Searcharxiv⌕ Search

arXiv subjects

Yun Liang

Publications and source records attributed to Yun Liang.

At least 19 recordsLinked to original sources

AMARA: Compiler-Driven Accelerator Architecture Design for Graphical Probabilistic Sampling

Sampling methods are fundamental primitives for training and inference on probabilistic models. However, practical deployment of sampling algorithms such as Markov Chain Monte Carlo (MCMC) remains difficult on general-purpose processors. Existing hardware accelerators improve sampling efficiency, but they are typically specialized for a narrow class of models, graph topologies, or update schedules, making it difficult to support the diverse workloads used in real applications. This paper presents AMARA, an end-to-end compiler-driven accelerator framework for probabilistic sampling on arbitrary probabilistic graphical models. AMARA introduces MCMC-IR, a domain-specific intermediate representation that separates local factorized computation from global update dependencies. Based on this representation, the compiler performs architecture-aware partitioning, scheduling, and memory-access optimization to expose parallelism and reduce irregular graph communication. The optimized program is lowered to a compact ISA and executed on a programmable ASIC accelerator with specialized compute, sampling, and memory support. By co-designing the compiler and the architecture, AMARA bridges the gap between model generality and accelerator efficiency for practical MCMC-based probabilistic computing. We evaluate AMARA across representative workloads with different structures, including grid-structured and irregular energy-based models, and causal inference networks. The results show that AMARA supports a broad spectrum of discrete probabilistic models while achieving high sampling throughput and efficient hardware utilization. AMARA achieves an average of 6.1$\times$ (up to 16.3$\times$) higher sampling throughput than a JAX-GPU baseline on irregular workloads, and offers broader programmability than state-of-the-art accelerators.

cs.AR↗

Retargetable Compilation for Tensor Kernels via a Unified Layout Abstraction

Modern hardware accelerators achieve high performance through specialized instructions coupled with tightly managed memory hierarchies. These instructions impose strict layout requirements on their operands: where tensor fragments reside, how they are organized, and how parallel units access them. Such instruction-visible layout is critical to kernel performance, as it determines whether instructions execute correctly and how much data movement they incur. However, existing compilers either scatter layout requirements across handwritten programs and local scheduling rules, or provide layout representations and conversions specific to a single class of targets. Both approaches expose the same abstraction gap: the absence of a unified model for instruction layout requirements across backends. This paper presents Arknife, a retargetable compiler that treats instruction-visible layout as first-class instruction semantics. Its central idea is a constraint-based layout algebra: tensor layouts map logical axes to hardware axes spanning parallel levels and memory spaces. Instruction operands declare layout requirements, and target-provided repairs resolve conflicts. Layouts are then solved globally across the program. ISA-specific layout facts are supplied by target-side instruction descriptions rather than hardcoded in the compiler. Retargeting reuses the layout algebra and solver while defining the new target's instructions and their operand requirements. We evaluate Arknife across x86 CPU, Hexagon NPU, and NVIDIA A100 GPU. Arknife matches cuBLAS on A100, and on x86 and Hexagon outperforms vendor-optimized libraries by $2.17\times$ and $3.78\times$ and the retargetable compiler MISAAL by $5.08\times$ and $4.53\times$, respectively.

cs.PL↗

FedHQ: Hybrid Runtime Quantization for Federated Learning

Federated Learning (FL) must balance training efficiency and model accuracy across heterogeneous clients. Post-training quantization (PTQ) avoids the extra computation of quantization-aware training (QAT), but can incur greater accuracy loss. We propose FedHQ, a hybrid quantization framework that assigns PTQ or QAT according to clients' hardware and data characteristics. Hardware-based speed estimates and local data-distribution indicators guide coarse-grained global initialization, followed by fine-grained training-based adjustment of selected client strategies. Experiments on three image-classification datasets show that FedHQ achieves up to 2.47x training speedup over FedAQT and up to 11.15 percentage points higher accuracy than FedFQ.

