• ETRI Journal
• /
• v.42 no.3
• /
• pp.376-387
• /
• 2020

Massive computation of the reconstruction algorithm for compressive sensing (CS) has been a major concern for its real-time application. In this paper, we propose a novel high-speed architecture for the orthogonal matching pursuit (OMP) algorithm, which is the most frequently used to reconstruct compressively sensed signals. The proposed design offers a very high throughput and includes an innovative pipeline architecture and scheduling algorithm. Least-squares problem solving, which requires a huge amount of computations in the OMP, is implemented by using systolic arrays with four new processing elements. In addition, a distributed-arithmetic-based circuit for matrix multiplication is proposed to counterbalance the area overhead caused by the multi-stage pipelining. The results of logic synthesis show that the proposed design reconstructs signals nearly 19 times faster while occupying an only 1.06 times larger area than the existing designs for N = 256, M = 64, and m = 16, where N is the number of the original samples, M is the length of the measurement vector, and m is the sparsity level of the signal.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.39 no.9
• /
• pp.37-44
• /
• 2002

This paper proposes efficient digital hardware design method by using fixed weight of pre-trained neural network. For this, arithmetic operations of PEs(Processing Elements) are represented with matrix-vector multiplication. The relationship of fixed weight and input data present bit-level array structure architecture which is consisted operation node. To minimize the operation node, this paper proposes node elimination method and setting common node depend on bit pattern of weight. The result of FPGA simulation shows the efficiency on hardware cost and operation speed with full precision. And proposed design method makes possibility that many PEs are implemented to on-chip.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.40 no.9
• /
• pp.597-604
• /
• 2016

A parallel algorithm of bi-conjugate gradient method was developed based on CUDA for parallel computation of the incompressible Navier-Stokes equations. The governing equations were discretized using splitting P2P1 finite element method. Asymmetric stenotic flow problem was solved to validate the proposed algorithm, and then the parallel performance of the GPU was examined by measuring the elapsed times. Further, the GPU performance for sparse matrix-vector multiplication was also investigated with a matrix of fluid-structure interaction problem. A kernel was generated to simultaneously compute the inner product of each row of sparse matrix and a vector. In addition, the kernel was optimized to improve the performance by using both parallel reduction and memory coalescing. In the kernel construction, the effect of warp on the parallel performance of the present CUDA was also examined. The present GPU computation was more than 7 times faster than the single CPU by double precision.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.12
• /
• pp.4345-4363
• /
• 2021

Deep Learning as a Service (DLaaS), utilizing the cloud-based deep neural network models to provide customer prediction services, has been widely deployed on mobile cloud computing (MCC). Such services raise privacy concerns since customers need to send private data to untrusted service providers. In this paper, we devote ourselves to building an efficient protocol to classify users' images using the convolutional neural network (CNN) model trained and held by the server, while keeping both parties' data secure. Most previous solutions commonly employ homomorphic encryption schemes based on Ring Learning with Errors (RLWE) hardness or two-party secure computation protocols to achieve it. However, they have limitations on large communication overheads and costs in MCC. To address this issue, we present LeHE4SCNN, a scalable privacy-preserving and communication-efficient framework for CNN-based DLaaS. Firstly, we design a novel low-expansion rate homomorphic encryption scheme with packing and unpacking methods (LeHE). It supports fast homomorphic operations such as vector-matrix multiplication and addition. Then we propose a secure prediction framework for CNN. It employs the LeHE scheme to compute linear layers while exploiting the data shuffling technique to perform non-linear operations. Finally, we implement and evaluate LeHE4SCNN with various CNN models on a real-world dataset. Experimental results demonstrate the effectiveness and superiority of the LeHE4SCNN framework in terms of response time, usage cost, and communication overhead compared to the state-of-the-art methods in the mobile cloud computing environment.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.19 no.2
• /
• pp.121-129
• /
• 2008

In this paper, we present a fast analysis of multilayer microstrip fractal structure by using the fast multipole method (FMM). In the analysis, accurate spatial green's functions from the real-axis integration method(RAIM) are employed to solve the mixed potential integral equation(MPIE) with FMM algorithm. MoM's iteration and memory requirement is $O(N^2)$ in case of calculation using the green function. the problem is the unknown number N can be extremely large for calculation of large scale objects and high accuracy. To improve these problem is fast algorithm FMM. FMM use the addition theorem of green function. So, it reduce the complexity of a matrix-vector multiplication and reduce the cost of calculation to the order of $O(N^{1.5})$, The efficiency is proved from comparing calculation results of the moment method and Fast algorithm.