Comparison of the two descriptions (original) (raw)

10.18.8.3 Drawbacks of the old pipeline description

The old instruction level parallelism description and the pipeline hazards recognizer based on it have the following drawbacks in comparison with the DFA-based ones:

• Each functional unit is believed to be reserved at the instruction execution start. This is a very inaccurate model for modern processors.
• An inadequate description of instruction latency times. The latency time is bound with a functional unit reserved by an instruction not with the instruction itself. In other words, the description is oriented to describe at most one unit reservation by each instruction. It also does not permit to describe special bypasses between instruction pairs.
• The implementation of the pipeline hazard recognizer interface has constraints on number of functional units. This is a number of bits in integer on the host machine.
• The interface to the pipeline hazard recognizer is more complex than one to the automaton based pipeline recognizer.
• An unnatural description when you write a unit and a condition which selects instructions using the unit. Writing all unit reservations for an instruction (an instruction class) is more natural.
• The recognition of the interlock delays has a slow implementation. The GCC scheduler supports structures which describe the unit reservations. The more functional units a processor has, the slower its pipeline hazard recognizer will be. Such an implementation would become even slower when we allowed to reserve functional units not only at the instruction execution start. In an automaton based pipeline hazard recognizer, speed is not dependent on processor complexity.