__lsx_vfsqrt_d
LSX intrinsic · group: Floating Point Computation
Synopsis
__m128d __lsx_vfsqrt_d (__m128d a)
#include <lsxintrin.h>
Instruction: vfsqrt.d vr, vr
CPU Flags: LSX
Description
Compute square root of double precision floating point elements in a.
Operation
for (int i = 0; i < 2; i++) {
dst.fp64[i] = sqrt(a.fp64[i]);
}
Latency and Throughput
| CPU | µarch | Latency | Throughput (IPC) |
|---|---|---|---|
| 3C5000 | LA464 | 36 | 0.05(1/18.5) |
| 3A6000 | LA664 | 36 | 0.06(1/17.5) |
| 3C6000 | LA664 | 36 | 0.06(1/17) |
| 2K1000LA | LA264 | 11 | 0.03(1/37) |
| 2K3000 | LA364E | 11 | 0.03(1/37) |