Dismiss
InnovationQ will be updated on Sunday, Oct. 22, from 10am ET - noon. You may experience brief service interruptions during that time.
Browse Prior Art Database

Direct Data Coupling

IP.com Disclosure Number: IPCOM000086244D
Original Publication Date: 1976-Aug-01
Included in the Prior Art Database: 2005-Mar-03
Document File: 3 page(s) / 52K

Publishing Venue

IBM

Related People

Cardenia, PA: AUTHOR [+4]

Abstract

This is a technique for transferring bulk data from a storage device such as a disk to a Digital Control Unit (DCU) under control of a Central Processing Unit (CPU). The technique allows data transfer at higher than channel speeds and simplifies data transfer scheduling.

This text was extracted from a PDF file.
At least one non-text object (such as an image or picture) has been suppressed.
This is the abbreviated version, containing approximately 53% of the total text.

Page 1 of 3

Direct Data Coupling

This is a technique for transferring bulk data from a storage device such as a disk to a Digital Control Unit (DCU) under control of a Central Processing Unit (CPU). The technique allows data transfer at higher than channel speeds and simplifies data transfer scheduling.

The scheme capitalizes on the fact that data read from the storage device is placed on the CPU storage data bus (X-Bus) while its corresponding memory address is placed on the storage address bus (SA-Bus). These two busses are extended to the DCU so the data is available at the same time it is placed in the CPU's memory. hardware in the DCU recognizes appropriate addresses and also stores the data in the DCU buffer, thus eliminating a second transfer from the CPU memory to DCU.

The conventional data flow is illustrated in Fig. 1. One or more disk storage units 1 are read by a software program in a computer 3, such as an IBM S/370 Model 155 via one or more channels 2. The data is placed in temporary buffers 4 within the CPU 3. The data is transferred from the temporary buffers 4 to the DCU 7 via channel interface 5 and then to the large capacity buffer 6 in the DCU 7, also under software control. The software schedules disk reads, buffer usage, and writes to the DCU 7 to order data and achieve optimal transfer to the DCU.

The new data flow is shown in Fig. 2. When a software program in the CPU 3 causes data to be transferred into temporary buffers 4 from disks or other storage devices 1, it flows via channel 2 and X bus 8. The associated storage address in the temporary buffer 4 appears on the SA bus 10. The data and address busses 8 and 10 are extended to the DCU 7 where c...