omp-low.c (struct omp_context): Add for_simd_scan_phase member.

	* omp-low.c (struct omp_context): Add for_simd_scan_phase member.
	(maybe_lookup_ctx): Add forward declaration.
	(omp_find_scan): Likewise.  Walk into body of simd if composited
	with worksharing loop.
	(scan_omp_simd_scan): New function.
	(scan_omp_1_stmt): Call it.
	(lower_rec_simd_input_clauses): Don't create rvar nor rvar2 if
	ctx->for_simd_scan_phase.
	(lower_rec_input_clauses): Do much less work for inscan reductions
	in ctx->for_simd_scan_phase is_simd regions.
	(lower_omp_scan): Set is_simd also on simd constructs composited
	with worksharing loop, unless ctx->for_simd_scan_phase.  Never emit
	a sorry message.  Don't change GIMPLE_OMP_SCAN stmts into nops and
	emit their body after in simd constructs composited with worksharing
	loop.
	(lower_omp_for_scan): Handle worksharing loop composited with simd.

	* c-c++-common/gomp/scan-4.c: Don't expect sorry message.

	* testsuite/libgomp.c/scan-11.c: New test.
	* testsuite/libgomp.c/scan-12.c: New test.
	* testsuite/libgomp.c/scan-13.c: New test.
	* testsuite/libgomp.c/scan-14.c: New test.
	* testsuite/libgomp.c/scan-15.c: New test.
	* testsuite/libgomp.c/scan-16.c: New test.
	* testsuite/libgomp.c/scan-17.c: New test.
	* testsuite/libgomp.c/scan-18.c: New test.
	* testsuite/libgomp.c++/scan-9.C: New test.
	* testsuite/libgomp.c++/scan-10.C: New test.
	* testsuite/libgomp.c++/scan-11.C: New test.
	* testsuite/libgomp.c++/scan-12.C: New test.
	* testsuite/libgomp.c++/scan-13.C: New test.
	* testsuite/libgomp.c++/scan-14.C: New test.
	* testsuite/libgomp.c++/scan-15.C: New test.
	* testsuite/libgomp.c++/scan-16.C: New test.

From-SVN: r273157

gcc/ChangeLog

 2019-07-06  Jakub Jelinek  <jakub@redhat.com>
 
+	* omp-low.c (struct omp_context): Add for_simd_scan_phase member.
+	(maybe_lookup_ctx): Add forward declaration.
+	(omp_find_scan): Likewise.  Walk into body of simd if composited
+	with worksharing loop.
+	(scan_omp_simd_scan): New function.
+	(scan_omp_1_stmt): Call it.
+	(lower_rec_simd_input_clauses): Don't create rvar nor rvar2 if
+	ctx->for_simd_scan_phase.
+	(lower_rec_input_clauses): Do much less work for inscan reductions
+	in ctx->for_simd_scan_phase is_simd regions.
+	(lower_omp_scan): Set is_simd also on simd constructs composited
+	with worksharing loop, unless ctx->for_simd_scan_phase.  Never emit
+	a sorry message.  Don't change GIMPLE_OMP_SCAN stmts into nops and
+	emit their body after in simd constructs composited with worksharing
+	loop.
+	(lower_omp_for_scan): Handle worksharing loop composited with simd.
+
 	* omp-low.c (omp_find_scan): Make static.
 	(lower_omp_for_scan): Fix order of merge arguments in input phase of
 	the second loop, var2 represents the first partial sum and so needs

gcc/testsuite/ChangeLog

 2019-07-06  Jakub Jelinek  <jakub@redhat.com>
 
+	* c-c++-common/gomp/scan-4.c: Don't expect sorry message.
+
 	PR tree-optimization/91096
 	* gcc.dg/vect/vect-simd-10.c (FLT_MIN_VALUE): Define.
 	(bar, main): Use it instead of -__builtin_inff ().

gcc/testsuite/c-c++-common/gomp/scan-4.c

@@ -8,7 +8,7 @@ f1 (int *c, int *d)
   for (i = 0; i < 64; i++)
     {
       d[i] = a;
-      #pragma omp scan exclusive (a)		/* { dg-message "sorry, unimplemented: '#pragma omp scan' not supported yet" } */
+      #pragma omp scan exclusive (a)
       a += c[i];
     }
 }

libgomp/ChangeLog

+2019-07-06  Jakub Jelinek  <jakub@redhat.com>
+
+	* testsuite/libgomp.c/scan-11.c: New test.
+	* testsuite/libgomp.c/scan-12.c: New test.
+	* testsuite/libgomp.c/scan-13.c: New test.
+	* testsuite/libgomp.c/scan-14.c: New test.
+	* testsuite/libgomp.c/scan-15.c: New test.
+	* testsuite/libgomp.c/scan-16.c: New test.
+	* testsuite/libgomp.c/scan-17.c: New test.
+	* testsuite/libgomp.c/scan-18.c: New test.
+	* testsuite/libgomp.c++/scan-9.C: New test.
+	* testsuite/libgomp.c++/scan-10.C: New test.
+	* testsuite/libgomp.c++/scan-11.C: New test.
+	* testsuite/libgomp.c++/scan-12.C: New test.
+	* testsuite/libgomp.c++/scan-13.C: New test.
+	* testsuite/libgomp.c++/scan-14.C: New test.
+	* testsuite/libgomp.c++/scan-15.C: New test.
+	* testsuite/libgomp.c++/scan-16.C: New test.
+
 2019-07-04  Jakub Jelinek  <jakub@redhat.com>
 
 	* testsuite/libgomp.c/scan-9.c: New test.

libgomp/testsuite/libgomp.c++/scan-10.C

+// { dg-require-effective-target size32plus }
+// { dg-additional-options "-O2 -fopenmp -fdump-tree-vect-details" }
+// { dg-additional-options "-mavx" { target avx_runtime } }
+// { dg-final { scan-tree-dump-times "vectorized \[2-6] loops" 2 "vect" { target sse2_runtime } } }
+
+extern "C" void abort ();
+int r, a[1024], b[1024], q;
+
+__attribute__((noipa)) void
+foo (int *a, int *b, int &r)
+{
+  #pragma omp for simd if (0) reduction (inscan, +:r) nowait
+  for (int i = 0; i < 1024; i++)
+    {
+      r += a[i];
+      #pragma omp scan inclusive(r)
+      b[i] = r;
+    }
+}
+
+__attribute__((noipa)) int
+bar (void)
+{
+  int &s = q;
+  q = 0;
+  #pragma omp parallel
+  #pragma omp for simd simdlen(1) reduction (inscan, +:s) nowait
+  for (int i = 0; i < 1024; i++)
+    {
+      s += 2 * a[i];
+      #pragma omp scan inclusive(s)
+      b[i] = s;
+    }
+  return s;
+}
+
+__attribute__((noipa)) void
+baz (int *a, int *b, int &r)
+{
+  #pragma omp parallel for simd reduction (inscan, +:r)
+  for (int i = 0; i < 1024; i++)
+    {
+      r += a[i];
+      #pragma omp scan inclusive(r)
+      b[i] = r;
+    }
+}
+
+__attribute__((noipa)) int
+qux (void)
+{
+  int &s = q;
+  q = 0;
+  #pragma omp parallel for simd reduction (inscan, +:s)
+  for (int i = 0; i < 1024; i++)
+    {
+      s += 2 * a[i];
+      #pragma omp scan inclusive(s)
+      b[i] = s;
+    }
+  return s;
+}
+
+int
+main ()
+{
+  int s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      a[i] = i;
+      b[i] = -1;
+      asm ("" : "+g" (i));
+    }
+  #pragma omp parallel
+  foo (a, b, r);
+  if (r != 1024 * 1023 / 2)
+    abort ();
+  for (int i = 0; i < 1024; ++i)
+    {
+      s += i;
+      if (b[i] != s)
+	abort ();
+      else
+	b[i] = 25;
+    }
+  if (bar () != 1024 * 1023)
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      s += 2 * i;
+      if (b[i] != s)
+	abort ();
+      else
+	b[i] = -1;
+    }
+  r = 0;
+  baz (a, b, r);
+  if (r != 1024 * 1023 / 2)
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      s += i;
+      if (b[i] != s)
+	abort ();
+      else
+	b[i] = -25;
+    }
+  if (qux () != 1024 * 1023)
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      s += 2 * i;
+      if (b[i] != s)
+	abort ();
+    }
+}

