__lsx_vfrstpi_h
LSX intrinsic · group: Misc
Synopsis
__m128i __lsx_vfrstpi_h (__m128i a, __m128i b, imm0_31 imm)
#include <lsxintrin.h>
Instruction: vfrstpi.h vr, vr, imm
CPU Flags: LSX
Description
For each 128-bit lane, find the first negative 16-bit element in b. Write its index into the lane of a selected by imm modulo 8, or write the maximum valid index plus one if no such element exists. Other elements of a remain unchanged.
Operation
for (int i = 0; i < 8; i++) {
dst.half[i] = a.half[i];
}
int i;
for (i = 0; i < 8; i++) {
if ((s16)b.half[i] < 0) {
break;
}
}
dst.half[imm % 8] = i;
Tested on real machine.
Latency and Throughput
| CPU | µarch | Latency | Throughput (IPC) |
|---|---|---|---|
| 3C5000 | LA464 | 2 | 2 |
| 3A6000 | LA664 | 2 | 2 |
| 3C6000 | LA664 | 2 | 2 |
| 2K1000LA | LA264 | 2 | 1 |
| 2K3000 | LA364E | 1 | 1 |