Given by Geoffrey C. Fox at General NPAC Foilsets on 1995-1996. Foils prepared Feb 22 1996
Abstract * Foil Index for this file
This resource contains a variety of Screendumps through March 1996
|
This table of Contents Abstract
Geoffrey Fox |
Syracuse University |
NPAC |
111 College Place |
Syracuse NY 13244-4100 |
A NYNEX Joint Venture |
This shows fiber draping Africa with coast off ramps |
A NYNEX Joint Venture |
This picture illustrates Business Opportunities enabled by FLAG |
A NYNEX Joint Venture |
This shows FLAG linking Africa and Far East to Europe (and then to USA) |
INitial Architecture combines Satellites and Ocean fiber |
Geoffrey Fox explaining InfoVision to Mrs Clinton |
There is a larger Better Quality Image available |
Dr. Smith of SUNY Health Science Center demonstrates Telemedicine over ATM in area of pediatric cardiology |
There is a larger Better Quality Image available |
A Simulation on Demand InfoVision application using CM5 for simulation and AVS for coarse grain software decomposition support |
There is a larger Better Quality Image available |
Produced by Gang Cheng April 1995 |
There is a larger Better Quality Image available |
Produced by Gang Cheng April 1995 |
There is a larger Better Quality Image available |
Produced by Gang Cheng April 1995 |
There is a larger Better Quality Image available |
Produced by Gang Cheng April 1995 |
There is a larger Better Quality Image available |
Produced by Gang Cheng April 1995 |
There is a larger Better Quality Image available |
Produced by Gang Cheng April 1995 |
There is a larger Better Quality Image available |
Produced by Gang Cheng April 1995 |
There is a larger Better Quality Image available |
Produced by Gang Cheng April 1995 |
There is a larger Better Quality Image available |
Produced by Gang Cheng April 1995 |
There is a larger Better Quality Image available |
Produced by Gang Cheng April 1995 |
There is a larger Better Quality Image available |
Produced by Gang Cheng April 1995 |
There is a larger Better Quality Image available |
Produced by Gang Cheng April 1995 |
There is a larger Better Quality Image available |
Produced by Gang Cheng April 1995 |
There is a larger Better Quality Image available |
Produced by Gang Cheng April 1995 |
There is a larger Better Quality Image available |
Produced by Gang Cheng April 1995 |
There is a larger Better Quality Image available |
Produced by Gang Cheng April 1995 |
Produced by Gang Cheng April 1995 |
Produced by Gang Cheng April 1995 |
Produced by Gang Cheng April 1995 |
There is a larger Better Quality Image available |
Produced by Gang Cheng April 1995 |
There is a larger Better Quality Image available |
Produced by Gang Cheng April 1995 |
There is a larger Better Quality Image available |
Produced by Gang Cheng April 1995 |
There is a larger Better Quality Image available |
150:1, 100:1, 50:1, 1:1 |
Which is the most beautiful of them all? |
Figure 1 of CPS616 TCE Threads Discussion |
There is a larger Better Quality Image available |
Figure 2 of CPS616 TCE Threads Discussion |
There is a larger Better Quality Image available |
Figure 3 of CPS616 TCE Threads Discussion |
There is a larger Better Quality Image available |
Figure 4 of CPS616 TCE Threads Discussion |
There is a larger Better Quality Image available |
Figure 5 of CPS616 TCE Threads Discussion |
There is a larger Better Quality Image available |
Figure 6 of CPS616 TCE Threads Discussion |
There is a larger Better Quality Image available |
Refined from last bullet of previous foil July 28,95 |
There are two main distinctions between the HotJava browser and other browsers such as Mosaic or Netscape. In the HotJava case a bulk of execution takes place at the client side as the transmitted code is linked with the HotJava runtime and started as Java threads. Standard browsers on the other hand are only involved in presenting the received information, and all other computation is to be performed by servers. Secondly, the Java ability to transmit executable code allows a HotJava browser to acquire any information from a server, not being aware of the information type or structure. The necessary tools for presenting this information will be transferred from a server and installed, and executed by the HotJava client. |
See Two Postscript Foils |
First Foil--TLNS3D is a Production Level Code for the solving 3D Inviscid + Viscous Flows
|
Second Foil -- work done on HPF for TLNS3D
|
see NASA's 4 dimensional Data Assimilation Grand Challenge for more details of Makivic analysis of HPF for this application |
Major goal of the Four-Dimensional Data Assimilation project is to ensure smooth transition of NASA Data Assimilation Office operations to future scalable HPC platforms. |
