AI Processor IP Cores

Compare 78 AI Processor IP Cores from 39 vendors (1 - 10)

NPU IP for AI Vision and AI Voice
- 128-bit vector processing unit (shader + ext)
- OpenCL 3.0 shader instruction set
- Enhanced vision instruction set (EVIS)
- INT 8/16/32b, Float 16/32b
NPU IP for Wearable and IoT Market
- ML inference engine for deeply embedded system
  NN Engine
  Supports popular ML frameworks
  Support wide range of NN algorithms and flexible in layer ordering
NPU IP for Data Center and Automotive
- 128-bit vector processing unit (shader + ext)
- OpenCL 1.2 shader instruction set
- Enhanced vision instruction set (EVIS)
- INT 8/16/32b, Float 16/32b in PPU
- Convolution layers
LLM AI IP Core
- For sophisticated workloads, DeepTransformCore is optimized for language and vision applications.
- Supporting both encoder and decoder transformer architectures with flexible DRAM configurations and FPGA compatibility, DeepTransformCore eliminates complex software integration burdens, empowering customers to rapidly develop custom AI SoC (System-on-chip) designs with unprecedented efficiency.
CNN AI IP Core
- DeepMentor has developed an AI IP that combines low-power and high-performance features with the RISC-V SOC.
- This integration allows customers to quickly create unique AI SOC without worrying about software integration or system development issues.
- DeepLogCore supports both RISC-V and ARM systems, enabling faster and more flexible development.
Multi-core capable 64-bit RISC-V CPU with vector extensions
- The SiFive® Intelligence™ X180 core IP products are designed to meet the increasing requirements of embedded IoT and AI at the far edge.
- With this 64-bit version, X100 series IP delivers higher performance and better integration with larger memory systems.
Multi-core capable 32-bit RISC-V CPU with vector extensions
- The SiFive® Intelligence™ X160 core IP products are designed to meet the increasing requirements of embedded IoT and AI at the far edge.
- With this 32-bit version, X100 series IP can be optimized for power efficiency and severely area-constrained applications.
Multi-core capable RISC-V processor with vector extensions
- The SiFive® Intelligence™ X280 Gen 2 is an 8-stage dual issue, in-order, superscalar design with wide vector processing (512 bit VLEN/256-bit DLEN).
- It supports RISC-V Vectors v1.0 (RVV 1.0) and SiFive Intelligence Extensions to accelerate critical AI/ML operations.
Multi-core capable processor
- The SiFive® Intelligence™ X288 is a multi-core capable processor extensively optimized to meet the harsh environmental and stringent reliability requirements of aerospace and defense applications.
- The X288 features the powerful combination of a RISC-V 64-bit 8-stage dual-issue in-order scalar pipeline and a 512-bit vector length pipeline.
Neuromorphic Processor IP
- In-Memory Compute: Efficient analog MACs for AI workloads
- Compact Footprint: 0.28 mm² including peripheral circuitry
- Wishbone Interface: Easy integration with standard digital buses
- Ready for Tapeout: Fully synthesized and foundry-compatible

1
2
3
4
5
6
7
8
»
»»