AuroraMiddleware/VulkanMemoryAllocator
1
0
Fork 0
mirror of https://github.com/GPUOpen-LibrariesAndSDKs/VulkanMemoryAllocator synced 2024-11-05 04:10:06 +00:00
Code Issues Projects Releases Wiki Activity

Added new API for selecting preferred memory type: VMA_MEMORY_USAGE_AUTO, VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE, VMA_MEMORY_USAGE_AUTO_PREFER_HOST, VMA_ALLOCATION_CREATE_HOST_ACCESS_SEQUENTIAL_WRITE_BIT, VMA_ALLOCATION_CREATE_HOST_ACCESS_RANDOM_BIT, VMA_ALLOCATION_CREATE_HOST_ACCESS_ALLOW_TRANSFER_INSTEAD_BIT

Browse Source 
Old values like VMA_MEMORY_USAGE_GPU_ONLY still work as before, for backward compatibility.
Updated documentation accordingly.

Introduced a concept of mappable and non-mappable allocations - with VMA_MEMORY_USAGE_AUTO* an intent to map has to be specified using VMA_ALLOCATION_CREATE_HOST_ACCESS*.

Added mapping hysteresis logic (internal class VmaMappingHysteresis, config macro VMA_MAPPING_HYSTERESIS_ENABLED) that prevents too many calls vkMapMemory/vkUnmapMemory back and forth.

Internal improvement in VmaBlockVector::AllocatePage to try to keep mappable and non-mappable allocations separate.
This commit is contained in:
Adam Sawicki 2022-02-17 14:44:06 +01:00
parent b41615cfce
commit aee61b1d25
7 changed files with 1322 additions and 717 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

