SeqCDC speeds up content-defined chunking by detecting monotonic byte sequences, skipping unfavorable regions, and vectorizing with SSE/AVX, achieving up to roughly 10x throughput over unaccelerated and 1.2x to 1.35x over vector-accelerated chunkers at 8 to 16 KB chunks.
Network attached storage architecture,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Vectorized Sequence-Based Chunking for Data Deduplication
SeqCDC speeds up content-defined chunking by detecting monotonic byte sequences, skipping unfavorable regions, and vectorizing with SSE/AVX, achieving up to roughly 10x throughput over unaccelerated and 1.2x to 1.35x over vector-accelerated chunkers at 8 to 16 KB chunks.