--- /dev/null
+2011-11-22 Ira Rosen <ira.rosen@linaro.org>
+
+ Backport from mainline:
+
+ 2011-10-06 Jakub Jelinek <jakub@redhat.com>
+
+ gcc/
+ PR tree-optimization/50596
+ * tree-vectorizer.h (vect_is_simple_cond): New prototype.
+ (NUM_PATTERNS): Change to 6.
+ * tree-vect-patterns.c (vect_recog_mixed_size_cond_pattern): New
+ function.
+ (vect_vect_recog_func_ptrs): Add vect_recog_mixed_size_cond_pattern.
+ (vect_mark_pattern_stmts): Don't create stmt_vinfo for def_stmt
+ if it already has one, and don't set STMT_VINFO_VECTYPE in it
+ if it is already set.
+ * tree-vect-stmts.c (vect_mark_stmts_to_be_vectorized): Handle
+ COND_EXPR in pattern stmts.
+ (vect_is_simple_cond): No longer static.
+
+ gcc/testsuite:
+ PR tree-optimization/50596
+ * gcc.dg/vect/vect-cond-8.c: New test.
+
+ 2011-10-07 Jakub Jelinek <jakub@redhat.com>
+
+ gcc/
+ PR tree-optimization/50650
+ * tree-vect-patterns.c (vect_recog_mixed_size_cond_pattern): Don't
+ call vect_is_simple_cond here, instead fail if cond_expr isn't
+ COMPARISON_CLASS_P or if get_vectype_for_scalar_type returns NULL
+ for cond_expr's first operand.
+ * tree-vect-stmts.c (vect_is_simple_cond): Static again.
+ * tree-vectorizer.h (vect_is_simple_cond): Remove prototype.
+
+
+ gcc/
+ * tree-vect-patterns.c (vect_recog_mixed_size_cond_pattern): Reduce
+ it to integral types only.
+
+ gcc/testsuite/
+ * gcc.dg/vect/pr30858.c: Expect the error message twice for targets
+ with multiple vector sizes.
+ * gcc.dg/vect/vect-cond-8.c: Rename to...
+ * gcc.dg/vect/vect-cond-8a.c: ... this and change the type from float
+ to int.
+ * lib/target-supports.exp (check_effective_target_vect_condition):
+ Return true for NEON.
+
+=== modified file 'gcc/testsuite/gcc.dg/vect/pr30858.c'
+--- old/gcc/testsuite/gcc.dg/vect/pr30858.c 2007-02-22 08:16:18 +0000
++++ new/gcc/testsuite/gcc.dg/vect/pr30858.c 2011-11-20 09:11:09 +0000
+@@ -11,5 +11,6 @@
+ }
+
+ /* { dg-final { scan-tree-dump-times "vectorized 0 loops" 1 "vect" } } */
+-/* { dg-final { scan-tree-dump-times "Unknown def-use cycle pattern." 1 "vect" } } */
++/* { dg-final { scan-tree-dump-times "Unknown def-use cycle pattern." 1 "vect" { xfail vect_multiple_sizes } } } */
++/* { dg-final { scan-tree-dump-times "Unknown def-use cycle pattern." 2 "vect" { target vect_multiple_sizes } } } */
+ /* { dg-final { cleanup-tree-dump "vect" } } */
+
+=== added file 'gcc/testsuite/gcc.dg/vect/vect-cond-8a.c'
+--- old/gcc/testsuite/gcc.dg/vect/vect-cond-8a.c 1970-01-01 00:00:00 +0000
++++ new/gcc/testsuite/gcc.dg/vect/vect-cond-8a.c 2011-11-20 09:11:09 +0000
+@@ -0,0 +1,75 @@
++/* { dg-require-effective-target vect_condition } */
++
++#include "tree-vect.h"
++
++#define N 1024
++int a[N], b[N], c[N];
++char d[N], e[N], f[N];
++unsigned char k[N];
++
++__attribute__((noinline, noclone)) void
++f1 (void)
++{
++ int i;
++ for (i = 0; i < N; ++i)
++ k[i] = a[i] < b[i] ? 17 : 0;
++}
++
++__attribute__((noinline, noclone)) void
++f2 (void)
++{
++ int i;
++ for (i = 0; i < N; ++i)
++ k[i] = a[i] < b[i] ? 0 : 24;
++}
++
++__attribute__((noinline, noclone)) void
++f3 (void)
++{
++ int i;
++ for (i = 0; i < N; ++i)
++ k[i] = a[i] < b[i] ? 51 : 12;
++}
++
++int
++main ()
++{
++ int i;
++
++ check_vect ();
++
++ for (i = 0; i < N; i++)
++ {
++ switch (i % 9)
++ {
++ case 0: asm (""); a[i] = - i - 1; b[i] = i + 1; break;
++ case 1: a[i] = 0; b[i] = 0; break;
++ case 2: a[i] = i + 1; b[i] = - i - 1; break;
++ case 3: a[i] = i; b[i] = i + 7; break;
++ case 4: a[i] = i; b[i] = i; break;
++ case 5: a[i] = i + 16; b[i] = i + 3; break;
++ case 6: a[i] = - i - 5; b[i] = - i; break;
++ case 7: a[i] = - i; b[i] = - i; break;
++ case 8: a[i] = - i; b[i] = - i - 7; break;
++ }
++ d[i] = i;
++ e[i] = 2 * i;
++ }
++ f1 ();
++ for (i = 0; i < N; i++)
++ if (k[i] != ((i % 3) == 0 ? 17 : 0))
++ abort ();
++ f2 ();
++ for (i = 0; i < N; i++)
++ if (k[i] != ((i % 3) == 0 ? 0 : 24))
++ abort ();
++ f3 ();
++ for (i = 0; i < N; i++)
++ if (k[i] != ((i % 3) == 0 ? 51 : 12))
++ abort ();
++
++ return 0;
++}
++
++/* { dg-final { scan-tree-dump-times "note: vectorized 1 loops" 3 "vect" } } */
++/* { dg-final { cleanup-tree-dump "vect" } } */
+
+=== modified file 'gcc/testsuite/lib/target-supports.exp'
+--- old/gcc/testsuite/lib/target-supports.exp 2011-11-21 01:45:54 +0000
++++ new/gcc/testsuite/lib/target-supports.exp 2011-11-22 16:52:23 +0000
+@@ -3150,7 +3150,8 @@
+ || [istarget ia64-*-*]
+ || [istarget i?86-*-*]
+ || [istarget spu-*-*]
+- || [istarget x86_64-*-*] } {
++ || [istarget x86_64-*-*]
++ || ([istarget arm*-*-*] && [check_effective_target_arm_neon_ok]) } {
+ set et_vect_cond_saved 1
+ }
+ }
+
+=== modified file 'gcc/tree-vect-patterns.c'
+--- old/gcc/tree-vect-patterns.c 2011-10-23 13:33:07 +0000
++++ new/gcc/tree-vect-patterns.c 2011-11-20 09:11:09 +0000
+@@ -50,13 +50,16 @@
+ tree *);
+ static gimple vect_recog_widen_shift_pattern (VEC (gimple, heap) **,
+ tree *, tree *);
++static gimple vect_recog_mixed_size_cond_pattern (VEC (gimple, heap) **,
++ tree *, tree *);
+ static vect_recog_func_ptr vect_vect_recog_func_ptrs[NUM_PATTERNS] = {
+ vect_recog_widen_mult_pattern,
+ vect_recog_widen_sum_pattern,
+ vect_recog_dot_prod_pattern,
+ vect_recog_pow_pattern,
+ vect_recog_over_widening_pattern,
+- vect_recog_widen_shift_pattern};
++ vect_recog_widen_shift_pattern,
++ vect_recog_mixed_size_cond_pattern};
+
+
+ /* Function widened_name_p
+@@ -1441,6 +1444,118 @@
+ return pattern_stmt;
+ }
+
++/* Function vect_recog_mixed_size_cond_pattern
++
++ Try to find the following pattern:
++
++ type x_t, y_t;
++ TYPE a_T, b_T, c_T;
++ loop:
++ S1 a_T = x_t CMP y_t ? b_T : c_T;
++
++ where type 'TYPE' is an integral type which has different size
++ from 'type'. b_T and c_T are constants and if 'TYPE' is wider
++ than 'type', the constants need to fit into an integer type
++ with the same width as 'type'.
++
++ Input:
++
++ * LAST_STMT: A stmt from which the pattern search begins.
++
++ Output:
++
++ * TYPE_IN: The type of the input arguments to the pattern.
++
++ * TYPE_OUT: The type of the output of this pattern.
++
++ * Return value: A new stmt that will be used to replace the pattern.
++ Additionally a def_stmt is added.
++
++ a_it = x_t CMP y_t ? b_it : c_it;
++ a_T = (TYPE) a_it; */
++
++static gimple
++vect_recog_mixed_size_cond_pattern (VEC (gimple, heap) **stmts, tree *type_in,
++ tree *type_out)
++{
++ gimple last_stmt = VEC_index (gimple, *stmts, 0);
++ tree cond_expr, then_clause, else_clause;
++ stmt_vec_info stmt_vinfo = vinfo_for_stmt (last_stmt), def_stmt_info;
++ tree type, vectype, comp_vectype, comp_type, op, tmp;
++ enum machine_mode cmpmode;
++ gimple pattern_stmt, def_stmt;
++ loop_vec_info loop_vinfo = STMT_VINFO_LOOP_VINFO (stmt_vinfo);
++
++ if (!is_gimple_assign (last_stmt)
++ || gimple_assign_rhs_code (last_stmt) != COND_EXPR
++ || STMT_VINFO_DEF_TYPE (stmt_vinfo) != vect_internal_def)
++ return NULL;
++
++ op = gimple_assign_rhs1 (last_stmt);
++ cond_expr = TREE_OPERAND (op, 0);
++ then_clause = TREE_OPERAND (op, 1);
++ else_clause = TREE_OPERAND (op, 2);
++
++ if (TREE_CODE (then_clause) != INTEGER_CST
++ || TREE_CODE (else_clause) != INTEGER_CST)
++ return NULL;
++
++ if (!COMPARISON_CLASS_P (cond_expr))
++ return NULL;
++
++ type = gimple_expr_type (last_stmt);
++ comp_type = TREE_TYPE (TREE_OPERAND (cond_expr, 0));
++ if (!INTEGRAL_TYPE_P (comp_type)
++ || !INTEGRAL_TYPE_P (type))
++ return NULL;
++
++ comp_vectype = get_vectype_for_scalar_type (comp_type);
++ if (comp_vectype == NULL_TREE)
++ return NULL;
++
++ cmpmode = GET_MODE_INNER (TYPE_MODE (comp_vectype));
++
++ if (GET_MODE_BITSIZE (TYPE_MODE (type)) == GET_MODE_BITSIZE (cmpmode))
++ return NULL;
++
++ vectype = get_vectype_for_scalar_type (type);
++ if (vectype == NULL_TREE)
++ return NULL;
++
++ if (types_compatible_p (vectype, comp_vectype))
++ return NULL;
++
++ if (!expand_vec_cond_expr_p (comp_vectype, TYPE_MODE (comp_vectype)))
++ return NULL;
++
++ if (GET_MODE_BITSIZE (TYPE_MODE (type)) > GET_MODE_BITSIZE (cmpmode))
++ {
++ if (!int_fits_type_p (then_clause, comp_type)
++ || !int_fits_type_p (else_clause, comp_type))
++ return NULL;
++ }
++
++ tmp = build3 (COND_EXPR, comp_type, unshare_expr (cond_expr),
++ fold_convert (comp_type, then_clause),
++ fold_convert (comp_type, else_clause));
++ def_stmt = gimple_build_assign (vect_recog_temp_ssa_var (comp_type, NULL), tmp);
++
++ pattern_stmt
++ = gimple_build_assign_with_ops (NOP_EXPR,
++ vect_recog_temp_ssa_var (type, NULL),
++ gimple_assign_lhs (def_stmt), NULL_TREE);
++
++ STMT_VINFO_PATTERN_DEF_STMT (stmt_vinfo) = def_stmt;
++ def_stmt_info = new_stmt_vec_info (def_stmt, loop_vinfo, NULL);
++ set_vinfo_for_stmt (def_stmt, def_stmt_info);
++ STMT_VINFO_VECTYPE (def_stmt_info) = comp_vectype;
++ *type_in = vectype;
++ *type_out = vectype;
++
++ return pattern_stmt;
++}
++
++
+ /* Mark statements that are involved in a pattern. */
+
+ static inline void
+@@ -1468,14 +1583,18 @@
+ if (STMT_VINFO_PATTERN_DEF_STMT (pattern_stmt_info))
+ {
+ def_stmt = STMT_VINFO_PATTERN_DEF_STMT (pattern_stmt_info);
+- set_vinfo_for_stmt (def_stmt,
+- new_stmt_vec_info (def_stmt, loop_vinfo, NULL));
++ def_stmt_info = vinfo_for_stmt (def_stmt);
++ if (def_stmt_info == NULL)
++ {
++ def_stmt_info = new_stmt_vec_info (def_stmt, loop_vinfo, NULL);
++ set_vinfo_for_stmt (def_stmt, def_stmt_info);
++ }
+ gimple_set_bb (def_stmt, gimple_bb (orig_stmt));
+- def_stmt_info = vinfo_for_stmt (def_stmt);
+ STMT_VINFO_RELATED_STMT (def_stmt_info) = orig_stmt;
+ STMT_VINFO_DEF_TYPE (def_stmt_info)
+ = STMT_VINFO_DEF_TYPE (orig_stmt_info);
+- STMT_VINFO_VECTYPE (def_stmt_info) = pattern_vectype;
++ if (STMT_VINFO_VECTYPE (def_stmt_info) == NULL_TREE)
++ STMT_VINFO_VECTYPE (def_stmt_info) = pattern_vectype;
+ }
+ }
+
+
+=== modified file 'gcc/tree-vect-stmts.c'
+--- old/gcc/tree-vect-stmts.c 2011-11-14 11:38:08 +0000
++++ new/gcc/tree-vect-stmts.c 2011-11-22 16:52:23 +0000
+@@ -655,20 +655,40 @@
+ tree rhs = gimple_assign_rhs1 (stmt);
+ unsigned int op_num;
+ tree op;
++ enum tree_code rhs_code;
+ switch (get_gimple_rhs_class (gimple_assign_rhs_code (stmt)))
+ {
+ case GIMPLE_SINGLE_RHS:
+- op_num = TREE_OPERAND_LENGTH (gimple_assign_rhs1 (stmt));
+- for (i = 0; i < op_num; i++)
+- {
+- op = TREE_OPERAND (rhs, i);
+- if (!process_use (stmt, op, loop_vinfo, live_p, relevant,
+- &worklist))
+- {
+- VEC_free (gimple, heap, worklist);
+- return false;
+- }
+- }
++ op = gimple_assign_rhs1 (stmt);
++ rhs_code = gimple_assign_rhs_code (stmt);
++ i = 0;
++ if (rhs_code == COND_EXPR
++ && COMPARISON_CLASS_P (TREE_OPERAND (op, 0)))
++ {
++ op = TREE_OPERAND (op, 0);
++ if (!process_use (stmt, TREE_OPERAND (op, 0),
++ loop_vinfo,
++ live_p, relevant, &worklist)
++ || !process_use (stmt, TREE_OPERAND (op, 1),
++ loop_vinfo,
++ live_p, relevant, &worklist))
++ {
++ VEC_free (gimple, heap, worklist);
++ return false;
++ }
++ i = 1;
++ }
++ op_num = TREE_OPERAND_LENGTH (gimple_assign_rhs1 (stmt));
++ for (i; i < op_num; i++)
++ {
++ op = TREE_OPERAND (rhs, i);
++ if (!process_use (stmt, op, loop_vinfo, live_p, relevant,
++ &worklist))
++ {
++ VEC_free (gimple, heap, worklist);
++ return false;
++ }
++ }
+ break;
+
+ case GIMPLE_BINARY_RHS:
+
+=== modified file 'gcc/tree-vectorizer.h'
+--- old/gcc/tree-vectorizer.h 2011-11-14 11:38:08 +0000
++++ new/gcc/tree-vectorizer.h 2011-11-22 16:52:23 +0000
+@@ -917,7 +917,7 @@
+ Additional pattern recognition functions can (and will) be added
+ in the future. */
+ typedef gimple (* vect_recog_func_ptr) (VEC (gimple, heap) **, tree *, tree *);
+-#define NUM_PATTERNS 6
++#define NUM_PATTERNS 7
+ void vect_pattern_recog (loop_vec_info);
+
+ /* In tree-vectorizer.c. */
+
--- /dev/null
+2011-11-22 Ira Rosen <ira.rosen@linaro.org>
+ Backport from mainline:
+
+ 2011-11-06 Ira Rosen <ira.rosen@linaro.org>
+
+ gcc/
+ * tree-vectorizer.h (vectorizable_condition): Add argument.
