草榴社区 Cloud
Cloud native EDA tools & pre-optimized hardware platforms
Request a Free Trial →
What if your car could alert you to an impending brake failure well before it happened? Or your smart speaker could signal that it has been hacked? Or your phone’s power utilization suddenly spikes without an obvious reason? For valuable clues, you can look to the silicon inside these electronic systems. Chip parameters like performance, power consumption, safety, and security could ultimately impact how well the end device or system operates. The challenge, however, lies in uncovering that treasure trove of data. What happens with devices once they leave the fab and are deployed in the field has historically been a mystery. Silicon lifecycle management (SLM) technology, a relatively new category of offering, provides insights into chips in all stages of their lifecycles.
In this blog post, I’ll explain how SLM technology provides valuable insights from design to manufacturing and how embedded AI extends SLM to bring a new level of benefit for in-field operation. Read on to learn how you can better understand your silicon, inside and out.
Staving Off Device Attacks and Failures
For safety-critical applications like advanced driver assistance systems (ADAS), autonomous vehicles, and medical devices as well as for equipment that relies on continuous uptime, performance monitoring and predictive maintenance of the silicon are hugely beneficial. For example, aging effects may degrade the silicon that operates a vehicle’s braking system, eventually leading to brake failure if not detected in advance. Similarly, aging effects or a lack of optimization can cause power utilization to go up, impacting battery life of portable IoT devices. Voltage can spike when there’s a malicious attack, while changes in data traffic on certain data buses can raise suspicions. With SLM technology integrated onto the chips, these scenarios can be flagged in time to prevent or mitigate negative outcomes.
Based on the more established product lifecycle management methodology, the emerging SLM applies the same holistic approach and types of capabilities to ICs. According to a 2020 research paper by , “Analytics can improve design calibration, accelerate yield improvements, reduce testing time and time to market and, most importantly, predict failures or deterioration in the field.” The process involves embedding sensors and monitors into the silicon chips—this could encompass process/voltage/temperature (PVT) sensors, design-for-test (DFT) and built-in self-test (BIST) sensors, structural and functional monitors, embedded on-chip analysis tools, and data transport resources. The data collected is then funneled into a centralized database, where analytics engines extract useful insight to optimize the silicon throughout its lifecycle.
Consider, for example, the testing lifecycle phase. Chip data pulled off the test floor can be analyzed, with optimization insights fed back into the tester or other design tools to apply the recommended optimizations.
While solutions are well established for the early stages of the silicon lifecycle, there remains opportunity to enhance in-field optimization. To optimize hardware once it has been deployed in the field, whether that’s a car, a data center, or an IoT device, an SLM agent needs to be installed in the system to monitor it and access its data. This is where real-time, AI-based optimization comes into play. As it has positively impacted so many application areas, chip design included, AI provides the analytical prowess and speed to provide continuous system optimization.
Extending Pioneering SLM Platform with AI
草榴社区 introduced the industry’s first SLM platform in 2020, tapping into our leading implementation, verification, test, and IP solutions to deliver a comprehensive, holistic methodology for chipmakers and system integrators to better manage critical issues across the chip’s lifespan. Along the way, we’ve continued to enhance our SiliconMAX? SLM platform with:
- , including PVT sensors
- for semiconductor test and manufacturing
- And, through our , real-time, AI-based optimization technology
Concertio’s autonomous software agent is installed on systems to continuously monitor the interactions between operating applications and the underlying system environment. It uses reinforcement learning to refine its understanding of the system and predict how the system will perform. With these insights, the software agent’s optimization engine can adapt and reconfigure the system dynamically. The result? A self-tuning system that remains optimized for its current usage.
The early-stage elements of the SiliconMAX SLM platform are also available in the cloud; in-field optimization technologies will be cloud-ready down the road, as the Concertio technology brings support for AI at the edge with big data analytics in the cloud.
What makes the SiliconMAX platform particularly effective is that it’s closely linked with an array of 草榴社区 solutions, including:
- The 草榴社区 TestMAX? family of test products and technologies for automated integration of monitors and sensors into the RTL or gate-level design as well as for sharing of on-chip monitoring and data transport infrastructure
- 草榴社区 Fusion Design Platform? for unique design performance optimizations, while keeping design flows and schedules intact
- 草榴社区 Fusion Compiler? RTL-to-GDSII solution, which ensures that monitors are integrated while maintaining optimal PPA design metrics
Intelligent Insights for Smarter Chip Design
Semiconductors play an integral role in so many of the devices and systems we rely on each day. Given this, any technique or technology that can make these components perform better and with greater power efficiency, safety, and security should be embraced by chipmakers, system integrators, and end users alike. Enhanced with reinforcement learning, SLM technology that spans early design stages to in-field deployment can help ensure that the electronic products we use will live up to or even exceed our expectations.