__lasx_xvsrln_b_h
LASX intrinsic · group: Shift
Synopsis
__m256i __lasx_xvsrln_b_h (__m256i a, __m256i b)
#include <lasxintrin.h>
Instruction: xvsrln.b.h xr, xr, xr
CPU Flags: LASX
Description
Logical right shift each unsigned 16-bit element in a by the corresponding element of b modulo 16, write the lower 8 bits of the shifted result into the lower half of each 128-bit lane of dst, and zero the upper half.
Operation
for (int i = 0; i < 16; i++) {
dst.byte[i] = (i < 8) ? (u8)((u16)a.half[i] >> (b.half[i] & 15)) : 0;
}
for (int i = 16; i < 32; i++) {
dst.byte[i] = (i < 24) ? (u8)((u16)a.half[i - 8] >> (b.half[i - 8] & 15)) : 0;
}
Tested on real machine.
Latency and Throughput
| CPU | µarch | Latency | Throughput (IPC) |
|---|---|---|---|
| 3C5000 | LA464 | 2 | 1 |
| 3A6000 | LA664 | 2 | 2 |
| 3C6000 | LA664 | 2 | 2 |