__lsx_vfsqrt_s
LSX intrinsic · group: Floating Point Computation
Synopsis
__m128 __lsx_vfsqrt_s (__m128 a)
#include <lsxintrin.h>
Instruction: vfsqrt.s vr, vr
CPU Flags: LSX
Description
Compute square root of single precision floating point elements in a.
Operation
for (int i = 0; i < 4; i++) {
dst.fp32[i] = sqrt(a.fp32[i]);
}
Latency and Throughput
| CPU | µarch | Latency | Throughput (IPC) |
|---|---|---|---|
| 3C5000 | LA464 | 27 | 0.17(1/6) |
| 3A6000 | LA664 | 11 | 0.08(1/12) |
| 3C6000 | LA664 | 25 | 0.09(1/11.5) |
| 2K1000LA | LA264 | 16 | 0.03(1/40) |
| 2K3000 | LA364E | 28 | 0.03(1/40) |