SANTA ROSA, Calif. — Keysight Technologies Inc., a company that helps enterprises, service providers and governments accelerate innovation to connect and secure the world, announced PathWave Waveform Analytics, an edge-to-cloud computing application that improves anomaly detection and reduces data storage costs in pre-silicon validation using machine learning algorithms.

The automotive, IoT, and mobile devices markets are growing rapidly.  These markets need to leverage design thinking and innovative technology to enable semiconductor design engineers to quickly develop products that are robust, reliable, and secure against malicious intrusions while reducing power consumption.

Keysight’s PathWave Waveform Analytics is an advanced analytics software solution that includes a new data compression technology that enables long-duration waveform compression, high-resolution playback, and analysis exceeding several terabytes of data. Built-in machine learning improves the discovery of voltage and current anomalies as well as transient trends captured by the waveforms.

The application addresses challenges currently faced by semiconductor designers with the following key features and benefits:

  • Shortens analysis time in pre-silicon validation with patented machine learning algorithms that identify anomalies and outliers.
  • Reduces overall project costs by debugging in pre-silicon, which saves time in the costly post-silicon validation phase.
  • Improves design reliability with pre-and post-processing algorithms that accurately detect voltage and current spikes on power and signal waveforms.

“Highly power-efficient semiconductors require robust, reliable, and secure analytics during design qualification,” said Christopher Cain, vice president and general manager of Keysight’s Electronic Industrial Solutions Group. “Keysight’s innovative big-data waveform analytics solutions enable those semiconductor designers to automate design analysis, improving productivity of those tasks by up to 90%, thus accelerating their companies’ time-to-market opportunity.”

PathWave also enables designers to:

  • Identify outlier waveform shapes via a high-level view into clustering results.
  • Analyze data in high resolution with hierarchical clustering for multilevel drill-down,
  • Query and analyze any portion of the big vector data or waveform that was captured and stored.
  • Respond quickly, as minimum data is transferred between the edge computer and the server.
  • View an unlimited number of channels on a single dashboard, with options to pin or move the waveform in the interested channel for comparison.
  • Perform multiple dimensional comparisons and fine-tune the waveforms for analysis.