
 	$(LNKLIB) /out:$@ $**
 	-xcopy $(DIROBJ)\*.pdb $(DIRLIB) /y
 !ENDIF
@@ -463,6 +458,13 @@ $(LIBWEBPDECODER) $(LIBWEBP) $(LIBWEBPMUX) $(LIBWEBPDEMUX) $(LIBSHARPYUV):
 $(OUTPUT_DIRS):
 	@if not exist "$(@)" mkdir "$(@)"

+# generate a helper include to define WEBP_EXTERN suitable for the DLL build
+$(DIROBJ)\$(DLLINC):
+	@echo #ifndef WEBP_DLL_H_ > $@
+	@echo #define WEBP_DLL_H_ >> $@
+	@echo #define WEBP_EXTERN __declspec(dllexport) >> $@
+	@echo #endif  /* WEBP_DLL_H_ */ >> $@
+
 .SUFFIXES: .c .obj .res .exe
 # File-specific flag builds. Note batch rules take precedence over wildcards,
 # so for now name each file individually.
--- a/33
+++ b/33
@@ -1,36 +1,3 @@
- 9/13/2023: version 1.3.2
-  This is a binary compatible release.
-  * security fix for lossless decoder (chromium: #1479274, CVE-2023-4863)
-
- 6/23/2023: version 1.3.1
-  This is a binary compatible release.
-  * security fixes for lossless encoder (#603, chromium: #1420107, #1455619,
-    CVE-2023-1999)
-  * improve error reporting through WebPPicture error codes
-  * fix upsampling for RGB565 and RGBA4444 in NEON builds
-  * img2webp: add -sharp_yuv & -near_lossless
-  * Windows builds:
-    - fix compatibility with clang-cl (#607)
-    - improve Arm64 performance with cl.exe
-    - add Arm64EC support
-  * fix webp_js with emcc >= 3.1.27 (stack size change, #614)
-  * CMake fixes (#592, #610, #612)
-  * further updates to the container and lossless bitstream docs (#581, #611)
-
- 12/16/2022: version 1.3.0
-  This is a binary compatible release.
-  * add libsharpyuv, which exposes -sharp_yuv/config.use_sharp_yuv
-    functionality to other libraries; libwebp now depends on this library
-  * major updates to the container and lossless bitstream docs (#448, #546,
-    #551)
-  * miscellaneous warning, bug & build fixes (#576, #583, #584)
-
- 8/4/2022: version 1.2.4
-  This is a binary compatible release.
-  * restore CMake libwebpmux target name for compatibility with 1.2.2 (#575)
-  * fix lossless crunch mode encoding with WEBP_REDUCE_SIZE
-    (chromium: #1345547, #1345595, #1345772, #1345804)
-
 - 6/30/2022: version 1.2.3
  This is a binary compatible release.
  * security fix for lossless encoder (#565, chromium:1313709)
--- a/README.md
+++ b/README.md
@@ -7,7 +7,7 @@
      \__\__/\____/\_____/__/ ____  ___
            / _/ /    \    \ /  _ \/ _/
           /  \_/   / /   \ \   __/  \__
-           \____/____/\_____/_____/____/v1.3.2
+           \____/____/\_____/_____/____/v1.2.3
 ```

 WebP codec is a library to encode and decode images in WebP format. This package
--- a/build.gradle
+++ b/build.gradle
@@ -107,7 +107,6 @@ model {
          source {
            srcDir "sharpyuv"
            include "sharpyuv.c"
-            include "sharpyuv_cpu.c"
            include "sharpyuv_csp.c"
            include "sharpyuv_dsp.c"
            include "sharpyuv_gamma.c"
--- a/cmake/WebPConfig.cmake.in
+++ b/cmake/WebPConfig.cmake.in
@@ -3,16 +3,9 @@ set(WEBP_VERSION ${WebP_VERSION})

@PACKAGE_INIT@

-if(@WEBP_USE_THREAD@)
-  include(CMakeFindDependencyMacro)
-  find_dependency(Threads REQUIRED)
-endif()
+include ("${CMAKE_CURRENT_LIST_DIR}/@PROJECT_NAME@Targets.cmake")

-include("${CMAKE_CURRENT_LIST_DIR}/@PROJECT_NAME@Targets.cmake")
-
-set_and_check(WebP_INCLUDE_DIR "@PACKAGE_CMAKE_INSTALL_INCLUDEDIR@")
+set(WebP_INCLUDE_DIRS "@CMAKE_INSTALL_FULL_INCLUDEDIR@")
 set(WEBP_INCLUDE_DIRS ${WebP_INCLUDE_DIRS})
 set(WebP_LIBRARIES "@INSTALLED_LIBRARIES@")
 set(WEBP_LIBRARIES "${WebP_LIBRARIES}")
-
-check_required_components(WebP)
--- a/cmake/config.h.in
+++ b/cmake/config.h.in
@@ -16,18 +16,48 @@
 /* Define to 1 if you have the <cpu-features.h> header file. */
 #cmakedefine HAVE_CPU_FEATURES_H 1

+/* Define to 1 if you have the <dlfcn.h> header file. */
+#cmakedefine HAVE_DLFCN_H 1
+
 /* Define to 1 if you have the <GLUT/glut.h> header file. */
 #cmakedefine HAVE_GLUT_GLUT_H 1

 /* Define to 1 if you have the <GL/glut.h> header file. */
 #cmakedefine HAVE_GL_GLUT_H 1

+/* Define to 1 if you have the <inttypes.h> header file. */
+#cmakedefine HAVE_INTTYPES_H 1
+
+/* Define to 1 if you have the <memory.h> header file. */
+#cmakedefine HAVE_MEMORY_H 1
+
 /* Define to 1 if you have the <OpenGL/glut.h> header file. */
 #cmakedefine HAVE_OPENGL_GLUT_H 1

+/* Have PTHREAD_PRIO_INHERIT. */
+#cmakedefine HAVE_PTHREAD_PRIO_INHERIT @HAVE_PTHREAD_PRIO_INHERIT@
+
 /* Define to 1 if you have the <shlwapi.h> header file. */
 #cmakedefine HAVE_SHLWAPI_H 1

+/* Define to 1 if you have the <stdint.h> header file. */
+#cmakedefine HAVE_STDINT_H 1
+
+/* Define to 1 if you have the <stdlib.h> header file. */
+#cmakedefine HAVE_STDLIB_H 1
+
+/* Define to 1 if you have the <strings.h> header file. */
+#cmakedefine HAVE_STRINGS_H 1
+
+/* Define to 1 if you have the <string.h> header file. */
+#cmakedefine HAVE_STRING_H 1
+
+/* Define to 1 if you have the <sys/stat.h> header file. */
+#cmakedefine HAVE_SYS_STAT_H 1
+
+/* Define to 1 if you have the <sys/types.h> header file. */
+#cmakedefine HAVE_SYS_TYPES_H 1
+
 /* Define to 1 if you have the <unistd.h> header file. */
 #cmakedefine HAVE_UNISTD_H 1

@@ -63,6 +93,9 @@
 /* Define to the version of this package. */
 #cmakedefine PACKAGE_VERSION "@PACKAGE_VERSION@"

+/* Define to 1 if you have the ANSI C header files. */
+#cmakedefine STDC_HEADERS 1
+
 /* Version number of package */
 #cmakedefine VERSION "@VERSION@"

--- a/cmake/cpu.cmake
+++ b/cmake/cpu.cmake
@@ -18,8 +18,7 @@ function(webp_check_compiler_flag WEBP_SIMD_FLAG ENABLE_SIMD)
  unset(WEBP_HAVE_FLAG_${WEBP_SIMD_FLAG} CACHE)
  cmake_push_check_state()
  set(CMAKE_REQUIRED_INCLUDES ${CMAKE_CURRENT_SOURCE_DIR})
-  check_c_source_compiles(
-    "
+  check_c_source_compiles("
      #include \"${CMAKE_CURRENT_LIST_DIR}/../src/dsp/dsp.h\"
      int main(void) {
        #if !defined(WEBP_USE_${WEBP_SIMD_FLAG})
@@ -27,8 +26,7 @@ function(webp_check_compiler_flag WEBP_SIMD_FLAG ENABLE_SIMD)
        #endif
        return 0;
      }
-    "
-    WEBP_HAVE_FLAG_${WEBP_SIMD_FLAG})
+    " WEBP_HAVE_FLAG_${WEBP_SIMD_FLAG})
  cmake_pop_check_state()
  if(WEBP_HAVE_FLAG_${WEBP_SIMD_FLAG})
    set(WEBP_HAVE_${WEBP_SIMD_FLAG} 1 PARENT_SCOPE)
@@ -54,10 +52,13 @@ if(MSVC AND CMAKE_C_COMPILER_ID STREQUAL "MSVC")
  endif()
  set(SIMD_DISABLE_FLAGS)
 else()
-  set(SIMD_ENABLE_FLAGS "-msse4.1;-msse2;-mips32;-mdspr2;-mfpu=neon;-mmsa")
-  set(SIMD_DISABLE_FLAGS "-mno-sse4.1;-mno-sse2;;-mno-dspr2;;-mno-msa")
+  set(SIMD_ENABLE_FLAGS
+      "-msse4.1;-msse2;-mips32;-mdspr2;-mfpu=neon;-mmsa")
+  set(SIMD_DISABLE_FLAGS
+      "-mno-sse4.1;-mno-sse2;;-mno-dspr2;;-mno-msa")
 endif()

+set(WEBP_SIMD_FILES_TO_NOT_INCLUDE)
 set(WEBP_SIMD_FILES_TO_INCLUDE)
 set(WEBP_SIMD_FLAGS_TO_INCLUDE)

@@ -74,8 +75,8 @@ list(LENGTH WEBP_SIMD_FLAGS WEBP_SIMD_FLAGS_LENGTH)
 math(EXPR WEBP_SIMD_FLAGS_RANGE "${WEBP_SIMD_FLAGS_LENGTH} - 1")

 foreach(I_SIMD RANGE ${WEBP_SIMD_FLAGS_RANGE})
-  # With Emscripten 2.0.9 -msimd128 -mfpu=neon will enable NEON, but the source
-  # will fail to compile.
+  # With Emscripten 2.0.9 -msimd128 -mfpu=neon will enable NEON, but the
+  # source will fail to compile.
  if(EMSCRIPTEN AND ${I_SIMD} GREATER_EQUAL 2)
    break()
  endif()
@@ -107,7 +108,7 @@ foreach(I_SIMD RANGE ${WEBP_SIMD_FLAGS_RANGE})
  # Check which files we should include or not.
  list(GET WEBP_SIMD_FILE_EXTENSIONS ${I_SIMD} WEBP_SIMD_FILE_EXTENSION)
  file(GLOB SIMD_FILES "${CMAKE_CURRENT_LIST_DIR}/../"
-       "src/dsp/*${WEBP_SIMD_FILE_EXTENSION}")
+            "src/dsp/*${WEBP_SIMD_FILE_EXTENSION}")
  if(WEBP_HAVE_${WEBP_SIMD_FLAG})
    # Memorize the file and flags.
    foreach(FILE ${SIMD_FILES})
@@ -141,9 +142,11 @@ foreach(I_SIMD RANGE ${WEBP_SIMD_FLAGS_RANGE})
            set(COMMON_PATTERNS)
          endif()
          set(CMAKE_REQUIRED_DEFINITIONS ${SIMD_COMPILE_FLAG})
-          check_c_source_compiles(
-            "int main(void) {return 0;}" FLAG_${SIMD_COMPILE_FLAG} FAIL_REGEX
-            "warning: argument unused during compilation:" ${COMMON_PATTERNS})
+          check_c_source_compiles("int main(void) {return 0;}"
+                                  FLAG_${SIMD_COMPILE_FLAG}
+                                  FAIL_REGEX
+                                  "warning: argument unused during compilation:"
+                                  ${COMMON_PATTERNS})
          if(NOT FLAG_${SIMD_COMPILE_FLAG})
            unset(HAS_COMPILE_FLAG)
            unset(HAS_COMPILE_FLAG CACHE)
--- a/cmake/deps.cmake
+++ b/cmake/deps.cmake
@@ -10,30 +10,24 @@

 # Check for compiler options.
 include(CheckCSourceCompiles)
-check_c_source_compiles(
-  "
+check_c_source_compiles("
    int main(void) {
      (void)__builtin_bswap16(0);
      return 0;
    }
-  "
-  HAVE_BUILTIN_BSWAP16)
-check_c_source_compiles(
-  "
+  " HAVE_BUILTIN_BSWAP16)
+check_c_source_compiles("
    int main(void) {
      (void)__builtin_bswap32(0);
      return 0;
    }
-  "
-  HAVE_BUILTIN_BSWAP32)
-check_c_source_compiles(
-  "
+  " HAVE_BUILTIN_BSWAP32)
+check_c_source_compiles("
    int main(void) {
      (void)__builtin_bswap64(0);
      return 0;
    }
-  "
-  HAVE_BUILTIN_BSWAP64)
+  " HAVE_BUILTIN_BSWAP64)

 # Check for libraries.
 if(WEBP_USE_THREAD)
@@ -43,6 +37,14 @@ if(WEBP_USE_THREAD)
    if(CMAKE_USE_PTHREADS_INIT AND NOT CMAKE_SYSTEM_NAME STREQUAL "QNX")
      set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -pthread")
    endif()
+    check_c_source_compiles("
+        #include <pthread.h>
+        int main (void) {
+          int attr = PTHREAD_PRIO_INHERIT;
+          return attr;
+        }
+      " FLAG_HAVE_PTHREAD_PRIO_INHERIT)
+    set(HAVE_PTHREAD_PRIO_INHERIT ${FLAG_HAVE_PTHREAD_PRIO_INHERIT})
    list(APPEND WEBP_DEP_LIBRARIES Threads::Threads)
  endif()
  set(WEBP_USE_THREAD ${Threads_FOUND})
@@ -57,88 +59,94 @@ set(WEBP_HAVE_GL ${OPENGL_FOUND})

 # Check if we need to link to the C math library. We do not look for it as it is
 # not found when cross-compiling, while it is here.
-check_c_source_compiles(
-  "
+check_c_source_compiles("
    #include <math.h>
    int main(int argc, char** argv) {
      return (int)pow(argc, 2.5);
    }
-  "
-  HAVE_MATH_LIBRARY)
+  " HAVE_MATH_LIBRARY)
 if(NOT HAVE_MATH_LIBRARY)
  message(STATUS "Adding -lm flag.")
-  list(APPEND SHARPYUV_DEP_LIBRARIES m)
  list(APPEND WEBP_DEP_LIBRARIES m)
 endif()

 # Find the standard image libraries.
 set(WEBP_DEP_IMG_LIBRARIES)
 set(WEBP_DEP_IMG_INCLUDE_DIRS)
-if(WEBP_FIND_IMG_LIBS)
-  foreach(I_LIB PNG JPEG TIFF)
-    # Disable tiff when compiling in static mode as it is failing on Ubuntu.
-    if(WEBP_LINK_STATIC AND ${I_LIB} STREQUAL "TIFF")
-      message(STATUS "TIFF is disabled when statically linking.")
-      continue()
-    endif()
-    find_package(${I_LIB})
-    set(WEBP_HAVE_${I_LIB} ${${I_LIB}_FOUND})
-    if(${I_LIB}_FOUND)
-      list(APPEND WEBP_DEP_IMG_LIBRARIES ${${I_LIB}_LIBRARIES})
-      list(APPEND WEBP_DEP_IMG_INCLUDE_DIRS ${${I_LIB}_INCLUDE_DIR}
-           ${${I_LIB}_INCLUDE_DIRS})
-    endif()
-  endforeach()
-  if(WEBP_DEP_IMG_INCLUDE_DIRS)
-    list(REMOVE_DUPLICATES WEBP_DEP_IMG_INCLUDE_DIRS)
+foreach(I_LIB PNG JPEG TIFF)
+  # Disable tiff when compiling in static mode as it is failing on Ubuntu.
+  if(WEBP_LINK_STATIC AND ${I_LIB} STREQUAL "TIFF")
+    message("TIFF is disabled when statically linking.")
+    continue()
  endif()
+  find_package(${I_LIB})
+  set(WEBP_HAVE_${I_LIB} ${${I_LIB}_FOUND})
+  if(${I_LIB}_FOUND)
+    list(APPEND WEBP_DEP_IMG_LIBRARIES ${${I_LIB}_LIBRARIES})
+    list(APPEND WEBP_DEP_IMG_INCLUDE_DIRS ${${I_LIB}_INCLUDE_DIR}
+                ${${I_LIB}_INCLUDE_DIRS})
+  endif()
+endforeach()
+if(WEBP_DEP_IMG_INCLUDE_DIRS)
+  list(REMOVE_DUPLICATES WEBP_DEP_IMG_INCLUDE_DIRS)
+endif()

-  # GIF detection, gifdec isn't part of the imageio lib.
-  include(CMakePushCheckState)
-  set(WEBP_DEP_GIF_LIBRARIES)
-  set(WEBP_DEP_GIF_INCLUDE_DIRS)
-  find_package(GIF)
-  set(WEBP_HAVE_GIF ${GIF_FOUND})
-  if(GIF_FOUND)
-    # GIF find_package only locates the header and library, it doesn't fail
-    # compile tests when detecting the version, but falls back to 3 (as of at
-    # least cmake 3.7.2). Make sure the library links to avoid incorrect
-    # detection when cross compiling.
-    cmake_push_check_state()
-    set(CMAKE_REQUIRED_LIBRARIES ${GIF_LIBRARIES})
-    set(CMAKE_REQUIRED_INCLUDES ${GIF_INCLUDE_DIR})
-    check_c_source_compiles(
-      "
+# GIF detection, gifdec isn't part of the imageio lib.
+include(CMakePushCheckState)
+set(WEBP_DEP_GIF_LIBRARIES)
+set(WEBP_DEP_GIF_INCLUDE_DIRS)
+find_package(GIF)
+set(WEBP_HAVE_GIF ${GIF_FOUND})
+if(GIF_FOUND)
+  # GIF find_package only locates the header and library, it doesn't fail
+  # compile tests when detecting the version, but falls back to 3 (as of at
+  # least cmake 3.7.2). Make sure the library links to avoid incorrect detection
+  # when cross compiling.
+  cmake_push_check_state()
+  set(CMAKE_REQUIRED_LIBRARIES ${GIF_LIBRARIES})
+  set(CMAKE_REQUIRED_INCLUDES ${GIF_INCLUDE_DIR})
+  check_c_source_compiles("
      #include <gif_lib.h>
      int main(void) {
        (void)DGifOpenFileHandle;
        return 0;
      }
-      "
-      GIF_COMPILES)
-    cmake_pop_check_state()
-    if(GIF_COMPILES)
-      list(APPEND WEBP_DEP_GIF_LIBRARIES ${GIF_LIBRARIES})
-      list(APPEND WEBP_DEP_GIF_INCLUDE_DIRS ${GIF_INCLUDE_DIR})
-    else()
-      unset(GIF_FOUND)
-    endif()
+      " GIF_COMPILES)
+  cmake_pop_check_state()
+  if(GIF_COMPILES)
+    list(APPEND WEBP_DEP_GIF_LIBRARIES ${GIF_LIBRARIES})
+    list(APPEND WEBP_DEP_GIF_INCLUDE_DIRS ${GIF_INCLUDE_DIR})
+  else()
+    unset(GIF_FOUND)
  endif()
 endif()

 # Check for specific headers.
 include(CheckIncludeFiles)
+check_include_files("stdlib.h;stdarg.h;string.h;float.h" STDC_HEADERS)
+check_include_files(dlfcn.h HAVE_DLFCN_H)
 check_include_files(GLUT/glut.h HAVE_GLUT_GLUT_H)
 check_include_files(GL/glut.h HAVE_GL_GLUT_H)
+check_include_files(inttypes.h HAVE_INTTYPES_H)
+check_include_files(memory.h HAVE_MEMORY_H)
 check_include_files(OpenGL/glut.h HAVE_OPENGL_GLUT_H)
 check_include_files(shlwapi.h HAVE_SHLWAPI_H)
+check_include_files(stdint.h HAVE_STDINT_H)
+check_include_files(stdlib.h HAVE_STDLIB_H)
+check_include_files(strings.h HAVE_STRINGS_H)
+check_include_files(string.h HAVE_STRING_H)
+check_include_files(sys/stat.h HAVE_SYS_STAT_H)
+check_include_files(sys/types.h HAVE_SYS_TYPES_H)
 check_include_files(unistd.h HAVE_UNISTD_H)
 check_include_files(wincodec.h HAVE_WINCODEC_H)
 check_include_files(windows.h HAVE_WINDOWS_H)

 # Windows specifics
 if(HAVE_WINCODEC_H)
-  list(APPEND WEBP_DEP_LIBRARIES shlwapi ole32 windowscodecs)
+  list(APPEND WEBP_DEP_LIBRARIES
+              shlwapi
+              ole32
+              windowscodecs)
 endif()

 # Check for SIMD extensions.
@@ -150,12 +158,17 @@ set(PACKAGE_NAME ${PROJECT_NAME})

 # Read from configure.ac.
 file(READ ${CMAKE_CURRENT_SOURCE_DIR}/configure.ac CONFIGURE_AC)
-string(REGEX MATCHALL "\\[([0-9a-z\\.:/]*)\\]" CONFIGURE_AC_PACKAGE_INFO
+string(REGEX MATCHALL
+             "\\[([0-9a-z\\.:/]*)\\]"
+             CONFIGURE_AC_PACKAGE_INFO
             ${CONFIGURE_AC})
 function(strip_bracket VAR)
  string(LENGTH ${${VAR}} TMP_LEN)
  math(EXPR TMP_LEN ${TMP_LEN}-2)
-  string(SUBSTRING ${${VAR}} 1 ${TMP_LEN} TMP_SUB)
+  string(SUBSTRING ${${VAR}}
+                   1
+                   ${TMP_LEN}
+                   TMP_SUB)
  set(${VAR} ${TMP_SUB} PARENT_SCOPE)
 endfunction()

--- a/configure.ac
+++ b/configure.ac
@@ -1,4 +1,4 @@
-AC_INIT([libwebp], [1.3.2],
+AC_INIT([libwebp], [1.2.3],
        [https://bugs.chromium.org/p/webp],,
        [https://developers.google.com/speed/webp])
 AC_CANONICAL_HOST
@@ -749,13 +749,11 @@ fi

 dnl =========================

-dnl Add an empty webp_libname_prefix variable for use in *.pc.in.
-AC_SUBST([webp_libname_prefix])
 AC_CONFIG_MACRO_DIR([m4])
 AC_CONFIG_HEADERS([src/webp/config.h])
 AC_CONFIG_FILES([Makefile src/Makefile man/Makefile \
                 examples/Makefile extras/Makefile imageio/Makefile \
-                 sharpyuv/Makefile sharpyuv/libsharpyuv.pc \
+                 sharpyuv/Makefile \
                 src/dec/Makefile src/enc/Makefile src/dsp/Makefile \
                 src/demux/Makefile src/mux/Makefile \
                 src/utils/Makefile \
--- a/doc/api.md
+++ b/doc/api.md
@@ -233,7 +233,7 @@ WebPIDelete(idec);
 WebPFreeDecBuffer(&config.output);
 ```

-## WebP Mux
+## Webp Mux

 WebPMux is a set of two libraries 'Mux' and 'Demux' for creation, extraction and
 manipulation of an extended format WebP file, which can have features like color
--- a/doc/tools.md
+++ b/doc/tools.md
@@ -82,8 +82,8 @@ Options:
                         green=0xe0 and blue=0xd0
 -noalpha ............... discard any transparency information
 -lossless .............. encode image losslessly, default=off
-near_lossless <int> ... use near-lossless image preprocessing
-                         (0..100=off), default=100
+-near_lossless <int> ... use near-lossless image
+                         preprocessing (0..100=off), default=100
 -hint <string> ......... specify image characteristics hint,
                         one of: photo, picture or graph

@@ -295,23 +295,19 @@ etc.
 Usage:

 ```shell
-img2webp [file_options] [[frame_options] frame_file]... [-o webp_file]
+img2webp [file_options] [[frame_options] frame_file]...
 ```

