Hacker News new | past | comments | ask | show | jobs | submit login
SparseDNN: Fast Sparse Deep Learning Inference on CPUs (Stanford) (arxiv.org)
15 points by Katydid 39 days ago | hide | past | favorite | 2 comments

I asked the author to compare the NN-512 dense convolver (https://NN-512.com) in his benchmark, as an alternative to Intel's closed source OpenVINO

Neural Magic (https://neuralmagic.com/) is also doing very sophisticated sparse convolution (closed source) on CPUs, and they benchmark against NN-512

Neural Magic achieves astonishing performance by exploiting sparsity

Thank you for listing my work! Feel free to reach out with any questions at zihengw@stanford.edu. Also see analogous work for GPUs / others at: https://www.oneseventwoai.com/

Applications are open for YC Summer 2021

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact