| |
| | POWER3: The next generation of PowerPC processors |
 | | The single-cycle units execute all single-cycle instructions (arithmetic, shift, logical, compare, trap, and count leading zero) with a single-cycle latency (this means that instructions dependent upon the result can execute in the next cycle). |
 | | The independence of the fixed-point execution units and the load/store execution units is obviously a large performance benefit for calculations that are predominately integer in nature, such as Monte Carlo simulations. |
 | | In the case of data forwarding between execution units, or when, on the same execution unit, the first instruction is feeding the FRA operand of the dependent instruction, the latency is four cycles. |
| www.research.ibm.com /journal/rd/446/oconnell.html (7426 words) |
|