 File-level options (only used at the start of compression):

 ```
 -min_size ............ minimize size
+-loop <int> .......... loop count (default: 0, = infinite loop)
 -kmax <int> .......... maximum number of frame between key-frames
                        (0=only keyframes)
 -kmin <int> .......... minimum number of frame between key-frames
                        (0=disable key-frames altogether)
 -mixed ............... use mixed lossy/lossless automatic mode
-near_lossless <int> . use near-lossless image preprocessing
-                       (0..100=off), default=100
-sharp_yuv ........... use sharper (and slower) RGB->YUV conversion
-                       (lossy only)
-loop <int> .......... loop count (default: 0, = infinite loop)
 -v ................... verbose mode
 -h ................... this help
 -version ............. print version number and exit
--- a/doc/webp-container-spec.txt
+++ b/doc/webp-container-spec.txt
@@ -20,25 +20,25 @@ WebP Container Specification
 Introduction
 ------------

-WebP is an image format that uses either (i) the VP8 key frame encoding to
-compress image data in a lossy way, or (ii) the WebP lossless encoding. These
-encoding schemes should make it more efficient than older formats such as JPEG,
-GIF and PNG. It is optimized for fast image transfer over the network (for
-example, for websites). The WebP format has feature parity (color profile,
-metadata, animation, etc.) with other formats as well. This document describes
-the structure of a WebP file.
+WebP is an image format that uses either (i) the VP8 key frame encoding
+to compress image data in a lossy way, or (ii) the WebP lossless encoding
+(and possibly other encodings in the future). These encoding schemes should
+make it more efficient than currently used formats. It is optimized for fast
+image transfer over the network (e.g., for websites). The WebP format has
+feature parity (color profile, metadata, animation etc) with other formats as
+well. This document describes the structure of a WebP file.

-The WebP container (that is, the RIFF container for WebP) allows feature support
-over and above the basic use case of WebP (that is, a file containing a single
-image encoded as a VP8 key frame). The WebP container provides additional
-support for:
+The WebP container (i.e., RIFF container for WebP) allows feature support over
+and above the basic use case of WebP (i.e., a file containing a single image
+encoded as a VP8 key frame). The WebP container provides additional support
+for:

  * **Lossless compression.** An image can be losslessly compressed, using the
    WebP Lossless Format.

  * **Metadata.** An image may have metadata stored in Exif or XMP formats.

-  * **Transparency.** An image may have transparency, that is, an alpha channel.
+  * **Transparency.** An image may have transparency, i.e., an alpha channel.

  * **Color Profile.** An image may have an embedded ICC profile as described
    by the [International Color Consortium][iccspec].
@@ -46,21 +46,20 @@ support for:
  * **Animation.** An image may have multiple frames with pauses between them,
    making it an animation.

-The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", "SHOULD",
-"SHOULD NOT", "RECOMMENDED", "NOT RECOMMENDED", "MAY", and "OPTIONAL" in this
-document are to be interpreted as described in BCP 14 [RFC 2119][] [RFC 8174][]
-when, and only when, they appear in all capitals, as shown here.
+The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT",
+"SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and "OPTIONAL" in this
+document are to be interpreted as described in [RFC 2119][].

 Bit numbering in chunk diagrams starts at `0` for the most significant bit
 ('MSB 0') as described in [RFC 1166][].

-Terminology & Basics
--------------------
+Terminology &amp; Basics
+------------------------

-A WebP file contains either a still image (that is, an encoded matrix of pixels)
+A WebP file contains either a still image (i.e., an encoded matrix of pixels)
 or an [animation](#animation). Optionally, it can also contain transparency
-information, color profile and metadata. We refer to the matrix of pixels as the
-_canvas_ of the image.
+information, color profile and metadata. In case we need to refer only to the
+matrix of pixels, we will call it the _canvas_ of the image.

 Below are additional terms used throughout this document:

@@ -84,19 +83,12 @@ _uint32_
 _FourCC_

 : A _FourCC_ (four-character code) is a _uint32_ created by concatenating four
-  ASCII characters in little-endian order. This means 'aaaa' (0x61616161) and
- 'AAAA' (0x41414141) are treated as different _FourCCs_.
+  ASCII characters in little-endian order.

 _1-based_

-: An unsigned integer field storing values offset by `-1`, for example, such a
-  field would store value _25_ as _24_.
-
-_ChunkHeader('ABCD')_
-
-: This is used to describe the _FourCC_ and _Chunk Size_ header of individual
-  chunks, where 'ABCD' is the FourCC for the chunk. This element's size is 8
-  bytes.
+: An unsigned integer field storing values offset by `-1`. e.g., Such a field
+  would store value _25_ as _24_.


 RIFF File Format
@@ -114,7 +106,7 @@ The basic element of a RIFF file is a _chunk_. It consists of:
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
    |                          Chunk Size                           |
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-    :                         Chunk Payload                         :
+    |                         Chunk Payload                         |
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

 Chunk FourCC: 32 bits
@@ -123,13 +115,19 @@ Chunk FourCC: 32 bits

 Chunk Size: 32 bits (_uint32_)

-: The size of the chunk in bytes, not including this field, the chunk
-  identifier or padding.
+: The size of the chunk not including this field, the chunk identifier or
+  padding.

 Chunk Payload: _Chunk Size_ bytes

-: The data payload. If _Chunk Size_ is odd, a single padding byte -- that MUST
-  be `0` to conform with RIFF -- is added.
+: The data payload. If _Chunk Size_ is odd, a single padding byte -- that
+  SHOULD be `0` -- is added.
+
+_ChunkHeader('ABCD')_
+
+: This is used to describe the _FourCC_ and _Chunk Size_ header of individual
+  chunks, where 'ABCD' is the FourCC for the chunk. This element's
+  size is 8 bytes.

 **Note:** RIFF has a convention that all-uppercase chunk FourCCs are standard
 chunks that apply to any RIFF file format, while FourCCs specific to a file
@@ -165,11 +163,9 @@ File Size: 32 bits (_uint32_)

 A WebP file MUST begin with a RIFF header with the FourCC 'WEBP'. The file size
 in the header is the total size of the chunks that follow plus `4` bytes for
-the 'WEBP' FourCC. The file SHOULD NOT contain any data after the data
-specified by _File Size_. Readers MAY parse such files, ignoring the trailing
-data. As the size of any chunk is even, the size given by the RIFF header is
-also even. The contents of individual chunks are described in the following
-sections.
+the 'WEBP' FourCC. The file SHOULD NOT contain anything after it. As the size
+of any chunk is even, the size given by the RIFF header is also even. The
+contents of individual chunks will be described in the following sections.


 Simple File Format (Lossy)
@@ -184,11 +180,9 @@ Simple WebP (lossy) file format:
     0                   1                   2                   3
     0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-    |                                                               |
    |                    WebP file header (12 bytes)                |
-    |                                                               |
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-    :                          VP8 chunk                            :
+    |                          VP8 chunk                            |
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

 VP8 chunk:
@@ -197,24 +191,20 @@ VP8 chunk:
     0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
    |                      ChunkHeader('VP8 ')                      |
-    |                                                               |
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-    :                           VP8 data                            :
+    |                           VP8 data                            |
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

 VP8 data: _Chunk Size_ bytes

 : VP8 bitstream data.

-Note the fourth character in the 'VP8 ' FourCC is an ASCII space (0x20).
-
 The VP8 bitstream format specification can be found at [VP8 Data Format and
 Decoding Guide][vp8spec]. Note that the VP8 frame header contains the VP8 frame
 width and height. That is assumed to be the width and height of the canvas.

-The VP8 specification describes how to decode the image into Y'CbCr format. To
-convert to RGB, Rec. 601 SHOULD be used. Applications MAY use another
-conversion method, but visual results may differ among decoders.
+The VP8 specification describes how to decode the image into Y'CbCr
+format. To convert to RGB, Rec. 601 SHOULD be used.


 Simple File Format (Lossless)
@@ -231,11 +221,9 @@ Simple WebP (lossless) file format:
     0                   1                   2                   3
     0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-    |                                                               |
    |                    WebP file header (12 bytes)                |
-    |                                                               |
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-    :                          VP8L chunk                           :
+    |                          VP8L chunk                           |
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

 VP8L chunk:
@@ -244,9 +232,8 @@ VP8L chunk:
     0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
    |                      ChunkHeader('VP8L')                      |
-    |                                                               |
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-    :                           VP8L data                           :
+    |                           VP8L data                           |
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

 VP8L data: _Chunk Size_ bytes
@@ -292,7 +279,7 @@ details about frames can be found in the [Animation](#animation) section.

 All chunks SHOULD be placed in the same order as listed above. If a chunk
 appears in the wrong place, the file is invalid, but readers MAY parse the
-file, ignoring the chunks that are out of order.
+file, ignoring the chunks that come too late.

 **Rationale:** Setting the order of chunks should allow quicker file
 parsing. For example, if an 'ALPH' chunk does not appear in its required
@@ -306,12 +293,9 @@ Extended WebP file header:
     0                   1                   2                   3
     0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-    |                                                               |
    |                   WebP file header (12 bytes)                 |
-    |                                                               |
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
    |                      ChunkHeader('VP8X')                      |
-    |                                                               |
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
    |Rsv|I|L|E|X|A|R|                   Reserved                    |
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
@@ -322,7 +306,7 @@ Extended WebP file header:

 Reserved (Rsv): 2 bits

-: MUST be `0`. Readers MUST ignore this field.
+: SHOULD be `0`.

 ICC profile (I): 1 bit

@@ -348,11 +332,11 @@ Animation (A): 1 bit

 Reserved (R): 1 bit

-: MUST be `0`. Readers MUST ignore this field.
+: SHOULD be `0`.

 Reserved: 24 bits

-: MUST be `0`. Readers MUST ignore this field.
+: SHOULD be `0`.

 Canvas Width Minus One: 24 bits

@@ -366,7 +350,7 @@ Canvas Height Minus One: 24 bits

 The product of _Canvas Width_ and _Canvas Height_ MUST be at most `2^32 - 1`.

-Future specifications may add more fields. Unknown fields MUST be ignored.
+Future specifications MAY add more fields.

 ### Chunks

@@ -384,7 +368,6 @@ animation.
     0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
    |                      ChunkHeader('ANIM')                      |
-    |                                                               |
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
    |                       Background Color                        |
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
@@ -400,8 +383,8 @@ Background Color: 32 bits (_uint32_)

 **Note**:

-  * Background color MAY contain a non-opaque alpha value, even if the _Alpha_
-    flag in [VP8X chunk](#extended_header) is unset.
+  * Background color MAY contain a transparency value (alpha), even if the
+    _Alpha_ flag in [VP8X chunk](#extended_header) is unset.

  * Viewer applications SHOULD treat the background color value as a hint, and
    are not required to use it.
@@ -414,8 +397,8 @@ Loop Count: 16 bits (_uint16_)
 : The number of times to loop the animation. `0` means infinitely.

 This chunk MUST appear if the _Animation_ flag in the VP8X chunk is set.
-If the _Animation_ flag is not set and this chunk is present, it MUST be
-ignored.
+If the _Animation_ flag is not set and this chunk is present, it
+SHOULD be ignored.

 ANMF chunk:

@@ -426,7 +409,6 @@ If the _Animation flag_ is not set, then this chunk SHOULD NOT be present.
     0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
    |                      ChunkHeader('ANMF')                      |
-    |                                                               |
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
    |                        Frame X                |             ...
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
@@ -436,7 +418,7 @@ If the _Animation flag_ is not set, then this chunk SHOULD NOT be present.
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
    |                 Frame Duration                |  Reserved |B|D|
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-    :                         Frame Data                            :
+    |                         Frame Data                            |
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

 Frame X: 24 bits (_uint24_)
@@ -466,7 +448,7 @@ Frame Duration: 24 bits (_uint24_)

 Reserved: 6 bits

-: MUST be `0`. Readers MUST ignore this field.
+: SHOULD be 0.

 Blending method (B): 1 bit

@@ -511,9 +493,8 @@ Disposal method (D): 1 bit
    if blend.A = 0 then
      blend.RGB = 0
    else
-      blend.RGB =
-          (src.RGB * src.A +
-           dst.RGB * dst.A * (1 - src.A / 255)) / blend.A
+      blend.RGB = (src.RGB * src.A +
+                   dst.RGB * dst.A * (1 - src.A / 255)) / blend.A
 ~~~~~

  * Alpha-blending SHOULD be done in linear color space, by taking into account
@@ -540,23 +521,22 @@ _padded_ chunks as described by the [RIFF file format](#riff-file-format).
     0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
    |                      ChunkHeader('ALPH')                      |
-    |                                                               |
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
    |Rsv| P | F | C |     Alpha Bitstream...                        |
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

 Reserved (Rsv): 2 bits

-: MUST be `0`. Readers MUST ignore this field.
+: SHOULD be `0`.

 Pre-processing (P): 2 bits

-: These _informative_ bits are used to signal the pre-processing that has
+: These INFORMATIVE bits are used to signal the pre-processing that has
  been performed during compression. The decoder can use this information to
-  for example, dither the values or smooth the gradients prior to display.
+  e.g. dither the values or smooth the gradients prior to display.

-    * `0`: No pre-processing.
-    * `1`: Level reduction.
+    * `0`: no pre-processing
+    * `1`: level reduction

 Filtering method (F): 2 bits

@@ -589,14 +569,14 @@ where `clip(v)` is equal to:
  * v    otherwise

 The final value is derived by adding the decompressed value `X` to the
-predictor and using modulo-256 arithmetic to wrap the \[256..511\] range
-into the \[0..255\] one:
+predictor and using modulo-256 arithmetic to wrap the \[256-511\] range
+into the \[0-255\] one:

 `alpha = (predictor + X) % 256`

-There are special cases for the left-most and top-most pixel positions:
+There are special cases for left-most and top-most pixel positions:

-  * The top-left value at location (0, 0) uses 0 as predictor value. Otherwise,
+  * Top-left value at location (0,0) uses 0 as predictor value. Otherwise,
  * For horizontal or gradient filtering methods, the left-most pixels at
    location (0, y) are predicted using the location (0, y-1) just above.
  * For vertical or gradient filtering methods, the top-most pixels at
@@ -658,15 +638,14 @@ The formats of VP8 and VP8L chunks are as described in sections
 [Simple File Format (Lossy)](#simple-file-format-lossy)
 and [Simple File Format (Lossless)](#simple-file-format-lossless) respectively.

-#### Color Profile
+#### Color profile

     0                   1                   2                   3
     0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
    |                      ChunkHeader('ICCP')                      |
-    |                                                               |
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-    :                       Color Profile                           :
+    |                       Color Profile                           |
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

 Color Profile: _Chunk Size_ bytes
@@ -686,7 +665,8 @@ If this chunk is not present, sRGB SHOULD be assumed.
 Metadata can be stored in 'EXIF' or 'XMP ' chunks.

 There SHOULD be at most one chunk of each type ('EXIF' and 'XMP '). If there
-are more such chunks, readers MAY ignore all except the first one.
+are more such chunks, readers MAY ignore all except the first one. Also, a file
+may possibly contain both 'EXIF' and 'XMP ' chunks.

 The chunks are defined as follows:

@@ -696,14 +676,13 @@ EXIF chunk:
     0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
    |                      ChunkHeader('EXIF')                      |
-    |                                                               |
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-    :                        Exif Metadata                          :
+    |                        Exif Metadata                          |
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

 Exif Metadata: _Chunk Size_ bytes

-: Image metadata in Exif format.
+: image metadata in Exif format.

 XMP chunk:

@@ -711,16 +690,13 @@ XMP chunk:
     0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
    |                      ChunkHeader('XMP ')                      |
-    |                                                               |
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
-    :                        XMP Metadata                           :
+    |                        XMP Metadata                           |
    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

 XMP Metadata: _Chunk Size_ bytes

-: Image metadata in XMP format.
-
-Note the fourth character in the 'XMP ' FourCC is an ASCII space (0x20).
+: image metadata in XMP format.

 Additional guidance about handling metadata can be found in the
 Metadata Working Group's [Guidelines for Handling Metadata][metadata].
@@ -744,73 +720,49 @@ A file MAY contain unknown chunks:
 Readers SHOULD ignore these chunks. Writers SHOULD preserve them in their
 original order (unless they specifically intend to modify these chunks).

-### Assembling the Canvas From Frames
+### Assembling the Canvas from frames

-Here we provide an overview of how a reader MUST assemble a canvas in the case
-of an animated image.
+Here we provide an overview of how a reader should assemble a canvas in the
+case of an animated image. The notation _VP8X.field_ means the field in the
+'VP8X' chunk with the same description.

-The process begins with creating a canvas using the dimensions given in the
-'VP8X' chunk, `Canvas Width Minus One + 1` pixels wide by `Canvas Height Minus
-One + 1` pixels high. The `Loop Count` field from the 'ANIM' chunk controls how
-many times the animation process is repeated. This is `Loop Count - 1` for
-non-zero `Loop Count` values or infinitely if `Loop Count` is zero.
-
-At the beginning of each loop iteration the canvas is filled using the
-background color from the 'ANIM' chunk or an application defined color.
-
-'ANMF' chunks contain individual frames given in display order. Before rendering
-each frame, the previous frame's `Disposal method` is applied.
-
-The rendering of the decoded frame begins at the Cartesian coordinates (`2 *
-Frame X`, `2 * Frame Y`) using the top-left corner of the canvas as the origin.
-`Frame Width Minus One + 1` pixels wide by `Frame Height Minus One + 1` pixels
-high are rendered onto the canvas using the `Blending method`.
-
-The canvas is displayed for `Frame Duration` milliseconds. This continues until
-all frames given by 'ANMF' chunks have been displayed. A new loop iteration is
-then begun or the canvas is left in its final state if all iterations have been
-completed.
-
-The following pseudocode illustrates the rendering process. The notation
-_VP8X.field_ means the field in the 'VP8X' chunk with the same description.
+Displaying an _animated image_ canvas MUST be equivalent to the following
+pseudocode:

 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 assert VP8X.flags.hasAnimation
 canvas ← new image of size VP8X.canvasWidth x VP8X.canvasHeight with
         background color ANIM.background_color.
 loop_count ← ANIM.loopCount
-dispose_method ← Dispose to background color
+dispose_method ← ANIM.disposeMethod
 if loop_count == 0:
-  loop_count = ∞
+    loop_count = ∞
 frame_params ← nil
 assert next chunk in image_data is ANMF
 for loop = 0..loop_count - 1
-  clear canvas to ANIM.background_color or application defined color
-  until eof or non-ANMF chunk
-    frame_params.frameX = Frame X
-    frame_params.frameY = Frame Y
-    frame_params.frameWidth = Frame Width Minus One + 1
-    frame_params.frameHeight = Frame Height Minus One + 1
-    frame_params.frameDuration = Frame Duration
-    frame_right = frame_params.frameX + frame_params.frameWidth
-    frame_bottom = frame_params.frameY + frame_params.frameHeight
-    assert VP8X.canvasWidth >= frame_right
-    assert VP8X.canvasHeight >= frame_bottom
-    for subchunk in 'Frame Data':
-      if subchunk.tag == "ALPH":
-        assert alpha subchunks not found in 'Frame Data' earlier
-        frame_params.alpha = alpha_data
-      else if subchunk.tag == "VP8 " OR subchunk.tag == "VP8L":
-        assert bitstream subchunks not found in 'Frame Data' earlier
-        frame_params.bitstream = bitstream_data
-    render frame with frame_params.alpha and frame_params.bitstream
-      on canvas with top-left corner at (frame_params.frameX,
-      frame_params.frameY), using blending method
-      frame_params.blendingMethod.
-    canvas contains the decoded image.
-    Show the contents of the canvas for
-    frame_params.frameDuration * 1ms.
-    dispose_method = frame_params.disposeMethod
+    clear canvas to ANIM.background_color or application defined color
+    until eof or non-ANMF chunk
+        frame_params.frameX = Frame X
+        frame_params.frameY = Frame Y
+        frame_params.frameWidth = Frame Width Minus One + 1
+        frame_params.frameHeight = Frame Height Minus One + 1
+        frame_params.frameDuration = Frame Duration
+        frame_right = frame_params.frameX + frame_params.frameWidth
+        frame_bottom = frame_params.frameY + frame_params.frameHeight
+        assert VP8X.canvasWidth >= frame_right
+        assert VP8X.canvasHeight >= frame_bottom
+        for subchunk in 'Frame Data':
+            if subchunk.tag == "ALPH":
+                assert alpha subchunks not found in 'Frame Data' earlier
+                frame_params.alpha = alpha_data
+            else if subchunk.tag == "VP8 " OR subchunk.tag == "VP8L":
+                assert bitstream subchunks not found in 'Frame Data' earlier
+                frame_params.bitstream = bitstream_data
+        render frame with frame_params.alpha and frame_params.bitstream on
+            canvas with top-left corner at (frame_params.frameX,
+            frame_params.frameY), using dispose method dispose_method.
+        canvas contains the decoded image.
+        Show the contents of the canvas for frame_params.frameDuration * 1ms.
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~


@@ -865,4 +817,3 @@ RIFF/WEBP
 [metadata]: https://web.archive.org/web/20180919181934/http://www.metadataworkinggroup.org/pdf/mwg_guidance.pdf
 [rfc 1166]: https://datatracker.ietf.org/doc/html/rfc1166
 [rfc 2119]: https://datatracker.ietf.org/doc/html/rfc2119
-[rfc 8174]: https://datatracker.ietf.org/doc/html/rfc8174
--- a/doc/webp-lossless-bitstream-spec.txt
+++ b/doc/webp-lossless-bitstream-spec.txt
--- a/examples/Android.mk
+++ b/examples/Android.mk
@@ -1,5 +1,3 @@
-# Ignore this file during non-NDK builds.
-ifdef NDK_ROOT
 LOCAL_PATH := $(call my-dir)

 ################################################################################
@@ -93,4 +91,3 @@ LOCAL_STATIC_LIBRARIES := example_util imageio_util webp
 LOCAL_MODULE := webpinfo_example

 include $(BUILD_EXECUTABLE)
-endif  # NDK_ROOT
--- a/examples/Makefile.am
+++ b/examples/Makefile.am
@@ -47,7 +47,7 @@ anim_dump_LDADD += ../imageio/libimageenc.la
 anim_dump_LDADD += $(PNG_LIBS) $(GIF_LIBS) $(TIFF_LIBS) -lm

 cwebp_SOURCES  = cwebp.c stopwatch.h
-cwebp_CPPFLAGS  = $(AM_CPPFLAGS) -I$(top_srcdir)
+cwebp_CPPFLAGS  = $(AM_CPPFLAGS)
 cwebp_LDADD  =
 cwebp_LDADD += libexample_util.la
 cwebp_LDADD += ../imageio/libimageio_util.la
@@ -92,7 +92,7 @@ webpmux_LDADD += ../src/mux/libwebpmux.la
 webpmux_LDADD += ../src/libwebp.la

 img2webp_SOURCES = img2webp.c
-img2webp_CPPFLAGS = $(AM_CPPFLAGS) -I$(top_srcdir)
+img2webp_CPPFLAGS = $(AM_CPPFLAGS)
 img2webp_LDADD  =
 img2webp_LDADD += libexample_util.la
 img2webp_LDADD += ../imageio/libimageio_util.la
--- a/examples/cwebp.c
+++ b/examples/cwebp.c
@@ -27,7 +27,6 @@
 #include "../imageio/webpdec.h"
 #include "./stopwatch.h"
 #include "./unicode.h"
-#include "sharpyuv/sharpyuv.h"
 #include "webp/encode.h"

 #ifndef WEBP_DLL
@@ -592,8 +591,9 @@ static void HelpLong(void) {
         "                           green=0xe0 and blue=0xd0\n");
  printf("  -noalpha ............... discard any transparency information\n");
  printf("  -lossless .............. encode image losslessly, default=off\n");
-  printf("  -near_lossless <int> ... use near-lossless image preprocessing\n"
-         "                           (0..100=off), default=100\n");
+  printf("  -near_lossless <int> ... use near-lossless image\n"
+         "                           preprocessing (0..100=off), "
+         "default=100\n");
  printf("  -hint <string> ......... specify image characteristics hint,\n");
  printf("                           one of: photo, picture or graph\n");

@@ -832,12 +832,8 @@ int main(int argc, const char* argv[]) {
 #endif
    } else if (!strcmp(argv[c], "-version")) {
      const int version = WebPGetEncoderVersion();
-      const int sharpyuv_version = SharpYuvGetVersion();
      printf("%d.%d.%d\n",
             (version >> 16) & 0xff, (version >> 8) & 0xff, version & 0xff);
-      printf("libsharpyuv: %d.%d.%d\n",
-             (sharpyuv_version >> 24) & 0xff, (sharpyuv_version >> 16) & 0xffff,
-             sharpyuv_version & 0xff);
      FREE_WARGV_AND_RETURN(0);
    } else if (!strcmp(argv[c], "-progress")) {
      show_progress = 1;
@@ -1144,10 +1140,9 @@ int main(int argc, const char* argv[]) {
      }

      picture.use_argb = 1;
-      if (!ReadWebP(
-              memory_writer.mem, memory_writer.size, &picture,
-              /*keep_alpha=*/WebPPictureHasTransparency(&original_picture),
-              /*metadata=*/NULL)) {
+      if (!ReadWebP(memory_writer.mem, memory_writer.size, &picture,
+                    /*keep_alpha=*/WebPPictureHasTransparency(&picture),
+                    /*metadata=*/NULL)) {
        fprintf(stderr, "Error! Cannot decode encoded WebP bitstream\n");
        fprintf(stderr, "Error code: %d (%s)\n", picture.error_code,
                kErrorMessages[picture.error_code]);
--- a/examples/img2webp.c
+++ b/examples/img2webp.c
@@ -28,7 +28,6 @@
 #include "../imageio/imageio_util.h"
 #include "./stopwatch.h"
 #include "./unicode.h"
-#include "sharpyuv/sharpyuv.h"
 #include "webp/encode.h"
 #include "webp/mux.h"

@@ -36,22 +35,17 @@

 static void Help(void) {
  printf("Usage:\n\n");
-  printf("  img2webp [file_options] [[frame_options] frame_file]...");
-  printf(" [-o webp_file]\n\n");
+  printf("  img2webp [file_options] [[frame_options] frame_file]...\n");
+  printf("\n");

  printf("File-level options (only used at the start of compression):\n");
  printf(" -min_size ............ minimize size\n");
+  printf(" -loop <int> .......... loop count (default: 0, = infinite loop)\n");
  printf(" -kmax <int> .......... maximum number of frame between key-frames\n"
         "                        (0=only keyframes)\n");
  printf(" -kmin <int> .......... minimum number of frame between key-frames\n"
         "                        (0=disable key-frames altogether)\n");
  printf(" -mixed ............... use mixed lossy/lossless automatic mode\n");
-  printf(" -near_lossless <int> . use near-lossless image preprocessing\n"
-         "                        (0..100=off), default=100\n");
-  printf(" -sharp_yuv ........... use sharper (and slower) RGB->YUV "
-                                  "conversion\n                        "
-                                  "(lossy only)\n");
-  printf(" -loop <int> .......... loop count (default: 0, = infinite loop)\n");
  printf(" -v ................... verbose mode\n");
  printf(" -h ................... this help\n");
  printf(" -version ............. print version number and exit\n");
@@ -190,11 +184,6 @@ int main(int argc, const char* argv[]) {
      } else if (!strcmp(argv[c], "-mixed")) {
        anim_config.allow_mixed = 1;
        config.lossless = 0;
-      } else if (!strcmp(argv[c], "-near_lossless") && c + 1 < argc) {
-        argv[c] = NULL;
-        config.near_lossless = ExUtilGetInt(argv[++c], 0, &parse_error);
-      } else if (!strcmp(argv[c], "-sharp_yuv")) {
-        config.use_sharp_yuv = 1;
      } else if (!strcmp(argv[c], "-v")) {
        verbose = 1;
      } else if (!strcmp(argv[c], "-h") || !strcmp(argv[c], "-help")) {
@@ -203,13 +192,10 @@ int main(int argc, const char* argv[]) {
      } else if (!strcmp(argv[c], "-version")) {
        const int enc_version = WebPGetEncoderVersion();
        const int mux_version = WebPGetMuxVersion();
-        const int sharpyuv_version = SharpYuvGetVersion();
        printf("WebP Encoder version: %d.%d.%d\nWebP Mux version: %d.%d.%d\n",
               (enc_version >> 16) & 0xff, (enc_version >> 8) & 0xff,
               enc_version & 0xff, (mux_version >> 16) & 0xff,
               (mux_version >> 8) & 0xff, mux_version & 0xff);
-        printf("libsharpyuv: %d.%d.%d\n", (sharpyuv_version >> 24) & 0xff,
-               (sharpyuv_version >> 16) & 0xffff, sharpyuv_version & 0xff);
        goto End;
      } else {
        continue;
--- a/extras/extras.c
+++ b/extras/extras.c
@@ -18,8 +18,8 @@
 #include <string.h>

 #define XTRA_MAJ_VERSION 1
-#define XTRA_MIN_VERSION 3
-#define XTRA_REV_VERSION 2
+#define XTRA_MIN_VERSION 2
+#define XTRA_REV_VERSION 3

 //------------------------------------------------------------------------------

--- a/extras/vwebp_sdl.c
+++ b/extras/vwebp_sdl.c
@@ -75,7 +75,7 @@ int main(int argc, char* argv[]) {
      fprintf(stderr, "File too large.\n");
      goto Error;
    }
-    ok = WebPToSDL((const char*)webp, (int)webp_size);
+    ok = WebpToSDL((const char*)webp, (int)webp_size);
    free((void*)webp);
    if (!ok) {
      WFPRINTF(stderr, "Error decoding file %s\n", (const W_CHAR*)file);
--- a/extras/webp_to_sdl.c
+++ b/extras/webp_to_sdl.c
@@ -29,7 +29,7 @@
 #endif

 static int init_ok = 0;
-int WebPToSDL(const char* data, unsigned int data_size) {
+int WebpToSDL(const char* data, unsigned int data_size) {
  int ok = 0;
  VP8StatusCode status;
  WebPDecoderConfig config;
--- a/extras/webp_to_sdl.h
+++ b/extras/webp_to_sdl.h
@@ -14,9 +14,9 @@
 #ifndef WEBP_EXTRAS_WEBP_TO_SDL_H_
 #define WEBP_EXTRAS_WEBP_TO_SDL_H_

