#include <OgreHlmsComputeJob.h>

Inheritance diagram for Ogre::HlmsComputeJob:

Public Types
enum	ThreadGroupsBasedOn { ThreadGroupsBasedOnNothing , ThreadGroupsBasedOnTexture , ThreadGroupsBasedOnUav }

Public Types inherited from Ogre::TextureGpuListener
enum	Reason { Unknown , FromStorageToSysRam , FromSysRamToStorage , GainedResidency , LostResidency , PoolTextureSlotChanged , ResidentToSysRamSync , MetadataCacheOutOfDate , ExceptionThrown , FsaaSettingAlteredByApi , ReadyForRendering , Deleted }

Public Member Functions
	HlmsComputeJob (IdString name, Hlms *creator, const String &sourceFilename, const StringVector &includedPieceFiles)

	~HlmsComputeJob () override

void	_calculateNumThreadGroupsBasedOnSetting ()
	INTERNAL USE. More...

uint8	_getRawGlTexSlotStart () const

ShaderParams *	_getShaderParams (IdString key)
	Gets a shader parameter with the given key. More...

void	_setSamplerblock (uint8 slotIdx, const HlmsSamplerblock *refParams)
	Sets a samplerblock directly. More...

void	_setUavBuffer (uint8 slotIdx, const DescriptorSetUav::BufferSlot &newSlot)
	Sets an UAV buffer at the given slot ID. More...

void	_setUavTexture (uint8 slotIdx, const DescriptorSetUav::TextureSlot &texSlot)
	Sets an UAV texture. More...

void	_updateAutoProperties ()

void	analyzeBarriers (ResourceTransitionArray &resourceTransitions, bool clearBarriers=true)
	Checks every regular texture and every UAV (texture and buffers) bound and resolves transitions. More...

void	clearTexBuffers ()
	Sets all texture buffers to nullptr. More...

void	clearUavBuffers ()
	Sets all UAV buffers to nullptr. More...

HlmsComputeJob *	clone (const String &cloneName)

void	cloneTo (HlmsComputeJob *dstJob)

void	createShaderParams (IdString key)
	Creates a set of shader paramters with a given key, e.g. More...

Hlms *	getCreator () const

uint8	getGlTexSlotStart () const

IdString	getName () const

String	getNameStr () const

size_t	getNumSamplerUnits () const
	See setNumSamplerUnits. More...

size_t	getNumTexUnits () const

const uint32 *	getNumThreadGroups () const

uint32	getNumThreadGroupsX () const

uint32	getNumThreadGroupsY () const

uint32	getNumThreadGroupsZ () const

size_t	getNumUavUnits () const

int32	getProperty (IdString key, int32 defaultVal=0) const

ShaderParams &	getShaderParams (IdString key)
	Gets a shader parameter with the given key. More...

TextureGpu *	getTexture (uint8 slotIdx) const

const uint32 *	getThreadsPerGroup () const

uint32	getThreadsPerGroupX () const

uint32	getThreadsPerGroupY () const

uint32	getThreadsPerGroupZ () const

UavBufferPacked *	getUavBuffer (uint8 slotIdx) const

TextureGpu *	getUavTexture (uint8 slotIdx) const

void	notifyTextureChanged (TextureGpu texture, TextureGpuListener::Reason reason, void extraData) override
	Called when a TextureGpu changed in a way that affects how it is displayed: More...

void	removePiece (IdString pieceName)
	Removes an existing piece. More...

void	removeTexUnit (uint8 slotIdx)
	Destroys a given texture unit, displacing all the higher tex units. More...

void	removeUavUnit (uint8 slotIdx)
	Destroys a given texture unit, displacing all the higher tex units. More...

void	setConstBuffer (uint8 slotIdx, ConstBufferPacked *constBuffer)
	Sets a const/uniform bufferat the given slot ID. More...

void	setGlTexSlotStart (uint8 texSlotStart)
	By default HlmsComputeJob::setTexture and HlmsComputeJob::setTexBuffer are in range [0; getNumTexUnits) More...

void	setInformHlmsOfTextureData (bool bInformHlms)
	The Hlms has the ability to pass data to the shader source code via its syntax system to add hardcoded values. More...

void	setNumSamplerUnits (uint8 numSlots)
	This value is overriden by setNumTexUnits to be compatible with OpenGL. More...

void	setNumTexUnits (uint8 numSlots)
	Creates 'numSlots' number of slots before they can be set. More...

void	setNumThreadGroups (uint32 numThreadGroupsX, uint32 numThreadGroupsY, uint32 numThreadGroupsZ)
	Sets the number of groups of threads to dispatch. More...

void	setNumThreadGroupsBasedOn (ThreadGroupsBasedOn source, uint8 texSlot, uint8 divisorX, uint8 divisorY, uint8 divisorZ)
	Instead of calling setNumThreadGroups, Ogre can automatically deduce them based on the Texture resolution and the threads per group. More...

void	setNumUavUnits (uint8 numSlots)
	Creates 'numSlots' number of slots before they can be set. More...

void	setPiece (IdString pieceName, const String &pieceContent)
	Defines a piece, i.e. More...

void	setProperty (IdString key, int32 value)
	Sets an arbitrary property to pass to the shader. More...

void	setSamplerblock (uint8 slotIdx, const HlmsSamplerblock &refParams)
	Sets a samplerblock based on reference parameters. More...

void	setTexBuffer (uint8 slotIdx, const DescriptorSetTexture2::BufferSlot &newSlot)
	Sets a texture buffer at the given slot ID. More...

void	setTexture (uint8 slotIdx, const DescriptorSetTexture2::TextureSlot &newSlot, const HlmsSamplerblock *refParams=0, bool bSetSampler=true)
	Sets a texture buffer at the given slot ID. More...

void	setThreadsPerGroup (uint32 threadsPerGroupX, uint32 threadsPerGroupY, uint32 threadsPerGroupZ)
	Sets the number of threads per group. More...

void	setupRootLayout (RootLayout &rootLayout)

Public Member Functions inherited from Ogre::TextureGpuListener
virtual	~TextureGpuListener ()

virtual bool	shouldStayLoaded (TextureGpu *texture)
	Return true if this TextureGpu should likely stay loaded or else graphical changes could occur. More...

Member Enumeration Documentation

◆ ThreadGroupsBasedOn

enum Ogre::HlmsComputeJob::ThreadGroupsBasedOn

Enumerator
ThreadGroupsBasedOnNothing	Disabled. (obey setNumThreadGroups)
ThreadGroupsBasedOnTexture	Based the number of thread groups on a texture. See setNumThreadGroupsBasedOn.
ThreadGroupsBasedOnUav	Based the number of thread groups on a UAV. See setNumThreadGroupsBasedOn.

Constructor & Destructor Documentation

◆ HlmsComputeJob()

Ogre::HlmsComputeJob::HlmsComputeJob	(	IdString	name,
		Hlms *	creator,
		const String &	sourceFilename,
		const StringVector &	includedPieceFiles
	)

◆ ~HlmsComputeJob()

Ogre::HlmsComputeJob::~HlmsComputeJob ( )

override

Member Function Documentation

◆ _calculateNumThreadGroupsBasedOnSetting()

void Ogre::HlmsComputeJob::_calculateNumThreadGroupsBasedOnSetting ( )

INTERNAL USE.

Calculates the number of thread groups as specified in setNumThreadGroupsBasedOn, overriding setNumThreadGroups.

◆ _getRawGlTexSlotStart()

uint8 Ogre::HlmsComputeJob::_getRawGlTexSlotStart ( ) const

◆ _getShaderParams()

ShaderParams* Ogre::HlmsComputeJob::_getShaderParams ( IdString key )

Gets a shader parameter with the given key.

e.g. "default" "glsl" "hlsl". Returns null if doesn't exist. See createShaderParams

◆ _setSamplerblock()

void Ogre::HlmsComputeJob::_setSamplerblock	(	uint8	slotIdx,
		const HlmsSamplerblock *	refParams
	)

Sets a samplerblock directly.

For internal use / advanced users.

Parameters

slotIdx See setNumTexUnits.

Must be in range [0; getNumTexUnits) regardless of what getTexSlotStart is

Parameters

refParams	Direct samplerblock. Reference count is assumed to already have been increased. We won't increase it ourselves.
params	The sampler block to use as reference.

◆ _setUavBuffer()

void Ogre::HlmsComputeJob::_setUavBuffer	(	uint8	slotIdx,
		const DescriptorSetUav::BufferSlot &	newSlot
	)

Sets an UAV buffer at the given slot ID.

