gimplify.c (gimplify_omp_for): For #pragma omp for simd iterator not mentioned in clauses use private clause if...

* gimplify.c (gimplify_omp_for): For #pragma omp for simd iterator
	not mentioned in clauses use private clause if the iterator is
	declared in #pragma omp for simd, and when adding lastprivate
	instead, add it to the outer #pragma omp for too.  Diagnose
	if the variable is private in outer context.  For simd collapse > 1
	loops, replace all iterators with temporaries.
	* omp-low.c (lower_rec_input_clauses): Handle LINEAR clause the
	same even in collapse > 1 loops.
gcc/c/
	* c-parser.c (c_parser_omp_for_loop): For
	#pragma omp parallel for simd move lastprivate clause from parallel
	to for rather than simd.
gcc/cp/
	* parser.c (cp_parser_omp_for_loop): For
	#pragma omp parallel for simd move lastprivate clause from parallel
	to for rather than simd.
libgomp/
	* testsuite/libgomp.c/for-2.c: Define SC to static for
	#pragma omp for simd testing.
	* testsuite/libgomp.c/for-2.h (SC): Define if not defined.
	(N(f5), N(f6), N(f7), N(f8), N(f10), N(f12), N(f14)): Use
	SC macro.
	* testsuite/libgomp.c/simd-14.c: New test.
	* testsuite/libgomp.c/simd-15.c: New test.
	* testsuite/libgomp.c/simd-16.c: New test.
	* testsuite/libgomp.c/simd-17.c: New test.
	* testsuite/libgomp.c++/for-10.C: Define SC to static for
	#pragma omp for simd testing.
	* testsuite/libgomp.c++/simd10.C: New test.
	* testsuite/libgomp.c++/simd11.C: New test.
	* testsuite/libgomp.c++/simd12.C: New test.
	* testsuite/libgomp.c++/simd13.C: New test.

From-SVN: r211930

gcc/ChangeLog

@@ -1,5 +1,14 @@
 2014-06-24  Jakub Jelinek  <jakub@redhat.com>
 
+	* gimplify.c (gimplify_omp_for): For #pragma omp for simd iterator
+	not mentioned in clauses use private clause if the iterator is
+	declared in #pragma omp for simd, and when adding lastprivate
+	instead, add it to the outer #pragma omp for too.  Diagnose
+	if the variable is private in outer context.  For simd collapse > 1
+	loops, replace all iterators with temporaries.
+	* omp-low.c (lower_rec_input_clauses): Handle LINEAR clause the
+	same even in collapse > 1 loops.
+
 	* gimplify.c (gimplify_scan_omp_clauses) <case OMP_CLAUSE_MAP,
 	OMP_CLAUSE_TO, OMP_CLAUSE_FROM): Make sure OMP_CLAUSE_SIZE is
 	non-NULL.

gcc/c/ChangeLog

@@ -1,3 +1,9 @@
+2014-06-24  Jakub Jelinek  <jakub@redhat.com>
+
+	* c-parser.c (c_parser_omp_for_loop): For
+	#pragma omp parallel for simd move lastprivate clause from parallel
+	to for rather than simd.
+
 2014-06-23  Marek Polacek  <polacek@redhat.com>
 
 	* c-typeck.c (parser_build_binary_op): Don't call

gcc/c/c-parser.c

@@ -11910,8 +11910,17 @@ c_parser_omp_for_loop (location_t loc, c_parser *parser, enum tree_code code,
 			tree l = build_omp_clause (OMP_CLAUSE_LOCATION (*c),
 						   OMP_CLAUSE_LASTPRIVATE);
 			OMP_CLAUSE_DECL (l) = OMP_CLAUSE_DECL (*c);
+			if (code == OMP_SIMD)
+			  {
+			    OMP_CLAUSE_CHAIN (l)
+			      = cclauses[C_OMP_CLAUSE_SPLIT_FOR];
+			    cclauses[C_OMP_CLAUSE_SPLIT_FOR] = l;
+			  }
+			else
+			  {
 			    OMP_CLAUSE_CHAIN (l) = clauses;
 			    clauses = l;
+			  }
 			OMP_CLAUSE_SET_CODE (*c, OMP_CLAUSE_SHARED);
 		      }
 		  }

gcc/cp/ChangeLog

@@ -1,3 +1,9 @@
+2014-06-24  Jakub Jelinek  <jakub@redhat.com>
+
+	* parser.c (cp_parser_omp_for_loop): For
+	#pragma omp parallel for simd move lastprivate clause from parallel
+	to for rather than simd.
+
 2014-06-23  Paolo Carlini  <paolo.carlini@oracle.com>
 
