Related papers: GPU-parallelisation of wavelet-based grid adaptati…
Emerging AI accelerators increasingly adopt wafer-scale manufacturing technologies, integrating hundreds of thousands of AI cores in a mesh architecture with large distributed on-chip memory (tens of GB in total) and ultra-high on-chip…
We propose a highly parallel primal-dual algorithm for the multicut (a.k.a. correlation clustering) problem, a classical graph clustering problem widely used in machine learning and computer vision. Our algorithm consists of three steps…
Large Language Models (LLMs) demand substantial computational resources, resulting in high energy consumption on GPUs. To address this challenge, we focus on Coarse-Grained Reconfigurable Arrays (CGRAs) as an effective alternative that…
The aggressive densification of modern wireless networks necessitates judicious resource allocation to mitigate severe mutual interference. However, classical iterative algorithms remain computationally prohibitive for real-time…
The Convex Hull algorithm is one of the most important algorithms in computational geometry, with many applications such as in computer graphics, robotics, and data mining. Despite the advances in the new algorithms in this area, it is…
We describe an implementation of compressible inviscid fluid solvers with block-structured adaptive mesh refinement on Graphics Processing Units using NVIDIA's CUDA. We show that a class of high resolution shock capturing schemes can be…
The performance of applications that require frame rendering time estimation or dynamic frequency scaling, rely on the accuracy of the workload model that is utilized within these applications. Existing models lack sufficient accuracy in…
Field Programmable Gate Arrays(FPGA) exceed the computing power of software based implementations by breaking the paradigm of sequential execution and accomplishing more per clock cycle by enabling hardware level parallelization at an…
In this paper, we demonstrate how GPU-accelerated BEM routines can be used in a simple black-box fashion to accelerate fast boundary element formulations based on Hierarchical Matrices (H-Matrices) with ACA (Adaptive Cross Approximation).…
As the size of artificial intelligence and machine learning (AI/ML) models and datasets grows, the memory bandwidth becomes a critical bottleneck. The paper presents a novel extended memory hierarchy that addresses some major memory…
The rapid adoption of large language models and multimodal foundation models has made multimodal data preparation pipelines critical AI infrastructure. These pipelines interleave CPU-heavy preprocessing with accelerator-backed (GPU/NPU/TPU)…
Existing neural radiance fields (NeRF) methods for large-scale scene modeling require days of training using multiple GPUs, hindering their applications in scenarios with limited computing resources. Despite fast optimization NeRF variants…
The Random Phase Approximation (RPA) for correlation energy in the grid-based projector augmented wave (gpaw) code is accelerated by porting to the Graphics Processing Unit (GPU) architecture. The acceleration is achieved by grouping…
Modelling rock-fluid interaction requires solving a set of partial differential equations (PDEs) to predict the flow behaviour and the reactions of the fluid with the rock on the interfaces. Conventional high-fidelity numerical models…
This paper presents the design and evaluation of a GPU-accelerated inference pipeline for transformer models using NVIDIA TensorRT with mixed-precision optimization. We evaluate BERT-base (110M parameters) and GPT-2 (124M parameters) across…
In this paper, we explore the limits of graphics processors (GPUs) for general purpose parallel computing by studying problems that require highly irregular data access patterns: parallel graph algorithms for list ranking and connected…
This paper presents a multilevel convergence framework for multigrid-reduction-in-time (MGRIT) as a generalization of previous two-grid estimates. The framework provides a priori upper bounds on the convergence of MGRIT V- and F-cycles,…
In cloud machine learning (ML) inference systems, providing low latency to end-users is of utmost importance. However, maximizing server utilization and system throughput is also crucial for ML service providers as it helps lower the…
Cerebras' wafer-scale engine (WSE) technology merges multiple dies on a single wafer. It addresses the challenges of memory bandwidth, latency, and scalability, making it suitable for artificial intelligence. This work evaluates the WSE-3…
Domain-specific languages that execute image processing pipelineson GPUs, such as Halide and Forma, operate by 1) dividing the image into overlapped tiles, and 2) fusing loops to improve memory locality. However, current approaches have…