International Business Machines Corporation

John A deVeer

Daniel Francis Casper

Martin W Sachs

John H Sorg, Jr

Robert P Barner

Jan G Oblonsky

Edward Loizides

Anne M Gulick

A method and system for pipelining the processing of channel command words is provided. The channel is permitted to send commands and data to the control unit for several channel command words associated with a channel program without having to wait for responses from the control unit for prior commands sent. The channel can pipeline several commands to the control unit and the control unit can then process the commands in the order it receives them. The control unit sends responses to the channel for each command it receives acknowledging receipt of the commands.

Method and system for pipelining the processing of channel command words

Multiple stations exchange information without central supervision. Stations requiring a cycle of access time on a shared time-divided bus participate in a cyclic access resolution process. The station having highest priority for a next bus cycle indicates its precedence to the other stations, and assumes exclusive use of the bus in the next cycle. The bus may comprise separate sections for data and response communications. Separate access resolution processes are conducted relative to each section. After gaining access to the bus for one cycle of data transfer a station becomes ineligible to compete for access to the data section until it receives an associated response. Accordingly receiving stations may control both the rate of data transmittal and the rate of access competition activity at associated origin stations. The data and response communications may include address information for enabling stations to intercommunicate directly in pairs. Data processing stations subject to multi-level interruption may present control signals designating acceptable interruption priority levels. Other stations seeking to interrupt such processing stations are eligible to compete for access to the bus only if assigned interruption priorities are at designated levels.

Distributed priority resolution system

A data transmission system which includes stations connected in a closed loop configuration with interface capabilities at each station to connect to an external data processor. Through this configuration simultaneous transmission of data among processors connected to stations on the loop can be carried out by transmission of data around the loop between particular stations. Data is transmitted from a first processor to its individual station connected to the loop. This first station formats the data received from the first processor into frames of multi-bit configuration which are transmitted around the loop to a second station which is connected to a second processor. Data received by the second station is stored and transmitted to the second processor. During the time that this transmission from the first processor to the second processor is being carried out a transmission between other processors connected to stations on the loop can also be carried out. Each station on the loop receives all frames being serially transmitted around the loop and after examination of the address section of the frame will keep frames designated for that particular station and will pass on those frames addressed to other stations on the loop. Each of the stations connected in the loop is an identical unit including a clock generator and synchronizer with no master station being designated for control functions, therefore, no control lines other than a clock timing line are included in the loop. A bypass function selects an alternate path around a station on the loop to permit faulty stations to temporarily be disconnected from the loop bus. Each station has a purging capability which permits frames which have parity errors or illegitimate addresses to be removed from the loop.

Loop configured data transmission system

Growing community of inventors

Millbrook, NY, United States of America

John A deVeer