 	DR 577

gcc/cp/parser.c

@@ -29418,9 +29418,17 @@ cp_parser_omp_for_loop (cp_parser *parser, enum tree_code code, tree clauses,
 		   change it to shared (decl) in OMP_PARALLEL_CLAUSES.  */
 		tree l = build_omp_clause (loc, OMP_CLAUSE_LASTPRIVATE);
 		OMP_CLAUSE_DECL (l) = real_decl;
-		OMP_CLAUSE_CHAIN (l) = clauses;
 		CP_OMP_CLAUSE_INFO (l) = CP_OMP_CLAUSE_INFO (*c);
+		if (code == OMP_SIMD)
+		  {
+		    OMP_CLAUSE_CHAIN (l) = cclauses[C_OMP_CLAUSE_SPLIT_FOR];
+		    cclauses[C_OMP_CLAUSE_SPLIT_FOR] = l;
+		  }
+		else
+		  {
+		    OMP_CLAUSE_CHAIN (l) = clauses;
 		    clauses = l;
+		  }
 		OMP_CLAUSE_SET_CODE (*c, OMP_CLAUSE_SHARED);
 		CP_OMP_CLAUSE_INFO (*c) = NULL;
 		add_private_clause = false;

gcc/gimplify.c

@@ -6810,6 +6810,31 @@ gimplify_omp_for (tree *expr_p, gimple_seq *pre_p)
 	      bool lastprivate
 		= (!has_decl_expr
 		   || !bitmap_bit_p (has_decl_expr, DECL_UID (decl)));
+	      if (lastprivate
+		  && gimplify_omp_ctxp->outer_context
+		  && gimplify_omp_ctxp->outer_context->region_type
+		     == ORT_WORKSHARE
+		  && gimplify_omp_ctxp->outer_context->combined_loop
+		  && !gimplify_omp_ctxp->outer_context->distribute)
+		{
+		  struct gimplify_omp_ctx *outer
+		    = gimplify_omp_ctxp->outer_context;
+		  n = splay_tree_lookup (outer->variables,
+					 (splay_tree_key) decl);
+		  if (n != NULL
+		      && (n->value & GOVD_DATA_SHARE_CLASS) == GOVD_LOCAL)
+		    lastprivate = false;
+		  else if (omp_check_private (outer, decl, false))
+		    error ("lastprivate variable %qE is private in outer "
+			   "context", DECL_NAME (decl));
+		  else
+		    {
+		      omp_add_variable (outer, decl,
+					GOVD_LASTPRIVATE | GOVD_SEEN);
+		      if (outer->outer_context)
+			omp_notice_variable (outer->outer_context, decl, true);
+		    }
+		}
 	      c = build_omp_clause (input_location,
 				    lastprivate ? OMP_CLAUSE_LASTPRIVATE
 						: OMP_CLAUSE_PRIVATE);
@@ -6829,10 +6854,13 @@ gimplify_omp_for (tree *expr_p, gimple_seq *pre_p)
 
