ND-110 CPU: Difference between revisions

From NDWiki
Jump to navigation Jump to search
(Initial page copied from wikipedia.)
 
m (Adding link + category)
Line 13: Line 13:
In addition to the macro-instruction cache memory also found in the ND-100, the ND-110 had a unique implementation of cache memory on the micro-instruction level. The step known as mapping in the ND-100 was then avoided because the first micro-instruction word of a macro-instruction was written into the control store cache.
In addition to the macro-instruction cache memory also found in the ND-100, the ND-110 had a unique implementation of cache memory on the micro-instruction level. The step known as mapping in the ND-100 was then avoided because the first micro-instruction word of a macro-instruction was written into the control store cache.


Unlike the ND-100 CPU, it handled synchronous interrupts as traps, similar to how it was handled by the ND-500.
Unlike the ND-100 CPU, it handled synchronous interrupts as traps, similar to how it was handled by the [[ND-500]].


The control store consisted of 4K x 4 bit 40ns SRAM chips. This meant that the control store was writable. It was loaded at power up and Master Clear from two 32Kx8 bit EPROMs.
The control store consisted of 4K x 4 bit 40ns SRAM chips. This meant that the control store was writable. It was loaded at power up and Master Clear from two 32Kx8 bit EPROMs.
Line 29: Line 29:
== Sources ==
== Sources ==
*{{OriginWP-EN|NORD-100|6th February 2009}}
*{{OriginWP-EN|NORD-100|6th February 2009}}
[[Category:ND-100 hardware]]

Revision as of 09:23, 13 February 2009

The ND-110 CPU is an incremental improvement of the ND-100 CPU.

The ND-110 combined the Memory Management System and CPU, previously separate cards, on one board. The single CPU/MMS board was plugged into the memory management board slot, usually numbered 3. The power consumption was reduced from 90 watts to 60.

The ND-110 made extensive use of PALs and gate arrays - with "semi-custom" VLSI chips.

The ND-110 had three gate arrays:

  • The Micro Instruction Controller, the MIC - also known as RMIC, for "Rask MIC" ("Speedy MIC"). It replaced three 74S482 sequencers and about 30 other ICs.
  • The Arithmetical and Logical Unit gate array (ALU, also known as the "BUFALU"). Replaced four Am2901 bit-slice processors, and some additional registers like the data bus register the general purpose register, and the internal register block.
  • The Micro Address Controller (The MAC, also called RMAC, for "Rask MAC" ("Speedy MAC"). It implemented hardware address arithmetic, which in the ND-100 had been done in microcode.

In addition to the macro-instruction cache memory also found in the ND-100, the ND-110 had a unique implementation of cache memory on the micro-instruction level. The step known as mapping in the ND-100 was then avoided because the first micro-instruction word of a macro-instruction was written into the control store cache.

Unlike the ND-100 CPU, it handled synchronous interrupts as traps, similar to how it was handled by the ND-500.

The control store consisted of 4K x 4 bit 40ns SRAM chips. This meant that the control store was writable. It was loaded at power up and Master Clear from two 32Kx8 bit EPROMs.

The CPU clock and the bus arbitration network were implemented using 15ns PALs.

The main oscillator was a 39.3216 MHz crystal oscillator.

ND-110/CX

This was the ND-110 with the CX microcode PROM option. The added instructions were the same as the ND-100/CE.

Sources

  • This article was originally a copy of the English Wikipedia article NORD-100 in 6th February 2009.