Pith. sign in

REVIEW 2 cited by

Fast Convolutional Nets With fbfft: A GPU Performance Evaluation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1412.7580 v3 pith:XFUHDH6C submitted 2014-12-24 cs.LG cs.DCcs.NE

Fast Convolutional Nets With fbfft: A GPU Performance Evaluation

Nicolas Vasilache , Jeff Johnson , Michael Mathieu , Soumith Chintala , Serkan Piantino , Yann LeCun This is my paper
classification cs.LG cs.DCcs.NE
keywords nvidiaconvolutionalconvolutionsfbfftimplementationperformanceconvolutioncufft
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We examine the performance profile of Convolutional Neural Network training on the current generation of NVIDIA Graphics Processing Units. We introduce two new Fast Fourier Transform convolution implementations: one based on NVIDIA's cuFFT library, and another based on a Facebook authored FFT implementation, fbfft, that provides significant speedups over cuFFT (over 1.5x) for whole CNNs. Both of these convolution implementations are available in open source, and are faster than NVIDIA's cuDNN implementation for many common convolutional layers (up to 23.5x for some synthetic kernel configurations). We discuss different performance regimes of convolutions, comparing areas where straightforward time domain convolutions outperform Fourier frequency domain convolutions. Details on algorithmic applications of NVIDIA GPU hardware specifics in the implementation of fbfft are also provided.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. The Indirect Convolution Algorithm

    cs.CV 2019-07 unverdicted novelty 7.0

    The Indirect Convolution algorithm avoids im2col by using an indirection buffer, reducing memory overhead proportionally to input channels and outperforming GEMM-based methods by up to 62% for convolutions requiring t...

  2. Flash EQ-Linear: Accelerating Equivariant Linear Layers via Group-wise Discrete Fourier Transform

    cs.CV 2026-07 conditional novelty 6.0

    EQ-Linear can be computed exactly as pointwise multiplications in the Fourier domain along the group dimension, cutting FLOPs from NDC to ~2NDC/T and yielding up to ~2× wall-clock speedups for p4 equivariant transformers.