Remarks: UAV slots are shared with setUavTexture. Calling this function will remove the settings from previous setUavTexture calls to the same slot index.

: May trigger a recompilation if setInformHlmsOfTextureData is enabled.

: Be very careful when calling this directly. The Compositor needs to evaluate memory barriers and resource transitions. Leaving inconsistent memory barriers can result in hazards/race conditions in some APIs. If in doubt, change the CompositorPassComputeDef instead.

Parameters

slotIdx	See setNumUavUnits. The slot index to bind this UAV buffer.
newSlot

◆ _setUavTexture()

void Ogre::HlmsComputeJob::_setUavTexture	(	uint8	slotIdx,
		const DescriptorSetUav::TextureSlot &	texSlot
	)

Sets an UAV texture.

Remarks: UAV buffer slots are shared with setUavTexture's. Calling this function will remove the settings from previous setUavBuffer calls to the same slot index.

: May trigger a recompilation if setInformHlmsOfTextureData is enabled.

: Be very careful when calling this directly. The Compositor needs to evaluate memory barriers and resource transitions. Leaving inconsistent memory barriers can result in hazards/race conditions in some APIs. If in doubt, change the CompositorPassComputeDef instead.

Parameters

slot	See setNumUavUnits.

◆ _updateAutoProperties()

void Ogre::HlmsComputeJob::_updateAutoProperties ( )

◆ analyzeBarriers()

void Ogre::HlmsComputeJob::analyzeBarriers	(	ResourceTransitionArray &	resourceTransitions,
		bool	clearBarriers = `true`
	)

Checks every regular texture and every UAV (texture and buffers) bound and resolves transitions.

Parameters

resourceTransitions

◆ clearTexBuffers()

void Ogre::HlmsComputeJob::clearTexBuffers ( )

Sets all texture buffers to nullptr.

◆ clearUavBuffers()

void Ogre::HlmsComputeJob::clearUavBuffers ( )

Sets all UAV buffers to nullptr.

◆ clone()

HlmsComputeJob* Ogre::HlmsComputeJob::clone ( const String & cloneName )

◆ cloneTo()

void Ogre::HlmsComputeJob::cloneTo ( HlmsComputeJob * dstJob )

◆ createShaderParams()

void Ogre::HlmsComputeJob::createShaderParams ( IdString key )

Creates a set of shader paramters with a given key, e.g.

"default" "glsl" "hlsl". Does nothing if parameters already exist.

◆ getCreator()

Hlms* Ogre::HlmsComputeJob::getCreator ( ) const

inline

◆ getGlTexSlotStart()

uint8 Ogre::HlmsComputeJob::getGlTexSlotStart ( ) const

◆ getName()

IdString Ogre::HlmsComputeJob::getName ( ) const

inline

◆ getNameStr()

String Ogre::HlmsComputeJob::getNameStr ( ) const

◆ getNumSamplerUnits()

size_t Ogre::HlmsComputeJob::getNumSamplerUnits ( ) const

inline

See setNumSamplerUnits.

◆ getNumTexUnits()

size_t Ogre::HlmsComputeJob::getNumTexUnits ( ) const

inline

◆ getNumThreadGroups()

const uint32* Ogre::HlmsComputeJob::getNumThreadGroups ( ) const

inline

◆ getNumThreadGroupsX()

uint32 Ogre::HlmsComputeJob::getNumThreadGroupsX ( ) const

inline

◆ getNumThreadGroupsY()

uint32 Ogre::HlmsComputeJob::getNumThreadGroupsY ( ) const

inline

◆ getNumThreadGroupsZ()

uint32 Ogre::HlmsComputeJob::getNumThreadGroupsZ ( ) const

inline

◆ getNumUavUnits()

size_t Ogre::HlmsComputeJob::getNumUavUnits ( ) const

inline

◆ getProperty()

int32 Ogre::HlmsComputeJob::getProperty	(	IdString	key,
		int32	defaultVal = `0`
	)		const

◆ getShaderParams()

ShaderParams& Ogre::HlmsComputeJob::getShaderParams ( IdString key )

Gets a shader parameter with the given key.

e.g. "default" "glsl" "hlsl". Creates if does not exist.