-// Exports the method WebPToSDL(const char* data, int data_size) which decodes
+// Exports the method WebpToSDL(const char* data, int data_size) which decodes
 // a WebP bitstream into an RGBA SDL surface.
 // Return false on failure.
-extern int WebPToSDL(const char* data, unsigned int data_size);
+extern int WebpToSDL(const char* data, unsigned int data_size);

 #endif  // WEBP_EXTRAS_WEBP_TO_SDL_H_
--- a/imageio/Android.mk
+++ b/imageio/Android.mk
@@ -1,5 +1,3 @@
-# Ignore this file during non-NDK builds.
-ifdef NDK_ROOT
 LOCAL_PATH := $(call my-dir)

 ################################################################################
@@ -54,4 +52,3 @@ LOCAL_STATIC_LIBRARIES := imageio_util
 LOCAL_MODULE := imageenc

 include $(BUILD_STATIC_LIBRARY)
-endif  # NDK_ROOT
--- a/imageio/pngdec.c
+++ b/imageio/pngdec.c
@@ -235,7 +235,7 @@ int ReadPNG(const uint8_t* const data, size_t data_size,
  volatile png_infop end_info = NULL;
  PNGReadContext context = { NULL, 0, 0 };
  int color_type, bit_depth, interlaced;
-  int num_channels;
+  int has_alpha;
  int num_passes;
  int p;
  volatile int ok = 0;
@@ -293,6 +293,9 @@ int ReadPNG(const uint8_t* const data, size_t data_size,
  }
  if (png_get_valid(png, info, PNG_INFO_tRNS)) {
    png_set_tRNS_to_alpha(png);
+    has_alpha = 1;
+  } else {
+    has_alpha = !!(color_type & PNG_COLOR_MASK_ALPHA);
  }

  // Apply gamma correction if needed.
@@ -307,16 +310,13 @@ int ReadPNG(const uint8_t* const data, size_t data_size,

  if (!keep_alpha) {
    png_set_strip_alpha(png);
+    has_alpha = 0;
  }

  num_passes = png_set_interlace_handling(png);
  png_read_update_info(png, info);

-  num_channels = png_get_channels(png, info);
-  if (num_channels != 3 && num_channels != 4) {
-    goto Error;
-  }
-  stride = (int64_t)num_channels * width * sizeof(*rgb);
+  stride = (int64_t)(has_alpha ? 4 : 3) * width * sizeof(*rgb);
  if (stride != (int)stride ||
      !ImgIoUtilCheckSizeArgumentsOverflow(stride, height)) {
    goto Error;
@@ -341,8 +341,8 @@ int ReadPNG(const uint8_t* const data, size_t data_size,

  pic->width = (int)width;
  pic->height = (int)height;
-  ok = (num_channels == 4) ? WebPPictureImportRGBA(pic, rgb, (int)stride)
-                           : WebPPictureImportRGB(pic, rgb, (int)stride);
+  ok = has_alpha ? WebPPictureImportRGBA(pic, rgb, (int)stride)
+                 : WebPPictureImportRGB(pic, rgb, (int)stride);

  if (!ok) {
    goto Error;
--- a/imageio/pnmdec.c
+++ b/imageio/pnmdec.c
@@ -20,10 +20,6 @@
 #include "webp/encode.h"
 #include "./imageio_util.h"

-#if defined(_MSC_VER) && _MSC_VER < 1900
-#define snprintf _snprintf
-#endif
-
 typedef enum {
  WIDTH_FLAG      = 1 << 0,
  HEIGHT_FLAG     = 1 << 1,
@@ -115,9 +111,8 @@ static size_t ReadPAMFields(PNMInfo* const info, size_t off) {
      break;
    } else {
      static const char kEllipsis[] = " ...";
-      const size_t kLen = strlen(kEllipsis) + 1;  // +1 = trailing \0
      int i;
-      if (out_size > 20) snprintf(out + 20 - kLen, kLen, kEllipsis);
+      if (out_size > 20) sprintf(out + 20 - strlen(kEllipsis), kEllipsis);
      for (i = 0; i < (int)strlen(out); ++i) {
        // isprint() might trigger a "char-subscripts" warning if given a char.
        if (!isprint((int)out[i])) out[i] = ' ';
--- a/makefile.unix
+++ b/makefile.unix
@@ -3,8 +3,7 @@
 # It will not install the libraries system-wide, but just create the 'cwebp'
 # and 'dwebp' tools in the examples/ directory, along with the static
 # libraries 'src/libwebp.a', 'src/libwebpdecoder.a', 'src/mux/libwebpmux.a',
-# 'src/demux/libwebpdemux.a', 'extras/libwebpextras.a' and
-# 'sharpyuv/libsharpyuv.a'.
+# 'src/demux/libwebpdemux.a' and 'extras/libwebpextras.a'.
 #
 # To build the library and examples, use:
 #    make -f makefile.unix
@@ -128,7 +127,6 @@ ANIM_UTIL_OBJS = \

 SHARPYUV_OBJS = \
    sharpyuv/sharpyuv.o \
-    sharpyuv/sharpyuv_cpu.o \
    sharpyuv/sharpyuv_csp.o \
    sharpyuv/sharpyuv_dsp.o \
    sharpyuv/sharpyuv_gamma.o \
@@ -292,12 +290,11 @@ EXTRA_OBJS = \
    extras/quality_estimate.o \

 LIBWEBPDECODER_OBJS = $(DEC_OBJS) $(DSP_DEC_OBJS) $(UTILS_DEC_OBJS)
-LIBWEBP_OBJS = $(LIBWEBPDECODER_OBJS) $(ENC_OBJS) \
+LIBWEBP_OBJS = $(SHARPYUV_OBJS) $(LIBWEBPDECODER_OBJS) $(ENC_OBJS) \
               $(DSP_ENC_OBJS) $(UTILS_ENC_OBJS)
 LIBWEBPMUX_OBJS = $(MUX_OBJS)
 LIBWEBPDEMUX_OBJS = $(DEMUX_OBJS)
 LIBWEBPEXTRA_OBJS = $(EXTRA_OBJS)
-LIBSHARPYUV_OBJS = $(SHARPYUV_OBJS)

 HDRS_INSTALLED = \
    src/webp/decode.h \
@@ -307,11 +304,6 @@ HDRS_INSTALLED = \
    src/webp/mux_types.h \
    src/webp/types.h \

-SHARPYUV_HDRS_INSTALLED = \
-    sharpyuv/sharpyuv.h \
-    sharpyuv/sharpyuv_cpu.h \
-    sharpyuv/sharpyuv_csp.h \
-
 HDRS = \
    src/dec/alphai_dec.h \
    src/dec/common_dec.h \
@@ -351,7 +343,6 @@ HDRS = \
    src/utils/utils.h \
    src/webp/format_constants.h \
    $(HDRS_INSTALLED) \
-    $(SHARPYUV_HDRS_INSTALLED) \

 OUT_LIBS = examples/libexample_util.a
 OUT_LIBS += imageio/libimageio_util.a
@@ -359,7 +350,6 @@ OUT_LIBS += imageio/libimagedec.a
 OUT_LIBS += imageio/libimageenc.a
 OUT_LIBS += src/libwebpdecoder.a
 OUT_LIBS += src/libwebp.a
-OUT_LIBS += sharpyuv/libsharpyuv.a
 EXTRA_LIB = extras/libwebpextras.a
 OUT_EXAMPLES = examples/cwebp examples/dwebp
 EXTRA_EXAMPLES = examples/gif2webp examples/vwebp examples/webpmux \
@@ -405,7 +395,6 @@ src/libwebpdecoder.a: $(LIBWEBPDECODER_OBJS)
 src/libwebp.a: $(LIBWEBP_OBJS)
 src/mux/libwebpmux.a: $(LIBWEBPMUX_OBJS)
 src/demux/libwebpdemux.a: $(LIBWEBPDEMUX_OBJS)
-sharpyuv/libsharpyuv.a: $(LIBSHARPYUV_OBJS)

 %.a:
 	$(AR) $(ARFLAGS) $@ $^
@@ -423,7 +412,6 @@ examples/webpinfo: examples/webpinfo.o
 examples/anim_diff: examples/libanim_util.a examples/libgifdec.a
 examples/anim_diff: src/demux/libwebpdemux.a examples/libexample_util.a
 examples/anim_diff: imageio/libimageio_util.a src/libwebp.a
-examples/anim_diff: sharpyuv/libsharpyuv.a
 examples/anim_diff: override EXTRA_LIBS += $(GIF_LIBS)
 examples/anim_diff: EXTRA_FLAGS += -DWEBP_HAVE_GIF
 examples/anim_dump: examples/libanim_util.a examples/libgifdec.a
@@ -432,14 +420,12 @@ examples/anim_dump: examples/libexample_util.a
 examples/anim_dump: imageio/libimageio_util.a
 examples/anim_dump: imageio/libimageenc.a
 examples/anim_dump: src/libwebp.a
-examples/anim_dump: sharpyuv/libsharpyuv.a
 examples/anim_dump: override EXTRA_LIBS += $(GIF_LIBS) $(DWEBP_LIBS)
 examples/cwebp: examples/libexample_util.a
 examples/cwebp: imageio/libimagedec.a
 examples/cwebp: src/demux/libwebpdemux.a
 examples/cwebp: imageio/libimageio_util.a
 examples/cwebp: src/libwebp.a
-examples/cwebp: sharpyuv/libsharpyuv.a
 examples/cwebp: override EXTRA_LIBS += $(CWEBP_LIBS)
 examples/dwebp: examples/libexample_util.a
 examples/dwebp: imageio/libimagedec.a
@@ -447,16 +433,13 @@ examples/dwebp: src/demux/libwebpdemux.a
 examples/dwebp: imageio/libimageenc.a
 examples/dwebp: imageio/libimageio_util.a
 examples/dwebp: src/libwebp.a
-examples/dwebp: sharpyuv/libsharpyuv.a
 examples/dwebp: override EXTRA_LIBS += $(DWEBP_LIBS)
 examples/gif2webp: examples/libexample_util.a imageio/libimageio_util.a
 examples/gif2webp: examples/libgifdec.a src/mux/libwebpmux.a src/libwebp.a
-examples/gif2webp: sharpyuv/libsharpyuv.a
 examples/gif2webp: override EXTRA_LIBS += $(GIF_LIBS)
 examples/gif2webp: EXTRA_FLAGS += -DWEBP_HAVE_GIF
 examples/vwebp: examples/libexample_util.a src/demux/libwebpdemux.a
 examples/vwebp: imageio/libimageio_util.a src/libwebp.a
-examples/vwebp: sharpyuv/libsharpyuv.a
 examples/vwebp: override EXTRA_LIBS += $(GL_LIBS)
 examples/vwebp: EXTRA_FLAGS += -DWEBP_HAVE_GL
 examples/webpmux: examples/libexample_util.a imageio/libimageio_util.a
@@ -464,9 +447,7 @@ examples/webpmux: src/mux/libwebpmux.a src/libwebpdecoder.a
 examples/img2webp: examples/libexample_util.a imageio/libimageio_util.a
 examples/img2webp: imageio/libimagedec.a
 examples/img2webp: src/demux/libwebpdemux.a
-examples/img2webp: src/mux/libwebpmux.a
-examples/img2webp: src/libwebp.a
-examples/img2webp: sharpyuv/libsharpyuv.a
+examples/img2webp: src/mux/libwebpmux.a src/libwebp.a
 examples/img2webp: override EXTRA_LIBS += $(CWEBP_LIBS)
 examples/webpinfo: examples/libexample_util.a imageio/libimageio_util.a
 examples/webpinfo: src/libwebpdecoder.a
@@ -476,19 +457,16 @@ extras/get_disto: imageio/libimagedec.a
 extras/get_disto: src/demux/libwebpdemux.a
 extras/get_disto: imageio/libimageio_util.a
 extras/get_disto: src/libwebp.a
-extras/get_disto: sharpyuv/libsharpyuv.a
 extras/get_disto: override EXTRA_LIBS += $(CWEBP_LIBS)

 extras/webp_quality: extras/webp_quality.o
 extras/webp_quality: imageio/libimageio_util.a
 extras/webp_quality: $(EXTRA_LIB) src/libwebp.a
-extras/webp_quality: sharpyuv/libsharpyuv.a

 extras/vwebp_sdl: extras/vwebp_sdl.o
 extras/vwebp_sdl: extras/webp_to_sdl.o
 extras/vwebp_sdl: imageio/libimageio_util.a
 extras/vwebp_sdl: src/libwebp.a
-extras/vwebp_sdl: sharpyuv/libsharpyuv.a
 extras/vwebp_sdl: EXTRA_FLAGS += -DWEBP_HAVE_SDL $(SDL_FLAGS)
 extras/vwebp_sdl: override EXTRA_LIBS += $(SDL_LIBS)

@@ -499,15 +477,12 @@ dist: DESTDIR := dist
 dist: OUT_EXAMPLES += $(EXTRA_EXAMPLES)
 dist: all
 	$(INSTALL) -m755 -d $(DESTDIR)/include/webp \
-	            $(DESTDIR)/include/webp/sharpyuv \
-	            $(DESTDIR)/bin $(DESTDIR)/doc $(DESTDIR)/lib
+	           $(DESTDIR)/bin $(DESTDIR)/doc $(DESTDIR)/lib
 	$(INSTALL) -m755 -s $(OUT_EXAMPLES) $(DESTDIR)/bin
 	$(INSTALL) -m644 $(HDRS_INSTALLED) $(DESTDIR)/include/webp
-	$(INSTALL) -m644 $(SHARPYUV_HDRS_INSTALLED) $(DESTDIR)/include/webp/sharpyuv
 	$(INSTALL) -m644 src/libwebp.a $(DESTDIR)/lib
 	$(INSTALL) -m644 src/demux/libwebpdemux.a $(DESTDIR)/lib
 	$(INSTALL) -m644 src/mux/libwebpmux.a $(DESTDIR)/lib
-	$(INSTALL) -m644 sharpyuv/libsharpyuv.a $(DESTDIR)/lib
 	umask 022; \
 	for m in man/[cdv]webp.1 man/gif2webp.1 man/webpmux.1 \
                 man/img2webp.1 man/webpinfo.1; do \
--- a/man/img2webp.1
+++ b/man/img2webp.1
@@ -1,10 +1,10 @@
 .\"                                      Hey, EMACS: -*- nroff -*-
-.TH IMG2WEBP 1 "March 17, 2023"
+.TH IMG2WEBP 1 "January 5, 2022"
 .SH NAME
 img2webp \- create animated WebP file from a sequence of input images.
 .SH SYNOPSIS
 .B img2webp
-[file_options] [[frame_options] frame_file]... [\-o webp_file]
+[file_options] [[frame_options] frame_file]...
 .br
 .B img2webp argument_file_name
 .br
@@ -44,18 +44,6 @@ Mixed compression mode: optimize compression of the image by picking either
 lossy or lossless compression for each frame heuristically. This global
 option disables the local option \fB-lossy\fP and \fB-lossless\fP .
 .TP
-.BI \-near_lossless " int
-Specify the level of near\-lossless image preprocessing. This option adjusts
-pixel values to help compressibility, but has minimal impact on the visual
-quality. It triggers lossless compression mode automatically. The range is 0
-(maximum preprocessing) to 100 (no preprocessing, the default). The typical
-value is around 60. Note that lossy with \fB\-q 100\fP can at times yield
-better results.
-.TP
-.B \-sharp_yuv
-Use more accurate and sharper RGB->YUV conversion if needed. Note that this
-process is slower than the default 'fast' RGB->YUV conversion.
-.TP
 .BI \-loop " int
 Specifies the number of times the animation should loop. Using '0'
 means 'loop indefinitely'.
--- a/sharpyuv/Makefile.am
+++ b/sharpyuv/Makefile.am
@@ -1,19 +1,13 @@
 AM_CPPFLAGS += -I$(top_builddir) -I$(top_srcdir)
 AM_CPPFLAGS += -I$(top_builddir)/src -I$(top_srcdir)/src
-
-lib_LTLIBRARIES = libsharpyuv.la
-
 noinst_LTLIBRARIES =
+noinst_LTLIBRARIES += libsharpyuv.la
 noinst_LTLIBRARIES += libsharpyuv_sse2.la
 noinst_LTLIBRARIES += libsharpyuv_neon.la

-libsharpyuvinclude_HEADERS =
-libsharpyuvinclude_HEADERS += sharpyuv.h
-libsharpyuvinclude_HEADERS += sharpyuv_csp.h
 noinst_HEADERS =
-noinst_HEADERS += ../src/dsp/cpu.c
-noinst_HEADERS += ../src/dsp/cpu.h
 noinst_HEADERS += ../src/webp/types.h
+noinst_HEADERS += ../src/dsp/cpu.h

 libsharpyuv_sse2_la_SOURCES =
 libsharpyuv_sse2_la_SOURCES += sharpyuv_sse2.c
@@ -26,16 +20,15 @@ libsharpyuv_neon_la_CPPFLAGS = $(libsharpyuv_la_CPPFLAGS)
 libsharpyuv_neon_la_CFLAGS = $(AM_CFLAGS) $(NEON_FLAGS)

 libsharpyuv_la_SOURCES =
-libsharpyuv_la_SOURCES += sharpyuv_cpu.c sharpyuv_cpu.h
 libsharpyuv_la_SOURCES += sharpyuv_csp.c sharpyuv_csp.h
 libsharpyuv_la_SOURCES += sharpyuv_dsp.c sharpyuv_dsp.h
 libsharpyuv_la_SOURCES += sharpyuv_gamma.c sharpyuv_gamma.h
 libsharpyuv_la_SOURCES += sharpyuv.c sharpyuv.h

 libsharpyuv_la_CPPFLAGS = $(AM_CPPFLAGS)
-libsharpyuv_la_LDFLAGS = -no-undefined -version-info 0:1:0 -lm
+libsharpyuv_la_LDFLAGS =
 libsharpyuv_la_LIBADD =
 libsharpyuv_la_LIBADD += libsharpyuv_sse2.la
 libsharpyuv_la_LIBADD += libsharpyuv_neon.la
-libsharpyuvincludedir = $(includedir)/webp/sharpyuv
-pkgconfig_DATA = libsharpyuv.pc
+
+noinst_PROGRAMS =
--- a/sharpyuv/libsharpyuv.pc.in
+++ b/sharpyuv/libsharpyuv.pc.in
@@ -1,11 +0,0 @@
-prefix=@prefix@
-exec_prefix=@exec_prefix@
-libdir=@libdir@
-includedir=@includedir@/webp
-
-Name: libsharpyuv
-Description: Library for sharp RGB to YUV conversion
-Version: @PACKAGE_VERSION@
-Cflags: -I${includedir}
-Libs: -L${libdir} -l@webp_libname_prefix@sharpyuv
-Libs.private: -lm @PTHREAD_CFLAGS@ @PTHREAD_LIBS@
--- a/sharpyuv/libsharpyuv.rc
+++ b/sharpyuv/libsharpyuv.rc
@@ -1,41 +0,0 @@
-#define APSTUDIO_READONLY_SYMBOLS
-#include "winres.h"
-#undef APSTUDIO_READONLY_SYMBOLS
-
-#if !defined(AFX_RESOURCE_DLL) || defined(AFX_TARG_ENU)
-LANGUAGE LANG_ENGLISH, SUBLANG_ENGLISH_US
-
-VS_VERSION_INFO VERSIONINFO
- FILEVERSION 0,0,2,1
- PRODUCTVERSION 0,0,2,1
- FILEFLAGSMASK 0x3fL
-#ifdef _DEBUG
- FILEFLAGS 0x1L
-#else
- FILEFLAGS 0x0L
-#endif
- FILEOS 0x40004L
- FILETYPE 0x2L
- FILESUBTYPE 0x0L
-BEGIN
-    BLOCK "StringFileInfo"
-    BEGIN
-        BLOCK "040904b0"
-        BEGIN
-            VALUE "CompanyName", "Google, Inc."
-            VALUE "FileDescription", "libsharpyuv DLL"
-            VALUE "FileVersion", "0.2.1"
-            VALUE "InternalName", "libsharpyuv.dll"
-            VALUE "LegalCopyright", "Copyright (C) 2023"
-            VALUE "OriginalFilename", "libsharpyuv.dll"
-            VALUE "ProductName", "SharpYuv Library"
-            VALUE "ProductVersion", "0.2.1"
-        END
-    END
-    BLOCK "VarFileInfo"
-    BEGIN
-        VALUE "Translation", 0x409, 1200
-    END
-END
-
-#endif    // English (United States) resources
--- a/sharpyuv/sharpyuv.c
+++ b/sharpyuv/sharpyuv.c
@@ -15,21 +15,15 @@

 #include <assert.h>
 #include <limits.h>
-#include <stddef.h>
+#include <math.h>
 #include <stdlib.h>
 #include <string.h>

 #include "src/webp/types.h"
-#include "sharpyuv/sharpyuv_cpu.h"
+#include "src/dsp/cpu.h"
 #include "sharpyuv/sharpyuv_dsp.h"
 #include "sharpyuv/sharpyuv_gamma.h"

-//------------------------------------------------------------------------------
-
-int SharpYuvGetVersion(void) {
-  return SHARPYUV_VERSION;
-}
-
 //------------------------------------------------------------------------------
 // Sharp RGB->YUV conversion

@@ -420,46 +414,24 @@ static int DoSharpArgbToYuv(const uint8_t* r_ptr, const uint8_t* g_ptr,
 }
 #undef SAFE_ALLOC

-#if defined(WEBP_USE_THREAD) && !defined(_WIN32)
-#include <pthread.h>  // NOLINT
-
-#define LOCK_ACCESS \
-    static pthread_mutex_t sharpyuv_lock = PTHREAD_MUTEX_INITIALIZER; \
-    if (pthread_mutex_lock(&sharpyuv_lock)) return
-#define UNLOCK_ACCESS_AND_RETURN                  \
-    do {                                          \
-      (void)pthread_mutex_unlock(&sharpyuv_lock); \
-      return;                                     \
-    } while (0)
-#else  // !(defined(WEBP_USE_THREAD) && !defined(_WIN32))
-#define LOCK_ACCESS do {} while (0)
-#define UNLOCK_ACCESS_AND_RETURN return
-#endif  // defined(WEBP_USE_THREAD) && !defined(_WIN32)
-
 // Hidden exported init function.
-// By default SharpYuvConvert calls it with SharpYuvGetCPUInfo. If needed,
-// users can declare it as extern and call it with an alternate VP8CPUInfo
-// function.
-extern VP8CPUInfo SharpYuvGetCPUInfo;
-SHARPYUV_EXTERN void SharpYuvInit(VP8CPUInfo cpu_info_func);
+// By default SharpYuvConvert calls it with NULL. If needed, users can declare
+// it as extern and call it with a VP8CPUInfo function.
+extern void SharpYuvInit(VP8CPUInfo cpu_info_func);
 void SharpYuvInit(VP8CPUInfo cpu_info_func) {
  static volatile VP8CPUInfo sharpyuv_last_cpuinfo_used =
      (VP8CPUInfo)&sharpyuv_last_cpuinfo_used;
-  LOCK_ACCESS;
-  // Only update SharpYuvGetCPUInfo when called from external code to avoid a
-  // race on reading the value in SharpYuvConvert().
-  if (cpu_info_func != (VP8CPUInfo)&SharpYuvGetCPUInfo) {
-    SharpYuvGetCPUInfo = cpu_info_func;
-  }
-  if (sharpyuv_last_cpuinfo_used == SharpYuvGetCPUInfo) {
-    UNLOCK_ACCESS_AND_RETURN;
+  const int initialized =
+      (sharpyuv_last_cpuinfo_used != (VP8CPUInfo)&sharpyuv_last_cpuinfo_used);
+  if (cpu_info_func == NULL && initialized) return;
+  if (sharpyuv_last_cpuinfo_used == cpu_info_func) return;
+
+  SharpYuvInitDsp(cpu_info_func);
+  if (!initialized) {
+    SharpYuvInitGammaTables();
  }

-  SharpYuvInitDsp();
-  SharpYuvInitGammaTables();
-
-  sharpyuv_last_cpuinfo_used = SharpYuvGetCPUInfo;
-  UNLOCK_ACCESS_AND_RETURN;
+  sharpyuv_last_cpuinfo_used = cpu_info_func;
 }

 int SharpYuvConvert(const void* r_ptr, const void* g_ptr,
@@ -495,8 +467,7 @@ int SharpYuvConvert(const void* r_ptr, const void* g_ptr,
    // Stride should be even for uint16_t buffers.
    return 0;
  }
-  // The address of the function pointer is used to avoid a read race.
-  SharpYuvInit((VP8CPUInfo)&SharpYuvGetCPUInfo);
+  SharpYuvInit(NULL);

  // Add scaling factor to go from rgb_bit_depth to yuv_bit_depth, to the
  // rgb->yuv conversion matrix.
--- a/sharpyuv/sharpyuv.h
+++ b/sharpyuv/sharpyuv.h
@@ -12,32 +12,16 @@
 #ifndef WEBP_SHARPYUV_SHARPYUV_H_
 #define WEBP_SHARPYUV_SHARPYUV_H_

+#include <inttypes.h>
+
 #ifdef __cplusplus
 extern "C" {
 #endif

-#ifndef SHARPYUV_EXTERN
-#ifdef WEBP_EXTERN
-#define SHARPYUV_EXTERN WEBP_EXTERN
-#else
-// This explicitly marks library functions and allows for changing the
-// signature for e.g., Windows DLL builds.
-#if defined(__GNUC__) && __GNUC__ >= 4
-#define SHARPYUV_EXTERN extern __attribute__((visibility("default")))
-#else
-#if defined(_MSC_VER) && defined(WEBP_DLL)
-#define SHARPYUV_EXTERN __declspec(dllexport)
-#else
-#define SHARPYUV_EXTERN extern
-#endif /* _MSC_VER && WEBP_DLL */
-#endif /* __GNUC__ >= 4 */
-#endif /* WEBP_EXTERN */
-#endif /* SHARPYUV_EXTERN */
-
 // SharpYUV API version following the convention from semver.org
 #define SHARPYUV_VERSION_MAJOR 0
-#define SHARPYUV_VERSION_MINOR 2
-#define SHARPYUV_VERSION_PATCH 1
+#define SHARPYUV_VERSION_MINOR 1
+#define SHARPYUV_VERSION_PATCH 0
 // Version as a uint32_t. The major number is the high 8 bits.
 // The minor number is the middle 8 bits. The patch number is the low 16 bits.
 #define SHARPYUV_MAKE_VERSION(MAJOR, MINOR, PATCH) \
@@ -46,10 +30,6 @@ extern "C" {
  SHARPYUV_MAKE_VERSION(SHARPYUV_VERSION_MAJOR, SHARPYUV_VERSION_MINOR, \
                        SHARPYUV_VERSION_PATCH)

