_mm256_cvtph_ps()

Converts eight half-precision (16-bit) floating point values to single-precision floating point values.

Syntax

extern __m256 _mm_cvtph_ps(__m128i x, int imm);

Arguments

X

a vector containing eight 16-bit FP values

Imm

A conversion control constant

Description

This intrinsic converts eight half-precision (16-bit) floating point values to single-precision floating point values. The corresponding Intel® Post 32nm processor extension instruction is VCVTPH2PS.

Returns

A vector containing eight single-precision floating point elements.

Parent topic: Intrinsics for Converting Half Floats that Map to Intel(R) Post-32nm Processor Instructions

Submit feedback on this help topic

Copyright © 1996-2011, Intel Corporation. All rights reserved.