cs.LG↗

SkyEgg: Heterogeneity-Aware Hardware Synthesis via Equality Saturation

Hardware synthesis is a key interface between high-level programs and accelerator designs. Modern FPGAs increasingly expose heterogeneity in resource functionality and timing configurability. Exploiting these resources requires synthesis to choose among hardware implementations and fine-grained configuration options, and coordinate these choices across multiple stages. However, prior frameworks fail to fully explore these choices due to resource models confined to per-operation mappings and limited fusion patterns. Moreover, they perform transformation, scheduling, and mapping sequentially, selecting an expression form and assigning cycle boundaries before full mapping information is available. This problem precludes chaining and fusion, excludes viable implementations from subsequent optimization stages, and limits end-to-end performance. We present SkyEgg, a heterogeneity-aware hardware synthesis framework for FPGAs. The key insight of SkyEgg is to bring algebraic equivalence and diverse resource capabilities together throughout the synthesis flow. Specifically, it encodes target-specific hardware mappings and configurations as extensible mapping rules alongside algebraic rewrite rules in equality saturation, placing algebraic and resource alternatives in a common representation. It further proposes transformation- and mapping-aware scheduling that uses these alternatives and configuration-specific timing to jointly select an equivalent form, its resource mappings, and cycle assignments to minimize end-to-end latency under target-frequency and hardware constraints. This algebraic exploration reveals forms that enable otherwise unavailable mappings. SkyEgg also provides a heuristic solver that rapidly finds high-quality solutions. Against two commercial HLS tools, SkyEgg achieves average speedups of 3.12x over Vitis HLS and 3.18x over Altera HLS across target frequencies.

cs.PL↗

SLOTH: Lightweight Detection and Localization of On-Chip Fail-Slow Failures for DNN Accelerators

Spatial DNN accelerators are essential for high-performance inference, but their performance is undermined by widespread fail-slow failures. Detecting such failures on-chip is challenging, as prior methods from distributed systems are unsuitable due to strict memory limits and their inability to track failures across the hardware topology. We present SLOTH, a lightweight, hardware-aware framework for practical on-chip fail-slow detection in DNN accelerators. SLOTH combines workload-aware instrumentation for operator-level monitoring with minimal overhead, on-the-fly trace compression to operate within kilobytes of memory, and a novel topology-aware ranking algorithm to pinpoint a failure's root cause. We evaluate SLOTH on a wide range of representative DNN workloads. The results demonstrate that SLOTH reduces the storage overhead by an average of 115.9$\times$, while achieving an average fail-slow detection accuracy from 69.68\% to 86.69\%.

cs.AR↗

Finding a clean process $B^- \to K^- D^0 K^0$ to probe absolutely exotic four-quark states

Motivated by the observations of $T_{c\bar{s}0}(2900)^0$ and $T_{c\bar{s}0}(2900)^{++}$, we propose to search for $\tcsbar^0$ in the cleaner process $B^- \to K^- D^0 K^0$. In the $D^*K^*$ molecular picture, our estimates suggest that $T_{c\bar{s}0}(2900)^0$ should contribute significantly to the $D^0 K^0$ invariant mass distribution in $B^- \to K^- D^0 K^0$, as reported by the Belle II Collaboration. The corresponding fit fraction is estimated to be $(9.72\pm 3.92)\%$ or $(7.09\pm 5.88)\%$ in different fitting schemes. Further precise measurements of this process at Belle II and LHCb could be helpful for clarifying the nature of $T_{c\bar{s}0}(2900)$.

hep-ph↗

HWE-Bench: Benchmarking LLM Agents on Real-World Hardware Bug Repair Tasks

Existing benchmarks for hardware design primarily evaluate Large Language Models (LLMs) on isolated, component-level tasks such as generating HDL modules from specifications, leaving repository-scale evaluation unaddressed. We introduce HWE-Bench, the first large-scale, repository-level benchmark for evaluating LLM agents on real-world hardware bug repair tasks. HWE-Bench comprises 417 task instances derived from real historical bug-fix pull requests across six major open-source projects spanning both Verilog/SystemVerilog and Chisel, covering RISC-V cores, SoCs, and security roots-of-trust. Each task is grounded in a fully containerized environment where the agent must resolve a real bug report, with correctness validated through the project's native simulation and regression flows. The benchmark is built through a largely automated pipeline that enables efficient expansion to new repositories. We evaluate seven LLMs with four agent frameworks and find that the best agent resolves 70.7% of tasks overall, with performance exceeding 90% on smaller cores but dropping below 65% on complex SoC-level projects. We observe larger performance gaps across models than commonly reported on software benchmarks, and difficulty is driven by project scope and bug-type distribution rather than code size alone. Our failure analysis traces agent failures to three stages of the debugging process: fault localization, hardware-semantic reasoning, and cross-artifact coordination across RTL, configuration, and verification components, providing concrete directions for developing more capable hardware-aware agents.

