HLSmith: An Expert-Guided Agentic Framework for C/C++-to-HLS Translation
Authors:
Yuebo Luo,
Ahmad Sedigh Baroughi,
Philip Stachura,
Le Chen,
Venkatram Vishwanath,
Zhenman Fang,
Caiwen Ding
Abstract:
Application-specific FPGA accelerators offer substantial performance and energy-efficiency gains across many application domains, but developing them is costly, often requiring months of specialized effort. Even with high-level synthesis (HLS), designers still need extensive hardware expertise to build high-performance accelerators. Although large language models (LLMs) have demonstrated strong so…
▽ More
Application-specific FPGA accelerators offer substantial performance and energy-efficiency gains across many application domains, but developing them is costly, often requiring months of specialized effort. Even with high-level synthesis (HLS), designers still need extensive hardware expertise to build high-performance accelerators. Although large language models (LLMs) have demonstrated strong software-generation capabilities, even frontier models lack the hardware intuition and procedural knowledge needed to reliably translate baseline C/C++ programs into high-performance HLS designs: they struggle to identify effective architectures, follow the optimization processes used by HLS experts, and apply hardware transformations consistently across diverse kernels. We present HLSmith, an expert-guided framework for translating C/C++ programs into optimized HLS accelerators. HLSmith combines three components: an HLS optimization expertise library that encodes guarded transformation recipes, their applicability and prerequisite conditions, and unsafe cases to avoid; a staged, feedback-driven orchestration flow modeled on expert HLS development practice that guides agents through synthesis, bottleneck analysis, and optimization; and a tool-grounded model-adaptation pipeline that converts optimization trajectories from commercial frontier models into training data for fine-tuning open-weight LLMs. We evaluate HLSmith on PolyBench against ChatHLS, a leading prior agent-orchestration framework for HLS accelerator development. HLSmith achieves a geometric mean speedup of 4.24x over ChatHLS while producing functionally correct designs, in both software and RTL simulation, for every benchmark, compared with ChatHLS's 57% valid-design rate. It further reaches speedups of up to 252x and 138x with commercial frontier models and open-weight models, respectively.
△ Less
Submitted 7 August, 2026;
originally announced August 2026.
HyperColor: A HyperNetwork Approach for Synthesizing Auto-colored 3D Models for Game Scenes Population
Authors:
Ivan Kostiuk,
Przemysław Stachura,
Sławomir K. Tadeja,
Tomasz Trzciński,
Przemysław Spurek
Abstract:
Designing a 3D game scene is a tedious task that often requires a substantial amount of work. Typically, this task involves synthesis, coloring, and placement of 3D models within the game scene. To lessen this workload, we can apply machine learning to automate some aspects of the game scene development. Earlier research has already tackled automated generation of the game scene background with ma…
▽ More
Designing a 3D game scene is a tedious task that often requires a substantial amount of work. Typically, this task involves synthesis, coloring, and placement of 3D models within the game scene. To lessen this workload, we can apply machine learning to automate some aspects of the game scene development. Earlier research has already tackled automated generation of the game scene background with machine learning. However, model auto-coloring remains an underexplored problem. The automatic coloring of a 3D model is a challenging task, especially when dealing with the digital representation of a colorful, multipart object. In such a case, we have to ``understand'' the object's composition and coloring scheme of each part. Existing single-stage methods have their own caveats such as the need for segmentation of the object or generating individual parts that have to be assembled together to yield the final model. We address these limitations by proposing a two-stage training approach to synthesize auto-colored 3D models. In the first stage, we obtain a 3D point cloud representing a 3D object, whilst in the second stage, we assign colors to points within such cloud. Next, by leveraging the so-called triangulation trick, we generate a 3D mesh in which the surfaces are colored based on interpolation of colored points representing vertices of a given mesh triangle. This approach allows us to generate a smooth coloring scheme. Experimental evaluation shows that our two-stage approach gives better results in terms of shape reconstruction and coloring when compared to traditional single-stage techniques.
△ Less
Submitted 3 August, 2021;
originally announced August 2021.