__lsx_vmskltz_h
LSX intrinsic · group: Misc
Synopsis
__m128i __lsx_vmskltz_h (__m128i a)
#include <lsxintrin.h>
Instruction: vmskltz.h vr, vr
CPU Flags: LSX
Description
For each 128-bit lane, for each 16-bit element in a, set the bit at that element's index within the lane to one if the element is less than zero, otherwise zero; the remaining bits of the lane are zero.
Examples
__m128i __lsx_vmskltz_h(__m128i{0x1122334455667788, 0x99aabbccddeeff00})
= 0x00000000000000f0 0x0000000000000000
__m128i __lsx_vmskltz_h(__m128i{0x0000808000000000, 0x0081000081716151})
= 0x0000000000000024 0x0000000000000000
Operation
u64 m = 0x8000800080008000;
u64 c = m & a.dword[0];
c |= c << 15;
c |= c << 30;
c >>= 60;
dst.dword[0] = c;
c = m & a.dword[1];
c |= c << 15;
c |= c << 30;
c >>= 60;
dst.dword[0] |= c << 4;
dst.dword[1] = 0;
Tested on real machine.
Latency and Throughput
| CPU | µarch | Latency | Throughput (IPC) |
|---|---|---|---|
| 3C5000 | LA464 | 1 | 2 |
| 3A6000 | LA664 | 1 | 4 |
| 3C6000 | LA664 | 1 | 4 |
| 2K1000LA | LA264 | 1 | 1 |
| 2K3000 | LA364E | 1 | 1 |