Metraipolis › archive › dc_224cc1bdb0fe

Precision-Aware Variable Bit Processing Elements for Hardware-Efficient Systolic Array Designs — arXiv:2608.22378

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.22378
License (as archived)
CC0-1.0
Archived
2026-10-18T07:56:07.200Z
SHA-256 of the archived text
3187a65ac4b3557115116111a359bace0cc6b2426a22c59d42110d2897d52e89
Stable URL of this page
https://metraipolis.com/documento/dc_224cc1bdb0fe

How to cite

Precision-Aware Variable Bit Processing Elements for Hardware-Efficient Systolic Array Designs — arXiv:2608.22378 — arXiv (en), https://arxiv.org/abs/2608.22378 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_224cc1bdb0fe (Metraipolis archive dc_224cc1bdb0fe, sha256 3187a65ac4b3557115116111a359bace0cc6b2426a22c59d42110d2897d52e89)
BibTeX
@misc{dc224cc1bdb0fe,
  title = {Precision-Aware Variable Bit Processing Elements for Hardware-Efficient Systolic Array Designs — arXiv:2608.22378},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.22378},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_224cc1bdb0fe; sha256 3187a65ac4b3557115116111a359bace0cc6b2426a22c59d42110d2897d52e89},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.22378. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Systolic arrays (SAs) have emerged as prominent hardware accelerators for matrix operations in deep learning, while floating point number formats enable precision control across computational domains. This research investigates approximate computing techniques for floating point (FP) multipliers in Weight Stationary Systolic Arrays, focusing on IEEE 754 (FP32), TensorFloat-32 (TF32), and Brain Floating point (BF16) formats. By integrating partial product matrix (PPM) column truncation with positive and negative compressors in the FP multiplier architecture, we optimize the trade-off between computational efficiency and accuracy. NSGA-II optimization algorithm was employed to explore the vast design space for evolving FP multiplier designs, towards achieving substantial hardware improvements while maintaining acceptable output quality. Substantial hardware benefits were observed in the FP multiplier designs across various applications, while preserving output quality. The FP approximated Processing Elements designed in the SA was found to offer comparable CNN accuracy for models trained on MNIST, F-MNIST, and CIFAR-10 dataset. The FP approximated SA designs that fall in the top 10 CNN performance offered substantial hardware gains in the range of 66% to 92% footprint savings, 60% to 93% of power benefits with 21% to 54% improvement in the delay when compared with the corresponding exact implementations mentioned in the literature for running the model trained on CIFAR-10 dataset. The TF32 and BF16 approximated SA designs also achieved substantial gains while maintaining comparable CNN accuracy. Our findings confirm that targeted approximation in FP multiplier design significantly improves the efficiency of hardware accelerators for error-tolerant applications, establishing an effective approach to hardware resource optimization in contemporary computing architectures.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AR).
Categorie arXiv: Hardware Architecture (cs.AR) ; Emerging Technologies (cs.ET); Machine Learning (cs.LG); Image and Video Processing (eess.IV).
Pagina del lavoro: https://arxiv.org/abs/2608.22378 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T07:48:03.865Z dalla pagina https://arxiv.org/catchup/cs.AR/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).