Related papers: ParEVO: Synthesizing Code for Irregular Data: High…

Correctness alone is insufficient: LLM-generated programs frequently satisfy unit tests while violating contest time or memory budgets. We present SwiftSolve, a complexity-aware multi-agent system for competitive programming that couples…

While large language models (LLMs) exhibit state-of-the-art performance in various tasks, recent studies have revealed their struggle for code translation. This is because they haven't been extensively pre-trained with parallel multilingual…

GPUs are a key enabler of the revolution in machine learning and high performance computing, functioning as de facto co-processors to accelerate large-scale computation. As the programming stack and tool support have matured, GPUs have also…

Modern computing systems increasingly rely on composing heterogeneous devices to improve performance and efficiency. Programming these systems is often unproductive: algorithm implementations must be coupled to system-specific logic,…

GPGPU architectures have become significantly more diverse in recent years, which has led to an emergence of a variety of specialized programming models and software stacks to support them. Portable programming models exist, but they…

Large Language Models (LLMs) have achieved state-of-the-art performance across software engineering tasks, from code generation to translation. However, we identify and systematically evaluate a critical failure mode: Programming Language…

Regional hydrology studies are often supported by high resolution simulations of subsurface flow that require expensive and extensive computations. Efficient usage of the latest high performance parallel computing systems becomes a…

Software engineers mainly write code by editing existing programs. In contrast, language models (LMs) autoregressively synthesize programs in a single pass. One explanation for this is the scarcity of sequential edit data. While…

Analogy-making is central to human cognition, allowing us to adapt to novel situations -- an ability that current AI systems still lack. Most analogy datasets today focus on simple analogies (e.g., word analogies); datasets including…

Training capable Large Language Model (LLM) agents is critically bottlenecked by the high cost and static nature of real-world interaction data. We address this by introducing GenEnv, a framework that establishes a difficulty-aligned…

There are billions of lines of sequential code inside nowadays' software which do not benefit from the parallelism available in modern multicore architectures. Automatically parallelizing sequential code, to promote an efficient use of the…

Current approaches to scheduling workloads on heterogeneous systems with specialized accelerators often rely on manual partitioning, offloading tasks with specific compute patterns to accelerators. This method requires extensive…

Large language models have been successfully applied to programming assistance tasks, such as code completion, code insertion, and instructional code editing. However, these applications remain insufficiently automated and struggle to…

Large Language Model (LLM)-guided evolutionary search is increasingly used for automated algorithm discovery, yet most current methods track search progress primarily through executable programs and scalar fitness. Even when…

Writing data in parallel is a common operation in some computing environments and a good proxy for a number of other parallel processing patterns. The duration of time taken to write data in large-scale compute environments can vary…

Large language models (LLMs) often face a bottleneck in inference speed due to their reliance on auto-regressive decoding. Recently, parallel decoding has shown significant promise in enhancing inference efficiency. However, we have…

Large language models have shown remarkable ability in serial code generation, but they still struggle with parallel code for which training data is comparatively scarce. A common remedy is to use coding agents that interact with external…

Heuristic dispatching rules (HDRs) are widely regarded as effective methods for solving dynamic job shop scheduling problems (DJSSP) in real-world production environments. However, their performance is highly scenario-dependent, often…

Evolutionary computing, particularly genetic algorithm (GA), is a combinatorial optimization method inspired by natural selection and the transmission of genetic information, which is widely used to identify optimal solutions to complex…

The ability to edit 3D assets from natural language presents a compelling paradigm to aid in the democratization of 3D content creation. However, while natural language is often effective at communicating general intent, it is poorly suited…