+ * tree-vect-loop.c (vectorizable_reduction): Fail for condition
+ in SLP. Update calls to vectorizable_condition.
+ * tree-vect-stmts.c (vect_is_simple_cond): Add basic block info to
+ the arguments. Pass it to vect_is_simple_use_1.
+ (vectorizable_condition): Add slp_node to the arguments. Support
+ vectorization of basic blocks. Fail for reduction in SLP. Update
+ calls to vect_is_simple_cond and vect_is_simple_use. Support SLP:
+ call vect_get_slp_defs to get vector operands.
+ (vect_analyze_stmt): Update calls to vectorizable_condition.
+ (vect_transform_stmt): Likewise.
+ * tree-vect-slp.c (vect_create_new_slp_node): Handle COND_EXPR.
+ (vect_get_and_check_slp_defs): Handle COND_EXPR. Allow pattern
+ def stmts.
+ (vect_build_slp_tree): Handle COND_EXPR.
+ (vect_analyze_slp_instance): Push pattern statements to root node.
+ (vect_get_constant_vectors): Fix comments. Handle COND_EXPR.
+
+ gcc/testsuite/
+ * gcc.dg/vect/bb-slp-cond-1.c: New test.
+ * gcc.dg/vect/slp-cond-1.c: New test.
+
+=== added file 'gcc/testsuite/gcc.dg/vect/bb-slp-cond-1.c'
+--- old/gcc/testsuite/gcc.dg/vect/bb-slp-cond-1.c 1970-01-01 00:00:00 +0000
++++ new/gcc/testsuite/gcc.dg/vect/bb-slp-cond-1.c 2011-11-20 08:24:08 +0000
+@@ -0,0 +1,46 @@
++/* { dg-require-effective-target vect_condition } */
++
++#include "tree-vect.h"
++
++#define N 128
++
++__attribute__((noinline, noclone)) void
++foo (int *a, int stride)
++{
++ int i;
++
++ for (i = 0; i < N/stride; i++, a += stride)
++ {
++ a[0] = a[0] ? 1 : 5;
++ a[1] = a[1] ? 2 : 6;
++ a[2] = a[2] ? 3 : 7;
++ a[3] = a[3] ? 4 : 8;
++ }
++}
++
++
++int a[N];
++int main ()
++{
++ int i;
++
++ check_vect ();
++
++ for (i = 0; i < N; i++)
++ a[i] = i;
++
++ foo (a, 4);
++
++ for (i = 1; i < N; i++)
++ if (a[i] != i%4 + 1)
++ abort ();
++
++ if (a[0] != 5)
++ abort ();
++
++ return 0;
++}
++
++/* { dg-final { scan-tree-dump-times "basic block vectorized using SLP" 1 "slp" { target vect_element_align } } } */
++/* { dg-final { cleanup-tree-dump "slp" } } */
++
+
+=== added file 'gcc/testsuite/gcc.dg/vect/slp-cond-1.c'
+--- old/gcc/testsuite/gcc.dg/vect/slp-cond-1.c 1970-01-01 00:00:00 +0000
++++ new/gcc/testsuite/gcc.dg/vect/slp-cond-1.c 2011-11-20 08:24:08 +0000
+@@ -0,0 +1,126 @@
++/* { dg-require-effective-target vect_condition } */
++#include "tree-vect.h"
++
++#define N 32
++int a[N], b[N];
++int d[N], e[N];
++int k[N];
++
++__attribute__((noinline, noclone)) void
++f1 (void)
++{
++ int i;
++ for (i = 0; i < N/4; i++)
++ {
++ k[4*i] = a[4*i] < b[4*i] ? 17 : 0;
++ k[4*i+1] = a[4*i+1] < b[4*i+1] ? 17 : 0;
++ k[4*i+2] = a[4*i+2] < b[4*i+2] ? 17 : 0;
++ k[4*i+3] = a[4*i+3] < b[4*i+3] ? 17 : 0;
++ }
++}
++
++__attribute__((noinline, noclone)) void
++f2 (void)
++{
++ int i;
++ for (i = 0; i < N/2; ++i)
++ {
++ k[2*i] = a[2*i] < b[2*i] ? 0 : 24;
++ k[2*i+1] = a[2*i+1] < b[2*i+1] ? 7 : 4;
++ }
++}
++
++__attribute__((noinline, noclone)) void
++f3 (void)
++{
++ int i;
++ for (i = 0; i < N/2; ++i)
++ {
++ k[2*i] = a[2*i] < b[2*i] ? 51 : 12;
++ k[2*i+1] = a[2*i+1] > b[2*i+1] ? 51 : 12;
++ }
++}
++
++__attribute__((noinline, noclone)) void
++f4 (void)
++{
++ int i;
++ for (i = 0; i < N/2; ++i)
++ {
++ int d0 = d[2*i], e0 = e[2*i];
++ int d1 = d[2*i+1], e1 = e[2*i+1];
++ k[2*i] = a[2*i] >= b[2*i] ? d0 : e0;
++ k[2*i+1] = a[2*i+1] >= b[2*i+1] ? d1 : e1;
++ }
++}
++
++int
++main ()
++{
++ int i;
++
++ check_vect ();
++
++ for (i = 0; i < N; i++)
++ {
++ switch (i % 9)
++ {
++ case 0: asm (""); a[i] = - i - 1; b[i] = i + 1; break;
++ case 1: a[i] = 0; b[i] = 0; break;
++ case 2: a[i] = i + 1; b[i] = - i - 1; break;
++ case 3: a[i] = i; b[i] = i + 7; break;
++ case 4: a[i] = i; b[i] = i; break;
++ case 5: a[i] = i + 16; b[i] = i + 3; break;
++ case 6: a[i] = - i - 5; b[i] = - i; break;
++ case 7: a[i] = - i; b[i] = - i; break;
++ case 8: a[i] = - i; b[i] = - i - 7; break;
++ }
++ d[i] = i;
++ e[i] = 2 * i;
++ }
++ f1 ();
++ for (i = 0; i < N; i++)
++ if (k[i] != ((i % 3) == 0 ? 17 : 0))
++ abort ();
++
++ f2 ();
++ for (i = 0; i < N; i++)
++ {
++ switch (i % 9)
++ {
++ case 0:
++ case 6:
++ if (k[i] != ((i/9 % 2) == 0 ? 0 : 7))
++ abort ();
++ break;
++ case 1:
++ case 5:
++ case 7:
++ if (k[i] != ((i/9 % 2) == 0 ? 4 : 24))
++ abort ();
++ break;
++ case 2:
++ case 4:
++ case 8:
++ if (k[i] != ((i/9 % 2) == 0 ? 24 : 4))
++ abort ();
++ break;
++ case 3:
++ if (k[i] != ((i/9 % 2) == 0 ? 7 : 0))
++ abort ();
++ break;
++ }
++ }
++
++ f3 ();
++
++ f4 ();
++ for (i = 0; i < N; i++)
++ if (k[i] != ((i % 3) == 0 ? e[i] : d[i]))
++ abort ();
++
++ return 0;
++}
++
++/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 3 "vect" } } */
++/* { dg-final { cleanup-tree-dump "vect" } } */
+
+=== modified file 'gcc/tree-vect-loop.c'
+--- old/gcc/tree-vect-loop.c 2011-11-14 11:38:08 +0000
++++ new/gcc/tree-vect-loop.c 2011-11-20 08:24:08 +0000
+@@ -4087,6 +4087,9 @@
+ gcc_unreachable ();
+ }
+
++ if (code == COND_EXPR && slp_node)
++ return false;
++
+ scalar_dest = gimple_assign_lhs (stmt);
+ scalar_type = TREE_TYPE (scalar_dest);
+ if (!POINTER_TYPE_P (scalar_type) && !INTEGRAL_TYPE_P (scalar_type)
+@@ -4161,7 +4164,7 @@
+
+ if (code == COND_EXPR)
+ {
+- if (!vectorizable_condition (stmt, gsi, NULL, ops[reduc_index], 0))
++ if (!vectorizable_condition (stmt, gsi, NULL, ops[reduc_index], 0, NULL))
+ {
+ if (vect_print_dump_info (REPORT_DETAILS))
+ fprintf (vect_dump, "unsupported condition in reduction");
+@@ -4433,7 +4436,7 @@
+ gcc_assert (!slp_node);
+ vectorizable_condition (stmt, gsi, vec_stmt,
+ PHI_RESULT (VEC_index (gimple, phis, 0)),
+- reduc_index);
++ reduc_index, NULL);
+ /* Multiple types are not supported for condition. */
+ break;
+ }
+
+=== modified file 'gcc/tree-vect-slp.c'
+--- old/gcc/tree-vect-slp.c 2011-11-14 11:38:08 +0000
++++ new/gcc/tree-vect-slp.c 2011-11-21 06:58:40 +0000
+@@ -109,7 +109,11 @@
+ if (is_gimple_call (stmt))
+ nops = gimple_call_num_args (stmt);
+ else if (is_gimple_assign (stmt))
+- nops = gimple_num_ops (stmt) - 1;
++ {
++ nops = gimple_num_ops (stmt) - 1;
++ if (gimple_assign_rhs_code (stmt) == COND_EXPR)
++ nops = 4;
++ }
+ else
+ return NULL;
+
+@@ -190,20 +194,51 @@
+ bool different_types = false;
+ bool pattern = false;
+ slp_oprnd_info oprnd_info, oprnd0_info, oprnd1_info;
++ int op_idx = 1;
++ tree compare_rhs = NULL_TREE, rhs = NULL_TREE;
++ int cond_idx = -1;
+
+ if (loop_vinfo)
+ loop = LOOP_VINFO_LOOP (loop_vinfo);
+
+ if (is_gimple_call (stmt))
+ number_of_oprnds = gimple_call_num_args (stmt);
++ else if (is_gimple_assign (stmt))
++ {
++ number_of_oprnds = gimple_num_ops (stmt) - 1;
++ if (gimple_assign_rhs_code (stmt) == COND_EXPR)
++ {
++ number_of_oprnds = 4;
++ cond_idx = 0;
++ rhs = gimple_assign_rhs1 (stmt);
++ }
++ }
+ else
+- number_of_oprnds = gimple_num_ops (stmt) - 1;
++ return false;
+
+ for (i = 0; i < number_of_oprnds; i++)
+ {
+- oprnd = gimple_op (stmt, i + 1);
++ if (compare_rhs)
++ oprnd = compare_rhs;
++ else
++ oprnd = gimple_op (stmt, op_idx++);
++
+ oprnd_info = VEC_index (slp_oprnd_info, *oprnds_info, i);
+
++ if (-1 < cond_idx && cond_idx < 4)
++ {
++ if (compare_rhs)
++ compare_rhs = NULL_TREE;
++ else
++ oprnd = TREE_OPERAND (rhs, cond_idx++);
++ }
++
++ if (COMPARISON_CLASS_P (oprnd))
++ {
++ compare_rhs = TREE_OPERAND (oprnd, 1);
++ oprnd = TREE_OPERAND (oprnd, 0);
++ }
++
+ if (!vect_is_simple_use (oprnd, loop_vinfo, bb_vinfo, &def_stmt, &def,
+ &dt)
+ || (!def_stmt && dt != vect_constant_def))
+@@ -243,8 +278,7 @@
+ def_stmt = STMT_VINFO_RELATED_STMT (vinfo_for_stmt (def_stmt));
+ dt = STMT_VINFO_DEF_TYPE (vinfo_for_stmt (def_stmt));
+
+- if (dt == vect_unknown_def_type
+- || STMT_VINFO_PATTERN_DEF_STMT (vinfo_for_stmt (def_stmt)))
++ if (dt == vect_unknown_def_type)
+ {
+ if (vect_print_dump_info (REPORT_DETAILS))
+ fprintf (vect_dump, "Unsupported pattern.");
+@@ -423,6 +457,7 @@
+ VEC (gimple, heap) *stmts = SLP_TREE_SCALAR_STMTS (*node);
+ gimple stmt = VEC_index (gimple, stmts, 0);
+ enum tree_code first_stmt_code = ERROR_MARK, rhs_code = ERROR_MARK;
++ enum tree_code first_cond_code = ERROR_MARK;
+ tree lhs;
+ bool stop_recursion = false, need_same_oprnds = false;
+ tree vectype, scalar_type, first_op1 = NULL_TREE;
+@@ -439,11 +474,18 @@
+ VEC (slp_oprnd_info, heap) *oprnds_info;
+ unsigned int nops;
+ slp_oprnd_info oprnd_info;
++ tree cond;
+
+ if (is_gimple_call (stmt))
+ nops = gimple_call_num_args (stmt);
++ else if (is_gimple_assign (stmt))
++ {
++ nops = gimple_num_ops (stmt) - 1;
++ if (gimple_assign_rhs_code (stmt) == COND_EXPR)
++ nops = 4;
++ }
+ else
+- nops = gimple_num_ops (stmt) - 1;
++ return false;
+
+ oprnds_info = vect_create_oprnd_info (nops, group_size);
+
+@@ -484,6 +526,22 @@
+ return false;
+ }
+
++ if (is_gimple_assign (stmt)
++ && gimple_assign_rhs_code (stmt) == COND_EXPR
++ && (cond = TREE_OPERAND (gimple_assign_rhs1 (stmt), 0))
++ && !COMPARISON_CLASS_P (cond))
++ {
++ if (vect_print_dump_info (REPORT_SLP))
++ {
++ fprintf (vect_dump,
++ "Build SLP failed: condition is not comparison ");
++ print_gimple_stmt (vect_dump, stmt, 0, TDF_SLIM);
++ }
++
++ vect_free_oprnd_info (&oprnds_info);
++ return false;
++ }
++
+ scalar_type = vect_get_smallest_scalar_type (stmt, &dummy, &dummy);
+ vectype = get_vectype_for_scalar_type (scalar_type);
+ if (!vectype)
+@@ -737,7 +795,8 @@
+
+ /* Not memory operation. */
+ if (TREE_CODE_CLASS (rhs_code) != tcc_binary
+- && TREE_CODE_CLASS (rhs_code) != tcc_unary)
++ && TREE_CODE_CLASS (rhs_code) != tcc_unary
++ && rhs_code != COND_EXPR)
+ {
+ if (vect_print_dump_info (REPORT_SLP))
+ {
+@@ -750,6 +809,26 @@
+ return false;
+ }
+
++ if (rhs_code == COND_EXPR)
++ {
++ tree cond_expr = TREE_OPERAND (gimple_assign_rhs1 (stmt), 0);
++
++ if (i == 0)
++ first_cond_code = TREE_CODE (cond_expr);
++ else if (first_cond_code != TREE_CODE (cond_expr))
++ {
++ if (vect_print_dump_info (REPORT_SLP))
++ {
++ fprintf (vect_dump, "Build SLP failed: different"
++ " operation");
++ print_gimple_stmt (vect_dump, stmt, 0, TDF_SLIM);
++ }
++
++ vect_free_oprnd_info (&oprnds_info);
++ return false;
++ }
++ }
++
+ /* Find the def-stmts. */
+ if (!vect_get_and_check_slp_defs (loop_vinfo, bb_vinfo, *node, stmt,
+ ncopies_for_cost, (i == 0),
+@@ -1395,7 +1474,12 @@
+ /* Collect the stores and store them in SLP_TREE_SCALAR_STMTS. */
+ while (next)
+ {
+- VEC_safe_push (gimple, heap, scalar_stmts, next);
++ if (STMT_VINFO_IN_PATTERN_P (vinfo_for_stmt (next))
++ && STMT_VINFO_RELATED_STMT (vinfo_for_stmt (next)))
++ VEC_safe_push (gimple, heap, scalar_stmts,
++ STMT_VINFO_RELATED_STMT (vinfo_for_stmt (next)));
++ else
++ VEC_safe_push (gimple, heap, scalar_stmts, next);
+ next = DR_GROUP_NEXT_DR (vinfo_for_stmt (next));
+ }
+ }
+@@ -1404,7 +1488,7 @@
+ /* Collect reduction statements. */
+ VEC (gimple, heap) *reductions = LOOP_VINFO_REDUCTIONS (loop_vinfo);
+ for (i = 0; VEC_iterate (gimple, reductions, i, next); i++)
+- VEC_safe_push (gimple, heap, scalar_stmts, next);
++ VEC_safe_push (gimple, heap, scalar_stmts, next);
+ }
+
+ node = vect_create_new_slp_node (scalar_stmts);
+@@ -2160,15 +2244,15 @@
+
+ For example, we have two scalar operands, s1 and s2 (e.g., group of
+ strided accesses of size two), while NUNITS is four (i.e., four scalars
+- of this type can be packed in a vector). The output vector will contain
+- two copies of each scalar operand: {s1, s2, s1, s2}. (NUMBER_OF_COPIES
++ of this type can be packed in a vector). The output vector will contain
++ two copies of each scalar operand: {s1, s2, s1, s2}. (NUMBER_OF_COPIES
+ will be 2).
