NI900 is a DSA processor based on 900 Series. NI900 is optimized with features specifically targeting AI applications.
AI DSA Processor - 9-Stage Pipeline, Dual-issue
Overview
Key Features
- Base Processor:
Can be configured into any RV32 or RV64 processor ---N900/U900/NX900/UX900. - RVV1.0 VPU:
Support VPU based on RISC-V V Extension (RVV1.0 Vector ISA), with 512-bit to 1024-bit VLEN configurable.- Lite-VPU: VPU can be configured to Lite-VPU, supporting frequently used embedded AI vector instructions and data types to save VPU area.
- Shared VPU across Multiple Cores: Multiple cores within one cluster can share one VPU while keeping software consistent in a SMP architecture to save area.
- NPU Accelerator:
Can be tightly coupled with CPU through NI900's IOCP(IO Coherent Port) to maintain cache coherence with CPU. - User Defined Instruction Interface:
Users can add customized scalar/vector instructions through Nuclei NICE interface, maintaining coherency with main CPU core.
Block Diagram
Technical Specifications
Short description
AI DSA Processor - 9-Stage Pipeline, Dual-issue
Vendor
Vendor Name
Related IPs
- 32-Bit & 64-Bit High Performance Processor - 9-Stage Pipeline, Dual-issue
- 32-Bit Automotive Processor - 9-Stage Pipeline, Dual-issue
- Efficient Linux-capable application core with a 9-stage in-order pipeline, an MMU, L1 and L2 caches, and cache coherency
- High-performance Linux-capable application core with a 12-stage dual-issue out-of-order pipeline, and cache coherency
- 32-Bit High Performance Processor - 2-Stage Pipeline, Single-issue
- 32-Bit & 64-Bit High Performance Processor - 6-Stage Pipeline, Single-issue