libgomp/testsuite/libgomp.c++/scan-11.C

+// { dg-require-effective-target size32plus }
+// { dg-additional-options "-O2 -fopenmp -fdump-tree-vect-details" }
+// { dg-additional-options "-mavx" { target avx_runtime } }
+// { dg-final { scan-tree-dump-times "vectorized \[2-6] loops" 2 "vect" { target sse2_runtime } } }
+
+extern "C" void abort ();
+int r, a[1024], b[1024], q;
+
+#pragma omp declare reduction (foo: int: omp_out += omp_in) initializer (omp_priv = 0)
+
+__attribute__((noipa)) void
+foo (int *a, int *b, int &r)
+{
+  #pragma omp for simd reduction (inscan, foo:r)
+  for (int i = 0; i < 1024; i++)
+    {
+      r += a[i];
+      #pragma omp scan inclusive(r)
+      b[i] = r;
+    }
+}
+
+__attribute__((noipa)) int
+bar (void)
+{
+  int &s = q;
+  q = 0;
+  #pragma omp parallel
+  #pragma omp for simd reduction (inscan, foo:s) if (0)
+  for (int i = 0; i < 1024; i++)
+    {
+      s += 2 * a[i];
+      #pragma omp scan inclusive(s)
+      b[i] = s;
+    }
+  return s;
+}
+
+__attribute__((noipa)) void
+baz (int *a, int *b, int &r)
+{
+  #pragma omp parallel for simd simdlen (1) reduction (inscan, foo:r)
+  for (int i = 0; i < 1024; i++)
+    {
+      r += a[i];
+      #pragma omp scan inclusive(r)
+      b[i] = r;
+    }
+}
+
+__attribute__((noipa)) int
+qux (void)
+{
+  int &s = q;
+  q = 0;
+  #pragma omp parallel for simd reduction (inscan, foo:s)
+  for (int i = 0; i < 1024; i++)
+    {
+      s += 2 * a[i];
+      #pragma omp scan inclusive(s)
+      b[i] = s;
+    }
+  return s;
+}
+
+int
+main ()
+{
+  int s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      a[i] = i;
+      b[i] = -1;
+      asm ("" : "+g" (i));
+    }
+  #pragma omp parallel
+  foo (a, b, r);
+  if (r != 1024 * 1023 / 2)
+    abort ();
+  for (int i = 0; i < 1024; ++i)
+    {
+      s += i;
+      if (b[i] != s)
+	abort ();
+      else
+	b[i] = 25;
+    }
+  if (bar () != 1024 * 1023)
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      s += 2 * i;
+      if (b[i] != s)
+	abort ();
+      else
+	b[i] = -1;
+    }
+  r = 0;
+  baz (a, b, r);
+  if (r != 1024 * 1023 / 2)
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      s += i;
+      if (b[i] != s)
+	abort ();
+      else
+	b[i] = -25;
+    }
+  if (qux () != 1024 * 1023)
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      s += 2 * i;
+      if (b[i] != s)
+	abort ();
+    }
+  return 0;
+}

libgomp/testsuite/libgomp.c++/scan-12.C

+// { dg-require-effective-target size32plus }
+// { dg-additional-options "-O2 -fopenmp -fdump-tree-vect-details" }
+// { dg-additional-options "-mavx" { target avx_runtime } }
+// { dg-final { scan-tree-dump-times "vectorized \[2-6] loops" 2 "vect" { target sse2_runtime } } }
+
+extern "C" void abort ();
+
+struct S {
+  inline S ();
+  inline ~S ();
+  inline S (const S &);
+  inline S & operator= (const S &);
+  int s;
+};
+
+S::S () : s (0)
+{
+}
+
+S::~S ()
+{
+}
+
+S::S (const S &x)
+{
+  s = x.s;
+}
+
+S &
+S::operator= (const S &x)
+{
+  s = x.s;
+  return *this;
+}
+
+static inline void
+ini (S &x)
+{
+  x.s = 0;
+}
+
+S r, a[1024], b[1024];
+
+#pragma omp declare reduction (+: S: omp_out.s += omp_in.s)
+#pragma omp declare reduction (plus: S: omp_out.s += omp_in.s) initializer (ini (omp_priv))
+
+__attribute__((noipa)) void
+foo (S *a, S *b, S &r)
+{
+  #pragma omp for simd reduction (inscan, +:r)
+  for (int i = 0; i < 1024; i++)
+    {
+      r.s += a[i].s;
+      #pragma omp scan inclusive(r)
+      b[i] = r;
+    }
+}
+
+__attribute__((noipa)) S
+bar ()
+{
+  S s;
+  #pragma omp parallel
+  #pragma omp for simd reduction (inscan, plus:s)
+  for (int i = 0; i < 1024; i++)
+    {
+      s.s += 2 * a[i].s;
+      #pragma omp scan inclusive(s)
+      b[i] = s;
+    }
+  return s;
+}
+
+__attribute__((noipa)) void
+baz (S *a, S *b, S &r)
+{
+  #pragma omp parallel for simd if (simd: 0) reduction (inscan, +:r)
+  for (int i = 0; i < 1024; i++)
+    {
+      r.s += a[i].s;
+      #pragma omp scan inclusive(r)
+      b[i] = r;
+    }
+}
+
+__attribute__((noipa)) S
+qux ()
+{
+  S s;
+  #pragma omp parallel for simd reduction (inscan, plus:s) simdlen(1)
+  for (int i = 0; i < 1024; i++)
+    {
+      s.s += 2 * a[i].s;
+      #pragma omp scan inclusive(s)
+      b[i] = s;
+    }
+  return s;
+}
+
+int
+main ()
+{
+  S s;
+  for (int i = 0; i < 1024; ++i)
+    {
+      a[i].s = i;
+      b[i].s = -1;
+      asm ("" : "+g" (i));
+    }
+  #pragma omp parallel
+  foo (a, b, r);
+  if (r.s != 1024 * 1023 / 2)
+    abort ();
+  for (int i = 0; i < 1024; ++i)
+    {
+      s.s += i;
+      if (b[i].s != s.s)
+	abort ();
+      else
+	b[i].s = 25;
+    }
+  if (bar ().s != 1024 * 1023)
+    abort ();
+  s.s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      s.s += 2 * i;
+      if (b[i].s != s.s)
+	abort ();
+    }
+  r.s = 0;
+  baz (a, b, r);
+  if (r.s != 1024 * 1023 / 2)
+    abort ();
+  s.s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      s.s += i;
+      if (b[i].s != s.s)
+	abort ();
+      else
+	b[i].s = 25;
+    }
+  if (qux ().s != 1024 * 1023)
+    abort ();
+  s.s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      s.s += 2 * i;
+      if (b[i].s != s.s)
+	abort ();
+    }
+}