+
+ If GROUP_SIZE > NUNITS, the scalars will be split into several vectors
+ containing the operands.
+
+ For example, NUNITS is four as before, and the group size is 8
+- (s1, s2, ..., s8). We will create two vectors {s1, s2, s3, s4} and
++ (s1, s2, ..., s8). We will create two vectors {s1, s2, s3, s4} and
+ {s5, s6, s7, s8}. */
+
+ number_of_copies = least_common_multiple (nunits, group_size) / group_size;
+@@ -2180,8 +2264,18 @@
+ {
+ if (is_store)
+ op = gimple_assign_rhs1 (stmt);
+- else
++ else if (gimple_assign_rhs_code (stmt) != COND_EXPR)
+ op = gimple_op (stmt, op_num + 1);
++ else
++ {
++ if (op_num == 0 || op_num == 1)
++ {
++ tree cond = TREE_OPERAND (gimple_assign_rhs1 (stmt), 0);
++ op = TREE_OPERAND (cond, op_num);
++ }
++ else
++ op = TREE_OPERAND (gimple_assign_rhs1 (stmt), op_num - 1);
++ }
+
+ if (reduc_index != -1)
+ {
+
+=== modified file 'gcc/tree-vect-stmts.c'
+--- old/gcc/tree-vect-stmts.c 2011-11-22 16:52:23 +0000
++++ new/gcc/tree-vect-stmts.c 2011-11-22 17:10:17 +0000
+@@ -4816,7 +4816,7 @@
+ condition operands are supportable using vec_is_simple_use. */
+
+ static bool
+-vect_is_simple_cond (tree cond, loop_vec_info loop_vinfo)
++vect_is_simple_cond (tree cond, loop_vec_info loop_vinfo, bb_vec_info bb_vinfo)
+ {
+ tree lhs, rhs;
+ tree def;
+@@ -4831,7 +4831,7 @@
+ if (TREE_CODE (lhs) == SSA_NAME)
+ {
+ gimple lhs_def_stmt = SSA_NAME_DEF_STMT (lhs);
+- if (!vect_is_simple_use (lhs, loop_vinfo, NULL, &lhs_def_stmt, &def,
++ if (!vect_is_simple_use (lhs, loop_vinfo, bb_vinfo, &lhs_def_stmt, &def,
+ &dt))
+ return false;
+ }
+@@ -4842,7 +4842,7 @@
+ if (TREE_CODE (rhs) == SSA_NAME)
+ {
+ gimple rhs_def_stmt = SSA_NAME_DEF_STMT (rhs);
+- if (!vect_is_simple_use (rhs, loop_vinfo, NULL, &rhs_def_stmt, &def,
++ if (!vect_is_simple_use (rhs, loop_vinfo, bb_vinfo, &rhs_def_stmt, &def,
+ &dt))
+ return false;
+ }
+@@ -4868,7 +4868,8 @@
+
+ bool
+ vectorizable_condition (gimple stmt, gimple_stmt_iterator *gsi,
+- gimple *vec_stmt, tree reduc_def, int reduc_index)
++ gimple *vec_stmt, tree reduc_def, int reduc_index,
++ slp_tree slp_node)
+ {
+ tree scalar_dest = NULL_TREE;
+ tree vec_dest = NULL_TREE;
+@@ -4885,19 +4886,24 @@
+ tree def;
+ enum vect_def_type dt, dts[4];
+ int nunits = TYPE_VECTOR_SUBPARTS (vectype);
+- int ncopies = LOOP_VINFO_VECT_FACTOR (loop_vinfo) / nunits;
++ int ncopies;
+ enum tree_code code;
+ stmt_vec_info prev_stmt_info = NULL;
+- int j;
++ int i, j;
++ bb_vec_info bb_vinfo = STMT_VINFO_BB_VINFO (stmt_info);
++ VEC (tree, heap) *vec_oprnds0 = NULL, *vec_oprnds1 = NULL;
++ VEC (tree, heap) *vec_oprnds2 = NULL, *vec_oprnds3 = NULL;
+
+- /* FORNOW: unsupported in basic block SLP. */
+- gcc_assert (loop_vinfo);
++ if (slp_node || PURE_SLP_STMT (stmt_info))
++ ncopies = 1;
++ else
++ ncopies = LOOP_VINFO_VECT_FACTOR (loop_vinfo) / nunits;
+
+ gcc_assert (ncopies >= 1);
+- if (reduc_index && ncopies > 1)
++ if (reduc_index && (ncopies > 1 || STMT_SLP_TYPE (stmt_info)))
+ return false; /* FORNOW */
+
+- if (!STMT_VINFO_RELEVANT_P (stmt_info))
++ if (!STMT_VINFO_RELEVANT_P (stmt_info) && !bb_vinfo)
+ return false;
+
+ if (STMT_VINFO_DEF_TYPE (stmt_info) != vect_internal_def
+@@ -4905,10 +4911,6 @@
+ && reduc_def))
+ return false;
+
+- /* FORNOW: SLP not supported. */
+- if (STMT_SLP_TYPE (stmt_info))
+- return false;
+-
+ /* FORNOW: not yet supported. */
+ if (STMT_VINFO_LIVE_P (stmt_info))
+ {
+@@ -4932,7 +4934,7 @@
+ then_clause = TREE_OPERAND (op, 1);
+ else_clause = TREE_OPERAND (op, 2);
+
+- if (!vect_is_simple_cond (cond_expr, loop_vinfo))
++ if (!vect_is_simple_cond (cond_expr, loop_vinfo, bb_vinfo))
+ return false;
+
+ /* We do not handle two different vector types for the condition
+@@ -4944,7 +4946,7 @@
+ if (TREE_CODE (then_clause) == SSA_NAME)
+ {
+ gimple then_def_stmt = SSA_NAME_DEF_STMT (then_clause);
+- if (!vect_is_simple_use (then_clause, loop_vinfo, NULL,
++ if (!vect_is_simple_use (then_clause, loop_vinfo, bb_vinfo,
+ &then_def_stmt, &def, &dt))
+ return false;
+ }
+@@ -4956,7 +4958,7 @@
+ if (TREE_CODE (else_clause) == SSA_NAME)
+ {
+ gimple else_def_stmt = SSA_NAME_DEF_STMT (else_clause);
+- if (!vect_is_simple_use (else_clause, loop_vinfo, NULL,
++ if (!vect_is_simple_use (else_clause, loop_vinfo, bb_vinfo,
+ &else_def_stmt, &def, &dt))
+ return false;
+ }
+@@ -4974,7 +4976,15 @@
+ return expand_vec_cond_expr_p (TREE_TYPE (op), vec_mode);
+ }
+
+- /* Transform */
++ /* Transform. */
++
++ if (!slp_node)
++ {
++ vec_oprnds0 = VEC_alloc (tree, heap, 1);
++ vec_oprnds1 = VEC_alloc (tree, heap, 1);
++ vec_oprnds2 = VEC_alloc (tree, heap, 1);
++ vec_oprnds3 = VEC_alloc (tree, heap, 1);
++ }
+
+ /* Handle def. */
+ scalar_dest = gimple_assign_lhs (stmt);
+@@ -4983,67 +4993,118 @@
+ /* Handle cond expr. */
+ for (j = 0; j < ncopies; j++)
+ {
+- gimple new_stmt;
++ gimple new_stmt = NULL;
+ if (j == 0)
+ {
+- gimple gtemp;
+- vec_cond_lhs =
++ if (slp_node)
++ {
++ VEC (tree, heap) *ops = VEC_alloc (tree, heap, 4);
++ VEC (slp_void_p, heap) *vec_defs;
++
++ vec_defs = VEC_alloc (slp_void_p, heap, 4);
++ VEC_safe_push (tree, heap, ops, TREE_OPERAND (cond_expr, 0));
++ VEC_safe_push (tree, heap, ops, TREE_OPERAND (cond_expr, 1));
++ VEC_safe_push (tree, heap, ops, then_clause);
++ VEC_safe_push (tree, heap, ops, else_clause);
++ vect_get_slp_defs (ops, slp_node, &vec_defs, -1);
++ vec_oprnds3 = (VEC (tree, heap) *) VEC_pop (slp_void_p, vec_defs);
++ vec_oprnds2 = (VEC (tree, heap) *) VEC_pop (slp_void_p, vec_defs);
++ vec_oprnds1 = (VEC (tree, heap) *) VEC_pop (slp_void_p, vec_defs);
++ vec_oprnds0 = (VEC (tree, heap) *) VEC_pop (slp_void_p, vec_defs);
++
++ VEC_free (tree, heap, ops);
++ VEC_free (slp_void_p, heap, vec_defs);
++ }
++ else
++ {
++ gimple gtemp;
++ vec_cond_lhs =
+ vect_get_vec_def_for_operand (TREE_OPERAND (cond_expr, 0),
+ stmt, NULL);
+- vect_is_simple_use (TREE_OPERAND (cond_expr, 0), loop_vinfo,
++ vect_is_simple_use (TREE_OPERAND (cond_expr, 0), loop_vinfo,
+ NULL, >emp, &def, &dts[0]);
+- vec_cond_rhs =
+- vect_get_vec_def_for_operand (TREE_OPERAND (cond_expr, 1),
+- stmt, NULL);
+- vect_is_simple_use (TREE_OPERAND (cond_expr, 1), loop_vinfo,
+- NULL, >emp, &def, &dts[1]);
+- if (reduc_index == 1)
+- vec_then_clause = reduc_def;
+- else
+- {
+- vec_then_clause = vect_get_vec_def_for_operand (then_clause,
+- stmt, NULL);
+- vect_is_simple_use (then_clause, loop_vinfo,
+- NULL, >emp, &def, &dts[2]);
+- }
+- if (reduc_index == 2)
+- vec_else_clause = reduc_def;
+- else
+- {
+- vec_else_clause = vect_get_vec_def_for_operand (else_clause,
+- stmt, NULL);
+- vect_is_simple_use (else_clause, loop_vinfo,
++
++ vec_cond_rhs =
++ vect_get_vec_def_for_operand (TREE_OPERAND (cond_expr, 1),
++ stmt, NULL);
++ vect_is_simple_use (TREE_OPERAND (cond_expr, 1), loop_vinfo,
++ NULL, >emp, &def, &dts[1]);
++ if (reduc_index == 1)
++ vec_then_clause = reduc_def;
++ else
++ {
++ vec_then_clause = vect_get_vec_def_for_operand (then_clause,
++ stmt, NULL);
++ vect_is_simple_use (then_clause, loop_vinfo,
++ NULL, >emp, &def, &dts[2]);
++ }
++ if (reduc_index == 2)
++ vec_else_clause = reduc_def;
++ else
++ {
++ vec_else_clause = vect_get_vec_def_for_operand (else_clause,
++ stmt, NULL);
++ vect_is_simple_use (else_clause, loop_vinfo,
+ NULL, >emp, &def, &dts[3]);
++ }
+ }
+ }
+ else
+ {
+- vec_cond_lhs = vect_get_vec_def_for_stmt_copy (dts[0], vec_cond_lhs);
+- vec_cond_rhs = vect_get_vec_def_for_stmt_copy (dts[1], vec_cond_rhs);
++ vec_cond_lhs = vect_get_vec_def_for_stmt_copy (dts[0],
++ VEC_pop (tree, vec_oprnds0));
++ vec_cond_rhs = vect_get_vec_def_for_stmt_copy (dts[1],
++ VEC_pop (tree, vec_oprnds1));
+ vec_then_clause = vect_get_vec_def_for_stmt_copy (dts[2],
+- vec_then_clause);
++ VEC_pop (tree, vec_oprnds2));
+ vec_else_clause = vect_get_vec_def_for_stmt_copy (dts[3],
+- vec_else_clause);
++ VEC_pop (tree, vec_oprnds3));
++ }
++
++ if (!slp_node)
++ {
++ VEC_quick_push (tree, vec_oprnds0, vec_cond_lhs);
++ VEC_quick_push (tree, vec_oprnds1, vec_cond_rhs);
++ VEC_quick_push (tree, vec_oprnds2, vec_then_clause);
++ VEC_quick_push (tree, vec_oprnds3, vec_else_clause);
+ }
+
+ /* Arguments are ready. Create the new vector stmt. */
+- vec_compare = build2 (TREE_CODE (cond_expr), vectype,
+- vec_cond_lhs, vec_cond_rhs);
+- vec_cond_expr = build3 (VEC_COND_EXPR, vectype,
+- vec_compare, vec_then_clause, vec_else_clause);
+-
+- new_stmt = gimple_build_assign (vec_dest, vec_cond_expr);
+- new_temp = make_ssa_name (vec_dest, new_stmt);
+- gimple_assign_set_lhs (new_stmt, new_temp);
+- vect_finish_stmt_generation (stmt, new_stmt, gsi);
+- if (j == 0)
+- STMT_VINFO_VEC_STMT (stmt_info) = *vec_stmt = new_stmt;
+- else
+- STMT_VINFO_RELATED_STMT (prev_stmt_info) = new_stmt;
+-
+- prev_stmt_info = vinfo_for_stmt (new_stmt);
++ FOR_EACH_VEC_ELT (tree, vec_oprnds0, i, vec_cond_lhs)
++ {
++ vec_cond_rhs = VEC_index (tree, vec_oprnds1, i);
++ vec_then_clause = VEC_index (tree, vec_oprnds2, i);
++ vec_else_clause = VEC_index (tree, vec_oprnds3, i);
++
++ vec_compare = build2 (TREE_CODE (cond_expr), vectype,
++ vec_cond_lhs, vec_cond_rhs);
++ vec_cond_expr = build3 (VEC_COND_EXPR, vectype,
++ vec_compare, vec_then_clause, vec_else_clause);
++
++ new_stmt = gimple_build_assign (vec_dest, vec_cond_expr);
++ new_temp = make_ssa_name (vec_dest, new_stmt);
++ gimple_assign_set_lhs (new_stmt, new_temp);
++ vect_finish_stmt_generation (stmt, new_stmt, gsi);
++ if (slp_node)
++ VEC_quick_push (gimple, SLP_TREE_VEC_STMTS (slp_node), new_stmt);
++ }
++
++ if (slp_node)
++ continue;
++
++ if (j == 0)
++ STMT_VINFO_VEC_STMT (stmt_info) = *vec_stmt = new_stmt;
++ else
++ STMT_VINFO_RELATED_STMT (prev_stmt_info) = new_stmt;
++
++ prev_stmt_info = vinfo_for_stmt (new_stmt);
+ }
+
++ VEC_free (tree, heap, vec_oprnds0);
++ VEC_free (tree, heap, vec_oprnds1);
++ VEC_free (tree, heap, vec_oprnds2);
++ VEC_free (tree, heap, vec_oprnds3);
++
+ return true;
+ }
+
+@@ -5217,7 +5278,7 @@
+ || vectorizable_call (stmt, NULL, NULL)
+ || vectorizable_store (stmt, NULL, NULL, NULL)
+ || vectorizable_reduction (stmt, NULL, NULL, NULL)
+- || vectorizable_condition (stmt, NULL, NULL, NULL, 0));
++ || vectorizable_condition (stmt, NULL, NULL, NULL, 0, NULL));
+ else
+ {
+ if (bb_vinfo)
+@@ -5227,7 +5288,8 @@
+ || vectorizable_operation (stmt, NULL, NULL, node)
+ || vectorizable_assignment (stmt, NULL, NULL, node)
+ || vectorizable_load (stmt, NULL, NULL, node, NULL)
+- || vectorizable_store (stmt, NULL, NULL, node));
++ || vectorizable_store (stmt, NULL, NULL, node)
++ || vectorizable_condition (stmt, NULL, NULL, NULL, 0, node));
+ }
+
+ if (!ok)
+@@ -5343,8 +5405,7 @@
+ break;
+
+ case condition_vec_info_type:
+- gcc_assert (!slp_node);
+- done = vectorizable_condition (stmt, gsi, &vec_stmt, NULL, 0);
++ done = vectorizable_condition (stmt, gsi, &vec_stmt, NULL, 0, slp_node);
+ gcc_assert (done);
+ break;
+
+
+=== modified file 'gcc/tree-vectorizer.h'
+--- old/gcc/tree-vectorizer.h 2011-11-22 16:52:23 +0000
++++ new/gcc/tree-vectorizer.h 2011-11-22 17:10:17 +0000
+@@ -832,7 +832,7 @@
+ extern void vect_remove_stores (gimple);
+ extern bool vect_analyze_stmt (gimple, bool *, slp_tree);
+ extern bool vectorizable_condition (gimple, gimple_stmt_iterator *, gimple *,
+- tree, int);
++ tree, int, slp_tree);
+ extern void vect_get_load_cost (struct data_reference *, int, bool,
+ unsigned int *, unsigned int *);
+ extern void vect_get_store_cost (struct data_reference *, int, unsigned int *);
+
--- /dev/null
+2011-11-27 Ira Rosen <ira.rosen@linaro.org>
+
+ gcc/
+ * tree-vectorizer.h (vect_pattern_recog): Add new argument.
