Related papers: CUCo: An Agentic Framework for Compute and Communi…
We present a novel algorithm to reduce tensor compute required by a conditional image generation autoencoder without sacrificing quality of photo-realistic image generation. Our method is device agnostic, and can optimize an autoencoder for…
Writing high performance solvers for engineering applications is a delicate task. These codes are often developed on an application to application basis, highly optimized to solve a certain problem. Here, we present our work on developing a…
Customized processors are attractive solutions for vast domain-specific applications due to their high energy efficiency. However, designing a processor in traditional flows is time-consuming and expensive. To address this, researchers have…
GPUs have become indispensable in high-performance computing, machine learning, and many other domains. Efficiently utilizing the memory subsystem on GPUs is critical for maximizing computing power through massive parallelism. Analyzing…
We present cudaclaw, a CUDA-based high performance data-parallel framework for the solution of multidimensional hyperbolic partial differential equation (PDE) systems, equations describing wave motion. cudaclaw allows computational…
Communication overhead is a key challenge in distributed deep learning, especially on slower Ethernet interconnects, and given current hardware trends, communication is likely to become a major bottleneck. While gradient compression…
The UPC programming language offers parallelism via logically partitioned shared memory, which typically spans physically disjoint memory sub-systems. One convenient feature of UPC is its ability to automatically execute between-thread data…
AI applications increasingly run on fast-evolving, heterogeneous hardware to maximize performance, but general-purpose libraries lag in supporting these features. Performance-minded programmers often build custom communication stacks that…
Generating high-performance CUDA kernels remains challenging due to the need to navigate a combinatorial space of low-level transformations under noisy and expensive hardware feedback. Although large language models can synthesize…
FPGAs offer high performance, low latency, and energy efficiency for accelerated computing, yet adoption in scientific and edge settings is limited by the specialized hardware expertise required. High-level synthesis (HLS) boosts…
Training Large Language Models (LLMs) efficiently at scale presents a formidable challenge, driven by their ever-increasing computational demands and the need for enhanced performance. In this work, we introduce Liger-Kernel, an…
To alleviate hardware scarcity in training large deep neural networks (DNNs), particularly large language models (LLMs), we present FusionLLM, a decentralized training system designed and implemented for training DNNs using geo-distributed…
We describe the Bandicoot GPU linear algebra toolkit, a C++ based library that prioritises ease of use without compromising efficiency. Bandicoot's API is compatible with the popular Armadillo CPU linear algebra library, enabling easy…
Quantum approaches to combinatorial optimization problems (COPs) are often limited by the resource demands of Quadratic Unconstrained Binary Optimization (QUBO) encodings, which enlarge circuits through penalty terms and increase qubit and…
Coarse-Grained Reconfigurable Arrays (CGRAs) offer high performance and energy efficiency across domains, yet design remains difficult due to a vast, interdependent space and costly manual iteration. We present MACO, an open-source…
Multicore CPU architectures have been established as a structure for general-purpose systems for high-performance processing of applications. Recent multicore CPU has evolved as a system architecture based on non-uniform memory…
This paper presents Nova, a real-time scheduling framework for serving agentic vision-language models (VLMs) on a single GPU with balanced per-request latency and overall request process throughput. Our design begins by enabling effective…
For six decades, software engineering principles have been optimized for a single consumer: the human developer. The rise of agentic AI development, where LLM-based agents autonomously read, write, navigate, and debug codebases, introduces…
Scientific applications continue to rely on legacy Fortran codebases originally developed for homogeneous, CPU-based systems. As High-Performance Computing (HPC) shifts toward heterogeneous GPU-accelerated architectures, many accelerators…
Combinatorial optimization problems involving multiple agents are notoriously challenging due to their NP-hard nature and the necessity for effective agent coordination. Despite advancements in learning-based methods, existing approaches…