COMPUTER ARCHITECTURE and NETWORK ANALYSIS
- Complex Software System Hybrid Simulation Model
The system studied is an inventory and assignment system being designed for execution within the IMS/MVS environment. It is presently projected that the system will use an IBM 3090/200S, or equivalent, to support a customer of approximately 7 million customer accounts.
- Multiprocessor System Model - MPX
The MPX model allows users to modify various parameters including: general architecture, processor type, clock speeds, cache hierarchy, hit rates, bus width, transfer protocols, memory speeds, and organization.
- Reed-Soloman Card Modeling
The simulation was required to understand the bottlenecks, hardware/software relationships and data flows in various pipelines of the R- S PC board. SIMSCRIPT II.5 was used along with SIMGRAPHICS to visually analyze the performance of the R-S PC board.
- Computer and Channel Malfunctions in Distributed Database Systems
The models were designed to be as general as possible. The number of computers, and number of channels can be varied. In addition, the degree of local usage of data, the distribution of transactions between query, add, modify, and delete types, the processing speed of computers, and the channel speed, are all capable of being individually set for each computer or channel.
- Extendable Computer System Simulator II - ECSS II
ECSS II is a specialized programming language for constructing simulation models of computer-based systems. Using ECSS II statements, you can compactly express functions inherent to computer systems.
- Multi-Host Distributed Data Processing Network
A multi-host distributed processing network is modeled to determine expected system response time for handling approximately 72 million daily user transactions. Once the response time is determined, the model is used to examine methods of improving the response time by optimizing hardware/software allocations.
- Network Simulation Using SIMSCRIPT II.5
Most communications networks of interest involve a complexity that extends beyond the restrictive assumptions required of analytical methods of study. These systems can be studied effectively by the use of Discrete Event computer simulation models.
- Environment Simulation for Testing Ada Embedded Software
Testing and debugging of embedded software in actual hardware is expensive and time consuming and careful testing prior to field trials is normally done to the extent feasible. But embedded software has traditionally been written in assembly languages targeted to specific hardware.
- Expected CCR Ethernet Performance
This modeling effort suggests that the local availability of basic validated simulation models of the components of distributed systems would allow the building of application specific simulation models, much more quickly than is the norm, by modifying and extending these basic models.
- Starlan Network Simulation
The Starlan simulation enables system designers to monitor network traffic based on a set of changeable network parameters. A file is transferred, in packets, from each node to a hard disk.
- Disk Subsystem Simulation
The Disk Subsystem Simulation model is a fairly detailed model of the hardware, software, and job-load environment of a multiprocessor mainframe system.
- Simulation of Medium Access Protocols in LANs
A very simple and flexible strategy called "Plug Process" provides contention resolution among requesting stations, mutual exclusion on the single server (the bus) and implementation of several transmission policies.
- Computer System Sizing Model
The System Sizing Model (SSM) is a capacity-planning tool used by over 30 worldwide marketing specialists. A menu sub-system allows the specialists to quickly change workload and machine configurations to answer the all-important "what if?" questions concerning future growth at customer sites.
- Neural Network Simulation of an "NFLOP"
NFLOP is a generalization of a flip-flop, having more than two elements. Each element of the NFLOP is represented by one neuron. By selecting the sub-field "NEURON", a detailed schematic of the simulated neuron may be viewed.
- Delta Network Simulation
Interconnection networks are used in multiprocessor systems. The principal characteristic of the multiprocessor system is the ability of each processor to share a single main memory.