+ * tree-vect-loop.c (vect_analyze_loop_2): Update call to
+ vect_pattern_recog.
+ * tree-vect-patterns.c (widened_name_p): Pass basic block
+ info to vect_is_simple_use.
+ (vect_recog_dot_prod_pattern): Fail for basic blocks.
+ (vect_recog_widen_sum_pattern): Likewise.
+ (vect_handle_widen_op_by_const): Support basic blocks.
+ (vect_operation_fits_smaller_type,
+ vect_recog_over_widening_pattern): Likewise.
+ (vect_recog_mixed_size_cond_pattern): Support basic blocks.
+ Add printing.
+ (vect_mark_pattern_stmts): Update calls to new_stmt_vec_info.
+ (vect_pattern_recog_1): Check for reduction only in loops.
+ (vect_pattern_recog): Add new argument. Support basic blocks.
+ * tree-vect-stmts.c (vectorizable_conversion): Pass basic block
+ info to vect_is_simple_use_1.
+ * tree-vect-slp.c (vect_get_and_check_slp_defs): Support basic
+ blocks.
+ (vect_slp_analyze_bb_1): Call vect_pattern_recog.
+
+ gcc/testsuite/
+ * gcc.dg/vect/bb-slp-pattern-1.c: New test.
+ * gcc.dg/vect/bb-slp-pattern-2.c: New test.
+
+=== added file 'gcc/testsuite/gcc.dg/vect/bb-slp-pattern-1.c'
+--- old/gcc/testsuite/gcc.dg/vect/bb-slp-pattern-1.c 1970-01-01 00:00:00 +0000
++++ new/gcc/testsuite/gcc.dg/vect/bb-slp-pattern-1.c 2011-11-23 06:37:10 +0000
+@@ -0,0 +1,55 @@
++/* { dg-require-effective-target vect_int } */
++
++#include <stdarg.h>
++#include "tree-vect.h"
++
++#define N 8
++
++unsigned short X[N];
++unsigned short Y[N];
++unsigned int result[N];
++
++/* unsigned short->unsigned int widening-mult. */
++__attribute__ ((noinline, noclone)) void
++foo (void)
++{
++ result[0] = (unsigned int)(X[0] * Y[0]);
++ result[1] = (unsigned int)(X[1] * Y[1]);
++ result[2] = (unsigned int)(X[2] * Y[2]);
++ result[3] = (unsigned int)(X[3] * Y[3]);
++ result[4] = (unsigned int)(X[4] * Y[4]);
++ result[5] = (unsigned int)(X[5] * Y[5]);
++ result[6] = (unsigned int)(X[6] * Y[6]);
++ result[7] = (unsigned int)(X[7] * Y[7]);
++}
++
++int main (void)
++{
++ int i, tmp;
++
++ check_vect ();
++
++ for (i = 0; i < N; i++)
++ {
++ X[i] = i;
++ Y[i] = 64-i;
++ }
++
++ foo ();
++
++ for (i = 0; i < N; i++)
++ {
++ __asm__ volatile ("");
++ tmp = X[i] * Y[i];
++ if (result[i] != tmp)
++ abort ();
++ }
++
++ return 0;
++}
++
++/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 1 "slp" { target { vect_widen_mult_hi_to_si || vect_unpack } } } } */
++/* { dg-final { scan-tree-dump-times "vect_recog_widen_mult_pattern: detected" 8 "slp" { target vect_widen_mult_hi_to_si_pattern } } } */
++/* { dg-final { scan-tree-dump-times "pattern recognized" 8 "slp" { target vect_widen_mult_hi_to_si_pattern } } } */
++/* { dg-final { cleanup-tree-dump "slp" } } */
++
+
+=== added file 'gcc/testsuite/gcc.dg/vect/bb-slp-pattern-2.c'
+--- old/gcc/testsuite/gcc.dg/vect/bb-slp-pattern-2.c 1970-01-01 00:00:00 +0000
++++ new/gcc/testsuite/gcc.dg/vect/bb-slp-pattern-2.c 2011-11-23 06:37:10 +0000
+@@ -0,0 +1,53 @@
++/* { dg-require-effective-target vect_condition } */
++
++#include "tree-vect.h"
++
++#define N 128
++
++__attribute__((noinline, noclone)) void
++foo (short * __restrict__ a, int * __restrict__ b, int stride)
++{
++ int i;
++
++ for (i = 0; i < N/stride; i++, a += stride, b += stride)
++ {
++ a[0] = b[0] ? 1 : 7;
++ a[1] = b[1] ? 2 : 0;
++ a[2] = b[2] ? 3 : 0;
++ a[3] = b[3] ? 4 : 0;
++ a[4] = b[4] ? 5 : 0;
++ a[5] = b[5] ? 6 : 0;
++ a[6] = b[6] ? 7 : 0;
++ a[7] = b[7] ? 8 : 0;
++ }
++}
++
++short a[N];
++int b[N];
++int main ()
++{
++ int i;
++
++ check_vect ();
++
++ for (i = 0; i < N; i++)
++ {
++ a[i] = i;
++ b[i] = -i;
++ }
++
++ foo (a, b, 8);
++
++ for (i = 1; i < N; i++)
++ if (a[i] != i%8 + 1)
++ abort ();
++
++ if (a[0] != 7)
++ abort ();
++
++ return 0;
++}
++
++/* { dg-final { scan-tree-dump-times "basic block vectorized using SLP" 1 "slp" { target { vect_element_align && vect_pack_trunc } } } } */
++/* { dg-final { cleanup-tree-dump "slp" } } */
++
+
+=== modified file 'gcc/tree-vect-loop.c'
+--- old/gcc/tree-vect-loop.c 2011-11-20 08:24:08 +0000
++++ new/gcc/tree-vect-loop.c 2011-11-23 06:47:35 +0000
+@@ -1458,7 +1458,7 @@
+
+ vect_analyze_scalar_cycles (loop_vinfo);
+
+- vect_pattern_recog (loop_vinfo);
++ vect_pattern_recog (loop_vinfo, NULL);
+
+ /* Data-flow analysis to detect stmts that do not need to be vectorized. */
+
+
+=== modified file 'gcc/tree-vect-patterns.c'
+--- old/gcc/tree-vect-patterns.c 2011-11-20 09:11:09 +0000
++++ new/gcc/tree-vect-patterns.c 2011-11-23 07:49:33 +0000
+@@ -83,11 +83,13 @@
+ tree oprnd0;
+ enum vect_def_type dt;
+ tree def;
++ bb_vec_info bb_vinfo;
+
+ stmt_vinfo = vinfo_for_stmt (use_stmt);
+ loop_vinfo = STMT_VINFO_LOOP_VINFO (stmt_vinfo);
++ bb_vinfo = STMT_VINFO_BB_VINFO (stmt_vinfo);
+
+- if (!vect_is_simple_use (name, loop_vinfo, NULL, def_stmt, &def, &dt))
++ if (!vect_is_simple_use (name, loop_vinfo, bb_vinfo, def_stmt, &def, &dt))
+ return false;
+
+ if (dt != vect_internal_def
+@@ -111,7 +113,7 @@
+ || (TYPE_PRECISION (type) < (TYPE_PRECISION (*half_type) * 2)))
+ return false;
+
+- if (!vect_is_simple_use (oprnd0, loop_vinfo, NULL, &dummy_gimple, &dummy,
++ if (!vect_is_simple_use (oprnd0, loop_vinfo, bb_vinfo, &dummy_gimple, &dummy,
+ &dt))
+ return false;
+
+@@ -188,9 +190,14 @@
+ gimple pattern_stmt;
+ tree prod_type;
+ loop_vec_info loop_info = STMT_VINFO_LOOP_VINFO (stmt_vinfo);
+- struct loop *loop = LOOP_VINFO_LOOP (loop_info);
++ struct loop *loop;
+ tree var, rhs;
+
++ if (!loop_info)
++ return NULL;
++
++ loop = LOOP_VINFO_LOOP (loop_info);
++
+ if (!is_gimple_assign (last_stmt))
+ return NULL;
+
+@@ -358,8 +365,16 @@
+ {
+ tree new_type, new_oprnd, tmp;
+ gimple new_stmt;
+- loop_vec_info loop_info = STMT_VINFO_LOOP_VINFO (vinfo_for_stmt (stmt));
+- struct loop *loop = LOOP_VINFO_LOOP (loop_info);
++ loop_vec_info loop_vinfo;
++ struct loop *loop = NULL;
++ bb_vec_info bb_vinfo;
++ stmt_vec_info stmt_vinfo;
++
++ stmt_vinfo = vinfo_for_stmt (stmt);
++ loop_vinfo = STMT_VINFO_LOOP_VINFO (stmt_vinfo);
++ bb_vinfo = STMT_VINFO_BB_VINFO (stmt_vinfo);
++ if (loop_vinfo)
++ loop = LOOP_VINFO_LOOP (loop_vinfo);
+
+ if (code != MULT_EXPR && code != LSHIFT_EXPR)
+ return false;
+@@ -377,7 +392,9 @@
+
+ if (TYPE_PRECISION (type) < (TYPE_PRECISION (*half_type) * 4)
+ || !gimple_bb (def_stmt)
+- || !flow_bb_inside_loop_p (loop, gimple_bb (def_stmt))
++ || (loop && !flow_bb_inside_loop_p (loop, gimple_bb (def_stmt)))
++ || (!loop && gimple_bb (def_stmt) != BB_VINFO_BB (bb_vinfo)
++ && gimple_code (def_stmt) != GIMPLE_PHI)
+ || !vinfo_for_stmt (def_stmt))
+ return false;
+
+@@ -774,9 +791,14 @@
+ tree type, half_type;
+ gimple pattern_stmt;
+ loop_vec_info loop_info = STMT_VINFO_LOOP_VINFO (stmt_vinfo);
+- struct loop *loop = LOOP_VINFO_LOOP (loop_info);
++ struct loop *loop;
+ tree var;
+
++ if (!loop_info)
++ return NULL;
++
++ loop = LOOP_VINFO_LOOP (loop_info);
++
+ if (!is_gimple_assign (last_stmt))
+ return NULL;
+
+@@ -877,7 +899,11 @@
+ gimple def_stmt, new_stmt;
+ bool first = false;
+ loop_vec_info loop_info = STMT_VINFO_LOOP_VINFO (vinfo_for_stmt (stmt));
+- struct loop *loop = LOOP_VINFO_LOOP (loop_info);
++ bb_vec_info bb_info = STMT_VINFO_BB_VINFO (vinfo_for_stmt (stmt));
++ struct loop *loop = NULL;
++
++ if (loop_info)
++ loop = LOOP_VINFO_LOOP (loop_info);
+
+ *new_def_stmt = NULL;
+
+@@ -909,7 +935,9 @@
+ first = true;
+ if (!widened_name_p (oprnd, stmt, &half_type, &def_stmt, false)
+ || !gimple_bb (def_stmt)
+- || !flow_bb_inside_loop_p (loop, gimple_bb (def_stmt))
++ || (loop && !flow_bb_inside_loop_p (loop, gimple_bb (def_stmt)))
++ || (!loop && gimple_bb (def_stmt) != BB_VINFO_BB (bb_info)
++ && gimple_code (def_stmt) != GIMPLE_PHI)
+ || !vinfo_for_stmt (def_stmt))
+ return false;
+ }
+@@ -1087,7 +1115,16 @@
+ int nuses = 0;
+ tree var = NULL_TREE, new_type = NULL_TREE, tmp, new_oprnd;
+ bool first;
+- struct loop *loop = (gimple_bb (stmt))->loop_father;
++ loop_vec_info loop_vinfo;
++ struct loop *loop = NULL;
++ bb_vec_info bb_vinfo;
++ stmt_vec_info stmt_vinfo;
++
++ stmt_vinfo = vinfo_for_stmt (stmt);
++ loop_vinfo = STMT_VINFO_LOOP_VINFO (stmt_vinfo);
++ bb_vinfo = STMT_VINFO_BB_VINFO (stmt_vinfo);
++ if (loop_vinfo)
++ loop = LOOP_VINFO_LOOP (loop_vinfo);
+
+ first = true;
+ while (1)
+@@ -1120,7 +1157,8 @@
+
+ if (nuses != 1 || !is_gimple_assign (use_stmt)
+ || !gimple_bb (use_stmt)
+- || !flow_bb_inside_loop_p (loop, gimple_bb (use_stmt)))
++ || (loop && !flow_bb_inside_loop_p (loop, gimple_bb (use_stmt)))
++ || (!loop && gimple_bb (use_stmt) != BB_VINFO_BB (bb_vinfo)))
+ return NULL;
+
+ /* Create pattern statement for STMT. */
+@@ -1485,6 +1523,7 @@
+ enum machine_mode cmpmode;
+ gimple pattern_stmt, def_stmt;
+ loop_vec_info loop_vinfo = STMT_VINFO_LOOP_VINFO (stmt_vinfo);
++ bb_vec_info bb_vinfo = STMT_VINFO_BB_VINFO (stmt_vinfo);
+
+ if (!is_gimple_assign (last_stmt)
+ || gimple_assign_rhs_code (last_stmt) != COND_EXPR
+@@ -1538,7 +1577,8 @@
+ tmp = build3 (COND_EXPR, comp_type, unshare_expr (cond_expr),
+ fold_convert (comp_type, then_clause),
+ fold_convert (comp_type, else_clause));
+- def_stmt = gimple_build_assign (vect_recog_temp_ssa_var (comp_type, NULL), tmp);
++ def_stmt = gimple_build_assign (vect_recog_temp_ssa_var (comp_type, NULL),
++ tmp);
+
+ pattern_stmt
+ = gimple_build_assign_with_ops (NOP_EXPR,
+@@ -1546,12 +1586,15 @@
+ gimple_assign_lhs (def_stmt), NULL_TREE);
+
+ STMT_VINFO_PATTERN_DEF_STMT (stmt_vinfo) = def_stmt;
+- def_stmt_info = new_stmt_vec_info (def_stmt, loop_vinfo, NULL);
++ def_stmt_info = new_stmt_vec_info (def_stmt, loop_vinfo, bb_vinfo);
+ set_vinfo_for_stmt (def_stmt, def_stmt_info);
+ STMT_VINFO_VECTYPE (def_stmt_info) = comp_vectype;
+ *type_in = vectype;
+ *type_out = vectype;
+
++ if (vect_print_dump_info (REPORT_DETAILS))
++ fprintf (vect_dump, "vect_recog_mixed_size_cond_pattern: detected: ");
++
+ return pattern_stmt;
+ }
+
+@@ -1565,10 +1608,11 @@
+ stmt_vec_info pattern_stmt_info, def_stmt_info;
+ stmt_vec_info orig_stmt_info = vinfo_for_stmt (orig_stmt);
+ loop_vec_info loop_vinfo = STMT_VINFO_LOOP_VINFO (orig_stmt_info);
++ bb_vec_info bb_vinfo = STMT_VINFO_BB_VINFO (orig_stmt_info);
+ gimple def_stmt;
+
+ set_vinfo_for_stmt (pattern_stmt,
+- new_stmt_vec_info (pattern_stmt, loop_vinfo, NULL));
++ new_stmt_vec_info (pattern_stmt, loop_vinfo, bb_vinfo));
+ gimple_set_bb (pattern_stmt, gimple_bb (orig_stmt));
+ pattern_stmt_info = vinfo_for_stmt (pattern_stmt);
+
+@@ -1586,7 +1630,7 @@
+ def_stmt_info = vinfo_for_stmt (def_stmt);
+ if (def_stmt_info == NULL)