       /* If DECL is not a gimple register, create a temporary variable to act
 	 as an iteration counter.  This is valid, since DECL cannot be
-	 modified in the body of the loop.  */
+	 modified in the body of the loop.  Similarly for any iteration vars
+	 in simd with collapse > 1 where the iterator vars must be
+	 lastprivate.  */
       if (orig_for_stmt != for_stmt)
 	var = decl;
-      else if (!is_gimple_reg (decl))
+      else if (!is_gimple_reg (decl)
+	       || (simd && TREE_VEC_LENGTH (OMP_FOR_INIT (for_stmt)) > 1))
 	{
 	  var = create_tmp_var (TREE_TYPE (decl), get_name (decl));
 	  TREE_OPERAND (t, 0) = var;

gcc/omp-low.c

@@ -3421,8 +3421,6 @@ lower_rec_input_clauses (tree clauses, gimple_seq *ilist, gimple_seq *dlist,
 						OMP_CLAUSE__LOOPTEMP_);
 		      gcc_assert (c);
 		      tree l = OMP_CLAUSE_DECL (c);
-		      if (fd->collapse == 1)
-			{
 		      tree n1 = fd->loop.n1;
 		      tree step = fd->loop.step;
 		      tree itype = TREE_TYPE (l);
@@ -3432,13 +3430,11 @@ lower_rec_input_clauses (tree clauses, gimple_seq *ilist, gimple_seq *dlist,
 		      if (TYPE_UNSIGNED (itype)
 			  && fd->loop.cond_code == GT_EXPR)
 			l = fold_build2 (TRUNC_DIV_EXPR, itype,
-					     fold_build1 (NEGATE_EXPR,
+					 fold_build1 (NEGATE_EXPR, itype, l),
-							  itype, l),
 					 fold_build1 (NEGATE_EXPR,
 						      itype, step));
 		      else
 			l = fold_build2 (TRUNC_DIV_EXPR, itype, l, step);
-			}
 		      t = fold_build2 (MULT_EXPR, stept,
 				       fold_convert (stept, l), t);
 		      if (POINTER_TYPE_P (TREE_TYPE (x)))

libgomp/ChangeLog

@@ -1,5 +1,21 @@
 2014-06-24  Jakub Jelinek  <jakub@redhat.com>
 
+	* testsuite/libgomp.c/for-2.c: Define SC to static for
+	#pragma omp for simd testing.
+	* testsuite/libgomp.c/for-2.h (SC): Define if not defined.
+	(N(f5), N(f6), N(f7), N(f8), N(f10), N(f12), N(f14)): Use
+	SC macro.
+	* testsuite/libgomp.c/simd-14.c: New test.
+	* testsuite/libgomp.c/simd-15.c: New test.
+	* testsuite/libgomp.c/simd-16.c: New test.
+	* testsuite/libgomp.c/simd-17.c: New test.
+	* testsuite/libgomp.c++/for-10.C: Define SC to static for
+	#pragma omp for simd testing.
+	* testsuite/libgomp.c++/simd10.C: New test.
+	* testsuite/libgomp.c++/simd11.C: New test.
+	* testsuite/libgomp.c++/simd12.C: New test.
+	* testsuite/libgomp.c++/simd13.C: New test.
+
 	* testsuite/libgomp.fortran/aligned1.f03: New test.
 	* testsuite/libgomp.fortran/nestedfn5.f90: New test.
 	* testsuite/libgomp.fortran/target7.f90: Surround loop spawning

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

@@ -19,11 +19,14 @@ extern "C" void abort ();
 #undef F
 #undef G
 
+#undef SC
+#define SC static
 #define F for simd
 #define G f_simd
 #include "../libgomp.c/for-1.h"
 #undef F
 #undef G
+#undef SC
 
 int
 main ()

libgomp/testsuite/libgomp.c++/simd10.C

@@ -0,0 +1,6 @@
+// { dg-do run }
+// { dg-options "-O2" }
+// { dg-additional-options "-msse2" { target sse2_runtime } }
+// { dg-additional-options "-mavx" { target avx_runtime } }
+
+#include "../libgomp.c/simd-14.c"

libgomp/testsuite/libgomp.c++/simd11.C

@@ -0,0 +1,6 @@
+// { dg-do run }
+// { dg-options "-O2" }
+// { dg-additional-options "-msse2" { target sse2_runtime } }
+// { dg-additional-options "-mavx" { target avx_runtime } }
+
+#include "../libgomp.c/simd-15.c"

