From: robin on
"Richard Maine" <nospam(a)see.signature> wrote in message news:1jmsnwd.1y8u6r31f3t1oeN%nospam(a)see.signature...

| An interesting thing about integer arithmetic operations was that...
| there were none - at least none with their own dedicated opcodes.

The CDC Cyber had separate op codes for the integer instructions.*
Integer 60-bit add/subtract being 36 and 37.

Op codes 70 to 77 were the integer add/subtract using
one of the 18-bit registers as well as a 60-bit integer register.

The floating-point add/subtract/multiply instructions used the op-codes
30 to 35 and mult-div used codes 40 to 45 omitting 43.

| You
| just used the same opcodes as for floating point, and the hardware
| special-cased operands with the 12 high order bits all 0 or all 1.

That was only for integer multiply, introduced on the Cyber 70 series.

| It
| seemed like the machine was designed to crunch floating point numbers,
| with integers being a special case.

_______________
* The only exception being integer multiply, which used the same
op code as float multiply, as I said a few days ago.