217
Doxyfile
View File

@ -1,4 +1,4 @@
# Doxyfile 1.9.1
# Doxyfile 1.9.2
# This file describes the settings to be used by the documentation system
# doxygen (www.doxygen.org) for a project.
@ -93,14 +93,6 @@ ALLOW_UNICODE_NAMES = NO
OUTPUT_LANGUAGE = English
# The OUTPUT_TEXT_DIRECTION tag is used to specify the direction in which all
# documentation generated by doxygen is written. Doxygen will use this
# information to generate all generated output in the proper direction.
# Possible values are: None, LTR, RTL and Context.
# The default value is: None.
OUTPUT_TEXT_DIRECTION = None
# If the BRIEF_MEMBER_DESC tag is set to YES, doxygen will include brief member
# descriptions after the members that are listed in the file and class
# documentation (similar to Javadoc). Set to NO to disable this.
@ -258,16 +250,16 @@ TAB_SIZE = 4
# the documentation. An alias has the form:
# name=value
# For example adding
# "sideeffect=@par Side Effects:\n"
# "sideeffect=@par Side Effects:^^"
# will allow you to put the command \sideeffect (or @sideeffect) in the
# documentation, which will result in a user-defined paragraph with heading
# "Side Effects:". You can put \n's in the value part of an alias to insert
# newlines (in the resulting output). You can put ^^ in the value part of an
# alias to insert a newline as if a physical newline was in the original file.
# When you need a literal { or } or , in the value part of an alias you have to
# escape them by means of a backslash (\), this can lead to conflicts with the
# commands \{ and \} for these it is advised to use the version @{ and @} or use
# a double escape (\\{ and \\})
# "Side Effects:". Note that you cannot put \n's in the value part of an alias
# to insert newlines (in the resulting output). You can put ^^ in the value part
# of an alias to insert a newline as if a physical newline was in the original
# file. When you need a literal { or } or , in the value part of an alias you
# have to escape them by means of a backslash (\), this can lead to conflicts
# with the commands \{ and \} for these it is advised to use the version @{ and
# @} or use a double escape (\\{ and \\})
ALIASES =
@ -312,8 +304,8 @@ OPTIMIZE_OUTPUT_SLICE = NO
# extension. Doxygen has a built-in mapping, but you can override or extend it
# using this tag. The format is ext=language, where ext is a file extension, and
# language is one of the parsers supported by doxygen: IDL, Java, JavaScript,
# Csharp (C#), C, C++, D, PHP, md (Markdown), Objective-C, Python, Slice, VHDL,
# Fortran (fixed format Fortran: FortranFixed, free formatted Fortran:
# Csharp (C#), C, C++, Lex, D, PHP, md (Markdown), Objective-C, Python, Slice,
# VHDL, Fortran (fixed format Fortran: FortranFixed, free formatted Fortran:
# FortranFree, unknown formatted Fortran: Fortran. In the later case the parser
# tries to guess whether the code is fixed or free formatted code, this is the
# default for Fortran type files). For instance to make doxygen treat .inc files
@ -466,7 +458,7 @@ LOOKUP_CACHE_SIZE = 0
# than 0 to get more control over the balance between CPU load and processing
# speed. At this moment only the input processing can be done using multiple
# threads. Since this is still an experimental feature the default is set to 1,
# which efficively disables parallel processing. Please report any issues you
# which effectively disables parallel processing. Please report any issues you
# encounter. Generating dot graphs in parallel is controlled by the
# DOT_NUM_THREADS setting.
# Minimum value: 0, maximum value: 32, default value: 1.
@ -610,6 +602,12 @@ HIDE_SCOPE_NAMES = NO
HIDE_COMPOUND_REFERENCE= NO
# If the SHOW_HEADERFILE tag is set to YES then the documentation for a class
# will show which file needs to be included to use the class.
# The default value is: YES.
SHOW_HEADERFILE = NO
# If the SHOW_INCLUDE_FILES tag is set to YES then doxygen will put a list of
# the files that are included by a file in the documentation of that file.
# The default value is: YES.
@ -767,7 +765,8 @@ FILE_VERSION_FILTER =
# output files in an output format independent way. To create the layout file
# that represents doxygen's defaults, run doxygen with the -l option. You can
# optionally specify a file name after the option, if omitted DoxygenLayout.xml
# will be used as the name of the layout file.
# will be used as the name of the layout file. See also section "Changing the
# layout of pages" for information.
#
# Note that if you run doxygen from a directory containing a file called
# DoxygenLayout.xml, doxygen will parse it automatically even if the LAYOUT_FILE
@ -813,18 +812,26 @@ WARNINGS = YES
WARN_IF_UNDOCUMENTED = YES
# If the WARN_IF_DOC_ERROR tag is set to YES, doxygen will generate warnings for
# potential errors in the documentation, such as not documenting some parameters
# in a documented function, or documenting parameters that don't exist or using
# markup commands wrongly.
# potential errors in the documentation, such as documenting some parameters in
# a documented function twice, or documenting parameters that don't exist or
# using markup commands wrongly.
# The default value is: YES.
WARN_IF_DOC_ERROR = YES
# If WARN_IF_INCOMPLETE_DOC is set to YES, doxygen will warn about incomplete
# function parameter documentation. If set to NO, doxygen will accept that some
# parameters have no documentation without warning.
# The default value is: YES.
WARN_IF_INCOMPLETE_DOC = YES
# This WARN_NO_PARAMDOC option can be enabled to get warnings for functions that
# are documented, but have no documentation for their parameters or return
# value. If set to NO, doxygen will only warn about wrong or incomplete
# parameter documentation, but not about the absence of documentation. If
# EXTRACT_ALL is set to YES then this flag will automatically be disabled.
# value. If set to NO, doxygen will only warn about wrong parameter
# documentation, but not about the absence of documentation. If EXTRACT_ALL is
# set to YES then this flag will automatically be disabled. See also
# WARN_IF_INCOMPLETE_DOC
# The default value is: NO.
WARN_NO_PARAMDOC = NO
@ -888,10 +895,10 @@ INPUT_ENCODING = UTF-8
#
# If left blank the following patterns are tested:*.c, *.cc, *.cxx, *.cpp,
# *.c++, *.java, *.ii, *.ixx, *.ipp, *.i++, *.inl, *.idl, *.ddl, *.odl, *.h,
# *.hh, *.hxx, *.hpp, *.h++, *.cs, *.d, *.php, *.php4, *.php5, *.phtml, *.inc,
# *.m, *.markdown, *.md, *.mm, *.dox (to be provided as doxygen C comment),
# *.py, *.pyw, *.f90, *.f95, *.f03, *.f08, *.f18, *.f, *.for, *.vhd, *.vhdl,
# *.ucf, *.qsf and *.ice.
# *.hh, *.hxx, *.hpp, *.h++, *.l, *.cs, *.d, *.php, *.php4, *.php5, *.phtml,
# *.inc, *.m, *.markdown, *.md, *.mm, *.dox (to be provided as doxygen C
# comment), *.py, *.pyw, *.f90, *.f95, *.f03, *.f08, *.f18, *.f, *.for, *.vhd,
# *.vhdl, *.ucf, *.qsf and *.ice.
FILE_PATTERNS = *.c \
*.cc \
@ -1159,9 +1166,11 @@ VERBATIM_HEADERS = NO
CLANG_ASSISTED_PARSING = NO
# If clang assisted parsing is enabled and the CLANG_ADD_INC_PATHS tag is set to
# YES then doxygen will add the directory of each input to the include path.
# If the CLANG_ASSISTED_PARSING tag is set to YES and the CLANG_ADD_INC_PATHS
# tag is set to YES then doxygen will add the directory of each input to the
# include path.
# The default value is: YES.
# This tag requires that the tag CLANG_ASSISTED_PARSING is set to YES.
CLANG_ADD_INC_PATHS = YES
@ -1296,7 +1305,7 @@ HTML_EXTRA_FILES =
# The HTML_COLORSTYLE_HUE tag controls the color of the HTML output. Doxygen
# will adjust the colors in the style sheet and background images according to
# this color. Hue is specified as an angle on a colorwheel, see
# this color. Hue is specified as an angle on a color-wheel, see
# https://en.wikipedia.org/wiki/Hue for more information. For instance the value
# 0 represents red, 60 is yellow, 120 is green, 180 is cyan, 240 is blue, 300
# purple, and 360 is red again.
@ -1306,7 +1315,7 @@ HTML_EXTRA_FILES =
HTML_COLORSTYLE_HUE = 220
# The HTML_COLORSTYLE_SAT tag controls the purity (or saturation) of the colors
# in the HTML output. For a value of 0 the output will use grayscales only. A
# in the HTML output. For a value of 0 the output will use gray-scales only. A
# value of 255 will produce the most vivid colors.
# Minimum value: 0, maximum value: 255, default value: 100.
# This tag requires that the tag GENERATE_HTML is set to YES.
@ -1413,8 +1422,12 @@ DOCSET_PUBLISHER_NAME = Publisher
# If the GENERATE_HTMLHELP tag is set to YES then doxygen generates three
# additional HTML index files: index.hhp, index.hhc, and index.hhk. The
# index.hhp is a project file that can be read by Microsoft's HTML Help Workshop
# (see:
# https://www.microsoft.com/en-us/download/details.aspx?id=21138) on Windows.
# on Windows. In the beginning of 2021 Microsoft took the original page, with
# a.o. the download links, offline the HTML help workshop was already many years
# in maintenance mode). You can download the HTML help workshop from the web
# archives at Installation executable (see:
# http://web.archive.org/web/20160201063255/http://download.microsoft.com/downlo
# ad/0/A/9/0A939EF6-E31C-430F-A3DF-DFAE7960D564/htmlhelp.exe).
#
# The HTML Help Workshop contains a compiler that can convert all HTML output
# generated by doxygen into a single compiled HTML file (.chm). Compiled HTML
@ -1573,16 +1586,28 @@ DISABLE_INDEX = NO
# to work a browser that supports JavaScript, DHTML, CSS and frames is required
# (i.e. any modern browser). Windows users are probably better off using the
# HTML help feature. Via custom style sheets (see HTML_EXTRA_STYLESHEET) one can
# further fine-tune the look of the index. As an example, the default style
# sheet generated by doxygen has an example that shows how to put an image at
# the root of the tree instead of the PROJECT_NAME. Since the tree basically has
# the same information as the tab index, you could consider setting
# DISABLE_INDEX to YES when enabling this option.
# further fine tune the look of the index (see "Fine-tuning the output"). As an
# example, the default style sheet generated by doxygen has an example that
# shows how to put an image at the root of the tree instead of the PROJECT_NAME.
# Since the tree basically has the same information as the tab index, you could
# consider setting DISABLE_INDEX to YES when enabling this option.
# The default value is: NO.
# This tag requires that the tag GENERATE_HTML is set to YES.
GENERATE_TREEVIEW = NO
# When both GENERATE_TREEVIEW and DISABLE_INDEX are set to YES, then the
# FULL_SIDEBAR option determines if the side bar is limited to only the treeview
# area (value NO) or if it should extend to the full height of the window (value
# YES). Setting this to YES gives a layout similar to
# https://docs.readthedocs.io with more room for contents, but less room for the
# project logo, title, and description. If either GENERATOR_TREEVIEW or
# DISABLE_INDEX is set to NO, this option has no effect.
# The default value is: NO.
# This tag requires that the tag GENERATE_HTML is set to YES.
FULL_SIDEBAR = NO
# The ENUM_VALUES_PER_LINE tag can be used to set the number of enum values that
# doxygen will group on one line in the generated HTML documentation.
#
@ -1655,11 +1680,29 @@ FORMULA_MACROFILE =
USE_MATHJAX = NO
# With MATHJAX_VERSION it is possible to specify the MathJax version to be used.
# Note that the different versions of MathJax have different requirements with
# regards to the different settings, so it is possible that also other MathJax
# settings have to be changed when switching between the different MathJax
# versions.
# Possible values are: MathJax_2 and MathJax_3.
# The default value is: MathJax_2.
# This tag requires that the tag USE_MATHJAX is set to YES.
MATHJAX_VERSION = MathJax_2
# When MathJax is enabled you can set the default output format to be used for
# the MathJax output. See the MathJax site (see:
# http://docs.mathjax.org/en/v2.7-latest/output.html) for more details.
# the MathJax output. For more details about the output format see MathJax
# version 2 (see:
# http://docs.mathjax.org/en/v2.7-latest/output.html) and MathJax version 3
# (see:
# http://docs.mathjax.org/en/latest/web/components/output.html).
# Possible values are: HTML-CSS (which is slower, but has the best
# compatibility), NativeMML (i.e. MathML) and SVG.
# compatibility. This is the name for Mathjax version 2, for MathJax version 3
# this will be translated into chtml), NativeMML (i.e. MathML. Only supported
# for NathJax 2. For MathJax version 3 chtml will be used instead.), chtml (This
# is the name for Mathjax version 3, for MathJax version 2 this will be
# translated into HTML-CSS) and SVG.
# The default value is: HTML-CSS.
# This tag requires that the tag USE_MATHJAX is set to YES.
@ -1672,15 +1715,21 @@ MATHJAX_FORMAT = HTML-CSS
# MATHJAX_RELPATH should be ../mathjax. The default value points to the MathJax
# Content Delivery Network so you can quickly see the result without installing
# MathJax. However, it is strongly recommended to install a local copy of
# MathJax from https://www.mathjax.org before deployment.
# The default value is: https://cdn.jsdelivr.net/npm/mathjax@2.
# MathJax from https://www.mathjax.org before deployment. The default value is:
# - in case of MathJax version 2: https://cdn.jsdelivr.net/npm/mathjax@2
# - in case of MathJax version 3: https://cdn.jsdelivr.net/npm/mathjax@3
# This tag requires that the tag USE_MATHJAX is set to YES.
MATHJAX_RELPATH = http://cdn.mathjax.org/mathjax/latest
# The MATHJAX_EXTENSIONS tag can be used to specify one or more MathJax
# extension names that should be enabled during MathJax rendering. For example
# for MathJax version 2 (see
# https://docs.mathjax.org/en/v2.7-latest/tex.html#tex-and-latex-extensions):
# MATHJAX_EXTENSIONS = TeX/AMSmath TeX/AMSsymbols
# For example for MathJax version 3 (see
# http://docs.mathjax.org/en/latest/input/tex/extensions/index.html):
# MATHJAX_EXTENSIONS = ams
# This tag requires that the tag USE_MATHJAX is set to YES.
MATHJAX_EXTENSIONS =
@ -1860,29 +1909,31 @@ PAPER_TYPE = a4
EXTRA_PACKAGES =
# The LATEX_HEADER tag can be used to specify a personal LaTeX header for the
# generated LaTeX document. The header should contain everything until the first
# chapter. If it is left blank doxygen will generate a standard header. See
# section "Doxygen usage" for information on how to let doxygen write the
# default header to a separate file.
# The LATEX_HEADER tag can be used to specify a user-defined LaTeX header for
# the generated LaTeX document. The header should contain everything until the
# first chapter. If it is left blank doxygen will generate a standard header. It
# is highly recommended to start with a default header using
# doxygen -w latex new_header.tex new_footer.tex new_stylesheet.sty
# and then modify the file new_header.tex. See also section "Doxygen usage" for
# information on how to generate the default header that doxygen normally uses.
#
# Note: Only use a user-defined header if you know what you are doing! The
# following commands have a special meaning inside the header: $title,
# $datetime, $date, $doxygenversion, $projectname, $projectnumber,
# $projectbrief, $projectlogo. Doxygen will replace $title with the empty
# string, for the replacement values of the other commands the user is referred
# to HTML_HEADER.
# Note: Only use a user-defined header if you know what you are doing!
# Note: The header is subject to change so you typically have to regenerate the
# default header when upgrading to a newer version of doxygen. The following
# commands have a special meaning inside the header (and footer): For a
# description of the possible markers and block names see the documentation.
# This tag requires that the tag GENERATE_LATEX is set to YES.
LATEX_HEADER =
# The LATEX_FOOTER tag can be used to specify a personal LaTeX footer for the
# generated LaTeX document. The footer should contain everything after the last
# chapter. If it is left blank doxygen will generate a standard footer. See
# The LATEX_FOOTER tag can be used to specify a user-defined LaTeX footer for
# the generated LaTeX document. The footer should contain everything after the
# last chapter. If it is left blank doxygen will generate a standard footer. See
# LATEX_HEADER for more information on how to generate a default footer and what
# special commands can be used inside the footer.
#
# Note: Only use a user-defined footer if you know what you are doing!
# special commands can be used inside the footer. See also section "Doxygen
# usage" for information on how to generate the default footer that doxygen
# normally uses. Note: Only use a user-defined footer if you know what you are
# doing!
# This tag requires that the tag GENERATE_LATEX is set to YES.
LATEX_FOOTER =
@ -1927,8 +1978,7 @@ USE_PDFLATEX = YES
# If the LATEX_BATCHMODE tag is set to YES, doxygen will add the \batchmode
# command to the generated LaTeX files. This will instruct LaTeX to keep running
# if errors occur, instead of asking the user for help. This option is also used
# when generating formulas in HTML.
# if errors occur, instead of asking the user for help.
# The default value is: NO.
# This tag requires that the tag GENERATE_LATEX is set to YES.
@ -1941,16 +1991,6 @@ LATEX_BATCHMODE = NO
LATEX_HIDE_INDICES = NO
# If the LATEX_SOURCE_CODE tag is set to YES then doxygen will include source
# code with syntax highlighting in the LaTeX output.
#
# Note that which sources are shown also depends on other settings such as
# SOURCE_BROWSER.
# The default value is: NO.
# This tag requires that the tag GENERATE_LATEX is set to YES.
LATEX_SOURCE_CODE = NO
# The LATEX_BIB_STYLE tag can be used to specify the style to use for the
# bibliography, e.g. plainnat, or ieeetr. See
# https://en.wikipedia.org/wiki/BibTeX and \cite for more info.
@ -2031,16 +2071,6 @@ RTF_STYLESHEET_FILE =
RTF_EXTENSIONS_FILE =
# If the RTF_SOURCE_CODE tag is set to YES then doxygen will include source code
# with syntax highlighting in the RTF output.
#
# Note that which sources are shown also depends on other settings such as
# SOURCE_BROWSER.
# The default value is: NO.
# This tag requires that the tag GENERATE_RTF is set to YES.
RTF_SOURCE_CODE = NO
#---------------------------------------------------------------------------
# Configuration options related to the man page output
#---------------------------------------------------------------------------
@ -2137,15 +2167,6 @@ GENERATE_DOCBOOK = NO
DOCBOOK_OUTPUT = docbook
# If the DOCBOOK_PROGRAMLISTING tag is set to YES, doxygen will include the
# program listings (including syntax highlighting and cross-referencing
# information) to the DOCBOOK output. Note that enabling this will significantly
# increase the size of the DOCBOOK output.
# The default value is: NO.
# This tag requires that the tag GENERATE_DOCBOOK is set to YES.
DOCBOOK_PROGRAMLISTING = NO
#---------------------------------------------------------------------------
# Configuration options for the AutoGen Definitions output
#---------------------------------------------------------------------------
@ -2262,7 +2283,7 @@ PREDEFINED = VMA_CALL_PRE= \
VMA_NULLABLE_NON_DISPATCHABLE= \
VMA_VULKAN_VERSION=1002000 \
VMA_EXTERNAL_MEMORY=1 \
VMA_MEMORY_PRIORITY=1 \
VMA_MEMORY_PRIORITY=1
# If the MACRO_EXPANSION and EXPAND_ONLY_PREDEF tags are set to YES then this
# tag can be used to specify a list of macro names that should be expanded. The
@ -2657,8 +2678,8 @@ GENERATE_LEGEND = YES
# If the DOT_CLEANUP tag is set to YES, doxygen will remove the intermediate
# files that are used to generate the various graphs.
#
# Note: This setting is not only used for dot files but also for msc and
# plantuml temporary files.
# Note: This setting is not only used for dot files but also for msc temporary
# files.
# The default value is: YES.
DOT_CLEANUP = YES

