fz::Cdf97Stage< TInput > Class Template Reference

#include <cdf97_stage.h>

Inheritance diagram for fz::Cdf97Stage< TInput >:

Public Member Functions
void	setInverse (bool inv) override
void	setDims (const std::array< size_t, 3 > &dims) override
void	execute (cudaStream_t stream, MemoryPool *pool, const std::vector< void * > &inputs, const std::vector< void * > &outputs, const std::vector< size_t > &sizes) override
bool	isGraphCompatible () const override
	No mid-execute sync or D2H: every kernel is enqueued on stream.
std::string	getName () const override
std::vector< size_t >	estimateOutputSizes (const std::vector< size_t > &input_sizes) const override
std::unordered_map< std::string, size_t >	getActualOutputSizesByName () const override
size_t	getActualOutputSize (int index) const override
uint16_t	getStageTypeId () const override
uint8_t	getOutputDataType (size_t) const override
uint8_t	getInputDataType (size_t) const override
size_t	serializeHeader (size_t, uint8_t *buf, size_t max_size) const override
void	deserializeHeader (const uint8_t *buf, size_t size) override
size_t	getMaxHeaderSize (size_t) const override
void	saveState () override
Public Member Functions inherited from fz::Stage
virtual size_t	getRequiredInputAlignment () const
virtual std::vector< std::string >	getOutputNames () const
int	getOutputIndex (const std::string &name) const
virtual std::vector< std::string >	getRunNotes () const
virtual void	onFinalize (size_t, MemoryPool *)
virtual size_t	estimateDeviceFootprintBytes (size_t) const
virtual size_t	estimatePinnedFootprintBytes (size_t) const
virtual void	postStreamSync (fz::stream_t stream)
virtual void	setTerminalOutput (bool terminal)
virtual size_t	estimateScratchBytes (const std::vector< size_t > &input_sizes) const
virtual FusionSpec	getFusionSpec () const
virtual FusedOpDecl	getFusedOp () const
virtual EncodingOracleDecl	getEncodingOracle () const
virtual bool	bindDownstreamEncodingOracle (const EncodingOracleDecl &)
virtual std::vector< FusedAuxOutputDecl >	getFusedAuxOutputs () const
virtual void	primeFusedForwardState (const FusedPrimeContext &)
virtual void	setFusedArchiveResult (size_t, size_t)
virtual void	setFusedSideOutput (int, size_t)

Static Public Attributes
static constexpr size_t	kMaxLineElems = (48u * 1024u) / sizeof(TInput)
	Largest transform line that fits the shared-memory scheme, in elements.

Additional Inherited Members
Static Public Member Functions inherited from fz::Stage
static constexpr bool	isSupportedOnBackend ()

Detailed Description

template<typename TInput = double>
class fz::Cdf97Stage< TInput >

CDF 9/7 wavelet transform stage. Lossless, invertible, size-preserving.

Template Parameters

TInput

Floating-point element type (float or double). double is bit-exact with SPERR; float is a faster non-bit-exact variant.

Member Function Documentation

setInverse()

template<typename TInput = double>

void fz::Cdf97Stage< TInput >::setInverse ( bool  inverse )

inlineoverridevirtual

Switch between forward (compression) and inverse (decompression) mode. Affects getNumInputs()/getNumOutputs() for stages with asymmetric port counts.

Reimplemented from fz::Stage.

setDims()

template<typename TInput = double>

void fz::Cdf97Stage< TInput >::setDims ( const std::array< size_t, 3 > &  dims )

inlineoverridevirtual

Called once by Pipeline::finalize() so stages can react to the dataset dimensions set via Pipeline::setDims() after construction.

Parameters

dims	{x, y, z} extents (z==1 → 2-D; y==z==1 → 1-D)

Reimplemented from fz::Stage.

execute()

template<typename TInput = double>

void fz::Cdf97Stage< TInput >::execute ( cudaStream_t  stream, MemoryPool *  pool, const std::vector< void * > &  inputs, const std::vector< void * > &  outputs, const std::vector< size_t > &  sizes  )

overridevirtual

Execute the stage. Inputs, outputs, and sizes are device pointers/bytes.