libgomp/testsuite/libgomp.c++/scan-13.C

+// { dg-require-effective-target size32plus }
+// { dg-additional-options "-O2 -fopenmp -fdump-tree-vect-details" }
+// { dg-additional-options "-mavx" { target avx_runtime } }
+// { dg-final { scan-tree-dump-times "vectorized \[2-6] loops" 2 "vect" { xfail *-*-* } } }
+
+extern "C" void abort ();
+
+template <typename T>
+struct S {
+  inline S ();
+  inline ~S ();
+  inline S (const S &);
+  inline S & operator= (const S &);
+  T s;
+};
+
+template <typename T>
+S<T>::S () : s (0)
+{
+}
+
+template <typename T>
+S<T>::~S ()
+{
+}
+
+template <typename T>
+S<T>::S (const S &x)
+{
+  s = x.s;
+}
+
+template <typename T>
+S<T> &
+S<T>::operator= (const S &x)
+{
+  s = x.s;
+  return *this;
+}
+
+template <typename T>
+static inline void
+ini (S<T> &x)
+{
+  x.s = 0;
+}
+
+S<int> r, a[1024], b[1024];
+
+#pragma omp declare reduction (+: S<int>: omp_out.s += omp_in.s)
+#pragma omp declare reduction (plus: S<int>: omp_out.s += omp_in.s) initializer (ini (omp_priv))
+
+template <typename T>
+__attribute__((noipa)) void
+foo (S<T> *a, S<T> *b)
+{
+  #pragma omp for simd if (0) reduction (inscan, +:r)
+  for (int i = 0; i < 1024; i++)
+    {
+      b[i] = r;
+      #pragma omp scan exclusive(r)
+      r.s += a[i].s;
+    }
+}
+
+template <typename T>
+__attribute__((noipa)) S<T>
+bar (void)
+{
+  S<T> s;
+  #pragma omp parallel
+  #pragma omp for simd reduction (inscan, plus:s)
+  for (int i = 0; i < 1024; i++)
+    {
+      b[i] = s;
+      #pragma omp scan exclusive(s)
+      s.s += 2 * a[i].s;
+    }
+  return S<T> (s);
+}
+
+__attribute__((noipa)) void
+baz (S<int> *a, S<int> *b)
+{
+  #pragma omp parallel for simd reduction (inscan, +:r)
+  for (int i = 0; i < 1024; i++)
+    {
+      b[i] = r;
+      #pragma omp scan exclusive(r)
+      r.s += a[i].s;
+    }
+}
+
+__attribute__((noipa)) S<int>
+qux (void)
+{
+  S<int> s;
+  #pragma omp parallel for simd simdlen(1) reduction (inscan, plus:s)
+  for (int i = 0; i < 1024; i++)
+    {
+      b[i] = s;
+      #pragma omp scan exclusive(s)
+      s.s += 2 * a[i].s;
+    }
+  return S<int> (s);
+}
+
+int
+main ()
+{
+  S<int> s;
+  for (int i = 0; i < 1024; ++i)
+    {
+      a[i].s = i;
+      b[i].s = -1;
+      asm ("" : "+g" (i));
+    }
+  #pragma omp parallel
+  foo (a, b);
+  if (r.s != 1024 * 1023 / 2)
+    abort ();
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i].s != s.s)
+	abort ();
+      else
+	b[i].s = 25;
+      s.s += i;
+    }
+  if (bar<int> ().s != 1024 * 1023)
+    abort ();
+  s.s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i].s != s.s)
+	abort ();
+      s.s += 2 * i;
+    }
+  r.s = 0;
+  baz (a, b);
+  if (r.s != 1024 * 1023 / 2)
+    abort ();
+  s.s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i].s != s.s)
+	abort ();
+      else
+	b[i].s = 25;
+      s.s += i;
+    }
+  if (qux ().s != 1024 * 1023)
+    abort ();
+  s.s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i].s != s.s)
+	abort ();
+      s.s += 2 * i;
+    }
+}

libgomp/testsuite/libgomp.c++/scan-14.C

+// { dg-require-effective-target size32plus }
+// { dg-additional-options "-O2 -fopenmp -fdump-tree-vect-details" }
+// { dg-additional-options "-mavx" { target avx_runtime } }
+// { dg-final { scan-tree-dump-times "vectorized \[2-6] loops" 2 "vect" { target sse2_runtime } } }
+
+extern "C" void abort ();
+int r, a[1024], b[1024], q;
+
+template <typename T, typename U>
+__attribute__((noipa)) void
+foo (T a, T b, U r)
+{
+  #pragma omp for simd if (0) reduction (inscan, +:r)
+  for (int i = 0; i < 1024; i++)
+    {
+      b[i] = r;
+      #pragma omp scan exclusive(r)
+      r += a[i];
+    }
+}
+
+template <typename T>
+__attribute__((noipa)) T
+bar ()
+{
+  T &s = q;
+  q = 0;
+  #pragma omp parallel
+  #pragma omp for simd reduction (inscan, +:s) simdlen(1)
+  for (int i = 0; i < 1024; i++)
+    {
+      b[i] = s;
+      #pragma omp scan exclusive(s)
+      s += 2 * a[i];
+    }
+  return s;
+}
+
+template <typename T>
+__attribute__((noipa)) void
+baz (T *a, T *b, T &r)
+{
+  #pragma omp parallel for simd reduction (inscan, +:r)
+  for (T i = 0; i < 1024; i++)
+    {
+      b[i] = r;
+      #pragma omp scan exclusive(r)
+      r += a[i];
+    }
+}
+
+template <typename T>
+__attribute__((noipa)) int
+qux ()
+{
+  T s = q;
+  q = 0;
+  #pragma omp parallel for simd reduction (inscan, +:s)
+  for (int i = 0; i < 1024; i++)
+    {
+      b[i] = s;
+      #pragma omp scan exclusive(s)
+      s += 2 * a[i];
+    }
+  return s;
+}
+
+int
+main ()
+{
+  int s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      a[i] = i;
+      b[i] = -1;
+      asm ("" : "+g" (i));
+    }
+  #pragma omp parallel
+  foo<int *, int &> (a, b, r);
+  if (r != 1024 * 1023 / 2)
+    abort ();
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i] != s)
+	abort ();
+      else
+	b[i] = 25;
+      s += i;
+    }
+  if (bar<int> () != 1024 * 1023)
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i] != s)
+	abort ();
+      else
+	b[i] = -1;
+      s += 2 * i;
+    }
+  r = 0;
+  baz<int> (a, b, r);
+  if (r != 1024 * 1023 / 2)
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i] != s)
+	abort ();
+      else
+	b[i] = -25;
+      s += i;
+    }
+  if (qux<int &> () != 1024 * 1023)
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i] != s)
+	abort ();
+      s += 2 * i;
+    }
+}

libgomp/testsuite/libgomp.c++/scan-15.C

+// { dg-require-effective-target size32plus }
+// { dg-additional-options "-O2 -fopenmp -fdump-tree-vect-details" }
+// { dg-additional-options "-mavx" { target avx_runtime } }
+// { dg-final { scan-tree-dump-times "vectorized \[2-6] loops" 2 "vect" { target sse2_runtime } } }
+
+extern "C" void abort ();
+int r, a[1024], b[1024], q;
+
+#pragma omp declare reduction (foo: int: omp_out += omp_in) initializer (omp_priv = 0)
+
+__attribute__((noipa)) void
+foo (int *a, int *b, int &r)
+{
+  #pragma omp for simd reduction (inscan, foo:r)
+  for (int i = 0; i < 1024; i++)
+    {
+      b[i] = r;
+      #pragma omp scan exclusive(r)
+      r += a[i];
+    }
+}
+
+__attribute__((noipa)) int
+bar (void)
+{
+  int &s = q;
+  q = 0;
+  #pragma omp parallel
+  #pragma omp for simd reduction (inscan, foo:s) nowait
+  for (int i = 0; i < 1024; i++)
+    {
+      b[i] = s;
+      #pragma omp scan exclusive(s)
+      s += 2 * a[i];
+    }
+  return s;
+}
+
+__attribute__((noipa)) void
+baz (int *a, int *b, int &r)
+{
+  #pragma omp parallel for simd reduction (inscan, foo:r) if (simd: 0)
+  for (int i = 0; i < 1024; i++)
+    {
+      b[i] = r;
+      #pragma omp scan exclusive(r)
+      r += a[i];
+    }
+}
+
+__attribute__((noipa)) int
+qux (void)
+{
+  int &s = q;
+  q = 0;
+  #pragma omp parallel for simd reduction (inscan, foo:s)simdlen(1)
+  for (int i = 0; i < 1024; i++)
+    {
+      b[i] = s;
+      #pragma omp scan exclusive(s)
+      s += 2 * a[i];
+    }
+  return s;
+}
+
+int
+main ()
+{
+  int s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      a[i] = i;
+      b[i] = -1;
+      asm ("" : "+g" (i));
+    }
+  #pragma omp parallel
+  foo (a, b, r);
+  if (r != 1024 * 1023 / 2)
+    abort ();
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i] != s)
+	abort ();
+      else
+	b[i] = 25;
+      s += i;
+    }
+  if (bar () != 1024 * 1023)
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i] != s)
+	abort ();
+      else
+	b[i] = -1;
+      s += 2 * i;
+    }
+  r = 0;
+  baz (a, b, r);
+  if (r != 1024 * 1023 / 2)
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i] != s)
+	abort ();
+      else
+	b[i] = -25;
+      s += i;
+    }
+  if (qux () != 1024 * 1023)
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i] != s)
+	abort ();
+      s += 2 * i;
+    }
+}

libgomp/testsuite/libgomp.c++/scan-16.C

+// { dg-require-effective-target size32plus }
+// { dg-additional-options "-O2 -fopenmp -fdump-tree-vect-details" }
+// { dg-additional-options "-mavx" { target avx_runtime } }
+// { dg-final { scan-tree-dump-times "vectorized \[2-6] loops" 2 "vect" { xfail *-*-* } } }
+
+extern "C" void abort ();
+
+struct S {
+  inline S ();
+  inline ~S ();
+  inline S (const S &);
+  inline S & operator= (const S &);
+  int s;
+};
+
+S::S () : s (0)
+{
+}
+
+S::~S ()
+{
+}
+
+S::S (const S &x)
+{
+  s = x.s;
+}
+
+S &
+S::operator= (const S &x)
+{
+  s = x.s;
+  return *this;
+}
+
+static inline void
+ini (S &x)
+{
+  x.s = 0;
+}
+
+S r, a[1024], b[1024];
+
+#pragma omp declare reduction (+: S: omp_out.s += omp_in.s)
+#pragma omp declare reduction (plus: S: omp_out.s += omp_in.s) initializer (ini (omp_priv))
+
+__attribute__((noipa)) void
+foo (S *a, S *b, S &r)
+{
+  #pragma omp for simd simdlen (1) reduction (inscan, +:r)
+  for (int i = 0; i < 1024; i++)
+    {
+      b[i] = r;
+      #pragma omp scan exclusive(r)
+      r.s += a[i].s;
+    }
+}
+
+__attribute__((noipa)) S
+bar (void)
+{
+  S s;
+  #pragma omp parallel
+  #pragma omp for simd if (0) reduction (inscan, plus:s)
+  for (int i = 0; i < 1024; i++)
+    {
+      b[i] = s;
+      #pragma omp scan exclusive(s)
+      s.s += 2 * a[i].s;
+    }
+  return s;
+}
+
+__attribute__((noipa)) void
+baz (S *a, S *b, S &r)
+{
+  #pragma omp parallel for simd reduction (inscan, +:r)
+  for (int i = 0; i < 1024; i++)
+    {
+      b[i] = r;
+      #pragma omp scan exclusive(r)
+      r.s += a[i].s;
+    }
+}
+
+__attribute__((noipa)) S
+qux (void)
+{
+  S s;
+  #pragma omp parallel for simd reduction (inscan, plus:s)
+  for (int i = 0; i < 1024; i++)
+    {
+      b[i] = s;
+      #pragma omp scan exclusive(s)
+      s.s += 2 * a[i].s;
+    }
+  return s;
+}
+
+int
+main ()
+{
+  S s;
+  for (int i = 0; i < 1024; ++i)
+    {
+      a[i].s = i;
+      b[i].s = -1;
+      asm ("" : "+g" (i));
+    }
+  #pragma omp parallel
+  foo (a, b, r);
+  if (r.s != 1024 * 1023 / 2)
+    abort ();
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i].s != s.s)
+	abort ();
+      else
+	b[i].s = 25;
+      s.s += i;
+    }
+  if (bar ().s != 1024 * 1023)
+    abort ();
+  s.s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i].s != s.s)
+	abort ();
+      s.s += 2 * i;
+    }
+  r.s = 0;
+  baz (a, b, r);
+  if (r.s != 1024 * 1023 / 2)
+    abort ();
+  s.s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i].s != s.s)
+	abort ();
+      else
+	b[i].s = 25;
+      s.s += i;
+    }
+  if (qux ().s != 1024 * 1023)
+    abort ();
+  s.s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i].s != s.s)
+	abort ();
+      s.s += 2 * i;
+    }
+}

