Metraipolis › archive › dc_2d6840155ee2

To SIMD or Not to SIMD: Comparing RVV vs. CGRA SoCs for Non-Linear Functions in AI — arXiv:2611.12435

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.12435
License (as archived)
CC0-1.0
Archived
2026-11-10T18:44:07.316Z
SHA-256 of the archived text
c29133943093d65d807b6b04db7ae93eea939271f57e593777c4ccd2f7f62c63
Stable URL of this page
https://metraipolis.com/documento/dc_2d6840155ee2

How to cite

To SIMD or Not to SIMD: Comparing RVV vs. CGRA SoCs for Non-Linear Functions in AI — arXiv:2611.12435 — arXiv (en), https://arxiv.org/abs/2611.12435 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2d6840155ee2 (Metraipolis archive dc_2d6840155ee2, sha256 c29133943093d65d807b6b04db7ae93eea939271f57e593777c4ccd2f7f62c63)
BibTeX
@misc{dc2d6840155ee2,
  title = {To SIMD or Not to SIMD: Comparing RVV vs. CGRA SoCs for Non-Linear Functions in AI — arXiv:2611.12435},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.12435},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2d6840155ee2; sha256 c29133943093d65d807b6b04db7ae93eea939271f57e593777c4ccd2f7f62c63},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.12435. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Non-linear functions are an important class of operations in modern large language models. However, chip vendors building for AI have so far relied on traditional vector or scalar processing units for non-linear functions. The performance of these units has not kept pace with matrix multiplication units (MMUs), which can be found in both high-performance and edge-computing devices from almost every vendor. Reconfigurable units such as FPGAs and CGRAs have been proposed in the literature, but have not been systematically compared with traditional units backed by MMUs. In this paper, we build two SoCs: one using an RVV vector processor and the other using a latency-insensitive (\emph{elastic}) CGRA, both coupled with an MMU and driven by a single-core CPU. We then propose mappings for common feed-forward networks on our SoCs and find that the CGRA reaches a maximum speedup in clock cycles of 7.12x over RVV on the activation stage of simple point-wise non-linear functions like SiLU, whereas the RVV reaches a maximum speedup of \textbf{9.8x} over the CGRA on complex non-linear functions such as $\mathrm{softmax}$. Over the enclosing feed-forward block the corresponding maxima are 3.16x and 4.24x.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Hardware Architecture (cs.AR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.12435 — 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 2026-11-10T18:37:37.694Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).