Search Results - "Yan, Guihai"

SqueezeFlow: A Sparse CNN Accelerator Exploiting Concise Convolution Rules by Li, Jiajun, Jiang, Shuhao, Gong, Shijun, Wu, Jingya, Yan, Junchao, Yan, Guihai, Li, Xiaowei

“…Convolutional Neural Networks (CNNs) have been widely used in machine learning tasks. While delivering state-of-the-art accuracy, CNNs are known as both…”
Get full text

DPU-Direct: Unleashing Remote Accelerators via Enhanced RDMA for Disaggregated Datacenters by Liao, Yunkun, Wu, Jingya, Lu, Wenyan, Li, Xiaowei, Yan, Guihai

“…This paper presents DPU-Direct, an accelerator disaggregation system that connects accelerator nodes (ANs) and CPU nodes (CNs) over a standard Remote Direct…”
Get full text

FlexFlow: A Flexible Dataflow Accelerator Architecture for Convolutional Neural Networks by Wenyan Lu, Guihai Yan, Jiajun Li, Shijun Gong, Yinhe Han, Xiaowei Li

“…Convolutional Neural Networks (CNN) are very computation-intensive. Recently, a lot of CNN accelerators based on the CNN intrinsic parallelism are proposed…”
Get full text

Monocular 3D Multi-Person Pose Estimation for On-Site Joint Flexion Assessment: A Case of Extreme Knee Flexion Detection by Yan, Guihai, Yan, Haofeng, Yao, Zhidong, Lin, Zhongliang, Wang, Gang, Liu, Changyong, Yang, Xincong

“…Work-related musculoskeletal disorders (WMSDs) represent a significant health challenge for workers in construction environments, often arising from prolonged…”
Get full text

Joint Design of Training and Hardware Towards Efficient and Accuracy-Scalable Neural Network Inference by He, Xin, Lu, Wenyan, Yan, Guihai, Zhang, Xuan

“…The intrinsic error tolerance of neural network (NN) presents opportunities for approximate computing techniques to improve the energy efficiency of NN…”
Get full text

CoreRank: Redeeming "Sick Silicon" by Dynamically Quantifying Core-Level Healthy Condition by Yan, Guihai, Sun, Faqiang, Li, Huawei, Li, Xiaowei

“…In field degradation of manycore processors poses a grand challenge to core management, largely because the degradation is hard to quantify. We propose a novel…”
Get full text

DOE: database offloading engine for accelerating SQL processing by Kong, Hao, Lu, Wenyan, Chen, Yan, Wu, Jingya, Zhang, Yu, Yan, Guihai, Li, Xiaowei

“…The CPU-Accelerator heterogeneous systems have demonstrated performance and efficiency benefits on DBMSs. However, the CPU-Cache-DRAM architecture can not…”
Get full text

Promoting the Harmony between Sparsity and Regularity: A Relaxed Synchronous Architecture for Convolutional Neural Networks by Lu, Wenyan, Yan, Guihai, Li, Jiajun, Gong, Shijun, Jiang, Shuhao, Wu, Jingya, Li, Xiaowei

“…There are two approaches to improve the performance of Convolutional Neural Networks (CNNs): 1) accelerating computation and 2) reducing the amount of…”
Get full text

ShuttleNoC: Power-Adaptable Communication Infrastructure for Many-Core Processors by Lu, Hang, Chang, Yisong, Yan, Guihai, Lin, Ning, Wei, Xin, Li, Xiaowei

“…Networks-on-chip (NoCs), as the communication infrastructure in many-core processors, has demonstrated remarkable power consumption along with the technology…”
Get full text

SmartShuttle: Optimizing off-chip memory accesses for deep learning accelerators by Li, Jiajun, Yan, Guihai, Lu, Wenyan, Jiang, Shuhao, Gong, Shijun, Wu, Jingya, Li, Xiaowei

“…Convolutional Neural Network (CNN) accelerators are rapidly growing in popularity as a promising solution for deep learning based applications. Though…”
Get full text

An Analytical Framework for Estimating Scale-Out and Scale-Up Power Efficiency of Heterogeneous Manycores by Ma, Jun, Yan, Guihai, Han, Yinhe, Li, Xiaowei

“…Heterogeneous manycore architectures have shown to be highly promising to boost power efficiency through two independent ways: (1) enabling massive…”
Get full text

EcoUp: Towards Economical Datacenter Upgrading by Yan, Guihai, Ma, Jun, Han, Yinhe, Li, Xiaowei

“…The rapid growth of cloud services dictates increasingly powerful datacenters to maintain the high quality of service (QoS). It's a common practice in…”
Get full text

Automated Defect Detection on Dry-Hanging Stone Curtain Walls through Colored Point Clouds by Yao, Zhidong, Li, Xuelai, Yan, Guihai, Lin, Zhongliang, Wang, Gang, Liu, Changyong, Yang, Xincong

“…Stone curtain walls are widely used in contemporary architectures; however, their regular inspection is always labor-intensive, time-consuming, and hazardous…”
Get full text

Orchestrator: Guarding Against Voltage Emergencies in Multithreaded Applications by Hu, Xing, Yan, Guihai, Hu, Yu, Li, Xiaowei

“…Voltage emergency (VE) has become a critical challenge with decreasing feature size and increasing power capacity. Destructive core interference is one main…”
Get full text

ReviveNet: A Self-Adaptive Architecture for Improving Lifetime Reliability via Localized Timing Adaptation by Yan, Guihai, Han, yinhe, Li, Xiaowei

“…The aggressive technology scaling poses serious challenges to lifetime reliability. A parament challenge comes from a variety of aging mechanisms that can…”
Get full text

RISO: Enforce Noninterfered Performance With Relaxed Network-on-Chip Isolation in Many-Core Cloud Processors by Lu, Hang, Fu, Binzhang, Wang, Ying, Han, Yinhe, Yan, Guihai, Li, Xiaowei

“…Workload consolidation is widely used in modern cloud processors to reduce total cost of ownership. Performance isolation has to be enforced between…”
Get full text

CCR: A concise convolution rule for sparse neural network accelerators by Li, Jiajun, Yan, Guihai, Lu, Wenyan, Jiang, Shuhao, Gong, Shijun, Wu, Jingya, Li, Xiaowei

“…Convolutional Neural networks (CNNs) have achieved great success in a broad range of applications. As CNN-based methods are often both computation and memory…”
Get full text

SVFD: A Versatile Online Fault Detection Scheme via Checking of Stability Violation by Yan, Guihai, Han, Yinhe, Li, Xiaowei

“…In ultra-deep submicrometer technology, soft errors and device aging are two of the paramount reliability concerns. Although many studies have been done to…”
Get full text

Exploiting the Potential of Computation Reuse Through Approximate Computing by He, Xin, Jiang, Shuhao, Lu, Wenyan, Yan, Guihai, Han, Yinhe, Li, Xiaowei

“…Approximate computing, which tackles tradeoff between computation quality (e.g., accuracy) and computation efforts, is becoming a promising technique to…”
Get full text

PowerTrader: Enforcing Autonomous Power Management for Future Large-Scale Many-Core Processors by Lu, Hang, Yan, Guihai, Han, Yinhe, Li, Xiaowei

“…Existing power management approaches for modern many-core processors resort to "centralized" design concept, aiming to optimize chip performance under fixed…”
Get full text