__lasx_xvfrecip_s
LASX intrinsic · group: Floating Point Computation
Synopsis
__m256 __lasx_xvfrecip_s (__m256 a)
#include <lasxintrin.h>
Instruction: xvfrecip.s xr, xr
CPU Flags: LASX
Description
Compute reciprocal of single precision floating point elements in a.
Operation
for (int i = 0; i < 8; i++) {
dst.fp32[i] = 1 / a.fp32[i];
}
Latency and Throughput
| CPU | µarch | Latency | Throughput (IPC) |
|---|---|---|---|
| 3C5000 | LA464 | 11–29 | 0.07–0.17(1/15–1/6) |
| 3C6000 | LA664 | 11–29 | 0.22(1/4.5) |