-// Returns the library's version number, packed in hexadecimal. See
-// SHARPYUV_VERSION.
-SHARPYUV_EXTERN int SharpYuvGetVersion(void);
-
 // RGB to YUV conversion matrix, in 16 bit fixed point.
 // y = rgb_to_y[0] * r + rgb_to_y[1] * g + rgb_to_y[2] * b + rgb_to_y[3]
 // u = rgb_to_u[0] * r + rgb_to_u[1] * g + rgb_to_u[2] * b + rgb_to_u[3]
@@ -85,13 +65,11 @@ typedef struct {
 //     adjacent pixels on the y, u and v channels. If yuv_bit_depth > 8, they
 //     should be multiples of 2.
 // width, height: width and height of the image in pixels
-SHARPYUV_EXTERN int SharpYuvConvert(const void* r_ptr, const void* g_ptr,
-                                    const void* b_ptr, int rgb_step,
-                                    int rgb_stride, int rgb_bit_depth,
-                                    void* y_ptr, int y_stride, void* u_ptr,
-                                    int u_stride, void* v_ptr, int v_stride,
-                                    int yuv_bit_depth, int width, int height,
-                                    const SharpYuvConversionMatrix* yuv_matrix);
+int SharpYuvConvert(const void* r_ptr, const void* g_ptr, const void* b_ptr,
+                    int rgb_step, int rgb_stride, int rgb_bit_depth,
+                    void* y_ptr, int y_stride, void* u_ptr, int u_stride,
+                    void* v_ptr, int v_stride, int yuv_bit_depth, int width,
+                    int height, const SharpYuvConversionMatrix* yuv_matrix);

 // TODO(b/194336375): Add YUV444 to YUV420 conversion. Maybe also add 422
 // support (it's rarely used in practice, especially for images).
--- a/sharpyuv/sharpyuv_cpu.c
+++ b/sharpyuv/sharpyuv_cpu.c
@@ -1,14 +0,0 @@
-// Copyright 2022 Google Inc. All Rights Reserved.
-//
-// Use of this source code is governed by a BSD-style license
-// that can be found in the COPYING 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 "sharpyuv/sharpyuv_cpu.h"
-
-// Include src/dsp/cpu.c to create SharpYuvGetCPUInfo from VP8GetCPUInfo. The
-// function pointer is renamed in sharpyuv_cpu.h.
-#include "src/dsp/cpu.c"
--- a/sharpyuv/sharpyuv_cpu.h
+++ b/sharpyuv/sharpyuv_cpu.h
@@ -1,22 +0,0 @@
-// Copyright 2022 Google Inc. All Rights Reserved.
-//
-// Use of this source code is governed by a BSD-style license
-// that can be found in the COPYING 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.
-// -----------------------------------------------------------------------------
-//
-#ifndef WEBP_SHARPYUV_SHARPYUV_CPU_H_
-#define WEBP_SHARPYUV_SHARPYUV_CPU_H_
-
-#include "sharpyuv/sharpyuv.h"
-
-// Avoid exporting SharpYuvGetCPUInfo in shared object / DLL builds.
-// SharpYuvInit() replaces the use of the function pointer.
-#undef WEBP_EXTERN
-#define WEBP_EXTERN extern
-#define VP8GetCPUInfo SharpYuvGetCPUInfo
-#include "src/dsp/cpu.h"
-
-#endif  // WEBP_SHARPYUV_SHARPYUV_CPU_H_
--- a/sharpyuv/sharpyuv_csp.c
+++ b/sharpyuv/sharpyuv_csp.c
@@ -13,7 +13,7 @@

 #include <assert.h>
 #include <math.h>
-#include <stddef.h>
+#include <string.h>

 static int ToFixed16(float f) { return (int)floor(f * (1 << 16) + 0.5f); }

--- a/sharpyuv/sharpyuv_csp.h
+++ b/sharpyuv/sharpyuv_csp.h
@@ -35,9 +35,8 @@ typedef struct {
 } SharpYuvColorSpace;

 // Fills in 'matrix' for the given YUVColorSpace.
-SHARPYUV_EXTERN void SharpYuvComputeConversionMatrix(
-    const SharpYuvColorSpace* yuv_color_space,
-    SharpYuvConversionMatrix* matrix);
+void SharpYuvComputeConversionMatrix(const SharpYuvColorSpace* yuv_color_space,
+                                     SharpYuvConversionMatrix* matrix);

 // Enums for precomputed conversion matrices.
 typedef enum {
@@ -50,7 +49,7 @@ typedef enum {
 } SharpYuvMatrixType;

 // Returns a pointer to a matrix for one of the predefined colorspaces.
-SHARPYUV_EXTERN const SharpYuvConversionMatrix* SharpYuvGetConversionMatrix(
+const SharpYuvConversionMatrix* SharpYuvGetConversionMatrix(
    SharpYuvMatrixType matrix_type);

 #ifdef __cplusplus
--- a/sharpyuv/sharpyuv_dsp.c
+++ b/sharpyuv/sharpyuv_dsp.c
@@ -16,7 +16,7 @@
 #include <assert.h>
 #include <stdlib.h>

-#include "sharpyuv/sharpyuv_cpu.h"
+#include "src/dsp/cpu.h"

 //-----------------------------------------------------------------------------

@@ -72,28 +72,26 @@ void (*SharpYuvFilterRow)(const int16_t* A, const int16_t* B, int len,
                          const uint16_t* best_y, uint16_t* out,
                          int bit_depth);

-extern VP8CPUInfo SharpYuvGetCPUInfo;
 extern void InitSharpYuvSSE2(void);
 extern void InitSharpYuvNEON(void);

-void SharpYuvInitDsp(void) {
+void SharpYuvInitDsp(VP8CPUInfo cpu_info_func) {
+  (void)cpu_info_func;
+
 #if !WEBP_NEON_OMIT_C_CODE
  SharpYuvUpdateY = SharpYuvUpdateY_C;
  SharpYuvUpdateRGB = SharpYuvUpdateRGB_C;
  SharpYuvFilterRow = SharpYuvFilterRow_C;
 #endif

-  if (SharpYuvGetCPUInfo != NULL) {
 #if defined(WEBP_HAVE_SSE2)
-    if (SharpYuvGetCPUInfo(kSSE2)) {
-      InitSharpYuvSSE2();
-    }
-#endif  // WEBP_HAVE_SSE2
+  if (cpu_info_func == NULL || cpu_info_func(kSSE2)) {
+    InitSharpYuvSSE2();
  }
+#endif  // WEBP_HAVE_SSE2

 #if defined(WEBP_HAVE_NEON)
-  if (WEBP_NEON_OMIT_C_CODE ||
-      (SharpYuvGetCPUInfo != NULL && SharpYuvGetCPUInfo(kNEON))) {
+  if (WEBP_NEON_OMIT_C_CODE || cpu_info_func == NULL || cpu_info_func(kNEON)) {
    InitSharpYuvNEON();
  }
 #endif  // WEBP_HAVE_NEON
--- a/sharpyuv/sharpyuv_dsp.h
+++ b/sharpyuv/sharpyuv_dsp.h
@@ -12,8 +12,9 @@
 #ifndef WEBP_SHARPYUV_SHARPYUV_DSP_H_
 #define WEBP_SHARPYUV_SHARPYUV_DSP_H_

-#include "sharpyuv/sharpyuv_cpu.h"
-#include "src/webp/types.h"
+#include <stdint.h>
+
+#include "src/dsp/cpu.h"

 extern uint64_t (*SharpYuvUpdateY)(const uint16_t* src, const uint16_t* ref,
                                   uint16_t* dst, int len, int bit_depth);
@@ -23,6 +24,6 @@ extern void (*SharpYuvFilterRow)(const int16_t* A, const int16_t* B, int len,
                                 const uint16_t* best_y, uint16_t* out,
                                 int bit_depth);

-void SharpYuvInitDsp(void);
+void SharpYuvInitDsp(VP8CPUInfo cpu_info_func);

 #endif  // WEBP_SHARPYUV_SHARPYUV_DSP_H_
--- a/sharpyuv/sharpyuv_gamma.c
+++ b/sharpyuv/sharpyuv_gamma.c
@@ -13,6 +13,7 @@

 #include <assert.h>
 #include <math.h>
+#include <stdint.h>

 #include "src/webp/types.h"

--- a/sharpyuv/sharpyuv_gamma.h
+++ b/sharpyuv/sharpyuv_gamma.h
@@ -12,7 +12,7 @@
 #ifndef WEBP_SHARPYUV_SHARPYUV_GAMMA_H_
 #define WEBP_SHARPYUV_SHARPYUV_GAMMA_H_

-#include "src/webp/types.h"
+#include <stdint.h>

 #ifdef __cplusplus
 extern "C" {
--- a/sharpyuv/sharpyuv_neon.c
+++ b/sharpyuv/sharpyuv_neon.c
@@ -17,6 +17,11 @@
 #include <assert.h>
 #include <stdlib.h>
 #include <arm_neon.h>
+#endif
+
+extern void InitSharpYuvNEON(void);
+
+#if defined(WEBP_USE_NEON)

 static uint16_t clip_NEON(int v, int max) {
  return (v < 0) ? 0 : (v > max) ? max : (uint16_t)v;
@@ -164,8 +169,6 @@ static void SharpYuvFilterRow_NEON(const int16_t* A, const int16_t* B, int len,

 //------------------------------------------------------------------------------

-extern void InitSharpYuvNEON(void);
-
 WEBP_TSAN_IGNORE_FUNCTION void InitSharpYuvNEON(void) {
  SharpYuvUpdateY = SharpYuvUpdateY_NEON;
  SharpYuvUpdateRGB = SharpYuvUpdateRGB_NEON;
@@ -174,8 +177,6 @@ WEBP_TSAN_IGNORE_FUNCTION void InitSharpYuvNEON(void) {

 #else  // !WEBP_USE_NEON

-extern void InitSharpYuvNEON(void);
-
 void InitSharpYuvNEON(void) {}

 #endif  // WEBP_USE_NEON
--- a/sharpyuv/sharpyuv_sse2.c
+++ b/sharpyuv/sharpyuv_sse2.c
@@ -16,6 +16,11 @@
 #if defined(WEBP_USE_SSE2)
 #include <stdlib.h>
 #include <emmintrin.h>
+#endif
+
+extern void InitSharpYuvSSE2(void);
+
+#if defined(WEBP_USE_SSE2)

 static uint16_t clip_SSE2(int v, int max) {
  return (v < 0) ? 0 : (v > max) ? max : (uint16_t)v;
@@ -194,8 +199,6 @@ WEBP_TSAN_IGNORE_FUNCTION void InitSharpYuvSSE2(void) {
 }
 #else  // !WEBP_USE_SSE2

-extern void InitSharpYuvSSE2(void);
-
 void InitSharpYuvSSE2(void) {}

 #endif  // WEBP_USE_SSE2
--- a/src/Makefile.am
+++ b/src/Makefile.am
@@ -36,7 +36,7 @@ libwebp_la_LIBADD += utils/libwebputils.la
 # other than the ones listed on the command line, i.e., after linking, it will
 # not have unresolved symbols. Some platforms (Windows among them) require all
 # symbols in shared libraries to be resolved at library creation.
-libwebp_la_LDFLAGS = -no-undefined -version-info 8:8:1
+libwebp_la_LDFLAGS = -no-undefined -version-info 8:4:1
 libwebpincludedir = $(includedir)/webp
 pkgconfig_DATA = libwebp.pc

@@ -48,7 +48,7 @@ if BUILD_LIBWEBPDECODER
  libwebpdecoder_la_LIBADD += dsp/libwebpdspdecode.la
  libwebpdecoder_la_LIBADD += utils/libwebputilsdecode.la

-  libwebpdecoder_la_LDFLAGS = -no-undefined -version-info 4:8:1
+  libwebpdecoder_la_LDFLAGS = -no-undefined -version-info 4:4:1
  pkgconfig_DATA += libwebpdecoder.pc
 endif

--- a/src/dec/tree_dec.c
+++ b/src/dec/tree_dec.c
@@ -12,11 +12,10 @@
 // Author: Skal (pascal.massimino@gmail.com)

 #include "src/dec/vp8i_dec.h"
-#include "src/dsp/cpu.h"
 #include "src/utils/bit_reader_inl_utils.h"

 #if !defined(USE_GENERIC_TREE)
-#if !defined(__arm__) && !defined(_M_ARM) && !WEBP_AARCH64
+#if !defined(__arm__) && !defined(_M_ARM) && !defined(__aarch64__)
 // using a table is ~1-2% slower on ARM. Prefer the coded-tree approach then.
 #define USE_GENERIC_TREE 1   // ALTERNATE_CODE
 #else
--- a/src/dec/vp8_dec.c
+++ b/src/dec/vp8_dec.c
@@ -494,8 +494,6 @@ static int GetCoeffsAlt(VP8BitReader* const br,
  return 16;
 }

-extern VP8CPUInfo VP8GetCPUInfo;
-
 WEBP_DSP_INIT_FUNC(InitGetCoeffs) {
  if (VP8GetCPUInfo != NULL && VP8GetCPUInfo(kSlowSSSE3)) {
    GetCoeffs = GetCoeffsAlt;
--- a/src/dec/vp8i_dec.h
+++ b/src/dec/vp8i_dec.h
@@ -31,8 +31,8 @@ extern "C" {

 // version numbers
 #define DEC_MAJ_VERSION 1
-#define DEC_MIN_VERSION 3
-#define DEC_REV_VERSION 2
+#define DEC_MIN_VERSION 2
+#define DEC_REV_VERSION 3

 // YUV-cache parameters. Cache is 32-bytes wide (= one cacheline).
 // Constraints are: We need to store one 16x16 block of luma samples (y),
--- a/src/dec/vp8l_dec.c
+++ b/src/dec/vp8l_dec.c
@@ -1340,7 +1340,7 @@ static int ReadTransform(int* const xsize, int const* ysize,
       ok = ok && ExpandColorMap(num_colors, transform);
      break;
    }
-    case SUBTRACT_GREEN_TRANSFORM:
+    case SUBTRACT_GREEN:
      break;
    default:
      assert(0);    // can't happen
--- a/src/dec/webp_dec.c
+++ b/src/dec/webp_dec.c
@@ -179,7 +179,7 @@ static VP8StatusCode ParseOptionalChunks(const uint8_t** const data,
      return VP8_STATUS_BITSTREAM_ERROR;          // Not a valid chunk size.
    }
    // For odd-sized chunk-payload, there's one byte padding at the end.
-    disk_chunk_size = (CHUNK_HEADER_SIZE + chunk_size + 1) & ~1u;
+    disk_chunk_size = (CHUNK_HEADER_SIZE + chunk_size + 1) & ~1;
    total_size += disk_chunk_size;

    // Check that total bytes skipped so far does not exceed riff_size.
@@ -658,26 +658,19 @@ uint8_t* WebPDecodeBGRA(const uint8_t* data, size_t data_size,
 uint8_t* WebPDecodeYUV(const uint8_t* data, size_t data_size,
                       int* width, int* height, uint8_t** u, uint8_t** v,
                       int* stride, int* uv_stride) {
-  // data, width and height are checked by Decode().
-  if (u == NULL || v == NULL || stride == NULL || uv_stride == NULL) {
-    return NULL;
-  }
+  WebPDecBuffer output;   // only to preserve the side-infos
+  uint8_t* const out = Decode(MODE_YUV, data, data_size,
+                              width, height, &output);

-  {
-    WebPDecBuffer output;   // only to preserve the side-infos
-    uint8_t* const out = Decode(MODE_YUV, data, data_size,
-                                width, height, &output);
-
-    if (out != NULL) {
-      const WebPYUVABuffer* const buf = &output.u.YUVA;
-      *u = buf->u;
-      *v = buf->v;
-      *stride = buf->y_stride;
-      *uv_stride = buf->u_stride;
-      assert(buf->u_stride == buf->v_stride);
-    }
-    return out;
+  if (out != NULL) {
+    const WebPYUVABuffer* const buf = &output.u.YUVA;
+    *u = buf->u;
+    *v = buf->v;
+    *stride = buf->y_stride;
+    *uv_stride = buf->u_stride;
+    assert(buf->u_stride == buf->v_stride);
  }
+  return out;
 }

 static void DefaultFeatures(WebPBitstreamFeatures* const features) {
--- a/src/demux/Makefile.am
+++ b/src/demux/Makefile.am
@@ -13,6 +13,6 @@ noinst_HEADERS =
 noinst_HEADERS += ../webp/format_constants.h

 libwebpdemux_la_LIBADD = ../libwebp.la
-libwebpdemux_la_LDFLAGS = -no-undefined -version-info 2:14:0
+libwebpdemux_la_LDFLAGS = -no-undefined -version-info 2:10:0
 libwebpdemuxincludedir = $(includedir)/webp
 pkgconfig_DATA = libwebpdemux.pc
--- a/src/demux/demux.c
+++ b/src/demux/demux.c
@@ -24,8 +24,8 @@
 #include "src/webp/format_constants.h"

 #define DMUX_MAJ_VERSION 1
-#define DMUX_MIN_VERSION 3
-#define DMUX_REV_VERSION 2
+#define DMUX_MIN_VERSION 2
+#define DMUX_REV_VERSION 3

 typedef struct {
  size_t start_;        // start location of the data
--- a/src/demux/libwebpdemux.pc.in
+++ b/src/demux/libwebpdemux.pc.in
@@ -6,6 +6,6 @@ includedir=@includedir@
 Name: libwebpdemux
 Description: Library for parsing the WebP graphics format container
 Version: @PACKAGE_VERSION@
-Requires.private: libwebp >= 0.2.0
+Requires: libwebp >= 0.2.0
 Cflags: -I${includedir}
-Libs: -L${libdir} -l@webp_libname_prefix@webpdemux
+Libs: -L${libdir} -lwebpdemux
--- a/src/demux/libwebpdemux.rc
+++ b/src/demux/libwebpdemux.rc
@@ -6,8 +6,8 @@
 LANGUAGE LANG_ENGLISH, SUBLANG_ENGLISH_US

 VS_VERSION_INFO VERSIONINFO
- FILEVERSION 1,0,3,2
- PRODUCTVERSION 1,0,3,2
+ FILEVERSION 1,0,2,3
+ PRODUCTVERSION 1,0,2,3
 FILEFLAGSMASK 0x3fL
 #ifdef _DEBUG
 FILEFLAGS 0x1L
@@ -24,12 +24,12 @@ BEGIN
        BEGIN
            VALUE "CompanyName", "Google, Inc."
            VALUE "FileDescription", "libwebpdemux DLL"
-            VALUE "FileVersion", "1.3.2"
+            VALUE "FileVersion", "1.2.3"
            VALUE "InternalName", "libwebpdemux.dll"
-            VALUE "LegalCopyright", "Copyright (C) 2023"
+            VALUE "LegalCopyright", "Copyright (C) 2022"
            VALUE "OriginalFilename", "libwebpdemux.dll"
            VALUE "ProductName", "WebP Image Demuxer"
-            VALUE "ProductVersion", "1.3.2"
+            VALUE "ProductVersion", "1.2.3"
        END
    END
    BLOCK "VarFileInfo"
--- a/src/dsp/alpha_processing.c
+++ b/src/dsp/alpha_processing.c
@@ -425,7 +425,6 @@ void (*WebPAlphaReplace)(uint32_t* src, int length, uint32_t color);
 //------------------------------------------------------------------------------
 // Init function

-extern VP8CPUInfo VP8GetCPUInfo;
 extern void WebPInitAlphaProcessingMIPSdspR2(void);
 extern void WebPInitAlphaProcessingSSE2(void);
 extern void WebPInitAlphaProcessingSSE41(void);
--- a/src/dsp/alpha_processing_sse2.c
+++ b/src/dsp/alpha_processing_sse2.c
@@ -26,8 +26,8 @@ static int DispatchAlpha_SSE2(const uint8_t* WEBP_RESTRICT alpha,
  uint32_t alpha_and = 0xff;
  int i, j;
  const __m128i zero = _mm_setzero_si128();
-  const __m128i rgb_mask = _mm_set1_epi32((int)0xffffff00);  // to preserve RGB
-  const __m128i all_0xff = _mm_set_epi32(0, 0, ~0, ~0);
+  const __m128i rgb_mask = _mm_set1_epi32(0xffffff00u);  // to preserve RGB
+  const __m128i all_0xff = _mm_set_epi32(0, 0, ~0u, ~0u);
  __m128i all_alphas = all_0xff;

  // We must be able to access 3 extra bytes after the last written byte
@@ -106,8 +106,8 @@ static int ExtractAlpha_SSE2(const uint8_t* WEBP_RESTRICT argb, int argb_stride,
  // value is not 0xff if any of the alpha[] is not equal to 0xff.
  uint32_t alpha_and = 0xff;
  int i, j;
-  const __m128i a_mask = _mm_set1_epi32(0xff);  // to preserve alpha
-  const __m128i all_0xff = _mm_set_epi32(0, 0, ~0, ~0);
+  const __m128i a_mask = _mm_set1_epi32(0xffu);  // to preserve alpha
+  const __m128i all_0xff = _mm_set_epi32(0, 0, ~0u, ~0u);
  __m128i all_alphas = all_0xff;

  // We must be able to access 3 extra bytes after the last written byte
@@ -178,7 +178,7 @@ static int ExtractAlpha_SSE2(const uint8_t* WEBP_RESTRICT argb, int argb_stride,
 static void ApplyAlphaMultiply_SSE2(uint8_t* rgba, int alpha_first,
                                    int w, int h, int stride) {
  const __m128i zero = _mm_setzero_si128();
-  const __m128i kMult = _mm_set1_epi16((short)0x8081);
+  const __m128i kMult = _mm_set1_epi16(0x8081u);
  const __m128i kMask = _mm_set_epi16(0, 0xff, 0xff, 0, 0, 0xff, 0xff, 0);
  const int kSpan = 4;
  while (h-- > 0) {
@@ -267,7 +267,7 @@ static int HasAlpha32b_SSE2(const uint8_t* src, int length) {
 }

 static void AlphaReplace_SSE2(uint32_t* src, int length, uint32_t color) {
-  const __m128i m_color = _mm_set1_epi32((int)color);
+  const __m128i m_color = _mm_set1_epi32(color);
  const __m128i zero = _mm_setzero_si128();
  int i = 0;
  for (; i + 8 <= length; i += 8) {
--- a/src/dsp/alpha_processing_sse41.c
+++ b/src/dsp/alpha_processing_sse41.c
@@ -26,7 +26,7 @@ static int ExtractAlpha_SSE41(const uint8_t* WEBP_RESTRICT argb,
  // value is not 0xff if any of the alpha[] is not equal to 0xff.
  uint32_t alpha_and = 0xff;
  int i, j;
-  const __m128i all_0xff = _mm_set1_epi32(~0);
+  const __m128i all_0xff = _mm_set1_epi32(~0u);
  __m128i all_alphas = all_0xff;

  // We must be able to access 3 extra bytes after the last written byte
--- a/src/dsp/cost.c
+++ b/src/dsp/cost.c
@@ -374,7 +374,6 @@ static void SetResidualCoeffs_C(const int16_t* const coeffs,
 VP8GetResidualCostFunc VP8GetResidualCost;
 VP8SetResidualCoeffsFunc VP8SetResidualCoeffs;

-extern VP8CPUInfo VP8GetCPUInfo;
 extern void VP8EncDspCostInitMIPS32(void);
 extern void VP8EncDspCostInitMIPSdspR2(void);
 extern void VP8EncDspCostInitSSE2(void);
--- a/src/dsp/cost_neon.c
+++ b/src/dsp/cost_neon.c
@@ -29,7 +29,7 @@ static void SetResidualCoeffs_NEON(const int16_t* const coeffs,
  const uint8x16_t eob = vcombine_u8(vqmovn_u16(eob_0), vqmovn_u16(eob_1));
  const uint8x16_t masked = vandq_u8(eob, vld1q_u8(position));

-#if WEBP_AARCH64
+#ifdef __aarch64__
  res->last = vmaxvq_u8(masked) - 1;
 #else
  const uint8x8_t eob_8x8 = vmax_u8(vget_low_u8(masked), vget_high_u8(masked));
@@ -43,7 +43,7 @@ static void SetResidualCoeffs_NEON(const int16_t* const coeffs,

  vst1_lane_s32(&res->last, vreinterpret_s32_u32(eob_32x2), 0);
  --res->last;
-#endif  // WEBP_AARCH64
+#endif  // __aarch64__

  res->coeffs = coeffs;
 }
--- a/src/dsp/cpu.c
+++ b/src/dsp/cpu.c
@@ -173,7 +173,6 @@ static int x86CPUInfo(CPUFeature feature) {
  }
  return 0;
 }
-WEBP_EXTERN VP8CPUInfo VP8GetCPUInfo;
 VP8CPUInfo VP8GetCPUInfo = x86CPUInfo;
 #elif defined(WEBP_ANDROID_NEON)  // NB: needs to be before generic NEON test.
 static int AndroidCPUInfo(CPUFeature feature) {
@@ -185,7 +184,6 @@ static int AndroidCPUInfo(CPUFeature feature) {
  }
  return 0;
 }
-WEBP_EXTERN VP8CPUInfo VP8GetCPUInfo;
 VP8CPUInfo VP8GetCPUInfo = AndroidCPUInfo;
 #elif defined(EMSCRIPTEN) // also needs to be before generic NEON test
 // Use compile flags as an indicator of SIMD support instead of a runtime check.
@@ -210,12 +208,11 @@ static int wasmCPUInfo(CPUFeature feature) {
  }
  return 0;
 }
-WEBP_EXTERN VP8CPUInfo VP8GetCPUInfo;
 VP8CPUInfo VP8GetCPUInfo = wasmCPUInfo;
 #elif defined(WEBP_HAVE_NEON)
 // In most cases this function doesn't check for NEON support (it's assumed by
 // the configuration), but enables turning off NEON at runtime, for testing
-// purposes, by setting VP8GetCPUInfo = NULL.
+// purposes, by setting VP8DecGetCPUInfo = NULL.
 static int armCPUInfo(CPUFeature feature) {
  if (feature != kNEON) return 0;
 #if defined(__linux__) && defined(WEBP_HAVE_NEON_RTCD)
@@ -239,7 +236,6 @@ static int armCPUInfo(CPUFeature feature) {
  return 1;
 #endif
 }
-WEBP_EXTERN VP8CPUInfo VP8GetCPUInfo;
 VP8CPUInfo VP8GetCPUInfo = armCPUInfo;
 #elif defined(WEBP_USE_MIPS32) || defined(WEBP_USE_MIPS_DSP_R2) || \
      defined(WEBP_USE_MSA)
@@ -251,9 +247,7 @@ static int mipsCPUInfo(CPUFeature feature) {
  }

 }
-WEBP_EXTERN VP8CPUInfo VP8GetCPUInfo;
 VP8CPUInfo VP8GetCPUInfo = mipsCPUInfo;
 #else
-WEBP_EXTERN VP8CPUInfo VP8GetCPUInfo;
 VP8CPUInfo VP8GetCPUInfo = NULL;
 #endif
--- a/src/dsp/cpu.h
+++ b/src/dsp/cpu.h
@@ -14,8 +14,6 @@
 #ifndef WEBP_DSP_CPU_H_
 #define WEBP_DSP_CPU_H_

-#include <stddef.h>
-
 #ifdef HAVE_CONFIG_H
 #include "src/webp/config.h"
 #endif
@@ -43,9 +41,6 @@
 #define __has_builtin(x) 0
 #endif

