https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67406
--- Comment #5 from vincenzo Innocente <vincenzo.innocente at cern dot ch> ---
does not work...
pragma omp declare simd notinbranch
float __attribute__ ((__target__ ("default")))
fma(float x,float y, float z);
#pragma omp declare simd notinbranch
float __attribute__ ((__target__ ("arch=haswell")))
fma(float x,float y, float z);
void foo() {
#pragma omp simd
for (int i=0; i<1024; ++i)
v0[i] = fma(v1[i],v2[i],v3[i]);
}
generates
.L11:
vmovss v3(%rbx), %xmm2
addq $4, %rbx
vmovss v2-4(%rbx), %xmm1
vmovss v1-4(%rbx), %xmm0
call _Z15_Z3fmafff.ifuncfff
vmovss %xmm0, v0-4(%rbx)
cmpq $4096, %rbx
jne .L11
dispatching, no vectorization...
