+---------------+ +-----------------+
| d i g i t a l | | uNOTE # 039 |
+---------------+ +-----------------+
+----------------------------------------------------+-----------------+
| Title: Differences between KDJ11-A and KDJ11-B | Date: 8-Aug-85 |
+----------------------------------------------------+-----------------+
| Originator: Peter Kent | Page 1 of 5 |
+----------------------------------------------------+-----------------+
Purpose
The purpose of this MicroNote is to identify and discuss the differences
between the KDJ11-A and KDJ11-B CPU modules.
[ Stuff Deleted ]
For a full discussion of cache memory as used on the KJD11-A and KDJ11-B refer to MicroNote #9 and the KDJ11-A and KDJ11-B User's Guides. Both CPU modules have a similar cache organization using a nine bit tag. This nine bit field contains information that is compared to the address label, which is part of the physical address. When the physical address is generated, the address label is compared to the tag field. If there is a match it can be considered a hit provided that there is entry validation and no parity errors. The KDJ11-B has an additional tag store called the DMA tag. The DMA tag is an identical copy of the cache tag store and is used to monitor the main memory DMA updates while the cache tag store monitors the DCJ11 requirements. The presence of the second tag store - DMA tag - allows the J-11 microprocessor to continue processing after it has relinquished the system bus to a DMA device. When the DMA tag detects a hit (main memory location written to by the DMA device), the microprocessor stops and relinquishes the internal bus to the cache controller to allow it to monitor further DMA activity on the bus. The KDJ11-A, however, has only one tag store and stops processing as soon as it relinquishes the system bus to a DMA device.
The PDP-11 processors have also found themselves in other roles:
...and elsewhere.