分布式、并行与集群计算

Many techniques for the automated verification of distributed protocols have been developed over the past several years, but their performance is still unpredictable and their failure modes can be opaque for industrial scale verification…

As hardware failures such as node losses become increasingly common, MPI programmers may want to save vulnerable data in a resilient store. While third-party storage solutions such as Redis or the Hazelcast IMap exist, a tailored, MPI-based…

Critical infrastructures increasingly rely on interconnected and software-driven Cyber-Physical Systems (CPS), exposing operational processes to both accidental failures and sophisticated adversarial behavior. While Byzantine Fault Tolerant…

In modern distributed systems, efficient resource allocation is a vital aspect to maintain scalability, reduce operational costs, and ensure fast execution even across heterogeneous workloads. Predictive models for resource usage are…

We study the message complexity of leader election in synchronous networks of diameter two. Our main contribution is a refined analysis of the randomized algorithm proposed by Chatterjee et al. [DC, 2020]. In their work, the authors…

Modern deep learning workloads often consist of many small tensor operations, especially in inference, attention, and micro-batched training. In these settings, kernel launch overhead can become a major bottleneck, sometimes exceeding the…

Sparse Matrix-Matrix Multiplication (SpMM) is a fundamental kernel across scientific computing and machine learning. While prior work accelerates SpMM using Tensor Cores, no existing sparse kernel exploits the asynchronous features of…

Modern multi GPU HPC systems expose substantial computational capacity, yet inefficient GPU allocation often leads to wasted energy and underutilization. In practice, GPU applications exhibit heterogeneous and nonlinear scaling, making it…

Power-constrained HPC systems increasingly run heterogeneous CPU--GPU applications under strict cluster-wide power limits. Existing cluster-wide power management policies rely on fair-share or utilization heuristics and do not capture…

Design space exploration for future distributed Machine Learning systems suffers from a lack of readily available workload representation that enables flexible exploration across the stack. We present Flint, a framework that bridges this…

Edge computing enables AI inference closer to data sources, reducing latency and bandwidth costs. However, orchestrating AI services across the cloud-edge continuum remains challenging due to dynamic workloads and infrastructure…

The rapid rise of Large Language Models (LLMs) has revolutionized various artificial intelligence (AI) applications, from natural language processing to code generation. However, the computational demands of these models, particularly in…

When multiple LLM coding agents share a rate-limited API endpoint, they exhibit resource contention patterns analogous to unscheduled OS processes competing for CPU, memory, and I/O. In a motivating incident, 3 of 11 parallel agents died…

High-performance computing (HPC) systems must support fast-moving software stacks, especially in AI/ML, while preserving scheduler control, scalable startup, and production performance. Yet many HPC container solutions rely on specialized…

Conventional air traffic control divides airspace into specific regions, creating a scaling bottleneck as traffic grows. Choosing how to partition airspace is not straightforward because grid size affects workload, handoff frequency, and…

Many automated market makers can be understood through the geometry of their trading orbits, the sets of states reachable from one another through swaps. In prominent designs, this geometry is captured by a simple closed-form invariant such…

The deployment of long-context Large Language Models (LLMs) poses significant challenges due to the intense computational cost of self-attention and the substantial memory overhead of the Key-Value Cache (KV Cache). In this paper, we…

Graph foundation models have demonstrated remarkable adaptability across diverse downstream tasks through large-scale pretraining on graphs. However, existing implementations of the backbone model, graph transformers, are typically limited…

Power has become a central bottleneck for AI inference. This problem is becoming more urgent as agentic AI emerges as a major workload class, yet prior power-management techniques focus almost entirely on single-turn LLM serving. Our…

LLM agents execute in an interleaved reasoning-and-action loop, where future tool calls cannot be launched until the current reasoning step completes. This serial dependency inflates end-to-end latency and leaves the model idle while…