libgomp/testsuite/libgomp.c++/simd12.C

@@ -0,0 +1,6 @@
+// { dg-do run }
+// { dg-options "-O2" }
+// { dg-additional-options "-msse2" { target sse2_runtime } }
+// { dg-additional-options "-mavx" { target avx_runtime } }
+
+#include "../libgomp.c/simd-16.c"

libgomp/testsuite/libgomp.c++/simd13.C

@@ -0,0 +1,6 @@
+// { dg-do run }
+// { dg-options "-O2" }
+// { dg-additional-options "-msse2" { target sse2_runtime } }
+// { dg-additional-options "-mavx" { target avx_runtime } }
+
+#include "../libgomp.c/simd-17.c"

libgomp/testsuite/libgomp.c/for-2.c

@@ -21,11 +21,14 @@ extern void abort (void);
 #undef F
 #undef G
 
+#undef SC
+#define SC static
 #define F for simd
 #define G f_simd
 #include "for-1.h"
 #undef F
 #undef G
+#undef SC
 
 int
 main ()

libgomp/testsuite/libgomp.c/for-2.h

@@ -8,6 +8,9 @@ noreturn (void)
   for (;;);
 }
 #endif
+#ifndef SC
+#define SC
+#endif
 
 __attribute__((noinline, noclone)) void
 N(f0) (void)
@@ -57,7 +60,7 @@ __attribute__((noinline, noclone)) void
 N(f5) (int n11, int n12, int n21, int n22, int n31, int n32,
        int s1, int s2, int s3)
 {
-  int v1, v2, v3;
+  SC int v1, v2, v3;
 #pragma omp F S collapse(3)
   for (v1 = n11; v1 < n12; v1 += s1)
     for (v2 = n21; v2 < n22; v2 += s2)
@@ -69,8 +72,8 @@ __attribute__((noinline, noclone)) void
 N(f6) (int n11, int n12, int n21, int n22, long long n31, long long n32,
        int s1, int s2, long long int s3)
 {
-  int v1, v2;
+  SC int v1, v2;
-  long long v3;
+  SC long long v3;
 #pragma omp F S collapse(3)
   for (v1 = n11; v1 > n12; v1 += s1)
     for (v2 = n21; v2 > n22; v2 += s2)
@@ -81,8 +84,8 @@ N(f6) (int n11, int n12, int n21, int n22, long long n31, long long n32,
 __attribute__((noinline, noclone)) void
 N(f7) (void)
 {
-  unsigned int v1, v3;
+  SC unsigned int v1, v3;
-  unsigned long long v2;
+  SC unsigned long long v2;
 #pragma omp F S collapse(3)
   for (v1 = 0; v1 < 20; v1 += 2)
     for (v2 = __LONG_LONG_MAX__ + 16ULL;
@@ -94,7 +97,7 @@ N(f7) (void)
 __attribute__((noinline, noclone)) void
 N(f8) (void)
 {
-  long long v1, v2, v3;
+  SC long long v1, v2, v3;
 #pragma omp F S collapse(3)
   for (v1 = 0; v1 < 20; v1 += 2)
     for (v2 = 30; v2 < 20; v2++)
@@ -118,7 +121,7 @@ N(f9) (void)
 __attribute__((noinline, noclone)) void
 N(f10) (void)
 {
-  int i;
+  SC int i;
 #pragma omp F S collapse(3)
   for (i = 0; i < 10; i++)
     for (int j = 10; j < 8; j++)
@@ -146,7 +149,7 @@ N(f11) (int n)
 __attribute__((noinline, noclone)) void
 N(f12) (int n)
 {
-  int i;
+  SC int i;
 #pragma omp F S collapse(3)
   for (i = 0; i < 10; i++)
     for (int j = n; j < 8; j++)
@@ -170,7 +173,7 @@ N(f13) (void)
 __attribute__((noinline, noclone)) void
 N(f14) (void)
 {
-  float *i;
+  SC float *i;
 #pragma omp F S collapse(3)
   for (i = &b[0][0][0]; i < &b[0][0][10]; i++)
     for (float *j = &b[0][15][0]; j > &b[0][0][0]; j -= 10)

