Papers › GPU Kernels for Block-Sparse Weights

GPU Kernels for Block-Sparse Weights

1 Dec 2017OpenAi 2017 12archive 2025-07-28

Scott Gray, Alec Radford and Diederik P. Kingma

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 advancement in model and algorithm design.

PaperPDFCode

Code

openai/blocksparse mentioned in papertf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Sentiment Analysis

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Sentiment Analysis CR Block-sparse LSTM Accuracy 92.2 #4 of 9 Archive leaderboard report
Sentiment Analysis IMDb Block-sparse LSTM Accuracy 94.99 #19 of 49 Archive leaderboard report
Sentiment Analysis SST-2 Binary classification Block-sparse LSTM Accuracy 93.2 #41 of 87 Archive leaderboard report
Sentiment Analysis Yelp Binary classification Block-sparse LSTM Error 3.27 #11 of 20 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections