BUG: Disable -O3 on right_shift on compilers which emit an internal error

Needed to make CI pass

3 files changed, 50 insertions, 1 deletions

diff --git a/numpy/core/setup.py b/numpy/core/setup.py
index 338502791..e6088a48a 100644
--- a/numpy/core/setup.py
+++ b/numpy/core/setup.py
@@ -463,6 +463,12 @@ def configuration(parent_package='',top_path=None):
             rep = check_long_double_representation(config_cmd)
             moredefs.append(('HAVE_LDOUBLE_%s' % rep, 1))
 
+            if check_for_right_shift_internal_compiler_error(config_cmd):
+                moredefs.append('NPY_DO_NOT_OPTIMIZE_LONG_right_shift')
+                moredefs.append('NPY_DO_NOT_OPTIMIZE_ULONG_right_shift')
+                moredefs.append('NPY_DO_NOT_OPTIMIZE_LONGLONG_right_shift')
+                moredefs.append('NPY_DO_NOT_OPTIMIZE_ULONGLONG_right_shift')
+
             # Py3K check
             if sys.version_info[0] == 3:
                 moredefs.append(('NPY_PY3K', 1))
diff --git a/numpy/core/setup_common.py b/numpy/core/setup_common.py
index 6e3109ab5..6168e3f8d 100644
--- a/numpy/core/setup_common.py
+++ b/numpy/core/setup_common.py
@@ -5,6 +5,7 @@ import sys
 import warnings
 import copy
 import binascii
+import textwrap
 
 from numpy.distutils.misc_util import mingw32
 
@@ -414,3 +415,41 @@ def long_double_representation(lines):
     else:
         # We never detected the after_sequence
         raise ValueError("Could not lock sequences (%s)" % saw)
+
+
+def check_for_right_shift_internal_compiler_error(cmd):
+    """
+    On our arm CI, this fails with an internal compilation error
+
+    The failure looks like the following, and can be reproduced on ARM64 GCC 5.4:
+
+        <source>: In function 'right_shift':
+        <source>:4:20: internal compiler error: in expand_shift_1, at expmed.c:2349
+               ip1[i] = ip1[i] >> in2;
+                      ^
+        Please submit a full bug report,
+        with preprocessed source if appropriate.
+        See <http://gcc.gnu.org/bugs.html> for instructions.
+        Compiler returned: 1
+
+    This function returns True if this compiler bug is present, and we need to
+    turn off optimization for the function
+    """
+    cmd._check_compiler()
+    has_optimize = cmd.try_compile(textwrap.dedent("""\
+        __attribute__((optimize("O3"))) void right_shift() {}
+        """), None, None)
+    if not has_optimize:
+        return False
+
+    no_err = cmd.try_compile(textwrap.dedent("""\
+        typedef long the_type;  /* fails also for unsigned and long long */
+        __attribute__((optimize("O3"))) void right_shift(the_type in2, the_type *ip1, int n) {
+            for (int i = 0; i < n; i++) {
+                if (in2 < (the_type)sizeof(the_type) * 8) {
+                    ip1[i] = ip1[i] >> in2;
+                }
+            }
+        }
+        """), None, None)
+    return not no_err
diff --git a/numpy/core/src/umath/loops.c.src b/numpy/core/src/umath/loops.c.src
index 3d0b41318..0c5465761 100644
--- a/numpy/core/src/umath/loops.c.src
+++ b/numpy/core/src/umath/loops.c.src
@@ -828,7 +828,11 @@ NPY_NO_EXPORT NPY_GCC_OPT_3 void
 #undef INT_left_shift_needs_clear_floatstatus
 #undef UINT_left_shift_needs_clear_floatstatus
 
-NPY_NO_EXPORT NPY_GCC_OPT_3 void
+NPY_NO_EXPORT
+#ifndef NPY_DO_NOT_OPTIMIZE_@TYPE@_right_shift
+NPY_GCC_OPT_3
+#endif
+void
 @TYPE@_right_shift@isa@(char **args, npy_intp *dimensions, npy_intp *steps,
                    void *NPY_UNUSED(func))
 {