Editing Datapoint 2200 (section)

===Performance===
Although the Datapoint 2200 version I is somewhat faster than an [[Intel 8008]] on register instructions, any reference to the 2200's shift-register memory incurs a large 520 μs delay. Also any JMP, CALL, or RETURN can incur a variable delay up to 520 μs depending on the distance to the new address. The parallel-architecture Datapoint 2200 version II is much faster than either.<ref name="2200ref"/><ref name="8008man">{{cite book |title=8008 8 Bit Parallel Central Processor Unit |date=November 1973 |publisher=Intel |pages=14, 17 |edition=Rev 4, Second Printing |url=http://www.bitsavers.org/components/intel/MCS8/Intel_8008_8-Bit_Parallel_Central_Processing_Unit_Rev4_Nov73.pdf |access-date=30 April 2024}}</ref>

{|class="wikitable" style="text-align:center"
|-
!colspan=5|Instruction|| Description || Datapoint 2200 ver I μs|| 500&nbsp;kHz Intel 8008 μs|| Datapoint 2200 ver II μs
|-
|colspan=5|ADB|| Add B to A || 16 || 20 || 3.2
|-
|colspan=5|ADI nn|| Add nn immediate to A || 16 || 32 || 4.8
|-
|colspan=5|ADM|| Add memory to A || 520 || 32 || 4.8
|-
|colspan=5|JMP nnnn|| Jump to nnnn || 24-520 || 44 || 6.4
|-
|colspan=5|CALL+RET|| Call and Ret combined|| 520 || 64 || 9.6
|-
|colspan=5|Rcc (false)|| Conditional return not taken || 16 || 12 || 3.2
|}