GEMM-Like Convolution for Deep Learning Inference on the Xilinx Versal
نویسندگان
چکیده
We revisit a blocked formulation of the direct convolution algorithm that mimics modern realizations general matrix multiplication (gemm), demonstrating same approach can be adapted to deliver high performance for deep learning inference tasks on AI Engine (AIE) tile embedded in Xilinx Versal platforms. Our experimental results VCK190 shows an arithmetic throughput close 70% theoretical peak AIE 8-bit integer operands and convolutional layers arising ResNet-50 v.15+ImageNet.
منابع مشابه
Low-memory GEMM-based convolution algorithms for deep neural networks
Deep neural networks (DNNs) require very large amounts of computation both for training and for inference when deployed in the field. A common approach to implementing DNNs is to recast the most computationally expensive operations as general matrix multiplication (GEMM). However, as we demonstrate in this paper, there are a great many different ways to express DNN convolution operations using ...
متن کاملLearning Multiple Categories on Deep Convolution Networks
Deep convolution networks have proved very successful with big datasets such as the 1000-classes ImageNet. Results show that the error rate increases slowly as the size of the dataset increases. Experiments presented here may explain why these networks are very effective in solving big recognition problems. If the big task is made up of multiple smaller tasks, then the results show the ability ...
متن کاملDeep Learning for Causal Inference
In this paper, we propose the use of deep learning techniques in econometrics, specifically for causal inference and for estimating individual as well as average treatment effects. The contribution of this paper is twofold: 1.For generalized neighbor matching to estimate individual and average treatment effects, we analyze the use of autoencoders for dimensionality reduction while maintaining t...
متن کاملLearning Deep Inference Machines
Introduction. The traditional approach to structured prediction problems is to craft a graphical model structure, learn parameters for the model, and perform inference using an efficient– and usually approximate– inference approach, including, e.g., graph cut methods, belief propagation, and variational methods. Unfortunately, while remarkably powerful methods for inference have been developed ...
متن کاملFlex-Convolution (Deep Learning Beyond Grid-Worlds)
The goal of this work is to enable deep neural networks to learn representations for irregular 3D structures – just like in common approaches for 2D images. Unfortunately, current network primitives such as convolution layers are specifically designed to exploit the natural data representation of images – a fixed and regular grid structure. This represents a limitation when transferring these t...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Lecture Notes in Computer Science
سال: 2023
ISSN: ['1611-3349', '0302-9743']
DOI: https://doi.org/10.1007/978-3-031-40843-4_44