__lsx_vshuf4i_d
LSX intrinsic · group: Shuffling
Synopsis
__m128i __lsx_vshuf4i_d (__m128i a, __m128i b, imm0_255 imm)
#include <lsxintrin.h>
Instruction: vshuf4i.d vr, vr, imm
CPU Flags: LSX
Description
For each 128-bit lane, select two 64-bit elements from the four elements formed by the corresponding lanes of a and b using imm[1:0] and imm[3:2], save the result to dst.
Examples
__m128i __lsx_vshuf4i_d(__m128i{0x1122334455667788, 0x99aabbccddeeff00}, __m128i{0xabcdef1314156678, 0x1234123443214321}, 0x12)
= 0xabcdef1314156678 0x1122334455667788
Operation
dst.dword[0] = (imm & 2) ? b.dword[(imm & 1)] : a.dword[(imm & 1)];
dst.dword[1] =
(imm & 8) ? b.dword[((imm >> 2) & 1)] : a.dword[((imm >> 2) & 1)];
Tested on real machine.
Latency and Throughput
| CPU | µarch | Latency | Throughput (IPC) |
|---|---|---|---|
| 3C5000 | LA464 | 1 | 2 |
| 3A6000 | LA664 | 1 | 4 |
| 3C6000 | LA664 | 1 | 4 |
| 2K1000LA | LA264 | 1 | 1 |
| 2K3000 | LA364E | 1 | 1 |