SearcharxivSearch

arXiv subjects

Zhenguo Liu

Publications and source records attributed to Zhenguo Liu.

3 recordsLinked to original sources

HiFuzz: Hierarchical Reinforcement Learning for Semantic-Aware and Adaptive CPU Fuzzing

Modern processor verification struggles to reach deep architectural states due to the inefficiencies of traditional mutation-based fuzzing. We propose HiFuzz, a novel hierarchical reinforcement learning framework that replaces mutation with a structured, two-layer generation process: a Program Agent for global layout and a Basic Block Agent for precise instruction filling. To overcome reward sparsity, HiFuzz integrates an adaptive coverage reward mechanism and a semantic-aware basic block encoder providing intrinsic feedback. Extensive evaluations on three real-world RISC-V cores demonstrate that HiFuzz significantly outperforms state-of-the-art fuzzers in coverage and bug detection.

cs.AR

SemanticBBV: A Semantic Signature for Cross-Program Knowledge Reuse in Microarchitecture Simulation

For decades, sampling-based techniques have been the de facto standard for accelerating microarchitecture simulation, with the Basic Block Vector (BBV) serving as the cornerstone program representation. Yet, the BBV's fundamental limitations: order-dependent IDs that prevent cross-program knowledge reuse and a lack of semantic content predictive of hardware performance have left a massive potential for optimization untapped. To address these gaps, we introduce SemanticBBV, a novel, two-stage framework that generates robust, performance-aware signatures for cross-program simulation reuse. First, a lightweight RWKV-based semantic encoder transforms assembly basic blocks into rich Basic Block Embeddings (BBEs), capturing deep functional semantics. Second, an order-invariant Set Transformer aggregates these BBEs, weighted by execution frequency, into a final signature. Crucially, this stage is co-trained with a dual objective: a triplet loss for signature distinctiveness and a Cycles Per Instruction (CPI) regression task, directly imbuing the signature with performance sensitivity. Our evaluation demonstrates that SemanticBBV not only matches traditional BBVs in single-program accuracy but also enables unprecedented cross-program analysis. By simulating just 14 universal program points, we estimated the performance of ten SPEC CPU benchmarks with 86.3% average accuracy, achieving a 7143x simulation speedup. Furthermore, the signature shows strong adaptability to new microarchitectures with minimal fine-tuning.

cs.AR

A Low Profile Tunable Microwave Absorber based on Graphene Sandwich Structure and High Impedance Surface

In this paper, a low profile dynamically tunable microwave absorber is proposed, which consists of high impedance surface (HIS) and graphene sandwich structure (GSS). We theoretically demonstrate and experimentally verify that the proposed absorber can provide a dynamically tunable reflection range from larger than -3dB to less than -30 dB (corresponding to the absorption range from 50% to 99.9%) at opera-ting frequency of 11.2GHz by external bias voltage. The entire thickness of this absorber is only 2.8mm, nearly one tenth of working wavelength. In addition, a modified equivalent circuit model is proposed to explicate its absorption mechanism. At last, we fabricate a prototype absorber, and measure its absorption in anechoic chamber. The experimental results agree well with the full wave simulation results. This work may provide a reference for design and fabrication of dynamically tunable microwave absorber based on large-scale graphene and may promote the actual applications of graphene at microwave frequency.

physics.app-ph