Intel® C++ Compiler 16.0 User and Reference Guide
Gathers 2/4 quadword values from memory referenced by the given base address, dword indices and scale. The corresponding Intel® AVX2 instruction is VPGATHERDQ.
extern __m128i _mm_i32gather_epi64(__int64 const * base, __m128i vindex, const int scale); |
extern __m256i _mm256_i32gather_epi64(__int64 const * base, __m128i vindex, const int scale); |
base |
the base address used to reference the loaded qword elements. |
vindex |
the vector of dword indices used to reference the loaded qword elements. |
scale |
64-bit scale used to address the loaded qword elements; it is multiplied by the corresponding element from 'vindex'. |
The intrinsics load 2/4 quadword values from memory using the base address, dword indices, and 64-bit scale.
Below is the pseudo-code for the intrinsics:
_mm_i32gather_epi64():
result[63:0] = mem[base+vindex[31:0]*scale]; result[127:64] = mem[base+vindex[63:32]*scale];
_mm256_i32gather_epi64():
result[63:0] = mem[base+vindex[31:0]*scale]; result[127:64] = mem[base+vindex[63:32]*scale]; result[191:128] = mem[base+vindex[95:64]*scale]; result[255:192] = mem[base+vindex[127:96]*scale];
A 128/256-bit vector with unconditionally gathered integer64 values.