-//------------------------------------------------------------------------------
-// x86 defines.
-
 #if !defined(HAVE_CONFIG_H)
 #if defined(_MSC_VER) && _MSC_VER > 1310 && \
    (defined(_M_X64) || defined(_M_IX86))
@@ -83,9 +78,6 @@
 #undef WEBP_MSC_SSE41
 #undef WEBP_MSC_SSE2

-//------------------------------------------------------------------------------
-// Arm defines.
-
 // The intrinsics currently cause compiler errors with arm-nacl-gcc and the
 // inline assembly would need to be modified for use with Native Client.
 #if ((defined(__ARM_NEON__) || defined(__aarch64__)) &&       \
@@ -104,26 +96,16 @@
 // inclusion of arm64_neon.h; Visual Studio 2019 includes this file in
 // arm_neon.h. Compile errors were seen with Visual Studio 2019 16.4 with
 // vtbl4_u8(); a fix was made in 16.6.
-#if defined(_MSC_VER) && \
-    ((_MSC_VER >= 1700 && defined(_M_ARM)) || \
-     (_MSC_VER >= 1926 && (defined(_M_ARM64) || defined(_M_ARM64EC))))
+#if defined(_MSC_VER) && ((_MSC_VER >= 1700 && defined(_M_ARM)) || \
+                          (_MSC_VER >= 1926 && defined(_M_ARM64)))
 #define WEBP_USE_NEON
 #define WEBP_USE_INTRINSICS
 #endif

-#if defined(__aarch64__) || defined(_M_ARM64) || defined(_M_ARM64EC)
-#define WEBP_AARCH64 1
-#else
-#define WEBP_AARCH64 0
-#endif
-
 #if defined(WEBP_USE_NEON) && !defined(WEBP_HAVE_NEON)
 #define WEBP_HAVE_NEON
 #endif

-//------------------------------------------------------------------------------
-// MIPS defines.
-
 #if defined(__mips__) && !defined(__mips64) && defined(__mips_isa_rev) && \
    (__mips_isa_rev >= 1) && (__mips_isa_rev < 6)
 #define WEBP_USE_MIPS32
@@ -139,8 +121,6 @@
 #define WEBP_USE_MSA
 #endif

-//------------------------------------------------------------------------------
-
 #ifndef WEBP_DSP_OMIT_C_CODE
 #define WEBP_DSP_OMIT_C_CODE 1
 #endif
@@ -151,14 +131,13 @@
 #define WEBP_NEON_OMIT_C_CODE 0
 #endif

-#if !(LOCAL_CLANG_PREREQ(3, 8) || LOCAL_GCC_PREREQ(4, 8) || WEBP_AARCH64)
+#if !(LOCAL_CLANG_PREREQ(3, 8) || LOCAL_GCC_PREREQ(4, 8) || \
+      defined(__aarch64__))
 #define WEBP_NEON_WORK_AROUND_GCC 1
 #else
 #define WEBP_NEON_WORK_AROUND_GCC 0
 #endif

-//------------------------------------------------------------------------------
-
 // This macro prevents thread_sanitizer from reporting known concurrent writes.
 #define WEBP_TSAN_IGNORE_FUNCTION
 #if defined(__has_feature)
@@ -260,7 +239,16 @@ typedef enum {
  kMSA
 } CPUFeature;

+#ifdef __cplusplus
+extern "C" {
+#endif
+
 // returns true if the CPU supports the feature.
 typedef int (*VP8CPUInfo)(CPUFeature feature);
+WEBP_EXTERN VP8CPUInfo VP8GetCPUInfo;
+
+#ifdef __cplusplus
+}    // extern "C"
+#endif

 #endif  // WEBP_DSP_CPU_H_
--- a/src/dsp/dec.c
+++ b/src/dsp/dec.c
@@ -734,7 +734,6 @@ VP8SimpleFilterFunc VP8SimpleHFilter16i;
 void (*VP8DitherCombine8x8)(const uint8_t* dither, uint8_t* dst,
                            int dst_stride);

-extern VP8CPUInfo VP8GetCPUInfo;
 extern void VP8DspInitSSE2(void);
 extern void VP8DspInitSSE41(void);
 extern void VP8DspInitNEON(void);
--- a/src/dsp/dec_neon.c
+++ b/src/dsp/dec_neon.c
@@ -1428,7 +1428,7 @@ static WEBP_INLINE void DC8_NEON(uint8_t* dst, int do_top, int do_left) {

  if (do_top) {
    const uint8x8_t A = vld1_u8(dst - BPS);  // top row
-#if WEBP_AARCH64
+#if defined(__aarch64__)
    const uint16_t p2 = vaddlv_u8(A);
    sum_top = vdupq_n_u16(p2);
 #else
@@ -1511,7 +1511,7 @@ static WEBP_INLINE void DC16_NEON(uint8_t* dst, int do_top, int do_left) {

  if (do_top) {
    const uint8x16_t A = vld1q_u8(dst - BPS);  // top row
-#if WEBP_AARCH64
+#if defined(__aarch64__)
    const uint16_t p3 = vaddlvq_u8(A);
    sum_top = vdupq_n_u16(p3);
 #else
--- a/src/dsp/dec_sse2.c
+++ b/src/dsp/dec_sse2.c
@@ -158,10 +158,10 @@ static void Transform_SSE2(const int16_t* in, uint8_t* dst, int do_two) {
      dst3 = _mm_loadl_epi64((__m128i*)(dst + 3 * BPS));
    } else {
      // Load four bytes/pixels per line.
-      dst0 = _mm_cvtsi32_si128(WebPMemToInt32(dst + 0 * BPS));
-      dst1 = _mm_cvtsi32_si128(WebPMemToInt32(dst + 1 * BPS));
-      dst2 = _mm_cvtsi32_si128(WebPMemToInt32(dst + 2 * BPS));
-      dst3 = _mm_cvtsi32_si128(WebPMemToInt32(dst + 3 * BPS));
+      dst0 = _mm_cvtsi32_si128(WebPMemToUint32(dst + 0 * BPS));
+      dst1 = _mm_cvtsi32_si128(WebPMemToUint32(dst + 1 * BPS));
+      dst2 = _mm_cvtsi32_si128(WebPMemToUint32(dst + 2 * BPS));
+      dst3 = _mm_cvtsi32_si128(WebPMemToUint32(dst + 3 * BPS));
    }
    // Convert to 16b.
    dst0 = _mm_unpacklo_epi8(dst0, zero);
@@ -187,10 +187,10 @@ static void Transform_SSE2(const int16_t* in, uint8_t* dst, int do_two) {
      _mm_storel_epi64((__m128i*)(dst + 3 * BPS), dst3);
    } else {
      // Store four bytes/pixels per line.
-      WebPInt32ToMem(dst + 0 * BPS, _mm_cvtsi128_si32(dst0));
-      WebPInt32ToMem(dst + 1 * BPS, _mm_cvtsi128_si32(dst1));
-      WebPInt32ToMem(dst + 2 * BPS, _mm_cvtsi128_si32(dst2));
-      WebPInt32ToMem(dst + 3 * BPS, _mm_cvtsi128_si32(dst3));
+      WebPUint32ToMem(dst + 0 * BPS, _mm_cvtsi128_si32(dst0));
+      WebPUint32ToMem(dst + 1 * BPS, _mm_cvtsi128_si32(dst1));
+      WebPUint32ToMem(dst + 2 * BPS, _mm_cvtsi128_si32(dst2));
+      WebPUint32ToMem(dst + 3 * BPS, _mm_cvtsi128_si32(dst3));
    }
  }
 }
@@ -213,10 +213,10 @@ static void TransformAC3(const int16_t* in, uint8_t* dst) {
  const __m128i m3 = _mm_subs_epi16(B, d4);
  const __m128i zero = _mm_setzero_si128();
  // Load the source pixels.
-  __m128i dst0 = _mm_cvtsi32_si128(WebPMemToInt32(dst + 0 * BPS));
-  __m128i dst1 = _mm_cvtsi32_si128(WebPMemToInt32(dst + 1 * BPS));
-  __m128i dst2 = _mm_cvtsi32_si128(WebPMemToInt32(dst + 2 * BPS));
-  __m128i dst3 = _mm_cvtsi32_si128(WebPMemToInt32(dst + 3 * BPS));
+  __m128i dst0 = _mm_cvtsi32_si128(WebPMemToUint32(dst + 0 * BPS));
+  __m128i dst1 = _mm_cvtsi32_si128(WebPMemToUint32(dst + 1 * BPS));
+  __m128i dst2 = _mm_cvtsi32_si128(WebPMemToUint32(dst + 2 * BPS));
+  __m128i dst3 = _mm_cvtsi32_si128(WebPMemToUint32(dst + 3 * BPS));
  // Convert to 16b.
  dst0 = _mm_unpacklo_epi8(dst0, zero);
  dst1 = _mm_unpacklo_epi8(dst1, zero);
@@ -233,10 +233,10 @@ static void TransformAC3(const int16_t* in, uint8_t* dst) {
  dst2 = _mm_packus_epi16(dst2, dst2);
  dst3 = _mm_packus_epi16(dst3, dst3);
  // Store the results.
-  WebPInt32ToMem(dst + 0 * BPS, _mm_cvtsi128_si32(dst0));
-  WebPInt32ToMem(dst + 1 * BPS, _mm_cvtsi128_si32(dst1));
-  WebPInt32ToMem(dst + 2 * BPS, _mm_cvtsi128_si32(dst2));
-  WebPInt32ToMem(dst + 3 * BPS, _mm_cvtsi128_si32(dst3));
+  WebPUint32ToMem(dst + 0 * BPS, _mm_cvtsi128_si32(dst0));
+  WebPUint32ToMem(dst + 1 * BPS, _mm_cvtsi128_si32(dst1));
+  WebPUint32ToMem(dst + 2 * BPS, _mm_cvtsi128_si32(dst2));
+  WebPUint32ToMem(dst + 3 * BPS, _mm_cvtsi128_si32(dst3));
 }
 #undef MUL
 #endif   // USE_TRANSFORM_AC3
@@ -477,11 +477,11 @@ static WEBP_INLINE void Load8x4_SSE2(const uint8_t* const b, int stride,
  // A0 = 63 62 61 60 23 22 21 20 43 42 41 40 03 02 01 00
  // A1 = 73 72 71 70 33 32 31 30 53 52 51 50 13 12 11 10
  const __m128i A0 = _mm_set_epi32(
-      WebPMemToInt32(&b[6 * stride]), WebPMemToInt32(&b[2 * stride]),
-      WebPMemToInt32(&b[4 * stride]), WebPMemToInt32(&b[0 * stride]));
+      WebPMemToUint32(&b[6 * stride]), WebPMemToUint32(&b[2 * stride]),
+      WebPMemToUint32(&b[4 * stride]), WebPMemToUint32(&b[0 * stride]));
  const __m128i A1 = _mm_set_epi32(
-      WebPMemToInt32(&b[7 * stride]), WebPMemToInt32(&b[3 * stride]),
-      WebPMemToInt32(&b[5 * stride]), WebPMemToInt32(&b[1 * stride]));
+      WebPMemToUint32(&b[7 * stride]), WebPMemToUint32(&b[3 * stride]),
+      WebPMemToUint32(&b[5 * stride]), WebPMemToUint32(&b[1 * stride]));

  // B0 = 53 43 52 42 51 41 50 40 13 03 12 02 11 01 10 00
  // B1 = 73 63 72 62 71 61 70 60 33 23 32 22 31 21 30 20
@@ -540,7 +540,7 @@ static WEBP_INLINE void Store4x4_SSE2(__m128i* const x,
                                      uint8_t* dst, int stride) {
  int i;
  for (i = 0; i < 4; ++i, dst += stride) {
-    WebPInt32ToMem(dst, _mm_cvtsi128_si32(*x));
+    WebPUint32ToMem(dst, _mm_cvtsi128_si32(*x));
    *x = _mm_srli_si128(*x, 4);
  }
 }
@@ -908,10 +908,10 @@ static void VE4_SSE2(uint8_t* dst) {    // vertical
  const __m128i lsb = _mm_and_si128(_mm_xor_si128(ABCDEFGH, CDEFGH00), one);
  const __m128i b = _mm_subs_epu8(a, lsb);
  const __m128i avg = _mm_avg_epu8(b, BCDEFGH0);
-  const int vals = _mm_cvtsi128_si32(avg);
+  const uint32_t vals = _mm_cvtsi128_si32(avg);
  int i;
  for (i = 0; i < 4; ++i) {
-    WebPInt32ToMem(dst + i * BPS, vals);
+    WebPUint32ToMem(dst + i * BPS, vals);
  }
 }

@@ -925,10 +925,10 @@ static void LD4_SSE2(uint8_t* dst) {   // Down-Left
  const __m128i lsb = _mm_and_si128(_mm_xor_si128(ABCDEFGH, CDEFGHH0), one);
  const __m128i avg2 = _mm_subs_epu8(avg1, lsb);
  const __m128i abcdefg = _mm_avg_epu8(avg2, BCDEFGH0);
-  WebPInt32ToMem(dst + 0 * BPS, _mm_cvtsi128_si32(               abcdefg    ));
-  WebPInt32ToMem(dst + 1 * BPS, _mm_cvtsi128_si32(_mm_srli_si128(abcdefg, 1)));
-  WebPInt32ToMem(dst + 2 * BPS, _mm_cvtsi128_si32(_mm_srli_si128(abcdefg, 2)));
-  WebPInt32ToMem(dst + 3 * BPS, _mm_cvtsi128_si32(_mm_srli_si128(abcdefg, 3)));
+  WebPUint32ToMem(dst + 0 * BPS, _mm_cvtsi128_si32(               abcdefg    ));
+  WebPUint32ToMem(dst + 1 * BPS, _mm_cvtsi128_si32(_mm_srli_si128(abcdefg, 1)));
+  WebPUint32ToMem(dst + 2 * BPS, _mm_cvtsi128_si32(_mm_srli_si128(abcdefg, 2)));
+  WebPUint32ToMem(dst + 3 * BPS, _mm_cvtsi128_si32(_mm_srli_si128(abcdefg, 3)));
 }

 static void VR4_SSE2(uint8_t* dst) {   // Vertical-Right
@@ -946,10 +946,10 @@ static void VR4_SSE2(uint8_t* dst) {   // Vertical-Right
  const __m128i lsb = _mm_and_si128(_mm_xor_si128(IXABCD, ABCD0), one);
  const __m128i avg2 = _mm_subs_epu8(avg1, lsb);
  const __m128i efgh = _mm_avg_epu8(avg2, XABCD);
-  WebPInt32ToMem(dst + 0 * BPS, _mm_cvtsi128_si32(               abcd    ));
-  WebPInt32ToMem(dst + 1 * BPS, _mm_cvtsi128_si32(               efgh    ));
-  WebPInt32ToMem(dst + 2 * BPS, _mm_cvtsi128_si32(_mm_slli_si128(abcd, 1)));
-  WebPInt32ToMem(dst + 3 * BPS, _mm_cvtsi128_si32(_mm_slli_si128(efgh, 1)));
+  WebPUint32ToMem(dst + 0 * BPS, _mm_cvtsi128_si32(               abcd    ));
+  WebPUint32ToMem(dst + 1 * BPS, _mm_cvtsi128_si32(               efgh    ));
+  WebPUint32ToMem(dst + 2 * BPS, _mm_cvtsi128_si32(_mm_slli_si128(abcd, 1)));
+  WebPUint32ToMem(dst + 3 * BPS, _mm_cvtsi128_si32(_mm_slli_si128(efgh, 1)));

  // these two are hard to implement in SSE2, so we keep the C-version:
  DST(0, 2) = AVG3(J, I, X);
@@ -970,12 +970,11 @@ static void VL4_SSE2(uint8_t* dst) {   // Vertical-Left
  const __m128i abbc = _mm_or_si128(ab, bc);
  const __m128i lsb2 = _mm_and_si128(abbc, lsb1);
  const __m128i avg4 = _mm_subs_epu8(avg3, lsb2);
-  const uint32_t extra_out =
-      (uint32_t)_mm_cvtsi128_si32(_mm_srli_si128(avg4, 4));
-  WebPInt32ToMem(dst + 0 * BPS, _mm_cvtsi128_si32(               avg1    ));
-  WebPInt32ToMem(dst + 1 * BPS, _mm_cvtsi128_si32(               avg4    ));
-  WebPInt32ToMem(dst + 2 * BPS, _mm_cvtsi128_si32(_mm_srli_si128(avg1, 1)));
-  WebPInt32ToMem(dst + 3 * BPS, _mm_cvtsi128_si32(_mm_srli_si128(avg4, 1)));
+  const uint32_t extra_out = _mm_cvtsi128_si32(_mm_srli_si128(avg4, 4));
+  WebPUint32ToMem(dst + 0 * BPS, _mm_cvtsi128_si32(               avg1    ));
+  WebPUint32ToMem(dst + 1 * BPS, _mm_cvtsi128_si32(               avg4    ));
+  WebPUint32ToMem(dst + 2 * BPS, _mm_cvtsi128_si32(_mm_srli_si128(avg1, 1)));
+  WebPUint32ToMem(dst + 3 * BPS, _mm_cvtsi128_si32(_mm_srli_si128(avg4, 1)));

  // these two are hard to get and irregular
  DST(3, 2) = (extra_out >> 0) & 0xff;
@@ -991,7 +990,7 @@ static void RD4_SSE2(uint8_t* dst) {   // Down-right
  const uint32_t K = dst[-1 + 2 * BPS];
  const uint32_t L = dst[-1 + 3 * BPS];
  const __m128i LKJI_____ =
-      _mm_cvtsi32_si128((int)(L | (K << 8) | (J << 16) | (I << 24)));
+      _mm_cvtsi32_si128(L | (K << 8) | (J << 16) | (I << 24));
  const __m128i LKJIXABCD = _mm_or_si128(LKJI_____, ____XABCD);
  const __m128i KJIXABCD_ = _mm_srli_si128(LKJIXABCD, 1);
  const __m128i JIXABCD__ = _mm_srli_si128(LKJIXABCD, 2);
@@ -999,10 +998,10 @@ static void RD4_SSE2(uint8_t* dst) {   // Down-right
  const __m128i lsb = _mm_and_si128(_mm_xor_si128(JIXABCD__, LKJIXABCD), one);
  const __m128i avg2 = _mm_subs_epu8(avg1, lsb);
  const __m128i abcdefg = _mm_avg_epu8(avg2, KJIXABCD_);
-  WebPInt32ToMem(dst + 3 * BPS, _mm_cvtsi128_si32(               abcdefg    ));
-  WebPInt32ToMem(dst + 2 * BPS, _mm_cvtsi128_si32(_mm_srli_si128(abcdefg, 1)));
-  WebPInt32ToMem(dst + 1 * BPS, _mm_cvtsi128_si32(_mm_srli_si128(abcdefg, 2)));
-  WebPInt32ToMem(dst + 0 * BPS, _mm_cvtsi128_si32(_mm_srli_si128(abcdefg, 3)));
+  WebPUint32ToMem(dst + 3 * BPS, _mm_cvtsi128_si32(               abcdefg    ));
+  WebPUint32ToMem(dst + 2 * BPS, _mm_cvtsi128_si32(_mm_srli_si128(abcdefg, 1)));
+  WebPUint32ToMem(dst + 1 * BPS, _mm_cvtsi128_si32(_mm_srli_si128(abcdefg, 2)));
+  WebPUint32ToMem(dst + 0 * BPS, _mm_cvtsi128_si32(_mm_srli_si128(abcdefg, 3)));
 }

 #undef DST
@@ -1016,13 +1015,13 @@ static WEBP_INLINE void TrueMotion_SSE2(uint8_t* dst, int size) {
  const __m128i zero = _mm_setzero_si128();
  int y;
  if (size == 4) {
-    const __m128i top_values = _mm_cvtsi32_si128(WebPMemToInt32(top));
+    const __m128i top_values = _mm_cvtsi32_si128(WebPMemToUint32(top));
    const __m128i top_base = _mm_unpacklo_epi8(top_values, zero);
    for (y = 0; y < 4; ++y, dst += BPS) {
      const int val = dst[-1] - top[-1];
      const __m128i base = _mm_set1_epi16(val);
      const __m128i out = _mm_packus_epi16(_mm_add_epi16(base, top_base), zero);
-      WebPInt32ToMem(dst, _mm_cvtsi128_si32(out));
+      WebPUint32ToMem(dst, _mm_cvtsi128_si32(out));
    }
  } else if (size == 8) {
    const __m128i top_values = _mm_loadl_epi64((const __m128i*)top);
@@ -1063,7 +1062,7 @@ static void VE16_SSE2(uint8_t* dst) {
 static void HE16_SSE2(uint8_t* dst) {     // horizontal
  int j;
  for (j = 16; j > 0; --j) {
-    const __m128i values = _mm_set1_epi8((char)dst[-1]);
+    const __m128i values = _mm_set1_epi8(dst[-1]);
    _mm_storeu_si128((__m128i*)dst, values);
    dst += BPS;
  }
@@ -1071,7 +1070,7 @@ static void HE16_SSE2(uint8_t* dst) {     // horizontal

 static WEBP_INLINE void Put16_SSE2(uint8_t v, uint8_t* dst) {
  int j;
-  const __m128i values = _mm_set1_epi8((char)v);
+  const __m128i values = _mm_set1_epi8(v);
  for (j = 0; j < 16; ++j) {
    _mm_storeu_si128((__m128i*)(dst + j * BPS), values);
  }
@@ -1131,7 +1130,7 @@ static void VE8uv_SSE2(uint8_t* dst) {    // vertical
 // helper for chroma-DC predictions
 static WEBP_INLINE void Put8x8uv_SSE2(uint8_t v, uint8_t* dst) {
  int j;
-  const __m128i values = _mm_set1_epi8((char)v);
+  const __m128i values = _mm_set1_epi8(v);
  for (j = 0; j < 8; ++j) {
    _mm_storel_epi64((__m128i*)(dst + j * BPS), values);
  }
--- a/src/dsp/dec_sse41.c
+++ b/src/dsp/dec_sse41.c
@@ -23,7 +23,7 @@ static void HE16_SSE41(uint8_t* dst) {     // horizontal
  int j;
  const __m128i kShuffle3 = _mm_set1_epi8(3);
  for (j = 16; j > 0; --j) {
-    const __m128i in = _mm_cvtsi32_si128(WebPMemToInt32(dst - 4));
+    const __m128i in = _mm_cvtsi32_si128(WebPMemToUint32(dst - 4));
    const __m128i values = _mm_shuffle_epi8(in, kShuffle3);
    _mm_storeu_si128((__m128i*)dst, values);
    dst += BPS;
--- a/src/dsp/enc.c
+++ b/src/dsp/enc.c
@@ -732,7 +732,6 @@ VP8QuantizeBlockWHT VP8EncQuantizeBlockWHT;
 VP8BlockCopy VP8Copy4x4;
 VP8BlockCopy VP8Copy16x8;

-extern VP8CPUInfo VP8GetCPUInfo;
 extern void VP8EncDspInitSSE2(void);
 extern void VP8EncDspInitSSE41(void);
 extern void VP8EncDspInitNEON(void);
--- a/src/dsp/enc_neon.c
+++ b/src/dsp/enc_neon.c
@@ -764,14 +764,9 @@ static WEBP_INLINE void AccumulateSSE16_NEON(const uint8_t* const a,

 // Horizontal sum of all four uint32_t values in 'sum'.
 static int SumToInt_NEON(uint32x4_t sum) {
-#if WEBP_AARCH64
-  return (int)vaddvq_u32(sum);
-#else
  const uint64x2_t sum2 = vpaddlq_u32(sum);
-  const uint32x2_t sum3 = vadd_u32(vreinterpret_u32_u64(vget_low_u64(sum2)),
-                                   vreinterpret_u32_u64(vget_high_u64(sum2)));
-  return (int)vget_lane_u32(sum3, 0);
-#endif
+  const uint64_t sum3 = vgetq_lane_u64(sum2, 0) + vgetq_lane_u64(sum2, 1);
+  return (int)sum3;
 }

 static int SSE16x16_NEON(const uint8_t* a, const uint8_t* b) {
@@ -865,7 +860,7 @@ static int QuantizeBlock_NEON(int16_t in[16], int16_t out[16],
  uint8x8x4_t shuffles;
  // vtbl?_u8 are marked unavailable for iOS arm64 with Xcode < 6.3, use
  // non-standard versions there.
-#if defined(__APPLE__) && WEBP_AARCH64 && \
+#if defined(__APPLE__) && defined(__aarch64__) && \
    defined(__apple_build_version__) && (__apple_build_version__< 6020037)
  uint8x16x2_t all_out;
  INIT_VECTOR2(all_out, vreinterpretq_u8_s16(out0), vreinterpretq_u8_s16(out1));
--- a/src/dsp/enc_sse2.c
+++ b/src/dsp/enc_sse2.c
@@ -25,160 +25,9 @@
 //------------------------------------------------------------------------------
 // Transforms (Paragraph 14.4)

