__lsx_vdiv_bu
LSX intrinsic · group: Integer Computation
Synopsis
__m128i __lsx_vdiv_bu (__m128i a, __m128i b)
#include <lsxintrin.h>
Instruction: vdiv.bu vr, vr, vr
CPU Flags: LSX
Description
Divide each unsigned 8-bit element in a by the corresponding element in b.
Operation
for (int i = 0; i < 16; i++) {
dst.byte[i] = (b.byte[i] == 0) ? 0 : ((u8)a.byte[i] / (u8)b.byte[i]);
}
Tested on real machine.
Latency and Throughput
| CPU | µarch | Latency | Throughput (IPC) |
|---|---|---|---|
| 3C5000 | LA464 | 29, 36 | 0.06(1/18) |
| 3A6000 | LA664 | 29, 33 | 0.06(1/16.5) |
| 3C6000 | LA664 | 29, 36 | 0.07(1/13.5) |
| 2K1000LA | LA264 | 30, 44 | 0(1/55) |
| 2K3000 | LA364E | 30 | 0(1/55) |