{"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/ios-inter-operator-scheduler-for-cnn","title":"IOS: Inter-Operator Scheduler for CNN Acceleration","arxiv_id":"2011.01302","date":"2020-11-02","proceeding":null,"authors":["Yaoyao Ding","Ligeng Zhu","Zhihao Jia","Gennady Pekhimenko","Song Han"],"abstract":"To accelerate CNN inference, existing deep learning frameworks focus on optimizing intra-operator parallelization. However, a single operator can no longer fully utilize the available parallelism given the rapid advances in high-performance hardware, resulting in a large gap between the peak performance and the real performance. This performance gap is more severe under smaller batch sizes. In this work, we extensively study the parallelism between operators and propose Inter-Operator Scheduler (IOS) to automatically schedule multiple operators' parallel execution through a novel dynamic programming algorithm. IOS consistently outperforms state-of-the-art libraries (e.g., TensorRT) by 1.1 to 1.5x on modern CNN benchmarks. The code to reproduce each experiment is available at: https://github.com/mit-han-lab/inter-operator-scheduler.","url_abs":"https://arxiv.org/abs/2011.01302v2","url_pdf":"https://arxiv.org/pdf/2011.01302v2.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":"ios-inter-operator-scheduler-for-cnn","repo_url":"https://github.com/mit-han-lab/inter-operator-scheduler","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2011.01302","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.01302"}},"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/mit-han-lab/inter-operator-scheduler","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":10},"by_repo_kind":{"official":{"samples":10,"ran":0,"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":"ee3ee850ea9d519b","entry":"basic_block","repo":"mit-han-lab/inter-operator-scheduler","repo_kind":"official","path":"python/ios/models/resnet.py","file_url":"https://github.com/mit-han-lab/inter-operator-scheduler/blob/HEAD/python/ios/models/resnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ee3ee850ea9d519b"}},{"code_sha256_prefix":"3d8b4f9961e3fc55","entry":"block_front","repo":"mit-han-lab/inter-operator-scheduler","repo_kind":"official","path":"python/ios/models/squeezenet.py","file_url":"https://github.com/mit-han-lab/inter-operator-scheduler/blob/HEAD/python/ios/models/squeezenet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3d8b4f9961e3fc55"}},{"code_sha256_prefix":"eb83bf2ed7c9363e","entry":"block_middle","repo":"mit-han-lab/inter-operator-scheduler","repo_kind":"official","path":"python/ios/models/squeezenet.py","file_url":"https://github.com/mit-han-lab/inter-operator-scheduler/blob/HEAD/python/ios/models/squeezenet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eb83bf2ed7c9363e"}},{"code_sha256_prefix":"2d8a3c91baecd931","entry":"bottleneck","repo":"mit-han-lab/inter-operator-scheduler","repo_kind":"official","path":"python/ios/models/resnet.py","file_url":"https://github.com/mit-han-lab/inter-operator-scheduler/blob/HEAD/python/ios/models/resnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2d8a3c91baecd931"}},{"code_sha256_prefix":"72fbadcb66366986","entry":"count_bits","repo":"mit-han-lab/inter-operator-scheduler","repo_kind":"official","path":"python/ios/optimizer.py","file_url":"https://github.com/mit-han-lab/inter-operator-scheduler/blob/HEAD/python/ios/optimizer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"72fbadcb66366986"}},{"code_sha256_prefix":"ec2d99fa16d8fb57","entry":"read_graph","repo":"mit-han-lab/inter-operator-scheduler","repo_kind":"official","path":"python/ios/models/randwire.py","file_url":"https://github.com/mit-han-lab/inter-operator-scheduler/blob/HEAD/python/ios/models/randwire.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ec2d99fa16d8fb57"}},{"code_sha256_prefix":"9a59d198efd72702","entry":"read_log","repo":"mit-han-lab/inter-operator-scheduler","repo_kind":"official","path":"experiments/utilization/draw_curve.py","file_url":"https://github.com/mit-han-lab/inter-operator-scheduler/blob/HEAD/experiments/utilization/draw_curve.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9a59d198efd72702"}},{"code_sha256_prefix":"4cd1c23d24a2480c","entry":"resnet_front","repo":"mit-han-lab/inter-operator-scheduler","repo_kind":"official","path":"python/ios/models/resnet.py","file_url":"https://github.com/mit-han-lab/inter-operator-scheduler/blob/HEAD/python/ios/models/resnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4cd1c23d24a2480c"}},{"code_sha256_prefix":"2723d9fba66f72b5","entry":"running_mean","repo":"mit-han-lab/inter-operator-scheduler","repo_kind":"official","path":"experiments/utilization/draw_curve.py","file_url":"https://github.com/mit-han-lab/inter-operator-scheduler/blob/HEAD/experiments/utilization/draw_curve.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2723d9fba66f72b5"}},{"code_sha256_prefix":"812d6bc925cb7f23","entry":"vgg_net","repo":"mit-han-lab/inter-operator-scheduler","repo_kind":"official","path":"python/ios/models/vgg.py","file_url":"https://github.com/mit-han-lab/inter-operator-scheduler/blob/HEAD/python/ios/models/vgg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"812d6bc925cb7f23"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}