#include <rze_stage.h>

Inheritance diagram for fz::RZEStage:

Public Member Functions
void	setInverse (bool inv) override

bool	isGraphCompatible () const override

size_t	getRequiredInputAlignment () const 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

void	postStreamSync (cudaStream_t stream) override

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

size_t	estimateScratchBytes (const std::vector< size_t > &input_sizes) const override

uint16_t	getStageTypeId () const override

uint8_t	getOutputDataType (size_t) const override

size_t	serializeHeader (size_t output_index, 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 std::vector< std::string >	getOutputNames () const

int	getOutputIndex (const std::string &name) const

virtual uint8_t	getInputDataType (size_t) const

virtual void	setDims (const std::array< size_t, 3 > &dims)

Detailed Description

Recursive Zero-byte Elimination stage.

setChunkSize(bytes) — chunk size (default 16384; must be a multiple of 4096). setLevels(n) — recursion depth 1–4 (default 4).

Note: CUDA Graph capture is supported for compression only. The inverse path requires two blocking D2H copies to read the stream header before the decode kernel can be launched.

Member Function Documentation

◆ setInverse()

void fz::RZEStage::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.

◆ isGraphCompatible()

bool fz::RZEStage::isGraphCompatible ( ) const

inlineoverridevirtual

CUDA Graph capture is supported for compression (forward pass) only.

The inverse path reads the stream header (orig_bytes, per-chunk sizes) with two blocking D2H cudaMemcpy calls before it can compute per-chunk decode offsets and launch the decode kernel. These calls prevent the inverse path from being recorded into a CUDA Graph.

This is intentional by design, not a fixable limitation: graph-compatible decompression would only help a "repeatedly decompress the same compressed buffer" workflow, which has no practical use case. The compression path (new data every iteration) is where graph capture provides real value.

Reimplemented from fz::Stage.

◆ getRequiredInputAlignment()

size_t fz::RZEStage::getRequiredInputAlignment ( ) const

inlineoverridevirtual

Minimum input size alignment in bytes. Chunked stages return their chunk size; the pipeline uses the LCM of all stage alignments at finalize() to transparently zero-pad the input. Default: 1 (no alignment requirement).

Reimplemented from fz::Stage.

◆ execute()

void fz::RZEStage::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.

Implements fz::Stage.

◆ postStreamSync()

void fz::RZEStage::postStreamSync ( cudaStream_t stream )

overridevirtual

Called after dag->execute() and stream sync, before compress() returns. Use for D2H transfers that must not block mid-pipeline (e.g. Lorenzo's outlier count readback). The stream is already idle so a plain cudaMemcpy is safe here.

Reimplemented from fz::Stage.

◆ getName()

std::string fz::RZEStage::getName ( ) const

inlineoverridevirtual

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

Implements fz::Stage.

◆ estimateOutputSizes()

std::vector< size_t > fz::RZEStage::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()

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

overridevirtual

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

Implements fz::Stage.

◆ getActualOutputSize()

size_t fz::RZEStage::getActualOutputSize ( int index ) const

overridevirtual

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.

◆ estimateScratchBytes()

size_t fz::RZEStage::estimateScratchBytes ( const std::vector< size_t > & input_sizes ) const

inlineoverridevirtual

Forward pass allocates four persistent pool arrays proportional to n_chunks = ceil(input_bytes / chunk_size_): d_scratch_ : n_chunks * chunk_size_ (per-chunk worst-case output) d_sizes_dev_ : n_chunks * 4 (raw compressed sizes) d_clean_dev_ : n_chunks * 4 (flag-stripped sizes) d_dst_off_dev_: n_chunks * 4 (exclusive prefix-sum offsets)

Inverse path scratch is transient (allocated and freed within execute), so it is not reported here.

Reimplemented from fz::Stage.

◆ getStageTypeId()

uint16_t fz::RZEStage::getStageTypeId ( ) const

inlineoverridevirtual

Stage type identifier written into the FZM file header.

Implements fz::Stage.

◆ getOutputDataType()

uint8_t fz::RZEStage::getOutputDataType ( size_t output_index ) const

inlineoverridevirtual

DataType enum of the given output port.

Implements fz::Stage.

◆ serializeHeader()

size_t fz::RZEStage::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()

void fz::RZEStage::deserializeHeader	(	const uint8_t *	header_buffer,
		size_t	size
	)

inlineoverridevirtual

Restore stage config from header_buffer during decompression.

Reimplemented from fz::Stage.

◆ getMaxHeaderSize()

size_t fz::RZEStage::getMaxHeaderSize ( size_t output_index ) const

inlineoverridevirtual

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

Reimplemented from fz::Stage.

◆ saveState()

void fz::RZEStage::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.

Public Member Functions

Detailed Description

Member Function Documentation

◆ setInverse()

◆ isGraphCompatible()

◆ getRequiredInputAlignment()

◆ execute()

◆ postStreamSync()

◆ getName()

◆ estimateOutputSizes()

◆ getActualOutputSizesByName()

◆ getActualOutputSize()

◆ estimateScratchBytes()

◆ getStageTypeId()

◆ getOutputDataType()

◆ serializeHeader()

◆ deserializeHeader()

◆ getMaxHeaderSize()

◆ saveState()