RISC-V at NVIDIA: One Architecture, Dozens of Applications, Billions of Processors
By Frans Sijstermans, Vice President Multimedia Arch/ASIC, NVIDIA
Nine years ago, NVIDIA selected RISC-V for its embedded microcontrollers. Since then, we developed many processors and software stacks, all based on a common underlying hardware and software architecture. Today, every NVIDIA chip comes with multiple embedded RISC-V microcontrollers, each customized for a specific application. In the presentation, we will discuss our architecture as well as several applications. RISC-V’s rich feature set, configurability, extensibility, and active community are reasons why we stand by our 2015 decision to use RISC-V.
Related Semiconductor IP
- 64 bit RISC-V Multicore Processor with 2048-bit VLEN and AMM
- RISC-V AI Acceleration Platform - Scalable, standards-aligned soft chiplet IP
- 32 bit RISC-V Multicore Processor with 256-bit VLEN and AMM
- All-In-One RISC-V NPU
- ISO26262 ASIL-B/D Compliant 32-bit RISC-V Core
Related Videos
- Secure RISC-V Processor for Root of Trust
- LLM Inference on RISC-V Embedded CPUs
- RISC-V Design Innovations with Custom Extensions
- Using Formal For RISC-V Security