The Gen4 CEVA-XC DSP architecture delivers unmatched performance for the most complex parallel processing workloads required for 5G endpoints and RAN, enterprise access points and other multigigabit low latency applications.
The Gen4 CEVA-XC unifies the principles of scalar and vector processing in a powerful architecture, enabling two-times 8-way VLIW and up to an unprecedented 14,000 bits of data level parallelism. It incorporates an advanced, deep pipeline architecture enabling operating speeds of 1.8 GHz at a 7nm process node using a unique physical design architecture for a fully synthesizable design flow, and an innovative multithreading design. This allows the processors to be dynamically reconfigured as either a wide SIMD machine or divided into smaller simultaneous SIMD threads. This architecture also features a novel memory subsystem, using 2048-bit memory bandwidth, with coherent, tightly-coupled memory to support efficient simultaneous multithreading and memory access.
Mike Demler, Senior Analyst at The Linley Group, commented: “The Gen4 CEVA-XC architecture demonstrates CEVA’s industry-leading commitment to driving DSP innovation forward for parallel processing. Its dynamically reconfigurable multithreading and high speed design, along with comprehensive capabilities for both control and arithmetic processing, sets the foundation for the proliferation of ASICs and ASSPs for 5G infrastructure and endpoints.”
The CEVA-XC16 for 5G to AI
The first processor based on the Gen4 CEVA-XC architecture is the multicore CEVA-XC16, which is ideal for the rapid deployment of different form factors of 5G RAN architectures including Open RAN (O-RAN), Baseband Unit (BBU) aggregation as well as Wi-Fi and 5G enterprise access points. The CEVA-XC16 is also applicable to massive signal processing and AI workloads associated with base station operation.
The CEVA-XC16 has been specifically architected with the latest 3GPP release specifications in mind, building on the company’s extensive experience partnering with leading wireless infrastructure vendors for their cellular infrastructure ASICs. The previous generation CEVA-XC4500 and CEVA-XC12 DSPs are powering 4G and 5G cellular networks today, and the new CEVA-XC16 is already in design with a leading wireless vendor for their next-generation 5G ASIC.
The CEVA-XC16 offers high parallelism of up to 1,600 Giga Operations Per Second (GOPS) that can be reconfigured as two separate parallel threads. These can run simultaneously, sharing their L1 Data memory with cache coherency, which directly improves latency and performance efficiency for PHY control processing, without the need for an additional CPU. These new concepts boost the performance per square millimeter by 50% compared to a single-core/single-thread architecture when massive numbers of users are connected in a crowded area. This amounts to 35% die area savings for a large cluster of cores, as is typical for custom 5G base station silicon.
High multithreading performance
Other key features of the CEVA-XC16 include:
- Latest generation dual CEVA-BX scalar processor units – enable true simultaneous multithreading;
- Dynamic allocation of vector units resources to processing threads – for optimal vector unit resource utilization and reduced overhead of complex flows;
- Advanced scalar control architecture and tools, with 30% code size reduction from previous generations, using latest dynamic branch prediction and loop optimizations, and an LLVM based compiler;
- New Instruction Set Architectures for FFT and FIR – delivering 2X performance improvement;
- Enhanced multiuser capabilities supporting massive bandwidth allocation of single user as well as fine granularity user allocations;
- Simple software migration path from previous generations CEVA-XC4500 and CEVA-XC12 DSPs.
Aviv Malinovitch, Vice President and General Manager of the Mobile Broadband Business Unit at CEVA, commented: “5G is a technology with multiple growth vectors spanning consumer, industrial, telecom and AI. Addressing these fragmented and complex use cases requires new thinking and practices for processors. Our Gen 4 CEVA-XC architecture encapsulates this new approach, enabling never-before-seen DSP core performance through groundbreaking innovations and design. The CEVA-XC16 DSP is evidence of this and serves to substantially reduce the entry barriers for OEMs and semiconductor vendors looking to benefit from the growing 5G Capex and Open RAN network architectures.”
The CEVA-XC16 is available for general licensing starting in Q2 2020.