AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Kernel Operations on the GPU, with Autodiff, without Memory Overflows

Benjamin Charlier, Jean Feydy, Joan Alexis Glaunès, François-David Collin, Ghislain Durif

JMLR 2021 · Architectures and efficiency › RNNs and normalization · approach: Distributed LLM inference systems · 99 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use PyKeOps symbolic reduction instead of PyTorch dense tensorsGaussian kernel matvec · N=10k, D=3runtime (ms): 9 -> 0.7Improved
use PyKeOps instead of PyTorch dense tensors at larger sizeGaussian kernel matvec · N=100k, D=3memory: out of mem -> 15.0Improved
use PyKeOps instead of TF-XLAGaussian kernel matvec · N=100k, D=3runtime (ms): 89 -> 15.0Improved
use PyKeOps instead of HalideGaussian kernel matvec · N=1M, D=3runtime (s): 3.8 -> 1.39Improved
use PyKeOps instead of TVMGaussian kernel matvec · N=1M, D=3runtime (s): 2.79 -> 1.39Improved
use hand-written C++ KeOps++ instead of PyKeOpsGaussian kernel matvec · N=10k, D=3runtime (ms): 0.7 -> 0.4Improved
use hand-written C++ KeOps++ instead of PyKeOpsGaussian kernel matvec · N=1M, D=3runtime (s): 1.39 -> 1.38No clear effect
use PyKeOps instead of Halide for code lengthGaussian kernel matvec · code sizelines of code: 15 -> 5Improved
use PyKeOps instead of TVM for code lengthGaussian kernel matvec · code sizelines of code: 17 -> 5Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy