IoT

Machine learning (ML) inference software from Synopsys is optimised for low power IoT applications that use convolutional neural networks (CNNs) and recurrent neural networks (RNNs).

The embARC Machine Learning Inference (MLI) software library supports the energy-efficient Synopsys DesignWare ARC EM DSP and HS DSP processors. It is claimed to boost performance up to 16X for 2D convolution layers compared to unoptimised implementations and accelerates RNNs up to a factor of five for a range of topologies, including those built with long short-term memory (LSTM) cells.

The embARC Machine Learning Inference software library is designed to help developers create power-efficient neural network system on chip (SoC) designs incorporating Synopsys’ DesignWare ARC EM and HS DSP processor IP. The software library provides developers with optimised functions to implement neural network layer types, significantly reducing processor cycle counts for applications that require low power and area, such as voice detection, speech recognition, and sensor data processing, says Synopsys.

The embARC MLI software library is available through embARC.org, a dedicated website that provides software developers access to free and open source software, drivers, operating systems, and middleware supporting ARC processors.

The embARC MLI software library supports ARC EMxD and HS4xD processors and provides a set of kernels for effective inference of small- or mid-sized machine learning models. It enables the efficient implementation of operations such as convolutions, long short-term memory (LSTM) cells, pooling, activation functions such as rectified linear units (ReLU), and data routing operations, including padding, transposing, and concatenation, while reducing power and memory footprint.

Synopsys cites the example of low-power neural network benchmarks such as CIFAR-10 running on an ARC EM9D processor which can achieve up to a four fold reduction in cycle count compared to competitive processors in the same class, claims Synopsys. The MLI library provides an average of three to five times performance improvement across a wide range of neural network layers, such as depth-wise 2D convolution, fully connected, basic RNN cells, and LSTM cells with a maximum performance boost of up to 16X for 2D convolution layers.

Picture credit: iStock

https://www.synopsys.com

One Idea Is All It Takes

Keysight Technologies is inviting undergraduate and graduate students worldwide to participate in its IoT Innovation Challenge. To enter, students must design a low-power sensor network strategy in one of two Innovation Tracks.

Students will compete via online written and video submissions to win an all-expenses-paid trip to the Grand Final at the World Maker Faire in New York, September 21-22, 2019. Six teams will advance to the final, where they will demonstrate their prototypes live before a panel of judges.

Prizes
The Grand Champion team will win $50,000 in cash and $50,000 of select Keysight test equipment for their school. Two first-place winners in each Innovation Track will win $25,000 in cash and $25,000 of select Keysight test equipment for their school.

Pick Your Innovation Track

Track 1: Smart Land
Design a sensor network strategy to cover one sq. km. of urban area to monitor and report on one or more of the following: air quality, water quality, data quality and sound quality, for at least one year.

Track 2: Smart Water
Design a sensor network strategy to cover a major waterway area to monitor and report, on one or more of the following: acidity, turbidity, and contaminants, for at least one year.

Calling All Students!
This is your chance to make the world better for billions. Are you ready to step up and innovate? Contest open to graduate and undergraduate students. Any student graduating before the Grand Final event is also eligible to participate.

Registration opens April 2019. Contest rules are forthcoming. Sign up now to be notified when registration goes live. #KeysightIoTChallenge

Signup here

Read Keysight News