Filters








32,682 Hits in 10.5 sec

Programmable Architectures and Design Methods for Two-Variable Numeric Function Generators

Shinobu Nagayama, Tsutomu Sasao, Jon T. Butler
2010 IPSJ Transactions on System LSI Design Methodology  
This method can reduce the memory size needed for symmetric functions by nearly half with small speed penalty. The proposed architectures allow a systematic design of various two-variable functions.  ...  FPGA implementation results show that, for a complicated function, our NFG achieves 57% of memory size and 60% of delay time of a circuit designed based on a one-variable NFG. 118  ...  Interestingly, for this function, the memory size of the NFGs using uniform segmentation increases in the same way as the memory size of a single look-up table.  ... 
doi:10.2197/ipsjtsldm.3.118 fatcat:3duwd7ywojfmhgf73zxbbrwnya

Hierarchical Segmentation for Hardware Function Evaluation

Dong-U Lee, R.C.C. Cheung, W. Luk, J.D. Villasenor
2009 IEEE Transactions on Very Large Scale Integration (vlsi) Systems  
This paper presents a method for evaluating functions based on piecewise polynomial approximations (splines) with a hierarchical segmentation scheme targeting hardware implementation.  ...  The hierarchical segmentation method is illustrated using a set of functions including ( 2) log 2 cos 1 ( ) ln( ), a high-degree rational function, ln(1 + ), and 1 (1 + ).  ...  BACKGROUND Function evaluation methods can be classified into iterative methods and non-iterative methods.  ... 
doi:10.1109/tvlsi.2008.2003165 fatcat:xudnulkasrfadcbanmc4w2qcii

Persistent Memory Hash Indexes: An Experimental Evaluation

Daokun Hu, Zhiwen Chen, Jianbing Wu, Jianhua Sun, Hao Chen
2021 Proceedings of the VLDB Endowment  
To this end, this paper provides a comprehensive evaluation of persistent hash tables.  ...  Our evaluation was conducted using a unified benchmarking framework and representative workloads.  ...  ACKNOWLEDGMENTS This research was supported by the National Key Research and Development Program of China (No. 2018YFB1003502), and by the National Science Foundation of China under Grants 61772183 and  ... 
dblp:journals/pvldb/HuCW0021 fatcat:xifixwwcirc6vpnpr2aak4od2a

Multi-Scale Squeeze U-SegNet with Multi Global Attention for Brain MRI Segmentation

Chaitra Dayananda, Jae-Young Choi, Bumshik Lee
2021 Sensors  
In this paper, we propose a multi-scale feature extraction with novel attention-based convolutional learning using the U-SegNet architecture to achieve segmentation of brain tissue from a magnetic resonance  ...  The proposed method was evaluated on publicly accessible datasets for brain tissue segmentation.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s21103363 pmid:34066042 fatcat:qlmzlwho3zfjnc4y24fnjxgrlu

A case study of a system level approach to exploration of queuing management schemes for input queue packet switches

Chen He, M. Lajolo, M. Jacome
2003 Eleventh Euromicro Conference on Parallel, Distributed and Network-Based Processing, 2003. Proceedings.  
As shown in the experimental results, the method enables us to evaluate the impact of different data management algorithms and different system parameters such as DMA size and packet payload size, in terms  ...  The effectiveness of this novel method is demonstrated by a case study of exploring data queuing management schemes for packet switches with input queues.  ...  In this way, the amount of details that are simulated at the architectural level is reduced, while a high degree of accuracy is still maintained by appropriately selecting a useful set of functional information  ... 
doi:10.1109/empdp.2003.1183617 dblp:conf/pdp/HeLJ03 fatcat:pkcdyeemjrac3awp6bsgnunqyq

Image Complexity Guided Network Compression for Biomedical Image Segmentation [article]

