Adapting optimal code generation for arithmetic expressions to the instruction sets available on present-day computers
暂无分享,去创建一个
bo t tom before moving on to the next. The shaded areas in the figure show d rum latency. The record label indicates the period during which a record is being accessed. Figure 3(b) shows an SLTF schedule for the same collection. It is not difficult to show that this is the unique SLTF schedule for this example since no two records share a starting point. In general, however, when two or more distinct SErF schedules exist, they may not all be o f the same length. No te that the SeTF schedule in Figure 3(b) has less latency time than the schedule in Figure 3(a).
[1] Samuel H. Fuller,et al. An Optimal Drum Scheduling Algorithm , 1972, IEEE Transactions on Computers.
[2] Peter J. Denning,et al. Effects of scheduling on file memory operations , 1899, AFIPS '67 (Spring).