FPGA systolic array GZIP compressor
Bibliographic record
Abstract
In this paper we present a complete, open-source GZIP compressor implementation for FPGA based on a systolic array architecture. GZIP is one of the most utilized compression algorithms. Besides the usual use-case of compression for data storage, distributed computing systems such as Hadoop utilize compression to reduce the amount of data which is transferred between computing nodes in a cluster. However, compression with GZIP requires significant amounts of CPU processing power, negating some of the advantages of the compressed-transfer approach in distributed systems. We have designed, implemented and tested a hardware architecture and software application for compressing files using a hardware GZIP compressor. The system presented in this paper offloads GZIP compression from the host CPU to one or more systolic GZIP compression cores in FPGA, thereby reducing latency caused by compression and freeing up the CPU for other computing tasks. We implemented and evaluated a single GZIP compression core in a ML605 development board, equipped with a Xilinx Virtex 6 FPGA, utilizing Xillybus for data transfers over PCI Express. Our results indicate the peak compression throughput of our implementation is over 1.3 Gbps and an average throughput of 52 Mbps on the Calgary corpus. Our FPGA compression solution is at least twice as fast as software compression on an Intel Core i7, in all evaluated scenarios, and up to 18× faster for large files. The project source code is publicly available online1.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.018 | 0.003 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".