4
README.md
View File

@ -59,7 +59,7 @@ Additional features:
- Debug annotations: Associate string with name or opaque pointer to your own data with every allocation.
- JSON dump: Obtain a string in JSON format with detailed map of internal state, including list of allocations and gaps between them.
- Convert this JSON dump into a picture to visualize your memory. See [tools/VmaDumpVis](tools/VmaDumpVis/README.md).
- Debugging incorrect memory usage: Enable initialization of all allocated memory with a bit pattern to detect usage of uninitialized or freed memory. Enable validation of a magic number before and after every allocation to detect out-of-bounds memory corruption.
- Debugging incorrect memory usage: Enable initialization of all allocated memory with a bit pattern to detect usage of uninitialized or freed memory. Enable validation of a magic number after every allocation to detect out-of-bounds memory corruption.
- Support for interoperability with OpenGL.
- Virtual allocator: Interface for using core allocation algorithm to allocate any custom data, e.g. pieces of one large buffer.
@ -81,7 +81,7 @@ bufferInfo.size = 65536;
bufferInfo.usage = VK_BUFFER_USAGE_VERTEX_BUFFER_BIT | VK_BUFFER_USAGE_TRANSFER_DST_BIT;
VmaAllocationCreateInfo allocInfo = {};
allocInfo.usage = VMA_MEMORY_USAGE_GPU_ONLY;
allocInfo.usage = VMA_MEMORY_USAGE_AUTO;
VkBuffer buffer;
VmaAllocation allocation;

