__lsx_vbitclr_w
LSX intrinsic · group: Bitwise Operations
Synopsis
__m128i __lsx_vbitclr_w (__m128i a, __m128i b)
#include <lsxintrin.h>
Instruction: vbitclr.w vr, vr, vr
CPU Flags: LSX
Description
For each 32-bit element, clear the bit indexed by the corresponding element of b modulo 32, save the result in dst.
Examples
__m128i __lsx_vbitclr_w(__m128i{0xffffffffffffffff, 0x99aabbccddeeff00}, __m128i{0xabababababababab, 0x1234123443214321})
= 0xfffff7fffffff7ff 0x99aabbccddeeff00
Operation
for (int i = 0; i < 4; i++) {
dst.word[i] = a.word[i] & (~((u32)1 << (b.word[i] % 32)));
}
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 | 2 | 1 |