Intel® C++ Compiler 16.0 User and Reference Guide

_mm512_scale_round_ps/ _mm512_mask_scale_round_ps

Scales rounded float32 vectors. Corresponding instruction is VSCALEPS. This intrinsic only applies to Intel® Many Integrated Core Architecture (Intel® MIC Architecture).

Syntax

Without Mask

extern __m512 __cdecl _mm512_scale_round_ps(_m512 v2, _m512i v3, int rc);

With Mask

extern __m512 __cdecl _mm512_mask_scale_round_ps(_m512 v1_old, __mmask16 k1, _m512 v2, _m512i v3, int rc);

Parameters

v2

 float32 vector used for rounding

v3

 float32 vector providing exponent element to be multiplied to corresponding element in vector v2

v1_old

 Source vector that retains old values of the destination vector; the resulting vector gets corresponding elements from v1_old for zero mask bits

k1

 Writemask; only those elements of the source vectors with corresponding bit set to '1' in the k1 mask are computed and stored in the result; elements in the result vector corresponding to zero bit in k1 are copied from corresponding elements of vector v1_old

rc

Rounding control values; these can be one of the following:

  • _MM_FROUND_TO_NEAREST_INT - rounds to nearest even
  • _MM_FROUND_TO_NEG_INF - rounds to negative infinity
  • _MM_FROUND_TO_POS_INF - rounds to positive infinity
  • _MM_FROUND_TO_ZERO - rounds to zero
  • _MM_FROUND_CUR_DIRECTION - rounds using default from MXCSR register

Description

Performs an element-by-element scale of float32 vector v2 by multiplying it by 2**exponent, where exponent is the corresponding element of vector v3. Intermediate values are rounded according to rc value.

This intrinsic is required for scaling 'u' and 'v' coordinates according to the mipmap size, which is 2**mipmap level, and for the evaluation of Exp2. Where the exponent goes out of range, the operation is handled as if a multiplication of float32 vectors with 2**exp is performed.

The masked variant has one additional argument: k1. Only those elements in the source vectors with the corresponding bit set in vector mask k1 are used for computing.

Returns

Returns the result of the scaling operation.

Parent topic: Multiplication Operations