libgomp/testsuite/libgomp.c/simd-14.c

@@ -0,0 +1,123 @@
+/* { dg-do run } */
+/* { dg-options "-O2" } */
+/* { dg-additional-options "-msse2" { target sse2_runtime } } */
+/* { dg-additional-options "-mavx" { target avx_runtime } } */
+
+int
+main ()
+{
+  int i, j, b, c = 0;
+  i = 4; j = 4; b = 7;
+  #pragma omp simd linear(b:2) reduction(+:c)
+  for (i = 0; i < 64; i++)
+    {
+      c = c + (b != 7 + 2 * i);
+      b = b + 2;
+    }
+  if (c || i != 64 || b != 7 + 64 * 2)
+    __builtin_abort ();
+  i = 4; j = 4; b = 7;
+  #pragma omp simd linear(b:3) reduction(+:c)
+  for (i = 0; i < 64; i += 4)
+    {
+      c = c + (b != 7 + i / 4 * 3);
+      b = b + 3;
+    }
+  if (c || i != 64 || b != 7 + 16 * 3)
+    __builtin_abort ();
+  i = 4; j = 4; b = 7;
+  #pragma omp simd linear(i) linear(b:2) reduction(+:c)
+  for (i = 0; i < 64; i++)
+    {
+      c = c + (b != 7 + 2 * i);
+      b = b + 2;
+    }
+  if (c || i != 64 || b != 7 + 64 * 2)
+    __builtin_abort ();
+  i = 4; j = 4; b = 7;
+  #pragma omp simd linear(i:4) linear(b:3) reduction(+:c)
+  for (i = 0; i < 64; i += 4)
+    {
+      c = c + (b != 7 + i / 4 * 3);
+      b = b + 3;
+    }
+  if (c || i != 64 || b != 7 + 16 * 3)
+    __builtin_abort ();
+  i = 4; j = 4; b = 7;
+  #pragma omp simd collapse (2) linear(b:2) reduction(+:c)
+  for (i = 0; i < 8; i++)
+    for (j = 0; j < 8; j++)
+      {
+	c = c + (b != 7 + 2 * j + 2 * 8 * i);
+	b = b + 2;
+      }
+  if (c || i != 8 || j != 8 || b != 7 + 64 * 2)
+    __builtin_abort ();
+  i = 4; j = 4; b = 7;
+  #pragma omp simd collapse (2) lastprivate (i, j) linear(b:2) reduction(+:c)
+  for (i = 0; i < 8; i++)
+    for (j = 0; j < 8; j++)
+      {
+	c = c + (b != 7 + 2 * j + 2 * 8 * i);
+	b = b + 2;
+      }
+  if (c || i != 8 || j != 8 || b != 7 + 64 * 2)
+    __builtin_abort ();
+  i = 4; j = 4; b = 7;
+  #pragma omp parallel for simd schedule (static, 4) linear(b:2) reduction(+:c)
+  for (i = 0; i < 64; i++)
+    {
+      c = c + (b != 7 + 2 * i);
+      b = b + 2;
+    }
+  if (c || i != 64 || b != 7 + 64 * 2)
+    __builtin_abort ();
+  i = 4; j = 4; b = 7;
+  #pragma omp parallel for simd schedule (static, 4) linear(b:3) reduction(+:c)
+  for (i = 0; i < 64; i += 4)
+    {
+      c = c + (b != 7 + i / 4 * 3);
+      b = b + 3;
+    }
+  if (c || i != 64 || b != 7 + 16 * 3)
+    __builtin_abort ();
+  i = 4; j = 4; b = 7;
+  #pragma omp parallel for simd schedule (static, 4) linear(i) linear(b:2) reduction(+:c)
+  for (i = 0; i < 64; i++)
+    {
+      c = c + (b != 7 + 2 * i);
+      b = b + 2;
+    }
+  if (c || i != 64 || b != 7 + 64 * 2)
+    __builtin_abort ();
+  i = 4; j = 4; b = 7;
+  #pragma omp parallel for simd schedule (static, 4) linear(i:4) linear(b:3) reduction(+:c)
+  for (i = 0; i < 64; i += 4)
+    {
+      c = c + (b != 7 + i / 4 * 3);
+      b = b + 3;
+    }
+  if (c || i != 64 || b != 7 + 16 * 3)
+    __builtin_abort ();
+  i = 4; j = 4; b = 7;
+  #pragma omp parallel for simd lastprivate (i, j) collapse (2) schedule (static, 4) linear(b:2) reduction(+:c)
+  for (i = 0; i < 8; i++)
+    for (j = 0; j < 8; j++)
+      {
+	c = c + (b != 7 + 2 * j + 2 * 8 * i);
+	b = b + 2;
+      }
+  if (c || i != 8 || j != 8 || b != 7 + 64 * 2)
+    __builtin_abort ();
+  i = 4; j = 4; b = 7;
+  #pragma omp parallel for simd collapse (2) schedule (static, 4) linear(b:2) reduction(+:c)
+  for (i = 0; i < 8; i++)
+    for (j = 0; j < 8; j++)
+      {
+	c = c + (b != 7 + 2 * j + 2 * 8 * i);
+	b = b + 2;
+      }
+  if (c || i != 8 || j != 8 || b != 7 + 64 * 2)
+    __builtin_abort ();
+  return 0;
+}

