__lsx_vssrlni_bu_h
LSX intrinsic · group: Shift
Synopsis
__m128i __lsx_vssrlni_bu_h (__m128i a, __m128i b, imm0_15 imm)
#include <lsxintrin.h>
Instruction: vssrlni.bu.h vr, vr, imm
CPU Flags: LSX
Description
Logical right shift the unsigned 16-bit elements in a and b by imm, saturate the result to unsigned 8-bit, write the 8-bit result into the lower half of each 128-bit lane of dst, and zero the upper half.
Operation
for (int i = 0; i < 16; i++) {
if (i < 8) {
u16 temp = (u16)b.half[i] >> imm;
dst.byte[i] = clamp<u16>(temp, 0, 255);
} else {
u16 temp = (u16)a.half[i - 8] >> imm;
dst.byte[i] = clamp<u16>(temp, 0, 255);
}
}
Tested on real machine.
Latency and Throughput
| CPU | µarch | Latency | Throughput (IPC) |
|---|---|---|---|
| 3C5000 | LA464 | 4 | 1 |
| 3A6000 | LA664 | 4 | 2 |
| 3C6000 | LA664 | 4 | 2 |
| 2K1000LA | LA264 | 3 | 0.5(1/2) |
| 2K3000 | LA364E | 3 | 0.5(1/2) |