Stages may call cudaStreamSynchronize(stream) or issue blocking D2H copies when the algorithm requires it (e.g. Huffman histogram readback for codebook construction, ANS renormalization tables). Such stages must return false from isGraphCompatible() and must document the sync points.

Note: the DAG dispatches sibling nodes (same topological level) via a sequential CPU loop, each enqueuing to its own stream. A sync inside execute() blocks the CPU from dispatching subsequent siblings until the synced stream is idle — this delays parallel branches in wide DAGs. In a linear pipeline there are no siblings and no extra cost.

Implements fz::Stage.

getName()

template<typename TInput = double>

std::string fz::Cdf97Stage< TInput >::getName ( ) const

inlineoverridevirtual

Human-readable name used in error messages and debug output.

Implements fz::Stage.

estimateOutputSizes()

template<typename TInput = double>

std::vector< size_t > fz::Cdf97Stage< TInput >::estimateOutputSizes ( const std::vector< size_t > &  input_sizes ) const

inlineoverridevirtual

Estimate output buffer sizes given input sizes. Used for buffer allocation planning in PREALLOCATE mode — must be a safe upper bound; under-estimation causes buffer overruns.

Implements fz::Stage.

getActualOutputSizesByName()

template<typename TInput = double>

std::unordered_map< std::string, size_t > fz::Cdf97Stage< TInput >::getActualOutputSizesByName ( ) const

inlineoverridevirtual

Actual output sizes after execute(), keyed by output port name.

Implements fz::Stage.

getActualOutputSize()

template<typename TInput = double>

size_t fz::Cdf97Stage< TInput >::getActualOutputSize ( int  index ) const

inlineoverridevirtual

Actual size of a single output by index after execute(). Avoids constructing the map for the common single-output case. Default delegates to getActualOutputSizesByName(); override to return directly from an internal field.

Reimplemented from fz::Stage.

getStageTypeId()

template<typename TInput = double>

uint16_t fz::Cdf97Stage< TInput >::getStageTypeId ( ) const

inlineoverridevirtual

Stage type identifier written into the FZM file header.

Implements fz::Stage.

getOutputDataType()

template<typename TInput = double>

uint8_t fz::Cdf97Stage< TInput >::getOutputDataType ( size_t  output_index ) const

inlineoverridevirtual

DataType enum of the given output port.

Implements fz::Stage.

getInputDataType()

template<typename TInput = double>

uint8_t fz::Cdf97Stage< TInput >::getInputDataType ( size_t  ) const

inlineoverridevirtual

Expected DataType of the given input port.

Used by Pipeline::finalize() to detect type mismatches between connected stages before any execution. Return DataType::UNKNOWN to opt out of checking — byte-transparent stages (Bitshuffle, RZE, RRE) and mock stages must return UNKNOWN; finalize() skips any connection where either side is UNKNOWN.

Reimplemented from fz::Stage.

serializeHeader()

template<typename TInput = double>

size_t fz::Cdf97Stage< TInput >::serializeHeader ( size_t  output_index, uint8_t *  header_buffer, size_t  max_size  ) const

inlineoverridevirtual

Serialize stage config into header_buffer (max 128 bytes) for the FZM file. Return the number of bytes written, or 0 if the stage has no config.

Reimplemented from fz::Stage.

deserializeHeader()

template<typename TInput = double>

void fz::Cdf97Stage< TInput >::deserializeHeader ( const uint8_t *  header_buffer, size_t  size  )

inlineoverridevirtual

Restore stage config from header_buffer during decompression.

Reimplemented from fz::Stage.

getMaxHeaderSize()

template<typename TInput = double>

size_t fz::Cdf97Stage< TInput >::getMaxHeaderSize ( size_t  output_index ) const

inlineoverridevirtual

Maximum bytes this stage writes into its per-output FZM header slot.

Reimplemented from fz::Stage.

saveState()

template<typename TInput = double>

void fz::Cdf97Stage< TInput >::saveState ( )

inlineoverridevirtual

Save/restore config state around a decompression pass. deserializeHeader() overwrites the stage's forward-pass config; saveState() is called before and restoreState() after so the stage returns to its original configuration.

Reimplemented from fz::Stage.