1552
include/vk_mem_alloc.h
View File

File diff suppressed because it is too large Load Diff

12
src/SparseBindingTest.cpp
View File

@ -146,8 +146,8 @@ void BaseImage::UploadContent()
srcBufCreateInfo.size = 4 * m_CreateInfo.extent.width * m_CreateInfo.extent.height;
VmaAllocationCreateInfo srcBufAllocCreateInfo = {};
srcBufAllocCreateInfo.usage = VMA_MEMORY_USAGE_CPU_ONLY;
srcBufAllocCreateInfo.flags = VMA_ALLOCATION_CREATE_MAPPED_BIT;
srcBufAllocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO;
srcBufAllocCreateInfo.flags = VMA_ALLOCATION_CREATE_HOST_ACCESS_SEQUENTIAL_WRITE_BIT | VMA_ALLOCATION_CREATE_MAPPED_BIT;
VkBuffer srcBuf = nullptr;
VmaAllocation srcBufAlloc = nullptr;
@ -261,8 +261,8 @@ void BaseImage::ValidateContent(RandomNumberGenerator& rand)
dstBufCreateInfo.size = valueCount * sizeof(uint32_t) * 3;
VmaAllocationCreateInfo dstBufAllocCreateInfo = {};
dstBufAllocCreateInfo.flags = VMA_ALLOCATION_CREATE_MAPPED_BIT;
dstBufAllocCreateInfo.usage = VMA_MEMORY_USAGE_GPU_TO_CPU;
dstBufAllocCreateInfo.flags = VMA_ALLOCATION_CREATE_HOST_ACCESS_RANDOM_BIT | VMA_ALLOCATION_CREATE_MAPPED_BIT;
dstBufAllocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO;
VkBuffer dstBuf = nullptr;
VmaAllocation dstBufAlloc = nullptr;
@ -438,7 +438,7 @@ void TraditionalImage::Init(RandomNumberGenerator& rand)
FillImageCreateInfo(rand);
VmaAllocationCreateInfo allocCreateInfo = {};
allocCreateInfo.usage = VMA_MEMORY_USAGE_GPU_ONLY;
allocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO;
// Default BEST_FIT is clearly better.
//allocCreateInfo.flags |= VMA_ALLOCATION_CREATE_STRATEGY_WORST_FIT_BIT;
@ -484,7 +484,7 @@ void SparseBindingImage::Init(RandomNumberGenerator& rand)
const uint32_t pageCount = (uint32_t)ceil_div<VkDeviceSize>(imageMemReq.size, pageSize);
VmaAllocationCreateInfo allocCreateInfo = {};
allocCreateInfo.usage = VMA_MEMORY_USAGE_GPU_ONLY;
allocCreateInfo.preferredFlags = VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT;
VkMemoryRequirements pageMemReq = imageMemReq;
pageMemReq.size = pageSize;

