Related papers: Equivalence Checking of ML GPU Kernels

Large language models (LLMs) with billions of parameters and pretrained on massive amounts of data are now capable of near or better than state-of-the-art performance in a variety of downstream natural language processing tasks. Neural…

This paper presents a tool for repairing errors in GPU kernels written in CUDA or OpenCL due to data races and barrier divergence. Our novel extension to prior work can also remove barriers that are deemed unnecessary for correctness. We…

3D Gaussian splatting (3DGS) is a transformative technique with profound implications on novel view synthesis and real-time rendering. Given its importance, there have been many attempts to improve its performance. However, with the…

As high-performance computing (HPC) systems rapidly evolve, with increasing on-node parallelism and widespread use of accelerators, understanding how the code maps to hardware is essential for reaching optimal performance. Benchmarks are…

Large Language Models (LLMs) have emerged as powerful tools for natural language processing tasks, revolutionizing the field with their ability to understand and generate human-like text. As the demand for more sophisticated LLMs continues…

Lattice Boltzmann methods (LBM) are an important part of current computational fluid dynamics (CFD). They allow easy implementations and boundary handling. However, competitive time to solution not only depends on the choice of a reasonable…

Judging the equivalence between two SQL queries is a fundamental problem with many practical applications in data management and SQL generation (i.e., evaluating the quality of generated SQL queries in text-to-SQL task). While the research…

We propose a memory-efficient finetuning algorithm for large language models (LLMs) that supports finetuning LLMs with 65B parameters in 2/3/4-bit precision on as little as one 24GB GPU. Our method, modular low-rank adaptation (ModuLoRA),…

Large Language Models (LLMs) have demonstrated remarkable capabilities across various fields, from natural language understanding to text generation. Compared to non-generative LLMs like BERT and DeBERTa, generative LLMs like GPT series and…

High-performance GPU kernels are critical to modern machine learning systems, yet developing efficient implementations remains a challenging, expert-driven process due to the tight coupling between algorithmic structure, memory hierarchy…

This work presents CLTune, an auto-tuner for OpenCL kernels. It evaluates and tunes kernel performance of a generic, user-defined search space of possible parameter-value combinations. Example parameters include the OpenCL workgroup size,…

Equivalence checking of SQL queries is an intractable problem often encountered in settings ranging from grading SQL submissions to debugging query optimizers. Despite recent work toward developing practical solutions, only simple queries…

Optimizing GPU kernels presents a significantly greater challenge for large language models (LLMs) than standard code generation tasks, as it requires understanding hardware architecture, parallel optimization strategies, and performance…

The widespread adoption of large language models (LLMs) has made GPU-accelerated inference a critical part of modern computing infrastructure. Production inference systems rely on CUDA kernels to implement core transformer operations, yet…

CUDA and OpenCL are two different frameworks for GPU programming. OpenCL is an open standard that can be used to program CPUs, GPUs, and other devices from different vendors, while CUDA is specific to NVIDIA GPUs. Although OpenCL promises a…

Since the advent of parallel algorithms in the C++17 Standard Template Library (STL), the STL has become a viable framework for creating performance-portable applications. Given multiple existing implementations of the parallel algorithms,…

Recent advancements in multimodal large language models (MLLM) have shown a strong ability in visual perception, reasoning abilities, and vision-language understanding. However, the visual matching ability of MLLMs is rarely studied,…

The automatic generation of deep learning (DL) kernels using large language models (LLMs) has emerged as a promising approach to reduce the manual effort and hardware-specific expertise required for writing high-performance operator…

Neural kernels have drastically increased performance on diverse and nonstandard data modalities but require significantly more compute, which previously limited their application to smaller datasets. In this work, we address this by…

We explore the equivalence between neural networks and kernel methods by deriving the first exact representation of any finite-size parametric classification model trained with gradient descent as a kernel machine. We compare our exact…