Browse Prior Art Database

Monolithic Memory AS I/O Buffer

IP.com Disclosure Number: IPCOM000091720D
Original Publication Date: 1968-Apr-01
Included in the Prior Art Database: 2005-Mar-05
Document File: 2 page(s) / 32K

Publishing Venue

IBM

Related People

Tsui, F: AUTHOR

Abstract

The high-speed monolithic buffer memory MBM is divided into at least one pair of dual areas A and B which are used for complementary functions. F is complementary to G. S is complementary to P. As the cycle time of MBM is shorter than half the cycle time of main storage MS, two MBM operations can be performed during one MS operation, G or S during the first read part and F or P during the second write part of the full MS read-write cycle. For each data transfer, storage data register SDR is used. When transferring a block of data from MS to an I/O unit, two F operations are performed initially to fill both areas A and B. Subsequently, the MBM starts to Give out data from area A to the I/O unit at the low speed of the latter.

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 100% of the total text.

Page 1 of 2

Monolithic Memory AS I/O Buffer

The high-speed monolithic buffer memory MBM is divided into at least one pair of dual areas A and B which are used for complementary functions. F is complementary to G. S is complementary to P. As the cycle time of MBM is shorter than half the cycle time of main storage MS, two MBM operations can be performed during one MS operation, G or S during the first read part and F or P during the second write part of the full MS read-write cycle. For each data transfer, storage data register SDR is used. When transferring a block of data from MS to an I/O unit, two F operations are performed initially to fill both areas A and B. Subsequently, the MBM starts to Give out data from area A to the I/O unit at the low speed of the latter. After A has been given out, the MBM starts to Give out B and a Fetch operation is initiated to fill A, and so on, until the whole block is transferred. A certain period of time is available for services to other I/O units and for CPU processing after A is filled. A block transfer from an I/O unit to MS is performed in a similar way.

1

Page 2 of 2

2

[This page contains 2 pictures or other non-text objects]