An Implementation of Back-Propagation Learning on GF11, a Large SIMD Parallel Computer

01/04/2018
by   Michael Witbrock, et al.
0

Current connectionist simulations require huge computational resources. We describe a neural network simulator for the IBM GF11, an experimental SIMD machine with 566 processors and a peak arithmetic performance of 11 Gigaflops. We present our parallel implementation of the backpropagation learning algorithm, techniques for increasing efficiency, performance measurements on the NetTalk text-to-speech benchmark, and a performance model for the simulator. Our simulator currently runs the back-propagation learning algorithm at 900 million connections per second, where each "connection per second" includes both a forward and backward pass. This figure was obtained on the machine when only 356 processors were working; with all 566 processors operational, our simulation will run at over one billion connections per second. We conclude that the GF11 is well-suited to neural network simulation, and we analyze our use of the machine to determine which features are the most important for high performance.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/04/2022

Forward Signal Propagation Learning

We propose a new learning algorithm for propagating a learning signal an...
research
10/07/2019

Work Stealing Simulator

We present in this paper a Work Stealing lightweight PYTHON simulator. O...
research
10/21/2017

High Performance Canny Edge Detector using Parallel Patterns for Scalability on Modern Multicore Processors

Canny Edge Detector (CED) is an edge detection operator commonly used by...
research
02/08/2022

Convergence of a New Learning Algorithm

A new learning algorithm proposed by Brandt and Lin for neural network [...
research
12/02/2021

A Discrete-event-based Simulator for Deep Learning at Edge

Novel smart environments, such as smart home, smart city, and intelligen...
research
11/18/2018

Analyzing Machine Learning Workloads Using a Detailed GPU Simulator

Most deep neural networks deployed today are trained using GPUs via high...
research
12/31/2017

Deterministic Computations on a PRAM with Static Processor and Memory Faults

We consider Parallel Random Access Machine (PRAM) which has some process...

Please sign up or login with your details

Forgot password? Click here to reset