libgomp/testsuite/libgomp.c/simd-15.c

@@ -0,0 +1,129 @@
+/* { dg-do run } */
+/* { dg-options "-O2" } */
+/* { dg-additional-options "-msse2" { target sse2_runtime } } */
+/* { dg-additional-options "-mavx" { target avx_runtime } } */
+
+static inline void
+foo (int *b, int *i, int *j, int x)
+{
+  *b = *b + x + (*i - *i) + (*j - *j);
+}
+
+int
+main ()
+{
+  int i, j, b, c = 0;
+  i = 4; j = 4; b = 7;
+  #pragma omp simd linear(b:2) reduction(+:c)
+  for (i = 0; i < 64; i++)
+    {
+      c = c + (b != 7 + 2 * i);
+      foo (&b, &i, &j, 2);
+    }
+  if (c || i != 64 || b != 7 + 64 * 2)
+    __builtin_abort ();
+  i = 4; j = 4; b = 7;
+  #pragma omp simd linear(b:3) reduction(+:c)
+  for (i = 0; i < 64; i += 4)
+    {
+      c = c + (b != 7 + i / 4 * 3);
+      foo (&b, &i, &j, 3);
+    }
+  if (c || i != 64 || b != 7 + 16 * 3)
+    __builtin_abort ();
+  i = 4; j = 4; b = 7;
+  #pragma omp simd linear(i) linear(b:2) reduction(+:c)
+  for (i = 0; i < 64; i++)
+    {
+      c = c + (b != 7 + 2 * i);
+      foo (&b, &i, &j, 2);
+    }
+  if (c || i != 64 || b != 7 + 64 * 2)
+    __builtin_abort ();
+  i = 4; j = 4; b = 7;
+  #pragma omp simd linear(i:4) linear(b:3) reduction(+:c)
+  for (i = 0; i < 64; i += 4)
+    {
+      c = c + (b != 7 + i / 4 * 3);
+      foo (&b, &i, &j, 3);
+    }
+  if (c || i != 64 || b != 7 + 16 * 3)
+    __builtin_abort ();
+  i = 4; j = 4; b = 7;
+  #pragma omp simd collapse (2) linear(b:2) reduction(+:c)
+  for (i = 0; i < 8; i++)
+    for (j = 0; j < 8; j++)
+      {
+	c = c + (b != 7 + 2 * j + 2 * 8 * i);
+	foo (&b, &i, &j, 2);
+      }
+  if (c || i != 8 || j != 8 || b != 7 + 64 * 2)
+    __builtin_abort ();
+  i = 4; j = 4; b = 7;
+  #pragma omp simd collapse (2) lastprivate (i, j) linear(b:2) reduction(+:c)
+  for (i = 0; i < 8; i++)
+    for (j = 0; j < 8; j++)
+      {
+	c = c + (b != 7 + 2 * j + 2 * 8 * i);
+	foo (&b, &i, &j, 2);
