The X100 Series targets far edge compute and IoT applications, achieving high efficiency in a compact footprint and delivering a new level of AI functionality to the deeply embedded edge, which is heavily constrained by power and area. Ideal industries include automotive, autonomous robotics, industrial automation and smart IoT.
SiFive Intelligence
X100 Series
SiFive Intelligence
X100 Series Gen 2
SiFive Intelligence
X160 & X180 Key Features
32-bit or 64-bit RISC-V CPU (X160 or X180)
- Dual issue 8-stage scalar pipeline, integer and floating point
- Wide physical address space for larger memory systems
Vector Pipeline
- 2nd Generation Intelligence vector architecture
- 128b VLEN (register width), 64b DLEN (datapath width)
High Performance Coprocessor Interfaces
- 2nd Gen SSCI + VCIX accelerator interfaces
- Tight integration allows very low latency
Configurable L1 memory system
- Instruction cache, up to 64KiB, Data cache, up to 256KiB
- I & D Tightly Integrated Memories (TIMs) up to 2MiB each
Application Spotlight
Case Study: Standalone Vector CPU Use Case
Tier 1 US Semiconductor Company Chose X100 to Power Their Next Generation Edge AI SoCs.
Case Study: Accelerator Control Unit Use Case
Tier 1 US Semiconductor Company Licensed SiFive X100 for Industrial Edge AI Applications.
Download Intelligence X100 Series
Product Briefs
Learn more about SiFive Intelligence X100 Series benefits! Download our product briefs today or contact our sales team with any questions.
SiFive Intelligence Family
X200 Series
Intelligence
- 512-bit Vector length
- Single Vector ALU
- SSCI and VCIX (1024-bit)
X300 Series
Intelligence
- 1024-bit Vector Length
- Single/Dual Vector ALU
- SSCI and VCIX (2048-bit)
XM Series
Intelligence
- Scalable Matrix Engine
- 4 X300 cores per cluster
- 1 Cluster = 16 TOPS (INT8)