|
FZGPUModules 2.0
GPU-accelerated modular compression pipelines
|
Zero-Adaptive Reduction Encoding stage — lossless byte-stream compressor. More...
#include "stage/stage.h"#include "fzm_format.h"#include "backend/types.h"#include <cstdint>#include <cstring>#include <stdexcept>#include <string>#include <unordered_map>#include <vector>Go to the source code of this file.
Classes | |
| class | fz::RAZEStage |
Namespaces | |
| namespace | fz |
Zero-Adaptive Reduction Encoding stage — lossless byte-stream compressor.
Standalone port of the LC framework RAZE component. RAZE is the auto-k generalization of RZE (see RZEStage): rather than a binary "word is zero, or it's kept in full" test, it histograms how many top bits of each word are zero across the whole chunk, picks one global cut keep (0 <= keep < word_size*8) that maximizes total bit savings, then bit-packs the bottom keep bits of every word whose top bits are all zero (words with nonzero top bits are stored in full, same as RZE). The 4-level recursive bitmap compression is identical to RZE.
Output stream layout and serialized header are identical to RZEStage — the per-chunk keep value lives inside the chunk's own compressed bytes (accounted for in its csize), not in the container/host format, so the two stages share the same host-side orchestration byte-for-byte.
Serialized header (9 bytes): [0..3] chunk_size (uint32_t LE), [4] word_size (uint8_t), [5..8] cached_orig_bytes (uint32_t LE).