{"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/benchmarking-tpu-gpu-and-cpu-platforms-for","title":"Benchmarking TPU, GPU, and CPU Platforms for Deep Learning","arxiv_id":"1907.10701","date":"2019-07-24","proceeding":null,"authors":["Yu Emma Wang","Gu-Yeon Wei","David Brooks"],"abstract":"Training deep learning models is compute-intensive and there is an industry-wide trend towards hardware specialization to improve performance. To systematically benchmark deep learning platforms, we introduce ParaDnn, a parameterized benchmark suite for deep learning that generates end-to-end models for fully connected (FC), convolutional (CNN), and recurrent (RNN) neural networks. Along with six real-world models, we benchmark Google's Cloud TPU v2/v3, NVIDIA's V100 GPU, and an Intel Skylake CPU platform. We take a deep dive into TPU architecture, reveal its bottlenecks, and highlight valuable lessons learned for future specialized system design. We also provide a thorough comparison of the platforms and find that each has unique strengths for some types of models. Finally, we quantify the rapid performance improvements that specialized software stacks provide for the TPU and GPU platforms.","url_abs":"https://arxiv.org/abs/1907.10701v4","url_pdf":"https://arxiv.org/pdf/1907.10701v4.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":"benchmarking-tpu-gpu-and-cpu-platforms-for","repo_url":"https://github.com/Emma926/paradnn","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":null,"task_name":"CPU"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":null,"task_name":"GPU"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1907.10701","atlas_url":"https://app.syntology.ai/?focus=1907.10701","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.10701"}},"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/Emma926/paradnn","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"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":"f6bd89f80e36bc02","entry":"batch_norm_relu","repo":"Emma926/paradnn","repo_kind":"official","path":"paradnn/resnet_model.py","file_url":"https://github.com/Emma926/paradnn/blob/HEAD/paradnn/resnet_model.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":"f6bd89f80e36bc02"}},{"code_sha256_prefix":"543e9e36a2b9d04a","entry":"conv2d_fixed_padding","repo":"Emma926/paradnn","repo_kind":"official","path":"paradnn/resnet_model.py","file_url":"https://github.com/Emma926/paradnn/blob/HEAD/paradnn/resnet_model.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":"543e9e36a2b9d04a"}},{"code_sha256_prefix":"8bf0e3d1986303a5","entry":"fixed_padding","repo":"Emma926/paradnn","repo_kind":"official","path":"paradnn/resnet_model.py","file_url":"https://github.com/Emma926/paradnn/blob/HEAD/paradnn/resnet_model.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":"8bf0e3d1986303a5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}