Tags / Equivalents

_mm_rsqrt_ps() on Intel 64-bit - SSE4.2

Purpose: Compute the approximate reciprocal square root of packed single-precision (32-bit) floating-point elements in a, and store the results in output. The maximum relative error for this approximation is less than 1.5*2^-12.

Result value:

Endian considerations: None.

 

 Intel 64-bit
 
Some data for your search? Something else? whatever.