ForgeHLS: A Large-Scale, Open-Source Dataset for High-Level Synthesis

TL;DR

ForgeHLS is a comprehensive, large-scale open-source dataset designed to accelerate machine learning research in high-level synthesis optimization for hardware design, covering diverse kernels and application domains.

Contribution

We introduce ForgeHLS, the largest and most diverse dataset for ML-driven HLS research, enabling improved optimization techniques and benchmarking.

Findings

ForgeHLS contains over 400k designs from 846 kernels.

The dataset enables effective QoR prediction and pragma exploration.

ForgeHLS significantly advances ML applications in HLS optimization.

Abstract

High-Level Synthesis (HLS) plays a crucial role in modern hardware design by transforming high-level code into optimized hardware implementations. However, progress in applying machine learning (ML) to HLS optimization has been hindered by a shortage of sufficiently large and diverse datasets. To bridge this gap, we introduce ForgeHLS, a large-scale, open-source dataset explicitly designed for ML-driven HLS research. ForgeHLS comprises over 400k diverse designs generated from 846 kernels covering a broad range of application domains, consuming over 200k CPU hours during dataset construction. Each kernel includes systematically automated pragma insertions (loop unrolling, pipelining, array partitioning), combined with extensive design space exploration using Bayesian optimization. Compared to existing datasets, ForgeHLS significantly enhances scale, diversity, and design coverage. We further define and evaluate representative downstream tasks in Quality of Result (QoR) prediction and automated pragma exploration, clearly demonstrating ForgeHLS utility for developing and improving ML-based HLS optimization methodologies. The dataset and code are public at https://github.com/zedong-peng/ForgeHLS.