__lasx_xvsrlr_d
LASX intrinsic · group: Shift
Synopsis
__m256i __lasx_xvsrlr_d (__m256i a, __m256i b)
#include <lasxintrin.h>
Instruction: xvsrlr.d xr, xr, xr
CPU Flags: LASX
Description
Logical right shift with rounding each unsigned 64-bit element in a by the corresponding element of b modulo 64, store the result in dst.
Operation
for (int i = 0; i < 4; i++) {
if ((b.dword[i] & 0x3f) == 0) {
dst.dword[i] = a.dword[i];
} else {
dst.dword[i] = (a.dword[i] >> (b.dword[i] & 0x3f)) +
((a.dword[i] >> ((b.dword[i] & 0x3f) - 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 |