+ {
+- def_stmt_info = new_stmt_vec_info (def_stmt, loop_vinfo, NULL);
++ def_stmt_info = new_stmt_vec_info (def_stmt, loop_vinfo, bb_vinfo);
+ set_vinfo_for_stmt (def_stmt, def_stmt_info);
+ }
+ gimple_set_bb (def_stmt, gimple_bb (orig_stmt));
+@@ -1697,9 +1741,10 @@
+
+ /* Patterns cannot be vectorized using SLP, because they change the order of
+ computation. */
+- FOR_EACH_VEC_ELT (gimple, LOOP_VINFO_REDUCTIONS (loop_vinfo), i, next)
+- if (next == stmt)
+- VEC_ordered_remove (gimple, LOOP_VINFO_REDUCTIONS (loop_vinfo), i);
++ if (loop_vinfo)
++ FOR_EACH_VEC_ELT (gimple, LOOP_VINFO_REDUCTIONS (loop_vinfo), i, next)
++ if (next == stmt)
++ VEC_ordered_remove (gimple, LOOP_VINFO_REDUCTIONS (loop_vinfo), i);
+
+ /* It is possible that additional pattern stmts are created and inserted in
+ STMTS_TO_REPLACE. We create a stmt_info for each of them, and mark the
+@@ -1799,26 +1844,46 @@
+ be recorded in S3. */
+
+ void
+-vect_pattern_recog (loop_vec_info loop_vinfo)
++vect_pattern_recog (loop_vec_info loop_vinfo, bb_vec_info bb_vinfo)
+ {
+- struct loop *loop = LOOP_VINFO_LOOP (loop_vinfo);
+- basic_block *bbs = LOOP_VINFO_BBS (loop_vinfo);
+- unsigned int nbbs = loop->num_nodes;
++ struct loop *loop;
++ basic_block *bbs, bb;
++ unsigned int nbbs;
+ gimple_stmt_iterator si;
+ unsigned int i, j;
+ gimple (* vect_recog_func_ptr) (VEC (gimple, heap) **, tree *, tree *);
+ VEC (gimple, heap) *stmts_to_replace = VEC_alloc (gimple, heap, 1);
++ gimple stmt;
+
+ if (vect_print_dump_info (REPORT_DETAILS))
+ fprintf (vect_dump, "=== vect_pattern_recog ===");
+
+- /* Scan through the loop stmts, applying the pattern recognition
++ if (loop_vinfo)
++ {
++ loop = LOOP_VINFO_LOOP (loop_vinfo);
++ bbs = LOOP_VINFO_BBS (loop_vinfo);
++ nbbs = loop->num_nodes;
++ }
++ else
++ {
++ bb = BB_VINFO_BB (bb_vinfo);
++ nbbs = 1;
++ bbs = XNEW (basic_block);
++ bbs[0] = bb;
++ }
++
++ /* Scan through the stmts, applying the pattern recognition
+ functions starting at each stmt visited: */
+ for (i = 0; i < nbbs; i++)
+ {
+ basic_block bb = bbs[i];
+ for (si = gsi_start_bb (bb); !gsi_end_p (si); gsi_next (&si))
+ {
++ if (bb_vinfo && (stmt = gsi_stmt (si))
++ && vinfo_for_stmt (stmt)
++ && !STMT_VINFO_VECTORIZABLE (vinfo_for_stmt (stmt)))
++ continue;
++
+ /* Scan over all generic vect_recog_xxx_pattern functions. */
+ for (j = 0; j < NUM_PATTERNS; j++)
+ {
+@@ -1830,4 +1895,6 @@
+ }
+
+ VEC_free (gimple, heap, stmts_to_replace);
++ if (bb_vinfo)
++ free (bbs);
+ }
+
+=== modified file 'gcc/tree-vect-slp.c'
+--- old/gcc/tree-vect-slp.c 2011-11-21 06:58:40 +0000
++++ new/gcc/tree-vect-slp.c 2011-11-23 06:47:35 +0000
+@@ -255,12 +255,14 @@
+ /* Check if DEF_STMT is a part of a pattern in LOOP and get the def stmt
+ from the pattern. Check that all the stmts of the node are in the
+ pattern. */
+- if (loop && def_stmt && gimple_bb (def_stmt)
+- && flow_bb_inside_loop_p (loop, gimple_bb (def_stmt))
++ if (def_stmt && gimple_bb (def_stmt)
++ && ((loop && flow_bb_inside_loop_p (loop, gimple_bb (def_stmt)))
++ || (!loop && gimple_bb (def_stmt) == BB_VINFO_BB (bb_vinfo)
++ && gimple_code (def_stmt) != GIMPLE_PHI))
+ && vinfo_for_stmt (def_stmt)
+ && STMT_VINFO_IN_PATTERN_P (vinfo_for_stmt (def_stmt))
+- && !STMT_VINFO_RELEVANT (vinfo_for_stmt (def_stmt))
+- && !STMT_VINFO_LIVE_P (vinfo_for_stmt (def_stmt)))
++ && !STMT_VINFO_RELEVANT (vinfo_for_stmt (def_stmt))
++ && !STMT_VINFO_LIVE_P (vinfo_for_stmt (def_stmt)))
+ {
+ pattern = true;
+ if (!first && !oprnd_info->first_pattern)
+@@ -1972,6 +1974,8 @@
+ return NULL;
+ }
+
++ vect_pattern_recog (NULL, bb_vinfo);
++
+ if (!vect_analyze_data_ref_dependences (NULL, bb_vinfo, &max_vf,
+ &data_dependence_in_bb)
+ || min_vf > max_vf
+
+=== modified file 'gcc/tree-vect-stmts.c'
+--- old/gcc/tree-vect-stmts.c 2011-11-22 17:10:17 +0000
++++ new/gcc/tree-vect-stmts.c 2011-11-23 06:47:35 +0000
+@@ -3451,11 +3451,11 @@
+ /* For WIDEN_MULT_EXPR, if OP0 is a constant, use the type of
+ OP1. */
+ if (CONSTANT_CLASS_P (op0))
+- ok = vect_is_simple_use_1 (op1, loop_vinfo, NULL,
++ ok = vect_is_simple_use_1 (op1, loop_vinfo, bb_vinfo,
+ &def_stmt, &def, &dt[1], &vectype_in);
+ else
+- ok = vect_is_simple_use (op1, loop_vinfo, NULL, &def_stmt, &def,
+- &dt[1]);
++ ok = vect_is_simple_use (op1, loop_vinfo, bb_vinfo, &def_stmt,
++ &def, &dt[1]);
+
+ if (!ok)
+ {
+
+=== modified file 'gcc/tree-vectorizer.h'
+--- old/gcc/tree-vectorizer.h 2011-11-22 17:10:17 +0000
++++ new/gcc/tree-vectorizer.h 2011-11-23 06:47:35 +0000
+@@ -918,7 +918,7 @@
+ in the future. */
+ typedef gimple (* vect_recog_func_ptr) (VEC (gimple, heap) **, tree *, tree *);
+ #define NUM_PATTERNS 7
+-void vect_pattern_recog (loop_vec_info);
++void vect_pattern_recog (loop_vec_info, bb_vec_info);
+
+ /* In tree-vectorizer.c. */
+ unsigned vectorize_loops (void);
+
--- /dev/null
+2011-11-28 David Alan Gilbert <david.gilbert@linaro.org>
+
+ Backport from mainline (svn r19983):
+
+ 2011-10-14 David Alan Gilbert <david.gilbert@linaro.org>
+
+ gcc/testsuite/
+ * gcc.dg/di-longlong64-sync-1.c: New test.
+ * gcc.dg/di-sync-multithread.c: New test.
+ * gcc.target/arm/di-longlong64-sync-withhelpers.c: New test.
+ * gcc.target/arm/di-longlong64-sync-withldrexd.c: New test.
+ * lib/target-supports.exp: (arm_arch_*_ok): Series of effective-target
+ tests for v5, v6, v6k, and v7-a, and add-options helpers.
+ (check_effective_target_arm_arm_ok): New helper.
+ (check_effective_target_sync_longlong): New helper.
+
+2011-11-28 David Alan Gilbert <david.gilbert@linaro.org>
+
+ Backport from mainline (svn r19982):
+
+ 2011-10-14 David Alan Gilbert <david.gilbert@linaro.org>
+
+ gcc/
+ * config/arm/linux-atomic-64bit.c: New (based on linux-atomic.c).
+ * config/arm/linux-atomic.c: Change comment to point to 64bit version.
+ (SYNC_LOCK_RELEASE): Instantiate 64bit version.
+ * config/arm/t-linux-eabi: Pull in linux-atomic-64bit.c.
+
+2011-11-28 David Alan Gilbert <david.gilbert@linaro.org>
+
+ Backport from mainline (svn r19981):
+
+ 2011-10-14 David Alan Gilbert <david.gilbert@linaro.org>
+
+ gcc/
+ * config/arm/arm.c (arm_output_ldrex): Support ldrexd.
+ (arm_output_strex): Support strexd.
+ (arm_output_it): New helper to output it in Thumb2 mode only.
+ (arm_output_sync_loop): Support DI mode. Change comment to
+ not support const_int.
+ (arm_expand_sync): Support DI mode.
+ * config/arm/arm.h (TARGET_HAVE_LDREXBHD): Split into LDREXBH
+ and LDREXD.
+ * config/arm/iterators.md (NARROW): move from sync.md.
+ (QHSD): New iterator for all current ARM integer modes.
+ (SIDI): New iterator for SI and DI modes only.
+ * config/arm/sync.md (sync_predtab): New mode_attr.
+ (sync_compare_and_swapsi): Fold into sync_compare_and_swap<mode>.
+ (sync_lock_test_and_setsi): Fold into sync_lock_test_and_setsi<mode>.
+ (sync_<sync_optab>si): Fold into sync_<sync_optab><mode>.
+ (sync_nandsi): Fold into sync_nand<mode>.
+ (sync_new_<sync_optab>si): Fold into sync_new_<sync_optab><mode>.
+ (sync_new_nandsi): Fold into sync_new_nand<mode>.
+ (sync_old_<sync_optab>si): Fold into sync_old_<sync_optab><mode>.
+ (sync_old_nandsi): Fold into sync_old_nand<mode>.
+ (sync_compare_and_swap<mode>): Support SI & DI.
+ (sync_lock_test_and_set<mode>): Likewise.
+ (sync_<sync_optab><mode>): Likewise.
+ (sync_nand<mode>): Likewise.
+ (sync_new_<sync_optab><mode>): Likewise.
+ (sync_new_nand<mode>): Likewise.
+ (sync_old_<sync_optab><mode>): Likewise.
+ (sync_old_nand<mode>): Likewise.
+ (arm_sync_compare_and_swapsi): Turn into iterator on SI & DI.
+ (arm_sync_lock_test_and_setsi): Likewise.
+ (arm_sync_new_<sync_optab>si): Likewise.
+ (arm_sync_new_nandsi): Likewise.
+ (arm_sync_old_<sync_optab>si): Likewise.
+ (arm_sync_old_nandsi): Likewise.
+ (arm_sync_compare_and_swap<mode> NARROW): use sync_predtab, fix indent.
+ (arm_sync_lock_test_and_setsi<mode> NARROW): Likewise.
+ (arm_sync_new_<sync_optab><mode> NARROW): Likewise.
+ (arm_sync_new_nand<mode> NARROW): Likewise.
+ (arm_sync_old_<sync_optab><mode> NARROW): Likewise.
+ (arm_sync_old_nand<mode> NARROW): Likewise.
+
+2011-11-28 David Alan Gilbert <david.gilbert@linaro.org>
+
+ Backport from mainline (svn r19980):
+
+ 2011-10-14 David Alan Gilbert <david.gilbert@linaro.org>
+
+ PR target/48126
+
+ gcc/
+ * config/arm/arm.c (arm_output_sync_loop): Move label before barrier.
+
+2011-11-28 David Alan Gilbert <david.gilbert@linaro.org>
+
+ Backport from mainline (svn r19979):
+
+ 2011-10-14 David Alan Gilbert <david.gilbert@linaro.org>
+
+ gcc/
+ * config/arm/arm.h (TARGET_HAVE_DMB_MCR): MCR Not available in Thumb1.
+
+=== modified file 'gcc/config/arm/arm.c'
+--- old/gcc/config/arm/arm.c 2011-11-21 01:45:54 +0000
++++ new/gcc/config/arm/arm.c 2011-11-28 15:07:01 +0000
+@@ -24307,12 +24307,26 @@
+ rtx target,
+ rtx memory)
+ {
+- const char *suffix = arm_ldrex_suffix (mode);
+- rtx operands[2];
++ rtx operands[3];
+
+ operands[0] = target;
+- operands[1] = memory;
+- arm_output_asm_insn (emit, 0, operands, "ldrex%s\t%%0, %%C1", suffix);
++ if (mode != DImode)
++ {
++ const char *suffix = arm_ldrex_suffix (mode);
++ operands[1] = memory;
++ arm_output_asm_insn (emit, 0, operands, "ldrex%s\t%%0, %%C1", suffix);
++ }
++ else
++ {
++ /* The restrictions on target registers in ARM mode are that the two
++ registers are consecutive and the first one is even; Thumb is
++ actually more flexible, but DI should give us this anyway.
++ Note that the 1st register always gets the lowest word in memory. */
++ gcc_assert ((REGNO (target) & 1) == 0);
++ operands[1] = gen_rtx_REG (SImode, REGNO (target) + 1);
++ operands[2] = memory;
++ arm_output_asm_insn (emit, 0, operands, "ldrexd\t%%0, %%1, %%C2");
++ }
+ }
+
+ /* Emit a strex{b,h,d, } instruction appropriate for the specified
+@@ -24325,14 +24339,41 @@
+ rtx value,
+ rtx memory)
+ {
+- const char *suffix = arm_ldrex_suffix (mode);
+- rtx operands[3];
++ rtx operands[4];
+
+ operands[0] = result;
+ operands[1] = value;
+- operands[2] = memory;
+- arm_output_asm_insn (emit, 0, operands, "strex%s%s\t%%0, %%1, %%C2", suffix,
+- cc);
++ if (mode != DImode)
++ {
++ const char *suffix = arm_ldrex_suffix (mode);
++ operands[2] = memory;
++ arm_output_asm_insn (emit, 0, operands, "strex%s%s\t%%0, %%1, %%C2",
++ suffix, cc);
++ }
++ else
++ {
++ /* The restrictions on target registers in ARM mode are that the two
++ registers are consecutive and the first one is even; Thumb is
++ actually more flexible, but DI should give us this anyway.
