Reprogrammability

Google TPU v2 Training Chip

by
Google TPU v2 Training Chip

In 2017, Google updated their TPU series. Google referred to this generation of TPU as a “domain-specific supercomputer for training neural networks.” It is evident that compared to TPU v1, which focused on inference scenarios, TPU v2 shifted its design focus towards training-related scenarios. Looking back at history, around 2017, groundbreaking work in deep learning … Read more

Unleashing the Power and Flexibility of FPGA in Embedded Design

by
Unleashing the Power and Flexibility of FPGA in Embedded Design

Although FPGAs bring powerful capabilities and flexibility to embedded design, the additional development processes also introduce new complexities and limitations to the design work. Integrating traditional hardware-FPGA-software design processes and fully utilizing the reprogrammable features of FPGAs is one of our solutions. As FPGA technology gradually extends to military electronic systems and almost all areas … Read more