Mentor’s analog/RF/mixed-signal verification tools scale to 10,000 cores on Microsoft Azure

• Mentor demonstrates highly scalable cloud computing capacity for AMS verification workloads on Microsoft Azure

Mentor, a Siemens business, today announced that its analog/RF/mixed-signal (AMS) verification software recently scaled up to 10,000 cores on the Microsoft Azure cloud platform, exhibiting near-linear performance while handling runtime-intensive library characterization and analog/mixed-signal verification workloads.

For custom IC design teams, the proven scalability of Mentor’s AMS product portfolio translates to a dramatic reduction in turnaround time. Today’s libraries are characterized across more than 100 process, voltage and temperature (PVT) corners, requiring several days of characterization time, even with hundreds of CPU cores. By leveraging cloud platforms running Mentor’s AMS verification products across as many as 10,000 CPU cores, these characterization tasks can be completed in just a few hours. This significant time savings enables design teams to accelerate production schedules and deliver superior quality products faster.

Microsoft Azure validated the cloud scalability of Mentor’s AMS verification product using the EDA leader’s library characterization suite and foundry-certified Analog FastSPICE (AFS™) & Eldo circuit simulators to characterize standard cell libraries across a broad range of PVT values.

“Mentor is pleased to continue our collaboration with Microsoft Azure to address peak library characterization and AMS verification workloads by leveraging world-class cloud platforms,” said Ravi Subramanian, general manager and vice president of Mentor’s IC Verification Solutions Division. “Our customers have shown us the importance of utilizing burst capacity for peak demand to meet today’s design schedules, and our work with Azure has proven that we can jointly provide a robust, secure and highly scalable platform tailored to address this critical customer requirement.”

The availability of virtually unlimited processing performance in the era of cloud computing has challenged electronic design automation (EDA) software providers to develop IC design tools that deliver the levels of extreme performance necessary to leverage the vast compute capacity of today’s cloud offerings. This in turn supports chipmakers’ increasingly large designs for ICs targeting the artificial intelligence, autonomous vehicle and other fast-growing markets.

"Mentor’s results underscore the opportunity to reduce silicon design cycle times and improve verification quality, by leveraging cloud ready solutions like Mentor’s AMS verification product, optimized with the scalability and flexibility of using Microsoft Azure,”  said Kushagra Vaid, GM and distinguished engineer, Azure, Microsoft Corp.

Mentor’s AMS verification products are used by semiconductor customers worldwide, addressing the most complex AMS verification challenges for circuit simulation, mixed-signal verification and variation-aware design and characterization. Mentor continues to work closely with cloud partners such as Microsoft Azure, enabling semiconductor customers to utilize cloud-computing resources for today’s AMS verification needs.