libgomp/testsuite/libgomp.c++/scan-9.C

+// { dg-require-effective-target size32plus }
+// { dg-additional-options "-O2 -fopenmp -fdump-tree-vect-details" }
+// { dg-additional-options "-mavx" { target avx_runtime } }
+// { dg-final { scan-tree-dump-times "vectorized \[2-6] loops" 2 "vect" { target sse2_runtime } } }
+
+extern "C" void abort ();
+
+struct S {
+  inline S ();
+  inline ~S ();
+  inline S (const S &);
+  inline S & operator= (const S &);
+  int s;
+};
+
+S::S () : s (0)
+{
+}
+
+S::~S ()
+{
+}
+
+S::S (const S &x)
+{
+  s = x.s;
+}
+
+S &
+S::operator= (const S &x)
+{
+  s = x.s;
+  return *this;
+}
+
+static inline void
+ini (S &x)
+{
+  x.s = 0;
+}
+
+S r, a[1024], b[1024];
+
+#pragma omp declare reduction (+: S: omp_out.s += omp_in.s)
+#pragma omp declare reduction (plus: S: omp_out.s += omp_in.s) initializer (ini (omp_priv))
+
+__attribute__((noipa)) void
+foo (S *a, S *b)
+{
+  #pragma omp for simd reduction (inscan, +:r)
+  for (int i = 0; i < 1024; i++)
+    {
+      r.s += a[i].s;
+      #pragma omp scan inclusive(r)
+      b[i] = r;
+    }
+}
+
+__attribute__((noipa)) S
+bar (void)
+{
+  S s;
+  #pragma omp parallel
+  #pragma omp for simd reduction (inscan, plus:s)
+  for (int i = 0; i < 1024; i++)
+    {
+      s.s += 2 * a[i].s;
+      #pragma omp scan inclusive(s)
+      b[i] = s;
+    }
+  return S (s);
+}
+
+__attribute__((noipa)) void
+baz (S *a, S *b)
+{
+  #pragma omp parallel for simd simdlen (1) reduction (inscan, +:r)
+  for (int i = 0; i < 1024; i++)
+    {
+      r.s += a[i].s;
+      #pragma omp scan inclusive(r)
+      b[i] = r;
+    }
+}
+
+__attribute__((noipa)) S
+qux (void)
+{
+  S s;
+  #pragma omp parallel for simd if (simd: 0) reduction (inscan, plus:s)
+  for (int i = 0; i < 1024; i++)
+    {
+      s.s += 2 * a[i].s;
+      #pragma omp scan inclusive(s)
+      b[i] = s;
+    }
+  return S (s);
+}
+
+int
+main ()
+{
+  S s;
+  for (int i = 0; i < 1024; ++i)
+    {
+      a[i].s = i;
+      b[i].s = -1;
+      asm ("" : "+g" (i));
+    }
+  #pragma omp parallel
+  foo (a, b);
+  if (r.s != 1024 * 1023 / 2)
+    abort ();
+  for (int i = 0; i < 1024; ++i)
+    {
+      s.s += i;
+      if (b[i].s != s.s)
+	abort ();
+      else
+	b[i].s = 25;
+    }
+  if (bar ().s != 1024 * 1023)
+    abort ();
+  s.s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      s.s += 2 * i;
+      if (b[i].s != s.s)
+	abort ();
+    }
+  r.s = 0;
+  baz (a, b);
+  if (r.s != 1024 * 1023 / 2)
+    abort ();
+  s.s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      s.s += i;
+      if (b[i].s != s.s)
+	abort ();
+      else
+	b[i].s = 25;
+    }
+  if (qux ().s != 1024 * 1023)
+    abort ();
+  s.s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      s.s += 2 * i;
+      if (b[i].s != s.s)
+	abort ();
+    }
+  return 0;
+}

libgomp/testsuite/libgomp.c/scan-11.c

+/* { dg-require-effective-target size32plus } */
+/* { dg-additional-options "-O2 -fopenmp -fdump-tree-vect-details" } */
+/* { dg-additional-options "-mavx" { target avx_runtime } } */
+/* { dg-final { scan-tree-dump-times "vectorized \[2-6] loops" 2 "vect" { target sse2_runtime } } } */
+
+extern void abort (void);
+int r, a[1024], b[1024];
+
+__attribute__((noipa)) void
+foo (int *a, int *b)
+{
+  #pragma omp for simd reduction (inscan, +:r)
+  for (int i = 0; i < 1024; i++)
+    {
+      r += a[i];
+      #pragma omp scan inclusive(r)
+      b[i] = r;
+    }
+}
+
+__attribute__((noipa)) int
+bar (void)
+{
+  int s = 0;
+  #pragma omp parallel
+  #pragma omp for simd reduction (inscan, +:s) if (0)
+  for (int i = 0; i < 1024; i++)
+    {
+      s += 2 * a[i];
+      #pragma omp scan inclusive(s)
+      b[i] = s;
+    }
+  return s;
+}
+
+__attribute__((noipa)) void
+baz (int *a, int *b)
+{
+  #pragma omp parallel for simd reduction (inscan, +:r) simdlen(1)
+  for (int i = 0; i < 1024; i++)
+    {
+      r += a[i];
+      #pragma omp scan inclusive(r)
+      b[i] = r;
+    }
+}
+
+__attribute__((noipa)) int
+qux (void)
+{
+  int s = 0;
+  #pragma omp parallel for simd reduction (inscan, +:s)
+  for (int i = 0; i < 1024; i++)
+    {
+      s += 2 * a[i];
+      #pragma omp scan inclusive(s)
+      b[i] = s;
+    }
+  return s;
+}
+
+int
+main ()
+{
+  int s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      a[i] = i;
+      b[i] = -1;
+      asm ("" : "+g" (i));
+    }
+  #pragma omp parallel
+  foo (a, b);
+  if (r != 1024 * 1023 / 2)
+    abort ();
+  for (int i = 0; i < 1024; ++i)
+    {
+      s += i;
+      if (b[i] != s)
+	abort ();
+      else
+	b[i] = 25;
+    }
+  if (bar () != 1024 * 1023)
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      s += 2 * i;
+      if (b[i] != s)
+	abort ();
+      else
+	b[i] = -1;
+    }
+  r = 0;
+  baz (a, b);
+  if (r != 1024 * 1023 / 2)
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      s += i;
+      if (b[i] != s)
+	abort ();
+      else
+	b[i] = -25;
+    }
+  if (qux () != 1024 * 1023)
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      s += 2 * i;
+      if (b[i] != s)
+	abort ();
+    }
+  return 0;
+}

libgomp/testsuite/libgomp.c/scan-12.c

+/* { dg-require-effective-target size32plus } */
+/* { dg-additional-options "-O2 -fopenmp -fdump-tree-vect-details" } */
+/* { dg-additional-options "-mavx" { target avx_runtime } } */
+/* { dg-final { scan-tree-dump-times "vectorized \[2-6] loops" 2 "vect" { target sse2_runtime } } } */
+
+extern void abort (void);
+int r, a[1024], b[1024];
+
+#pragma omp declare reduction (foo: int: omp_out += omp_in) initializer (omp_priv = 0)
+
+__attribute__((noipa)) void
+foo (int *a, int *b)
+{
+  #pragma omp for simd reduction (inscan, foo:r) simdlen (1)
+  for (int i = 0; i < 1024; i++)
+    {
+      r += a[i];
+      #pragma omp scan inclusive(r)
+      b[i] = r;
+    }
+}
+
+__attribute__((noipa)) int
+bar (void)
+{
+  int s = 0;
+  #pragma omp parallel
+  #pragma omp for simd reduction (inscan, foo:s)
+  for (int i = 0; i < 1024; i++)
+    {
+      s += 2 * a[i];
+      #pragma omp scan inclusive(s)
+      b[i] = s;
+    }
+  return s;
+}
+
+__attribute__((noipa)) void
+baz (int *a, int *b)
+{
+  #pragma omp parallel for simd reduction (inscan, foo:r)
+  for (int i = 0; i < 1024; i++)
+    {
+      r += a[i];
+      #pragma omp scan inclusive(r)
+      b[i] = r;
+    }
+}
+
+__attribute__((noipa)) int
+qux (void)
+{
+  int s = 0;
+  #pragma omp parallel for simd if (simd: 0) reduction (inscan, foo:s)
+  for (int i = 0; i < 1024; i++)
+    {
+      s += 2 * a[i];
+      #pragma omp scan inclusive(s)
+      b[i] = s;
+    }
+  return s;
+}
+
+int
+main ()
+{
+  int s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      a[i] = i;
+      b[i] = -1;
+      asm ("" : "+g" (i));
+    }
+  #pragma omp parallel
+  foo (a, b);
+  if (r != 1024 * 1023 / 2)
+    abort ();
+  for (int i = 0; i < 1024; ++i)
+    {
+      s += i;
+      if (b[i] != s)
+	abort ();
+      else
+	b[i] = 25;
+    }
+  if (bar () != 1024 * 1023)
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      s += 2 * i;
+      if (b[i] != s)
+	abort ();
+      else
+	b[i] = -1;
+    }
+  r = 0;
+  baz (a, b);
+  if (r != 1024 * 1023 / 2)
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      s += i;
+      if (b[i] != s)
+	abort ();
+      else
+	b[i] = -25;
+    }
+  if (qux () != 1024 * 1023)
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      s += 2 * i;
+      if (b[i] != s)
+	abort ();
+    }
+  return 0;
+}