Suraj Mishra, Danny Z. Chen, X. Sharon Hu
2021 arXiv   pre-print
Our proposed framework is shown to be effective for generating compressed segmentation networks, retaining up to ≈ 95% of the full-sized network segmentation accuracy, and at the same time, utilizing ≈  ...  Such mapping enables us to predict the final accuracy for different network sizes, based on the computed dataset complexity.  ...  The training uses the Adam [11] optimizer ( 1 = 0.9, 2 = 0.999, = 1e−10) with a fixed learning rate of 0.00002 using a cross-entropy based loss function.  ... 
arXiv:2107.02927v1 fatcat:zpail5d7gfh73liwf6qtlcfley

Optimal Piecewise Linear Function Approximation for GPU-Based Applications

Daniel Berjon, Guillermo Gallego, Carlos Cuevas, Francisco Moran, Narciso Garcia
2016 IEEE Transactions on Cybernetics  
Following this idea, we propose a novel, efficient, and practical technique to evaluate complex and continuous functions using a nearly optimal design of two types of piecewise linear approximations in  ...  the case of a large budget of evaluation subintervals.  ...  However, their ease of use comes at the price of non-customizable reduced numerical precision [23] . A.  ... 
doi:10.1109/tcyb.2015.2482365 pmid:26462251 fatcat:xzcembv2cncofcnz2x7alr73pm

A Squeeze U-SegNet Architecture Based on Residual Convolution for Brain MRI Segmentation

Chaitra Dayananda, Jae Young Choi, Bumshik Lee
2022 IEEE Access  
In addition, the method provides a design with more efficient architecture, fewer network parameters, and better segmentation accuracy for brain MRI.  ...  The experimental results showed superior performance compared to other stateof-the-art methods on brain MRI segmentation with a dice similarity coefficient (DSC) score of 0.96 and Jaccard index (JI) of  ...  Quantitative metrics were used to evaluate the efficacy of a proposed architectural design.  ... 
doi:10.1109/access.2022.3175188 fatcat:2f4jhdtjfrh6vhotp42atomxum

3D Perception with Slanted Stixels on GPU

Daniel Hernandezjuarez, Antonio Espinosa, David Vazquez, Antonio Manuel Lopez, Juan Carlos Moure
2021 IEEE Transactions on Parallel and Distributed Systems  
This work presents a GPU-accelerated software design of the recently proposed model of Slanted Stixels, which represents the geometric and semantic information of a scene in a compact and accurate way.  ...  Our approach achieves real-time performance with high accuracy for 2048 × 1024 image sizes and 4 × 4 Stixel resolution on the low-power embedded GPU of an NVIDIA Tegra Xavier.  ...  Moure has focused on the GPU acceleration of Stixels, thus, they acknowledge the support of the project TIN2017-84553-C2-1-R of the Ministerio de Economía, Industria y Competitividad.  ... 
doi:10.1109/tpds.2021.3067836 fatcat:c2mbt44rvvg4vnmhixzr6xunoi

Automatic segmentation of brain MRI using a novel patch-wise U-net deep architecture

Bumshik Lee, Nagaraj Yamanakkanavar, Jae Young Choi, Kumaradevan Punithakumar
2020 PLoS ONE  
In the proposed brain segmentation method, the non-overlapping patch-wise U-net is used to overcome the drawbacks of conventional U-net with more retention of local information.  ...  In our proposed method, the slices from an MRI scan are divided into non-overlapping patches that are fed into the U-net model along with their corresponding patches of ground truth so as to train the  ...  From here, the expansive path starts with up-sampling of the feature maps followed by a 2×2 convolution ("up-convolution") that reduces the number of feature channels to half.  ... 
doi:10.1371/journal.pone.0236493 pmid:32745102 pmcid:PMC7398543 fatcat:vgrohlkkqvgd7pngnnljmbxwfq

Consistent RDMA-Friendly Hashing on Remote Persistent Memory [article]

