SMM-Conv: Scalar Matrix Multiplication with Zero Packing for Accelerated Convolution

Amir Ofir, Gil Ben-Artzi
11/23/2024
cs.CV

No confident code implementation found for this paper. 3 possible matches can be shown below.

Abstract

We present a novel approach for accelerating convolutions during inference for CPU-based architectures. The most common method of computation involves packing the image into the columns of a matrix (im2col) and performing general matrix multiplication (GEMM) with a matrix of weights. This results in two main drawbacks: (a) im2col requires a large memory buffer and can experience inefficient memory access, and (b) while GEMM is highly optimized for scientific matrices multiplications, it is not well suited for convolutions. We propose an approach that takes advantage of scalar-matrix multiplication and reduces memory overhead. Our experiments with commonly used network architectures demonstrate a significant speedup compared to existing indirect methods.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 3 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Im2win: Memory Efficient Convolution On SIMD Architectures

82% match1 repo142023

Karatsuba Matrix Multiplication and its Efficient Custom Hardware Implementations

82% match1 repo2962025

CPUBone: Efficient Vision Backbone Design for Devices with Low Parallelization Capabilities

82% match1 repo182026

TabConv: Low-Computation CNN Inference via Table Lookups

81% match2024

An Efficient Matrix Multiplication Algorithm for Accelerating Inference in Binary and Ternary Neural Networks

81% match1 repo172024

Receptive Field Expanded Look-Up Tables for Vision Inference: Advancing from Low-level to High-level Tasks

80% match2025

Cite this paper

@article{ofir2024smmconv,
  title  = {SMM-Conv: Scalar Matrix Multiplication with Zero Packing for Accelerated Convolution},
  author = {Amir Ofir and Gil Ben-Artzi},
  year   = {2024},
  eprint = {2411.15659},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2411.15659v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2411.15659.svg)](https://codeofpaper.com/paper/2411.15659)

Discussion