__lsx_vfscaleb_s
LSX intrinsic · group: Undocumented Intrinsics
Synopsis
__m128 __lsx_vfscaleb_s (__m128 a, __m128i b)
#include <lsxintrin.h>
Instruction: vfscaleb.s vr, vr, vr
CPU Flags: LSX
Description
Compute IEEE 754 scaleB (multiply by 2^b) of single precision floating point elements in a using integer exponents in b. Currently undocumented.
Operation
for (int i = 0; i < 4; i++) {
dst.fp32[i] = __builtin_scalbn(a.fp32[i], b.word[i]);
}
Tested on real machine.
Latency and Throughput
| CPU | µarch | Latency | Throughput (IPC) |
|---|---|---|---|
| 3C6000 | LA664 | 4 | 2 |
| 2K1000LA | LA264 | 4 | 1 |
| 2K3000 | LA364E | 4 | 1 |