Výsledky vyhľadávania - Computation/Dataflow Optimization

MnnFast: A Fast and Scalable System Architecture for Memory-Augmented Neural Networks Autor Jang, Hanhwi, Kim, Joonsung, Jo, Jae-Eon, Lee, Jaewon, Kim, Jangwoo

“…Memory-augmented neural networks are getting more attention from many researchers as they can make an inference with the previous history stored in memory…”
Získať plný text

NLP-Fast: A Fast, Scalable, and Flexible System to Accelerate Large-Scale Heterogeneous NLP Models Autor Kim, Joonsung, Hur, Suyeon, Lee, Eunbok, Lee, Seungho, Kim, Jangwoo

“…: three end-to-end optimization techniques to accelerate…”
Získať plný text

Reconfigurable Dataflow Optimization for Spatiotemporal Spiking Neural Computation on Systolic Array Accelerators Autor Lee, Jeong-Jun, Li, Peng

“… Recognizing the need for efficient processing of complex spatiotemporal data while considering the all-or-none nature of spiking activities, we propose holistic reconfigurable dataflow optimization…”
Získať plný text

VQ-LLM: High-performance Code Generation for Vector Quantization Augmented LLM Inference Autor Liu, Zihan, Luo, Xinhao, Guo, Junxian, Ni, Wentao, Zhou, Yangjie, Guan, Yue, Guo, Cong, Cui, Weihao, Feng, Yu, Guo, Minyi, Zhu, Yuhao, Zhang, Minjia, Jin, Chen, Leng, Jingwen

“… and uncoordinated computation dataflow. Meanwhile, the diversity of VQ algorithms (e.g., different vector sizes and entry counts…”
Získať plný text

Techniques for Efficient Performance Analysis and Memory Optimization in Mapping Dataflow Models of Computation Onto Embedded Systems Autor Luna, Mauro Martín Letras

“…The power of modern multi-core and many-core platforms is an excellent fit for meeting the performance needs of embedded software applications. However, there…”
Získať plný text

A high-performance dataflow-centric optimization framework for deep learning inference on the edge Autor Zhang, Runhua, Jiang, Hongxu, Geng, Jinkun, Tian, Fangzheng, Ma, Yuhang, Wang, Haojie

“… Targeting the existing drawbacks of operator-centric frameworks, we design Xenos, which can automatically conduct dataflow-centric optimization of the computation graph and accelerate inference in two dimensions…”
Získať plný text

SWG: an architecture for sparse weight gradient computation Autor Wu, Weiwei, Tu, Fengbin, Li, Xiangyu, Wei, Shaojun, Yin, Shouyi

“… Nevertheless, exploiting the optimization opportunities would meet three underutilization problems, which are caused by (1…”
Získať plný text

AttentionLib: A Scalable Optimization Framework for Automated Attention Acceleration on FPGA Autor Liu, Zhenyu, Zhou, Xilang, Sun, Faxian, Chen, Jianli, Yu, Jun, Wang, Kun

“… AttentionLib automatically performs fusion dataflow optimization for attention computations and generates high-level synthesis code in compliance…”
Získať plný text

Efficient N:M Sparse DNN Training Using Algorithm, Architecture, and Dataflow Co-Design Autor Fang, Chao, Sun, Wei, Zhou, Aojun, Wang, Zhongfeng

“…Sparse training is one of the promising techniques to reduce the computational cost of DNNs while retaining high accuracy. In particular, N:M fine-grained…”
Získať plný text

Unleashing Network/Accelerator Co-Exploration Potential on FPGAs: A Deeper Joint Search Autor Lou, Wenqi, Gong, Lei, Wang, Chao, Qian, Jiaming, Wang, Xuan, Li, Changlong, Zhou, Xuehai

“…Recently, algorithm-hardware (HW) co-exploration for neural networks (NNs) has become the key to obtaining high-quality solutions. However, previous efforts…”
Získať plný text

Algorithm/Hardware Co-optimization for Sparsity-Aware SpMM Acceleration of GNNs Autor Gao, Yingxue, Gong, Lei, Wang, Chao, Wang, Teng, Li, Xi, Zhou, Xuehai

“… So in this paper, we demonstrate an algorithm/hardware co-optimization chance to enhance SpMM acceleration for GNNs…”
Získať plný text

SCnC: Efficient Unification of Streaming with Dynamic Task Parallelism Autor Sbîrlea, Dragoş, Shirako, Jun, Newton, Ryan, Sarkar, Vivek

“… This work shows that it is possible to exploit streaming as a safe and automatic optimization of a more general dataflow-based model…”
Získať plný text

DiMO-Sparse: Differentiable Modeling and Optimization of Sparse CNN Dataflow and Hardware Architecture Autor Song, Jianfeng, Liang, Rongjian, Gong, Yu, Yuan, Bo, Hu, Jiang

“… To the best of our knowledge, this paper presents the first systematic investigation of automatic dataflow and hardware optimization for sparse CNN computation…”
Získať plný text

Mechanisms Towards Energy-Efficient Dynamic Hardware Specialization Autor Ho, Chen-Han

“…In the past few decades, Von Neumann superscalar processors have been the prevalent approach for general purpose processing. Hardware specialization, as a…”
Získať plný text

An FPGA-based efficient accelerator for fault interaction of rupture dynamics Autor Yuan, Ming, Liu, Qiang, Gan, Lin

“…Efficiently predicting aftershocks based on rupture dynamics simulation is a crucial task in high-performance computing, traditionally dependent on…”
Získať plný text

SpikeFlow: A hardware–software co-designed systolic array for spiking neural networks Autor Wang, Jianan, Shi, Yang, Chen, Zhaoyun, Wen, Mei

“…Spiking neural networks (SNNs), often referred to as third-generation neural networks, offer substantial advantages in efficiency and power consumption, which…”
Získať plný text

CHAUS： Scalable VM-Based Channels for Unbounded Streaming Autor Zhang, Yu, Yu, Yu-Fen, Cao, Hui-Fang, Chen, Jian-Kang, Zhang, Qi-Liang

“…Stream processing is a special form of the dataflow execution model that offers extensive opportunities for optimization and automatic parallelism…”
Získať plný text

SPADE: Sparse Pillar-based 3D Object Detection Accelerator for Autonomous Driving Autor Lee, Minjae, Park, Seongmin, Kim, Hyungmin, Yoon, Minyong, Lee, Janghwan, Choi, Jun Won, Kim, Nam Sung, Kang, Mingu, Choi, Jungwook

“…3D object detection using point cloud (PC) data is essential for perception pipelines of autonomous driving, where efficient encoding is key to meeting…”
Získať plný text

Dataflow computing models, languages, and machines for intelligence computations Autor Herath, J., Yamaguchi, Y., Saito, N., Yuba, T.

“…The authors compare dataflow computing models, languages, and dataflow computing machines for numerical and nonnumerical computations. The…”
Získať plný text

PolyJuice: Detecting Mis-compilation Bugs in Tensor Compilers with Equality Saturation Based Rewriting Autor Zhou, Chijin, Qian, Bingzhou, Go, Gwihwan, Zhang, Quan, Li, Shanshan, Jiang, Yu

“… The main challenge is to construct equivalent graphs capable of efficiently exploring the diverse optimization logic during compilation…”
Získať plný text