Related papers: Oobleck: Low-Compromise Design for Fault Tolerant …
With phenomenal growth of high speed and complex computing applications, the design of low power and high speed logic circuits have created tremendous interest. Conventional computing devices are based on irreversible logic and further…
A noise-tolerant data communications fabric has been developed to meet the real-time data acquisition and control requirements of fast feedback loops, machine protection systems, pulse-to-pulse sequencing, and machine-experiment…
Attention accounts for an increasingly dominant fraction of total computation during inference for mixture-of-experts (MoE) models, making efficient acceleration critical. Emerging domain-specific accelerators for large model inference are…
The idle computers on a local area, campus area, or even wide area network represent a significant computational resource---one that is, however, also unreliable, heterogeneous, and opportunistic. This type of resource has been used…
Transformers have become the backbone of neural network architecture for most machine learning applications. Their widespread use has resulted in multiple efforts on accelerating attention, the basic building block of transformers. This…
Vision Transformers (ViTs) have achieved state-of-the-art performance on various vision tasks. However, ViTs' self-attention module is still arguably a major bottleneck, limiting their achievable hardware efficiency. Meanwhile, existing…
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…
Compared to the first generation of deep neural networks, dominated by regular, compute-intensive kernels such as matrix multiplications (MatMuls) and convolutions, modern decoder-based transformers interleave attention, normalization, and…
In this paper, the program control unit of an embedded RISC processor is enhanced with a novel zero-overhead loop controller (ZOLC) supporting arbitrary loop structures with multiple-entry/exit nodes. The ZOLC has been incorporated to an…
Online Continual Learning (OCL) involves sequentially arriving data and is particularly challenged by catastrophic forgetting, which significantly impairs model performance. To address this issue, we introduce a novel framework, Online…
Sparsity, which occurs in both scientific applications and Deep Learning (DL) models, has been a key target of optimization within recent ASIC accelerators due to the potential memory and compute savings. These applications use data stored…
In dynamic systems that adapt to users' needs and changing environments, dependability needs cannot be avoided. This paper proposes an orthogonal fault tolerance model as a means to manage and reason about multiple fault tolerance…
Scaling up quantum computers to attain substantial speedups over classical computing requires fault tolerance. Conventionally, protocols for fault-tolerant quantum computation demand excessive space overheads by using many physical qubits…
The High Level Trigger (HLT) of the future ALICE heavy-ion experiment has to reduce its input data rate of up to 25 GB/s to at most 1.25 GB/s for output before the data is written to permanent storage. To cope with these data rates a large…
Accelerators provide large performance and energy-efficiency benefits, but can significantly change the hardware-software interface. The t\"{a}k\={o} programmable memory hierarchy accelerates data movement by enabling programmers to run…
Reliability has taken centre stage in the development of high-performance computing processors. A Surge of interest is noticeable in recent times in formulating fault and failure models, understanding failure mechanism and strategizing…
GPU-based fast Fourier transform (FFT) is extremely important for scientific computing and signal processing. However, we find the inefficiency of existing FFT libraries and the absence of fault tolerance against soft error. To address…
The rapidly-changing deep learning landscape presents a unique opportunity for building inference accelerators optimized for specific datacenter-scale workloads. We propose Full-stack Accelerator Search Technique (FAST), a hardware…
Thin-film technologies such as Indium Gallium Zinc Oxide (IGZO) enable Flexible Electronics (FE) for emerging applications in wearable sensing, personal health monitoring, and large-area systems. Analog-to-digital converters (ADCs) serve as…
Miniaturized satellites are currently not considered suitable for critical, high-priority, and complex multi-phased missions, due to their low reliability. As hardware-side fault tolerance (FT) solutions designed for larger spacecraft can…