English
Related papers

Related papers: TLX: Hardware-Native, Evolvable MIMW GPU Compiler …

200 papers

The rapid evolution of Large Language Models (LLMs) has driven a growing demand for automated, high-performance system kernels to accelerate machine learning workloads. We introduce TritonRL, a domain-specialized 8B-scale LLM for Triton…

Software Engineering · Computer Science 2026-02-10 Jiin Woo , Shaowei Zhu , Allen Nie , Zhen Jia , Yida Wang , Youngsuk Park

The demand for AI-generated GPU kernels is rapidly growing, influenced by the need for scalable, hardware-optimized solutions in both industry and academia. As deep learning workloads grow in complexity and diversity, it is imperative to…

Computation and Language · Computer Science 2025-08-01 Jianghui Wang , Vinay Joshi , Saptarshi Majumder , Xu Chao , Bin Ding , Ziqiong Liu , Pratik Prabhanjan Brahma , Dong Li , Zicheng Liu , Emad Barsoum

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

Recent studies have extensively explored NPU architectures for accelerating AI inference in on-device environments, which are inherently resource-constrained. Meanwhile, transformer-based large language models (LLMs) have become dominant,…

Hardware Architecture · Computer Science 2026-02-16 Jonghun Lee , Junghoon Lee , Hyeonjin Kim , Seoho Jeon , Jisup Yoon , Hyunbin Park , Meejeong Park , Heonjae Ha

Pipelining between data loading and computation is a critical tensor program optimization for GPUs. In order to unleash the high performance of latest GPUs, we must perform a synergetic optimization of multi-stage pipelining across the…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-05-09 Guyue Huang , Yang Bai , Liu Liu , Yuke Wang , Bei Yu , Yufei Ding , Yuan Xie

We consider the problem of transposing tensors of arbitrary dimension and describe TTC, an open source domain-specific parallel compiler. TTC generates optimized parallel C++/CUDA C code that achieves a significant fraction of the system's…

Mathematical Software · Computer Science 2016-07-06 Paul Springer , Aravind Sankaran , Paolo Bientinesi

Address translation and protection play important roles in today's processors, supporting multiprocessing and enforcing security. Historically, the design of the address translation mechanisms has been closely tied to the instruction set.…

Hardware Architecture · Computer Science 2019-05-17 Xuan Guo , Robert Mullins

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

Kernel development in deep learning requires optimizing computational units across hardware while balancing memory management, parallelism, and hardware-specific optimizations through extensive empirical tuning. Although domain-specific…

Machine Learning · Computer Science 2025-07-09 Shangzhan Li , Zefan Wang , Ye He , Yuxuan Li , Qi Shi , Jianling Li , Yonggang Hu , Wanxiang Che , Xu Han , Zhiyuan Liu , Maosong Sun

LLM-based Triton kernel generation has attracted significant interest, yet a fundamental empirical question remains unanswered: where does this capability break down, and why? We present KernelBenchX, a benchmark designed to answer this…

Machine Learning · Computer Science 2026-05-12 Han Wang , Jintao Zhang , Kai Jiang , Haoxu Wang , Jianfei Chen , Jun Zhu

Developing efficient GPU kernels is essential for scaling modern AI systems, yet it remains a complex task due to intricate hardware architectures and the need for specialized optimization expertise. Although Large Language Models (LLMs)…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-12 Ali Tehrani , Yahya Emara , Essam Wissam , Wojciech Paluch , Waleed Atallah , Łukasz Dudziak , Mohamed S. Abdelfattah

We present Calyx, a new intermediate language (IL) for compiling high-level programs into hardware designs. Calyx combines a hardware-like structural language with a software-like control flow representation with loops and conditionals.…

Programming Languages · Computer Science 2021-11-17 Rachit Nigam , Samuel Thomas , Zhijing Li , Adrian Sampson

Efficient tensor computation is a cornerstone of modern deep learning (DL) workloads, yet existing approaches struggle to achieve flexible and performant design and implementation of tensor layouts -- mappings between logical tensors and…

The current manufacturing technology allows the integration of a complex multiprocessor system on one piece of silicon (MPSoC for Multiprocessor System-on- Chip). One way to manage the growing complexity of these systems is to increase the…

Hardware Architecture · Computer Science 2014-08-06 Abdelhakim Alali , Ismail Assayad , Mohamed Sadik

Models of High-level Computation (MHCs) provide effective means to describe complex real-world computing systems because they offer formal foundations for the specification of interacting computing devices, as opposed to describing…

Logic in Computer Science · Computer Science 2026-02-17 Damian Arellanes

Tensor processing units (TPUs) are one of the most well-known machine learning (ML) accelerators utilized at large scale in data centers as well as in tiny ML applications. TPUs offer several improvements and advantages over conventional ML…

Hardware Architecture · Computer Science 2024-07-12 Mohammed Elbtity , Peyton Chandarana , Ramtin Zand

GPUs exploit a high degree of thread-level parallelism to hide long-latency stalls. Due to the heterogeneous compute requirements of different applications, there is a growing need to share the GPU across multiple applications in…

Although recent scaling up approaches to training deep neural networks have proven to be effective, the computational intensity of large and complex models, as well as the availability of large-scale datasets, require deep learning…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-04-21 Bita Hasheminezhad , Shahrzad Shirzad , Nanmiao Wu , Patrick Diehl , Hannes Schulz , Hartmut Kaiser

Machine learning models are increasingly being trained across multiple GPUs and servers. In this setting, data is transferred between GPUs using communication collectives such as AlltoAll and AllReduce, which can become a significant…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-10-06 Aashaka Shah , Vijay Chidambaram , Meghan Cowan , Saeed Maleki , Madan Musuvathi , Todd Mytkowicz , Jacob Nelson , Olli Saarikivi , Rachee Singh

We present an end-to-end open-source compiler toolchain that targets synthesizable SystemVerilog from ML models written in PyTorch. Our toolchain leverages the accelerator design language Allo, the hardware intermediate representation (IR)…

Hardware Architecture · Computer Science 2025-12-09 Jiahan Xie , Evan Williams , Adrian Sampson