English
Related papers

Related papers: PREBA: A Hardware/Software Co-Design for Multi-Ins…

200 papers

Retrieval-augmented generation (RAG) extends large language models (LLMs) with external data sources to enhance factual correctness and domain coverage. Modern RAG pipelines rely on large datastores, creating a significant system challenge:…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-19 Chien-Yu Lin , Keisuke Kamahori , Yiyu Liu , Xiaoxiang Shi , Madhav Kashyap , Yile Gu , Rulin Shao , Zihao Ye , Kan Zhu , Rohan Kadekodi , Stephanie Wang , Arvind Krishnamurthy , Luis Ceze , Baris Kasikci

To amortize cost, cloud vendors providing DNN acceleration as a service to end-users employ consolidation and virtualization to share the underlying resources among multiple DNN service requests. This paper makes a case for a "preemptible"…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-09-11 Yujeong Choi , Minsoo Rhu

Synthesizing Mixed-Boolean Arithmetic (MBA) expressions from input-output examples is central to program deobfuscation and also useful for compiler optimization, reverse engineering, and cryptanalysis. Existing MBA synthesizers are…

Programming Languages · Computer Science 2026-05-12 Gabriel Bathie , Baptiste Mouillon , Nathanaël Fijalkow

Inference on large-language models (LLMs) is constrained by GPU memory capacity. A sudden increase in the number of inference requests to a cloud-hosted LLM can deplete GPU memory, leading to contention between multiple prompts for limited…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-02-24 Abhishek Vijaya Kumar , Gianni Antichi , Rachee Singh

The efficiency of long-video inference remains a critical bottleneck, mainly due to the dense computation in the prefill stage of Large Multimodal Models (LMMs). Existing methods either compress visual embeddings or apply sparse attention…

Computer Vision and Pattern Recognition · Computer Science 2026-01-30 Yuxiang Huang , Mingye Li , Xu Han , Chaojun Xiao , Weilin Zhao , Ao Sun , Ziqi Yuan , Hao Zhou , Fandong Meng , Zhiyuan Liu

Deep neural networks are widely used in personalized recommendation systems. Unlike regular DNN inference workloads, recommendation inference is memory-bound due to the many random memory accesses needed to lookup the embedding tables. The…

GPU-accelerated computing is a key technology to realize high-speed inference servers using deep neural networks (DNNs). An important characteristic of GPU-based inference is that the computational efficiency, in terms of the processing…

Performance · Computer Science 2021-01-13 Yoshiaki Inoue

Modern large-scale scientific discovery requires multidisciplinary collaboration across diverse computing facilities, including High Performance Computing (HPC) machines and the Edge-to-Cloud continuum. Integrated data analysis plays a…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-08-21 Renan Souza , Tyler J. Skluzacek , Sean R. Wilkinson , Maxim Ziatdinov , Rafael Ferreira da Silva

Developing efficient GPU kernels can be difficult because of the complexity of GPU architectures and programming models. Existing performance tools only provide coarse-grained suggestions at the kernel level, if any. In this paper, we…

Performance · Computer Science 2020-11-25 Keren Zhou , Xiaozhu Meng , Ryuichi Sai , John Mellor-Crummey

GPUs are the most popular platform for accelerating HPC workloads, such as artificial intelligence and science simulations. However, most microarchitectural research in academia relies on GPU core pipeline designs based on architectures…

Hardware Architecture · Computer Science 2025-10-30 Rodrigo Huerta , Mojtaba Abaie Shoushtary , José-Lorenzo Cruz , Antonio González

New heterogeneous computing paradigms on dedicated hardware with increased parallelization, such as Field Programmable Gate Arrays (FPGAs), offer exciting solutions with large potential gains. The growing applications of machine learning…

Analog front-end design heavily relies on specialized human expertise and costly trial-and-error simulations, which motivated many prior works on analog design automation. However, efficient and effective exploration of the vast and complex…

Machine Learning · Computer Science 2024-08-08 Souradip Poddar , Youngmin Oh , Yao Lai , Hanqing Zhu , Bosun Hwang , David Z. Pan

This paper summarizes the ideas and key concepts in MISE (Memory Interference-induced Slowdown Estimation), which was published in HPCA 2013 [97], and examines the work's significance and future potential. Applications running concurrently…

Hardware Architecture · Computer Science 2018-05-16 Lavanya Subramanian , Vivek Seshadri , Yoongu Kim , Ben Jaiyen , Onur Mutlu

Artificial intelligence (AI) is increasingly deployed in real-time and energy-constrained environments, driving demand for hardware platforms that can deliver high performance and power efficiency. While central processing units (CPUs) and…

Hardware Architecture · Computer Science 2026-01-28 Aybars Yunusoglu , Talha Coskun , Hiruna Vishwamith , Murat Isik , I. Can Dikmen

AI acceleration has been dominated by GPUs, but the growing need for lower latency, energy efficiency, and fine-grained hardware control exposes the limits of fixed architectures. In this context, Field-Programmable Gate Arrays (FPGAs)…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-18 Arturo Urías Jiménez

Graph Neural Networks (GNNs) are becoming a promising technique in various domains due to their excellent capabilities in modeling non-Euclidean data. Although a spectrum of accelerators has been proposed to accelerate the inference of…

Hardware Architecture · Computer Science 2023-11-17 Zeyu Zhu , Fanrong Li , Gang Li , Zejian Liu , Zitao Mo , Qinghao Hu , Xiaoyao Liang , Jian Cheng

Modern LLM serving now spans multi-stage pipelines including RAG retrieval and KV cache reuse, each with distinct compute, memory, and latency demands. Inference engines expose a large configuration space with no systematic navigation…

Discrete optimization is a central problem in artificial intelligence. The optimization of the aggregated cost of a network of cost functions arises in a variety of problems including (W)CSP, DCOP, as well as optimization in stochastic…

Artificial Intelligence · Computer Science 2018-01-12 Ferdinando Fioretto , Enrico Pontelli , William Yeoh , Rina Dechter

Benefiting from the self-attention mechanism, Transformer models have attained impressive contextual comprehension capabilities for lengthy texts. The requirements of high-throughput inference arise as the large language models (LLMs)…

Hardware Architecture · Computer Science 2024-07-16 Huizheng Wang , Jiahao Fang , Xinru Tang , Zhiheng Yue , Jinxi Li , Yubin Qin , Sihan Guan , Qize Yang , Yang Wang , Chao Li , Yang Hu , Shouyi Yin

In this work, we propose KPerfIR, a novel multilevel compiler-centric infrastructure to enable the development of customizable, extendable, and portable profiling tools tailored for modern artificial intelligence (AI) workloads on modern…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-05-29 Yue Guan , Yuanwei Fang , Keren Zhou , Corbin Robeck , Manman Ren , Zhongkai Yu , Yufei Ding , Adnan Aziz