229
src/Tests.cpp
View File

@ -855,8 +855,8 @@ bool StagingBufferCollection::AcquireBuffer(VkDeviceSize size, VkBuffer& outBuff
bufCreateInfo.usage = VK_BUFFER_USAGE_TRANSFER_SRC_BIT | VK_BUFFER_USAGE_TRANSFER_DST_BIT;
VmaAllocationCreateInfo allocCreateInfo = {};
allocCreateInfo.usage = VMA_MEMORY_USAGE_CPU_ONLY;
allocCreateInfo.flags = VMA_ALLOCATION_CREATE_MAPPED_BIT;
allocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO;
allocCreateInfo.flags = VMA_ALLOCATION_CREATE_HOST_ACCESS_RANDOM_BIT | VMA_ALLOCATION_CREATE_MAPPED_BIT;
VmaAllocationInfo allocInfo;
VkResult res = vmaCreateBuffer(g_hAllocator, &bufCreateInfo, &allocCreateInfo, &bufInfo.Buffer, &bufInfo.Allocation, &allocInfo);
@ -1406,7 +1406,8 @@ void TestDefragmentationSimple()
bufCreateInfo.usage = VK_BUFFER_USAGE_TRANSFER_SRC_BIT;
VmaAllocationCreateInfo exampleAllocCreateInfo = {};
exampleAllocCreateInfo.usage = VMA_MEMORY_USAGE_CPU_ONLY;
exampleAllocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO;
exampleAllocCreateInfo.flags = VMA_ALLOCATION_CREATE_HOST_ACCESS_RANDOM_BIT;
uint32_t memTypeIndex = UINT32_MAX;
vmaFindMemoryTypeIndexForBufferInfo(g_hAllocator, &bufCreateInfo, &exampleAllocCreateInfo, &memTypeIndex);
@ -1595,7 +1596,8 @@ void TestDefragmentationWholePool()
bufCreateInfo.usage = VK_BUFFER_USAGE_TRANSFER_SRC_BIT;
VmaAllocationCreateInfo exampleAllocCreateInfo = {};
exampleAllocCreateInfo.usage = VMA_MEMORY_USAGE_CPU_ONLY;
exampleAllocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO;
exampleAllocCreateInfo.flags = VMA_ALLOCATION_CREATE_HOST_ACCESS_RANDOM_BIT;
uint32_t memTypeIndex = UINT32_MAX;
vmaFindMemoryTypeIndexForBufferInfo(g_hAllocator, &bufCreateInfo, &exampleAllocCreateInfo, &memTypeIndex);
@ -1770,7 +1772,7 @@ static void TestDefragmentationGpu()
VkBufferCreateInfo bufCreateInfo = { VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO };
VmaAllocationCreateInfo allocCreateInfo = {};
allocCreateInfo.usage = VMA_MEMORY_USAGE_GPU_ONLY;
allocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE;
allocCreateInfo.flags = 0;
// Create all intended buffers.
@ -2099,7 +2101,7 @@ static void TestDefragmentationIncrementalBasic()
imageInfo.samples = VK_SAMPLE_COUNT_1_BIT;
VmaAllocationCreateInfo allocCreateInfo = {};
allocCreateInfo.usage = VMA_MEMORY_USAGE_GPU_ONLY;
allocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE;
allocCreateInfo.flags = 0;
// Create all intended images.
@ -2283,7 +2285,7 @@ void TestDefragmentationIncrementalComplex()
imageInfo.samples = VK_SAMPLE_COUNT_1_BIT;
VmaAllocationCreateInfo allocCreateInfo = {};
allocCreateInfo.usage = VMA_MEMORY_USAGE_GPU_ONLY;
allocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE;
allocCreateInfo.flags = 0;
// Create all intended images.
@ -2484,7 +2486,7 @@ static void TestUserData()
void* pointerToSomething = &res;
VmaAllocationCreateInfo allocCreateInfo = {};
allocCreateInfo.usage = VMA_MEMORY_USAGE_CPU_ONLY;
allocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO;
allocCreateInfo.pUserData = numberAsPointer;
if(testIndex == 1)
allocCreateInfo.flags |= VMA_ALLOCATION_CREATE_DEDICATED_MEMORY_BIT;
@ -2514,7 +2516,7 @@ static void TestUserData()
strcpy_s(name1Buf, name1Len + 1, name1);
VmaAllocationCreateInfo allocCreateInfo = {};
allocCreateInfo.usage = VMA_MEMORY_USAGE_CPU_ONLY;
allocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO;
allocCreateInfo.flags = VMA_ALLOCATION_CREATE_USER_DATA_COPY_STRING_BIT;
allocCreateInfo.pUserData = name1Buf;
if(testIndex == 1)
@ -2549,7 +2551,6 @@ static void TestInvalidAllocations()
VkResult res;
VmaAllocationCreateInfo allocCreateInfo = {};
allocCreateInfo.usage = VMA_MEMORY_USAGE_CPU_ONLY;
// Try to allocate 0 bytes.
{
@ -2615,8 +2616,9 @@ static void TestMemoryRequirements()
TEST(res == VK_SUCCESS);
vmaDestroyBuffer(g_hAllocator, buf, alloc);
// Usage.
allocCreateInfo.usage = VMA_MEMORY_USAGE_CPU_ONLY;
// Usage = auto + host access.
allocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO;
allocCreateInfo.flags = VMA_ALLOCATION_CREATE_HOST_ACCESS_RANDOM_BIT;
allocCreateInfo.requiredFlags = 0;
allocCreateInfo.preferredFlags = 0;
allocCreateInfo.memoryTypeBits = UINT32_MAX;
@ -2628,6 +2630,7 @@ static void TestMemoryRequirements()
// Required flags, preferred flags.
allocCreateInfo.usage = VMA_MEMORY_USAGE_UNKNOWN;
allocCreateInfo.flags = 0;
allocCreateInfo.requiredFlags = VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT | VK_MEMORY_PROPERTY_HOST_COHERENT_BIT;
allocCreateInfo.preferredFlags = VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT | VK_MEMORY_PROPERTY_HOST_CACHED_BIT;
allocCreateInfo.memoryTypeBits = 0;
@ -2640,7 +2643,8 @@ static void TestMemoryRequirements()
// memoryTypeBits.
const uint32_t memType = allocInfo.memoryType;
allocCreateInfo.usage = VMA_MEMORY_USAGE_CPU_ONLY;
allocCreateInfo.usage = VMA_MEMORY_USAGE_UNKNOWN;
allocCreateInfo.flags = 0;
allocCreateInfo.requiredFlags = 0;
allocCreateInfo.preferredFlags = 0;
allocCreateInfo.memoryTypeBits = 1u << memType;
@ -2680,8 +2684,8 @@ static void TestBasics()
bufCreateInfo.size = 128;
VmaAllocationCreateInfo allocCreateInfo = {};
allocCreateInfo.usage = VMA_MEMORY_USAGE_GPU_ONLY;
allocCreateInfo.flags = VMA_ALLOCATION_CREATE_MAPPED_BIT;
allocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE;
allocCreateInfo.flags = VMA_ALLOCATION_CREATE_HOST_ACCESS_SEQUENTIAL_WRITE_BIT | VMA_ALLOCATION_CREATE_MAPPED_BIT;
VkBuffer buf; VmaAllocation alloc; VmaAllocationInfo allocInfo;
res = vmaCreateBuffer(g_hAllocator, &bufCreateInfo, &allocCreateInfo, &buf, &alloc, &allocInfo);
@ -2689,7 +2693,7 @@ static void TestBasics()
vmaDestroyBuffer(g_hAllocator, buf, alloc);
// Same with OWN_MEMORY.
// Same with DEDICATED_MEMORY.
allocCreateInfo.flags |= VMA_ALLOCATION_CREATE_DEDICATED_MEMORY_BIT;
res = vmaCreateBuffer(g_hAllocator, &bufCreateInfo, &allocCreateInfo, &buf, &alloc, &allocInfo);
@ -3023,11 +3027,15 @@ static void TestAllocationVersusResourceSize()
bufCreateInfo.usage = VK_BUFFER_USAGE_TRANSFER_SRC_BIT | VK_BUFFER_USAGE_TRANSFER_DST_BIT;
VmaAllocationCreateInfo allocCreateInfo = {};
allocCreateInfo.usage = VMA_MEMORY_USAGE_CPU_ONLY;
allocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO_PREFER_HOST;
allocCreateInfo.flags = VMA_ALLOCATION_CREATE_HOST_ACCESS_SEQUENTIAL_WRITE_BIT;
for(uint32_t i = 0; i < 2; ++i)
{
allocCreateInfo.flags = (i == 1) ? VMA_ALLOCATION_CREATE_DEDICATED_MEMORY_BIT : 0;
if(i == 1)
allocCreateInfo.flags |= VMA_ALLOCATION_CREATE_DEDICATED_MEMORY_BIT;
else
allocCreateInfo.flags &= ~VMA_ALLOCATION_CREATE_DEDICATED_MEMORY_BIT;
AllocInfo info;
info.CreateBuffer(bufCreateInfo, allocCreateInfo);
@ -3062,7 +3070,7 @@ static void TestPool_MinBlockCount()
static const VkDeviceSize BLOCK_SIZE = ALLOC_SIZE * 2; // Each block can fit 2 allocations.
VmaAllocationCreateInfo allocCreateInfo = {};
allocCreateInfo.usage = VMA_MEMORY_USAGE_CPU_COPY;
allocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO_PREFER_HOST;
VkBufferCreateInfo bufCreateInfo = { VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO };
bufCreateInfo.usage = VK_BUFFER_USAGE_TRANSFER_DST_BIT | VK_BUFFER_USAGE_TRANSFER_SRC_BIT;
