{"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/gpu-kernels-for-block-sparse-weights","title":"GPU Kernels for Block-Sparse Weights","arxiv_id":null,"date":"2017-12-01","proceeding":"OpenAi 2017 12","authors":["Scott Gray","Alec Radford and Diederik P. Kingma"],"abstract":"We’re releasing highly optimized GPU kernels for an underexplored class of neural network architectures: networks with block-sparse weights. The kernels allow for efficient evaluation and differentiation of linear layers, including convolutional layers, with flexibly configurable block-sparsity patterns in the weight matrix. We find that depending on the sparsity, these kernels can run orders of magnitude faster than the best available alternatives such as cuBLAS. Using the kernels we improve upon the state-of-the-art in text sentiment analysis and generative modeling of text and images. By releasing our kernels in the open we aim to spur further\r\nadvancement in model and algorithm design.","url_abs":"https://blog.openai.com/block-sparse-gpu-kernels/","url_pdf":"https://s3-us-west-2.amazonaws.com/openai-assets/blocksparse/blocksparsepaper.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":"gpu-kernels-for-block-sparse-weights","repo_url":"https://github.com/openai/blocksparse","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/sentiment-analysis-on-cr","task":"Sentiment Analysis","dataset":"CR","model":"Block-sparse LSTM","rank_in_archive_order":4,"of":9,"metrics":{"Accuracy":"92.2"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-imdb","task":"Sentiment Analysis","dataset":"IMDb","model":"Block-sparse LSTM","rank_in_archive_order":19,"of":49,"metrics":{"Accuracy":"94.99"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-sst-2-binary","task":"Sentiment Analysis","dataset":"SST-2 Binary classification","model":"Block-sparse LSTM","rank_in_archive_order":41,"of":87,"metrics":{"Accuracy":"93.2"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-yelp-binary","task":"Sentiment Analysis","dataset":"Yelp Binary classification","model":"Block-sparse LSTM","rank_in_archive_order":11,"of":20,"metrics":{"Error":"3.27"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}