Floating Point Math Execution Time

前端 未结 2 966
礼貌的吻别
礼貌的吻别 2020-12-19 18:18

What accounts for the added execution time of the first data set? The assembly instructions are the same.

With DN_FLUSH flag not on, the first data set takes 63 m

2条回答
  •  伪装坚强ぢ
    2020-12-19 18:38

    Another quote from the Intel manuals, volume 1, chapter 10.2.3.3:

    The flush-to-zero mode is not compatible with IEEE Standard 754. The IEEE mandated masked response to underflow is to deliver the denormalized result (see Section 4.8.3.2, “Normalized and Denormalized Finite Numbers”). The flush-to-zero mode is provided primarily for performance reasons. At the cost of a slight precision loss, faster execution can be achieved for applications where underflows are common and rounding the underflow result to zero can be tolerated.

提交回复
热议问题