Related papers: Evaluating CUDA Tile for AI Workloads on Hopper an…

The efficiency of attention is important due to its quadratic time complexity. We enhance the efficiency of attention through two key contributions: First, we leverage the new FP4 Tensor Cores in Blackwell GPUs to accelerate attention…

Efficient CUDA implementations of attention mechanisms are critical to modern deep learning systems, yet supporting diverse and evolving attention variants remains challenging. Existing frameworks and compilers trade performance for…

The challenge of mapping AI architectures to GPU hardware is creating a critical bottleneck in AI progress. Despite substantial efforts, hand-written custom kernels fail to meet their theoretical performance thresholds, even on…

The demand for efficient machine learning (ML) accelerators is growing rapidly, driving the development of novel computing concepts such as resistive random access memory (RRAM)-based tiled computing-in-memory (CIM) architectures. CIM…

In this work, we introduce new batching algorithms to effectively handle large contractions encountered in coupled-cluster singles and doubles (CCSD) implementations in Python on the Video Random Access Memory (VRAM) of graphical processing…

Graphics Processing Units (GPUs) have become the standard in accelerating scientific applications on heterogeneous systems. However, as GPUs are getting faster, one potential performance bottleneck with GPU-accelerated applications is the…

GPUs have become the dominant source of computing power for high performance computing and are increasingly being used across the High Energy Physics computing landscape for a wide variety of tasks. Though NVIDIA is currently the main…

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…

Deep learning (DL) frameworks take advantage of GPUs to improve the speed of DL inference and training. Ideally, DL frameworks should be able to fully utilize the computation power of GPUs such that the running time depends on the amount of…

We scrutinize how to accelerate the bottleneck operations of Pythonic coupled cluster implementations performed on a \texttt{NVIDIA} Tesla V100S PCIe 32GB (rev 1a) Graphics Processing Unit (GPU). The \texttt{NVIDIA} Compute Unified Device…

In this paper, we propose CUDA-L2, a system that combines large language models (LLMs) and reinforcement learning (RL) to automatically optimize Half-precision General Matrix Multiply (HGEMM) CUDA kernels. Using CUDA execution speed as the…

Artificial Intelligence (AI) applications, such as Large Language Models, are primarily driven and executed by Graphics Processing Units (GPUs). These GPU programs (kernels) consume substantial amounts of energy, yet software developers…

The rise of disaggregated AI GPUs has exposed a critical bottleneck in large-scale attention workloads: non-uniform memory access (NUMA). As multi-chiplet designs become the norm for scaling compute capabilities, memory latency and…

Modern GPUs adopt chiplet-based designs with multiple private cache hierarchies, but current programming models (CUDA/HIP) expose a flat execution hierarchy that cannot express chiplet-level locality or synchronization. This mismatch leads…

Large language models show promise for automated CUDA programming, however even the strongest coding models (e.g., Claude-Opus-4.6) may still fall short of expert-level, architecture-aware optimization. We introduce CUDAHercules, a…

CUDA is one of the most popular choices for GPU programming, but it can only be executed on NVIDIA GPUs. Executing CUDA on non-NVIDIA devices not only benefits the hardware community, but also allows data-parallel computation in…

We present a new very fast tree-code which runs on massively parallel Graphical Processing Units (GPU) with NVIDIA CUDA architecture. The tree-construction and calculation of multipole moments is carried out on the host CPU, while the force…

This paper introduces a unified, hardware-independent baremetal runtime architecture designed to enable high-performance machine learning (ML) inference on heterogeneous accelerators, such as AI Engine (AIE) arrays, without the overhead of…

Large Language Models (LLMs) such as LLaMA and DeepSeek, are built on transformer architectures, which have become a standard model for achieving state-of-the-art performance in natural language processing tasks. Recently, there has been…

Multi-GPU programming traditionally requires developers to navigate complex trade-offs between performance and programmability. High-performance implementations typically rely on low-level HIP/CUDA communication libraries that demand…