Výsledky vyhľadávania - Hardware Integrated circuits Reconfigurable logic and FPGAs

DSPlacer: DSP Placement for FPGA-based CNN Accelerator Autor Xie, Baohui, Zhu, Xinrui, Lu, Zhiyuan, Pu, Yuan, Wu, Tongkai, Zou, Xiaofeng, Yu, Bei, Chen, Tinghuan

“…Deploying convolutional neural networks (CNNs) on hardware platforms like Field Programmable Gate Arrays (FPGAs…”
Získať plný text

Caffeine: Towards uniformed representation and acceleration for deep convolutional neural networks Autor Chen Zhang, Zhenman Fang, Peipei Zhou, Peichen Pan, Jason Cong

“… In this paper we design and implement Caffeine, a hardware/software co-designed library to efficiently accelerate the entire CNN on FPGAs…”
Získať plný text

Gemmini: Enabling Systematic Deep-Learning Architecture Evaluation via Full-Stack Integration Autor Genc, Hasan, Kim, Seah, Amid, Alon, Haj-Ali, Ameer, Iyer, Vighnesh, Prakash, Pranav, Zhao, Jerry, Grubb, Daniel, Liew, Harrison, Mao, Howard, Ou, Albert, Schmidt, Colin, Steffl, Samuel, Wright, John, Stoica, Ion, Ragan-Kelley, Jonathan, Asanovic, Krste, Nikolic, Borivoje, Shao, Yakun Sophia

“…DNN accelerators are often developed and evaluated in isolation without considering the cross-stack, system-level effects in real-world environments. This…”
Získať plný text

SGX-FPGA: Trusted Execution Environment for CPU-FPGA Heterogeneous Architecture Autor Xia, Ke, Luo, Yukui, Xu, Xiaolin, Wei, Sheng

“… To fill the gap, we present SGX-FPGA, a trusted hardware isolation path enabling the first FPGA TEE by bridging SGX enclaves and FPGAs in the heterogeneous CPU-FPGA architecture…”
Získať plný text

FPGA-TrustZone: Security Extension of TrustZone to FPGA for SoC-FPGA Heterogeneous Architecture Autor Wang, Shupeng, Fan, Xindong, Xu, Xiao, Wang, Shuchen, Ju, Lei, Zhou, Zimeng

“… Experiments on real SoC-FPGA hardware development boards show that FPGA-TrustZone provides high security with low performance overhead…”
Získať plný text

BlockGNN: Towards Efficient GNN Acceleration Using Block-Circulant Weight Matrices Autor Zhou, Zhe, Shi, Bizhao, Zhang, Zhe, Guan, Yijin, Sun, Guangyu, Luo, Guojie

“… platforms.To tackle this challenge, we propose BlockGNN, a software-hardware co-design approach to realize efficient GNN acceleration…”
Získať plný text

High-Performance FPGA-based Accelerator for Bayesian Neural Networks Autor Fan, Hongxiang, Ferianc, Martin, Rodrigues, Miguel, Zhou, Hongyu, Niu, Xinyu, Luk, Wayne

“… This work proposes a novel FPGA based hardware architecture to accelerate BNNs inferred through Monte Carlo Dropout…”
Získať plný text

An Enhanced Data Packing Method for General Matrix Multiplication in Brakerski/Fan-Vercauteren Scheme Autor Meng, Xiangchen, Tan, Yan, Jiang, Zijun, Lyu, Yangdi

“… Furthermore, we design specialized hardware…”
Získať plný text

Configurable DSP-Based CAM Architecture for Data-Intensive Applications on FPGAs Autor Chen, Yao, Yu, Feng, Wu, Di, Wong, Weng-Fai, He, Bingsheng

“… They have been used in many domains, such as networking, databases, and graph processing. Field-programmable gate arrays (FPGAs…”
Získať plný text

XShift: FPGA-efficient Binarized LLM with Joint Quantization and Sparsification Autor Zhou, Shuai, Tian, Huinan, Meng, Sisi, Chen, Jianli, Yu, Jun, Wang, Kun