◆ getTexture()

TextureGpu* Ogre::HlmsComputeJob::getTexture ( uint8 slotIdx ) const

◆ getThreadsPerGroup()

const uint32* Ogre::HlmsComputeJob::getThreadsPerGroup ( ) const

inline

◆ getThreadsPerGroupX()

uint32 Ogre::HlmsComputeJob::getThreadsPerGroupX ( ) const

inline

◆ getThreadsPerGroupY()

uint32 Ogre::HlmsComputeJob::getThreadsPerGroupY ( ) const

inline

◆ getThreadsPerGroupZ()

uint32 Ogre::HlmsComputeJob::getThreadsPerGroupZ ( ) const

inline

◆ getUavBuffer()

UavBufferPacked* Ogre::HlmsComputeJob::getUavBuffer ( uint8 slotIdx ) const

◆ getUavTexture()

TextureGpu* Ogre::HlmsComputeJob::getUavTexture ( uint8 slotIdx ) const

◆ notifyTextureChanged()

void Ogre::HlmsComputeJob::notifyTextureChanged	(	TextureGpu *	texture,
		TextureGpuListener::Reason	reason,
		void *	extraData
	)

overridevirtual

Called when a TextureGpu changed in a way that affects how it is displayed:

TextureGpu::notifyDataIsReady got called (texture is ready to be displayed)
Texture changed residency status.
Texture is being deleted. It won't be a valid pointer after this call.

Implements Ogre::TextureGpuListener.

◆ removePiece()

void Ogre::HlmsComputeJob::removePiece ( IdString pieceName )

Removes an existing piece.

See setPiece. Does nothing if the piece didn't exist.

◆ removeTexUnit()

void Ogre::HlmsComputeJob::removeTexUnit ( uint8 slotIdx )

Destroys a given texture unit, displacing all the higher tex units.

◆ removeUavUnit()

void Ogre::HlmsComputeJob::removeUavUnit ( uint8 slotIdx )

Destroys a given texture unit, displacing all the higher tex units.

◆ setConstBuffer()

void Ogre::HlmsComputeJob::setConstBuffer	(	uint8	slotIdx,
		ConstBufferPacked *	constBuffer
	)

Sets a const/uniform bufferat the given slot ID.

Parameters

slotIdx	Slot to bind to. It's independent from the texture & UAV ones.
constBuffer	Const buffer to bind.

◆ setGlTexSlotStart()

void Ogre::HlmsComputeJob::setGlTexSlotStart ( uint8 texSlotStart )

By default HlmsComputeJob::setTexture and HlmsComputeJob::setTexBuffer are in range [0; getNumTexUnits)

However this allows you to offset the range to [texSlotStart; texSlotStart + getNumTexUnits)

This is useful when ReadOnlyBuffers are bound via setTexBuffers, because in OpenGL these will map to uav buffer slots, thus overlapping/conflicting with UAVs

Parameters

texSlotStart The offset at which the textures/texbuffers should start being bound

◆ setInformHlmsOfTextureData()

void Ogre::HlmsComputeJob::setInformHlmsOfTextureData ( bool bInformHlms )

The Hlms has the ability to pass data to the shader source code via its syntax system to add hardcoded values.

For example, you may want to unroll a loop based on the width of a texture for maximum performance.

: Enabling this feature informs the Hlms to reparse the shader on any change to bound textures that could trigger a recompilation. If you don't need it, keep this feature disabled to prevent unnecessary recompilations.

Parameters

bInformHlms True to enable this feature, false to disable.

◆ setNumSamplerUnits()

void Ogre::HlmsComputeJob::setNumSamplerUnits ( uint8 numSlots )

This value is overriden by setNumTexUnits to be compatible with OpenGL.

However you can later override this behavior to minimize the number of samplers by shrinking (or enlarging?) the sampler units.

This is an advanced function. Don't use it unless you're careful not to assume 1 tex unit = 1 sampler unit

◆ setNumTexUnits()

void Ogre::HlmsComputeJob::setNumTexUnits ( uint8 numSlots )

Creates 'numSlots' number of slots before they can be set.

◆ setNumThreadGroups()

void Ogre::HlmsComputeJob::setNumThreadGroups	(	uint32	numThreadGroupsX,
		uint32	numThreadGroupsY,
		uint32	numThreadGroupsZ
	)

Sets the number of groups of threads to dispatch.

