SANTA CLARA, Calif., March 22, 2021—Expedera Inc., announced today that Sharad Chole, Chief Scientist and Co-founder of Expedera will present at Linley Spring Processor Conference, which will be held online on April 19-23, 2021.
What: Sharad Chole will present, “Building a Neural Engine with Unrivaled IPS/W” during the Edge AI session. In his presentation, Chole will introduce an innovative neural engine architecture that can run neural network models natively to achieve scalable energy-efficient performance.
Obtaining the highest IPS/W on real neural network workloads requires a complete rethink of the AI architecture. This presentation explores a unique approach leveraging networking principles that achieves high utilization and lowest latency while minimizing power, external bandwidth, and die area. The architecture uses a hardware scheduler, innovative memory management to handle compute and data efficiently, and a unified pipeline with zero context switch penalty. Executing neural networks natively with only metadata from each layer greatly simplifies the software stack.
When: April 19, 2021, 9:40am-11:40am
Register Online Now at https://www.linleygroup.com/events/register.php?num=51
Expedera provides scalable neural engine semiconductor IP cores that enable major gains in performance, power, and latency while reducing cost and complexity. The company’s neural engine architecture reduces memory usage to the theoretical minimum, eliminating memory bottlenecks that can limit application performance. Additional performance can be achieved by tuning the neural engine for specific workloads. Expedera’s team includes seasoned ASIC experts from Cisco, Nvidia, Abrizio, AMD, and Ericsson. The company has headquarters in Santa Clara, California. For more information, visit www.expedera.com.