Intel® C++ Compiler 16.0 User and Reference Guide
Typecasts double-precision floating point values to single-precision floating point values. No corresponding Intel® AVX instruction.
extern __m256 _mm256_castpd_ps(__m256d a); |
a |
float64 source vector |
Performs a typecast operation from double-precision floating point values (float64 values) to single-precision floating point values (float32 values). This intrinsic does not introduce extra moves to the generated code. Source operand bits are passed unchanged to the result.
A vector with single-precision floating point values.