cs.AI↗

DITRON: Distributed Multi-level Tiling Compiler for Parallel Tensor Programs

The scaling of large language models (LLMs) is currently bottlenecked by the rigidity of distributed programming. While high-performance libraries like CuBLAS and NCCL provide optimized primitives, they lack the flexibility required for rapidly evolving model architectures. Conversely, existing tensor compilers fail to address the complex memory hierarchy of distributed clusters effectively. To bridge this gap, we propose DITRON, a scalable tile-level compiler that democratizes high-performance distributed kernel development. DITRON introduces a novel hierarchical programming abstraction spanning Core, Device, and Task levels to map tensor programs efficiently onto heterogeneous distributed hardware. This abstraction allows DITRON to support diverse parallelism strategies while abstracting away the complexity of inter-node and intra-node communication. Evaluated across large-scale clusters, DITRON achieves performance parity with or exceeding expert-tuned CUDA libraries, delivering speedups of $6\%-30\%$ on isolated kernels and $5\%-30\%$ on end-to-end inference in vLLM. Furthermore, DITRON demonstrates strong portability, achieving significant speedups on both NVIDIA and AMD platforms. \ours{} has been deployed at the enterprise level for both training and inference. It achieves an MFU improvement of over 10\% in training tasks, saving approximately 500,000 GPU hours of training cost per month. For inference tasks, it delivers an end-to-end gain of over 20\% and has been applied to cloud service inference and edge inference scenarios.

cs.PL↗

Clover: A Neural-Symbolic Agentic Harness with Stochastic Tree-of-Thoughts for Verified RTL Repair

RTL program repair remains a critical bottleneck in hardware design and verification. Traditional automatic program repair (APR) methods rely on predefined templates and synthesis, limiting their bug coverage. Large language models (LLMs) and coding agents based on them offer flexibility but suffer from randomness and context corruption when handling long RTL code and waveforms. We present Clover, a neural-symbolic agentic harness that orchestrates RTL repair as a structured search over code manipulations to explore a validated solution for the bug. Recognizing that different repair operations favor distinct strategies, Clover dynamically dispatches tasks to specialized LLM agents or symbolic solvers. At its core, Clover introduces stochastic tree-of-thoughts, a test-time scaling mechanism that manages the main agent's context as a search tree, balancing exploration and exploitation for reliable outcomes. An RTL-specific toolbox further empowers agents to interact with the debugging environment. Evaluated on the RTL-repair benchmark, Clover fixes 96.8% of bugs within a fixed time limit, covering 94% and 63% more bugs than both pure traditional and LLM-based baselines, respectively, while achieving an average pass@1 rate of 87.5%, demonstrating high reliability and effectiveness.

cs.AR↗

Hive: A Multi-Agent Infrastructure for Algorithm- and Task-Level Scaling

Large language models are increasingly deployed as complex agentic systems that scale with task complexity. While prior work has extensively explored model- and system-level scaling, algorithm- and task-level scaling remain largely unaddressed, constraining the full potential of agentic systems. At the algorithm level, allocating additional inference-time computation can enhance workflow capacity but introduces cross-path redundancy: overlapping computations across multiple reasoning branches. At the task level, complex tasks can be decomposed into subproblems and delegated across multiple agents for improved scalability and parallelism. However, existing infrastructures' scheduling is unaware of the existence of multiple agents, missing opportunities to optimize resource allocation. We propose Hive, a multi-agent infrastructure that enables algorithm- and task-level scaling. Hive features a description frontend that captures per-agent behavior and supports test-time scaling algorithms. Leveraging this specification, our backend introduces two key mechanisms: Logits Cache that reuses intermediate logits across redundant sampling paths to mitigate cross-path redundancy at the algorithm level, and Agent-Aware Scheduling that efficiently allocates compute and KV-cache resources according to agent contributions at the task level. Experiments show that Logits Cache achieves an average speedup of $1.11\times$-$1.76\times$ for re-sampling, and Agent-Aware Scheduling reduces the hotspot miss rate by $33\%$-$51\%$.

cs.AI↗

LLM-Guided Strategy Synthesis for Scalable Equality Saturation

Equality saturation (EqSat) is a powerful optimization paradigm that compactly represents many equivalent programs in an e-graph and delays commitment until extraction selects a lowest-cost program. Making EqSat effective, therefore, requires not only domain-specific rewrite rules but also domain-specific strategies. Today, much of this strategy design is still manual, making it a major obstacle to automating e-graph-based compilers. Recent rule-synthesis frameworks can automatically infer large rewrite vocabularies from semantic specifications, but they also enlarge the rewrite space and further exacerbate e-graph explosion. Although large language models (LLMs) make automated strategy synthesis plausible, directly evolving backend code remains ineffective in practice. The search lacks reusable strategy abstractions and actionable feedback, and can easily trigger e-graph explosion or converge to poor designs. We present EggMind, an LLM-guided, end-to-end framework for synthesizing reusable EqSat strategies. At its core, EggMind introduces a domain-specific language, EqSatL, to represent EqSat strategies as explicit and inspectable artifacts. It then proposes an LLM-guided agentic workflow, equipped with novel techniques including proof-derived rewrite motif caching and tractability guidance, to search efficiently for high-quality strategies while keeping synthesis stable under e-graph growth. Evaluation shows that EggMind substantially improves the resource-quality trade-off on vectorization benchmarks, reducing final cost by 45.1% and peak RAM by 69.1% relative to full EqSat. We further show that the same methodology transfers effectively to an XLA-based tensor compiler, and demonstrate its practical potential in a logic-synthesis case study with augmented rewrite spaces.

