InsideDSP — In-depth analysis and opinion

Jeff Bier’s Impulse Response—A Tale of Two Chips

In 2012, I wrote about how mobile application processors were becoming increasingly popular in embedded systems. Since then, this trend has accelerated, fueled in part by low-cost development boards aimed at enabling embedded system developers to evaluate these chips and quickly create prototype products. For embedded systems developers, these boards (some developed by chip suppliers and some from their partners) can seem like a dream come true: they're inexpensive and energy-efficient, and Read more...

Case Study: Squeezing Big Algorithms into Small Power Budgets Enables Mobile Audio Quality

Today's smartphones are technological marvels that deliver an extraordinary range of capabilities from GPS-based navigation to sophisticated photography. But sometimes we just want to make a phone call. And particularly when we're on the move, who hasn't struggled to hear the other party or to be heard on a mobile call? Realizing the importance of intelligible phone calls – not to mention a strong need to differentiate their products – smartphone manufacturers are incorporating increasingly Read more...

Freescale Introduces New Embedded Processors and Modules

Back in early 2013, the smartphone market was red hot, as was demand for Amazon's Kindle and other e-book readers. And the tablet market, although comparatively nascent, was in a rapid growth phase, as was interest in alternative computer platforms such as Google's Chrome O/S-based products. The substantial processing demands of these and other similar applications are evident in the formidable resources integrated within Freescale Semiconductor's i.MX 6 family introduced that same year: one to Read more...

Sensory Adds Deep Learning Support to TrulyHandsFree

Sensory's TrulyHandsFree software, which InsideDSP last covered at its v3 introduction in early 2013, precedes limited-vocabulary speech recognition with voice detection involving a specific key word or phrase. And with latest version 4.0, Sensory adopts convolutional (i.e. "deep learning") neural network (CNN) techniques. Jeff Bier began a recent editorial with the following statement: Lately, neural network algorithms have been gaining prominence in computer vision and other fields where Read more...

Jeff Bier’s Impulse Response—The Memory Bandwidth, Stupid!

"The economy, stupid" was one of the phrases that strategist James Carville hung on a sign in Bill Clinton's 1992 presidential campaign headquarters – a reminder to focus on what's most important. In a similar vein, the reminder "It's the memory bandwidth, stupid" should probably be prominently displayed wherever computer vision software developers work. As I've written about before, it has recently become feasible to implement sophisticated computer vision algorithms on embedded and mobile Read more...

Case Study: For Ultra Low Power, the Right Algorithms Are Key

When engineers set out to design a system (such as a wearable or handheld device) for minimum power consumption, there's a tendency to focus on selecting the most energy efficient processor and on optimizing the software for maximum efficiency. These are important steps, to be sure, but when the application is based on digital signal processing, choosing the right algorithms can be even more important. Digital signal processing is, of course, fundamentally the application of math to signals, Read more...

NVIDIA Toolsets Target GPU Acceleration of Deep Learning, Other Algorithms for High-Performance Computing

"General-purpose GPU" (or "GPGPU") refers to the use of graphics processors for a variety of non-graphics tasks, and is a frequently discussed topic here at InsideDSP. GPUs are massively parallel processors, originally designed to only handle vertex and pixel operations. However, with the emergence of programmable shader-based architectures beginning with NVIDIA's mainstream GeForce 3 line in 2001 and joined by ATI Technologies' (now AMD's) Radeon 9700 and derivatives unveiled the following Read more...

Jeff Bier’s Impulse Response—Neural Network Processors: Has Their Time Come?

Lately, neural network algorithms have been gaining prominence in computer vision and other fields where there's a need to extract insights based on ambiguous data. As I wrote last year, classical computer vision algorithms typically attempt to identify objects by first detecting small features, then finding collections of these small features to identify larger features, and then reasoning about these larger features to deduce the presence and location of an object of interest (such as a face Read more...

Case Study: Algorithm Optimizations Efficiently Utilize Processor Features

Your company’s core expertise lies in developing innovative digital signal processing algorithms, not in porting and optimizing those algorithms to any of the dozens of processors that your customers use. But optimized implementations are often critical to enable customers to utilize your algorithms within their processing performance and power budgets. Good compilers are definitely helpful, but they invariably leave significant performance on the table. Engaging the processor experts at BDTI Read more...

Analog Devices' SHARC Doubles Up, Adds ARM Option

The SHARC DSP family has long been a design staple of mid-range and high-end audio, industrial and other digital signal-processing intensive applications. With its two new series of products, Analog Devices delivers dual-core SHARC to the market for the first time. And the ADSP-SC58x devices also integrate an ARM processor core to tackle system control code functions (Figure 1). Figure 1. A migration from the 65 nm to 40 nm process node enables a high degree of integration in Analog Devices' Read more...