Publications

AESIP: Arch-aware ASIP-ISA Co-Design via Program Synthesis, Equality Saturation, and External Don’t Cares

Published in ISCA 2026 (Under review), 2026

We propose AESIP, a hardware-software co-optimization framework for efficient ASIP design that leverages e-graphs, program synthesis, and don’t care-based hardware optimization to achieve up to 29.7% area reduction.

Recommended citation: Haoran Jin, Nathaniel Bleier. AESIP: Arch-aware ASIP-ISA Co-Design via Program Synthesis, Equality Saturation, and External Don't Cares. ISCA 2026 (Under review).

Mozart: An Ecosystem-Accelerator Codesign Framework for Composable, Heterogeneous Chiplet-based Neural Network Accelerators

Published in ASPLOS 2026 (Under Submission), 2025

We present Mozart, a novel ecosystem-accelerator codesign framework that enables systematic composition of heterogeneous chiplet-based neural network accelerators with increased reuse and reduced costs.

Recommended citation: Haoran Jin, Jirong Yang, Yunpeng Liu, Barry Lyu, Kangqi Zhang, Nathaniel Bleier, "Mozart: An Ecosystem-Accelerator Codesign Framework for Composable, Heterogeneous Chiplet-based Neural Network Accelerators," ASPLOS 2026 (Under Submission).

SCGen: A Versatile Generator Framework for Agile Development of Stochastic Circuits

Published in DATE 2024, 2024

We present SCGen, a versatile generator framework designed for the agile development of stochastic circuits, enabling rapid prototyping and evaluation of stochastic computing systems.

Recommended citation: Zexi Li*, Haoran Jin*, Kuncai Zhong, Guojie Luo, Runsheng Wang, Weikang Qian, "SCGen: A Versatile Generator Framework for Agile Development of Stochastic Circuits," DATE 2024.

Exploiting Uniform Spatial Distribution to Design Efficient Random Number Source for Stochastic Computing

Published in IEEE/ACM International Conference on Computer-Aided Design (ICCAD), 2022

We propose a novel random number source design for stochastic computing that exploits uniform spatial distribution, achieving 88% area reduction with comparable accuracy.

Recommended citation: Kuncai Zhong, Zexi Li, Haoran Jin, Weikang Qian. Exploiting Uniform Spatial Distribution to Design Efficient Random Number Source for Stochastic Computing. ICCAD 2022. https://ieeexplore.ieee.org/document/10069467