cs.AI↗

Aquas: Enhancing Domain Specialization through Holistic Hardware-Software Co-Optimization based on MLIR

Application-Specific Instruction-Set Processors (ASIPs) built on the RISC-V architecture offer specialization opportunities for various applications. Existing frameworks are largely designed around fixed instruction extension interfaces and rely on manual software adaptation. However, as emerging domains scale up in complexity, two major challenges arise. First, memory access remains a primary bottleneck as existing design flows lack architectural awareness of memory interfaces, leading to suboptimal interface selection and orchestration. Second, the semantic complexity of custom instruction extensions, characterized by non-trivial control logic and irregular memory behaviors, hinders the ability of conventional compilers to perform automated and comprehensive offloading. We present Aquas, a holistic hardware-software co-design framework built upon MLIR. Aquas proposes a memory interface model that jointly considers interface characteristics and cache effects, along with an interface-aware synthesis flow guided by this model that progressively optimizes the input specification and generates efficient hardware implementations. We also propose an e-graph-based retargetable compiler approach with a novel matching engine for efficient instruction mapping and offloading, enabling robust and effective utilization of custom instruction capabilities. Case studies across four diverse domains show that Aquas delivers substantial acceleration, achieving up to 15.61x speedup with 14.5% area overhead and zero frequency degradation, proving highly competitive in domain acceleration against more powerful general-purpose cores and vector extensions.

cs.AR↗

Efficient Solving for Dynamic Data Structure Constraint Satisfaction Problem

Functional verification plays a central role in ensuring the correctness of modern integrated circuit designs, where constrained-random verification is widely adopted to generate diverse stimuli under high-level constraints. In industrial verification environments, constraint solving increasingly involves dynamic data structures whose shape and content are determined at runtime, causing the sets of variables and constraint instances to evolve across solver invocations, which in turn leads to substantial overhead when nested and high-dimensional structures repeatedly expand across solves. We formalize this class of problems as the Dynamic Data Structure Constraint Satisfaction Problem (D2SCSP),which captures the interaction between dynamic data structure expansion and constraint evaluation. We propose a dependency-guided problem partitioning framework combined with an incremental encoding and constraint activation mechanism, enabling reuse of solver state and encodings across multiple solves. The framework is integrated into an industrial SystemVerilog verification flow and implemented in the commercial simulator VeriSim. Experimental results on industrial benchmarks demonstrate significant performance improvements, achieving an average speedup of 24.80x over a baseline and 1.72x over a state-of-the-art commercial simulator, highlighting the practicality of the approach for real-world verification workflows.

cs.AR↗

TokenDance: Scaling Multi-Agent LLM Serving via Collective KV Cache Sharing

Multi-agent LLM applications organize execution in synchronized rounds where a central scheduler gathers outputs from all agents and redistributes the combined context. This All-Gather communication pattern creates massive KV Cache redundancy, because every agent's prompt contains the same shared output blocks, yet existing reuse methods fail to exploit it efficiently. We present TokenDance, a system that scales the number of concurrent agents by exploiting the All-Gather pattern for collective KV Cache sharing. TokenDance's KV Collector performs KV Cache reuse over the full round in one collective step, so the cost of reusing a shared block is paid once regardless of agent count. Its Diff-Aware Storage encodes sibling caches as block-sparse diffs against a single master copy, achieving 11-17x compression on representative workloads. Evaluation on GenerativeAgents and AgentSociety shows that TokenDance supports up to 2.7x more concurrent agents than vLLM with prefix caching under SLO requirement, reduces per-agent KV Cache storage by up to 17.5x, and achieves up to 1.9x prefill speedup over per-request position-independent caching.

cs.DC↗

STaRR: Spatial-Temporal Token-Dynamics-Aware Responsive Remasking for Diffusion Language Models