++ Note that the 1st register always gets the lowest word in memory. */
++ gcc_assert ((REGNO (value) & 1) == 0 || TARGET_THUMB2);
++ operands[2] = gen_rtx_REG (SImode, REGNO (value) + 1);
++ operands[3] = memory;
++ arm_output_asm_insn (emit, 0, operands, "strexd%s\t%%0, %%1, %%2, %%C3",
++ cc);
++ }
++}
++
++/* Helper to emit an it instruction in Thumb2 mode only; although the assembler
++ will ignore it in ARM mode, emitting it will mess up instruction counts we
++ sometimes keep 'flags' are the extra t's and e's if it's more than one
++ instruction that is conditional. */
++static void
++arm_output_it (emit_f emit, const char *flags, const char *cond)
++{
++ rtx operands[1]; /* Don't actually use the operand. */
++ if (TARGET_THUMB2)
++ arm_output_asm_insn (emit, 0, operands, "it%s\t%s", flags, cond);
+ }
+
+ /* Helper to emit a two operand instruction. */
+@@ -24374,7 +24415,7 @@
+
+ required_value:
+
+- RTX register or const_int representing the required old_value for
++ RTX register representing the required old_value for
+ the modify to continue, if NULL no comparsion is performed. */
+ static void
+ arm_output_sync_loop (emit_f emit,
+@@ -24388,7 +24429,13 @@
+ enum attr_sync_op sync_op,
+ int early_barrier_required)
+ {
+- rtx operands[1];
++ rtx operands[2];
++ /* We'll use the lo for the normal rtx in the none-DI case
++ as well as the least-sig word in the DI case. */
++ rtx old_value_lo, required_value_lo, new_value_lo, t1_lo;
++ rtx old_value_hi, required_value_hi, new_value_hi, t1_hi;
++
++ bool is_di = mode == DImode;
+
+ gcc_assert (t1 != t2);
+
+@@ -24399,82 +24446,142 @@
+
+ arm_output_ldrex (emit, mode, old_value, memory);
+
++ if (is_di)
++ {
++ old_value_lo = gen_lowpart (SImode, old_value);
++ old_value_hi = gen_highpart (SImode, old_value);
++ if (required_value)
++ {
++ required_value_lo = gen_lowpart (SImode, required_value);
++ required_value_hi = gen_highpart (SImode, required_value);
++ }
++ else
++ {
++ /* Silence false potentially unused warning. */
++ required_value_lo = NULL_RTX;
++ required_value_hi = NULL_RTX;
++ }
++ new_value_lo = gen_lowpart (SImode, new_value);
++ new_value_hi = gen_highpart (SImode, new_value);
++ t1_lo = gen_lowpart (SImode, t1);
++ t1_hi = gen_highpart (SImode, t1);
++ }
++ else
++ {
++ old_value_lo = old_value;
++ new_value_lo = new_value;
++ required_value_lo = required_value;
++ t1_lo = t1;
++
++ /* Silence false potentially unused warning. */
++ t1_hi = NULL_RTX;
++ new_value_hi = NULL_RTX;
++ required_value_hi = NULL_RTX;
++ old_value_hi = NULL_RTX;
++ }
++
+ if (required_value)
+ {
+- rtx operands[2];
++ operands[0] = old_value_lo;
++ operands[1] = required_value_lo;
+
+- operands[0] = old_value;
+- operands[1] = required_value;
+ arm_output_asm_insn (emit, 0, operands, "cmp\t%%0, %%1");
++ if (is_di)
++ {
++ arm_output_it (emit, "", "eq");
++ arm_output_op2 (emit, "cmpeq", old_value_hi, required_value_hi);
++ }
+ arm_output_asm_insn (emit, 0, operands, "bne\t%sLSYB%%=", LOCAL_LABEL_PREFIX);
+ }
+
+ switch (sync_op)
+ {
+ case SYNC_OP_ADD:
+- arm_output_op3 (emit, "add", t1, old_value, new_value);
++ arm_output_op3 (emit, is_di ? "adds" : "add",
++ t1_lo, old_value_lo, new_value_lo);
++ if (is_di)
++ arm_output_op3 (emit, "adc", t1_hi, old_value_hi, new_value_hi);
+ break;
+
+ case SYNC_OP_SUB:
+- arm_output_op3 (emit, "sub", t1, old_value, new_value);
++ arm_output_op3 (emit, is_di ? "subs" : "sub",
++ t1_lo, old_value_lo, new_value_lo);
++ if (is_di)
++ arm_output_op3 (emit, "sbc", t1_hi, old_value_hi, new_value_hi);
+ break;
+
+ case SYNC_OP_IOR:
+- arm_output_op3 (emit, "orr", t1, old_value, new_value);
++ arm_output_op3 (emit, "orr", t1_lo, old_value_lo, new_value_lo);
++ if (is_di)
++ arm_output_op3 (emit, "orr", t1_hi, old_value_hi, new_value_hi);
+ break;
+
+ case SYNC_OP_XOR:
+- arm_output_op3 (emit, "eor", t1, old_value, new_value);
++ arm_output_op3 (emit, "eor", t1_lo, old_value_lo, new_value_lo);
++ if (is_di)
++ arm_output_op3 (emit, "eor", t1_hi, old_value_hi, new_value_hi);
+ break;
+
+ case SYNC_OP_AND:
+- arm_output_op3 (emit,"and", t1, old_value, new_value);
++ arm_output_op3 (emit,"and", t1_lo, old_value_lo, new_value_lo);
++ if (is_di)
++ arm_output_op3 (emit, "and", t1_hi, old_value_hi, new_value_hi);
+ break;
+
+ case SYNC_OP_NAND:
+- arm_output_op3 (emit, "and", t1, old_value, new_value);
+- arm_output_op2 (emit, "mvn", t1, t1);
++ arm_output_op3 (emit, "and", t1_lo, old_value_lo, new_value_lo);
++ if (is_di)
++ arm_output_op3 (emit, "and", t1_hi, old_value_hi, new_value_hi);
++ arm_output_op2 (emit, "mvn", t1_lo, t1_lo);
++ if (is_di)
++ arm_output_op2 (emit, "mvn", t1_hi, t1_hi);
+ break;
+
+ case SYNC_OP_NONE:
+ t1 = new_value;
++ t1_lo = new_value_lo;
++ if (is_di)
++ t1_hi = new_value_hi;
+ break;
+ }
+
++ /* Note that the result of strex is a 0/1 flag that's always 1 register. */
+ if (t2)
+ {
+- arm_output_strex (emit, mode, "", t2, t1, memory);
+- operands[0] = t2;
+- arm_output_asm_insn (emit, 0, operands, "teq\t%%0, #0");
+- arm_output_asm_insn (emit, 0, operands, "bne\t%sLSYT%%=",
+- LOCAL_LABEL_PREFIX);
++ arm_output_strex (emit, mode, "", t2, t1, memory);
++ operands[0] = t2;
++ arm_output_asm_insn (emit, 0, operands, "teq\t%%0, #0");
++ arm_output_asm_insn (emit, 0, operands, "bne\t%sLSYT%%=",
++ LOCAL_LABEL_PREFIX);
+ }
+ else
+ {
+ /* Use old_value for the return value because for some operations
+ the old_value can easily be restored. This saves one register. */
+- arm_output_strex (emit, mode, "", old_value, t1, memory);
+- operands[0] = old_value;
++ arm_output_strex (emit, mode, "", old_value_lo, t1, memory);
++ operands[0] = old_value_lo;
+ arm_output_asm_insn (emit, 0, operands, "teq\t%%0, #0");
+ arm_output_asm_insn (emit, 0, operands, "bne\t%sLSYT%%=",
+ LOCAL_LABEL_PREFIX);
+
++ /* Note that we only used the _lo half of old_value as a temporary
++ so in DI we don't have to restore the _hi part. */
+ switch (sync_op)
+ {
+ case SYNC_OP_ADD:
+- arm_output_op3 (emit, "sub", old_value, t1, new_value);
++ arm_output_op3 (emit, "sub", old_value_lo, t1_lo, new_value_lo);
+ break;
+
+ case SYNC_OP_SUB:
+- arm_output_op3 (emit, "add", old_value, t1, new_value);
++ arm_output_op3 (emit, "add", old_value_lo, t1_lo, new_value_lo);
+ break;
+
+ case SYNC_OP_XOR:
+- arm_output_op3 (emit, "eor", old_value, t1, new_value);
++ arm_output_op3 (emit, "eor", old_value_lo, t1_lo, new_value_lo);
+ break;
+
+ case SYNC_OP_NONE:
+- arm_output_op2 (emit, "mov", old_value, required_value);
++ arm_output_op2 (emit, "mov", old_value_lo, required_value_lo);
+ break;
+
+ default:
+@@ -24482,8 +24589,11 @@
+ }
+ }
+
++ /* Note: label is before barrier so that in cmp failure case we still get
++ a barrier to stop subsequent loads floating upwards past the ldrex
++ PR target/48126. */
++ arm_output_asm_insn (emit, 1, operands, "%sLSYB%%=:", LOCAL_LABEL_PREFIX);
+ arm_process_output_memory_barrier (emit, NULL);
+- arm_output_asm_insn (emit, 1, operands, "%sLSYB%%=:", LOCAL_LABEL_PREFIX);
+ }
+
+ static rtx
+@@ -24577,7 +24687,7 @@
+ target = gen_reg_rtx (mode);
+
+ memory = arm_legitimize_sync_memory (memory);
+- if (mode != SImode)
++ if (mode != SImode && mode != DImode)
+ {
+ rtx load_temp = gen_reg_rtx (SImode);
+
+
+=== modified file 'gcc/config/arm/arm.h'
+--- old/gcc/config/arm/arm.h 2011-11-21 01:45:54 +0000
++++ new/gcc/config/arm/arm.h 2011-11-28 15:07:01 +0000
+@@ -300,7 +300,8 @@
+ #define TARGET_HAVE_DMB (arm_arch7)
+
+ /* Nonzero if this chip implements a memory barrier via CP15. */
+-#define TARGET_HAVE_DMB_MCR (arm_arch6k && ! TARGET_HAVE_DMB)
++#define TARGET_HAVE_DMB_MCR (arm_arch6 && ! TARGET_HAVE_DMB \
++ && ! TARGET_THUMB1)
+
+ /* Nonzero if this chip implements a memory barrier instruction. */
+ #define TARGET_HAVE_MEMORY_BARRIER (TARGET_HAVE_DMB || TARGET_HAVE_DMB_MCR)
+@@ -308,8 +309,12 @@
+ /* Nonzero if this chip supports ldrex and strex */
+ #define TARGET_HAVE_LDREX ((arm_arch6 && TARGET_ARM) || arm_arch7)
+
+-/* Nonzero if this chip supports ldrex{bhd} and strex{bhd}. */
+-#define TARGET_HAVE_LDREXBHD ((arm_arch6k && TARGET_ARM) || arm_arch7)
++/* Nonzero if this chip supports ldrex{bh} and strex{bh}. */
++#define TARGET_HAVE_LDREXBH ((arm_arch6k && TARGET_ARM) || arm_arch7)
++
++/* Nonzero if this chip supports ldrexd and strexd. */
++#define TARGET_HAVE_LDREXD (((arm_arch6k && TARGET_ARM) || arm_arch7) \
++ && arm_arch_notm)
+
+ /* Nonzero if integer division instructions supported. */
+ #define TARGET_IDIV ((TARGET_ARM && arm_arch_arm_hwdiv) \
+
+=== modified file 'gcc/config/arm/iterators.md'
+--- old/gcc/config/arm/iterators.md 2011-10-23 13:33:07 +0000
++++ new/gcc/config/arm/iterators.md 2011-11-28 15:07:01 +0000
+@@ -33,6 +33,15 @@
+ ;; A list of integer modes that are up to one word long
+ (define_mode_iterator QHSI [QI HI SI])
+
++;; A list of integer modes that are less than a word
++(define_mode_iterator NARROW [QI HI])
++
++;; A list of all the integer modes upto 64bit
++(define_mode_iterator QHSD [QI HI SI DI])
++
++;; A list of the 32bit and 64bit integer modes
++(define_mode_iterator SIDI [SI DI])
++
+ ;; Integer element sizes implemented by IWMMXT.
+ (define_mode_iterator VMMX [V2SI V4HI V8QI])
+
+
+=== added file 'gcc/config/arm/linux-atomic-64bit.c'
+--- old/gcc/config/arm/linux-atomic-64bit.c 1970-01-01 00:00:00 +0000
++++ new/gcc/config/arm/linux-atomic-64bit.c 2011-10-14 15:50:44 +0000
+@@ -0,0 +1,166 @@
++/* 64bit Linux-specific atomic operations for ARM EABI.
++ Copyright (C) 2008, 2009, 2010, 2011 Free Software Foundation, Inc.
++ Based on linux-atomic.c
++
++ 64 bit additions david.gilbert@linaro.org
++
++This file is part of GCC.
++
++GCC is free software; you can redistribute it and/or modify it under
++the terms of the GNU General Public License as published by the Free
++Software Foundation; either version 3, or (at your option) any later
++version.
++
++GCC is distributed in the hope that it will be useful, but WITHOUT ANY
++WARRANTY; without even the implied warranty of MERCHANTABILITY or
++FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
++for more details.
++
++Under Section 7 of GPL version 3, you are granted additional
++permissions described in the GCC Runtime Library Exception, version
++3.1, as published by the Free Software Foundation.
++
++You should have received a copy of the GNU General Public License and
++a copy of the GCC Runtime Library Exception along with this program;
++see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
++<http://www.gnu.org/licenses/>. */
++
++/* 64bit helper functions for atomic operations; the compiler will
++ call these when the code is compiled for a CPU without ldrexd/strexd.
++ (If the CPU had those then the compiler inlines the operation).
