Matrix multiplication

Quantum mechanics

Computational science

Xeon Phi

Engineering

Node (physics)

Computer graphics (images)

Theoretical computer science

Operating system

Compiler

Parallel computing

Computer science

Software

Physics

Xeon

Computer architecture

Graph

SIMD

Computer engineering

Artificial intelligence

Quantum

Structural engineering

Coprocessor

Deep learning

Artificial neural network

Convolutional neural network

Dynamic compilation

Convolution (computer science)

Convolution layers are prevalent in many classes of deep neural networks, including Convolutional Neural Networks (CNNs) which provide state-of-the-art results for tasks like image recognition, neural machine translation and speech recognition. The computationally expensive nature of a convolution operation has led to the proliferation of implementations including matrix-matrix multiplication formulation, and direct convolution primarily targeting GPUs. In this paper, we introduce direct convolution kernels for ×86 architectures, in particular for Xeon and Xeon Phi systems, which are implemented via a dynamic compilation approach. Our JIT-based implementation shows close to theoretical peak performance, depending on the setting and the CPU architecture at hand. We additionally demonstrate how these JIT-optimized kernels can be integrated into a light-weight multi-node graph execution model. This illustrates that single- and multi-node runs yield high efficiencies and high image-throughputs when executing state-of-the-art image recognition tasks on CPUs.

Anatomy of High-Performance Deep Learning Convolutions on SIMD Architectures