https://bugs.llvm.org/show_bug.cgi?id=49476
Bug ID: 49476
Summary: Missed loop vectorization
Product: libraries
Version: trunk
Hardware: PC
OS: Linux
Status: NEW
Severity: enhancement
Priority: P
Component: Loop Optimizer
Assignee: unassignedb...@nondot.org
Reporter: david.bolvan...@gmail.com
CC: llvm-bugs@lists.llvm.org
#define M 32000
#define N 256
double a[M],x[N][N];
void compute()
{
for (int j = 0; j < N; j++) {
for (int i = j+1; i < N; i++) {
a[i] -= x[j][i] * a[j];
}
}
}
With -Ofast, LLVM does not vectorize this code.
for a[j]:
remark: failed to move load with loop-invariant address because the loop may
invalidate its value [-Rpass-missed=licm]
https://godbolt.org/z/Gx6Px4
--
You are receiving this mail because:
You are on the CC list for the bug._______________________________________________
llvm-bugs mailing list
llvm-bugs@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-bugs
