Searcharxiv⌕ Search

arXiv subjects

Wenshuo Yue

Publications and source records attributed to Wenshuo Yue.

5 recordsLinked to original sources

SPLASH: A Virtualized HBM-HBF Hierarchy with Flash-Aware Sparse Attention for Long-Context Inference

As context lengths, request lifetimes and concurrency grow, the key-value (KV) cache dominates memory usage in large language model (LLM) inference. High-bandwidth memory (HBM), the memory on contemporary GPUs, achieves far higher bandwidth than off-package memory, yet its capacity, bounded by DRAM density, has not kept pace with this demand. High-Bandwidth Flash (HBF), an emerging memory technology, bridges this gap, combining the advanced packaging of HBM with the density of flash to deliver terabyte-scale capacity at HBM-class read bandwidth. Exploiting this capacity for long-context KV caches, however, requires hiding the vastly different physical characteristics of flash from the GPU while keeping decode interactive. We therefore introduce Splash, an architecture that virtualizes HBM and HBF for the KV cache. We architect custom HBM and HBF base dies with novel memory and flash controllers that handle the access semantics and device management of flash. These controllers keep the GPU agnostic of the underlying memory, allowing the HBM-HBF hierarchy to behave as one logical memory for the KV cache. The added capacity of HBF enables long contexts, but dense attention, which reads the entire KV cache for every generated token, cannot keep decode interactive at these lengths. Splash therefore makes sparse attention flash-aware through query-driven address translation, in which the HBF base die resolves each query into the flash addresses of the relevant KV pages and schedules their reads across flash planes. Since the HBF base die holds the location of every page, this translation hides flash from the GPU and balances the selected reads across flash planes, coupling abstraction with performance. Across five models and up to one million tokens, Splash improves per-GPU decode throughput by up to 4.5x over the strongest baseline under a 100 ms latency budget.

cs.AR↗

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↗

Physical AI: A Survey of Models, Learning, Systems, and Open Challenges

Physical AI aims to enable intelligent systems to perceive, reason, act, and learn through interaction with the physical world. Unlike purely digital intelligence, physical agents must operate under partial observability, uncertain dynamics, embodiment constraints, and real-time requirements, while their actions continuously reshape the environment and subsequent observations. Recent advances in foundation models and robot learning have expanded the capabilities of physical agents, yet achieving reliable autonomy requires more than improvements in individual models. This survey presents a comprehensive, system-level review of Physical AI, organized around the closed-loop process of physical interaction. We examine the foundations and recent developments in task representations and memory, predictive and action-generating models, data and learning methods, embodiment and control, computing systems, evaluation, and safety. Beyond reviewing individual advances, we investigate how these components interact and collectively shape the capabilities and limitations of Physical AI systems. Building on this integrated perspective, we identify fundamental challenges in generalization, resource-efficient learning and execution, reliable state tracking, safety, recovery, and continual adaptation. We argue that advancing Physical AI requires moving beyond isolated model performance toward integrated systems capable of robust, efficient, safe, and autonomous physical interaction under changing real-world conditions.

eess.SY↗

Probabilistic Compute-in-Memory Design For Efficient Markov Chain Monte Carlo Sampling

Markov chain Monte Carlo (MCMC) is a widely used sampling method in modern artificial intelligence and probabilistic computing systems. It involves repetitive random number generations and thus often dominates the latency of probabilistic model computing. Hence, we propose a compute-in-memory (CIM) based MCMC design as a hardware acceleration solution. This work investigates SRAM bitcell stochasticity and proposes a novel ``pseudo-read'' operation, based on which we offer a block-wise random number generation circuit scheme for fast random number generation. Moreover, this work proposes a novel multi-stage exclusive-OR gate (MSXOR) design method to generate strictly uniformly distributed random numbers. The probability error deviating from a uniform distribution is suppressed under $10^{-5}$. Also, this work presents a novel in-memory copy circuit scheme to realize data copy inside a CIM sub-array, significantly reducing the use of R/W circuits for power saving. Evaluated in a commercial 28-nm process development kit, this CIM-based MCMC design generates 4-bit$\sim$32-bit samples with an energy efficiency of $0.53$~pJ/sample and high throughput of up to $166.7$M~samples/s. Compared to conventional processors, the overall energy efficiency improves $5.41\times10^{11}$ to $2.33\times10^{12}$ times.

cs.AR↗

Effect of Sea-ice Drift on the Onset of Snowball Climate on Rapidly Rotating Aqua-planets

Previous studies have shown that sea-ice drift effectively promote the onset of a globally ice-covered snowball climate for paleo Earth and for tidally locked planets around low-mass stars. Here, we investigate whether sea-ice drift can influence the stellar flux threshold for a snowball climate onset on rapidly rotating aqua-planets around a Sun-like star. Using a fully coupled atmosphere--land--ocean--sea-ice model with turning on or off sea-ice drift, a circular orbit with no eccentricity (e=0) and an eccentric orbit (e=0.2) are examined. When sea-ice drift is turned off, the stellar flux threshold for the snowball onset is 1250--1275 and 1173--1199 W m^-2 for e=0 and 0.2, respectively. The difference is mainly due to the poleward retreat of sea ice and snow edges when the planet is close to the perihelion in the eccentric orbit. When sea-ice drift is turned on, the respective stellar flux threshold is 1335--1350 and 1250--1276 W m^-2. These mean that sea-ice drift increases the snowball onset threshold by ~80 W m^-2 for both e=0 and 0.2, promoting the formation of a snowball climate state. We further show that oceanic dynamics have a small effect, <26 W m^-2, on the snowball onset threshold. This is because oceanic heat transport becomes weaker and weaker as the sea ice edge is approaching the equator. These results imply that sea-ice dynamics are important for the climate of planets close to the outer edge of the habitable zone, but oceanic heat transport is less important.

astro-ph.EP↗