++
++ These helpers require a kernel helper that's only present on newer
++ kernels; we check for that in an init section and bail out rather
++ unceremoneously. */
++
++extern unsigned int __write (int fd, const void *buf, unsigned int count);
++extern void abort (void);
++
++/* Kernel helper for compare-and-exchange. */
++typedef int (__kernel_cmpxchg64_t) (const long long* oldval,
++ const long long* newval,
++ long long *ptr);
++#define __kernel_cmpxchg64 (*(__kernel_cmpxchg64_t *) 0xffff0f60)
++
++/* Kernel helper page version number. */
++#define __kernel_helper_version (*(unsigned int *)0xffff0ffc)
++
++/* Check that the kernel has a new enough version at load. */
++static void __check_for_sync8_kernelhelper (void)
++{
++ if (__kernel_helper_version < 5)
++ {
++ const char err[] = "A newer kernel is required to run this binary. "
++ "(__kernel_cmpxchg64 helper)\n";
++ /* At this point we need a way to crash with some information
++ for the user - I'm not sure I can rely on much else being
++ available at this point, so do the same as generic-morestack.c
++ write () and abort (). */
++ __write (2 /* stderr. */, err, sizeof (err));
++ abort ();
++ }
++};
++
++static void (*__sync8_kernelhelper_inithook[]) (void)
++ __attribute__ ((used, section (".init_array"))) = {
++ &__check_for_sync8_kernelhelper
++};
++
++#define HIDDEN __attribute__ ((visibility ("hidden")))
++
++#define FETCH_AND_OP_WORD64(OP, PFX_OP, INF_OP) \
++ long long HIDDEN \
++ __sync_fetch_and_##OP##_8 (long long *ptr, long long val) \
++ { \
++ int failure; \
++ long long tmp,tmp2; \
++ \
++ do { \
++ tmp = *ptr; \
++ tmp2 = PFX_OP (tmp INF_OP val); \
++ failure = __kernel_cmpxchg64 (&tmp, &tmp2, ptr); \
++ } while (failure != 0); \
++ \
++ return tmp; \
++ }
++
++FETCH_AND_OP_WORD64 (add, , +)
++FETCH_AND_OP_WORD64 (sub, , -)
++FETCH_AND_OP_WORD64 (or, , |)
++FETCH_AND_OP_WORD64 (and, , &)
++FETCH_AND_OP_WORD64 (xor, , ^)
++FETCH_AND_OP_WORD64 (nand, ~, &)
++
++#define NAME_oldval(OP, WIDTH) __sync_fetch_and_##OP##_##WIDTH
++#define NAME_newval(OP, WIDTH) __sync_##OP##_and_fetch_##WIDTH
++
++/* Implement both __sync_<op>_and_fetch and __sync_fetch_and_<op> for
++ subword-sized quantities. */
++
++#define OP_AND_FETCH_WORD64(OP, PFX_OP, INF_OP) \
++ long long HIDDEN \
++ __sync_##OP##_and_fetch_8 (long long *ptr, long long val) \
++ { \
++ int failure; \
++ long long tmp,tmp2; \
++ \
++ do { \
++ tmp = *ptr; \
++ tmp2 = PFX_OP (tmp INF_OP val); \
++ failure = __kernel_cmpxchg64 (&tmp, &tmp2, ptr); \
++ } while (failure != 0); \
++ \
++ return tmp2; \
++ }
++
++OP_AND_FETCH_WORD64 (add, , +)
++OP_AND_FETCH_WORD64 (sub, , -)
++OP_AND_FETCH_WORD64 (or, , |)
++OP_AND_FETCH_WORD64 (and, , &)
++OP_AND_FETCH_WORD64 (xor, , ^)
++OP_AND_FETCH_WORD64 (nand, ~, &)
++
++long long HIDDEN
++__sync_val_compare_and_swap_8 (long long *ptr, long long oldval,
++ long long newval)
++{
++ int failure;
++ long long actual_oldval;
++
++ while (1)
++ {
++ actual_oldval = *ptr;
++
++ if (__builtin_expect (oldval != actual_oldval, 0))
++ return actual_oldval;
++
++ failure = __kernel_cmpxchg64 (&actual_oldval, &newval, ptr);
++
++ if (__builtin_expect (!failure, 1))
++ return oldval;
++ }
++}
++
++typedef unsigned char bool;
++
++bool HIDDEN
++__sync_bool_compare_and_swap_8 (long long *ptr, long long oldval,
++ long long newval)
++{
++ int failure = __kernel_cmpxchg64 (&oldval, &newval, ptr);
++ return (failure == 0);
++}
++
++long long HIDDEN
++__sync_lock_test_and_set_8 (long long *ptr, long long val)
++{
++ int failure;
++ long long oldval;
++
++ do {
++ oldval = *ptr;
++ failure = __kernel_cmpxchg64 (&oldval, &val, ptr);
++ } while (failure != 0);
++
++ return oldval;
++}
+
+=== modified file 'gcc/config/arm/linux-atomic.c'
+--- old/gcc/config/arm/linux-atomic.c 2011-01-03 20:52:22 +0000
++++ new/gcc/config/arm/linux-atomic.c 2011-10-14 15:50:44 +0000
+@@ -32,8 +32,8 @@
+ #define __kernel_dmb (*(__kernel_dmb_t *) 0xffff0fa0)
+
+ /* Note: we implement byte, short and int versions of atomic operations using
+- the above kernel helpers, but there is no support for "long long" (64-bit)
+- operations as yet. */
++ the above kernel helpers; see linux-atomic-64bit.c for "long long" (64-bit)
++ operations. */
+
+ #define HIDDEN __attribute__ ((visibility ("hidden")))
+
+@@ -273,6 +273,7 @@
+ *ptr = 0; \
+ }
+
++SYNC_LOCK_RELEASE (long long, 8)
+ SYNC_LOCK_RELEASE (int, 4)
+ SYNC_LOCK_RELEASE (short, 2)
+ SYNC_LOCK_RELEASE (char, 1)
+
+=== modified file 'gcc/config/arm/sync.md'
+--- old/gcc/config/arm/sync.md 2010-12-31 13:25:33 +0000
++++ new/gcc/config/arm/sync.md 2011-10-14 15:47:15 +0000
+@@ -1,6 +1,7 @@
+ ;; Machine description for ARM processor synchronization primitives.
+ ;; Copyright (C) 2010 Free Software Foundation, Inc.
+ ;; Written by Marcus Shawcroft (marcus.shawcroft@arm.com)
++;; 64bit Atomics by Dave Gilbert (david.gilbert@linaro.org)
+ ;;
+ ;; This file is part of GCC.
+ ;;
+@@ -33,31 +34,24 @@
+ MEM_VOLATILE_P (operands[0]) = 1;
+ })
+
+-(define_expand "sync_compare_and_swapsi"
+- [(set (match_operand:SI 0 "s_register_operand")
+- (unspec_volatile:SI [(match_operand:SI 1 "memory_operand")
+- (match_operand:SI 2 "s_register_operand")
+- (match_operand:SI 3 "s_register_operand")]
+- VUNSPEC_SYNC_COMPARE_AND_SWAP))]
+- "TARGET_HAVE_LDREX && TARGET_HAVE_MEMORY_BARRIER"
+- {
+- struct arm_sync_generator generator;
+- generator.op = arm_sync_generator_omrn;
+- generator.u.omrn = gen_arm_sync_compare_and_swapsi;
+- arm_expand_sync (SImode, &generator, operands[0], operands[1], operands[2],
+- operands[3]);
+- DONE;
+- })
+
+-(define_mode_iterator NARROW [QI HI])
++(define_mode_attr sync_predtab [(SI "TARGET_HAVE_LDREX &&
++ TARGET_HAVE_MEMORY_BARRIER")
++ (QI "TARGET_HAVE_LDREXBH &&
++ TARGET_HAVE_MEMORY_BARRIER")
++ (HI "TARGET_HAVE_LDREXBH &&
++ TARGET_HAVE_MEMORY_BARRIER")
++ (DI "TARGET_HAVE_LDREXD &&
++ ARM_DOUBLEWORD_ALIGN &&
++ TARGET_HAVE_MEMORY_BARRIER")])
+
+ (define_expand "sync_compare_and_swap<mode>"
+- [(set (match_operand:NARROW 0 "s_register_operand")
+- (unspec_volatile:NARROW [(match_operand:NARROW 1 "memory_operand")
+- (match_operand:NARROW 2 "s_register_operand")
+- (match_operand:NARROW 3 "s_register_operand")]
++ [(set (match_operand:QHSD 0 "s_register_operand")
++ (unspec_volatile:QHSD [(match_operand:QHSD 1 "memory_operand")
++ (match_operand:QHSD 2 "s_register_operand")
++ (match_operand:QHSD 3 "s_register_operand")]
+ VUNSPEC_SYNC_COMPARE_AND_SWAP))]
+- "TARGET_HAVE_LDREXBHD && TARGET_HAVE_MEMORY_BARRIER"
++ "<sync_predtab>"
+ {
+ struct arm_sync_generator generator;
+ generator.op = arm_sync_generator_omrn;
+@@ -67,25 +61,11 @@
+ DONE;
+ })
+
+-(define_expand "sync_lock_test_and_setsi"
+- [(match_operand:SI 0 "s_register_operand")
+- (match_operand:SI 1 "memory_operand")
+- (match_operand:SI 2 "s_register_operand")]
+- "TARGET_HAVE_LDREX && TARGET_HAVE_MEMORY_BARRIER"
+- {
+- struct arm_sync_generator generator;
+- generator.op = arm_sync_generator_omn;
+- generator.u.omn = gen_arm_sync_lock_test_and_setsi;
+- arm_expand_sync (SImode, &generator, operands[0], operands[1], NULL,
+- operands[2]);
+- DONE;
+- })
+-
+ (define_expand "sync_lock_test_and_set<mode>"
+- [(match_operand:NARROW 0 "s_register_operand")
+- (match_operand:NARROW 1 "memory_operand")
+- (match_operand:NARROW 2 "s_register_operand")]
+- "TARGET_HAVE_LDREXBHD && TARGET_HAVE_MEMORY_BARRIER"
++ [(match_operand:QHSD 0 "s_register_operand")
++ (match_operand:QHSD 1 "memory_operand")
++ (match_operand:QHSD 2 "s_register_operand")]
++ "<sync_predtab>"
+ {
+ struct arm_sync_generator generator;
+ generator.op = arm_sync_generator_omn;
+@@ -115,51 +95,25 @@
+ (plus "*")
+ (minus "*")])
+
+-(define_expand "sync_<sync_optab>si"
+- [(match_operand:SI 0 "memory_operand")
+- (match_operand:SI 1 "s_register_operand")
+- (syncop:SI (match_dup 0) (match_dup 1))]
+- "TARGET_HAVE_LDREX && TARGET_HAVE_MEMORY_BARRIER"
+- {
+- struct arm_sync_generator generator;
+- generator.op = arm_sync_generator_omn;
+- generator.u.omn = gen_arm_sync_new_<sync_optab>si;
+- arm_expand_sync (SImode, &generator, NULL, operands[0], NULL, operands[1]);
+- DONE;
+- })
+-
+-(define_expand "sync_nandsi"
+- [(match_operand:SI 0 "memory_operand")
+- (match_operand:SI 1 "s_register_operand")
+- (not:SI (and:SI (match_dup 0) (match_dup 1)))]
+- "TARGET_HAVE_LDREX && TARGET_HAVE_MEMORY_BARRIER"
+- {
+- struct arm_sync_generator generator;
+- generator.op = arm_sync_generator_omn;
+- generator.u.omn = gen_arm_sync_new_nandsi;
+- arm_expand_sync (SImode, &generator, NULL, operands[0], NULL, operands[1]);
+- DONE;
+- })
+-
+ (define_expand "sync_<sync_optab><mode>"
+- [(match_operand:NARROW 0 "memory_operand")
+- (match_operand:NARROW 1 "s_register_operand")
+- (syncop:NARROW (match_dup 0) (match_dup 1))]
+- "TARGET_HAVE_LDREXBHD && TARGET_HAVE_MEMORY_BARRIER"
++ [(match_operand:QHSD 0 "memory_operand")
++ (match_operand:QHSD 1 "s_register_operand")
++ (syncop:QHSD (match_dup 0) (match_dup 1))]
++ "<sync_predtab>"
+ {
+ struct arm_sync_generator generator;
+ generator.op = arm_sync_generator_omn;
+ generator.u.omn = gen_arm_sync_new_<sync_optab><mode>;
+ arm_expand_sync (<MODE>mode, &generator, NULL, operands[0], NULL,
+- operands[1]);
++ operands[1]);
+ DONE;
+ })
+
+ (define_expand "sync_nand<mode>"
+- [(match_operand:NARROW 0 "memory_operand")
+- (match_operand:NARROW 1 "s_register_operand")
+- (not:NARROW (and:NARROW (match_dup 0) (match_dup 1)))]
+- "TARGET_HAVE_LDREXBHD && TARGET_HAVE_MEMORY_BARRIER"
++ [(match_operand:QHSD 0 "memory_operand")
++ (match_operand:QHSD 1 "s_register_operand")
++ (not:QHSD (and:QHSD (match_dup 0) (match_dup 1)))]
++ "<sync_predtab>"
+ {
+ struct arm_sync_generator generator;
+ generator.op = arm_sync_generator_omn;
+@@ -169,57 +123,27 @@
+ DONE;
+ })
+
+-(define_expand "sync_new_<sync_optab>si"
+- [(match_operand:SI 0 "s_register_operand")
+- (match_operand:SI 1 "memory_operand")
+- (match_operand:SI 2 "s_register_operand")
+- (syncop:SI (match_dup 1) (match_dup 2))]
+- "TARGET_HAVE_LDREX && TARGET_HAVE_MEMORY_BARRIER"
+- {
+- struct arm_sync_generator generator;
+- generator.op = arm_sync_generator_omn;
+- generator.u.omn = gen_arm_sync_new_<sync_optab>si;
+- arm_expand_sync (SImode, &generator, operands[0], operands[1], NULL,
+- operands[2]);
+- DONE;
+- })
+-
+-(define_expand "sync_new_nandsi"
+- [(match_operand:SI 0 "s_register_operand")
+- (match_operand:SI 1 "memory_operand")
+- (match_operand:SI 2 "s_register_operand")
+- (not:SI (and:SI (match_dup 1) (match_dup 2)))]
+- "TARGET_HAVE_LDREX && TARGET_HAVE_MEMORY_BARRIER"
+- {
+- struct arm_sync_generator generator;
+- generator.op = arm_sync_generator_omn;
+- generator.u.omn = gen_arm_sync_new_nandsi;
+- arm_expand_sync (SImode, &generator, operands[0], operands[1], NULL,
+- operands[2]);
+- DONE;
+- })
+-
+ (define_expand "sync_new_<sync_optab><mode>"
+- [(match_operand:NARROW 0 "s_register_operand")
+- (match_operand:NARROW 1 "memory_operand")
+- (match_operand:NARROW 2 "s_register_operand")
+- (syncop:NARROW (match_dup 1) (match_dup 2))]
+- "TARGET_HAVE_LDREXBHD && TARGET_HAVE_MEMORY_BARRIER"
++ [(match_operand:QHSD 0 "s_register_operand")
++ (match_operand:QHSD 1 "memory_operand")
++ (match_operand:QHSD 2 "s_register_operand")
++ (syncop:QHSD (match_dup 1) (match_dup 2))]
++ "<sync_predtab>"
+ {
+ struct arm_sync_generator generator;
+ generator.op = arm_sync_generator_omn;
+ generator.u.omn = gen_arm_sync_new_<sync_optab><mode>;
+ arm_expand_sync (<MODE>mode, &generator, operands[0], operands[1],
+- NULL, operands[2]);
++ NULL, operands[2]);
+ DONE;
+ })
+
+ (define_expand "sync_new_nand<mode>"
+- [(match_operand:NARROW 0 "s_register_operand")
+- (match_operand:NARROW 1 "memory_operand")
+- (match_operand:NARROW 2 "s_register_operand")
+- (not:NARROW (and:NARROW (match_dup 1) (match_dup 2)))]
+- "TARGET_HAVE_LDREXBHD && TARGET_HAVE_MEMORY_BARRIER"
++ [(match_operand:QHSD 0 "s_register_operand")
++ (match_operand:QHSD 1 "memory_operand")