This involves:
|
At NPAC, these tasks were associated with the following components of the complete assimilation system:
|
Major conclusion: HPF is one of the most relevant technologies for future computing needs at DAO |
DAO is developing a new assimilation system, Physical Space Analysis System (PSAS). NPAC will collaborate with DAO on developing HPF implementation of the production PSAS software. |
see NASA's 4 dimensional Data Assimilation Grand Challenge for more details of Makivic analysis of HPF for this application |
Tasks in the operational Data Assimilation system which can be efficiently accomplished using HPF:
|
These tasks are generic enough to be used in both Mini-Volume OI and PSAS |
There are three distributed templates which correspond to:
|
Data parallel operations which involve a single template usually require structured communication (scans, reductions) or no communication at all |
Data parallel operations which involve mappings between templates require general purpose communications and command highest overhead |
Dynamic memory allocation, reductions, scans and FORALL construct essential |
Independent calculations on mini-volume matrices can be handled via $HPF DO INDEPENDENT or as task parallel computations using $HPF EXTRINSIC facility (this approach can accomodate sophisticated load-balancing schemes) |
Performance: quality control routine for sea-level analysis runs at 0.5 GFLOPS sustained and 3.2 GFLOPS peak for unoptimized CM Fortan code and a small test data set (which cannot use effectively 1024 vector units on a 256 node CM-5). Much better performance can be achieved on production data sets. |
see NASA's 4 dimensional Data Assimilation Grand Challenge for more details of Makivic analysis of HPF for this application |
Van Leer and Prather methods are monotonic finite difference schemes for fluid advection which have good behaviour regarding diffusive and phase errors |
Very suitable for HPF implementation:
|
Load imbalance due to polar subcycling eliminated via gather/scatter procedure, which takes just a few code lines using array subsection notation (would have been tedious work in message passing!):
|
Communication costs due to gather/scatter are smaller than load imbalance costs |
Big advantage of HPF implementation: very easy to experiment with different decomposition strategies |
For example, depending on hardware parameters and/or model grid resolution either two-dimensional or one-dimensional decomposition may be optimal. |
Simple <em>preprocessor directives</em> are sufficient to implement either decomposition using HPF: <em>bulk</em> of the code would have to be changed to go from one decomposition to another using message passing. |
Performance: 2.5 GFLOPS sustained and 6.8 GFLOPS peak on a 256 node CM-5 for a 144 X 88 latitude/longitude grid. Much better performance can be achieved on finer grids. |
see NASA's 4 dimensional Data Assimilation Grand Challenge for more details of Makivic analysis of HPF for this application |
Forecast model and observational data are combined to produce a minimum error representation of the state of the atmosphere |
The goal of the analysis is to find a set of weights for each observation which will determine the contribution of that observation to the correction of model estimate at every grid point |
The formal solution can be expressed as a linear problem defined by the correlation matrix of observational error data |
Given that presently there are 150000 observations per assimilation cycle, one must resort to approximations |
Mini-Volume approximation technique scans for observations in a 1500 km radius arond a cluster of gridpoints. Effectively, a large linear problem is approximated by a large number of small linear problems for each mini-volume |
Before the covariance matrices are constructed observations are processed to eliminate and/or correct erroneous data (gross check and buddy check) |
Solution of mini-volume linear systems is a task parallel computation |
Everything else involves manipulations of large observational data, model data and mini-volume data arrays and can be efficiently expressed using HPF syntax |
One of set of screendumps for HPFA Package |
There is a PostScript version |
This is taken from Actual Web Page |
One of set of screendumps for HPFA Package |
There is a PostScript version |
This is taken from Actual Web Page |
One of set of screendumps for HPFA Package |
There is a PostScript version |
This is taken from Actual Web Page |
One of set of screendumps for HPFA Package |
There is a PostScript version |
This is taken from Actual Web Page |
One of set of screendumps for HPFA Package |
There is a PostScript version |
This is taken from Actual Web Page |
