{"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/optimizing-grouped-convolutions-on-edge","title":"Optimizing Grouped Convolutions on Edge Devices","arxiv_id":"2006.09791","date":"2020-06-17","proceeding":null,"authors":["Perry Gibson","José Cano","Jack Turner","Elliot J. Crowley","Michael O'Boyle","Amos Storkey"],"abstract":"When deploying a deep neural network on constrained hardware, it is possible to replace the network's standard convolutions with grouped convolutions. This allows for substantial memory savings with minimal loss of accuracy. However, current implementations of grouped convolutions in modern deep learning frameworks are far from performing optimally in terms of speed. In this paper we propose Grouped Spatial Pack Convolutions (GSPC), a new implementation of grouped convolutions that outperforms existing solutions. We implement GSPC in TVM, which provides state-of-the-art performance on edge devices. We analyze a set of networks utilizing different types of grouped convolutions and evaluate their performance in terms of inference time on several edge devices. We observe that our new implementation scales well with the number of groups and provides the best inference times in all settings, improving the existing implementations of grouped convolutions in TVM, PyTorch and TensorFlow Lite by 3.4x, 8x and 4x on average respectively. Code is available at https://github.com/gecLAB/tvm-GSPC/","url_abs":"https://arxiv.org/abs/2006.09791v1","url_pdf":"https://arxiv.org/pdf/2006.09791v1.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":"optimizing-grouped-convolutions-on-edge","repo_url":"https://github.com/gecLAB/tvm-GSPC","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.09791","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.09791"}},"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/gecLAB/tvm-GSPC","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"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":"211fd29e63cb541a","entry":"bind_params_by_name","repo":"gecLAB/tvm-GSPC","repo_kind":"official","path":"python/tvm/relay/build_module.py","file_url":"https://github.com/gecLAB/tvm-GSPC/blob/HEAD/python/tvm/relay/build_module.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"211fd29e63cb541a"}},{"code_sha256_prefix":"b35150c8cd9f2057","entry":"check_numerical_grads","repo":"gecLAB/tvm-GSPC","repo_kind":"official","path":"python/tvm/testing.py","file_url":"https://github.com/gecLAB/tvm-GSPC/blob/HEAD/python/tvm/testing.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b35150c8cd9f2057"}},{"code_sha256_prefix":"f7f40fde4f7279e1","entry":"enabled","repo":"gecLAB/tvm-GSPC","repo_kind":"official","path":"python/tvm/runtime/module.py","file_url":"https://github.com/gecLAB/tvm-GSPC/blob/HEAD/python/tvm/runtime/module.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f7f40fde4f7279e1"}},{"code_sha256_prefix":"670d33f60a876bd1","entry":"load_module","repo":"gecLAB/tvm-GSPC","repo_kind":"official","path":"python/tvm/runtime/module.py","file_url":"https://github.com/gecLAB/tvm-GSPC/blob/HEAD/python/tvm/runtime/module.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"670d33f60a876bd1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}