English
Related papers

Related papers: Tilus: A Tile-Level GPGPU Programming Language for…

200 papers

We present LLMQ, an end-to-end CUDA/C++ implementation for medium-sized language-model training, e.g. 3B to 32B parameters, on affordable, commodity GPUs. These devices are characterized by low memory availability and slow communication…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-18 Erik Schultheis , Dan Alistarh

Large Language Model (LLM) inference uses an autoregressive manner to generate one token at a time, which exhibits notably lower operational intensity compared to earlier Machine Learning (ML) models such as encoder-only transformers and…

Hardware Architecture · Computer Science 2025-05-06 Yufeng Gu , Alireza Khadem , Sumanth Umesh , Ning Liang , Xavier Servot , Onur Mutlu , Ravi Iyer , Reetuparna Das

Efficient GPU programming is crucial for achieving high performance in deep learning (DL) applications. The performance of GPU programs depends on how data is parallelized across threads and arranged within memory subsystems. The mapping…

Machine Learning · Computer Science 2026-01-30 Xiao Zhang , Yaoyao Ding , Bolin Sun , Yang Hu , Tatiana Shpeisman , Gennady Pekhimenko

Specializing large language models (LLMs) for local deployment in domain-specific use cases is necessary for strong performance while meeting latency and privacy constraints. However, conventional task-specific adaptation approaches do not…

Machine Learning · Computer Science 2024-12-20 Lanxiang Hu , Tajana Rosing , Hao Zhang

The increasing complexity and scale of Deep Neural Networks (DNNs) necessitate specialized tensor accelerators, such as Tensor Processing Units (TPUs), to meet various computational and energy efficiency requirements. Nevertheless,…

Hardware Architecture · Computer Science 2025-03-11 Deepak Vungarala , Mohammed E. Elbtity , Sumiya Syed , Sakila Alam , Kartik Pandit , Arnob Ghosh , Ramtin Zand , Shaahin Angizi

Fine-grained workload and resource balancing is the key to high performance for regular and irregular computations on the GPUs. In this dissertation, we conduct an extensive survey of existing load-balancing techniques to build an…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-12-20 Muhammad Osama

Recent breakthroughs in Large-scale language models (LLMs) have demonstrated impressive performance on various tasks. The immense sizes of LLMs have led to very high resource demand and cost for running the models. Though the models are…

Machine Learning · Computer Science 2024-03-05 Juntao Zhao , Borui Wan , Yanghua Peng , Haibin Lin , Chuan Wu

Although Large Language Models (LLMs) have demonstrated remarkable capabilities, their massive parameter counts and associated extensive computing make LLMs' deployment the main part of carbon emission from nowadays AI applications.…

Machine Learning · Computer Science 2024-10-24 Jie Peng , Zhang Cao , Huaizhi Qu , Zhengyu Zhang , Chang Guo , Yanyong Zhang , Zhichao Cao , Tianlong Chen

Machine translation (MT) systems that support low-resource languages often struggle on specialized domains. While researchers have proposed various techniques for domain adaptation, these approaches typically require model fine-tuning,…

Computation and Language · Computer Science 2025-05-27 Raphaël Merx , Hanna Suominen , Lois Hong , Nick Thieberger , Trevor Cohn , Ekaterina Vylomova

Performance modeling, a pivotal domain in program cost analysis, currently relies on manually crafted models constrained by various program and hardware limitations, especially in the intricate landscape of GPGPU. Meanwhile, Large Language…

Performance · Computer Science 2025-03-17 Khoi N. M. Nguyen , Hoang Duy Nguyen Do , Huyen Thao Le , Thanh Tuan Dao

Large Language Model (LLM) inference requires substantial computational resources, yet CPU-based inference remains essential for democratizing AI due to the widespread availability of CPUs compared to specialized accelerators. However,…

Hardware Architecture · Computer Science 2025-10-01 Jingyao Zhang , Jaewoo Park , Jongeun Lee , Elaheh Sadredini

Machine Learning (ML) models execute several parallel computations including Generalized Matrix Multiplication, Convolution, Dropout, etc. These computations are commonly executed on Graphics Processing Units (GPUs), by dividing the…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-02-15 Abhinav Jangda , Saeed Maleki , Maryam Mehri Dehnavi , Madan Musuvathi , Olli Saarikivi

FPGAs are increasingly adopted in datacenter environments for their reconfigurability and energy efficiency. High-Level Synthesis (HLS) tools have eased FPGA programming by raising the abstraction level from RTL to untimed C/C++, yet…

Machine Learning · Computer Science 2025-05-01 Neha Prakriya , Zijian Ding , Yizhou Sun , Jason Cong

Fine-tuning large language models (LLMs) requires significant memory, often exceeding the capacity of a single GPU. A common solution to this memory challenge is offloading compute and data from the GPU to the CPU. However, this approach is…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-02-11 Siyuan Chen , Zhuofeng Wang , Zelong Guan , Yudong Liu , Phillip B. Gibbons

The billion-scale Large Language Models (LLMs) need deployment on expensive server-grade GPUs with large-storage HBMs and abundant computation capability. As LLM-assisted services become popular, achieving cost-effective LLM inference on…

Hardware Architecture · Computer Science 2025-02-25 Lian Liu , Shixin Zhao , Bing Li , Haimeng Ren , Zhaohui Xu , Mengdi Wang , Xiaowei Li , Yinhe Han , Ying Wang

NVIDIA's CUDA Tile (CuTile) introduces a Python-based, tile-centric abstraction for GPU kernel development that aims to simplify programming while retaining Tensor Core and Tensor Memory Accelerator (TMA) efficiency on modern GPUs. We…

Machine Learning · Computer Science 2026-04-28 Divakar Kumar Yadav , Tian Zhao , Deepak Kumar

High-Level Synthesis (HLS) plays a crucial role in modern hardware design by transforming high-level code into optimized hardware implementations. However, progress in applying machine learning (ML) to HLS optimization has been hindered by…

Hardware Architecture · Computer Science 2025-08-05 Zedong Peng , Zeju Li , Mingzhe Gao , Qiang Xu , Chen Zhang , Jieru Zhao

Neural processing units (NPUs) are gaining prominence in power-sensitive devices like client devices, with AI PCs being defined by their inclusion of these specialized processors. Running AI workloads efficiently on these devices requires…

Programming Languages · Computer Science 2025-07-22 Sarunas Kalade , Graham Schelle

High-performance GPU kernels are essential for efficient LLM deployment, yet optimizing them remains expertise-intensive. Recent LLM-based code generation makes automatic GPU operator generation promising, but operator optimization remains…

Computation and Language · Computer Science 2026-05-29 Yining Zhang , Mingyang Yi , Chen Wang , Xuwen Xiang , Tianhe Jia , Zedong Dan , Chengqing Zong , Yue Wang

The rapid scaling of Large Language Models (LLMs) has pushed training workloads far beyond the limits of single-node analysis, demanding a deeper understanding of how these models behave across large-scale, multi-GPU systems. In this paper,…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-22 Seokjin Go , Joongun Park , Spandan More , Hanjiang Wu , Irene Wang , Aaron Jezghani , Tushar Krishna , Divya Mahajan