libgomp/testsuite/libgomp.c/scan-13.c

+/* { dg-require-effective-target size32plus } */
+/* { dg-additional-options "-O2 -fopenmp -fdump-tree-vect-details" } */
+/* { dg-additional-options "-mavx" { target avx_runtime } } */
+/* { dg-final { scan-tree-dump-times "vectorized \[2-6] loops" 2 "vect" { target sse2_runtime } } } */
+
+extern void abort (void);
+float r = 1.0f, a[1024], b[1024];
+
+__attribute__((noipa)) void
+foo (float *a, float *b)
+{
+  #pragma omp for simd reduction (inscan, *:r)
+  for (int i = 0; i < 1024; i++)
+    {
+      r *= a[i];
+      #pragma omp scan inclusive(r)
+      b[i] = r;
+    }
+}
+
+__attribute__((noipa)) float
+bar (void)
+{
+  float s = -__builtin_inff ();
+  #pragma omp parallel for simd reduction (inscan, max:s)
+  for (int i = 0; i < 1024; i++)
+    {
+      s = s > a[i] ? s : a[i];
+      #pragma omp scan inclusive(s)
+      b[i] = s;
+    }
+  return s;
+}
+
+int
+main ()
+{
+  float s = 1.0f;
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (i < 80)
+	a[i] = (i & 1) ? 0.25f : 0.5f;
+      else if (i < 200)
+	a[i] = (i % 3) == 0 ? 2.0f : (i % 3) == 1 ? 4.0f : 1.0f;
+      else if (i < 280)
+	a[i] = (i & 1) ? 0.25f : 0.5f;
+      else if (i < 380)
+	a[i] = (i % 3) == 0 ? 2.0f : (i % 3) == 1 ? 4.0f : 1.0f;
+      else
+	switch (i % 6)
+	  {
+	  case 0: a[i] = 0.25f; break;
+	  case 1: a[i] = 2.0f; break;
+	  case 2: a[i] = -1.0f; break;
+	  case 3: a[i] = -4.0f; break;
+	  case 4: a[i] = 0.5f; break;
+	  case 5: a[i] = 1.0f; break;
+	  default: a[i] = 0.0f; break;
+	  }
+      b[i] = -19.0f;
+      asm ("" : "+g" (i));
+    }
+  #pragma omp parallel
+  foo (a, b);
+  if (r * 16384.0f != 0.125f)
+    abort ();
+  float m = -175.25f;
+  for (int i = 0; i < 1024; ++i)
+    {
+      s *= a[i];
+      if (b[i] != s)
+	abort ();
+      else
+	{
+	  a[i] = m - ((i % 3) == 1 ? 2.0f : (i % 3) == 2 ? 4.0f : 0.0f);
+	  b[i] = -231.75f;
+	  m += 0.75f;
+	}
+    }
+  if (bar () != 592.0f)
+    abort ();
+  s = -__builtin_inff ();
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (s < a[i])
+	s = a[i];
+      if (b[i] != s)
+	abort ();
+    }
+  return 0;
+}

libgomp/testsuite/libgomp.c/scan-14.c

+/* { dg-require-effective-target size32plus } */
+/* { dg-additional-options "-O2 -fopenmp -fdump-tree-vect-details" } */
+/* { dg-additional-options "-mavx" { target avx_runtime } } */
+/* { dg-final { scan-tree-dump-times "vectorized \[2-6] loops" 2 "vect" { target sse2_runtime } } } */
+
+extern void abort (void);
+int r, a[1024], b[1024];
+unsigned short r2, b2[1024];
+unsigned char r3, b3[1024];
+
+__attribute__((noipa)) void
+foo (int *a, int *b, unsigned short *b2, unsigned char *b3)
+{
+  #pragma omp for simd reduction (inscan, +:r, r2, r3) if (simd:0)
+  for (int i = 0; i < 1024; i++)
+    {
+      { r += a[i]; r2 += a[i]; r3 += a[i]; }
+      #pragma omp scan inclusive(r, r2, r3)
+      {
+	b[i] = r;
+	b2[i] = r2;
+	b3[i] = r3;
+      }
+    }
+}
+
+__attribute__((noipa)) int
+bar (unsigned short *s2p, unsigned char *s3p)
+{
+  int s = 0;
+  unsigned short s2 = 0;
+  unsigned char s3 = 0;
+  #pragma omp parallel
+  #pragma omp for simd reduction (inscan, +:s, s2, s3) simdlen (1)
+  for (int i = 0; i < 1024; i++)
+    {
+      {
+	s += 2 * a[i];
+	s2 += 2 * a[i];
+	s3 += 2 * a[i];
+      }
+      #pragma omp scan inclusive(s, s2, s3)
+      { b[i] = s; b2[i] = s2; b3[i] = s3; }
+    }
+  *s2p = s2;
+  *s3p = s3;
+  return s;
+}
+
+__attribute__((noipa)) void
+baz (int *a, int *b, unsigned short *b2, unsigned char *b3)
+{
+  #pragma omp parallel for simd reduction (inscan, +:r, r2, r3)
+  for (int i = 0; i < 1024; i++)
+    {
+      {
+	r += a[i];
+	r2 += a[i];
+	r3 += a[i];
+      }
+      #pragma omp scan inclusive(r, r2, r3)
+      {
+	b[i] = r;
+	b2[i] = r2;
+	b3[i] = r3;
+      }
+    }
+}
+
+__attribute__((noipa)) int
+qux (unsigned short *s2p, unsigned char *s3p)
+{
+  int s = 0;
+  unsigned short s2 = 0;
+  unsigned char s3 = 0;
+  #pragma omp parallel for simd reduction (inscan, +:s, s2, s3)
+  for (int i = 0; i < 1024; i++)
+    {
+      { s += 2 * a[i]; s2 += 2 * a[i]; s3 += 2 * a[i]; }
+      #pragma omp scan inclusive(s, s2, s3)
+      { b[i] = s; b2[i] = s2; b3[i] = s3; }
+    }
+  *s2p = s2;
+  *s3p = s3;
+  return s;
+}
+
+int
+main ()
+{
+  int s = 0;
+  unsigned short s2;
+  unsigned char s3;
+  for (int i = 0; i < 1024; ++i)
+    {
+      a[i] = i;
+      b[i] = -1;
+      b2[i] = -1;
+      b3[i] = -1;
+      asm ("" : "+g" (i));
+    }
+  #pragma omp parallel
+  foo (a, b, b2, b3);
+  if (r != 1024 * 1023 / 2
+      || r2 != (unsigned short) r
+      || r3 != (unsigned char) r)
+    abort ();
+  for (int i = 0; i < 1024; ++i)
+    {
+      s += i;
+      if (b[i] != s
+	  || b2[i] != (unsigned short) s
+	  || b3[i] != (unsigned char) s)
+	abort ();
+      else
+	{
+	  b[i] = 25;
+	  b2[i] = 24;
+	  b3[i] = 26;
+	}
+    }
+  if (bar (&s2, &s3) != 1024 * 1023)
+    abort ();
+  if (s2 != (unsigned short) (1024 * 1023)
+      || s3 != (unsigned char) (1024 * 1023))
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      s += 2 * i;
+      if (b[i] != s
+	  || b2[i] != (unsigned short) s
+	  || b3[i] != (unsigned char) s)
+	abort ();
+      else
+	{
+	  b[i] = -1;
+	  b2[i] = -1;
+	  b3[i] = -1;
+	}
+    }
+  r = 0;
+  r2 = 0;
+  r3 = 0;
+  baz (a, b, b2, b3);
+  if (r != 1024 * 1023 / 2
+      || r2 != (unsigned short) r
+      || r3 != (unsigned char) r)
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      s += i;
+      if (b[i] != s
+	  || b2[i] != (unsigned short) s
+	  || b3[i] != (unsigned char) s)
+	abort ();
+      else
+	{
+	  b[i] = 25;
+	  b2[i] = 24;
+	  b3[i] = 26;
+	}
+    }
+  s2 = 0;
+  s3 = 0;
+  if (qux (&s2, &s3) != 1024 * 1023)
+    abort ();
+  if (s2 != (unsigned short) (1024 * 1023)
+      || s3 != (unsigned char) (1024 * 1023))
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      s += 2 * i;
+      if (b[i] != s
+	  || b2[i] != (unsigned short) s
+	  || b3[i] != (unsigned char) s)
+	abort ();
+    }
+  return 0;
+}

