Tenstorrent develops AI IP with precision, anchored in RISC-V’s open architecture, delivering specialized, silicon-proven solutions for both AI training and inference. Our platforms are optimized for high performance per watt, ensuring scalable and adaptable technology for all AI-specific workloads.
RISC-V-based AI IP development for enhanced training and inference
Overview
Key Features
- RISC-V-based AI IP development for enhanced training and inference.
- Silicon-proven solutions tailored for AI workload optimization.
- Energy-efficient performance with industry-leading Perf/W.
- Scalable and configurable AI technology platforms.
- Direct control over AI IP with flexible, rapid integration.
Block Diagram
Technical Specifications
Related IPs
- Fast Access Controller – a plug-and-play IP solution for fast embedded Flash Programming and Memory Testing
- Warping Engine IP block for image transformation, HUDs and fish-eye correction
- UCIe/BoW BlueLynx™ Dual Mode PHY and subsystem IP for chiplet interconnect
- DDR Memory Controller IP for low power and high reliability
- ARC NPX Neural Processing Unit (NPU) IP supports the latest, most complex neural network models and addresses demands for real-time compute with ultra-low power consumption for AI applications
- Complete memory system supporting any combinations of SDR SDRAM, DDR, DDR2, Mobile SDR, FCRAM, Flash, EEPROM, SRAM and NAND Flash, all in one IP core