__lasx_xvmaddwev_d_w
LASX intrinsic · group: Integer Computation
Synopsis
__m256i __lasx_xvmaddwev_d_w (__m256i a, __m256i b, __m256i c)
#include <lasxintrin.h>
Instruction: xvmaddwev.d.w xr, xr, xr
CPU Flags: LASX
Description
Multiply the even-positioned signed 32-bit elements in b and the corresponding signed 32-bit elements in c, extending both to 64-bit, and add the product to the 64-bit elements in a.
Operation
for (int i = 0; i < 4; i++) {
dst.dword[i] =
(s64)(s32)b.word[2 * i] * (s64)(s32)c.word[2 * i] + (s64)a.dword[i];
}
// Expands to:
if (0) {
dst.dword[0] =
(((s64)((s32)b.word[0])) * ((s64)((s32)c.word[0]))) + ((s64)a.dword[0]);
dst.dword[1] =
(((s64)((s32)b.word[2])) * ((s64)((s32)c.word[2]))) + ((s64)a.dword[1]);
dst.dword[2] =
(((s64)((s32)b.word[4])) * ((s64)((s32)c.word[4]))) + ((s64)a.dword[2]);
dst.dword[3] =
(((s64)((s32)b.word[6])) * ((s64)((s32)c.word[6]))) + ((s64)a.dword[3]);
}
Tested on real machine.
Latency and Throughput
| CPU | µarch | Latency | Throughput (IPC) |
|---|---|---|---|
| 3C5000 | LA464 | 4 | 2 |
| 3A6000 | LA664 | 4 | 2 |
| 3C6000 | LA664 | 4 | 2 |