libgomp/testsuite/libgomp.c/scan-15.c

+/* { dg-require-effective-target size32plus } */
+/* { dg-additional-options "-O2 -fopenmp -fdump-tree-vect-details" } */
+/* { dg-additional-options "-mavx" { target avx_runtime } } */
+/* { dg-final { scan-tree-dump-times "vectorized \[2-6] loops" 2 "vect" { target sse2_runtime } } } */
+
+extern void abort (void);
+int r, a[1024], b[1024];
+
+__attribute__((noipa)) void
+foo (int *a, int *b)
+{
+  #pragma omp for simd reduction (inscan, +:r)
+  for (int i = 0; i < 1024; i++)
+    {
+      b[i] = r;
+      #pragma omp scan exclusive(r)
+      r += a[i];
+    }
+}
+
+__attribute__((noipa)) int
+bar (void)
+{
+  int s = 0;
+  #pragma omp parallel
+  #pragma omp for simd reduction (inscan, +:s)
+  for (int i = 0; i < 1024; i++)
+    {
+      b[i] = s;
+      #pragma omp scan exclusive(s)
+      s += 2 * a[i];
+    }
+  return s;
+}
+
+__attribute__((noipa)) void
+baz (int *a, int *b)
+{
+  #pragma omp parallel for simd simdlen (1) reduction (inscan, +:r)
+  for (int i = 0; i < 1024; i++)
+    {
+      b[i] = r;
+      #pragma omp scan exclusive(r)
+      r += a[i];
+    }
+}
+
+__attribute__((noipa)) int
+qux (void)
+{
+  int s = 0;
+  #pragma omp parallel for simd if (simd: 0) reduction (inscan, +:s)
+  for (int i = 0; i < 1024; i++)
+    {
+      b[i] = s;
+      #pragma omp scan exclusive(s)
+      s += 2 * a[i];
+    }
+  return s;
+}
+
+int
+main ()
+{
+  int s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      a[i] = i;
+      b[i] = -1;
+      asm ("" : "+g" (i));
+    }
+  #pragma omp parallel
+  foo (a, b);
+  if (r != 1024 * 1023 / 2)
+    abort ();
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i] != s)
+	abort ();
+      else
+	b[i] = 25;
+      s += i;
+    }
+  if (bar () != 1024 * 1023)
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i] != s)
+	abort ();
+      else
+	b[i] = -1;
+      s += 2 * i;
+    }
+  r = 0;
+  baz (a, b);
+  if (r != 1024 * 1023 / 2)
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i] != s)
+	abort ();
+      else
+	b[i] = -25;
+      s += i;
+    }
+  if (qux () != 1024 * 1023)
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i] != s)
+	abort ();
+      s += 2 * i;
+    }
+  return 0;
+}

libgomp/testsuite/libgomp.c/scan-16.c

+/* { dg-require-effective-target size32plus } */
+/* { dg-additional-options "-O2 -fopenmp -fdump-tree-vect-details" } */
+/* { dg-additional-options "-mavx" { target avx_runtime } } */
+/* { dg-final { scan-tree-dump-times "vectorized \[2-6] loops" 2 "vect" { target sse2_runtime } } } */
+
+extern void abort (void);
+int r, a[1024], b[1024];
+
+#pragma omp declare reduction (foo: int: omp_out += omp_in) initializer (omp_priv = 0)
+
+__attribute__((noipa)) void
+foo (int *a, int *b)
+{
+  #pragma omp for simd reduction (inscan, foo:r)
+  for (int i = 0; i < 1024; i++)
+    {
+      b[i] = r;
+      #pragma omp scan exclusive(r)
+      r += a[i];
+    }
+}
+
+__attribute__((noipa)) int
+bar (void)
+{
+  int s = 0;
+  #pragma omp parallel
+  #pragma omp for simd simdlen (1) reduction (inscan, foo:s)
+  for (int i = 0; i < 1024; i++)
+    {
+      b[i] = s;
+      #pragma omp scan exclusive(s)
+      s += 2 * a[i];
+    }
+  return s;
+}
+
+__attribute__((noipa)) void
+baz (int *a, int *b)
+{
+  #pragma omp parallel for simd if (simd: 0) reduction (inscan, foo:r)
+  for (int i = 0; i < 1024; i++)
+    {
+      b[i] = r;
+      #pragma omp scan exclusive(r)
+      r += a[i];
+    }
+}
+
+__attribute__((noipa)) int
+qux (void)
+{
+  int s = 0;
+  #pragma omp parallel for simd reduction (inscan, foo:s)
+  for (int i = 0; i < 1024; i++)
+    {
+      b[i] = s;
+      #pragma omp scan exclusive(s)
+      s += 2 * a[i];
+    }
+  return s;
+}
+
+int
+main ()
+{
+  int s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      a[i] = i;
+      b[i] = -1;
+      asm ("" : "+g" (i));
+    }
+  #pragma omp parallel
+  foo (a, b);
+  if (r != 1024 * 1023 / 2)
+    abort ();
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i] != s)
+	abort ();
+      else
+	b[i] = 25;
+      s += i;
+    }
+  if (bar () != 1024 * 1023)
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i] != s)
+	abort ();
+      else
+	b[i] = -1;
+      s += 2 * i;
+    }
+  r = 0;
+  baz (a, b);
+  if (r != 1024 * 1023 / 2)
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i] != s)
+	abort ();
+      else
+	b[i] = -25;
+      s += i;
+    }
+  if (qux () != 1024 * 1023)
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i] != s)
+	abort ();
+      s += 2 * i;
+    }
+  return 0;
+}

