__lsx_vavgr_w
LSX intrinsic · group: Integer Computation
Synopsis
__m128i __lsx_vavgr_w (__m128i a, __m128i b)
#include <lsxintrin.h>
Instruction: vavgr.w vr, vr, vr
CPU Flags: LSX
Description
Compute the average (rounded towards positive infinity) of corresponding signed 32-bit elements in a and b, save the result in dst.
Operation
for (int i = 0; i < 4; i++) {
dst.word[i] = ((s32)a.word[i] >> 1) + ((s32)b.word[i] >> 1) +
((a.word[i] | b.word[i]) & 1);
}
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 |