NASA is making RISC-V the go-to ecosystem for future space missions


SiFive is the first company to manufacture a chip that implements the RISC-V ISA.

They have now been chosen to provide the core CPU for NASA’s next-generation High-Performance Spaceflight Computing Processor (or HSPC).

HPSC is expected to be used in virtually every future space mission, from planetary exploration to missions to the surface of the Moon and Mars.

HPSC will use an eight-core SiFive® Intelligence X280 RISC-V vector core plus four additional SiFive RISC-V cores to provide 100 times the processing power of today’s space computers. This massive increase in computing power will help usher in new possibilities for a variety of mission elements such as autonomous rovers, image processing, space travel, guidance systems, communications and other applications….

The SiFive X280 is a multi-core capable RISC-V processor with vector extensions and SiFive Intelligence Extensions and is optimized for AI/ML computation at the edge. The X280 is ideal for applications that require single-threaded performance with high throughput while being under severe performance limitations. The X280 has demonstrated a 100x increase in processing power compared to today’s space computers..

For scientific and space workloads, the X280 offers orders of magnitude improvement over competing CPU solutions.

A business development manager at SiFive says their X280 core “demonstrates orders of magnitude performance gains over competing processor technology,” adding that the company’s intellectual property “enables NASA to leverage the support, flexibility and long-term viability of the fast-growing company globally.” RISC-V ecosystem.

“We’ve always said that with SiFive, the future knows no bounds, and we’re excited to see the impact of our innovations stretching far beyond our planet.”

And their announcement emphasizes that open hardware is a win for all:

The open and collaborative nature of RISC-V will allow the broad academic and scientific software development community to contribute and develop scientific applications and algorithms, as well as optimize the many mathematical functions, filters, transforms, neural network libraries and other software libraries to be part of a robust and long-term software -Ecosystems.


Comments are closed.