Related papers: Computation offloading to hardware accelerators in…

Nowadays, the High Performance Computing is part of the context of embedded systems. Graphics Processing Units (GPUs) are more and more used in acceleration of the most part of algorithms and applications. Over the past years, not many…

Deploying deep neural networks on mobile devices is increasingly important but remains challenging due to limited computing resources. On the other hand, their unified memory architecture and narrower gap between CPU and GPU performance…

FPGA-based hardware accelerators are becoming increasingly popular due to their versatility, customizability, energy efficiency, constant latency, and scalability. FPGAs can be tailored to specific algorithms, enabling efficient hardware…

Domain-specific accelerators are used in various computing systems ranging from edge devices to data centers. Coarse-grained reconfigurable arrays (CGRAs) represent an architectural midpoint between the flexibility of an FPGA and the…

As part of the Exascale Computing Project (ECP), a recent focus of development efforts for the SUite of Nonlinear and DIfferential/ALgebraic equation Solvers (SUNDIALS) has been to enable GPU-accelerated time integration in scientific…

Differential privacy offers a formal privacy guarantee for individuals, but many deployments of differentially private systems require a trusted third party (the data curator). We propose DuetSGX, a system that uses secure hardware (Intel's…

Large Language Models (LLMs) have demonstrated exceptional benefits to a wide range of domains, for tasks as diverse as code generation and robot navigation. While LLMs are usually served from cloud data centers, mission-critical and…

Sparse tensor programs are essential in deep learning and graph analytics, driving the need for optimized processing. To meet this demand, specialized hardware accelerators are being developed. Optimizing these programs for accelerators is…

In this paper, we focus on three sparse matrix operations that are relevant for machine learning applications, namely, the sparse-dense matrix multiplication (SPMM), the sampled dense-dense matrix multiplication (SDDMM), and the composition…

For many years, systems running Nvidia-based GPU architectures have dominated the heterogeneous supercomputer landscape. However, recently GPU chipsets manufactured by Intel and AMD have cut into this market and can now be found in some of…

Graph Neural Networks (GNNs) are emerging as a powerful tool for learning from graph-structured data and performing sophisticated inference tasks in various application domains. Although GNNs have been shown to be effective on modest-sized…

Modern GPU applications, such as machine learning (ML), can only partially utilize GPUs, leading to GPU underutilization in cloud environments. Sharing GPUs across multiple applications from different tenants can improve resource…

Future MPSoCs with 1000 or more processor cores on a chip require new means for resource-aware programming in order to deal with increasing imperfections such as process variation, fault rates, aging effects, and power as well as thermal…

Software configurable processors (SCP) implement compute intensive applications very efficiently on the special onchip configurable hardware. The SCP by Stretch Inc. converts the computeheavy algorithms into custom instructions, called…

Scientific computing sometimes involves computation on sensitive data. Depending on the data and the execution environment, the HPC (high-performance computing) user or data provider may require confidentiality and/or integrity guarantees.…

Last several years, GPUs are used to accelerate computations in many computer science domains. We focused on GPU accelerated Support Vector Machines (SVM) training with non-linear kernel functions. We had searched for all available GPU…

The expansion of context windows in large language models (LLMs) to multi-million tokens introduces severe memory and compute bottlenecks, particularly in managing the growing Key-Value (KV) cache. While Compute Express Link (CXL) enables…

The extensive use of GPUs in cloud computing and the growing need for multitenancy have driven the development of innovative solutions for efficient GPU resource management. Multi-Instance GPU (MIG) technology from NVIDIA enables shared GPU…

Sparse-dense linear algebra is crucial in many domains, but challenging to handle efficiently on CPUs, GPUs, and accelerators alike; multiplications with sparse formats like CSR and CSF require indirect memory lookups. In this work, we…

Graph neural networks (GNNs) can extract features by learning both the representation of each objects (i.e., graph nodes) and the relationship across different objects (i.e., the edges that connect nodes), achieving state-of-the-art…