libgomp/testsuite/libgomp.c/scan-17.c

+/* { dg-require-effective-target size32plus } */
+/* { dg-additional-options "-O2 -fopenmp -fdump-tree-vect-details" } */
+/* { dg-additional-options "-mavx" { target avx_runtime } } */
+/* { dg-final { scan-tree-dump-times "vectorized \[2-6] loops" 2 "vect" { target sse2_runtime } } } */
+
+extern void abort (void);
+float r = 1.0f, a[1024], b[1024];
+
+__attribute__((noipa)) void
+foo (float *a, float *b)
+{
+  #pragma omp for simd reduction (inscan, *:r)
+  for (int i = 0; i < 1024; i++)
+    {
+      b[i] = r;
+      #pragma omp scan exclusive(r)
+      r *= a[i];
+    }
+}
+
+__attribute__((noipa)) float
+bar (void)
+{
+  float s = -__builtin_inff ();
+  #pragma omp parallel for simd reduction (inscan, max:s)
+  for (int i = 0; i < 1024; i++)
+    {
+      b[i] = s;
+      #pragma omp scan exclusive(s)
+      s = s > a[i] ? s : a[i];
+    }
+  return s;
+}
+
+int
+main ()
+{
+  float s = 1.0f;
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (i < 80)
+	a[i] = (i & 1) ? 0.25f : 0.5f;
+      else if (i < 200)
+	a[i] = (i % 3) == 0 ? 2.0f : (i % 3) == 1 ? 4.0f : 1.0f;
+      else if (i < 280)
+	a[i] = (i & 1) ? 0.25f : 0.5f;
+      else if (i < 380)
+	a[i] = (i % 3) == 0 ? 2.0f : (i % 3) == 1 ? 4.0f : 1.0f;
+      else
+	switch (i % 6)
+	  {
+	  case 0: a[i] = 0.25f; break;
+	  case 1: a[i] = 2.0f; break;
+	  case 2: a[i] = -1.0f; break;
+	  case 3: a[i] = -4.0f; break;
+	  case 4: a[i] = 0.5f; break;
+	  case 5: a[i] = 1.0f; break;
+	  default: a[i] = 0.0f; break;
+	  }
+      b[i] = -19.0f;
+      asm ("" : "+g" (i));
+    }
+  #pragma omp parallel
+  foo (a, b);
+  if (r * 16384.0f != 0.125f)
+    abort ();
+  float m = -175.25f;
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i] != s)
+	abort ();
+      else
+	b[i] = -231.75f;
+      s *= a[i];
+      a[i] = m - ((i % 3) == 1 ? 2.0f : (i % 3) == 2 ? 4.0f : 0.0f);
+      m += 0.75f;
+    }
+  if (bar () != 592.0f)
+    abort ();
+  s = -__builtin_inff ();
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i] != s)
+	abort ();
+      if (s < a[i])
+	s = a[i];
+    }
+  return 0;
+}

libgomp/testsuite/libgomp.c/scan-18.c

+/* { dg-require-effective-target size32plus } */
+/* { dg-additional-options "-O2 -fopenmp -fdump-tree-vect-details" } */
+/* { dg-additional-options "-mavx" { target avx_runtime } } */
+/* { dg-final { scan-tree-dump-times "vectorized \[2-6] loops" 2 "vect" { target sse2_runtime } } } */
+
+extern void abort (void);
+int r, a[1024], b[1024];
+unsigned short r2, b2[1024];
+unsigned char r3, b3[1024];
+
+__attribute__((noipa)) void
+foo (int *a, int *b, unsigned short *b2, unsigned char *b3)
+{
+  #pragma omp for simd reduction (inscan, +:r, r2, r3)
+  for (int i = 0; i < 1024; i++)
+    {
+      {
+	b[i] = r;
+	b2[i] = r2;
+	b3[i] = r3;
+      }
+      #pragma omp scan exclusive(r, r2, r3)
+      { r += a[i]; r2 += a[i]; r3 += a[i]; }
+    }
+}
+
+__attribute__((noipa)) int
+bar (unsigned short *s2p, unsigned char *s3p)
+{
+  int s = 0;
+  unsigned short s2 = 0;
+  unsigned char s3 = 0;
+  #pragma omp parallel
+  #pragma omp for simd reduction (inscan, +:s, s2, s3)
+  for (int i = 0; i < 1024; i++)
+    {
+      { b[i] = s; b2[i] = s2; b3[i] = s3; }
+      #pragma omp scan exclusive(s, s2, s3)
+      {
+	s += 2 * a[i];
+	s2 += 2 * a[i];
+	s3 += 2 * a[i];
+      }
+    }
+  *s2p = s2;
+  *s3p = s3;
+  return s;
+}
+
+__attribute__((noipa)) void
+baz (int *a, int *b, unsigned short *b2, unsigned char *b3)
+{
+  #pragma omp parallel for simd reduction (inscan, +:r, r2, r3) if (simd: 0)
+  for (int i = 0; i < 1024; i++)
+    {
+      {
+	b[i] = r;
+	b2[i] = r2;
+	b3[i] = r3;
+      }
+      #pragma omp scan exclusive(r, r2, r3)
+      {
+	r += a[i];
+	r2 += a[i];
+	r3 += a[i];
+      }
+    }
+}
+
+__attribute__((noipa)) int
+qux (unsigned short *s2p, unsigned char *s3p)
+{
+  int s = 0;
+  unsigned short s2 = 0;
+  unsigned char s3 = 0;
+  #pragma omp parallel for simd simdlen (1) reduction (inscan, +:s, s2, s3)
+  for (int i = 0; i < 1024; i++)
+    {
+      { b[i] = s; b2[i] = s2; b3[i] = s3; }
+      #pragma omp scan exclusive(s, s2, s3)
+      { s += 2 * a[i]; s2 += 2 * a[i]; s3 += 2 * a[i]; }
+    }
+  *s2p = s2;
+  *s3p = s3;
+  return s;
+}
+
+int
+main ()
+{
+  int s = 0;
+  unsigned short s2;
+  unsigned char s3;
+  for (int i = 0; i < 1024; ++i)
+    {
+      a[i] = i;
+      b[i] = -1;
+      b2[i] = -1;
+      b3[i] = -1;
+      asm ("" : "+g" (i));
+    }
+  #pragma omp parallel
+  foo (a, b, b2, b3);
+  if (r != 1024 * 1023 / 2
+      || r2 != (unsigned short) r
+      || r3 != (unsigned char) r)
+    abort ();
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i] != s
+	  || b2[i] != (unsigned short) s
+	  || b3[i] != (unsigned char) s)
+	abort ();
+      else
+	{
+	  b[i] = 25;
+	  b2[i] = 24;
+	  b3[i] = 26;
+	}
+      s += i;
+    }
+  if (bar (&s2, &s3) != 1024 * 1023)
+    abort ();
+  if (s2 != (unsigned short) (1024 * 1023)
+      || s3 != (unsigned char) (1024 * 1023))
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i] != s
+	  || b2[i] != (unsigned short) s
+	  || b3[i] != (unsigned char) s)
+	abort ();
+      else
+	{
+	  b[i] = -1;
+	  b2[i] = -1;
+	  b3[i] = -1;
+	}
+      s += 2 * i;
+    }
+  r = 0;
+  r2 = 0;
+  r3 = 0;
+  baz (a, b, b2, b3);
+  if (r != 1024 * 1023 / 2
+      || r2 != (unsigned short) r
+      || r3 != (unsigned char) r)
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i] != s
+	  || b2[i] != (unsigned short) s
+	  || b3[i] != (unsigned char) s)
+	abort ();
+      else
+	{
+	  b[i] = 25;
+	  b2[i] = 24;
+	  b3[i] = 26;
+	}
+      s += i;
+    }
+  s2 = 0;
+  s3 = 0;
+  if (qux (&s2, &s3) != 1024 * 1023)
+    abort ();
+  if (s2 != (unsigned short) (1024 * 1023)
+      || s3 != (unsigned char) (1024 * 1023))
+    abort ();
+  s = 0;
+  for (int i = 0; i < 1024; ++i)
+    {
+      if (b[i] != s
+	  || b2[i] != (unsigned short) s
+	  || b3[i] != (unsigned char) s)
+	abort ();
+      s += 2 * i;
+    }
+  return 0;
+}