Metraipolis › archive › dc_64dc01fdb82a

AI Query Compilation for Unified and Optimized Execution — arXiv:2608.10139

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.10139
License (as archived)
CC0-1.0
Archived
2026-10-19T06:36:34.082Z
SHA-256 of the archived text
526b9071ca1028182b6b8119c68933682799233419aeaaa82cf6b4a483c2c149
Stable URL of this page
https://metraipolis.com/documento/dc_64dc01fdb82a

How to cite

AI Query Compilation for Unified and Optimized Execution — arXiv:2608.10139 — arXiv (en), https://arxiv.org/abs/2608.10139 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_64dc01fdb82a (Metraipolis archive dc_64dc01fdb82a, sha256 526b9071ca1028182b6b8119c68933682799233419aeaaa82cf6b4a483c2c149)
BibTeX
@misc{dc64dc01fdb82a,
  title = {AI Query Compilation for Unified and Optimized Execution — arXiv:2608.10139},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.10139},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_64dc01fdb82a; sha256 526b9071ca1028182b6b8119c68933682799233419aeaaa82cf6b4a483c2c149},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10139. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In this vision paper, we propose a novel architectural paradigm for accelerated AI query execution via a unified compiled execution strategy. By compiling the hybrid AI Query as a whole -- integrating both standard SQL relational constructs and LLM inference layers into a single, unified tensor compute graph -- we completely alleviate PCIe data movement bottlenecks across execution boundaries and enable global compiler optimizations and efficient automatic sharding. We demonstrate the viability of this unified execution paradigm on select and extended AI queries on SemBench Reviews and Movies datasets, achieving up to 5.3x latency speedup and 9.8x throughput speedup on TPUs, and outline a research roadmap of open technical challenges to realize this vision.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-12 in cs.DB).
Categorie arXiv: Databases (cs.DB).
Pagina del lavoro: https://arxiv.org/abs/2608.10139 — 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 2026-10-19T06:27:34.461Z dalla pagina https://arxiv.org/catchup/cs.DB/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).