__lasx_xvsrari_d
LASX intrinsic · group: Shift
Synopsis
__m256i __lasx_xvsrari_d (__m256i a, imm0_63 imm)
#include <lasxintrin.h>
Instruction: xvsrari.d xr, xr, imm
CPU Flags: LASX
Description
Arithmetic right shift (with rounding) the signed 64-bit elements in a by imm, store the result to dst.
Operation
for (int i = 0; i < 4; i++) {
if (imm == 0) {
dst.dword[i] = a.dword[i];
} else {
dst.dword[i] =
((s64)a.dword[i] >> imm) + (((s64)a.dword[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 |