__lasx_xvfnmadd_s
LASX intrinsic · group: Fused Multiply-Add
Synopsis
__m256 __lasx_xvfnmadd_s (__m256 a, __m256 b, __m256 c)
#include <lasxintrin.h>
Instruction: xvfnmadd.s xr, xr, xr, xr
CPU Flags: LASX
Description
Compute packed single precision floating point FMA(Fused Multiply-Add): multiply elements in a and b, accumulate to elements in c and store the negated result in dst.
Operation
for (int i = 0; i < 8; i++) {
dst.fp32[i] = -(a.fp32[i] * b.fp32[i] + c.fp32[i]);
}
Latency and Throughput
| CPU | µarch | Latency | Throughput (IPC) |
|---|---|---|---|
| 3C5000 | LA464 | 5 | 2 |
| 3A6000 | LA664 | 5 | 2 |
| 3C6000 | LA664 | 5 | 2 |