-// Does one inverse transform.
-static void ITransform_One_SSE2(const uint8_t* ref, const int16_t* in,
-                                uint8_t* dst) {
-  // This implementation makes use of 16-bit fixed point versions of two
-  // multiply constants:
-  //    K1 = sqrt(2) * cos (pi/8) ~= 85627 / 2^16
-  //    K2 = sqrt(2) * sin (pi/8) ~= 35468 / 2^16
-  //
-  // To be able to use signed 16-bit integers, we use the following trick to
-  // have constants within range:
-  // - Associated constants are obtained by subtracting the 16-bit fixed point
-  //   version of one:
-  //      k = K - (1 << 16)  =>  K = k + (1 << 16)
-  //      K1 = 85267  =>  k1 =  20091
-  //      K2 = 35468  =>  k2 = -30068
-  // - The multiplication of a variable by a constant become the sum of the
-  //   variable and the multiplication of that variable by the associated
-  //   constant:
-  //      (x * K) >> 16 = (x * (k + (1 << 16))) >> 16 = ((x * k ) >> 16) + x
-  const __m128i k1k2 = _mm_set_epi16(-30068, -30068, -30068, -30068,
-                                     20091, 20091, 20091, 20091);
-  const __m128i k2k1 = _mm_set_epi16(20091, 20091, 20091, 20091,
-                                     -30068, -30068, -30068, -30068);
-  const __m128i zero = _mm_setzero_si128();
-  const __m128i zero_four = _mm_set_epi16(0, 0, 0, 0, 4, 4, 4, 4);
-  __m128i T01, T23;
-
-  // Load and concatenate the transform coefficients.
-  const __m128i in01 = _mm_loadu_si128((const __m128i*)&in[0]);
-  const __m128i in23 = _mm_loadu_si128((const __m128i*)&in[8]);
-  // a00 a10 a20 a30   a01 a11 a21 a31
-  // a02 a12 a22 a32   a03 a13 a23 a33
-
-  // Vertical pass and subsequent transpose.
-  {
-    const __m128i in1 = _mm_unpackhi_epi64(in01, in01);
-    const __m128i in3 = _mm_unpackhi_epi64(in23, in23);
-
-    // First pass, c and d calculations are longer because of the "trick"
-    // multiplications.
-    // c = MUL(in1, K2) - MUL(in3, K1) = MUL(in1, k2) - MUL(in3, k1) + in1 - in3
-    // d = MUL(in1, K1) + MUL(in3, K2) = MUL(in1, k1) + MUL(in3, k2) + in1 + in3
-    const __m128i a_d3 = _mm_add_epi16(in01, in23);
-    const __m128i b_c3 = _mm_sub_epi16(in01, in23);
-    const __m128i c1d1 = _mm_mulhi_epi16(in1, k2k1);
-    const __m128i c2d2 = _mm_mulhi_epi16(in3, k1k2);
-    const __m128i c3 = _mm_unpackhi_epi64(b_c3, b_c3);
-    const __m128i c4 = _mm_sub_epi16(c1d1, c2d2);
-    const __m128i c = _mm_add_epi16(c3, c4);
-    const __m128i d4u = _mm_add_epi16(c1d1, c2d2);
-    const __m128i du = _mm_add_epi16(a_d3, d4u);
-    const __m128i d = _mm_unpackhi_epi64(du, du);
-
-    // Second pass.
-    const __m128i comb_ab = _mm_unpacklo_epi64(a_d3, b_c3);
-    const __m128i comb_dc = _mm_unpacklo_epi64(d, c);
-
-    const __m128i tmp01 = _mm_add_epi16(comb_ab, comb_dc);
-    const __m128i tmp32 = _mm_sub_epi16(comb_ab, comb_dc);
-    const __m128i tmp23 = _mm_shuffle_epi32(tmp32, _MM_SHUFFLE(1, 0, 3, 2));
-
-    const __m128i transpose_0 = _mm_unpacklo_epi16(tmp01, tmp23);
-    const __m128i transpose_1 = _mm_unpackhi_epi16(tmp01, tmp23);
-    // a00 a20 a01 a21   a02 a22 a03 a23
-    // a10 a30 a11 a31   a12 a32 a13 a33
-
-    T01 = _mm_unpacklo_epi16(transpose_0, transpose_1);
-    T23 = _mm_unpackhi_epi16(transpose_0, transpose_1);
-    // a00 a10 a20 a30   a01 a11 a21 a31
-    // a02 a12 a22 a32   a03 a13 a23 a33
-  }
-
-  // Horizontal pass and subsequent transpose.
-  {
-    const __m128i T1 = _mm_unpackhi_epi64(T01, T01);
-    const __m128i T3 = _mm_unpackhi_epi64(T23, T23);
-
-    // First pass, c and d calculations are longer because of the "trick"
-    // multiplications.
-    const __m128i dc = _mm_add_epi16(T01, zero_four);
-
-    // c = MUL(T1, K2) - MUL(T3, K1) = MUL(T1, k2) - MUL(T3, k1) + T1 - T3
-    // d = MUL(T1, K1) + MUL(T3, K2) = MUL(T1, k1) + MUL(T3, k2) + T1 + T3
-    const __m128i a_d3 = _mm_add_epi16(dc, T23);
-    const __m128i b_c3 = _mm_sub_epi16(dc, T23);
-    const __m128i c1d1 = _mm_mulhi_epi16(T1, k2k1);
-    const __m128i c2d2 = _mm_mulhi_epi16(T3, k1k2);
-    const __m128i c3 = _mm_unpackhi_epi64(b_c3, b_c3);
-    const __m128i c4 = _mm_sub_epi16(c1d1, c2d2);
-    const __m128i c = _mm_add_epi16(c3, c4);
-    const __m128i d4u = _mm_add_epi16(c1d1, c2d2);
-    const __m128i du = _mm_add_epi16(a_d3, d4u);
-    const __m128i d = _mm_unpackhi_epi64(du, du);
-
-    // Second pass.
-    const __m128i comb_ab = _mm_unpacklo_epi64(a_d3, b_c3);
-    const __m128i comb_dc = _mm_unpacklo_epi64(d, c);
-
-    const __m128i tmp01 = _mm_add_epi16(comb_ab, comb_dc);
-    const __m128i tmp32 = _mm_sub_epi16(comb_ab, comb_dc);
-    const __m128i tmp23 = _mm_shuffle_epi32(tmp32, _MM_SHUFFLE(1, 0, 3, 2));
-
-    const __m128i shifted01 = _mm_srai_epi16(tmp01, 3);
-    const __m128i shifted23 = _mm_srai_epi16(tmp23, 3);
-    // a00 a01 a02 a03   a10 a11 a12 a13
-    // a20 a21 a22 a23   a30 a31 a32 a33
-
-    const __m128i transpose_0 = _mm_unpacklo_epi16(shifted01, shifted23);
-    const __m128i transpose_1 = _mm_unpackhi_epi16(shifted01, shifted23);
-    // a00 a20 a01 a21   a02 a22 a03 a23
-    // a10 a30 a11 a31   a12 a32 a13 a33
-
-    T01 = _mm_unpacklo_epi16(transpose_0, transpose_1);
-    T23 = _mm_unpackhi_epi16(transpose_0, transpose_1);
-    // a00 a10 a20 a30   a01 a11 a21 a31
-    // a02 a12 a22 a32   a03 a13 a23 a33
-  }
-
-  // Add inverse transform to 'ref' and store.
-  {
-    // Load the reference(s).
-    __m128i ref01, ref23, ref0123;
-    int32_t buf[4];
-
-    // Load four bytes/pixels per line.
-    const __m128i ref0 = _mm_cvtsi32_si128(WebPMemToInt32(&ref[0 * BPS]));
-    const __m128i ref1 = _mm_cvtsi32_si128(WebPMemToInt32(&ref[1 * BPS]));
-    const __m128i ref2 = _mm_cvtsi32_si128(WebPMemToInt32(&ref[2 * BPS]));
-    const __m128i ref3 = _mm_cvtsi32_si128(WebPMemToInt32(&ref[3 * BPS]));
-    ref01 = _mm_unpacklo_epi32(ref0, ref1);
-    ref23 = _mm_unpacklo_epi32(ref2, ref3);
-
-    // Convert to 16b.
-    ref01 = _mm_unpacklo_epi8(ref01, zero);
-    ref23 = _mm_unpacklo_epi8(ref23, zero);
-    // Add the inverse transform(s).
-    ref01 = _mm_add_epi16(ref01, T01);
-    ref23 = _mm_add_epi16(ref23, T23);
-    // Unsigned saturate to 8b.
-    ref0123 = _mm_packus_epi16(ref01, ref23);
-
-    _mm_storeu_si128((__m128i *)buf, ref0123);
-
-    // Store four bytes/pixels per line.
-    WebPInt32ToMem(&dst[0 * BPS], buf[0]);
-    WebPInt32ToMem(&dst[1 * BPS], buf[1]);
-    WebPInt32ToMem(&dst[2 * BPS], buf[2]);
-    WebPInt32ToMem(&dst[3 * BPS], buf[3]);
-  }
-}
-
-// Does two inverse transforms.
-static void ITransform_Two_SSE2(const uint8_t* ref, const int16_t* in,
-                                uint8_t* dst) {
+// Does one or two inverse transforms.
+static void ITransform_SSE2(const uint8_t* ref, const int16_t* in, uint8_t* dst,
+                            int do_two) {
  // This implementation makes use of 16-bit fixed point versions of two
  // multiply constants:
  //    K1 = sqrt(2) * cos (pi/8) ~= 85627 / 2^16
@@ -200,21 +49,33 @@ static void ITransform_Two_SSE2(const uint8_t* ref, const int16_t* in,
  __m128i T0, T1, T2, T3;

  // Load and concatenate the transform coefficients (we'll do two inverse
-  // transforms in parallel).
+  // transforms in parallel). In the case of only one inverse transform, the
+  // second half of the vectors will just contain random value we'll never
+  // use nor store.
  __m128i in0, in1, in2, in3;
  {
-    const __m128i tmp0 = _mm_loadu_si128((const __m128i*)&in[0]);
-    const __m128i tmp1 = _mm_loadu_si128((const __m128i*)&in[8]);
-    const __m128i tmp2 = _mm_loadu_si128((const __m128i*)&in[16]);
-    const __m128i tmp3 = _mm_loadu_si128((const __m128i*)&in[24]);
-    in0 = _mm_unpacklo_epi64(tmp0, tmp2);
-    in1 = _mm_unpackhi_epi64(tmp0, tmp2);
-    in2 = _mm_unpacklo_epi64(tmp1, tmp3);
-    in3 = _mm_unpackhi_epi64(tmp1, tmp3);
-    // a00 a10 a20 a30   b00 b10 b20 b30
-    // a01 a11 a21 a31   b01 b11 b21 b31
-    // a02 a12 a22 a32   b02 b12 b22 b32
-    // a03 a13 a23 a33   b03 b13 b23 b33
+    in0 = _mm_loadl_epi64((const __m128i*)&in[0]);
+    in1 = _mm_loadl_epi64((const __m128i*)&in[4]);
+    in2 = _mm_loadl_epi64((const __m128i*)&in[8]);
+    in3 = _mm_loadl_epi64((const __m128i*)&in[12]);
+    // a00 a10 a20 a30   x x x x
+    // a01 a11 a21 a31   x x x x
+    // a02 a12 a22 a32   x x x x
+    // a03 a13 a23 a33   x x x x
+    if (do_two) {
+      const __m128i inB0 = _mm_loadl_epi64((const __m128i*)&in[16]);
+      const __m128i inB1 = _mm_loadl_epi64((const __m128i*)&in[20]);
+      const __m128i inB2 = _mm_loadl_epi64((const __m128i*)&in[24]);
+      const __m128i inB3 = _mm_loadl_epi64((const __m128i*)&in[28]);
+      in0 = _mm_unpacklo_epi64(in0, inB0);
+      in1 = _mm_unpacklo_epi64(in1, inB1);
+      in2 = _mm_unpacklo_epi64(in2, inB2);
+      in3 = _mm_unpacklo_epi64(in3, inB3);
+      // a00 a10 a20 a30   b00 b10 b20 b30
+      // a01 a11 a21 a31   b01 b11 b21 b31
+      // a02 a12 a22 a32   b02 b12 b22 b32
+      // a03 a13 a23 a33   b03 b13 b23 b33
+    }
  }

  // Vertical pass and subsequent transpose.
@@ -287,11 +148,19 @@ static void ITransform_Two_SSE2(const uint8_t* ref, const int16_t* in,
    const __m128i zero = _mm_setzero_si128();
    // Load the reference(s).
    __m128i ref0, ref1, ref2, ref3;
-    // Load eight bytes/pixels per line.
-    ref0 = _mm_loadl_epi64((const __m128i*)&ref[0 * BPS]);
-    ref1 = _mm_loadl_epi64((const __m128i*)&ref[1 * BPS]);
-    ref2 = _mm_loadl_epi64((const __m128i*)&ref[2 * BPS]);
-    ref3 = _mm_loadl_epi64((const __m128i*)&ref[3 * BPS]);
+    if (do_two) {
+      // Load eight bytes/pixels per line.
+      ref0 = _mm_loadl_epi64((const __m128i*)&ref[0 * BPS]);
+      ref1 = _mm_loadl_epi64((const __m128i*)&ref[1 * BPS]);
+      ref2 = _mm_loadl_epi64((const __m128i*)&ref[2 * BPS]);
+      ref3 = _mm_loadl_epi64((const __m128i*)&ref[3 * BPS]);
+    } else {
+      // Load four bytes/pixels per line.
+      ref0 = _mm_cvtsi32_si128(WebPMemToUint32(&ref[0 * BPS]));
+      ref1 = _mm_cvtsi32_si128(WebPMemToUint32(&ref[1 * BPS]));
+      ref2 = _mm_cvtsi32_si128(WebPMemToUint32(&ref[2 * BPS]));
+      ref3 = _mm_cvtsi32_si128(WebPMemToUint32(&ref[3 * BPS]));
+    }
    // Convert to 16b.
    ref0 = _mm_unpacklo_epi8(ref0, zero);
    ref1 = _mm_unpacklo_epi8(ref1, zero);
@@ -307,21 +176,20 @@ static void ITransform_Two_SSE2(const uint8_t* ref, const int16_t* in,
    ref1 = _mm_packus_epi16(ref1, ref1);
    ref2 = _mm_packus_epi16(ref2, ref2);
    ref3 = _mm_packus_epi16(ref3, ref3);
-    // Store eight bytes/pixels per line.
-    _mm_storel_epi64((__m128i*)&dst[0 * BPS], ref0);
-    _mm_storel_epi64((__m128i*)&dst[1 * BPS], ref1);
-    _mm_storel_epi64((__m128i*)&dst[2 * BPS], ref2);
-    _mm_storel_epi64((__m128i*)&dst[3 * BPS], ref3);
-  }
-}
-
-// Does one or two inverse transforms.
-static void ITransform_SSE2(const uint8_t* ref, const int16_t* in, uint8_t* dst,
-                            int do_two) {
-  if (do_two) {
-    ITransform_Two_SSE2(ref, in, dst);
-  } else {
-    ITransform_One_SSE2(ref, in, dst);
+    // Store the results.
+    if (do_two) {
+      // Store eight bytes/pixels per line.
+      _mm_storel_epi64((__m128i*)&dst[0 * BPS], ref0);
+      _mm_storel_epi64((__m128i*)&dst[1 * BPS], ref1);
+      _mm_storel_epi64((__m128i*)&dst[2 * BPS], ref2);
+      _mm_storel_epi64((__m128i*)&dst[3 * BPS], ref3);
+    } else {
+      // Store four bytes/pixels per line.
+      WebPUint32ToMem(&dst[0 * BPS], _mm_cvtsi128_si32(ref0));
+      WebPUint32ToMem(&dst[1 * BPS], _mm_cvtsi128_si32(ref1));
+      WebPUint32ToMem(&dst[2 * BPS], _mm_cvtsi128_si32(ref2));
+      WebPUint32ToMem(&dst[3 * BPS], _mm_cvtsi128_si32(ref3));
+    }
  }
 }

@@ -613,7 +481,7 @@ static void CollectHistogram_SSE2(const uint8_t* ref, const uint8_t* pred,
 // helper for chroma-DC predictions
 static WEBP_INLINE void Put8x8uv_SSE2(uint8_t v, uint8_t* dst) {
  int j;
-  const __m128i values = _mm_set1_epi8((char)v);
+  const __m128i values = _mm_set1_epi8(v);
  for (j = 0; j < 8; ++j) {
    _mm_storel_epi64((__m128i*)(dst + j * BPS), values);
  }
@@ -621,7 +489,7 @@ static WEBP_INLINE void Put8x8uv_SSE2(uint8_t v, uint8_t* dst) {

 static WEBP_INLINE void Put16_SSE2(uint8_t v, uint8_t* dst) {
  int j;
-  const __m128i values = _mm_set1_epi8((char)v);
+  const __m128i values = _mm_set1_epi8(v);
  for (j = 0; j < 16; ++j) {
    _mm_store_si128((__m128i*)(dst + j * BPS), values);
  }
@@ -672,7 +540,7 @@ static WEBP_INLINE void VerticalPred_SSE2(uint8_t* dst,
 static WEBP_INLINE void HE8uv_SSE2(uint8_t* dst, const uint8_t* left) {
  int j;
  for (j = 0; j < 8; ++j) {
-    const __m128i values = _mm_set1_epi8((char)left[j]);
+    const __m128i values = _mm_set1_epi8(left[j]);
    _mm_storel_epi64((__m128i*)dst, values);
    dst += BPS;
  }
@@ -681,7 +549,7 @@ static WEBP_INLINE void HE8uv_SSE2(uint8_t* dst, const uint8_t* left) {
 static WEBP_INLINE void HE16_SSE2(uint8_t* dst, const uint8_t* left) {
  int j;
  for (j = 0; j < 16; ++j) {
-    const __m128i values = _mm_set1_epi8((char)left[j]);
+    const __m128i values = _mm_set1_epi8(left[j]);
    _mm_store_si128((__m128i*)dst, values);
    dst += BPS;
  }
@@ -854,10 +722,10 @@ static WEBP_INLINE void VE4_SSE2(uint8_t* dst,
  const __m128i lsb = _mm_and_si128(_mm_xor_si128(ABCDEFGH, CDEFGH00), one);
  const __m128i b = _mm_subs_epu8(a, lsb);
  const __m128i avg = _mm_avg_epu8(b, BCDEFGH0);
-  const int vals = _mm_cvtsi128_si32(avg);
+  const uint32_t vals = _mm_cvtsi128_si32(avg);
  int i;
  for (i = 0; i < 4; ++i) {
-    WebPInt32ToMem(dst + i * BPS, vals);
+    WebPUint32ToMem(dst + i * BPS, vals);
  }
 }

@@ -892,10 +760,10 @@ static WEBP_INLINE void LD4_SSE2(uint8_t* dst,
  const __m128i lsb = _mm_and_si128(_mm_xor_si128(ABCDEFGH, CDEFGHH0), one);
  const __m128i avg2 = _mm_subs_epu8(avg1, lsb);
  const __m128i abcdefg = _mm_avg_epu8(avg2, BCDEFGH0);
-  WebPInt32ToMem(dst + 0 * BPS, _mm_cvtsi128_si32(               abcdefg    ));
-  WebPInt32ToMem(dst + 1 * BPS, _mm_cvtsi128_si32(_mm_srli_si128(abcdefg, 1)));
-  WebPInt32ToMem(dst + 2 * BPS, _mm_cvtsi128_si32(_mm_srli_si128(abcdefg, 2)));
-  WebPInt32ToMem(dst + 3 * BPS, _mm_cvtsi128_si32(_mm_srli_si128(abcdefg, 3)));
+  WebPUint32ToMem(dst + 0 * BPS, _mm_cvtsi128_si32(               abcdefg    ));
+  WebPUint32ToMem(dst + 1 * BPS, _mm_cvtsi128_si32(_mm_srli_si128(abcdefg, 1)));
+  WebPUint32ToMem(dst + 2 * BPS, _mm_cvtsi128_si32(_mm_srli_si128(abcdefg, 2)));
+  WebPUint32ToMem(dst + 3 * BPS, _mm_cvtsi128_si32(_mm_srli_si128(abcdefg, 3)));
 }

 static WEBP_INLINE void VR4_SSE2(uint8_t* dst,
@@ -914,10 +782,10 @@ static WEBP_INLINE void VR4_SSE2(uint8_t* dst,
  const __m128i lsb = _mm_and_si128(_mm_xor_si128(IXABCD, ABCD0), one);
  const __m128i avg2 = _mm_subs_epu8(avg1, lsb);
  const __m128i efgh = _mm_avg_epu8(avg2, XABCD);
-  WebPInt32ToMem(dst + 0 * BPS, _mm_cvtsi128_si32(               abcd    ));
-  WebPInt32ToMem(dst + 1 * BPS, _mm_cvtsi128_si32(               efgh    ));
-  WebPInt32ToMem(dst + 2 * BPS, _mm_cvtsi128_si32(_mm_slli_si128(abcd, 1)));
-  WebPInt32ToMem(dst + 3 * BPS, _mm_cvtsi128_si32(_mm_slli_si128(efgh, 1)));
+  WebPUint32ToMem(dst + 0 * BPS, _mm_cvtsi128_si32(               abcd    ));
+  WebPUint32ToMem(dst + 1 * BPS, _mm_cvtsi128_si32(               efgh    ));
+  WebPUint32ToMem(dst + 2 * BPS, _mm_cvtsi128_si32(_mm_slli_si128(abcd, 1)));
+  WebPUint32ToMem(dst + 3 * BPS, _mm_cvtsi128_si32(_mm_slli_si128(efgh, 1)));

  // these two are hard to implement in SSE2, so we keep the C-version:
  DST(0, 2) = AVG3(J, I, X);
@@ -939,12 +807,11 @@ static WEBP_INLINE void VL4_SSE2(uint8_t* dst,
  const __m128i abbc = _mm_or_si128(ab, bc);
  const __m128i lsb2 = _mm_and_si128(abbc, lsb1);
  const __m128i avg4 = _mm_subs_epu8(avg3, lsb2);
-  const uint32_t extra_out =
-      (uint32_t)_mm_cvtsi128_si32(_mm_srli_si128(avg4, 4));
-  WebPInt32ToMem(dst + 0 * BPS, _mm_cvtsi128_si32(               avg1    ));
-  WebPInt32ToMem(dst + 1 * BPS, _mm_cvtsi128_si32(               avg4    ));
-  WebPInt32ToMem(dst + 2 * BPS, _mm_cvtsi128_si32(_mm_srli_si128(avg1, 1)));
-  WebPInt32ToMem(dst + 3 * BPS, _mm_cvtsi128_si32(_mm_srli_si128(avg4, 1)));
+  const uint32_t extra_out = _mm_cvtsi128_si32(_mm_srli_si128(avg4, 4));
+  WebPUint32ToMem(dst + 0 * BPS, _mm_cvtsi128_si32(               avg1    ));
+  WebPUint32ToMem(dst + 1 * BPS, _mm_cvtsi128_si32(               avg4    ));
+  WebPUint32ToMem(dst + 2 * BPS, _mm_cvtsi128_si32(_mm_srli_si128(avg1, 1)));
+  WebPUint32ToMem(dst + 3 * BPS, _mm_cvtsi128_si32(_mm_srli_si128(avg4, 1)));

  // these two are hard to get and irregular
  DST(3, 2) = (extra_out >> 0) & 0xff;
@@ -962,10 +829,10 @@ static WEBP_INLINE void RD4_SSE2(uint8_t* dst,
  const __m128i lsb = _mm_and_si128(_mm_xor_si128(JIXABCD__, LKJIXABCD), one);
  const __m128i avg2 = _mm_subs_epu8(avg1, lsb);
  const __m128i abcdefg = _mm_avg_epu8(avg2, KJIXABCD_);
-  WebPInt32ToMem(dst + 3 * BPS, _mm_cvtsi128_si32(               abcdefg    ));
-  WebPInt32ToMem(dst + 2 * BPS, _mm_cvtsi128_si32(_mm_srli_si128(abcdefg, 1)));
-  WebPInt32ToMem(dst + 1 * BPS, _mm_cvtsi128_si32(_mm_srli_si128(abcdefg, 2)));
-  WebPInt32ToMem(dst + 0 * BPS, _mm_cvtsi128_si32(_mm_srli_si128(abcdefg, 3)));
+  WebPUint32ToMem(dst + 3 * BPS, _mm_cvtsi128_si32(               abcdefg    ));
+  WebPUint32ToMem(dst + 2 * BPS, _mm_cvtsi128_si32(_mm_srli_si128(abcdefg, 1)));
+  WebPUint32ToMem(dst + 1 * BPS, _mm_cvtsi128_si32(_mm_srli_si128(abcdefg, 2)));
+  WebPUint32ToMem(dst + 0 * BPS, _mm_cvtsi128_si32(_mm_srli_si128(abcdefg, 3)));
 }

 static WEBP_INLINE void HU4_SSE2(uint8_t* dst, const uint8_t* top) {
@@ -1008,14 +875,14 @@ static WEBP_INLINE void HD4_SSE2(uint8_t* dst, const uint8_t* top) {

 static WEBP_INLINE void TM4_SSE2(uint8_t* dst, const uint8_t* top) {
  const __m128i zero = _mm_setzero_si128();
-  const __m128i top_values = _mm_cvtsi32_si128(WebPMemToInt32(top));
+  const __m128i top_values = _mm_cvtsi32_si128(WebPMemToUint32(top));
  const __m128i top_base = _mm_unpacklo_epi8(top_values, zero);
  int y;
  for (y = 0; y < 4; ++y, dst += BPS) {
    const int val = top[-2 - y] - top[-1];
    const __m128i base = _mm_set1_epi16(val);
    const __m128i out = _mm_packus_epi16(_mm_add_epi16(base, top_base), zero);
-    WebPInt32ToMem(dst, _mm_cvtsi128_si32(out));
+    WebPUint32ToMem(dst, _mm_cvtsi128_si32(out));
  }
 }

--- a/src/dsp/filters.c
+++ b/src/dsp/filters.c
@@ -233,7 +233,6 @@ static void GradientUnfilter_C(const uint8_t* prev, const uint8_t* in,
 WebPFilterFunc WebPFilters[WEBP_FILTER_LAST];
 WebPUnfilterFunc WebPUnfilters[WEBP_FILTER_LAST];

-extern VP8CPUInfo VP8GetCPUInfo;
 extern void VP8FiltersInitMIPSdspR2(void);
 extern void VP8FiltersInitMSA(void);
 extern void VP8FiltersInitNEON(void);
--- a/src/dsp/lossless.c
+++ b/src/dsp/lossless.c
@@ -49,7 +49,7 @@ static WEBP_INLINE uint32_t Clip255(uint32_t a) {
 }

 static WEBP_INLINE int AddSubtractComponentFull(int a, int b, int c) {
-  return Clip255((uint32_t)(a + b - c));
+  return Clip255(a + b - c);
 }

 static WEBP_INLINE uint32_t ClampedAddSubtractFull(uint32_t c0, uint32_t c1,
@@ -66,7 +66,7 @@ static WEBP_INLINE uint32_t ClampedAddSubtractFull(uint32_t c0, uint32_t c1,
 }

 static WEBP_INLINE int AddSubtractComponentHalf(int a, int b) {
-  return Clip255((uint32_t)(a + (a - b) / 2));
+  return Clip255(a + (a - b) / 2);
 }

 static WEBP_INLINE uint32_t ClampedAddSubtractHalf(uint32_t c0, uint32_t c1,
@@ -293,10 +293,10 @@ void VP8LTransformColorInverse_C(const VP8LMultipliers* const m,
    const uint32_t red = argb >> 16;
    int new_red = red & 0xff;
    int new_blue = argb & 0xff;
-    new_red += ColorTransformDelta((int8_t)m->green_to_red_, green);
+    new_red += ColorTransformDelta(m->green_to_red_, green);
    new_red &= 0xff;
-    new_blue += ColorTransformDelta((int8_t)m->green_to_blue_, green);
-    new_blue += ColorTransformDelta((int8_t)m->red_to_blue_, (int8_t)new_red);
+    new_blue += ColorTransformDelta(m->green_to_blue_, green);
+    new_blue += ColorTransformDelta(m->red_to_blue_, (int8_t)new_red);
    new_blue &= 0xff;
    dst[i] = (argb & 0xff00ff00u) | (new_red << 16) | (new_blue);
  }
@@ -395,7 +395,7 @@ void VP8LInverseTransform(const VP8LTransform* const transform,
  assert(row_start < row_end);
  assert(row_end <= transform->ysize_);
  switch (transform->type_) {
-    case SUBTRACT_GREEN_TRANSFORM:
+    case SUBTRACT_GREEN:
      VP8LAddGreenToBlueAndRed(in, (row_end - row_start) * width, out);
      break;
    case PREDICTOR_TRANSFORM:
@@ -588,7 +588,6 @@ VP8LConvertFunc VP8LConvertBGRAToBGR;
 VP8LMapARGBFunc VP8LMapColor32b;
 VP8LMapAlphaFunc VP8LMapColor8b;

