Related papers: sPIN: High-performance streaming Processing in the…
Spiking neural networks (SNNs) communicate via discrete spikes in time rather than continuous activations. Their event-driven nature offers advantages for temporal processing and energy efficiency on resource-constrained hardware, but…
Spiking Neural Network (SNN) inference has a clear potential for high energy efficiency as computation is triggered by events. However, the inherent sparsity of events poses challenges for conventional computing systems, driving the…
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…
Processing-in-memory (PIM) is a promising computing paradigm to tackle the "memory wall" challenge. However, PIM system-level benefits over traditional von Neumann architecture can be reduced when the memory array cannot fully store all the…
Accurate multiple-input multiple-output (MIMO) channel estimation is critical for next-generation wireless systems, enabling enhanced communication and sensing performance. Traditional model-based channel estimation methods suffer, however,…
Model parameter synchronization across GPUs introduces high overheads for data-parallel training at scale. Existing parameter synchronization protocols cannot effectively leverage available network resources in the face of ever increasing…
Demand for data-intensive workloads and confidential computing are the prominent research directions shaping the future of cloud computing. Computer architectures are evolving to accommodate the computing of large data better. Protecting…
Ising machines are specialized computers for finding the lowest energy states of Ising spin models, onto which many practical combinatorial optimization problems can be mapped. Simulated bifurcation (SB) is a quantum-inspired parallelizable…
We describe our experiences in using SPIN to verify parts of the Multi Purpose Daemon (MPD) parallel process management system. MPD is a distributed collection of processes connected by Unix network sockets. MPD is dynamic: processes and…
Modern heterogeneous supercomputing systems are comprised of CPUs, GPUs, and high-speed network interconnects. Communication libraries supporting efficient data transfers involving memory buffers from the GPU memory typically require the…
Computing demands for large scientific experiments, such as the CMS experiment at the CERN LHC, will increase dramatically in the next decades. To complement the future performance increases of software running on central processing units…
Portability is critical to ensuring high productivity in developing and maintaining scientific software as the diversity in on-node hardware architectures increases. While several programming models provide portability for diverse GPU…
Research has shown that convolutional neural networks contain significant redundancy, and high classification accuracy can be obtained even when weights and activations are reduced from floating point to binary values. In this paper, we…
Our long term goal is to execute General Purpose computation on homogeneous computing media consisting of millions of small identical Processing Elements (PE) communicating locally. We proceed by simulating the Self-Development of a Network…
With the rapid development of connecting massive devices to the Internet, especially for remote areas without cellular network infrastructures, space-air-ground integrated networks (SAGINs) emerge and offload computation-intensive tasks. In…
Software-defined networking (SDN) technology aims to create a highly flexible network by decoupling control plane and the data plane and programming them independently. There has been a lot of research on improving and optimizing the…
Dynamic behaviors are becoming prevalent in tensor applications, like machine learning, where many widely used models contain data-dependent tensor shapes and control flow. However, the limited expressiveness of prior programming…
In-Network Computing (INC) has found many applications for performance boosts or cost reduction. However, given heterogeneous devices, diverse applications, and multi-path network typologies, it is cumbersome and error-prone for application…
Arbitrary text appearance poses a great challenge in scene text recognition tasks. Existing works mostly handle with the problem in consideration of the shape distortion, including perspective distortions, line curvature or other style…
Large-scale neuromorphic architectures consist of computing tiles that communicate spikes using a shared interconnect. The communication patterns in such systems are inherently sparse, asynchronous, and localized due to the spiking nature…