Design of 2.5D Interposer in High Bandwidth Memory and Through Silicon Via for High Speed Signal

<p>The 2.5D interposer becomes a crucial solution to realize grand bandwidth of HBM for the increasing data requirement of high performance computing (HPC) and Artificial Intelligence (AI) applications. To overcome high speed switching bottleneck caused by the large resistive and capacitive characteristics of interposer, design methods to achieve an optimized performance in a limited routing area are proposed. Unlike the conventional single through silicon via (TSV), considering the reliability, multiple TSV are used as the robust 3D interconnects for each signal path. An equivalent model to accurately describe the electrical characteristics of the multiple TSVs, and a configuration pattern strategy of TSV to mitigate crosstalk are also proposed.</p>

High-Bandwidth Tactical-Network Data Analysis in a High-Performance-Computing (HPC) Environment: Transport Protocol (Transmission Control Protocol/User Datagram Protocol [TCP/UDP]) Analysis

10.21236/ada621268 ◽

2015 ◽

Author(s):

Kenneth D. Renard ◽

James R. Adametz

Keyword(s):

Data Analysis ◽

High Performance ◽

Transmission Control Protocol ◽

Network Data ◽

Transport Protocol ◽

Transmission Control ◽

Control Protocol ◽

High Bandwidth ◽

High-Bandwidth Tactical-Network Data Analysis in a High-Performance-Computing (HPC) Environment: Device Status Data

10.21236/ada626790 ◽

2015 ◽

Author(s):

Brian Panneton ◽

Brendan Tauras ◽

Christopher Wancowicz ◽

Sean Coyne

Keyword(s):

Data Analysis ◽

High Performance ◽

Network Data ◽

High Bandwidth ◽

Status Data ◽

High-Performance Computing Based on High-Speed Dynamic Reconfiguration

High-Performance Computing Using FPGAs ◽

10.1007/978-1-4614-1791-0_20 ◽

2013 ◽

pp. 605-627 ◽

Cited By ~ 2

Author(s):

Minoru Watanabe

Keyword(s):

High Speed ◽

High Performance ◽

Dynamic Reconfiguration ◽

Proceedings of the Ninth International Conference on Civil and Structural Engineering Computing ◽

High Performance Computing for High Speed Railways

10.4203/ccp.77.94 ◽

2009 ◽

Author(s):

L. Argandoña ◽

E. Arias ◽

J. Benet ◽

F. Cuartero ◽

T. Rojo

Keyword(s):

High Speed ◽

High Performance ◽

4H-SIC Dmosfets for High Frequency Power Switching Applications

MRS Proceedings ◽

10.1557/proc-764-c2.7 ◽

2003 ◽

Vol 764 ◽

Cited By ~ 6

Author(s):

Sei-Hyung Ryu ◽

Anant K. Agarwal ◽

James Richmond ◽

John W. Palmour

Keyword(s):

High Voltage ◽

High Speed ◽

High Performance ◽

High Frequency Power ◽

Power Devices ◽

Power Switching ◽

High Speed Switching ◽

Unipolar Devices ◽

Very High ◽

Frequency Power

AbstractVery high critical field, reasonable bulk electron mobility, and high thermal conductivity make 4H-Silicon carbide very attractive for high voltage power devices. These advantages make high performance unipolar switching devices with blocking voltages greater than 1 kV possible in 4H-SiC. Several exploratory devices, such as vertical MOSFETs and JFETs, have been reported in SiC. However, most of the previous works were focused on high voltage aspects of the devices, and the high speed switching aspects of the SiC unipolar devices were largely neglected. In this paper, we report on the static and dynamic characteristics of our 4H-SiC DMOSFETs. A simple model of the on-state characteristics of 4H-SiC DMOSFETs is also presented.

A Framework for HI Spectral Source Finding Using Distributed-Memory Supercomputing

Publications of the Astronomical Society of Australia ◽

10.1017/pasa.2014.18 ◽

2014 ◽

Vol 31 ◽

Cited By ~ 2

Author(s):

Stefan Westerlund ◽

Christopher Harris

Keyword(s):

High Performance ◽

Distributed Memory ◽

Computing Systems ◽

Sky Surveys ◽

Local Statistics ◽

Wide Range ◽

Gaussian Source ◽

High Bandwidth ◽

Traditional Approaches ◽

AbstractThe latest generation of radio astronomy interferometers will conduct all sky surveys with data products consisting of petabytes of spectral line data. Traditional approaches to identifying and parameterising the astrophysical sources within this data will not scale to datasets of this magnitude, since the performance of workstations will not keep up with the real-time generation of data. For this reason, it is necessary to employ high performance computing systems consisting of a large number of processors connected by a high-bandwidth network. In order to make use of such supercomputers substantial modifications must be made to serial source finding code. To ease the transition, this work presents the Scalable Source Finder Framework, a framework providing storage access, networking communication and data composition functionality, which can support a wide range of source finding algorithms provided they can be applied to subsets of the entire image. Additionally, the Parallel Gaussian Source Finder was implemented using SSoFF, utilising Gaussian filters, thresholding, and local statistics. PGSF was able to search on a 256GB simulated dataset in under 24 minutes, significantly less than the 8 to 12 hour observation that would generate such a dataset.