Cadence: Tensilica ConnX B20 DSP boosts performance by up to 30X for 5G communications

Cadence Design Systems announced the Cadence Tensilica ConnX B20 DSP IP, the highest-performing DSP in the popular ConnX family. Based on a deeper processor pipeline architecture, the ConnX B20 DSP provides a faster and more power-efficient solution for the automotive and 5G communications markets, including next-generation radar, lidar, vehicle-to-everything, user equipment infrastructure and IoT applications. With an enhanced instruction set architecture and clock-speed increase, the ConnX B20 DSP processes parts of the communication processing chain up to 30X faster and parts of the radar/lidar processing chain up to 10X faster compared to the popular Tensilica ConnX BBE32EP DSP. Further expanding the ConnX family, Cadence has introduced the ConnX B10 DSP, which delivers half the vector width of the ConnX B20 DSP for applications requiring less parallelism.

Both the trend toward higher resolution imaging radar with more antennas for autonomous driving applications and the emergence of 5G mobile equipment and infrastructure demand significantly more processing power. In addition, consumer/industrial radar, automotive V2X and 5G IoT applications all require low-energy processing solutions. With the addition of the ConnX B20 and B10 DSPs, the ConnX family excels at meeting the demands for higher performance and low energy consumption.

Software compatible with the rest of the ConnX DSP family (the ConnX BBE16/32/64EP), the ConnX B20 DSP has a 512-bit vector width up to 128 MACs, can load 1024 bits of data each cycle and achieves 1.4GHz or greater frequency in 16nm process technology. This extends the ConnX family to serve an even broader range of performance. Customers have a variety of algorithm acceleration options to reduce cycle counts, including higher precision with either 32-bit fixed-point operations (including operations to optimize MAC, FFT and FIR) with native complex support, or single-/half-precision vector floating-point (VFPU) operations with half precision at 2X the single-precision throughput. This flexibility allows customers to choose higher precision only when needed. In addition, an extended VFPU option enables support for complex floating-point operations and doubles the real floating-point operations at the same vector width typically used in the front end of the radar processing chain. The communications option accelerates forward-error correction (FEC) in lower bit-rate communication applications seeking software-defined radio solutions.

The ConnX B20 DSP’s native 32-bit support option and higher clock speed deliver up to 10X faster performance for parts of the radar/lidar processing chain compared to the popular ConnX BBE32EP DSP used today. With the clock speed increase and FEC acceleration option,  the ConnX B20 DSP is also up to 30X faster for parts of the communication processing chain compared to the ConnX BBE32EP DSP. Both the ConnX B20 and B10 DSPs provide customers with more performance and efficiency while preserving their existing architecture and development environment. Customers can quickly optimize for an application’s power, performance, and area (PPA) requirements with easy scalability and extensive configurability within the compatible ConnX DSP family. In addition, they can perform fast software development with advanced compiler, debug and simulation tools as well as an optimized math library and application examples with source code.

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.