Related papers: Experience with PCIe streaming on FPGA for high th…

While ML model training and inference are both GPU-intensive, CPU-based data processing is often the bottleneck. Distributed data processing systems based on the batch or stream processing models assume homogeneous resource requirements.…

Point clouds are increasingly important in intelligent applications, but frequent off-chip memory traffic in accelerators causes pipeline stalls and leads to high energy consumption. While conventional line buffer techniques can eliminate…

Real-time Big Data architectures evolved into specialized layers for handling data streams' ingestion, storage, and processing over the past decade. Layered streaming architectures integrate pull-based read and push-based write RPC…

This paper presents a stream processor generator, called SPGen, for FPGA-based system-on-chip platforms. In our research project, we use an FPGA as a common platform for applications ranging from HPC to embedded/robotics computing.…

Among hardware accelerators for deep-learning inference, data flow implementations offer low latency and high throughput capabilities. In these architectures, each neuron is mapped to a dedicated hardware unit, making them well-suited for…

GPUs are broadly used in I/O-intensive big data applications. Prior works demonstrate the benefits of using GPU-side file system layer, GPUfs, to improve the GPU performance and programmability in such workloads. However, GPUfs fails to…

High-throughput physics experiments require efficient and increasingly complex real-time processing. This paper presents a modular, software-defined platform combining high-bandwidth PCIe digitizers with consumer GPUs to achieve continuous,…

Transformers have revolutionized AI in natural language processing and computer vision, but their large computation and memory demands pose major challenges for hardware acceleration. In practice, end-to-end throughput is often limited by…

In high-energy physics, the increasing luminosity and detector granularity at the Large Hadron Collider are driving the need for more efficient data processing solutions. Machine Learning has emerged as a promising tool for reconstructing…

Intensive computation is entering data centers with multiple workloads of deep learning. To balance the compute efficiency, performance, and total cost of ownership (TCO), the use of a field-programmable gate array (FPGA) with…

Modern GPUs support special protocols to exchange data directly across the PCI Express bus. While these protocols could be used to reduce GPU data transmission times, basically by avoiding staging to host memory, they require specific…

Serverless computing has gained significant traction for machine learning inference applications, which are often deployed as serverless workflows consisting of multiple CPU and GPU functions with data dependency. However, existing…

Edge computing has emerged as a pivotal technology, offering significant advantages such as low latency, enhanced data security, and reduced reliance on centralized cloud infrastructure. These benefits are crucial for applications requiring…

Principal Component Analysis (PCA) is a widely used technique in machine learning, data analysis and signal processing. With the increase in the size and complexity of datasets, it has become important to develop low-space usage algorithms…

Searching for sources of electromagnetic emission in spectral-line radio astronomy interferometric data is a computationally intensive process. Parallel programming techniques and High Performance Computing hardware may be used to improve…

We designed and implemented a direct memory access (DMA) architecture of PCI-Express(PCIe) between Xilinx Field Program Gate Array(FPGA) and Freescale PowerPC. The DMA architecture based on FPGA is compatible with the Xilinx PCIe core while…

In recent years, high speed and high resolution analog-to-digital converter (ADC) is widely employed in many physical experiments, especially in high precision time and charge measurement. The rapid increasing amount of digitized data…

The attention layer, a core component of Transformer-based LLMs, brings out inefficiencies in current GPU systems due to its low operational intensity and the substantial memory requirements of KV caches. We propose a High-bandwidth…

Developing high performance embedded vision applications requires balancing run-time performance with energy constraints. Given the mix of hardware accelerators that exist for embedded computer vision (e.g. multi-core CPUs, GPUs, and…

Efficient deployment of large language models, particularly Mixture of Experts (MoE), on resource-constrained platforms presents significant challenges, especially in terms of computational efficiency and memory utilization. The MoE…