arXiv subjects

Chenglong Xiao

Publications and source records attributed to Chenglong Xiao.

7 recordsLinked to original sources

arXiv2026

SoberDSE: Sample-Efficient Design Space Exploration via Learning-Based Algorithm Selection

High-Level Synthesis (HLS) is a pivotal electronic design automation (EDA) technology that enables the generation of hardware circuits from high-level language descriptions. A critical step in HLS is Design Space Exploration (DSE), which seeks to identify high-quality hardware architectures under given constraints. However, the enormous size of the design space makes DSE computationally prohibitive. Although numerous algorithms have been proposed to accelerate DSE, our extensive experimental studies reveal that no single algorithm consistently achieves Pareto dominance across all problem instances. Consequently, the inability of any single algorithm to dominate all benchmarks necessitates an automated selection mechanism to identify the best-performing DSE algorithm for each specific case. To address this challenge, we propose the SoberDSE framework, which recommends suitable algorithm based on benchmark characteristics. Experimental results demonstrate that our SoberDSE framework significantly outperforms state-of-the-art heuristic-based DSE algorithms by up to 5.7 $\times$ and state-of-the-art learning-based DSE methods by up to 4.2 $\times$. Furthermore, compared to conventional classification models, SoberDSE delivers superior accuracy in small-sample learning scenarios, with an average enhancement of 35.57\%. Code and models are available at https://anonymous.4open.science/r/Sober-4377.

cs.AR↗

arXiv2026

MPM-LLM4DSE: Reaching the Pareto Frontier in HLS with Multimodal Learning and LLM-Driven Exploration

High-Level Synthesis (HLS) design space exploration (DSE) seeks Pareto-optimal designs within expansive pragma configuration spaces. To accelerate HLS DSE, graph neural networks (GNNs) are commonly employed as surrogates for HLS tools to predict quality of results (QoR) metrics, while multi-objective optimization algorithms expedite the exploration. However, GNN-based prediction methods may not fully capture the rich semantic features inherent in behavioral descriptions, and conventional multi-objective optimization algorithms often do not explicitly account for the domain-specific knowledge regarding how pragma directives influence QoR. To address these limitations, this paper proposes the MPM-LLM4DSE framework, which incorporates a multimodal prediction model (MPM) that simultaneously fuses features from behavioral descriptions and control and data flow graphs. Furthermore, the framework employs a large language model (LLM) as an optimizer, accompanied by a tailored prompt engineering methodology. This methodology incorporates pragma impact analysis on QoR to guide the LLM in generating high-quality configurations (LLM4DSE). Experimental results demonstrate that our multimodal predictive model significantly outperforms state-of-the-art work ProgSG by up to 10.25$\times$. Furthermore, in DSE tasks, the proposed LLM4DSE achieves an average performance gain of 39.90\% over prior methods, validating the effectiveness of our prompting methodology. Code and models are available at https://github.com/wslcccc/MPM-LLM4DSE.

cs.AR↗

arXiv2025

Intelligent4DSE: Optimizing High-Level Synthesis Design Space Exploration with Graph Neural Networks and Large Language Models

High-Level Synthesis (HLS) Design Space Exploration (DSE) is essential for generating hardware designs that balance performance, power, and area (PPA). To optimize this process, existing works often employs message-passing neural networks (MPNNs) to predict quality of results (QoR). These predictors serve as evaluators in the DSE process, effectively bypassing the time-consuming estimations traditionally required by HLS tools. However, existing models based on MPNNs struggle with over-smoothing and limited expressiveness. Additionally, while meta-heuristic algorithms are widely used in DSE, they typically require extensive domain-specific knowledge to design operators and time-consuming tuning. To address these limitations, we propose ECoGNNs-LLMMHs, a framework that integrates graph neural networks with task-adaptive message passing and large language model-enhanced meta-heuristic algorithms. Compared with state-of-the-art works, ECoGNN exhibits lower prediction error in the post-HLS prediction task, with the error reduced by 57.27\%. For post-implementation prediction tasks, ECoGNN demonstrates the lowest prediction errors, with average reductions of 17.6\% for flip-flop (FF) usage, 33.7\% for critical path (CP) delay, 26.3\% for power consumption, 38.3\% for digital signal processor (DSP) utilization, and 40.8\% for BRAM usage. LLMMH variants can generate superior Pareto fronts compared to meta-heuristic algorithms in terms of average distance from the reference set (ADRS) with average improvements of 87.47\%, respectively. Compared with the SOTA DSE approaches GNN-DSE and IRONMAN-PRO, LLMMH can reduce the ADRS by 68.17\% and 63.07\% respectively.