Xinxin Liu, Yu Hua, Rong Bai
2021 arXiv   pre-print
Coalescing RDMA and Persistent Memory (PM) delivers high end-to-end performance for networked storage systems, which requires rethinking the design of efficient hash structures.  ...  Evaluation results demonstrate that compared with state-of-the-art schemes, continuity hashing achieves high throughput (i.e., 1.45X -- 2.43X improvement), low latency (about 1.7X speedup) and the smallest  ...  Specifically, the numbered buckets are addressable by a hash function, and two numbered buckets with adjacent bucket numbers (but non-contiguous memory addresses) share a fine-grained contiguous memory  ... 
arXiv:2107.06836v1 fatcat:lpvj3qsat5cjpbh7nk6h27yuvu

Efficient virtual memory for big memory servers

Arkaprava Basu, Jayneel Gandhi, Jichuan Chang, Mark D. Hill, Michael M. Swift
2013 SIGARCH Computer Architecture News  
To remove the TLB miss overhead for big-memory workloads, we propose mapping part of a process's linear virtual address space with a direct segment, while page mapping the rest of the virtual address space  ...  Direct segments use minimal hardware-base, limit and offset registers per core-to map contiguous virtual memory regions directly to contiguous physical memory.  ...  The views expressed herein are not necessarily those of any sponsor. Hill has a significant financial interest in AMD, and Swift has a significant financial interest in Microsoft.  ... 
doi:10.1145/2508148.2485943 fatcat:vix4kkpe5veefmas7inuv72uay

Efficient virtual memory for big memory servers

Arkaprava Basu, Jayneel Gandhi, Jichuan Chang, Mark D. Hill, Michael M. Swift
2013 Proceedings of the 40th Annual International Symposium on Computer Architecture - ISCA '13  
To remove the TLB miss overhead for big-memory workloads, we propose mapping part of a process's linear virtual address space with a direct segment, while page mapping the rest of the virtual address space  ...  Direct segments use minimal hardware-base, limit and offset registers per core-to map contiguous virtual memory regions directly to contiguous physical memory.  ...  The views expressed herein are not necessarily those of any sponsor. Hill has a significant financial interest in AMD, and Swift has a significant financial interest in Microsoft.  ... 
doi:10.1145/2485922.2485943 dblp:conf/isca/BasuGCHS13 fatcat:2p7dghs7g5axrn7dh2tttcufoe

NuI-Go: Recursive Non-Local Encoder-Decoder Network for Retinal Image Non-Uniform Illumination Removal [article]

Chongyi Li, Huazhu Fu, Runmin Cong, Zechao Li, Qianqian Xu
2020 arXiv   pre-print
We further demonstrate the advantages of the proposed method for improving the accuracy of retinal vessel segmentation.  ...  analysis.To address this issue, we propose a non-uniform illumination removal network for retinal image, called NuI-Go, which consists of three Recursive Non-local Encoder-Decoder Residual Blocks (NEDRBs  ...  In [34] , a non-uniform illuminated fundus image enhancement method was proposed, which reduces the blurriness of fundus images based on the cataract physical model and enhances the images with an objective  ... 
arXiv:2008.02984v1 fatcat:yf77vmdebzhtzdwlnnz6lcvws4

Prioritized Experience Replay [article]

Tom Schaul, John Quan, Ioannis Antonoglou, David Silver
2016 arXiv   pre-print
DQN with prioritized experience replay achieves a new state-of-the-art, outperforming DQN with uniform replay on 41 out of 49 games.  ...  In prior work, experience transitions were uniformly sampled from a replay memory.  ...  Furthermore, Hinton (2007) introduced a form of non-uniform sampling based on error, with an importance sampling correction, which led to a 3x speed-up on MNIST digit classification.  ... 
arXiv:1511.05952v4 fatcat:mcttbjzpsvhhrkcupyt2cksqai
« Previous Showing results 1 — 15 out of 32,682 results