Synthesizing specialized sparse tensor accelerators for reconfigurable hardware using high-level functional abstractions
Bibliographic record
Abstract
Sparsity is inherent in many applications such as machine learning and graph analytics.However, achieving high efficiency in sparse computations requires specialized hardware accelerators like FPGAs, as traditional accelerators like CPUs and GPUs typically cater to dense data.While high level synthesis enables the automatic generation of FPGA-based accelerators, generic solutions produced via C-based synthesis flows often demand extensive development time, leading designers to prioritize broad applicability over fine-grained structural specialization.Consequently, these accelerators fail to fully exploit FPGA's reconfigurability, leaving substantial performance and efficiency gains untapped.This thesis pushes the boundary by automatically generating specialized accelerators that match a given fixed sparse-structure (e.g., in static graph analytics and pruned neural networks).It accomplishes this by adapting a functional, type-driven compilation methodology previously shown to be highly effective at producing high-performance GPU code for sparse tensor algebra.By reimagining this approach for reconfigurable hardware, the thesis introduces specialized primitives designed specifically for irregular data.Encoding tensor shapes directly within the type system allows concise specifications of sparse accelerators and facilitates advanced optimizations, such as dynamic partitioning and vector sharding, ultimately generating hardware precisely customized to the sparsity patterns of the underlying tensors.Compared to state-of-the-art generic accelerators (HiSparse, HiSpMV and GraphLily), the approach achieves up to a 2.8 improvement in bandwidth efficiency for sparse matrix i computations and a 1.8 speedup on graph algorithms.Against the HLS4ML neural network acceleration framework, it achieves up to a 1.8 improvement in throughput with a 4 reduction in resource usage, enabling scaling to larger networks.These results establish this functional approach as a flexible, powerful, and rapid solution for high-performance specialized sparse accelerator design.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.003 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.000 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".