+      }
+  if (c || i != 8 || j != 8 || b != 7 + 64 * 2)
+    __builtin_abort ();
+  i = 4; j = 4; b = 7;
+  #pragma omp parallel for simd schedule (static, 4) linear(b:2) reduction(+:c)
+  for (i = 0; i < 64; i++)
+    {
+      c = c + (b != 7 + 2 * i);
+      foo (&b, &i, &j, 2);
+    }
+  if (c || i != 64 || b != 7 + 64 * 2)
+    __builtin_abort ();
+  i = 4; j = 4; b = 7;
+  #pragma omp parallel for simd schedule (static, 4) linear(b:3) reduction(+:c)
+  for (i = 0; i < 64; i += 4)
+    {
+      c = c + (b != 7 + i / 4 * 3);
+      foo (&b, &i, &j, 3);
+    }
+  if (c || i != 64 || b != 7 + 16 * 3)
+    __builtin_abort ();
+  i = 4; j = 4; b = 7;
+  #pragma omp parallel for simd schedule (static, 4) linear(i) linear(b:2) reduction(+:c)
+  for (i = 0; i < 64; i++)
+    {
+      c = c + (b != 7 + 2 * i);
+      foo (&b, &i, &j, 2);
+    }
+  if (c || i != 64 || b != 7 + 64 * 2)
+    __builtin_abort ();
+  i = 4; j = 4; b = 7;
+  #pragma omp parallel for simd schedule (static, 4) linear(i:4) linear(b:3) reduction(+:c)
+  for (i = 0; i < 64; i += 4)
+    {
+      c = c + (b != 7 + i / 4 * 3);
+      foo (&b, &i, &j, 3);
+    }
+  if (c || i != 64 || b != 7 + 16 * 3)
+    __builtin_abort ();
+  i = 4; j = 4; b = 7;
+  #pragma omp parallel for simd lastprivate (i, j) collapse (2) schedule (static, 4) linear(b:2) reduction(+:c)
+  for (i = 0; i < 8; i++)
+    for (j = 0; j < 8; j++)
+      {
+	c = c + (b != 7 + 2 * j + 2 * 8 * i);
+	foo (&b, &i, &j, 2);
+      }
+  if (c || i != 8 || j != 8 || b != 7 + 64 * 2)
+    __builtin_abort ();
+  i = 4; j = 4; b = 7;
+  #pragma omp parallel for simd collapse (2) schedule (static, 4) linear(b:2) reduction(+:c)
+  for (i = 0; i < 8; i++)
+    for (j = 0; j < 8; j++)
+      {
+	c = c + (b != 7 + 2 * j + 2 * 8 * i);
+	foo (&b, &i, &j, 2);
+      }
+  if (c || i != 8 || j != 8 || b != 7 + 64 * 2)
+    __builtin_abort ();
+  return 0;
+}