-extern VP8CPUInfo VP8GetCPUInfo;
 extern void VP8LDspInitSSE2(void);
 extern void VP8LDspInitSSE41(void);
 extern void VP8LDspInitNEON(void);
--- a/src/dsp/lossless_enc.c
+++ b/src/dsp/lossless_enc.c
@@ -522,11 +522,11 @@ static void GetCombinedEntropyUnrefined_C(const uint32_t X[],
 void VP8LSubtractGreenFromBlueAndRed_C(uint32_t* argb_data, int num_pixels) {
  int i;
  for (i = 0; i < num_pixels; ++i) {
-    const int argb = (int)argb_data[i];
+    const int argb = argb_data[i];
    const int green = (argb >> 8) & 0xff;
    const uint32_t new_r = (((argb >> 16) & 0xff) - green) & 0xff;
    const uint32_t new_b = (((argb >>  0) & 0xff) - green) & 0xff;
-    argb_data[i] = ((uint32_t)argb & 0xff00ff00u) | (new_r << 16) | new_b;
+    argb_data[i] = (argb & 0xff00ff00u) | (new_r << 16) | new_b;
  }
 }

@@ -547,10 +547,10 @@ void VP8LTransformColor_C(const VP8LMultipliers* const m, uint32_t* data,
    const int8_t red   = U32ToS8(argb >> 16);
    int new_red = red & 0xff;
    int new_blue = argb & 0xff;
-    new_red -= ColorTransformDelta((int8_t)m->green_to_red_, green);
+    new_red -= ColorTransformDelta(m->green_to_red_, green);
    new_red &= 0xff;
-    new_blue -= ColorTransformDelta((int8_t)m->green_to_blue_, green);
-    new_blue -= ColorTransformDelta((int8_t)m->red_to_blue_, red);
+    new_blue -= ColorTransformDelta(m->green_to_blue_, green);
+    new_blue -= ColorTransformDelta(m->red_to_blue_, red);
    new_blue &= 0xff;
    data[i] = (argb & 0xff00ff00u) | (new_red << 16) | (new_blue);
  }
@@ -560,7 +560,7 @@ static WEBP_INLINE uint8_t TransformColorRed(uint8_t green_to_red,
                                             uint32_t argb) {
  const int8_t green = U32ToS8(argb >> 8);
  int new_red = argb >> 16;
-  new_red -= ColorTransformDelta((int8_t)green_to_red, green);
+  new_red -= ColorTransformDelta(green_to_red, green);
  return (new_red & 0xff);
 }

@@ -569,9 +569,9 @@ static WEBP_INLINE uint8_t TransformColorBlue(uint8_t green_to_blue,
                                              uint32_t argb) {
  const int8_t green = U32ToS8(argb >>  8);
  const int8_t red   = U32ToS8(argb >> 16);
-  int new_blue = argb & 0xff;
-  new_blue -= ColorTransformDelta((int8_t)green_to_blue, green);
-  new_blue -= ColorTransformDelta((int8_t)red_to_blue, red);
+  uint8_t new_blue = argb & 0xff;
+  new_blue -= ColorTransformDelta(green_to_blue, green);
+  new_blue -= ColorTransformDelta(red_to_blue, red);
  return (new_blue & 0xff);
 }

@@ -791,7 +791,6 @@ VP8LBundleColorMapFunc VP8LBundleColorMap;
 VP8LPredictorAddSubFunc VP8LPredictorsSub[16];
 VP8LPredictorAddSubFunc VP8LPredictorsSub_C[16];

-extern VP8CPUInfo VP8GetCPUInfo;
 extern void VP8LEncDspInitSSE2(void);
 extern void VP8LEncDspInitSSE41(void);
 extern void VP8LEncDspInitNEON(void);
--- a/src/dsp/lossless_enc_neon.c
+++ b/src/dsp/lossless_enc_neon.c
@@ -25,7 +25,7 @@

 // vtbl?_u8 are marked unavailable for iOS arm64 with Xcode < 6.3, use
 // non-standard versions there.
-#if defined(__APPLE__) && WEBP_AARCH64 && \
+#if defined(__APPLE__) && defined(__aarch64__) && \
    defined(__apple_build_version__) && (__apple_build_version__< 6020037)
 #define USE_VTBLQ
 #endif
--- a/src/dsp/lossless_enc_sse2.c
+++ b/src/dsp/lossless_enc_sse2.c
@@ -54,8 +54,8 @@ static void TransformColor_SSE2(const VP8LMultipliers* const m,
  const __m128i mults_rb = MK_CST_16(CST_5b(m->green_to_red_),
                                     CST_5b(m->green_to_blue_));
  const __m128i mults_b2 = MK_CST_16(CST_5b(m->red_to_blue_), 0);
-  const __m128i mask_ag = _mm_set1_epi32((int)0xff00ff00);  // alpha-green masks
-  const __m128i mask_rb = _mm_set1_epi32(0x00ff00ff);       // red-blue masks
+  const __m128i mask_ag = _mm_set1_epi32(0xff00ff00);  // alpha-green masks
+  const __m128i mask_rb = _mm_set1_epi32(0x00ff00ff);  // red-blue masks
  int i;
  for (i = 0; i + 4 <= num_pixels; i += 4) {
    const __m128i in = _mm_loadu_si128((__m128i*)&argb_data[i]); // argb
@@ -376,7 +376,7 @@ static void BundleColorMap_SSE2(const uint8_t* const row, int width, int xbits,
      break;
    }
    case 2: {
-      const __m128i mask_or = _mm_set1_epi32((int)0xff000000);
+      const __m128i mask_or = _mm_set1_epi32(0xff000000);
      const __m128i mul_cst = _mm_set1_epi16(0x0104);
      const __m128i mask_mul = _mm_set1_epi16(0x0f00);
      for (x = 0; x + 16 <= width; x += 16, dst += 4) {
@@ -427,7 +427,7 @@ static WEBP_INLINE void Average2_m128i(const __m128i* const a0,
 static void PredictorSub0_SSE2(const uint32_t* in, const uint32_t* upper,
                               int num_pixels, uint32_t* out) {
  int i;
-  const __m128i black = _mm_set1_epi32((int)ARGB_BLACK);
+  const __m128i black = _mm_set1_epi32(ARGB_BLACK);
  for (i = 0; i + 4 <= num_pixels; i += 4) {
    const __m128i src = _mm_loadu_si128((const __m128i*)&in[i]);
    const __m128i res = _mm_sub_epi8(src, black);
--- a/src/dsp/lossless_neon.c
+++ b/src/dsp/lossless_neon.c
@@ -498,7 +498,7 @@ static void PredictorAdd13_NEON(const uint32_t* in, const uint32_t* upper,

 // vtbl?_u8 are marked unavailable for iOS arm64 with Xcode < 6.3, use
 // non-standard versions there.
-#if defined(__APPLE__) && WEBP_AARCH64 && \
+#if defined(__APPLE__) && defined(__aarch64__) && \
    defined(__apple_build_version__) && (__apple_build_version__< 6020037)
 #define USE_VTBLQ
 #endif
--- a/src/dsp/lossless_sse2.c
+++ b/src/dsp/lossless_sse2.c
@@ -27,22 +27,23 @@ static WEBP_INLINE uint32_t ClampedAddSubtractFull_SSE2(uint32_t c0,
                                                        uint32_t c1,
                                                        uint32_t c2) {
  const __m128i zero = _mm_setzero_si128();
-  const __m128i C0 = _mm_unpacklo_epi8(_mm_cvtsi32_si128((int)c0), zero);
-  const __m128i C1 = _mm_unpacklo_epi8(_mm_cvtsi32_si128((int)c1), zero);
-  const __m128i C2 = _mm_unpacklo_epi8(_mm_cvtsi32_si128((int)c2), zero);
+  const __m128i C0 = _mm_unpacklo_epi8(_mm_cvtsi32_si128(c0), zero);
+  const __m128i C1 = _mm_unpacklo_epi8(_mm_cvtsi32_si128(c1), zero);
+  const __m128i C2 = _mm_unpacklo_epi8(_mm_cvtsi32_si128(c2), zero);
  const __m128i V1 = _mm_add_epi16(C0, C1);
  const __m128i V2 = _mm_sub_epi16(V1, C2);
  const __m128i b = _mm_packus_epi16(V2, V2);
-  return (uint32_t)_mm_cvtsi128_si32(b);
+  const uint32_t output = _mm_cvtsi128_si32(b);
+  return output;
 }

 static WEBP_INLINE uint32_t ClampedAddSubtractHalf_SSE2(uint32_t c0,
                                                        uint32_t c1,
                                                        uint32_t c2) {
  const __m128i zero = _mm_setzero_si128();
-  const __m128i C0 = _mm_unpacklo_epi8(_mm_cvtsi32_si128((int)c0), zero);
-  const __m128i C1 = _mm_unpacklo_epi8(_mm_cvtsi32_si128((int)c1), zero);
-  const __m128i B0 = _mm_unpacklo_epi8(_mm_cvtsi32_si128((int)c2), zero);
+  const __m128i C0 = _mm_unpacklo_epi8(_mm_cvtsi32_si128(c0), zero);
+  const __m128i C1 = _mm_unpacklo_epi8(_mm_cvtsi32_si128(c1), zero);
+  const __m128i B0 = _mm_unpacklo_epi8(_mm_cvtsi32_si128(c2), zero);
  const __m128i avg = _mm_add_epi16(C1, C0);
  const __m128i A0 = _mm_srli_epi16(avg, 1);
  const __m128i A1 = _mm_sub_epi16(A0, B0);
@@ -51,15 +52,16 @@ static WEBP_INLINE uint32_t ClampedAddSubtractHalf_SSE2(uint32_t c0,
  const __m128i A3 = _mm_srai_epi16(A2, 1);
  const __m128i A4 = _mm_add_epi16(A0, A3);
  const __m128i A5 = _mm_packus_epi16(A4, A4);
-  return (uint32_t)_mm_cvtsi128_si32(A5);
+  const uint32_t output = _mm_cvtsi128_si32(A5);
+  return output;
 }

 static WEBP_INLINE uint32_t Select_SSE2(uint32_t a, uint32_t b, uint32_t c) {
  int pa_minus_pb;
  const __m128i zero = _mm_setzero_si128();
-  const __m128i A0 = _mm_cvtsi32_si128((int)a);
-  const __m128i B0 = _mm_cvtsi32_si128((int)b);
-  const __m128i C0 = _mm_cvtsi32_si128((int)c);
+  const __m128i A0 = _mm_cvtsi32_si128(a);
+  const __m128i B0 = _mm_cvtsi32_si128(b);
+  const __m128i C0 = _mm_cvtsi32_si128(c);
  const __m128i AC0 = _mm_subs_epu8(A0, C0);
  const __m128i CA0 = _mm_subs_epu8(C0, A0);
  const __m128i BC0 = _mm_subs_epu8(B0, C0);
@@ -92,8 +94,8 @@ static WEBP_INLINE void Average2_uint32_SSE2(const uint32_t a0,
                                             __m128i* const avg) {
  // (a + b) >> 1 = ((a + b + 1) >> 1) - ((a ^ b) & 1)
  const __m128i ones = _mm_set1_epi8(1);
-  const __m128i A0 = _mm_cvtsi32_si128((int)a0);
-  const __m128i A1 = _mm_cvtsi32_si128((int)a1);
+  const __m128i A0 = _mm_cvtsi32_si128(a0);
+  const __m128i A1 = _mm_cvtsi32_si128(a1);
  const __m128i avg1 = _mm_avg_epu8(A0, A1);
  const __m128i one = _mm_and_si128(_mm_xor_si128(A0, A1), ones);
  *avg = _mm_sub_epi8(avg1, one);
@@ -101,8 +103,8 @@ static WEBP_INLINE void Average2_uint32_SSE2(const uint32_t a0,

 static WEBP_INLINE __m128i Average2_uint32_16_SSE2(uint32_t a0, uint32_t a1) {
  const __m128i zero = _mm_setzero_si128();
-  const __m128i A0 = _mm_unpacklo_epi8(_mm_cvtsi32_si128((int)a0), zero);
-  const __m128i A1 = _mm_unpacklo_epi8(_mm_cvtsi32_si128((int)a1), zero);
+  const __m128i A0 = _mm_unpacklo_epi8(_mm_cvtsi32_si128(a0), zero);
+  const __m128i A1 = _mm_unpacklo_epi8(_mm_cvtsi32_si128(a1), zero);
  const __m128i sum = _mm_add_epi16(A1, A0);
  return _mm_srli_epi16(sum, 1);
 }
@@ -110,18 +112,19 @@ static WEBP_INLINE __m128i Average2_uint32_16_SSE2(uint32_t a0, uint32_t a1) {
 static WEBP_INLINE uint32_t Average2_SSE2(uint32_t a0, uint32_t a1) {
  __m128i output;
  Average2_uint32_SSE2(a0, a1, &output);
-  return (uint32_t)_mm_cvtsi128_si32(output);
+  return _mm_cvtsi128_si32(output);
 }

 static WEBP_INLINE uint32_t Average3_SSE2(uint32_t a0, uint32_t a1,
                                          uint32_t a2) {
  const __m128i zero = _mm_setzero_si128();
  const __m128i avg1 = Average2_uint32_16_SSE2(a0, a2);
-  const __m128i A1 = _mm_unpacklo_epi8(_mm_cvtsi32_si128((int)a1), zero);
+  const __m128i A1 = _mm_unpacklo_epi8(_mm_cvtsi32_si128(a1), zero);
  const __m128i sum = _mm_add_epi16(avg1, A1);
  const __m128i avg2 = _mm_srli_epi16(sum, 1);
  const __m128i A2 = _mm_packus_epi16(avg2, avg2);
-  return (uint32_t)_mm_cvtsi128_si32(A2);
+  const uint32_t output = _mm_cvtsi128_si32(A2);
+  return output;
 }

 static WEBP_INLINE uint32_t Average4_SSE2(uint32_t a0, uint32_t a1,
@@ -131,7 +134,8 @@ static WEBP_INLINE uint32_t Average4_SSE2(uint32_t a0, uint32_t a1,
  const __m128i sum = _mm_add_epi16(avg2, avg1);
  const __m128i avg3 = _mm_srli_epi16(sum, 1);
  const __m128i A0 = _mm_packus_epi16(avg3, avg3);
-  return (uint32_t)_mm_cvtsi128_si32(A0);
+  const uint32_t output = _mm_cvtsi128_si32(A0);
+  return output;
 }

 static uint32_t Predictor5_SSE2(const uint32_t* const left,
@@ -188,7 +192,7 @@ static uint32_t Predictor13_SSE2(const uint32_t* const left,
 static void PredictorAdd0_SSE2(const uint32_t* in, const uint32_t* upper,
                               int num_pixels, uint32_t* out) {
  int i;
-  const __m128i black = _mm_set1_epi32((int)ARGB_BLACK);
+  const __m128i black = _mm_set1_epi32(ARGB_BLACK);
  for (i = 0; i + 4 <= num_pixels; i += 4) {
    const __m128i src = _mm_loadu_si128((const __m128i*)&in[i]);
    const __m128i res = _mm_add_epi8(src, black);
@@ -204,7 +208,7 @@ static void PredictorAdd0_SSE2(const uint32_t* in, const uint32_t* upper,
 static void PredictorAdd1_SSE2(const uint32_t* in, const uint32_t* upper,
                               int num_pixels, uint32_t* out) {
  int i;
-  __m128i prev = _mm_set1_epi32((int)out[-1]);
+  __m128i prev = _mm_set1_epi32(out[-1]);
  for (i = 0; i + 4 <= num_pixels; i += 4) {
    // a | b | c | d
    const __m128i src = _mm_loadu_si128((const __m128i*)&in[i]);
@@ -281,12 +285,12 @@ GENERATE_PREDICTOR_2(9, upper[i + 1])
 #undef GENERATE_PREDICTOR_2

 // Predictor10: average of (average of (L,TL), average of (T, TR)).
-#define DO_PRED10(OUT) do {                         \
-  __m128i avgLTL, avg;                              \
-  Average2_m128i(&L, &TL, &avgLTL);                 \
-  Average2_m128i(&avgTTR, &avgLTL, &avg);           \
-  L = _mm_add_epi8(avg, src);                       \
-  out[i + (OUT)] = (uint32_t)_mm_cvtsi128_si32(L);  \
+#define DO_PRED10(OUT) do {               \
+  __m128i avgLTL, avg;                    \
+  Average2_m128i(&L, &TL, &avgLTL);       \
+  Average2_m128i(&avgTTR, &avgLTL, &avg); \
+  L = _mm_add_epi8(avg, src);             \
+  out[i + (OUT)] = _mm_cvtsi128_si32(L);  \
 } while (0)

 #define DO_PRED10_SHIFT do {                                  \
@@ -299,7 +303,7 @@ GENERATE_PREDICTOR_2(9, upper[i + 1])
 static void PredictorAdd10_SSE2(const uint32_t* in, const uint32_t* upper,
                                int num_pixels, uint32_t* out) {
  int i;
-  __m128i L = _mm_cvtsi32_si128((int)out[-1]);
+  __m128i L = _mm_cvtsi32_si128(out[-1]);
  for (i = 0; i + 4 <= num_pixels; i += 4) {
    __m128i src = _mm_loadu_si128((const __m128i*)&in[i]);
    __m128i TL = _mm_loadu_si128((const __m128i*)&upper[i - 1]);
@@ -332,7 +336,7 @@ static void PredictorAdd10_SSE2(const uint32_t* in, const uint32_t* upper,
  const __m128i B = _mm_andnot_si128(mask, T);                         \
  const __m128i pred = _mm_or_si128(A, B); /* pred = (pa > b)? L : T*/ \
  L = _mm_add_epi8(src, pred);                                         \
-  out[i + (OUT)] = (uint32_t)_mm_cvtsi128_si32(L);                     \
+  out[i + (OUT)] = _mm_cvtsi128_si32(L);                               \
 } while (0)

 #define DO_PRED11_SHIFT do {                                \
@@ -347,7 +351,7 @@ static void PredictorAdd11_SSE2(const uint32_t* in, const uint32_t* upper,
                                int num_pixels, uint32_t* out) {
  int i;
  __m128i pa;
-  __m128i L = _mm_cvtsi32_si128((int)out[-1]);
+  __m128i L = _mm_cvtsi32_si128(out[-1]);
  for (i = 0; i + 4 <= num_pixels; i += 4) {
    __m128i T = _mm_loadu_si128((const __m128i*)&upper[i]);
    __m128i TL = _mm_loadu_si128((const __m128i*)&upper[i - 1]);
@@ -380,12 +384,12 @@ static void PredictorAdd11_SSE2(const uint32_t* in, const uint32_t* upper,
 #undef DO_PRED11_SHIFT

 // Predictor12: ClampedAddSubtractFull.
-#define DO_PRED12(DIFF, LANE, OUT) do {              \
-  const __m128i all = _mm_add_epi16(L, (DIFF));      \
-  const __m128i alls = _mm_packus_epi16(all, all);   \
-  const __m128i res = _mm_add_epi8(src, alls);       \
-  out[i + (OUT)] = (uint32_t)_mm_cvtsi128_si32(res); \
-  L = _mm_unpacklo_epi8(res, zero);                  \
+#define DO_PRED12(DIFF, LANE, OUT) do {            \
+  const __m128i all = _mm_add_epi16(L, (DIFF));    \
+  const __m128i alls = _mm_packus_epi16(all, all); \
+  const __m128i res = _mm_add_epi8(src, alls);     \
+  out[i + (OUT)] = _mm_cvtsi128_si32(res);         \
+  L = _mm_unpacklo_epi8(res, zero);                \
 } while (0)

 #define DO_PRED12_SHIFT(DIFF, LANE) do {                    \
@@ -398,7 +402,7 @@ static void PredictorAdd12_SSE2(const uint32_t* in, const uint32_t* upper,
                                int num_pixels, uint32_t* out) {
  int i;
  const __m128i zero = _mm_setzero_si128();
-  const __m128i L8 = _mm_cvtsi32_si128((int)out[-1]);
+  const __m128i L8 = _mm_cvtsi32_si128(out[-1]);
  __m128i L = _mm_unpacklo_epi8(L8, zero);
  for (i = 0; i + 4 <= num_pixels; i += 4) {
    // Load 4 pixels at a time.
@@ -464,7 +468,7 @@ static void TransformColorInverse_SSE2(const VP8LMultipliers* const m,
  const __m128i mults_b2 = MK_CST_16(CST(red_to_blue_), 0);
 #undef MK_CST_16
 #undef CST
-  const __m128i mask_ag = _mm_set1_epi32((int)0xff00ff00);  // alpha-green masks
+  const __m128i mask_ag = _mm_set1_epi32(0xff00ff00);  // alpha-green masks
  int i;
  for (i = 0; i + 4 <= num_pixels; i += 4) {
    const __m128i in = _mm_loadu_si128((const __m128i*)&src[i]); // argb
@@ -528,7 +532,7 @@ static void ConvertBGRAToRGB_SSE2(const uint32_t* src, int num_pixels,

 static void ConvertBGRAToRGBA_SSE2(const uint32_t* src,
                                   int num_pixels, uint8_t* dst) {
-  const __m128i red_blue_mask = _mm_set1_epi32(0x00ff00ff);
+  const __m128i red_blue_mask = _mm_set1_epi32(0x00ff00ffu);
  const __m128i* in = (const __m128i*)src;
  __m128i* out = (__m128i*)dst;
  while (num_pixels >= 8) {
@@ -557,7 +561,7 @@ static void ConvertBGRAToRGBA_SSE2(const uint32_t* src,
 static void ConvertBGRAToRGBA4444_SSE2(const uint32_t* src,
                                       int num_pixels, uint8_t* dst) {
  const __m128i mask_0x0f = _mm_set1_epi8(0x0f);
-  const __m128i mask_0xf0 = _mm_set1_epi8((char)0xf0);
+  const __m128i mask_0xf0 = _mm_set1_epi8(0xf0);
  const __m128i* in = (const __m128i*)src;
  __m128i* out = (__m128i*)dst;
  while (num_pixels >= 8) {
@@ -592,8 +596,8 @@ static void ConvertBGRAToRGBA4444_SSE2(const uint32_t* src,

 static void ConvertBGRAToRGB565_SSE2(const uint32_t* src,
                                     int num_pixels, uint8_t* dst) {
-  const __m128i mask_0xe0 = _mm_set1_epi8((char)0xe0);
-  const __m128i mask_0xf8 = _mm_set1_epi8((char)0xf8);
+  const __m128i mask_0xe0 = _mm_set1_epi8(0xe0);
+  const __m128i mask_0xf8 = _mm_set1_epi8(0xf8);
  const __m128i mask_0x07 = _mm_set1_epi8(0x07);
  const __m128i* in = (const __m128i*)src;
  __m128i* out = (__m128i*)dst;
--- a/src/dsp/lossless_sse41.c
+++ b/src/dsp/lossless_sse41.c
@@ -25,12 +25,11 @@ static void TransformColorInverse_SSE41(const VP8LMultipliers* const m,
                                        int num_pixels, uint32_t* dst) {
 // sign-extended multiplying constants, pre-shifted by 5.
 #define CST(X)  (((int16_t)(m->X << 8)) >> 5)   // sign-extend
-  const __m128i mults_rb =
-      _mm_set1_epi32((int)((uint32_t)CST(green_to_red_) << 16 |
-                           (CST(green_to_blue_) & 0xffff)));
+  const __m128i mults_rb = _mm_set1_epi32((uint32_t)CST(green_to_red_) << 16 |
+                                          (CST(green_to_blue_) & 0xffff));
  const __m128i mults_b2 = _mm_set1_epi32(CST(red_to_blue_));
 #undef CST
-  const __m128i mask_ag = _mm_set1_epi32((int)0xff00ff00);
+  const __m128i mask_ag = _mm_set1_epi32(0xff00ff00);
  const __m128i perm1 = _mm_setr_epi8(-1, 1, -1, 1, -1, 5, -1, 5,
                                      -1, 9, -1, 9, -1, 13, -1, 13);
  const __m128i perm2 = _mm_setr_epi8(-1, 2, -1, -1, -1, 6, -1, -1,
--- a/src/dsp/neon.h
+++ b/src/dsp/neon.h
@@ -21,7 +21,7 @@
 // Right now, some intrinsics functions seem slower, so we disable them
 // everywhere except newer clang/gcc or aarch64 where the inline assembly is
 // incompatible.
-#if LOCAL_CLANG_PREREQ(3, 8) || LOCAL_GCC_PREREQ(4, 9) || WEBP_AARCH64
+#if LOCAL_CLANG_PREREQ(3,8) || LOCAL_GCC_PREREQ(4,9) || defined(__aarch64__)
 #define WEBP_USE_INTRINSICS   // use intrinsics when possible
 #endif

@@ -46,7 +46,7 @@
 // if using intrinsics, this flag avoids some functions that make gcc-4.6.3
 // crash ("internal compiler error: in immed_double_const, at emit-rtl.").
 // (probably similar to gcc.gnu.org/bugzilla/show_bug.cgi?id=48183)
-#if !(LOCAL_CLANG_PREREQ(3, 8) || LOCAL_GCC_PREREQ(4, 8) || WEBP_AARCH64)
+#if !(LOCAL_CLANG_PREREQ(3,8) || LOCAL_GCC_PREREQ(4,8) || defined(__aarch64__))
 #define WORK_AROUND_GCC
 #endif

--- a/src/dsp/quant.h
+++ b/src/dsp/quant.h
@@ -21,15 +21,10 @@

 #define IsFlat IsFlat_NEON

-static uint32_t horizontal_add_uint32x4(const uint32x4_t a) {
-#if WEBP_AARCH64
-  return vaddvq_u32(a);
-#else
+static uint32x2_t horizontal_add_uint32x4(const uint32x4_t a) {
  const uint64x2_t b = vpaddlq_u32(a);
-  const uint32x2_t c = vadd_u32(vreinterpret_u32_u64(vget_low_u64(b)),
-                                vreinterpret_u32_u64(vget_high_u64(b)));
-  return vget_lane_u32(c, 0);
-#endif
+  return vadd_u32(vreinterpret_u32_u64(vget_low_u64(b)),
+                  vreinterpret_u32_u64(vget_high_u64(b)));
 }

 static WEBP_INLINE int IsFlat(const int16_t* levels, int num_blocks,
@@ -50,7 +45,7 @@ static WEBP_INLINE int IsFlat(const int16_t* levels, int num_blocks,

    levels += 16;
  }
-  return thresh >= (int)horizontal_add_uint32x4(sum);
+  return thresh >= (int32_t)vget_lane_u32(horizontal_add_uint32x4(sum), 0);
 }

 #else
--- a/src/dsp/rescaler.c
+++ b/src/dsp/rescaler.c
@@ -197,7 +197,6 @@ WebPRescalerImportRowFunc WebPRescalerImportRowShrink;
 WebPRescalerExportRowFunc WebPRescalerExportRowExpand;
 WebPRescalerExportRowFunc WebPRescalerExportRowShrink;

