I need to shift vector register in 64-bit double floats. The value in the register is showed as follows:
V: | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 |
I want to perform an element-by-element logical left or right shift of float64 vector V. For example, after shifting by the number of 2 float64, we can get the result as follows:
V: | 0 | 0 | 5 | 4 | 3 | 2 | 1 | 0 |
But I cann't find a instruction like that. Are there some instructions satisfy me?
(By the way, I saw instructions can performs an element-by-element logical shift of int32 vector v2. For example:_mm512_sllv_epi32 )