Related papers: FlashAbacus: A Self-Governing Flash-Based Accelera…
In this paper, we consider a heterogenous network (HetNet), where low-power indoor femtocells are deployed in the coverage area of the existing macro base station (MBS). This paper proposes a novel coordinated random beamforming and user…
Optimizing data movements is becoming one of the biggest challenges in heterogeneous computing to cope with data deluge and, consequently, big data applications. When creating specialized accelerators, modern high-level synthesis (HLS)…
Attention mechanisms, particularly within Transformer architectures and large language models (LLMs), have revolutionized sequence modeling in machine learning and artificial intelligence applications. To compute attention for increasingly…
Hardware heterogeneity is here to stay for high-performance computing. Large-scale systems are currently equipped with multiple GPU accelerators per compute node and are expected to incorporate more specialized hardware. This shift in the…
This paper introduces FlexNN, a Flexible Neural Network accelerator, which adopts agile design principles to enable versatile dataflows, enhancing energy efficiency. Unlike conventional convolutional neural network accelerator architectures…
Today's computing systems require moving data back-and-forth between computing resources (e.g., CPUs, GPUs, accelerators) and off-chip main memory so that computation can take place on the data. Unfortunately, this data movement is a major…
Novel materials and devices in photonics have the potential to revolutionize optical information processing, beyond conventional binary-logic approaches. Laser systems offer a rich repertoire of useful dynamical behaviors, including the…
The surge in generative AI workloads has created a need for scalable inference systems that can flexibly harness both GPUs and specialized accelerators while containing operational costs. This paper proposes a hardware-agnostic control loop…
As the performance gains from accelerating quantized matrix multiplication plateau, the softmax operation becomes the critical bottleneck in Transformer inference. This bottleneck stems from two hardware limitations: (1) limited data…
Graph processing systems are essential for analyzing large-scale data with complex relationships, yet most existing frameworks rely on statically provisioned clusters, resulting in poor elasticity and inefficient resource utilization under…
Transformer architectures have become the standard neural network model for various machine learning applications including natural language processing and computer vision. However, the compute and memory requirements introduced by…
Heterogeneous systems consisting of general-purpose processors and different types of hardware accelerators are becoming more and more common in HPC systems. Especially FPGAs provide a promising opportunity to improve both performance and…
Sparsity is a growing trend in modern DNN models. Existing Sparse-Sparse Matrix Multiplication (SpMSpM) accelerators are tailored to a particular SpMSpM dataflow (i.e., Inner Product, Outer Product or Gustavsons), that determines their…
This paper consists of three parts. The first part provides a unified programming model for heterogeneous computing with CPU and accelerator (like GPU, FPGA, Google TPU, Atos QPU, and more) technologies. To some extent, this new programming…
Neutral atoms have emerged as a promising technology for implementing quantum computers due to their scalability and long coherence times. However, the execution frequency of neutral atom quantum computers is constrained by image processing…
Heterogeneous processors, formed by binary compatible CPU cores with different microarchitectures, enable energy reductions by better matching processing capabilities and software application requirements. This new hardware platform…
This paper proposes a hybrid energy storage system (HESS)-based control framework that enables comprehensive power smoothing for hyperscale AI datacenters with large load variations. Datacenters impose severe ramping and fluctuation-induced…
Edge/Fog computing is a novel computing paradigm that provides resource-limited Internet of Things (IoT) devices with scalable computing and storage resources. Compared to cloud computing, edge/fog servers have fewer resources, but they can…
Image processing algorithms are prime targets for hardware acceleration as they are commonly used in resource- and power-limited applications. Today's image processing accelerator designs make rigid assumptions about the algorithm…
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…