ZTA-Q: an Open-source RISC-V Platform for Accurate Quantized CNN Inference
By Yike Li ∗, Ajay Kumar M ∗, Vishnu PS ∗, Dimitrios S. Nikolopoulos ‡, Bo Ji ‡, Hans Vandierendonck §, Deepu John ∗
∗ University College Dublin, Ireland
‡ Virginia Tech, USA
§ Queen’s University Belfast, UK
Abstract
Low-precision inference is widely adopted in edge AI to reduce computational cost and memory footprint. However, existing open-source accelerator platforms provide limited end-to-end support for CNNs following the standard TensorFlow Lite integer inference scheme. This paper presents ZTA-Q, an open-source RISC-V-based platform that enables accurate deployment of TensorFlow Lite INT8 models. In addition to extending operator support, ZTA-Q provides a configurable post-processing datapath for studying how circuit-level approximations, including reduced multiplier precision, shared shift scaling, and simplified rounding, affect model accuracy. The proposed system is implemented on a Digilent Arty A7-100T FPGA and operates at 83.3 MHz. Evaluations on representative CNN models show that with LUT, register, and DSP overheads of 26.3%, 12.6%, and 150%, respectively, ZTA-Q limits the degradation in both top-1 and top-5 accuracy to within 0.25 percentage points.
Index Terms—Deep Learning, Hardware accelerators, RISC-V, Quantization, FPGA
To read the full article, click here
Related Semiconductor IP
- AI/ML Accelerator
- Controller for CXL
- UCIe Die-to-Die Chiplet Controller
- GDDR6 Controller
- Multi-core capable RISC-V processor with vector extensions
Related Articles
- Open-Source Design of Heterogeneous SoCs for AI Acceleration: the PULP Platform Experience
- An Open-Source Approach to Developing a RISC-V Chip with XiangShan and Mulan PSL v2
- A RISC-V Multicore and GPU SoC Platform with a Qualifiable Software Stack for Safety Critical Systems
- Leveraging RISC-V as a Unified, Heterogeneous Platform for Next-Gen AI Chips
Latest Articles
- A Secure dToF LiDAR SoC with Dual-Domain Fingerprinting and Event-Driven AFE Circuit Achieving Sensor-Level Attack Resilience
- ZTA-Q: an Open-source RISC-V Platform for Accurate Quantized CNN Inference
- Automated Pre-Silicon Verification of High-Speed DDR5 and LPDDR5/6 Memory Controllers: Closed-Loop Timing, Mode Register, and PHY Synchronization in UVM
- U-Sonic: An Open-Source 8-Channel Ultrasound Transmit IP in a 130 nm RISC-V SoC
- S-ALSA: Co-Design of Adiabatic Logic-based Sensing and Balanced Bit-Cells for Secure and Energy-Efficient MRAM