Block-Based High Performance CNN Architectures for Frame-Level Overlapping Speech Detection

2021 ◽  
Vol 29 ◽  
pp. 28-40
Author(s):  
Midia Yousefi ◽  
John H. L. Hansen
Keyword(s):  
High Performance ◽  
Speech Detection ◽  
Block Based

High Performance Spatial and Temporal Error-Concealment Algorithms for Block-Based Video Coding Techniques

ETRI Journal ◽  
2005 ◽  
Vol 27 (1) ◽  
pp. 53-63 ◽  
Author(s):  
Ching-Ting Hsu ◽  
Mei-Juan Chen ◽  
Wen-Wei Liao ◽  
Shen-Yi Lo
Keyword(s):  
Video Coding ◽  
High Performance ◽  
Error Concealment ◽  
Block Based ◽  
Temporal Error Concealment

High Performance Hierarchical Block-based Motion Estimation for Real-Time Video Coding

1998 ◽  
Vol 4 (1) ◽  
pp. 67-79 ◽  
Author(s):  
Marco Accame ◽  
Francesco G.B. De Natale ◽  
Daniele D. Giusto
Keyword(s):  
Motion Estimation ◽  
Video Coding ◽  
Real Time ◽  
High Performance ◽  
Block Based

scholarly journals Block-Based Compressed Sensing for Neutron Radiation Image Using WDFB

2015 ◽  
Vol 2015 ◽  
pp. 1-5 ◽  
Author(s):  
Wei Jin ◽  
Zhen Liu ◽  
Gang Li
Keyword(s):  
Compressed Sensing ◽  
High Performance ◽  
Filter Banks ◽  
Neutron Radiation ◽  
Sampling Theorem ◽  
Original Image ◽  
Compression Scheme ◽  
Directional Filter ◽  
Directional Filter Banks ◽  
Block Based

An ideal compression method for neutron radiation image should have high compression ratio while keeping more details of the original image. Compressed sensing (CS), which can break through the restrictions of sampling theorem, is likely to offer an efficient compression scheme for the neutron radiation image. Combining wavelet transform with directional filter banks, a novel nonredundant multiscale geometry analysis transform named Wavelet Directional Filter Banks (WDFB) is constructed and applied to represent neutron radiation image sparsely. Then, the block-based CS technique is introduced and a high performance CS scheme for neutron radiation image is proposed. By performing two-step iterative shrinkage algorithm the problem of L1 norm minimization is solved to reconstruct neutron radiation image from random measurements. The experiment results demonstrate that the scheme not only improves the quality of reconstructed image obviously but also retains more details of original image.

scholarly journals Computing the sparse matrix vector product using block-based kernels without zero padding on processors with AVX-512 instructions

2018 ◽  
Vol 4 ◽  
pp. e151 ◽  
Author(s):  
Bérenger Bramas ◽  
Pavel Kus
Keyword(s):  
Open Source ◽  
High Performance ◽  
Sparse Matrix ◽  
Assembly Language ◽  
Memory Storage ◽  
Vector Product ◽  
Zero Padding ◽  
The Matrix ◽  
Block Based ◽  
Matrix Vector

The sparse matrix-vector product (SpMV) is a fundamental operation in many scientific applications from various fields. The High Performance Computing (HPC) community has therefore continuously invested a lot of effort to provide an efficient SpMV kernel on modern CPU architectures. Although it has been shown that block-based kernels help to achieve high performance, they are difficult to use in practice because of the zero padding they require. In the current paper, we propose new kernels using the AVX-512 instruction set, which makes it possible to use a blocking scheme without any zero padding in the matrix memory storage. We describe mask-based sparse matrix formats and their corresponding SpMV kernels highly optimized in assembly language. Considering that the optimal blocking size depends on the matrix, we also provide a method to predict the best kernel to be used utilizing a simple interpolation of results from previous executions. We compare the performance of our approach to that of the Intel MKL CSR kernel and the CSR5 open-source package on a set of standard benchmark matrices. We show that we can achieve significant improvements in many cases, both for sequential and for parallel executions. Finally, we provide the corresponding code in an open source library, called SPC5.

scholarly journals InK: In-Kernel Key-Value Storage with Persistent Memory

Electronics ◽  
2020 ◽  
Vol 9 (11) ◽  
pp. 1913
Author(s):  
Minjong Ha ◽  
Sang-Hoon Kim
Keyword(s):  
High Performance ◽  
File Systems ◽  
Cloud Service ◽  
Main Memory ◽  
Storage Device ◽  
Storage Devices ◽  
Persistent Memory ◽  
Non Volatile Memory ◽  
Long Time ◽  
Block Based

Block-based storage devices exhibit different characteristics from main memory, and applications and systems have been optimized for a long time considering the characteristics in mind. However, emerging non-volatile memory technologies are about to change the situation. Persistent Memory (PM) provides a huge, persistent, and byte-addressable address space to the system, thereby enabling new opportunities for systems software. However, existing applications are usually apt to indirectly utilize PM as a storage device on top of file systems. This makes applications and file systems perform unnecessary operations and amplify I/O traffic, thereby under-utilizing the high performance of PM. In this paper, we make the case for an in-Kernel key-value storage service optimized for PM, called InK. While providing the persistence of data at a high performance, InK considers the characteristics of PM to guarantee the crash consistency. To this end, InK indexes key-value pairs with B+ tree, which is more efficient on PM. We implemented InK based on the Linux kernel and evaluated its performance with Yahoo Cloud Service Benchmark (YCSB) and RocksDB. Evaluation results confirms that InK has advantages over LSM-tree-based key-value store systems in terms of throughput and tail latency.

Sign in / Sign up

Export Citation Format

Share Document