SiFive’s new XM Series offers an extremely scalable and efficient AI compute engine. By integrating scalar, vector, and matrix engines, XM Series customers can take advantage of very efficient memory bandwidth. The XM Series also continues SiFive’s legacy of offering extremely high performance per watt for compute-intensive applications. To speed up development time, SiFive is also open sourcing the SiFive Kernel Library.
SiFive Intelligence
XM Series
XM Series
SiFive Intelligence
XM Series Key Features
- SiFive Matrix Engine
- Fat Outer Product design
- Tightly integrated with 4 X-Cores
- Deep fusion with vector units - 4 X-Cores per cluster
- Each with dual vector units
- Executes all other layers e.g. activation functions
- New exponential acceleration instructions - New matrix instructions
- Fetched by scalar unit
- Source data comes from vector registers
- Destination to each matrix accumulator
- 1 Cluster = 16 TOPS (INT8), 8 TFLOPS (BF16) per GHz
- 1TB/s sustained bandwidth per XM Series cluster
- XM clusters connect to memory in 2 ways:
- CHI port for coherent memory access
- High bandwidth port connected to SRAM for model data - Host CPU can be RISC-V, x86 or Arm (or not present)
- System can scale across multiple dies using CHI
SiFive Intelligence Family
X200 Series
Intelligence
- 512-bit Vector length
- Single Vector ALU
- VCIX (1024-bit)
X300 Series
Intelligence
- 1024-bit Vector Length
- Single/Dual Vector ALU
- VCIX (2048-bit)
Contact Sales
Core IP Families
Automotive
SiFive Automotive™ solutions provide a range of high-end application and real-time processors, delivering industry-leading performance, minimal area, and low power consumption. ISO 21434, ISO26262 ASIL B, ASIL D and split-lock certifications.
Intelligence
Intelligence embraces a software-first approach to processor design, addressing the future needs of deploying ML and AI at the edge. It provides high-performance, scalable vector and matrix compute capabilities, adaptable to evolving workloads.
Performance
The SiFive Performance™ family of RISC-V processors is designed for maximum throughput and performance efficiency for a range of application from datacenter workloads, ranging from Web servers and multimedia processing, Networking/Storage to consumer applications like TV, wearables and other smart devices requiring AI functionality.