Metraipolis › archive › dc_b3f592d0fefd
RAPID: Row-Parallel Arithmetic Processing in DRAM — arXiv:2610.02502
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.02502
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-05T22:53:45.310Z
- SHA-256 of the archived text
fdd7f980baf5786e5e6cd3209005885969d841f0a7013563d74fce85319e8248- Stable URL of this page
https://metraipolis.com/documento/dc_b3f592d0fefd
How to cite
RAPID: Row-Parallel Arithmetic Processing in DRAM — arXiv:2610.02502 — arXiv, https://arxiv.org/abs/2610.02502 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b3f592d0fefd (Metraipolis archive dc_b3f592d0fefd, sha256 fdd7f980baf5786e5e6cd3209005885969d841f0a7013563d74fce85319e8248)
BibTeX
@misc{dcb3f592d0fefd,
title = {RAPID: Row-Parallel Arithmetic Processing in DRAM — arXiv:2610.02502},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.02502},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b3f592d0fefd; sha256 fdd7f980baf5786e5e6cd3209005885969d841f0a7013563d74fce85319e8248},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02502. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Processing-using-memory (PUM) architectures perform computation directly within DRAM to reduce costly data movement between memory and processors. Because charge-sharing operations are confined to individual bitlines, existing DRAM-PUM architectures reorganize data into column-oriented, bit-serial representations. This organization is fundamentally incompatible with the row-oriented, word-parallel layouts used by conventional processors and accelerators, requiring expensive data-layout transformations whenever computation transitions between PUM and conventional execution. In this paper, we present RAPID, a Row-parallel Arithmetic Processing-In-DRAM architecture. RAPID augments the DRAM subarray with two lightweight extensions: migration cells that enable localized horizontal data movement between neighboring bitlines and inversion cells that provide efficient in-array logical inversion. These primitives enable RAPID to operate directly on row-parallel, bit-parallel data, preserving CPU-compatible layouts while exploiting the massive parallelism of the DRAM subarray. In particular, RAPID demonstrates that localized horizontal communication is sufficient to realize shallow arithmetic networks and efficient parallel reduction for multiplication, reducing arithmetic latency while preserving throughput and eliminating costly data-layout transformations, all while maintaining the conventional DRAM array organization. We demonstrate the feasibility and overhead of augmenting DRAM subarrays with migration and inversion cells through detailed transistor-level layout and SPICE-validated circuit simulations. Using the RAPID compiler it is possible to evaluate the performance and data reorganization tradeoffs to ensure the best execution across combined CPU and PUM. Evaluating RAPID on 19 MLPerf benchmarks, there is a 5.9x higher end-to-end performance compared to SIMDRAM for DDR4 PUM execution. Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.AR, nuovi lavori del giorno). Categorie arXiv: Hardware Architecture (cs.AR). Pagina del lavoro: https://arxiv.org/abs/2610.02502 — 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 2026-10-05T22:46:40.540Z dalla pagina https://arxiv.org/list/cs.AR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).