Note the actual value may be changed by the shader template using the @pset() function. These values are passed to the template as:

num_thread_groups_x
num_thread_groups_y
num_thread_groups_z
Remarks
As an example, it's typical to do: numThreadGroupsX = ceil( threadsPerGroupX / image.width ); numThreadGroupsY = ceil( threadsPerGroupY / image.height );

May trigger a recompilation if the value changes, regardless of what setInformHlmsOfTextureData says. There may be API / HW limitations on the max values for each dimension.

◆ setNumThreadGroupsBasedOn()

void Ogre::HlmsComputeJob::setNumThreadGroupsBasedOn	(	ThreadGroupsBasedOn	source,
		uint8	texSlot,
		uint8	divisorX,
		uint8	divisorY,
		uint8	divisorZ
	)

Instead of calling setNumThreadGroups, Ogre can automatically deduce them based on the Texture resolution and the threads per group.

It is calculated as follows: scaledWidth = (textureWidth + divisorX - 1u) / divisorX; numThreadGroupsX = (scaledWidth + threadsPerGroupX - 1u) / threadsPerGroupX;

Remarks: Unless disabled, this will overwrite your setNumThreadGroups based on the texture bound at the time the job is dispatched.

: If no texture/uav is bound at the given slot (or no such slot exists), we will log a warning.

Parameters

source	What to use as source for the calculations. See ThreadGroupsBasedOn
texSlot	Index of the texture/uav unit.
divisorX	divisorY divisorZ Often compute shaders operate on multiple pixels, thus you need less thread groups. For example if you operate on blocks of 2x2, then you want divisorX = 2 and divisorY = 2.

◆ setNumUavUnits()

void Ogre::HlmsComputeJob::setNumUavUnits ( uint8 numSlots )

Creates 'numSlots' number of slots before they can be set.

◆ setPiece()

void Ogre::HlmsComputeJob::setPiece	(	IdString	pieceName,
		const String &	pieceContent
	)

Defines a piece, i.e.

the same as doing @piece( pieceName )pieceContent@end If the piece doesn't exist, it gets created. If the piece already exists, it gets overwritten.

Remarks: Because we need to efficiently track changes (to know when to recompile, when we can reuse a cached shader, etc), we store a property of the same name as pieceName with the hash of the piece's content as value. e.g. doing setPiece( pieceName, pieceContent ) implies calling setProperty( pieceName, hash( pieceContent ). Hence you should NOT manipulate mPieces directly, otherwise we won't see changes performed to it, or use shaders from a cache we shouldn't use.

Parameters

pieceName	Name of the piece.
pieceContent	The contents of the piece.

◆ setProperty()

void Ogre::HlmsComputeJob::setProperty	(	IdString	key,
		int32	value
	)

Sets an arbitrary property to pass to the shader.

Remarks: Will trigger a recompilation if the value changes, regardless of what setInformHlmsOfTextureData says.

Parameters

key	Name of the property
value	Value to set

◆ setSamplerblock()

void Ogre::HlmsComputeJob::setSamplerblock	(	uint8	slotIdx,
		const HlmsSamplerblock &	refParams
	)

Sets a samplerblock based on reference parameters.

Parameters

slotIdx See setNumTexUnits.

Must be in range [0; getNumTexUnits) regardless of what getTexSlotStart is

Parameters

refParams We'll create (or retrieve an existing) samplerblock based on the input parameters.

◆ setTexBuffer()

void Ogre::HlmsComputeJob::setTexBuffer	(	uint8	slotIdx,
		const DescriptorSetTexture2::BufferSlot &	newSlot
	)

Sets a texture buffer at the given slot ID.

Remarks: Texture buffer slots are shared with setTexture's. Calling this function will remove the settings from previous setTexture calls to the same slot index.

: May trigger a recompilation if setInformHlmsOfTextureData is enabled.

: Setting a RenderTarget that could be used for writing is dangerous in explicit APIs (DX12, Vulkan). Use the CompositorPassComputeDef

: ReadOnlyBufferPacked can be bound using this function. But please note in certain APIs these type of buffers may end up being bound to UAV slots already taken by _setUav* functions.