Diffusion Language Models (DLMs) enable parallel decoding via iterative denoising, where remasking strategies play a critical role in balancing inference speed and output quality. Existing methods predominantly rely on static confidence thresholds, overlooking the spatial-temporal dynamics of token confidence, causing unnecessary remasking. We propose Spatial-Temporal Token-Dynamics-Aware Responsive Remasking (STaRR), a training-free framework that dynamically adapts remasking decisions based on token confidence evolution. STaRR introduces two metrics, temporal variance and spatial deviance, to guide fine-grained, step-wise dynamic thresholding. We further introduce a step-wise dynamic thresholding strategy, further enhanced with responsiveness optimizations for scalability and robustness. Experiments show that STaRR achieves an average speedup of 4.1 and up to 8.9 while maintaining comparable accuracy.

cs.CL↗

DynaMo: Runtime Switchable Quantization for MoE with Cross-Dataset Adaptation

As the Mix-of-Experts (MoE) architecture increases the number of parameters in large models, there is an even greater need for model quantization. However, existing quantization methods overlook the expert dynamics of MoE across multiple datasets. Moreover, the existing static quantization cannot adapt MoE to various data change scenarios. In this paper, we perform a multi-level analysis to reveal MoE dynamics and define the significance of each channel/each expert. Based on the analysis results, we propose \textit{DynaMo}, an end-to-end MoE quantization framework. DynaMo adopts an expert-level mixed-precision baseline quantization strategy, which ensures the quantized MoEs are compatible with multiple existing datasets. Furthermore, DynaMo incorporates a channel-level dynamic switching mechanism to adapt these quantized MoE models to novel datasets. Experiments show that DynaMo achieves a 2.78~4.54 PPL decrease and a 1.85%~3.77% accuracy improvement in various datasets, with ~3x inference speedup and negligible overhead.

cs.LG↗

R3A: Reliable RTL Repair Framework with Multi-Agent Fault Localization and Stochastic Tree-of-Thoughts Patch Generation

Repairing RTL bugs is crucial for hardware design and verification. Traditional automatic program repair (APR) methods define dedicated search spaces to locate and fix bugs with program synthesis. However, they heavily rely on fixed templates and can only deal with limited bugs. As an alternative, Large Language Models with the ability to understand code semantics can be explored for RTL repair. However, they suffer from unreliable outcomes due to inherent randomness and long input contexts of RTL code and waveform. To address these challenges, we propose R3A, an LLM-based automatic RTL program repair framework upon the basic model to improve reliability. R3A proposes the stochastic Tree-Of-Thoughts method to control a patch generation agent to explore a validated solution for the bug. The algorithm samples search states according to a heuristic function to balance between exploration and exploitation for a reliable outcome. Besides, R3A proposes a multi-agent fault localization method to find fault candidates as the starting points for the patch generation agent, further increasing the reliability. Experiments show R3A can fix 90.6% of bugs in the RTL-repair dataset within a given time limit, which covers 45% more bugs than traditional methods and other LLM-based approaches, while achieving an 86.7% pass@5 rate on average, showing a high reliability.

cs.AR↗

Cement2: Temporal Hardware Transactions for High-Level and Efficient FPGA Programming

Hardware design faces a fundamental challenge: raising abstraction to improve productivity while maintaining control over low-level details like cycle accuracy. Traditional RTL design in languages like SystemVerilog composes modules through wiring-style connections that provide weak guarantees for behavioral correctness. While high-level synthesis (HLS) and emerging abstractions attempt to address this, they either introduce unpredictable overhead or restrict design generality. Although transactional HDLs provide a promising foundation by lifting design abstraction to atomic and composable rules, they solely model intra-cycle behavior and do not reflect the native temporal design characteristics, hindering applicability and productivity for FPGA programming scenarios. We propose temporal hardware transactions, a new abstraction that brings cycle-level timing awareness to designers at the transactional language level. Our approach models temporal relationships between rules and supports the description of rules whose actions span multiple clock cycles, providing intuitive abstraction to describe multi-cycle architectural behavior. We implement this in Cement2, a transactional HDL embedded in Rust, enabling programming hardware constructors to build both intra-cycle and temporal transactions. Cement2's synthesis framework lowers description abstraction through multiple analysis and optimization phases, generating efficient hardware. With Cement2's abstraction, we program a RISC-V soft-core processor, custom CPU instructions, linear algebra kernels, and systolic array accelerators, leveraging the high-level abstraction for boosted productivity. Evaluation shows that Cement2 does not sacrifice performance and resources compared to hand-coded RTL designs, demonstrating the high applicability for general FPGA design tasks.

cs.PL↗