libgomp/testsuite/libgomp.c/simd-16.c

@@ -0,0 +1,67 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -std=c99" } */
+/* { dg-additional-options "-msse2" { target sse2_runtime } } */
+/* { dg-additional-options "-mavx" { target avx_runtime } } */
+
+int
+main ()
+{
+  int b, c = 0;
+  b = 7;
+  #pragma omp simd linear(b:2) reduction(+:c)
+  for (int i = 0; i < 64; i++)
+    {
+      c = c + (b != 7 + 2 * i);
+      b = b + 2;
+    }
+  if (c || b != 7 + 64 * 2)
+    __builtin_abort ();
+  b = 7;
+  #pragma omp simd linear(b:3) reduction(+:c)
+  for (int i = 0; i < 64; i += 4)
+    {
+      c = c + (b != 7 + i / 4 * 3);
+      b = b + 3;
+    }
+  if (c || b != 7 + 16 * 3)
+    __builtin_abort ();
+  b = 7;
+  #pragma omp simd collapse (2) linear(b:2) reduction(+:c)
+  for (int i = 0; i < 8; i++)
+    for (int j = 0; j < 8; j++)
+      {
+	c = c + (b != 7 + 2 * j + 2 * 8 * i);
+	b = b + 2;
+      }
+  if (c || b != 7 + 64 * 2)
+    __builtin_abort ();
+  b = 7;
+  #pragma omp parallel for simd schedule (static, 4) linear(b:2) reduction(+:c)
+  for (int i = 0; i < 64; i++)
+    {
+      c = c + (b != 7 + 2 * i);
+      b = b + 2;
+    }
+  if (c || b != 7 + 64 * 2)
+    __builtin_abort ();
+  b = 7;
+  #pragma omp parallel for simd schedule (static, 4) linear(b:3) reduction(+:c)
+  for (int i = 0; i < 64; i += 4)
+    {
+      c = c + (b != 7 + i / 4 * 3);
+      b = b + 3;
+    }
+  if (c || b != 7 + 16 * 3)
+    __builtin_abort ();
+  b = 7;
+  #pragma omp parallel for simd collapse (2) schedule (static, 4) linear(b:2) reduction(+:c)
+  for (int i = 0; i < 8; i++)
+    for (int j = 0; j < 8; j++)
+      {
+	c = c + (b != 7 + 2 * j + 2 * 8 * i);
+	b = b + 2;
+      }
+  if (c || b != 7 + 64 * 2)
+    __builtin_abort ();
+  return 0;
+}

libgomp/testsuite/libgomp.c/simd-17.c

@@ -0,0 +1,73 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -std=c99" } */
+/* { dg-additional-options "-msse2" { target sse2_runtime } } */
+/* { dg-additional-options "-mavx" { target avx_runtime } } */
+
+static inline void
+foo (int *b, int *i, int *j, int x)
+{
+  *b = *b + x + (*i - *i) + (*j - *j);
+}
+
+int
+main ()
+{
+  int b, c = 0;
+  b = 7;
+  #pragma omp simd linear(b:2) reduction(+:c)
+  for (int i = 0; i < 64; i++)
+    {
+      c = c + (b != 7 + 2 * i);
+      foo (&b, &i, &i, 2);
+    }
+  if (c || b != 7 + 64 * 2)
+    __builtin_abort ();
+  b = 7;
+  #pragma omp simd linear(b:3) reduction(+:c)
+  for (int i = 0; i < 64; i += 4)
+    {
+      c = c + (b != 7 + i / 4 * 3);
+      foo (&b, &i, &i, 3);
+    }
+  if (c || b != 7 + 16 * 3)
+    __builtin_abort ();
+  b = 7;
+  #pragma omp simd collapse (2) linear(b:2) reduction(+:c)
+  for (int i = 0; i < 8; i++)
+    for (int j = 0; j < 8; j++)
+      {
+	c = c + (b != 7 + 2 * j + 2 * 8 * i);
+	foo (&b, &i, &j, 2);
+      }
+  if (c || b != 7 + 64 * 2)
+    __builtin_abort ();
+  b = 7;
+  #pragma omp parallel for simd schedule (static, 4) linear(b:2) reduction(+:c)
+  for (int i = 0; i < 64; i++)
+    {
+      c = c + (b != 7 + 2 * i);
+      foo (&b, &i, &i, 2);
+    }
+  if (c || b != 7 + 64 * 2)
+    __builtin_abort ();
+  b = 7;
+  #pragma omp parallel for simd schedule (static, 4) linear(b:3) reduction(+:c)
+  for (int i = 0; i < 64; i += 4)
+    {
+      c = c + (b != 7 + i / 4 * 3);
+      foo (&b, &i, &i, 3);
+    }
+  if (c || b != 7 + 16 * 3)
+    __builtin_abort ();
+  b = 7;
+  #pragma omp parallel for simd collapse (2) schedule (static, 4) linear(b:2) reduction(+:c)
+  for (int i = 0; i < 8; i++)
+    for (int j = 0; j < 8; j++)
+      {
+	c = c + (b != 7 + 2 * j + 2 * 8 * i);
+	foo (&b, &i, &j, 2);
+      }
+  if (c || b != 7 + 64 * 2)
+    __builtin_abort ();
+  return 0;
+}