Related papers: AutoKernel: Autonomous GPU Kernel Optimization via…

When large language models (LLMs) serve real-time inference in commercial online advertising systems, end-to-end latency must be strictly bounded to the millisecond range. Yet every token generated during the decode phase triggers thousands…

Modern computing platforms tend to deploy multiple GPUs (2, 4, or more) on a single node to boost system performance, with each GPU having a large capacity of global memory and streaming multiprocessors (SMs). GPUs are an expensive…

Spiking Neural Networks (SNNs) can offer ultra-low power/energy consumption for machine learning-based application tasks due to their sparse spike-based operations. Currently, most of the SNN architectures need a significantly larger model…

Recent studies operationalize self-improvement through coding agents that edit their own codebases. They grow a tree of self-modifications through expansion strategies that favor higher software engineering benchmark performance, assuming…

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…

Due to noisy actuation and external disturbances, tuning controllers for high-speed flight is very challenging. In this paper, we ask the following questions: How sensitive are controllers to tuning when tracking high-speed maneuvers? What…

Autotuning is an established technique for optimizing the performance of parallel applications. However, programmers must prepare applications for autotuning, which is tedious and error prone coding work. We demonstrate how applications…

VIBETENSOR is an open-source research system software stack for deep learning, generated by LLM-powered coding agents under high-level human guidance. In this paper, "fully generated" refers to code provenance: implementation changes were…

Hand-optimizing linear algebra kernels for different GPU devices and applications is complex and labor-intensive. Instead, many developers use automatic performance tuning (autotuning) to achieve high performance on a variety of devices.…

Autonomous vehicles have limited computational resources and thus require efficient control systems. The cost and size of sensors have limited the development of self-driving cars. To overcome these restrictions, this study proposes an…

Large language models (LLMs) have already revolutionized code generation, after being pretrained on publicly available code data. However, while various methods have been proposed to augment LLMs with retrieved knowledge and enhance the…

Stencil computation is one of the most widely-used compute patterns in high performance computing applications. Spatial and temporal blocking have been proposed to overcome the memory-bound nature of this type of computation by moving…

Finding errors in machine learning applications requires a thorough exploration of their behavior over data. Existing approaches used by practitioners are often ad-hoc and lack the abstractions needed to scale this process. We present…

Benchmarking has been the cornerstone of progress in computer vision, natural language processing, and the broader deep learning domain, driving algorithmic innovation through standardized datasets and reproducible evaluation protocols. The…

Generative artificial intelligence (AI) technology is revolutionizing the computing industry. Not only its applications have broadened to various sectors but also poses new system design and optimization opportunities. The technology is…

Graph Neural Networks (GNNs) have been widely adopted due to their strong performance. However, GNN training often relies on expensive, high-performance computing platforms, limiting accessibility for many tasks. Profiling of representative…

Automated machine learning (AutoML) accelerates AI development by automating tasks in the development pipeline, such as optimal model search and hyperparameter tuning. Existing AutoML systems often require technical expertise to set up…

Current AutoML platforms leave substantial performance untapped. Testing 180 fine-tuning tasks across models from 70M to 70B parameters, we found that HuggingFace AutoTrain, TogetherAI, Databricks, and Google Cloud consistently produce…

Peak performance metrics published by vendors often do not correspond to what can be achieved in practice. It is therefore of great interest to do extensive benchmarking on core applications and library routines. Since DGEMM is one of the…

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…