__lasx_xvsrari_h
LASX intrinsic · group: Shift
Synopsis
__m256i __lasx_xvsrari_h (__m256i a, imm0_15 imm)
#include <lasxintrin.h>
Instruction: xvsrari.h xr, xr, imm
CPU Flags: LASX
Description
Arithmetic right shift (with rounding) the signed 16-bit elements in a by imm, store the result to dst.
Operation
for (int i = 0; i < 16; i++) {
if (imm == 0) {
dst.half[i] = a.half[i];
} else {
dst.half[i] =
((s16)a.half[i] >> imm) + (((s16)a.half[i] >> (imm - 1)) & 0x1);
}
}
Tested on real machine.
Latency and Throughput
| CPU | µarch | Latency | Throughput (IPC) |
|---|---|---|---|
| 3C5000 | LA464 | 3 | 2 |
| 3A6000 | LA664 | 3 | 2 |
| 3C6000 | LA664 | 3 | 2 |