RISC-V Solution

Many AI models, one die

It is a multi-model edge AI inference chip that runs many AI models on a single die. It pairs a RISC-V host with the WZ-NPU matrix engine and the VAI inference architecture for real-time inference across vision, transformer and control workloads.

Architecture

RISC-V Host (schedules and manages concurrent AI models) COMPUTE ENGINES DATA MOVEMENT INTERFACES WZ-NPU Matrix Engine INT8 and mixed precision VAI Inference Engine executes models in hardware DMA and Data Mover keeps the engines fed On-chip Interconnect links host, engines, memory I/O PCIe Ethernet Camera Model and Weight Memory (on-chip SRAM and external DDR)

Clean architectural view. Every block is WIOWIZ IP on our own RISC-V host, and internal micro-architecture is not shown.

Specifications

CategoryMulti-model AI inference chip
Host CPURISC-V host
AI engineWZ-NPU matrix engine with VAI inference architecture
Workloadsvision, transformer and control models
PrecisionINT8 and mixed precision
Memoryon-chip SRAM and external DDR for model weights
Data movementDMA data mover
I/OPCIe, Ethernet, camera
IP ownershipWIOWIZ IP and WIOWIZ VIP
Design flowWIOWIZ in-house EDA
Statusarchitecture

RISC-V Architecture

A RISC-V host schedules and manages many concurrent AI models while the WZ-NPU and VAI inference engine execute them in hardware, on-chip and external memory hold model weights, and a DMA data mover keeps the engines fed. WIOWIZ IP.

Key Features

Many AI models on one chip

Multiple AI models run concurrently on a single die under RISC-V host scheduling.

Real-time vision and transformer inference

Vision and transformer workloads execute in real time directly in hardware.

WZ-NPU matrix acceleration

The WZ-NPU matrix engine accelerates model execution at INT8 and mixed precision.

RISC-V host scheduling

A RISC-V host schedules and manages the concurrent models feeding the engines.

On-chip and external model memory

On-chip SRAM and external DDR hold model weights close to the engines.

In-house IP

Architected, implemented and verified as WIOWIZ IP with our in-house EDA.

Applications

Real-time ADAS inference Edge AI Transformer and LLM inference Multi-workload AI