SiFive
Intelligence

SiFive Intelligence™ processors are designed to address the future requirements of AI technology to the edge, with high performance scalar and vector compute capability. Our AI Dataflow Processors are changing the way people architect their AI flows with power efficient, small footprint, high performance compute.

SiFive Intelligence Family

  • High-performance AI dataflow processor with scalable vector compute capabilities
  • AI workloads, data flow management, object detection, speech and recommendation processing

XM Series
SiFive Matrix Engine
4 X-Cores per cluster
1 Cluster = 16 TOPS (INT8)

X390
1024-bit Vector Length
Single/Dual Vector ALU
VCIX (2048-bit)

X380
512-bit Vector Length
Single Vector ALU
VCIX (1024-bit)

X288
Single Vector ALU
Split- lock with DCLS
CXL Host Interface

X280
512-bit Vector length
Single Vector ALU
VCIX (1024 -bit)

Building Solutions for
Modern AI/ML

AI/ML Challenges

Commonly used embedded control processors lack compute resources needed to execute inference workloads efficiently. Dedicated accelerators can work well for CNN layers, however:

  • They may not work for modern neural networks
  • They can be difficult to program, may have immature tools
  • In-house solutions may be expensive to maintain

The SiFive Intelligence™ solution is a better option: A high-performance control processor with scalable vector compute resources, all based on an open instruction set.  SiFive Intelligence is a scalable platform to meet ML processing requirements, from extremely low power to high-performance compute.

The SiFive Solution

SiFive Intelligence is an integrated software + hardware solution that addresses energy efficient inference applications. It starts with SiFive’s industry-leading RISC-V Core IP, adds RISC-V Vector (RVV) support, and then goes a step further with the inclusion of software tools and new SiFive Intelligence Extensions, vector operations specifically tuned for the acceleration of machine learning operations. These new instructions, integrated with a multi-core capable, Linux-capable, dual-issue microarchitecture, with up to 512b wide vectors, and bundled with TensorFlow Lite support, are well-suited for high-performance, low-power inference applications.

Learn more about the first announced SiFive Intelligence product, the SiFive Intelligence X280.

Software + Hardware
Machine Learning Solutions

SiFive Intelligence Solution Combines Hardware and Software

Software

Support for popular machine learning frameworks

  • Ease of deployment
  • Generality to new ML ops
  • Portability

Hardware

Family of ML processors with RVV

  • Built on silicon proven SiFive architectures
  • New SiFive Intelligence Extensions

Automatically Handle
Legacy Arm Neon Code

New SiFive Recode tool creates SiFive RISC-V Vector code from legacy Arm® Neon™ code

Protect your existing software investment; migrate with confidence

SiFive Intelligence Delivers Full
TensorFlow Lite Support

SiFive Intelligence News

New XM Series designed for accelerating high performance AI workloads

Read More

SiFive and Samsung Foundry Extend Partnership to Accelerate AI SoC Development

Read More

What’s New in AI & ML from SiFive

Read More

Tenstorrent Selects SiFive Intelligence X280 for Next-Generation AI Processors

Read More

Renesas and SiFive Partner to Jointly-Develop Next-Generation High-End RISC-V Solutions for Automotive Applications

Read More

SiFive Intelligence X280 as AI Compute Host: Google Datacenter Case Study

Read More

Contact Sales