@ -3133,7 +3141,7 @@ static void TestPool_MinAllocationAlignment()
static const VkDeviceSize MIN_ALLOCATION_ALIGNMENT = 64 * 1024;
VmaAllocationCreateInfo allocCreateInfo = {};
allocCreateInfo.usage = VMA_MEMORY_USAGE_CPU_COPY;
allocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO_PREFER_HOST;
VkBufferCreateInfo bufCreateInfo = { VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO };
bufCreateInfo.usage = VK_BUFFER_USAGE_TRANSFER_DST_BIT | VK_BUFFER_USAGE_TRANSFER_SRC_BIT;
@ -3340,7 +3348,7 @@ void TestHeapSizeLimit()
VmaAllocationInfo dedicatedAllocInfo;
{
VmaAllocationCreateInfo allocCreateInfo = {};
allocCreateInfo.usage = VMA_MEMORY_USAGE_GPU_ONLY;
allocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE;
allocCreateInfo.flags = VMA_ALLOCATION_CREATE_DEDICATED_MEMORY_BIT;
bufCreateInfo.size = BLOCK_SIZE / 2;
@ -3422,7 +3430,8 @@ static void TestDebugMargin()
bufInfo.size = 256; // Doesn't matter
VmaAllocationCreateInfo allocCreateInfo = {};
allocCreateInfo.usage = VMA_MEMORY_USAGE_CPU_ONLY;
allocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO_PREFER_HOST;
allocCreateInfo.flags = VMA_ALLOCATION_CREATE_HOST_ACCESS_RANDOM_BIT;
VmaPoolCreateInfo poolCreateInfo = {};
TEST(vmaFindMemoryTypeIndexForBufferInfo(
@ -3541,7 +3550,7 @@ static void TestLinearAllocator()
sampleBufCreateInfo.usage = VK_BUFFER_USAGE_TRANSFER_DST_BIT | VK_BUFFER_USAGE_VERTEX_BUFFER_BIT;
VmaAllocationCreateInfo sampleAllocCreateInfo = {};
sampleAllocCreateInfo.usage = VMA_MEMORY_USAGE_GPU_ONLY;
sampleAllocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE;
VmaPoolCreateInfo poolCreateInfo = {};
VkResult res = vmaFindMemoryTypeIndexForBufferInfo(g_hAllocator, &sampleBufCreateInfo, &sampleAllocCreateInfo, &poolCreateInfo.memoryTypeIndex);
@ -3857,7 +3866,7 @@ static void TestLinearAllocatorMultiBlock()
sampleBufCreateInfo.usage = VK_BUFFER_USAGE_TRANSFER_SRC_BIT;
VmaAllocationCreateInfo sampleAllocCreateInfo = {};
sampleAllocCreateInfo.usage = VMA_MEMORY_USAGE_CPU_ONLY;
sampleAllocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO_PREFER_HOST;
VmaPoolCreateInfo poolCreateInfo = {};
poolCreateInfo.flags = VMA_POOL_CREATE_LINEAR_ALGORITHM_BIT;
@ -4180,7 +4189,7 @@ static void ManuallyTestLinearAllocator()
sampleBufCreateInfo.usage = VK_BUFFER_USAGE_TRANSFER_DST_BIT | VK_BUFFER_USAGE_VERTEX_BUFFER_BIT;
VmaAllocationCreateInfo sampleAllocCreateInfo = {};
sampleAllocCreateInfo.usage = VMA_MEMORY_USAGE_GPU_ONLY;
sampleAllocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE;
VmaPoolCreateInfo poolCreateInfo = {};
VkResult res = vmaFindMemoryTypeIndexForBufferInfo(g_hAllocator, &sampleBufCreateInfo, &sampleAllocCreateInfo, &poolCreateInfo.memoryTypeIndex);
@ -4300,7 +4309,7 @@ static void BenchmarkAlgorithmsCase(FILE* file,
sampleBufCreateInfo.usage = VK_BUFFER_USAGE_TRANSFER_DST_BIT | VK_BUFFER_USAGE_VERTEX_BUFFER_BIT;
VmaAllocationCreateInfo sampleAllocCreateInfo = {};
sampleAllocCreateInfo.usage = VMA_MEMORY_USAGE_GPU_ONLY;
sampleAllocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE;
VmaPoolCreateInfo poolCreateInfo = {};
VkResult res = vmaFindMemoryTypeIndexForBufferInfo(g_hAllocator, &sampleBufCreateInfo, &sampleAllocCreateInfo, &poolCreateInfo.memoryTypeIndex);
@ -4447,7 +4456,7 @@ static void TestBufferDeviceAddress()
VK_BUFFER_USAGE_SHADER_DEVICE_ADDRESS_BIT; // !!!
VmaAllocationCreateInfo allocCreateInfo = {};
allocCreateInfo.usage = VMA_MEMORY_USAGE_GPU_ONLY;
allocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE;
for(uint32_t testIndex = 0; testIndex < 2; ++testIndex)
{
@ -4481,7 +4490,7 @@ static void TestMemoryPriority()
bufCreateInfo.usage = VK_BUFFER_USAGE_TRANSFER_DST_BIT | VK_BUFFER_USAGE_VERTEX_BUFFER_BIT;
VmaAllocationCreateInfo allocCreateInfo = {};
allocCreateInfo.usage = VMA_MEMORY_USAGE_GPU_ONLY;
allocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE;
allocCreateInfo.priority = 1.f;
for(uint32_t testIndex = 0; testIndex < 2; ++testIndex)
@ -4607,7 +4616,7 @@ static void TestPool_SameSize()
}
VmaAllocationCreateInfo poolAllocInfo = {};
poolAllocInfo.usage = VMA_MEMORY_USAGE_CPU_ONLY;
poolAllocInfo.requiredFlags = VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT | VK_MEMORY_PROPERTY_HOST_COHERENT_BIT | VK_MEMORY_PROPERTY_HOST_CACHED_BIT;
uint32_t memTypeIndex;
res = vmaFindMemoryTypeIndex(
g_hAllocator,
@ -4821,7 +4830,8 @@ static void TestAllocationsInitialization()
bufInfo.usage = VK_BUFFER_USAGE_TRANSFER_SRC_BIT;
VmaAllocationCreateInfo dummyBufAllocCreateInfo = {};
dummyBufAllocCreateInfo.usage = VMA_MEMORY_USAGE_CPU_ONLY;
dummyBufAllocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO;
dummyBufAllocCreateInfo.flags = VMA_ALLOCATION_CREATE_HOST_ACCESS_RANDOM_BIT;
VmaPoolCreateInfo poolCreateInfo = {};
poolCreateInfo.blockSize = BUF_SIZE * 10;
@ -4978,7 +4988,7 @@ static void TestPool_Benchmark(
while(memoryTypeBits)
{
VmaAllocationCreateInfo dummyAllocCreateInfo = {};
dummyAllocCreateInfo.usage = VMA_MEMORY_USAGE_GPU_ONLY;
dummyAllocCreateInfo.preferredFlags = VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT;
vmaFindMemoryTypeIndex(g_hAllocator, memoryTypeBits, &dummyAllocCreateInfo, &poolCreateInfo.memoryTypeIndex);
const uint32_t heapIndex = memProps->memoryTypes[poolCreateInfo.memoryTypeIndex].heapIndex;
@ -5667,7 +5677,7 @@ static void TestBudget()
bufInfo.usage = VK_BUFFER_USAGE_TRANSFER_DST_BIT;
VmaAllocationCreateInfo allocCreateInfo = {};
allocCreateInfo.usage = VMA_MEMORY_USAGE_GPU_ONLY;
allocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE;
if(testIndex == 0)
{
allocCreateInfo.flags |= VMA_ALLOCATION_CREATE_DEDICATED_MEMORY_BIT;
@ -5786,7 +5796,7 @@ static void TestAliasing()
img1MemReq.memoryTypeBits, img2MemReq.memoryTypeBits, finalMemReq.memoryTypeBits);
VmaAllocationCreateInfo allocCreateInfo = {};
allocCreateInfo.usage = VMA_MEMORY_USAGE_GPU_ONLY;
allocCreateInfo.preferredFlags = VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT;
VmaAllocation alloc = VK_NULL_HANDLE;
ERR_GUARD_VULKAN(vmaAllocateMemory(g_hAllocator, &finalMemReq, &allocCreateInfo, &alloc, nullptr));
@ -5830,7 +5840,7 @@ static void TestAllocationAliasing()
VmaAllocationCreateInfo allocationCreateInfo = {};
allocationCreateInfo.flags = VMA_ALLOCATION_CREATE_DEDICATED_MEMORY_BIT;
allocationCreateInfo.usage = VMA_MEMORY_USAGE_GPU_ONLY;
allocationCreateInfo.usage = VMA_MEMORY_USAGE_AUTO;
// Bind 2 textures together into same memory without VMA_ALLOCATION_CREATE_CAN_ALIAS_BIT and then with flag set
/*
@ -5909,7 +5919,8 @@ static void TestMapping()
bufInfo.usage = VK_BUFFER_USAGE_TRANSFER_SRC_BIT;
VmaAllocationCreateInfo allocCreateInfo = {};
allocCreateInfo.usage = VMA_MEMORY_USAGE_CPU_ONLY;
allocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO;
allocCreateInfo.flags = VMA_ALLOCATION_CREATE_HOST_ACCESS_RANDOM_BIT;
allocCreateInfo.pool = pool;
if(testIndex == TEST_DEDICATED)
allocCreateInfo.flags |= VMA_ALLOCATION_CREATE_DEDICATED_MEMORY_BIT;
@ -6059,7 +6070,8 @@ static void TestMappingMultithreaded()
bufCreateInfo.usage = VK_BUFFER_USAGE_TRANSFER_SRC_BIT;
VmaAllocationCreateInfo allocCreateInfo = {};
allocCreateInfo.usage = VMA_MEMORY_USAGE_CPU_ONLY;
allocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO;
allocCreateInfo.flags = VMA_ALLOCATION_CREATE_HOST_ACCESS_RANDOM_BIT;
allocCreateInfo.pool = pool;
if(testIndex == TEST_DEDICATED)
allocCreateInfo.flags |= VMA_ALLOCATION_CREATE_DEDICATED_MEMORY_BIT;
@ -6895,7 +6907,6 @@ static void BasicTestBuddyAllocator()
sampleBufCreateInfo.usage = VK_BUFFER_USAGE_TRANSFER_DST_BIT | VK_BUFFER_USAGE_VERTEX_BUFFER_BIT;
VmaAllocationCreateInfo sampleAllocCreateInfo = {};
sampleAllocCreateInfo.usage = VMA_MEMORY_USAGE_GPU_ONLY;
VmaPoolCreateInfo poolCreateInfo = {};
VkResult res = vmaFindMemoryTypeIndexForBufferInfo(g_hAllocator, &sampleBufCreateInfo, &sampleAllocCreateInfo, &poolCreateInfo.memoryTypeIndex);
@ -7000,7 +7011,8 @@ static void BasicTestAllocatePages()
sampleBufCreateInfo.usage = VK_BUFFER_USAGE_TRANSFER_SRC_BIT;
VmaAllocationCreateInfo sampleAllocCreateInfo = {};
sampleAllocCreateInfo.usage = VMA_MEMORY_USAGE_CPU_ONLY;
sampleAllocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO;
sampleAllocCreateInfo.flags = VMA_ALLOCATION_CREATE_HOST_ACCESS_SEQUENTIAL_WRITE_BIT;
VmaPoolCreateInfo poolCreateInfo = {};
VkResult res = vmaFindMemoryTypeIndexForBufferInfo(g_hAllocator, &sampleBufCreateInfo, &sampleAllocCreateInfo, &poolCreateInfo.memoryTypeIndex);
@ -7062,7 +7074,7 @@ static void BasicTestAllocatePages()
memReq.size = 4 * 1024;
VmaAllocationCreateInfo dedicatedAllocCreateInfo = {};
dedicatedAllocCreateInfo.usage = VMA_MEMORY_USAGE_CPU_ONLY;
dedicatedAllocCreateInfo.requiredFlags = VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT;
dedicatedAllocCreateInfo.flags = VMA_ALLOCATION_CREATE_MAPPED_BIT | VMA_ALLOCATION_CREATE_DEDICATED_MEMORY_BIT;
res = vmaAllocateMemoryPages(g_hAllocator, &memReq, &dedicatedAllocCreateInfo, allocCount, alloc.data(), allocInfo.data());
TEST(res == VK_SUCCESS);
@ -7104,7 +7116,7 @@ static void TestGpuData()
info.m_BufferInfo.size = 1024 * 1024 * (rand.Generate() % 9 + 1);
VmaAllocationCreateInfo allocCreateInfo = {};
allocCreateInfo.usage = VMA_MEMORY_USAGE_GPU_ONLY;
allocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO;
VkResult res = vmaCreateBuffer(g_hAllocator, &info.m_BufferInfo, &allocCreateInfo, &info.m_Buffer, &info.m_Allocation, nullptr);
TEST(res == VK_SUCCESS);
@ -7251,6 +7263,142 @@ static void TestVirtualBlocksAlgorithmsBenchmark()
}
}
static void TestMappingHysteresis()
{
/*
We have no way to check here if hysteresis worked as expected,
but at least we provoke some cases and make sure it doesn't crash or assert.
You can always check details with the debugger.
*/
wprintf(L"Test mapping hysteresis\n");
VkBufferCreateInfo bufCreateInfo = {VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO};
bufCreateInfo.usage = VK_BUFFER_USAGE_TRANSFER_SRC_BIT;
bufCreateInfo.size = 0x10000;
VmaAllocationCreateInfo templateAllocCreateInfo = {};
templateAllocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO;
templateAllocCreateInfo.flags = VMA_ALLOCATION_CREATE_HOST_ACCESS_SEQUENTIAL_WRITE_BIT;
VmaPoolCreateInfo poolCreateInfo = {};
poolCreateInfo.blockSize = 10 * MEGABYTE;
poolCreateInfo.minBlockCount = poolCreateInfo.maxBlockCount = 1;
TEST(vmaFindMemoryTypeIndexForBufferInfo(g_hAllocator,
&bufCreateInfo, &templateAllocCreateInfo, &poolCreateInfo.memoryTypeIndex) == VK_SUCCESS);
constexpr uint32_t BUF_COUNT = 30;
bool endOfScenarios = false;
for(uint32_t scenarioIndex = 0; !endOfScenarios; ++scenarioIndex)
{
VmaPool pool;
TEST(vmaCreatePool(g_hAllocator, &poolCreateInfo, &pool) == VK_SUCCESS);
BufferInfo buf;
VmaAllocationInfo allocInfo;
std::vector<BufferInfo> bufs;
// Scenario: Create + destroy buffers without mapping. Hysteresis should not launch.
if(scenarioIndex == 0)
{
VmaAllocationCreateInfo allocCreateInfo = {};
allocCreateInfo.pool = pool;
for(uint32_t bufIndex = 0; bufIndex < BUF_COUNT; ++bufIndex)
{
TEST(vmaCreateBuffer(g_hAllocator, &bufCreateInfo, &allocCreateInfo, &buf.Buffer, &buf.Allocation, &allocInfo) == VK_SUCCESS);
TEST(allocInfo.pMappedData == nullptr);
vmaDestroyBuffer(g_hAllocator, buf.Buffer, buf.Allocation);
}
}
// Scenario:
// - Create one buffer mapped that stays there.
// - Create + destroy mapped buffers back and forth. Hysteresis should launch.
else if(scenarioIndex == 1)
{
VmaAllocationCreateInfo allocCreateInfo = {};
allocCreateInfo.pool = pool;
allocCreateInfo.flags = VMA_ALLOCATION_CREATE_MAPPED_BIT;
TEST(vmaCreateBuffer(g_hAllocator, &bufCreateInfo, &allocCreateInfo, &buf.Buffer, &buf.Allocation, &allocInfo) == VK_SUCCESS);
TEST(allocInfo.pMappedData != nullptr);
bufs.push_back(buf);
for(uint32_t bufIndex = 0; bufIndex < BUF_COUNT; ++bufIndex)
{
TEST(vmaCreateBuffer(g_hAllocator, &bufCreateInfo, &allocCreateInfo, &buf.Buffer, &buf.Allocation, &allocInfo) == VK_SUCCESS);
TEST(allocInfo.pMappedData != nullptr);
vmaDestroyBuffer(g_hAllocator, buf.Buffer, buf.Allocation);
}
}
// Scenario: Create + destroy mapped buffers.
// Hysteresis should launch as it maps and unmaps back and forth.
else if(scenarioIndex == 2)
{
VmaAllocationCreateInfo allocCreateInfo = {};
allocCreateInfo.pool = pool;
allocCreateInfo.flags = VMA_ALLOCATION_CREATE_MAPPED_BIT;
for(uint32_t bufIndex = 0; bufIndex < BUF_COUNT; ++bufIndex)
{
TEST(vmaCreateBuffer(g_hAllocator, &bufCreateInfo, &allocCreateInfo, &buf.Buffer, &buf.Allocation, &allocInfo) == VK_SUCCESS);
TEST(allocInfo.pMappedData != nullptr);
vmaDestroyBuffer(g_hAllocator, buf.Buffer, buf.Allocation);
}
}
// Scenario: Create one buffer and map it back and forth. Hysteresis should launch.
else if(scenarioIndex == 3)
{
VmaAllocationCreateInfo allocCreateInfo = {};
allocCreateInfo.pool = pool;
TEST(vmaCreateBuffer(g_hAllocator, &bufCreateInfo, &allocCreateInfo, &buf.Buffer, &buf.Allocation, &allocInfo) == VK_SUCCESS);
for(uint32_t i = 0; i < BUF_COUNT; ++i)
{
void* mappedData = nullptr;
TEST(vmaMapMemory(g_hAllocator, buf.Allocation, &mappedData) == VK_SUCCESS);
TEST(mappedData != nullptr);
vmaUnmapMemory(g_hAllocator, buf.Allocation);
}
vmaDestroyBuffer(g_hAllocator, buf.Buffer, buf.Allocation);
}
// Scenario:
// - Create many buffers
// - Map + unmap one of them many times. Hysteresis should launch.
// - Hysteresis should unmap during freeing the buffers.
else if(scenarioIndex == 4)
{
VmaAllocationCreateInfo allocCreateInfo = {};
allocCreateInfo.pool = pool;
for(uint32_t bufIndex = 0; bufIndex < BUF_COUNT; ++bufIndex)
{
TEST(vmaCreateBuffer(g_hAllocator, &bufCreateInfo, &allocCreateInfo, &buf.Buffer, &buf.Allocation, &allocInfo) == VK_SUCCESS);
TEST(allocInfo.pMappedData == nullptr);
bufs.push_back(buf);
}
for(uint32_t i = 0; i < BUF_COUNT; ++i)
{
void* mappedData = nullptr;
TEST(vmaMapMemory(g_hAllocator, buf.Allocation, &mappedData) == VK_SUCCESS);
TEST(mappedData != nullptr);
vmaUnmapMemory(g_hAllocator, buf.Allocation);
}
}
else
endOfScenarios = true;
for(size_t i = bufs.size(); i--; )
vmaDestroyBuffer(g_hAllocator, bufs[i].Buffer, bufs[i].Allocation);
vmaDestroyPool(g_hAllocator, pool);
}
}
void Test()
{
wprintf(L"TESTING:\n");
@ -7288,6 +7436,7 @@ void Test()
TestAliasing();
TestAllocationAliasing();
TestMapping();
TestMappingHysteresis();
TestDeviceLocalMapped();
TestMappingMultithreaded();
TestLinearAllocator();

