lorenzo_quant.h File Reference

Fused Lorenzo predictor and quantizer stage. More...

#include "stage/stage.h"
#include "fzm_format.h"
#include <cuda_runtime.h>
#include <array>
#include <cstdint>
#include <cmath>
#include <cstring>

Go to the source code of this file.

Classes
struct	fz::LorenzoQuantConfig
class	fz::LorenzoQuantStage< TInput, TCode >
struct	fz::LorenzoQuantStage< TInput, TCode >::Config

Enumerations
enum class	fz::ErrorBoundMode : uint8_t { ABS = 0 , REL = 1 , NOA = 2 }

Functions
template<typename TInput , typename TCode >
void	fz::launchLorenzoKernel2D (const TInput *d_input, size_t nx, size_t ny, TInput ebx2_r, TCode quant_radius, TCode *d_codes, TInput *d_outlier_errors, uint32_t *d_outlier_indices, uint32_t *d_outlier_count, size_t max_outliers, bool zigzag_codes, cudaStream_t stream)
	2-D forward Lorenzo kernel launcher. nx is the fast (x) dimension.
template<typename TInput , typename TCode >
void	fz::launchLorenzoInverseKernel2D (const TCode *d_codes, const TInput *d_outlier_errors, const uint32_t *d_outlier_indices, const uint32_t *d_outlier_count, size_t nx, size_t ny, size_t max_outliers, TInput ebx2, TCode quant_radius, TInput *d_output, bool zigzag_codes, cudaStream_t stream, MemoryPool *pool)
	2-D inverse Lorenzo kernel launcher.
template<typename TInput , typename TCode >
void	fz::launchLorenzoKernel3D (const TInput *d_input, size_t nx, size_t ny, size_t nz, TInput ebx2_r, TCode quant_radius, TCode *d_codes, TInput *d_outlier_errors, uint32_t *d_outlier_indices, uint32_t *d_outlier_count, size_t max_outliers, bool zigzag_codes, cudaStream_t stream)
	3-D forward Lorenzo kernel launcher.
template<typename TInput , typename TCode >
void	fz::launchLorenzoInverseKernel3D (const TCode *d_codes, const TInput *d_outlier_errors, const uint32_t *d_outlier_indices, const uint32_t *d_outlier_count, size_t nx, size_t ny, size_t nz, size_t max_outliers, TInput ebx2, TCode quant_radius, TInput *d_output, bool zigzag_codes, cudaStream_t stream, MemoryPool *pool)
	3-D inverse Lorenzo kernel launcher.

Detailed Description

Fused Lorenzo predictor and quantizer stage.

Enumeration Type Documentation

ErrorBoundMode

enum class fz::ErrorBoundMode : uint8_t

strong

Interpretation of the user-specified error bound.

• ABS — |x_orig - x_recon| <= eb (default).
• REL — point-wise relative (PFPL): |error| / |x_orig| <= eb. For Lorenzo this is a global approximation: abs_eb = eb × max(|data|). Values much smaller than max(|data|) may exceed the per-element ratio. For an exact per-element REL bound use QuantizerStage with REL mode.
• NOA — norm-of-absolute / value-range relative (PFPL): abs_eb = eb × (max(data) - min(data)). Equivalent to what most other compressors call "relative".

Enumerator
ABS	Absolute error bound.
REL	Global-approximate point-wise relative bound.
NOA	Value-range relative bound (norm-of-absolute).