{"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/tvm-an-automated-end-to-end-optimizing","title":"TVM: An Automated End-to-End Optimizing Compiler for Deep Learning","arxiv_id":"1802.04799","date":"2018-02-12","proceeding":null,"authors":["Tianqi Chen","Thierry Moreau","Ziheng Jiang","Lianmin Zheng","Eddie Yan","Meghan Cowan","Haichen Shen","Leyuan Wang","Yuwei Hu","Luis Ceze","Carlos Guestrin","Arvind Krishnamurthy"],"abstract":"There is an increasing need to bring machine learning to a wide diversity of\nhardware devices. Current frameworks rely on vendor-specific operator libraries\nand optimize for a narrow range of server-class GPUs. Deploying workloads to\nnew platforms -- such as mobile phones, embedded devices, and accelerators\n(e.g., FPGAs, ASICs) -- requires significant manual effort. We propose TVM, a\ncompiler that exposes graph-level and operator-level optimizations to provide\nperformance portability to deep learning workloads across diverse hardware\nback-ends. TVM solves optimization challenges specific to deep learning, such\nas high-level operator fusion, mapping to arbitrary hardware primitives, and\nmemory latency hiding. It also automates optimization of low-level programs to\nhardware characteristics by employing a novel, learning-based cost modeling\nmethod for rapid exploration of code optimizations. Experimental results show\nthat TVM delivers performance across hardware back-ends that are competitive\nwith state-of-the-art, hand-tuned libraries for low-power CPU, mobile GPU, and\nserver-class GPUs. We also demonstrate TVM's ability to target new accelerator\nback-ends, such as the FPGA-based generic deep learning accelerator. The system\nis open sourced and in production use inside several major companies.","url_abs":"http://arxiv.org/abs/1802.04799v3","url_pdf":"http://arxiv.org/pdf/1802.04799v3.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":"tvm-an-automated-end-to-end-optimizing","repo_url":"https://github.com/ctuning/ck-tvm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":null,"task_name":"CPU"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":null,"task_name":"GPU"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1802.04799","atlas_url":"https://app.syntology.ai/?focus=1802.04799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.04799"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/ctuning/ck-tvm","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"unverified":5},"by_repo_kind":{"listed":{"samples":5,"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":"a77cd04423243725","entry":"ck_postprocess","repo":"ctuning/ck-tvm","repo_kind":"listed","path":"program/image-classification-tvm/ck_postprocess.py","file_url":"https://github.com/ctuning/ck-tvm/blob/HEAD/program/image-classification-tvm/ck_postprocess.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"a77cd04423243725"}},{"code_sha256_prefix":"2a7ba538c8f051e5","entry":"get_top5","repo":"ctuning/ck-tvm","repo_kind":"listed","path":"program/image-classification-tvm/classify.py","file_url":"https://github.com/ctuning/ck-tvm/blob/HEAD/program/image-classification-tvm/classify.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"2a7ba538c8f051e5"}},{"code_sha256_prefix":"e2f22913f77585d2","entry":"pre_path","repo":"ctuning/ck-tvm","repo_kind":"listed","path":"package/lib-tvm-master-cpu/custom.py","file_url":"https://github.com/ctuning/ck-tvm/blob/HEAD/package/lib-tvm-master-cpu/custom.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"e2f22913f77585d2"}},{"code_sha256_prefix":"38053dd65bd84275","entry":"setup","repo":"ctuning/ck-tvm","repo_kind":"listed","path":"package/lib-tvm-master-cpu/custom.py","file_url":"https://github.com/ctuning/ck-tvm/blob/HEAD/package/lib-tvm-master-cpu/custom.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"38053dd65bd84275"}},{"code_sha256_prefix":"e7267f02e6660d86","entry":"transform_image","repo":"ctuning/ck-tvm","repo_kind":"listed","path":"program/image-classification-tvm/classify.py","file_url":"https://github.com/ctuning/ck-tvm/blob/HEAD/program/image-classification-tvm/classify.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"e7267f02e6660d86"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}