One of set of screendumps for HPFA Package |
There is a PostScript version |
This is taken from Actual Web Page |
One of set of screendumps for HPFA Package |
There is a PostScript version |
This is taken from Actual Web Page |
One of set of screendumps for HPFA Package |
There is a PostScript version |
This is taken from Actual Web Page |
One of set of screendumps for HPFA Package |
There is a PostScript version |
This is taken from Actual Web Page |
One of set of screendumps for HPFA Package |
There is a PostScript version |
One of set of screendumps for HPFA Package |
There is a PostScript version |
One of set of screendumps for HPFA Package |
There is a PostScript version |
One of set of screendumps for HPFA Package |
There is a PostScript version |
One of set of screendumps for HPFA Package |
There is a PostScript version |
Searched on Inventions |
Also shown are the 3 Upstate Living Schoolbook Schools connected via NPAC |
Living SchoolBook Material for SC95 San Diego Dec 95 |
Living SchoolBook Material for SC95 San Diego Dec 95 |
Living SchoolBook Material for SC95 San Diego Dec 95 |
Living SchoolBook Material for SC95 San Diego Dec 95 |
Living SchoolBook Material for SC95 San Diego Dec 95 |
Living SchoolBook Material for SC95 San Diego Dec 95 |
Living SchoolBook Material for SC95 San Diego Dec 95 |
Living SchoolBook Material for SC95 San Diego Dec 95 |
Living SchoolBook Material for SC95 San Diego Dec 95 |
Living SchoolBook Material for SC95 San Diego Dec 95 |
Living SchoolBook Material for SC95 San Diego Dec 95 |
Living SchoolBook Material for SC95 San Diego Dec 95 |
Living SchoolBook Material for SC95 San Diego Dec 95 |
Living SchoolBook Material for SC95 San Diego Dec 95 |
Living SchoolBook Material for SC95 San Diego Dec 95 |
Living SchoolBook Material for SC95 San Diego Dec 95 |
Living SchoolBook Material for SC95 San Diego Dec 95 |
Living SchoolBook Material for SC95 San Diego Dec 95 |
From Rome Laboratory/AFMC Technology Integration Server Presentation |
Basic talk can be found here |
and here is Poscript Version of picture |
From Rome Laboratory/AFMC Technology Integration Server Presentation |
Basic talk can be found here |
and here is Poscript Version of picture |
From Rome Laboratory/AFMC Technology Integration Server Presentation |
Basic talk can be found here |
and here is Poscript Version of picture |
From Rome Laboratory/AFMC Technology Integration Server Presentation |
Basic talk can be found here |
and here is Poscript Version of picture |
From Rome Laboratory/AFMC Technology Integration Server Presentation |
Basic talk can be found here |
and here is Poscript Version of picture |
From Rome Laboratory/AFMC Technology Integration Server Presentation |
Basic talk can be found here |
and here is Poscript Version of picture |
From Rome Laboratory/AFMC Technology Integration Server Presentation |
Basic talk can be found here |
and here is Poscript Version of picture |
From Rome Laboratory/AFMC Technology Integration Server Presentation |
Basic talk can be found here |
and here is Poscript Version of picture |
From Rome Laboratory/AFMC Technology Integration Server Presentation |
Basic talk can be found here |
and here is Poscript Version of picture |
From Rome Laboratory/AFMC Technology Integration Server Presentation |
Basic talk can be found here |
and here is Poscript Version of picture |
From Rome Laboratory/AFMC Technology Integration Server Presentation |
Basic talk can be found here |
and here is Poscript Version of picture |
From Rome Laboratory/AFMC Technology Integration Server Presentation |
Basic talk can be found here |
and here is Poscript Version of picture |
From Rome Laboratory/AFMC Technology Integration Server Presentation |
Basic talk can be found here |
and here is Poscript Version of picture |
From Rome Laboratory/AFMC Technology Integration Server Presentation |
Basic talk can be found here |
and here is Poscript Version of picture |
From Rome Laboratory/AFMC Technology Integration Server Presentation |
Basic talk can be found here |
and here is Poscript Version of picture |
From Kemal Ispirli with 36 threads running client-side |
Colors represent node status and links message-passing |
From Meryem Ispirli |
Prototype of Algorithmic Visualization System |
From Meryem Ispirli |
Prototype of Algorithmic Visualization System |
From Meryem Ispirli |
From Meryem Ispirli |
From Kivanc Dincer |
From Kivanc Dincer |
From Chris Walczak |
From Chris Walczak |
From Chris Walczak |
From Chris Walczak |
From Chris Walczak |
InterNet versus IntraNet Web Business |
From Information Week Jan 29, 96 issue |
From Information Week Jan 29, 96 issue |
From Kemal Ispirli |
see Java Applet |
Small JPEG version |
Large JPEG version |