SiFive has announced the integration of NVIDIA NVLink Fusion into its high-performance RISC-V compute platforms, enabling coherent, high-bandwidth connectivity between SiFive CPUs and NVIDIA GPUs or other accelerators. This collaboration supports the development of scalable, energy-efficient AI infrastructure for next-generation data centers.
As AI workloads continue to outpace traditional power and scaling constraints, data center architects are turning to heterogeneous, co-designed systems that prioritize efficiency and flexibility. SiFive’s RISC-V solutions, already proven in high-performance applications, gain significant new capabilities through NVLink Fusion, allowing tighter integration with NVIDIA’s ecosystem while preserving the openness and customizability that define RISC-V.
The addition of NVLink Fusion enables coherent data sharing and high-bandwidth communication between SiFive CPUs and NVIDIA accelerators, minimizing latency and maximizing overall system throughput. This is particularly valuable for large-scale AI deployments where data movement overhead can limit performance gains. SiFive’s platforms allow tailoring of CPU configurations to specific workload needs—such as optimizing for inference efficiency or training throughput—while maintaining ecosystem compatibility and portability across the growing RISC-V software stack.
The collaboration reflects a broader shift toward systems that combine open CPU architectures with advanced interconnects and specialized accelerators. By removing traditional CPU-to-accelerator limitations, SiFive and NVIDIA enable cloud providers, system vendors, and hyperscalers to build more efficient, purpose-built AI infrastructure that scales without excessive power consumption.
“AI infrastructure is no longer built from generic components, it is co-designed from the ground up,” said Patrick Little, President and CEO of SiFive. “By integrating NVLink Fusion with SiFive’s high-performance compute subsystems, we’re enabling customers with an open and customizable CPU platform that pairs seamlessly with NVIDIA’s AI Infrastructure to deliver exceptional efficiency at data center scale.”
“With SiFive, we’re bringing our coherent, high-bandwidth NVLink interconnect to the RISC-V ecosystem,” said Jensen Huang, founder and CEO of NVIDIA. “This provides the flexibility to combine customizable RISC-V CPUs with NVIDIA accelerators to build scalable, power-efficient and specialized AI infrastructure – and move from innovation to deployment faster than ever.”
This partnership positions SiFive as a key enabler of heterogeneous AI computing, where open standards meet world-class acceleration to meet the evolving demands of modern data centers.
About SiFive
As the pioneers who introduced RISC-V to the world, SiFive is transforming the future of computing by bringing the limitless potential of RISC-V to the highest performance and most data-intensive applications in the world. SiFive’s RISC-V compute platforms have enabled leading technology companies around the world to innovate, optimize and deliver the most advanced solutions of tomorrow across every market segment of chip design, including artificial intelligence, machine learning, automotive, data center, mobile, and consumer. With SiFive, the future of RISC-V has no limits.
TechIntelPro empowers B2B technology decision-makers with the latest industry trends, deep insights, leadership perspectives and actionable intelligence to drive both organizational and professional milestones—and thrive on the tech pulse.