它可以有效地利用数据的并行,并将其作为一个整体数组在不同处理器上使用不同的索引来同时执行指令。
It makes effective use of data parallelism and can act on entire arrays at once by executing instructions on different indexes of an array in different processors.
现在,如果在 INGREDIENT 上有合适的索引,同样的搜索只需 6 个 CPU 指令,会在几分之一秒内完成。
Now, if a useful index on INGREDIENT is available, the same search could be completed using only six CPU instructions and would be finished in a fraction of a second.
在多分支结构的识别过程中,通过对索引表和跳转表调用指令的格式分析,提出了双特征指令匹配算法。
By analyzing the formats of calling instructions to the indexed table and the jump table, proposed a novel recognition algorithm based on character instruction matching.
应用推荐