__lasx_xvrepl128vei_d
LASX intrinsic · group: Misc
Synopsis
__m256i __lasx_xvrepl128vei_d (__m256i a, imm0_1 idx)
#include <lasxintrin.h>
Instruction: xvrepl128vei.d xr, xr, imm
CPU Flags: LASX
Description
For each 128-bit lane, repeat that lane's element idx to fill the same lane.
Operation
for (int i = 0; i < 2; i++) {
dst.dword[i] = a.dword[idx];
}
for (int i = 2; i < 4; i++) {
dst.dword[i] = a.dword[idx + 2];
}
Tested on real machine.
Latency and Throughput
| CPU | µarch | Latency | Throughput (IPC) |
|---|---|---|---|
| 3C5000 | LA464 | 1 | 2 |
| 3A6000 | LA664 | 1 | 4 |
| 3C6000 | LA664 | 1 | 4 |