Related papers: Intel(R) SHMEM: GPU-initiated OpenSHMEM using SYCL

We present SPDL (Scalable and Performant Data Loading), an open-source, framework-agnostic library designed for efficiently loading array data to GPU. Data loading is often a bottleneck in AI applications, and is challenging to optimize…

RAPID-LLM is a unified performance modeling framework for large language model (LLM) training and inference on GPU clusters. It couples a DeepFlow-based frontend that generates hardware-aware, operator-level Chakra execution traces from an…

Since the first idea of using GPU to general purpose computing, things have evolved over the years and now there are several approaches to GPU programming. GPU computing practically began with the introduction of CUDA (Compute Unified…

GPU-enhanced architectures are now dominant in HPC systems, but message-passing communication involving GPUs with MPI has proven to be both complex and expensive, motivating new approaches that lower such costs. We compare and contrast…

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…

FPGAs are increasingly prevalent in cloud deployments, serving as Smart NICs or network-attached accelerators. Despite their potential, developing distributed FPGA-accelerated applications remains cumbersome due to the lack of appropriate…

The remarkable progress of vision-language models (VLMs) has enabled GUI agents to interact with computers in a human-like manner. Yet real-world computer-use tasks remain difficult due to long-horizon workflows, diverse interfaces, and…

In modern computer architectures, the performance of many memory-bound workloads (e.g., machine learning, graph processing, databases) is limited by the data movement bottleneck that emerges when transferring large amounts of data between…

Distributed memory programming is the established paradigm used in high-performance computing (HPC) systems, requiring explicit communication between nodes and devices. When FPGAs are deployed in distributed settings, communication is…

Medical image processing is often limited by the computational cost of the involved algorithms. Whereas dedicated computing devices (GPUs in particular) exist and do provide significant efficiency boosts, they have an extra cost of use in…

The growing demands in the training and inference of Large Language Models (LLMs) are accelerating the adoption of scale-up systems that extend server shared memory through the use of Compute Express Link (CXL)-based load/store…

Large language models (LLMs) with different architectures and sizes have been developed. Serving each LLM with dedicated GPUs leads to resource waste and service inefficiency due to the varying demand of LLM requests. A common practice is…

We present hls4ml, a free and open-source platform that translates machine learning (ML) models from modern deep learning frameworks into high-level synthesis (HLS) code that can be integrated into full designs for field-programmable gate…

We propose a novel computing runtime that exposes remote compute devices via the cross-vendor open heterogeneous computing standard OpenCL and can execute compute tasks on the MEC cluster side across multiple servers in a scalable manner.…

The increasing scale and wealth of inter-connected data, such as those accrued by social network applications, demand the design of new techniques and platforms to efficiently derive actionable knowledge from large-scale graphs. However,…

Parallel programming models can encourage performance portability by moving the responsibility for work assignment and data distribution from the programmer to a runtime system. However, analyzing the resulting implicit memory allocations,…

We introduce pyGSL, a Python library that provides efficient implementations of state-of-the-art graph structure learning models along with diverse datasets to evaluate them on. The implementations are written in GPU-friendly ways, allowing…

Fully Homomorphic Encryption (FHE) is a technique that allows arbitrary computations to be performed on encrypted data without the need for decryption, making it ideal for securing many emerging applications. However, FHE computation is…

MGSim is an open source discrete event simulator for on-chip hardware components, developed at the University of Amsterdam. It is intended to be a research and teaching vehicle to study the fine-grained hardware/software interactions on…

Large Language Models (LLMs) have achieved impressive results across various tasks, yet their high computational demands pose deployment challenges, especially on consumer-grade hardware. Mixture of Experts (MoE) models provide an efficient…