__lasx_xvfcmp_cune_d

LASX intrinsic · group: Floating Point Comparison

Synopsis

__m256i __lasx_xvfcmp_cune_d (__m256d a, __m256d b)
#include <lasxintrin.h>
Instruction: xvfcmp.cune.d xr, xr, xr
CPU Flags: LASX

Description

Compare corresponding double precision elements in a and b, save the comparison result (all ones if UNE(Unordered or Not Equal), all zeros otherwise) into dst. No exception is raised for QNaN.

Operation

for (int i = 0; i < 4; i++) {
  if (fp_compare_cune(a.fp64[i], b.fp64[i])) {
    dst.dword[i] = 0xFFFFFFFFFFFFFFFF;
  } else {
    dst.dword[i] = 0;
  }

Latency and Throughput

CPU	µarch	Latency	Throughput (IPC)
3C5000	LA464	2	2
3A6000	LA664	2	4
3C6000	LA664	2	4

---

All intrinsics in alphabetical order