Dependable dnn accelerator for safety-critical systems: A review on the aging perspective
In the modern era, artificial intelligence (AI) and deep learning (DL) seamlessly integrate into
various spheres of our daily lives. These cutting-edge disciplines have given rise to …
various spheres of our daily lives. These cutting-edge disciplines have given rise to …
Tbdb: Token bucket-based dynamic batching for resource scheduling supporting neural network inference in intelligent consumer electronics
Consumer electronics such as mobile phones, wearable devices, and vehicle electronics
use many intelligent applications such as voice commands, machine translation, and face …
use many intelligent applications such as voice commands, machine translation, and face …
Fusionai: Decentralized training and deploying llms with massive consumer-level gpus
The rapid growth of memory and computation requirements of large language models
(LLMs) has outpaced the development of hardware, hindering people who lack large-scale …
(LLMs) has outpaced the development of hardware, hindering people who lack large-scale …
iGniter: Interference-Aware GPU Resource Provisioning for Predictable DNN Inference in the Cloud
GPUs are essential to accelerating the latency-sensitive deep neural network (DNN)
inference workloads in cloud datacenters. To fully utilize GPU resources, spatial sharing of …
inference workloads in cloud datacenters. To fully utilize GPU resources, spatial sharing of …
Coordinated planning of multiple energy hubs considering the spatiotemporal load regulation of data centers
S Zhang, J Lyu, W Jin, H Cheng, C Li… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
With the digitalization of energy systems, data centers are gradually becoming an integral
part of energy hubs (EHs). Considering the spatiotemporal load regulation of data centers …
part of energy hubs (EHs). Considering the spatiotemporal load regulation of data centers …
DVFO: Learning-Based DVFS for Energy-Efficient Edge-Cloud Collaborative Inference
Due to limited resources on edge and different characteristics of deep neural network (DNN)
models, it is a big challenge to optimize DNN inference performance in terms of energy …
models, it is a big challenge to optimize DNN inference performance in terms of energy …
Sigmoid Activation Implementation for Neural Networks Hardware Accelerators Based on Reconfigurable Computing Environments for Low-Power Intelligent Systems
V Shatravin, D Shashev, S Shidlovskiy - Applied Sciences, 2022 - mdpi.com
The remarkable results of applying machine learning algorithms to complex tasks are well
known. They open wide opportunities in natural language processing, image recognition …
known. They open wide opportunities in natural language processing, image recognition …
Polca: Power oversubscription in llm cloud providers
Recent innovation in large language models (LLMs), and their myriad use-cases have
rapidly driven up the compute capacity demand for datacenter GPUs. Several cloud …
rapidly driven up the compute capacity demand for datacenter GPUs. Several cloud …
Characterizing Power Management Opportunities for LLMs in the Cloud
Recent innovation in large language models (LLMs), and their myriad use cases have
rapidly driven up the compute demand for datacenter GPUs. Several cloud providers and …
rapidly driven up the compute demand for datacenter GPUs. Several cloud providers and …
An automated and portable method for selecting an optimal GPU frequency
Power consumption poses a significant challenge in current and emerging graphics
processing unit (GPU) enabled high-performance computing systems. In modern GPUs …
processing unit (GPU) enabled high-performance computing systems. In modern GPUs …