See HlmsComputeJob::setTexSlotStart to workaround that

Parameters

slotIdx See setNumTexUnits. The slot index to bind this texture buffer In OpenGL, a few cards support between to 16-18 texture units, while most cards support up to 32

Must be in range [0; getNumTexUnits) regardless of what getTexSlotStart is

Parameters

newSlot

◆ setTexture()

void Ogre::HlmsComputeJob::setTexture	(	uint8	slotIdx,
		const DescriptorSetTexture2::TextureSlot &	newSlot,
		const HlmsSamplerblock *	refParams = `0`,
		bool	bSetSampler = `true`
	)

Sets a texture buffer at the given slot ID.

Remarks: Texture slots are shared with setTexBuffer's. Calling this function will remove the settings from previous setTexBuffer calls to the same slot index.

: UAVs and Textures share the same slots in OpenGL, but don't in D3D11. For best compatibility, assume they're shared and put the UAVs in the first slots.

: May trigger a recompilation if setInformHlmsOfTextureData is enabled.

Parameters

slotIdx See setNumTexUnits. The slot index to bind this texture In OpenGL, some cards support up to 16-18 texture units, while most cards support up to 32

Must be in range [0; getNumTexUnits) regardless of what getTexSlotStart is

Parameters

samplerblock	Optional. We'll create (or retrieve an existing) samplerblock based on the input parameters. When null, we leave the previously set samplerblock (if a texture is being set, and if no samplerblock was set, we'll create a default one)
bSetSampler	If true, samplerblock will behave as described. When false and samplerblock is nullptr, we won't touch the samplerblock. Only use this with APIs that have separate texturse & sampler (e.g. everyone except GL)

◆ setThreadsPerGroup()

void Ogre::HlmsComputeJob::setThreadsPerGroup	(	uint32	threadsPerGroupX,
		uint32	threadsPerGroupY,
		uint32	threadsPerGroupZ
	)

Sets the number of threads per group.

Note the actual value may be changed by the shader template using the @pset() function. These values are passed to the template as:

threads_per_group_x
threads_per_group_y
threads_per_group_z
Remarks
May trigger a recompilation if the value changes, regardless of what setInformHlmsOfTextureData says. There may be API / HW limitations on the max values for each dimension.

◆ setupRootLayout()

void Ogre::HlmsComputeJob::setupRootLayout ( RootLayout & rootLayout )

The documentation for this class was generated from the following file:

OgreHlmsComputeJob.h

Public Types

Public Member Functions

Member Enumeration Documentation

◆ ThreadGroupsBasedOn

Constructor & Destructor Documentation

◆ HlmsComputeJob()

◆ ~HlmsComputeJob()

Member Function Documentation

◆ _calculateNumThreadGroupsBasedOnSetting()

◆ _getRawGlTexSlotStart()

◆ _getShaderParams()

◆ _setSamplerblock()

◆ _setUavBuffer()

◆ _setUavTexture()

◆ _updateAutoProperties()

◆ analyzeBarriers()

◆ clearTexBuffers()

◆ clearUavBuffers()

◆ clone()

◆ cloneTo()

◆ createShaderParams()

◆ getCreator()

◆ getGlTexSlotStart()

◆ getName()

◆ getNameStr()

◆ getNumSamplerUnits()

◆ getNumTexUnits()

◆ getNumThreadGroups()

◆ getNumThreadGroupsX()

◆ getNumThreadGroupsY()

◆ getNumThreadGroupsZ()

◆ getNumUavUnits()

◆ getProperty()

◆ getShaderParams()

◆ getTexture()

◆ getThreadsPerGroup()

◆ getThreadsPerGroupX()

◆ getThreadsPerGroupY()

◆ getThreadsPerGroupZ()

◆ getUavBuffer()

◆ getUavTexture()

◆ notifyTextureChanged()

◆ removePiece()

◆ removeTexUnit()

◆ removeUavUnit()

◆ setConstBuffer()

◆ setGlTexSlotStart()

◆ setInformHlmsOfTextureData()

◆ setNumSamplerUnits()

◆ setNumTexUnits()

◆ setNumThreadGroups()

◆ setNumThreadGroupsBasedOn()

◆ setNumUavUnits()

◆ setPiece()

◆ setProperty()

◆ setSamplerblock()

◆ setTexBuffer()

◆ setTexture()

◆ setThreadsPerGroup()

◆ setupRootLayout()