{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/parallelizing-linear-recurrent-neural-nets","title":"Parallelizing Linear Recurrent Neural Nets Over Sequence Length","arxiv_id":"1709.04057","date":"2017-09-12","proceeding":"ICLR 2018 1","authors":["Eric Martin","Chris Cundy"],"abstract":"Recurrent neural networks (RNNs) are widely used to model sequential data but\ntheir non-linear dependencies between sequence elements prevent parallelizing\ntraining over sequence length. We show the training of RNNs with only linear\nsequential dependencies can be parallelized over the sequence length using the\nparallel scan algorithm, leading to rapid training on long sequences even with\nsmall minibatch size. We develop a parallel linear recurrence CUDA kernel and\nshow that it can be applied to immediately speed up training and inference of\nseveral state of the art RNN architectures by up to 9x. We abstract recent work\non linear RNNs into a new framework of linear surrogate RNNs and develop a\nlinear surrogate model for the long short-term memory unit, the GILR-LSTM, that\nutilizes parallel linear recurrence. We extend sequence learning to new\nextremely long sequence regimes that were previously out of reach by\nsuccessfully training a GILR-LSTM on a synthetic sequence classification task\nwith a one million timestep dependency.","url_abs":"http://arxiv.org/abs/1709.04057v2","url_pdf":"http://arxiv.org/pdf/1709.04057v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"parallelizing-linear-recurrent-neural-nets","repo_url":"https://github.com/eamartin/parallelizing_linear_rnns","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"parallelizing-linear-recurrent-neural-nets","repo_url":"https://github.com/proger/accelerated-scan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1709.04057","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1709.04057"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/eamartin/parallelizing_linear_rnns","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/proger/accelerated-scan","reach":null}],"summary":{"ran_honours":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"6ac2ecfb8cd3b4a0","entry":"init","repo":"proger/accelerated-scan","repo_kind":"listed","path":"tests/bench.py","file_url":"https://github.com/proger/accelerated-scan/blob/HEAD/tests/bench.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6ac2ecfb8cd3b4a0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}