__lsx_vffint_s_w
LSX intrinsic · group: Floating Point Conversion
Synopsis
__m128 __lsx_vffint_s_w (__m128i a)
#include <lsxintrin.h>
Instruction: vffint.s.w vr, vr
CPU Flags: LSX
Description
Convert signed 32-bit integer elements in a to single-precision floating point numbers.
Operation
for (int i = 0; i < 4; i++) {
dst.fp32[i] = (f32)(s32)a.word[i]; // rounding mode is not expressed in C
}
Tested on real machine.
Latency and Throughput
| CPU | µarch | Latency | Throughput (IPC) |
|---|---|---|---|
| 3C5000 | LA464 | 4 | 2 |
| 3A6000 | LA664 | 4 | 4 |
| 3C6000 | LA664 | 4 | 4 |
| 2K1000LA | LA264 | 4 | 1 |
| 2K3000 | LA364E | 4 | 1 |