__lasx_xvrotr_b
LASX intrinsic · group: Shift
Synopsis
__m256i __lasx_xvrotr_b (__m256i a, __m256i b)
#include <lasxintrin.h>
Instruction: xvrotr.b xr, xr, xr
CPU Flags: LASX
Description
Rotate right each unsigned 8-bit element in a by the corresponding element of b modulo 8, store the result in dst.
Operation
for (int i = 0; i < 32; i++) {
dst.byte[i] =
(a.byte[i] >> (b.byte[i] & 0x7)) | (a.byte[i] << (8 - (b.byte[i] & 0x7)));
}
Tested on real machine.
Latency and Throughput
| CPU | µarch | Latency | Throughput (IPC) |
|---|---|---|---|
| 3C5000 | LA464 | 2 | 2 |
| 3A6000 | LA664 | 1 | 4 |
| 3C6000 | LA664 | 1 | 4 |