“… a specialized inference framework. In response, we introduce XShift, an algorithm-hardware co-design framework optimized for efficient binarized LLM inference on FPGAs…”
Získať plný text

WSQ-AdderNet: Efficient Weight Standardization based Quantized AdderNet FPGA Accelerator Design with High-Density INT8 DSP-LUT Co-Packing Optimization Autor Zhang, Yunxiang, Sun, Biao, Jiang, Weixiong, Ha, Yajun, Hu, Miao, Zhao, Wenfeng

“… Recent proposals on hardware-optimal neural network architectures suggest that AdderNet with a lightweight ℓ…”
Získať plný text

DuoQ: A DSP Utilization-aware and Outlier-free Quantization for FPGA-based LLMs Acceleration Autor Yu, Zhuoquan, Ji, Huidong, Cao, Yue, Wu, Junfu, Yan, Xiaoze, Zheng, Lirong, Zou, Zhuo

“… To address this problem, we introduce DuoQ, an FPGA-oriented algorithm-hardware co-design framework…”
Získať plný text

April: Accuracy-Improved Floating-Point Approximation For Neural Network Accelerators Autor Chen, Yonghao, Zou, Jiaxiang, Chen, Xinyu

“… Floatingpoint approximation, such as Mitchell's logarithm, enables floating-point multiplication using simpler integer additions, thereby improving hardware efficiency…”
Získať plný text

An Efficient Bit-level Sparse MAC-accelerated Architecture with SW/HW Co-design on FPGA Autor Zhang, Chenming, Gong, Lei, Wang, Chao, Zhou, Xuehai

“… The reconfigurable platform offers possibilities for identifying the bitlevel unstructured redundancy during inference with different DNN models…”
Získať plný text

FLAG: An FPGA-Based System for Low-Latency GNN Inference Service Using Vector Quantization Autor Han, Yunki, Kim, Taehwan, Kim, Jiwan, Ha, Seohye, Kim, Lee-Sup

“… In this paper, we propose FLAG, an FPGA-based GNN inference serving system using vector quantization…”
Získať plný text

An Algorithm-Hardware Co-design Based on Revised Microscaling Format Quantization for Accelerating Large Language Models Autor Hao, Yingbo, Chen, Huangxu, Zou, Yi, Yang, Yanfeng

“… However, deploying such a new format into existing hardware systems is still challenging, and the dominant solution for LLM inference at low precision is still low-bit quantization…”
Získať plný text

Classifying Computations on Multi-Tenant FPGAs Autor Gobulukoglu, Mustafa, Drewes, Colin, Hunter, William, Kastner, Ryan, Richmond, Dustin

“…Modern data centers leverage large FPGAs to provide low latency, high throughput, and low energy computation…”
Získať plný text

KLiNQ: Knowledge Distillation-Assisted Lightweight Neural Network for Qubit Readout on FPGA Autor Guo, Xiaorang, Bunarjyan, Tigran, Liu, Dai, Lienhard, Benjamin, Schulz, Martin

“… While current methods, including deep neural networks, enhance readout accuracy, they typically lack support for mid-circuit measurements essential for quantum error correction, and they usually rely…”
Získať plný text

CoSPARSE: A Software and Hardware Reconfigurable SpMV Framework for Graph Analytics Autor Feng, Siying, Sun, Jiawen, Pal, Subhankar, He, Xin, Kaszyk, Kuba, Park, Dong-hyeon, Morton, Magnus, Mudge, Trevor, Cole, Murray, O'Boyle, Michael, Chakrabarti, Chaitali, Dreslinski, Ronald

“… reconfiguration as a synergistic solution to accelerate SpMV-based graph analytics algorithms. Building on previously proposed general-purpose reconfigurable hardware…”
Získať plný text

ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization Autor Guo, Cong, Zhang, Chen, Leng, Jingwen, Liu, Zihan, Yang, Fan, Liu, Yunxin, Guo, Minyi, Zhu, Yuhao

“… Even though this line of work brings algorithmic benefits, it also introduces significant hardware overheads due to variable-length encoding…”
Získať plný text