Intel® C++ Compiler 16.0 User and Reference Guide

_mm_i32gather_epi32, _mm256_i32gather_epi32

Gathers 2/4 doubleword values from memory referenced by the given base address, dword indices, and scale. The corresponding Intel® AVX2 instruction is VPGATHERDD.

Syntax

extern __m128i _mm_i32gather_epi32(int const * base, __m128i vindex, const int scale);

extern __m256i _mm256_i32gather_epi32(int const * base, __m256i vindex, const int scale);

Arguments

base

the base address used to reference the loaded dword elements.

vindex

the vector of dword indices used to reference the loaded dword elements.

scale

32-bit scale used to address the loaded dword elements; it is multiplied by the corresponding element from 'vindex'.

Description

The intrinsics load 2/4 doubleword values from memory using the base address, qword indices, and 32-bit scale.

Below is the pseudo-code for the intrinsics:

_mm_i32gather_epi32():

result[31:0] = mem[base+vindex[31:0]*scale];
result[63:32] = mem[base+vindex[63:32]*scale];
result[95:64] = mem[base+vindex[95:64]*scale];
result127:96] = mem[base+vindex[127:96]*scale];

_mm256_i32gather_epi32():

result[31:0] = mem[base+vindex[31:0]*scale];
result[63:32] = mem[base+vindex[63:32]*scale];
result[95:64] = mem[base+vindex[95:64]*scale];
result127:96] = mem[base+vindex[127:96]*scale];
result[159:128] = mem[base+vindex[159:128]*scale];
result[191:160] = mem[base+vindex[191:160]*scale];
result[223:192] = mem[base+vindex[223:192]*scale];
result[255:224] = mem[base+vindex[255:224]*scale];

Returns

A 128/256-bit vector with unconditionally gathered integer32 values.