[llvm-bugs] [Bug 47034] New: Loops with "# pragma clang loop interleave (enable)" specified are vectorized even if -fno-vectorize is specified

[via llvm-bugs]

https://bugs.llvm.org/show_bug.cgi?id=47034

            Bug ID: 47034
           Summary: Loops with "# pragma clang loop interleave (enable)"
                    specified are vectorized even if -fno-vectorize is
                    specified
           Product: libraries
           Version: trunk
          Hardware: PC
                OS: Linux
            Status: NEW
          Severity: enhancement
          Priority: P
         Component: Loop Optimizer
          Assignee: unassignedbugs at nondot.org
          Reporter: fj8765ah at aa.jp.fujitsu.com
                CC: llvm-bugs at lists.llvm.org

Loops with "# pragma clang loop interleave (enable)" specified are vectorized
even if -fno-vectorize is specified.
By the way, it is not interleaved. Is the movement as expected?


a.c

void foo(double * restrict a,
         double * restrict b,
         double * restrict c,
         int n) {

#pragma clang loop interleave(enable)
  for (int i=0;i<n;i++)
    c[i] = a[i] + b[i];

  return;
}


% clang -O1 -fno-vectorize a.c -Rpass=vectorize -S
a.c:7:3: remark: vectorized loop (vectorization width: 2, interleaved count: 1)
[-Rpass=loop-vectorize]
  for (int i=0;i<n;i++)
  ^
%

-- 
You are receiving this mail because:
You are on the CC list for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-bugs/attachments/20200807/b3fa0eed/attachment.html>