-extern VP8CPUInfo VP8GetCPUInfo;
 extern void WebPRescalerDspInitSSE2(void);
 extern void WebPRescalerDspInitMIPS32(void);
 extern void WebPRescalerDspInitMIPSdspR2(void);
--- a/src/dsp/rescaler_sse2.c
+++ b/src/dsp/rescaler_sse2.c
@@ -85,7 +85,7 @@ static void RescalerImportRowExpand_SSE2(WebPRescaler* const wrk,
      const __m128i mult = _mm_cvtsi32_si128(((x_add - accum) << 16) | accum);
      const __m128i out = _mm_madd_epi16(cur_pixels, mult);
      assert(sizeof(*frow) == sizeof(uint32_t));
-      WebPInt32ToMem((uint8_t*)frow, _mm_cvtsi128_si32(out));
+      WebPUint32ToMem((uint8_t*)frow, _mm_cvtsi128_si32(out));
      frow += 1;
      if (frow >= frow_end) break;
      accum -= wrk->x_sub;
@@ -132,7 +132,7 @@ static void RescalerImportRowShrink_SSE2(WebPRescaler* const wrk,
    __m128i base = zero;
    accum += wrk->x_add;
    while (accum > 0) {
-      const __m128i A = _mm_cvtsi32_si128(WebPMemToInt32(src));
+      const __m128i A = _mm_cvtsi32_si128(WebPMemToUint32(src));
      src += 4;
      base = _mm_unpacklo_epi8(A, zero);
      // To avoid overflow, we need: base * x_add / x_sub < 32768
@@ -198,7 +198,7 @@ static WEBP_INLINE void ProcessRow_SSE2(const __m128i* const A0,
                                        const __m128i* const mult,
                                        uint8_t* const dst) {
  const __m128i rounder = _mm_set_epi32(0, ROUNDER, 0, ROUNDER);
-  const __m128i mask = _mm_set_epi32(~0, 0, ~0, 0);
+  const __m128i mask = _mm_set_epi32(0xffffffffu, 0, 0xffffffffu, 0);
  const __m128i B0 = _mm_mul_epu32(*A0, *mult);
  const __m128i B1 = _mm_mul_epu32(*A1, *mult);
  const __m128i B2 = _mm_mul_epu32(*A2, *mult);
--- a/src/dsp/ssim.c
+++ b/src/dsp/ssim.c
@@ -137,7 +137,6 @@ VP8SSIMGetClippedFunc VP8SSIMGetClipped;
 VP8AccumulateSSEFunc VP8AccumulateSSE;
 #endif

-extern VP8CPUInfo VP8GetCPUInfo;
 extern void VP8SSIMDspInitSSE2(void);

 WEBP_DSP_INIT_FUNC(VP8SSIMDspInit) {
--- a/src/dsp/upsampling.c
+++ b/src/dsp/upsampling.c
@@ -215,7 +215,6 @@ static void EmptyYuv444Func(const uint8_t* y,

 WebPYUV444Converter WebPYUV444Converters[MODE_LAST];

-extern VP8CPUInfo VP8GetCPUInfo;
 extern void WebPInitYUV444ConvertersMIPSdspR2(void);
 extern void WebPInitYUV444ConvertersSSE2(void);
 extern void WebPInitYUV444ConvertersSSE41(void);
--- a/src/dsp/upsampling_neon.c
+++ b/src/dsp/upsampling_neon.c
@@ -111,7 +111,7 @@ static const int16_t kCoeffs1[4] = { 19077, 26149, 6419, 13320 };
  vst4_u8(out, v255_r_g_b);                                             \
 } while (0)

-#if (WEBP_SWAP_16BIT_CSP == 0)
+#if !defined(WEBP_SWAP_16BIT_CSP)
 #define ZIP_U8(lo, hi) vzip_u8((lo), (hi))
 #else
 #define ZIP_U8(lo, hi) vzip_u8((hi), (lo))
--- a/src/dsp/upsampling_sse2.c
+++ b/src/dsp/upsampling_sse2.c
@@ -121,7 +121,7 @@ static void FUNC_NAME(const uint8_t* top_y, const uint8_t* bottom_y,           \
  int uv_pos, pos;                                                             \
  /* 16byte-aligned array to cache reconstructed u and v */                    \
  uint8_t uv_buf[14 * 32 + 15] = { 0 };                                        \
-  uint8_t* const r_u = (uint8_t*)((uintptr_t)(uv_buf + 15) & ~(uintptr_t)15);  \
+  uint8_t* const r_u = (uint8_t*)((uintptr_t)(uv_buf + 15) & ~15);             \
  uint8_t* const r_v = r_u + 32;                                               \
                                                                               \
  assert(top_y != NULL);                                                       \
--- a/src/dsp/yuv.c
+++ b/src/dsp/yuv.c
@@ -70,7 +70,6 @@ void WebPSamplerProcessPlane(const uint8_t* y, int y_stride,

 WebPSamplerRowFunc WebPSamplers[MODE_LAST];

-extern VP8CPUInfo VP8GetCPUInfo;
 extern void WebPInitSamplersSSE2(void);
 extern void WebPInitSamplersSSE41(void);
 extern void WebPInitSamplersMIPS32(void);
--- a/src/dsp/yuv_sse2.c
+++ b/src/dsp/yuv_sse2.c
@@ -15,12 +15,10 @@

 #if defined(WEBP_USE_SSE2)

+#include "src/dsp/common_sse2.h"
 #include <stdlib.h>
 #include <emmintrin.h>

-#include "src/dsp/common_sse2.h"
-#include "src/utils/utils.h"
-
 //-----------------------------------------------------------------------------
 // Convert spans of 32 pixels to various RGB formats for the fancy upsampler.

@@ -76,7 +74,7 @@ static WEBP_INLINE __m128i Load_HI_16_SSE2(const uint8_t* src) {
 // Load and replicate the U/V samples
 static WEBP_INLINE __m128i Load_UV_HI_8_SSE2(const uint8_t* src) {
  const __m128i zero = _mm_setzero_si128();
-  const __m128i tmp0 = _mm_cvtsi32_si128(WebPMemToInt32(src));
+  const __m128i tmp0 = _mm_cvtsi32_si128(*(const uint32_t*)src);
  const __m128i tmp1 = _mm_unpacklo_epi8(zero, tmp0);
  return _mm_unpacklo_epi16(tmp1, tmp1);   // replicate samples
 }
@@ -132,7 +130,7 @@ static WEBP_INLINE void PackAndStore4444_SSE2(const __m128i* const R,
  const __m128i rg0 = _mm_packus_epi16(*B, *A);
  const __m128i ba0 = _mm_packus_epi16(*R, *G);
 #endif
-  const __m128i mask_0xf0 = _mm_set1_epi8((char)0xf0);
+  const __m128i mask_0xf0 = _mm_set1_epi8(0xf0);
  const __m128i rb1 = _mm_unpacklo_epi8(rg0, ba0);  // rbrbrbrbrb...
  const __m128i ga1 = _mm_unpackhi_epi8(rg0, ba0);  // gagagagaga...
  const __m128i rb2 = _mm_and_si128(rb1, mask_0xf0);
@@ -149,10 +147,9 @@ static WEBP_INLINE void PackAndStore565_SSE2(const __m128i* const R,
  const __m128i r0 = _mm_packus_epi16(*R, *R);
  const __m128i g0 = _mm_packus_epi16(*G, *G);
  const __m128i b0 = _mm_packus_epi16(*B, *B);
-  const __m128i r1 = _mm_and_si128(r0, _mm_set1_epi8((char)0xf8));
+  const __m128i r1 = _mm_and_si128(r0, _mm_set1_epi8(0xf8));
  const __m128i b1 = _mm_and_si128(_mm_srli_epi16(b0, 3), _mm_set1_epi8(0x1f));
-  const __m128i g1 =
-      _mm_srli_epi16(_mm_and_si128(g0, _mm_set1_epi8((char)0xe0)), 5);
+  const __m128i g1 = _mm_srli_epi16(_mm_and_si128(g0, _mm_set1_epi8(0xe0)), 5);
  const __m128i g2 = _mm_slli_epi16(_mm_and_si128(g0, _mm_set1_epi8(0x1c)), 3);
  const __m128i rg = _mm_or_si128(r1, g1);
  const __m128i gb = _mm_or_si128(g2, b1);
--- a/src/dsp/yuv_sse41.c
+++ b/src/dsp/yuv_sse41.c
@@ -15,12 +15,10 @@

 #if defined(WEBP_USE_SSE41)

+#include "src/dsp/common_sse41.h"
 #include <stdlib.h>
 #include <smmintrin.h>

-#include "src/dsp/common_sse41.h"
-#include "src/utils/utils.h"
-
 //-----------------------------------------------------------------------------
 // Convert spans of 32 pixels to various RGB formats for the fancy upsampler.

@@ -76,7 +74,7 @@ static WEBP_INLINE __m128i Load_HI_16_SSE41(const uint8_t* src) {
 // Load and replicate the U/V samples
 static WEBP_INLINE __m128i Load_UV_HI_8_SSE41(const uint8_t* src) {
  const __m128i zero = _mm_setzero_si128();
-  const __m128i tmp0 = _mm_cvtsi32_si128(WebPMemToInt32(src));
+  const __m128i tmp0 = _mm_cvtsi32_si128(*(const uint32_t*)src);
  const __m128i tmp1 = _mm_unpacklo_epi8(zero, tmp0);
  return _mm_unpacklo_epi16(tmp1, tmp1);   // replicate samples
 }
--- a/src/enc/alpha_enc.c
+++ b/src/enc/alpha_enc.c
@@ -13,7 +13,6 @@

 #include <assert.h>
 #include <stdlib.h>
-#include <string.h>

 #include "src/enc/vp8i_enc.h"
 #include "src/dsp/dsp.h"
@@ -141,11 +140,6 @@ static int EncodeAlphaInternal(const uint8_t* const data, int width, int height,
                              !reduce_levels, &tmp_bw, &result->stats);
    if (ok) {
      output = VP8LBitWriterFinish(&tmp_bw);
-      if (tmp_bw.error_) {
-        VP8LBitWriterWipeOut(&tmp_bw);
-        memset(&result->bw, 0, sizeof(result->bw));
-        return 0;
-      }
      output_size = VP8LBitWriterNumBytes(&tmp_bw);
      if (output_size > data_size) {
        // compressed size is larger than source! Revert to uncompressed mode.
@@ -154,7 +148,6 @@ static int EncodeAlphaInternal(const uint8_t* const data, int width, int height,
      }
    } else {
      VP8LBitWriterWipeOut(&tmp_bw);
-      memset(&result->bw, 0, sizeof(result->bw));
      return 0;
    }
  }
@@ -169,7 +162,7 @@ static int EncodeAlphaInternal(const uint8_t* const data, int width, int height,
  header = method | (filter << 2);
  if (reduce_levels) header |= ALPHA_PREPROCESSED_LEVELS << 4;

-  if (!VP8BitWriterInit(&result->bw, ALPHA_HEADER_LEN + output_size)) ok = 0;
+  VP8BitWriterInit(&result->bw, ALPHA_HEADER_LEN + output_size);
  ok = ok && VP8BitWriterAppend(&result->bw, &header, ALPHA_HEADER_LEN);
  ok = ok && VP8BitWriterAppend(&result->bw, output, output_size);

@@ -319,11 +312,11 @@ static int EncodeAlpha(VP8Encoder* const enc,
  assert(filter >= WEBP_FILTER_NONE && filter <= WEBP_FILTER_FAST);

  if (quality < 0 || quality > 100) {
-    return WebPEncodingSetError(pic, VP8_ENC_ERROR_INVALID_CONFIGURATION);
+    return 0;
  }

  if (method < ALPHA_NO_COMPRESSION || method > ALPHA_LOSSLESS_COMPRESSION) {
-    return WebPEncodingSetError(pic, VP8_ENC_ERROR_INVALID_CONFIGURATION);
+    return 0;
  }

  if (method == ALPHA_NO_COMPRESSION) {
@@ -333,7 +326,7 @@ static int EncodeAlpha(VP8Encoder* const enc,

  quant_alpha = (uint8_t*)WebPSafeMalloc(1ULL, data_size);
  if (quant_alpha == NULL) {
-    return WebPEncodingSetError(pic, VP8_ENC_ERROR_OUT_OF_MEMORY);
+    return 0;
  }

  // Extract alpha data (width x height) from raw_data (stride x height).
@@ -353,9 +346,6 @@ static int EncodeAlpha(VP8Encoder* const enc,
    ok = ApplyFiltersAndEncode(quant_alpha, width, height, data_size, method,
                               filter, reduce_levels, effort_level, output,
                               output_size, pic->stats);
-    if (!ok) {
-      WebPEncodingSetError(pic, VP8_ENC_ERROR_OUT_OF_MEMORY);  // imprecise
-    }
 #if !defined(WEBP_DISABLE_STATS)
    if (pic->stats != NULL) {  // need stats?
      pic->stats->coded_size += (int)(*output_size);
@@ -415,7 +405,7 @@ int VP8EncStartAlpha(VP8Encoder* const enc) {
      WebPWorker* const worker = &enc->alpha_worker_;
      // Makes sure worker is good to go.
      if (!WebPGetWorkerInterface()->Reset(worker)) {
-        return WebPEncodingSetError(enc->pic_, VP8_ENC_ERROR_OUT_OF_MEMORY);
+        return 0;
      }
      WebPGetWorkerInterface()->Launch(worker);
      return 1;
--- a/src/enc/analysis_enc.c
+++ b/src/enc/analysis_enc.c
@@ -391,14 +391,12 @@ static int DoSegmentsJob(void* arg1, void* arg2) {
  return ok;
 }

-#ifdef WEBP_USE_THREAD
 static void MergeJobs(const SegmentJob* const src, SegmentJob* const dst) {
  int i;
  for (i = 0; i <= MAX_ALPHA; ++i) dst->alphas[i] += src->alphas[i];
  dst->alpha += src->alpha;
  dst->uv_alpha += src->uv_alpha;
 }
-#endif

 // initialize the job struct with some tasks to perform
 static void InitSegmentJob(VP8Encoder* const enc, SegmentJob* const job,
@@ -427,10 +425,10 @@ int VP8EncAnalyze(VP8Encoder* const enc) {
      (enc->method_ <= 1);  // for method 0 - 1, we need preds_[] to be filled.
  if (do_segments) {
    const int last_row = enc->mb_h_;
-    const int total_mb = last_row * enc->mb_w_;
-#ifdef WEBP_USE_THREAD
    // We give a little more than a half work to the main thread.
    const int split_row = (9 * last_row + 15) >> 4;
+    const int total_mb = last_row * enc->mb_w_;
+#ifdef WEBP_USE_THREAD
    const int kMinSplitRow = 2;  // minimal rows needed for mt to be worth it
    const int do_mt = (enc->thread_level_ > 0) && (split_row >= kMinSplitRow);
 #else
@@ -440,7 +438,6 @@ int VP8EncAnalyze(VP8Encoder* const enc) {
        WebPGetWorkerInterface();
    SegmentJob main_job;
    if (do_mt) {
-#ifdef WEBP_USE_THREAD
      SegmentJob side_job;
      // Note the use of '&' instead of '&&' because we must call the functions
      // no matter what.
@@ -458,7 +455,6 @@ int VP8EncAnalyze(VP8Encoder* const enc) {
      }
      worker_interface->End(&side_job.worker);
      if (ok) MergeJobs(&side_job, &main_job);  // merge results together
-#endif  // WEBP_USE_THREAD
    } else {
      // Even for single-thread case, we use the generic Worker tools.
      InitSegmentJob(enc, &main_job, 0, last_row);
@@ -474,10 +470,6 @@ int VP8EncAnalyze(VP8Encoder* const enc) {
  } else {   // Use only one default segment.
    ResetAllMBInfo(enc);
  }
-  if (!ok) {
-    return WebPEncodingSetError(enc->pic_,
-                                VP8_ENC_ERROR_OUT_OF_MEMORY);  // imprecise
-  }
  return ok;
 }

--- a/src/enc/backward_references_enc.c
+++ b/src/enc/backward_references_enc.c
@@ -283,7 +283,8 @@ int VP8LHashChainFill(VP8LHashChain* const p, int quality,
  hash_to_first_index =
      (int32_t*)WebPSafeMalloc(HASH_SIZE, sizeof(*hash_to_first_index));
  if (hash_to_first_index == NULL) {
-    return WebPEncodingSetError(pic, VP8_ENC_ERROR_OUT_OF_MEMORY);
+    WebPEncodingSetError(pic, VP8_ENC_ERROR_OUT_OF_MEMORY);
+    return 0;
  }

  percent_range = remaining_percent / 2;
@@ -1049,7 +1050,8 @@ int VP8LGetBackwardReferences(
    refs_best = GetBackwardReferencesLowEffort(
        width, height, argb, cache_bits_best, hash_chain, refs);
    if (refs_best == NULL) {
-      return WebPEncodingSetError(pic, VP8_ENC_ERROR_OUT_OF_MEMORY);
+      WebPEncodingSetError(pic, VP8_ENC_ERROR_OUT_OF_MEMORY);
+      return 0;
    }
    // Set it in first position.
    BackwardRefsSwap(refs_best, &refs[0]);
@@ -1057,7 +1059,8 @@ int VP8LGetBackwardReferences(
    if (!GetBackwardReferences(width, height, argb, quality, lz77_types_to_try,
                               cache_bits_max, do_no_cache, hash_chain, refs,
                               cache_bits_best)) {
-      return WebPEncodingSetError(pic, VP8_ENC_ERROR_OUT_OF_MEMORY);
+      WebPEncodingSetError(pic, VP8_ENC_ERROR_OUT_OF_MEMORY);
+      return 0;
    }
  }

--- a/src/enc/frame_enc.c
+++ b/src/enc/frame_enc.c
@@ -689,7 +689,7 @@ static int PreLoopInitialize(VP8Encoder* const enc) {
  }
  if (!ok) {
    VP8EncFreeBitWriters(enc);  // malloc error occurred
-    return WebPEncodingSetError(enc->pic_, VP8_ENC_ERROR_OUT_OF_MEMORY);
+    WebPEncodingSetError(enc->pic_, VP8_ENC_ERROR_OUT_OF_MEMORY);
  }
  return ok;
 }
@@ -719,7 +719,6 @@ static int PostLoopFinalize(VP8EncIterator* const it, int ok) {
  } else {
    // Something bad happened -> need to do some memory cleanup.
    VP8EncFreeBitWriters(enc);
-    return WebPEncodingSetError(enc->pic_, VP8_ENC_ERROR_OUT_OF_MEMORY);
  }
  return ok;
 }
@@ -755,11 +754,6 @@ int VP8EncLoop(VP8Encoder* const enc) {
    // *then* decide how to code the skip decision if there's one.
    if (!VP8Decimate(&it, &info, rd_opt) || dont_use_skip) {
      CodeResiduals(it.bw_, &it, &info);
-      if (it.bw_->error_) {
-        // enc->pic_->error_code is set in PostLoopFinalize().
-        ok = 0;
-        break;
-      }
    } else {   // reset predictors after a skip
      ResetAfterSkip(&it);
    }
--- a/src/enc/picture_csp_enc.c
+++ b/src/enc/picture_csp_enc.c
@@ -69,12 +69,10 @@ static int CheckNonOpaque(const uint8_t* alpha, int width, int height,
 int WebPPictureHasTransparency(const WebPPicture* picture) {
  if (picture == NULL) return 0;
  if (picture->use_argb) {
-    if (picture->argb != NULL) {
-      return CheckNonOpaque((const uint8_t*)picture->argb + ALPHA_OFFSET,
-                            picture->width, picture->height,
-                            4, picture->argb_stride * sizeof(*picture->argb));
-    }
-    return 0;
+    const int alpha_offset = ALPHA_OFFSET;
+    return CheckNonOpaque((const uint8_t*)picture->argb + alpha_offset,
+                          picture->width, picture->height,
+                          4, picture->argb_stride * sizeof(*picture->argb));
  }
  return CheckNonOpaque(picture->a, picture->width, picture->height,
                        1, picture->a_stride);
@@ -98,7 +96,6 @@ static int kLinearToGammaTab[GAMMA_TAB_SIZE + 1];
 static uint16_t kGammaToLinearTab[256];
 static volatile int kGammaTablesOk = 0;
 static void InitGammaTables(void);
-extern VP8CPUInfo VP8GetCPUInfo;

 WEBP_DSP_INIT_FUNC(InitGammaTables) {
  if (!kGammaTablesOk) {
@@ -173,6 +170,21 @@ static const int kMinDimensionIterativeConversion = 4;
 //------------------------------------------------------------------------------
 // Main function

+extern void SharpYuvInit(VP8CPUInfo cpu_info_func);
+
+static void SafeInitSharpYuv(void) {
+#if defined(WEBP_USE_THREAD) && !defined(_WIN32)
+  static pthread_mutex_t initsharpyuv_lock = PTHREAD_MUTEX_INITIALIZER;
+  if (pthread_mutex_lock(&initsharpyuv_lock)) return;
+#endif
+
+  SharpYuvInit(VP8GetCPUInfo);
+
+#if defined(WEBP_USE_THREAD) && !defined(_WIN32)
+  (void)pthread_mutex_unlock(&initsharpyuv_lock);
+#endif
+}
+
 static int PreprocessARGB(const uint8_t* r_ptr,
                          const uint8_t* g_ptr,
                          const uint8_t* b_ptr,
@@ -469,8 +481,6 @@ static WEBP_INLINE void ConvertRowsToUV(const uint16_t* rgb,
  }
 }

-extern void SharpYuvInit(VP8CPUInfo cpu_info_func);
-
 static int ImportYUVAFromRGBA(const uint8_t* r_ptr,
                              const uint8_t* g_ptr,
                              const uint8_t* b_ptr,
@@ -506,7 +516,7 @@ static int ImportYUVAFromRGBA(const uint8_t* r_ptr,
  }

  if (use_iterative_conversion) {
-    SharpYuvInit(VP8GetCPUInfo);
+    SafeInitSharpYuv();
    if (!PreprocessARGB(r_ptr, g_ptr, b_ptr, step, rgb_stride, picture)) {
      return 0;
    }
@@ -535,9 +545,7 @@ static int ImportYUVAFromRGBA(const uint8_t* r_ptr,
    WebPInitConvertARGBToYUV();
    InitGammaTables();

-    if (tmp_rgb == NULL) {
-      return WebPEncodingSetError(picture, VP8_ENC_ERROR_OUT_OF_MEMORY);
-    }
+    if (tmp_rgb == NULL) return 0;  // malloc error

    // Downsample Y/U/V planes, two rows at a time
    for (y = 0; y < (height >> 1); ++y) {
--- a/src/enc/picture_rescale_enc.c
+++ b/src/enc/picture_rescale_enc.c
@@ -137,9 +137,7 @@ int WebPPictureCrop(WebPPicture* pic,
  PictureGrabSpecs(pic, &tmp);
  tmp.width = width;
  tmp.height = height;
-  if (!WebPPictureAlloc(&tmp)) {
-    return WebPEncodingSetError(pic, tmp.error_code);
-  }
+  if (!WebPPictureAlloc(&tmp)) return 0;

  if (!pic->use_argb) {
    const int y_offset = top * pic->y_stride + left;
@@ -214,28 +212,26 @@ int WebPPictureRescale(WebPPicture* picture, int width, int height) {
  prev_height = picture->height;
  if (!WebPRescalerGetScaledDimensions(
          prev_width, prev_height, &width, &height)) {
-    return WebPEncodingSetError(picture, VP8_ENC_ERROR_BAD_DIMENSION);
+    return 0;
  }

  PictureGrabSpecs(picture, &tmp);
  tmp.width = width;
  tmp.height = height;
-  if (!WebPPictureAlloc(&tmp)) {
-    return WebPEncodingSetError(picture, tmp.error_code);
-  }
+  if (!WebPPictureAlloc(&tmp)) return 0;

  if (!picture->use_argb) {
    work = (rescaler_t*)WebPSafeMalloc(2ULL * width, sizeof(*work));
    if (work == NULL) {
      WebPPictureFree(&tmp);
-      return WebPEncodingSetError(picture, VP8_ENC_ERROR_OUT_OF_MEMORY);
+      return 0;
    }
    // If present, we need to rescale alpha first (for AlphaMultiplyY).
    if (picture->a != NULL) {
      WebPInitAlphaProcessing();
      if (!RescalePlane(picture->a, prev_width, prev_height, picture->a_stride,
                        tmp.a, width, height, tmp.a_stride, work, 1)) {
-        return WebPEncodingSetError(picture, VP8_ENC_ERROR_BAD_DIMENSION);
+        return 0;
      }
    }

@@ -250,14 +246,14 @@ int WebPPictureRescale(WebPPicture* picture, int width, int height) {
        !RescalePlane(picture->v, HALVE(prev_width), HALVE(prev_height),
                      picture->uv_stride, tmp.v, HALVE(width), HALVE(height),
                      tmp.uv_stride, work, 1)) {
-      return WebPEncodingSetError(picture, VP8_ENC_ERROR_BAD_DIMENSION);
+      return 0;
    }
    AlphaMultiplyY(&tmp, 1);
  } else {
    work = (rescaler_t*)WebPSafeMalloc(2ULL * width * 4, sizeof(*work));
    if (work == NULL) {
      WebPPictureFree(&tmp);
-      return WebPEncodingSetError(picture, VP8_ENC_ERROR_OUT_OF_MEMORY);
+      return 0;
    }
    // In order to correctly interpolate colors, we need to apply the alpha
    // weighting first (black-matting), scale the RGB values, and remove
@@ -267,7 +263,7 @@ int WebPPictureRescale(WebPPicture* picture, int width, int height) {
    if (!RescalePlane((const uint8_t*)picture->argb, prev_width, prev_height,
                      picture->argb_stride * 4, (uint8_t*)tmp.argb, width,
                      height, tmp.argb_stride * 4, work, 4)) {
-      return WebPEncodingSetError(picture, VP8_ENC_ERROR_BAD_DIMENSION);
+      return 0;
    }
    AlphaMultiplyARGB(&tmp, 1);
  }
--- a/src/enc/syntax_enc.c
+++ b/src/enc/syntax_enc.c
@@ -258,10 +258,7 @@ static int EmitPartitionsSize(const VP8Encoder* const enc,
    buf[3 * p + 1] = (part_size >>  8) & 0xff;
    buf[3 * p + 2] = (part_size >> 16) & 0xff;
  }
-  if (p && !pic->writer(buf, 3 * p, pic)) {
-    return WebPEncodingSetError(pic, VP8_ENC_ERROR_BAD_WRITE);
-  }
-  return 1;
+  return p ? pic->writer(buf, 3 * p, pic) : 1;
 }

 //------------------------------------------------------------------------------
@@ -384,7 +381,6 @@ int VP8EncWrite(VP8Encoder* const enc) {

  enc->coded_size_ = (int)(CHUNK_HEADER_SIZE + riff_size);
  ok = ok && WebPReportProgress(pic, final_percent, &enc->percent_);
-  if (!ok) WebPEncodingSetError(pic, VP8_ENC_ERROR_BAD_WRITE);
  return ok;
 }

--- a/src/enc/vp8i_enc.h
+++ b/src/enc/vp8i_enc.h
@@ -31,8 +31,8 @@ extern "C" {

 // version numbers
 #define ENC_MAJ_VERSION 1
-#define ENC_MIN_VERSION 3
-#define ENC_REV_VERSION 2
+#define ENC_MIN_VERSION 2
+#define ENC_REV_VERSION 3

 enum { MAX_LF_LEVELS = 64,       // Maximum loop filter level
       MAX_VARIABLE_LEVEL = 67,  // last (inclusive) level with variable cost
--- a/Show More
+++ b/Show More