cs.LG↗

arXiv2025

Instance-Aware Algorithm Selection for Maximum Clique via a Dual-Channel Graph Neural Architecture

Although the Maximum Clique Problem (MCP) has been extensively studied and features a rich ecosystem of exact solvers, empirical evidence shows that solver performance varies substantially across graph families. Consequently, selecting an appropriate algorithm for a given instance remains an open and practically important challenge that has received little systematic attention. We address this gap by developing an instance-aware selection framework that systematically combines global statistical descriptors with learned topological representations. We construct a comprehensive benchmark by evaluating four state-of-the-art exact solvers on a diverse collection of graph instances and deriving both global statistical and local structural features. An evaluation of conventional classifiers establishes Random Forest as a strong baseline and reveals that connectivity and topological features are key predictors of performance. Motivated by these observations, we introduce a dual-channel architecture that jointly leverages a Graph Attention Network for capturing local neighborhood patterns and a Multilayer Perceptron for modeling global statistical features. Extensive experiments show that the proposed dual-channel model consistently surpasses classical baselines and the single-best solver, achieving 90.43% test accuracy. These findings demonstrate the value of integrating local topological encoding with global statistical cues for combinatorial algorithm selection. Code and models are available at: https://anonymous.4open.science/r/GAT-MLP-7E5F.

cs.LG↗

arXiv2025

An algorithm with a delay of $\mathcal{O}(kΔ)$ for enumerating connected induced subgraphs of size $k$

The problem of enumerating connected subgraphs of a given size in a graph has been extensively studied in recent years. In this paper, we propose an algorithm with a delay of $O(kΔ)$ for enumerating all connected induced subgraphs of size $k$ in an undirected graph $G=(V, E)$, where $k$ and $Δ$ are respectively the size of subgraphs and the maximum degree of $G$. The algorithm requires a preprocessing step of $O(|V| + |E|)$ time to compute a depth-first search traversal order. The proposed algorithm improves upon the current best delay bound $O(k^2Δ)$ for the connected induced subgraph enumeration problem in the literature.

cs.DS↗

arXiv2023

Novel Algorithms for Efficient Mining of Connected Induced Subgraphs of a Given Cardinality

Mining subgraphs with interesting structural properties from networks (or graphs) is a computationally challenging task. In this paper, we propose two algorithms for enumerating all connected induced subgraphs of a given cardinality from networks (or connected undirected graphs in networks). The first algorithm is a variant of a previous well-known algorithm. The algorithm enumerates all connected induced subgraphs of cardinality $k$ in a bottom-up manner. The data structures that lead to unit time element checking and linear space are presented. Different from previous algorithms that either work in a bottom-up manner or a reverse search manner, an algorithm that enumerates all connected induced subgraphs of cardinality $k$ in a top-down manner is proposed. The correctness and complexity of the top-down algorithm are theoretically analyzed and proven. In the experiments, we evaluate the efficiency of the algorithms using a set of real-world networks from various fields. Experimental results show that the variant bottom-up algorithm outperforms the state-of-the-art algorithms for enumerating connected induced subgraphs of small cardinality, and the top-down algorithm can achieve an order of magnitude speedup over the state-of-the-art algorithms for enumerating connected induced subgraphs of large cardinality.

cs.DS↗

arXiv2023

Algorithms with improved delay for enumerating connected induced subgraphs of a large cardinality

The problem of enumerating all connected induced subgraphs of a given order $k$ from a given graph arises in many practical applications: bioinformatics, information retrieval, processor design,to name a few. The upper bound on the number of connected induced subgraphs of order $k$ is $n\cdot\frac{(eΔ)^{k}}{(Δ-1)k}$, where $Δ$ is the maximum degree in the input graph $G$ and $n$ is the number of vertices in $G$. In this short communication, we first introduce a new neighborhood operator that is the key to design reverse search algorithms for enumerating all connected induced subgraphs of order $k$. Based on the proposed neighborhood operator, three algorithms with delay of $O(k\cdot min\{(n-k),kΔ\}\cdot(k\logΔ+\log{n}))$, $O(k\cdot min\{(n-k),kΔ\}\cdot n)$ and $O(k^2\cdot min\{(n-k),kΔ\}\cdot min\{k,Δ\})$ respectively are proposed. The first two algorithms require exponential space to improve upon the current best delay bound $O(k^2Δ)$\cite{4} for this problem in the case $k>\frac{n\logΔ-\log{n}-Δ+\sqrt{n\log{n}\logΔ}}{\logΔ}$ and $k>\frac{n^2}{n+Δ}$ respectively.

cs.DS↗