Intel® C++ Compiler 16.0 User and Reference Guide
Performs an arithmetic right shift operation of the int32 vector. Corresponding instruction is VPSRAD. This intrinsic only applies to Intel® Many Integrated Core Architecture (Intel® MIC Architecture).
Without Mask extern __m512i __cdecl _mm512_srai_epi32(__m512i v2, unsigned int count); |
With Mask extern __m512i __cdecl _mm512_mask_srai_epi32(__m512i v1_old, __mmask16 k1, __m512i v2, unsigned int count); |
v2 |
int32 vector where the arithmetic right shift operation is performed |
count |
specifies the number of bits by which the arithmetic right shift must occur |
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 |
Performs an element-by-element arithmetic right shift of int32 vector v2, shifting by the number of bits given by immediate count. If the shift value specified by this parameter is greater than 31 then the result of the shift is all ones or all zeroes, depending on the original sign bit.
The masked variant has one additional argument: k1. Only those elements in the source registers with the corresponding bit set in vector mask k1 are used for computing.
Returns the result of the operation.