2
src/VmaUsage.h
View File

@ -57,7 +57,9 @@ include all public interface declarations. Example:
//#define VMA_USE_STL_SHARED_MUTEX 0
//#define VMA_MEMORY_BUDGET 0
//#define VMA_STATS_STRING_ENABLED 0
//#define VMA_MAPPING_HYSTERESIS_ENABLED 0
//#define VMA_VULKAN_VERSION 1003000 // Vulkan 1.3
#define VMA_VULKAN_VERSION 1002000 // Vulkan 1.2
//#define VMA_VULKAN_VERSION 1001000 // Vulkan 1.1
//#define VMA_VULKAN_VERSION 1000000 // Vulkan 1.0

23
src/VulkanSample.cpp
View File

@ -393,7 +393,9 @@ static VkExtent2D ChooseSwapExtent()
static constexpr uint32_t GetVulkanApiVersion()
{
#if VMA_VULKAN_VERSION == 1002000
#if VMA_VULKAN_VERSION == 1003000
return VK_API_VERSION_1_3;
#elif VMA_VULKAN_VERSION == 1002000
return VK_API_VERSION_1_2;
#elif VMA_VULKAN_VERSION == 1001000
return VK_API_VERSION_1_1;
@ -486,6 +488,7 @@ void VulkanUsage::Init()
case VK_API_VERSION_1_0: wprintf(L"1.0\n"); break;
case VK_API_VERSION_1_1: wprintf(L"1.1\n"); break;
case VK_API_VERSION_1_2: wprintf(L"1.2\n"); break;
case VK_API_VERSION_1_3: wprintf(L"1.3\n"); break;
default: assert(0);
}
@ -672,8 +675,8 @@ static void CreateMesh()
vbInfo.sharingMode = VK_SHARING_MODE_EXCLUSIVE;
VmaAllocationCreateInfo vbAllocCreateInfo = {};
vbAllocCreateInfo.usage = VMA_MEMORY_USAGE_CPU_ONLY;
vbAllocCreateInfo.flags = VMA_ALLOCATION_CREATE_MAPPED_BIT;
vbAllocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO;
vbAllocCreateInfo.flags = VMA_ALLOCATION_CREATE_HOST_ACCESS_SEQUENTIAL_WRITE_BIT | VMA_ALLOCATION_CREATE_MAPPED_BIT;
VkBuffer stagingVertexBuffer = VK_NULL_HANDLE;
VmaAllocation stagingVertexBufferAlloc = VK_NULL_HANDLE;
@ -685,7 +688,6 @@ static void CreateMesh()
// No need to flush stagingVertexBuffer memory because CPU_ONLY memory is always HOST_COHERENT.
vbInfo.usage = VK_BUFFER_USAGE_TRANSFER_DST_BIT | VK_BUFFER_USAGE_VERTEX_BUFFER_BIT;
vbAllocCreateInfo.usage = VMA_MEMORY_USAGE_GPU_ONLY;
vbAllocCreateInfo.flags = 0;
ERR_GUARD_VULKAN( vmaCreateBuffer(g_hAllocator, &vbInfo, &vbAllocCreateInfo, &g_hVertexBuffer, &g_hVertexBufferAlloc, nullptr) );
@ -697,8 +699,8 @@ static void CreateMesh()
ibInfo.sharingMode = VK_SHARING_MODE_EXCLUSIVE;
VmaAllocationCreateInfo ibAllocCreateInfo = {};
ibAllocCreateInfo.usage = VMA_MEMORY_USAGE_CPU_ONLY;
ibAllocCreateInfo.flags = VMA_ALLOCATION_CREATE_MAPPED_BIT;
ibAllocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO;
ibAllocCreateInfo.flags = VMA_ALLOCATION_CREATE_HOST_ACCESS_SEQUENTIAL_WRITE_BIT | VMA_ALLOCATION_CREATE_MAPPED_BIT;
VkBuffer stagingIndexBuffer = VK_NULL_HANDLE;
VmaAllocation stagingIndexBufferAlloc = VK_NULL_HANDLE;
@ -710,7 +712,6 @@ static void CreateMesh()
// No need to flush stagingIndexBuffer memory because CPU_ONLY memory is always HOST_COHERENT.
ibInfo.usage = VK_BUFFER_USAGE_TRANSFER_DST_BIT | VK_BUFFER_USAGE_INDEX_BUFFER_BIT;
ibAllocCreateInfo.usage = VMA_MEMORY_USAGE_GPU_ONLY;
ibAllocCreateInfo.flags = 0;
ERR_GUARD_VULKAN( vmaCreateBuffer(g_hAllocator, &ibInfo, &ibAllocCreateInfo, &g_hIndexBuffer, &g_hIndexBufferAlloc, nullptr) );
@ -747,8 +748,8 @@ static void CreateTexture(uint32_t sizeX, uint32_t sizeY)
stagingBufInfo.usage = VK_BUFFER_USAGE_TRANSFER_SRC_BIT;
VmaAllocationCreateInfo stagingBufAllocCreateInfo = {};
stagingBufAllocCreateInfo.usage = VMA_MEMORY_USAGE_CPU_ONLY;
stagingBufAllocCreateInfo.flags = VMA_ALLOCATION_CREATE_MAPPED_BIT;
stagingBufAllocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO;
stagingBufAllocCreateInfo.flags = VMA_ALLOCATION_CREATE_HOST_ACCESS_SEQUENTIAL_WRITE_BIT | VMA_ALLOCATION_CREATE_MAPPED_BIT;
VkBuffer stagingBuf = VK_NULL_HANDLE;
VmaAllocation stagingBufAlloc = VK_NULL_HANDLE;
@ -792,7 +793,7 @@ static void CreateTexture(uint32_t sizeX, uint32_t sizeY)
imageInfo.flags = 0;
VmaAllocationCreateInfo imageAllocCreateInfo = {};
imageAllocCreateInfo.usage = VMA_MEMORY_USAGE_GPU_ONLY;
imageAllocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO;
ERR_GUARD_VULKAN( vmaCreateImage(g_hAllocator, &imageInfo, &imageAllocCreateInfo, &g_hTextureImage, &g_hTextureImageAlloc, nullptr) );
@ -1021,7 +1022,7 @@ static void CreateSwapchain()
depthImageInfo.flags = 0;
VmaAllocationCreateInfo depthImageAllocCreateInfo = {};
depthImageAllocCreateInfo.usage = VMA_MEMORY_USAGE_GPU_ONLY;
depthImageAllocCreateInfo.usage = VMA_MEMORY_USAGE_AUTO;
ERR_GUARD_VULKAN( vmaCreateImage(g_hAllocator, &depthImageInfo, &depthImageAllocCreateInfo, &g_hDepthImage, &g_hDepthImageAlloc, nullptr) );