https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66142
Bug ID: 66142
Summary: Loop is not vectorized because not sufficient support
for GOMP_SIMD_LANE
Product: gcc
Version: 6.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: tree-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: ysrumyan at gmail dot com
Target Milestone: ---
The attached test-case compiled with "-Ofast -fopenmp -march=core-avx2" options
contains loop marked with pragma omp simd which is not vectorized:
t1.cpp:66:20: note: not vectorized: data ref analysis failed MEM[(struct vec_
*)_9] = 1.0e+0;
where index is defined as
_12 = GOMP_SIMD_LANE (simduid.0_11(D));
_9 = &D.4231[_12].org;
Note that this test was extracted from important benchmark and loop in question
is vectorized if we revert fix for 59984.