++ (match_operand:QHSD 2 "s_register_operand")
++ (not:QHSD (and:QHSD (match_dup 1) (match_dup 2)))]
++ "<sync_predtab>"
+ {
+ struct arm_sync_generator generator;
+ generator.op = arm_sync_generator_omn;
+@@ -229,57 +153,27 @@
+ DONE;
+ });
+
+-(define_expand "sync_old_<sync_optab>si"
+- [(match_operand:SI 0 "s_register_operand")
+- (match_operand:SI 1 "memory_operand")
+- (match_operand:SI 2 "s_register_operand")
+- (syncop:SI (match_dup 1) (match_dup 2))]
+- "TARGET_HAVE_LDREX && TARGET_HAVE_MEMORY_BARRIER"
+- {
+- struct arm_sync_generator generator;
+- generator.op = arm_sync_generator_omn;
+- generator.u.omn = gen_arm_sync_old_<sync_optab>si;
+- arm_expand_sync (SImode, &generator, operands[0], operands[1], NULL,
+- operands[2]);
+- DONE;
+- })
+-
+-(define_expand "sync_old_nandsi"
+- [(match_operand:SI 0 "s_register_operand")
+- (match_operand:SI 1 "memory_operand")
+- (match_operand:SI 2 "s_register_operand")
+- (not:SI (and:SI (match_dup 1) (match_dup 2)))]
+- "TARGET_HAVE_LDREX && TARGET_HAVE_MEMORY_BARRIER"
+- {
+- struct arm_sync_generator generator;
+- generator.op = arm_sync_generator_omn;
+- generator.u.omn = gen_arm_sync_old_nandsi;
+- arm_expand_sync (SImode, &generator, operands[0], operands[1], NULL,
+- operands[2]);
+- DONE;
+- })
+-
+ (define_expand "sync_old_<sync_optab><mode>"
+- [(match_operand:NARROW 0 "s_register_operand")
+- (match_operand:NARROW 1 "memory_operand")
+- (match_operand:NARROW 2 "s_register_operand")
+- (syncop:NARROW (match_dup 1) (match_dup 2))]
+- "TARGET_HAVE_LDREXBHD && TARGET_HAVE_MEMORY_BARRIER"
++ [(match_operand:QHSD 0 "s_register_operand")
++ (match_operand:QHSD 1 "memory_operand")
++ (match_operand:QHSD 2 "s_register_operand")
++ (syncop:QHSD (match_dup 1) (match_dup 2))]
++ "<sync_predtab>"
+ {
+ struct arm_sync_generator generator;
+ generator.op = arm_sync_generator_omn;
+ generator.u.omn = gen_arm_sync_old_<sync_optab><mode>;
+ arm_expand_sync (<MODE>mode, &generator, operands[0], operands[1],
+- NULL, operands[2]);
++ NULL, operands[2]);
+ DONE;
+ })
+
+ (define_expand "sync_old_nand<mode>"
+- [(match_operand:NARROW 0 "s_register_operand")
+- (match_operand:NARROW 1 "memory_operand")
+- (match_operand:NARROW 2 "s_register_operand")
+- (not:NARROW (and:NARROW (match_dup 1) (match_dup 2)))]
+- "TARGET_HAVE_LDREXBHD && TARGET_HAVE_MEMORY_BARRIER"
++ [(match_operand:QHSD 0 "s_register_operand")
++ (match_operand:QHSD 1 "memory_operand")
++ (match_operand:QHSD 2 "s_register_operand")
++ (not:QHSD (and:QHSD (match_dup 1) (match_dup 2)))]
++ "<sync_predtab>"
+ {
+ struct arm_sync_generator generator;
+ generator.op = arm_sync_generator_omn;
+@@ -289,22 +183,22 @@
+ DONE;
+ })
+
+-(define_insn "arm_sync_compare_and_swapsi"
+- [(set (match_operand:SI 0 "s_register_operand" "=&r")
+- (unspec_volatile:SI
+- [(match_operand:SI 1 "arm_sync_memory_operand" "+Q")
+- (match_operand:SI 2 "s_register_operand" "r")
+- (match_operand:SI 3 "s_register_operand" "r")]
+- VUNSPEC_SYNC_COMPARE_AND_SWAP))
+- (set (match_dup 1) (unspec_volatile:SI [(match_dup 2)]
++(define_insn "arm_sync_compare_and_swap<mode>"
++ [(set (match_operand:SIDI 0 "s_register_operand" "=&r")
++ (unspec_volatile:SIDI
++ [(match_operand:SIDI 1 "arm_sync_memory_operand" "+Q")
++ (match_operand:SIDI 2 "s_register_operand" "r")
++ (match_operand:SIDI 3 "s_register_operand" "r")]
++ VUNSPEC_SYNC_COMPARE_AND_SWAP))
++ (set (match_dup 1) (unspec_volatile:SIDI [(match_dup 2)]
+ VUNSPEC_SYNC_COMPARE_AND_SWAP))
+ (set (reg:CC CC_REGNUM) (unspec_volatile:CC [(match_dup 1)]
+ VUNSPEC_SYNC_COMPARE_AND_SWAP))
+ ]
+- "TARGET_HAVE_LDREX && TARGET_HAVE_MEMORY_BARRIER"
++ "<sync_predtab>"
+ {
+ return arm_output_sync_insn (insn, operands);
+- }
++ }
+ [(set_attr "sync_result" "0")
+ (set_attr "sync_memory" "1")
+ (set_attr "sync_required_value" "2")
+@@ -318,7 +212,7 @@
+ (zero_extend:SI
+ (unspec_volatile:NARROW
+ [(match_operand:NARROW 1 "arm_sync_memory_operand" "+Q")
+- (match_operand:SI 2 "s_register_operand" "r")
++ (match_operand:SI 2 "s_register_operand" "r")
+ (match_operand:SI 3 "s_register_operand" "r")]
+ VUNSPEC_SYNC_COMPARE_AND_SWAP)))
+ (set (match_dup 1) (unspec_volatile:NARROW [(match_dup 2)]
+@@ -326,10 +220,10 @@
+ (set (reg:CC CC_REGNUM) (unspec_volatile:CC [(match_dup 1)]
+ VUNSPEC_SYNC_COMPARE_AND_SWAP))
+ ]
+- "TARGET_HAVE_LDREXBHD && TARGET_HAVE_MEMORY_BARRIER"
++ "<sync_predtab>"
+ {
+ return arm_output_sync_insn (insn, operands);
+- }
++ }
+ [(set_attr "sync_result" "0")
+ (set_attr "sync_memory" "1")
+ (set_attr "sync_required_value" "2")
+@@ -338,18 +232,18 @@
+ (set_attr "conds" "clob")
+ (set_attr "predicable" "no")])
+
+-(define_insn "arm_sync_lock_test_and_setsi"
+- [(set (match_operand:SI 0 "s_register_operand" "=&r")
+- (match_operand:SI 1 "arm_sync_memory_operand" "+Q"))
++(define_insn "arm_sync_lock_test_and_set<mode>"
++ [(set (match_operand:SIDI 0 "s_register_operand" "=&r")
++ (match_operand:SIDI 1 "arm_sync_memory_operand" "+Q"))
+ (set (match_dup 1)
+- (unspec_volatile:SI [(match_operand:SI 2 "s_register_operand" "r")]
+- VUNSPEC_SYNC_LOCK))
++ (unspec_volatile:SIDI [(match_operand:SIDI 2 "s_register_operand" "r")]
++ VUNSPEC_SYNC_LOCK))
+ (clobber (reg:CC CC_REGNUM))
+ (clobber (match_scratch:SI 3 "=&r"))]
+- "TARGET_HAVE_LDREX && TARGET_HAVE_MEMORY_BARRIER"
++ "<sync_predtab>"
+ {
+ return arm_output_sync_insn (insn, operands);
+- }
++ }
+ [(set_attr "sync_release_barrier" "no")
+ (set_attr "sync_result" "0")
+ (set_attr "sync_memory" "1")
+@@ -364,10 +258,10 @@
+ (zero_extend:SI (match_operand:NARROW 1 "arm_sync_memory_operand" "+Q")))
+ (set (match_dup 1)
+ (unspec_volatile:NARROW [(match_operand:SI 2 "s_register_operand" "r")]
+- VUNSPEC_SYNC_LOCK))
++ VUNSPEC_SYNC_LOCK))
+ (clobber (reg:CC CC_REGNUM))
+ (clobber (match_scratch:SI 3 "=&r"))]
+- "TARGET_HAVE_LDREX && TARGET_HAVE_MEMORY_BARRIER"
++ "<sync_predtab>"
+ {
+ return arm_output_sync_insn (insn, operands);
+ }
+@@ -380,22 +274,48 @@
+ (set_attr "conds" "clob")
+ (set_attr "predicable" "no")])
+
+-(define_insn "arm_sync_new_<sync_optab>si"
++(define_insn "arm_sync_new_<sync_optab><mode>"
++ [(set (match_operand:SIDI 0 "s_register_operand" "=&r")
++ (unspec_volatile:SIDI [(syncop:SIDI
++ (match_operand:SIDI 1 "arm_sync_memory_operand" "+Q")
++ (match_operand:SIDI 2 "s_register_operand" "r"))
++ ]
++ VUNSPEC_SYNC_NEW_OP))
++ (set (match_dup 1)
++ (unspec_volatile:SIDI [(match_dup 1) (match_dup 2)]
++ VUNSPEC_SYNC_NEW_OP))
++ (clobber (reg:CC CC_REGNUM))
++ (clobber (match_scratch:SI 3 "=&r"))]
++ "<sync_predtab>"
++ {
++ return arm_output_sync_insn (insn, operands);
++ }
++ [(set_attr "sync_result" "0")
++ (set_attr "sync_memory" "1")
++ (set_attr "sync_new_value" "2")
++ (set_attr "sync_t1" "0")
++ (set_attr "sync_t2" "3")
++ (set_attr "sync_op" "<sync_optab>")
++ (set_attr "conds" "clob")
++ (set_attr "predicable" "no")])
++
++(define_insn "arm_sync_new_<sync_optab><mode>"
+ [(set (match_operand:SI 0 "s_register_operand" "=&r")
+ (unspec_volatile:SI [(syncop:SI
+- (match_operand:SI 1 "arm_sync_memory_operand" "+Q")
+- (match_operand:SI 2 "s_register_operand" "r"))
+- ]
+- VUNSPEC_SYNC_NEW_OP))
++ (zero_extend:SI
++ (match_operand:NARROW 1 "arm_sync_memory_operand" "+Q"))
++ (match_operand:SI 2 "s_register_operand" "r"))
++ ]
++ VUNSPEC_SYNC_NEW_OP))
+ (set (match_dup 1)
+- (unspec_volatile:SI [(match_dup 1) (match_dup 2)]
+- VUNSPEC_SYNC_NEW_OP))
++ (unspec_volatile:NARROW [(match_dup 1) (match_dup 2)]
++ VUNSPEC_SYNC_NEW_OP))
+ (clobber (reg:CC CC_REGNUM))
+ (clobber (match_scratch:SI 3 "=&r"))]
+- "TARGET_HAVE_LDREX && TARGET_HAVE_MEMORY_BARRIER"
++ "<sync_predtab>"
+ {
+ return arm_output_sync_insn (insn, operands);
+- }
++ }
+ [(set_attr "sync_result" "0")
+ (set_attr "sync_memory" "1")
+ (set_attr "sync_new_value" "2")
+@@ -405,22 +325,22 @@
+ (set_attr "conds" "clob")
+ (set_attr "predicable" "no")])
+
+-(define_insn "arm_sync_new_nandsi"
+- [(set (match_operand:SI 0 "s_register_operand" "=&r")
+- (unspec_volatile:SI [(not:SI (and:SI
+- (match_operand:SI 1 "arm_sync_memory_operand" "+Q")
+- (match_operand:SI 2 "s_register_operand" "r")))
+- ]
+- VUNSPEC_SYNC_NEW_OP))
++(define_insn "arm_sync_new_nand<mode>"
++ [(set (match_operand:SIDI 0 "s_register_operand" "=&r")
++ (unspec_volatile:SIDI [(not:SIDI (and:SIDI
++ (match_operand:SIDI 1 "arm_sync_memory_operand" "+Q")
++ (match_operand:SIDI 2 "s_register_operand" "r")))
++ ]
++ VUNSPEC_SYNC_NEW_OP))
+ (set (match_dup 1)
+- (unspec_volatile:SI [(match_dup 1) (match_dup 2)]
+- VUNSPEC_SYNC_NEW_OP))
++ (unspec_volatile:SIDI [(match_dup 1) (match_dup 2)]
++ VUNSPEC_SYNC_NEW_OP))
+ (clobber (reg:CC CC_REGNUM))
+ (clobber (match_scratch:SI 3 "=&r"))]
+- "TARGET_HAVE_LDREX && TARGET_HAVE_MEMORY_BARRIER"
++ "<sync_predtab>"
+ {
+ return arm_output_sync_insn (insn, operands);
+- }
++ }
+ [(set_attr "sync_result" "0")
+ (set_attr "sync_memory" "1")
+ (set_attr "sync_new_value" "2")
+@@ -430,50 +350,24 @@
+ (set_attr "conds" "clob")
+ (set_attr "predicable" "no")])
+
+-(define_insn "arm_sync_new_<sync_optab><mode>"
+- [(set (match_operand:SI 0 "s_register_operand" "=&r")
+- (unspec_volatile:SI [(syncop:SI
+- (zero_extend:SI
+- (match_operand:NARROW 1 "arm_sync_memory_operand" "+Q"))
+- (match_operand:SI 2 "s_register_operand" "r"))
+- ]
+- VUNSPEC_SYNC_NEW_OP))
+- (set (match_dup 1)
+- (unspec_volatile:NARROW [(match_dup 1) (match_dup 2)]
+- VUNSPEC_SYNC_NEW_OP))
+- (clobber (reg:CC CC_REGNUM))
+- (clobber (match_scratch:SI 3 "=&r"))]
+- "TARGET_HAVE_LDREXBHD && TARGET_HAVE_MEMORY_BARRIER"
+- {
+- return arm_output_sync_insn (insn, operands);
+- }
+- [(set_attr "sync_result" "0")
+- (set_attr "sync_memory" "1")
+- (set_attr "sync_new_value" "2")
+- (set_attr "sync_t1" "0")
+- (set_attr "sync_t2" "3")
+- (set_attr "sync_op" "<sync_optab>")
+- (set_attr "conds" "clob")
+- (set_attr "predicable" "no")])
+-
+ (define_insn "arm_sync_new_nand<mode>"
+ [(set (match_operand:SI 0 "s_register_operand" "=&r")
+ (unspec_volatile:SI
+ [(not:SI
+ (and:SI
+- (zero_extend:SI
+- (match_operand:NARROW 1 "arm_sync_memory_operand" "+Q"))
+- (match_operand:SI 2 "s_register_operand" "r")))
++ (zero_extend:SI
++ (match_operand:NARROW 1 "arm_sync_memory_operand" "+Q"))
++ (match_operand:SI 2 "s_register_operand" "r")))
+ ] VUNSPEC_SYNC_NEW_OP))
+ (set (match_dup 1)
+ (unspec_volatile:NARROW [(match_dup 1) (match_dup 2)]
+- VUNSPEC_SYNC_NEW_OP))
++ VUNSPEC_SYNC_NEW_OP))
+ (clobber (reg:CC CC_REGNUM))
+ (clobber (match_scratch:SI 3 "=&r"))]
+- "TARGET_HAVE_LDREX && TARGET_HAVE_MEMORY_BARRIER"
++ "<sync_predtab>"
+ {
+ return arm_output_sync_insn (insn, operands);
+- }
++ }
+ [(set_attr "sync_result" "0")
+ (set_attr "sync_memory" "1")
+ (set_attr "sync_new_value" "2")
+@@ -483,20 +377,20 @@
+ (set_attr "conds" "clob")
+ (set_attr "predicable" "no")])
+
+-(define_insn "arm_sync_old_<sync_optab>si"
+- [(set (match_operand:SI 0 "s_register_operand" "=&r")
+- (unspec_volatile:SI [(syncop:SI
+- (match_operand:SI 1 "arm_sync_memory_operand" "+Q")
+- (match_operand:SI 2 "s_register_operand" "r"))
+- ]
+- VUNSPEC_SYNC_OLD_OP))
++(define_insn "arm_sync_old_<sync_optab><mode>"
++ [(set (match_operand:SIDI 0 "s_register_operand" "=&r")
++ (unspec_volatile:SIDI [(syncop:SIDI
++ (match_operand:SIDI 1 "arm_sync_memory_operand" "+Q")
++ (match_operand:SIDI 2 "s_register_operand" "r"))
++ ]
++ VUNSPEC_SYNC_OLD_OP))
+ (set (match_dup 1)
+- (unspec_volatile:SI [(match_dup 1) (match_dup 2)]
+- VUNSPEC_SYNC_OLD_OP))
++ (unspec_volatile:SIDI [(match_dup 1) (match_dup 2)]
++ VUNSPEC_SYNC_OLD_OP))
+ (clobber (reg:CC CC_REGNUM))
+- (clobber (match_scratch:SI 3 "=&r"))
++ (clobber (match_scratch:SIDI 3 "=&r"))
+ (clobber (match_scratch:SI 4 "<sync_clobber>"))]
+- "TARGET_HAVE_LDREX && TARGET_HAVE_MEMORY_BARRIER"
++ "<sync_predtab>"
+ {
+ return arm_output_sync_insn (insn, operands);
+ }
+@@ -509,47 +403,21 @@
+ (set_attr "conds" "clob")
+ (set_attr "predicable" "no")])
+
+-(define_insn "arm_sync_old_nandsi"
+- [(set (match_operand:SI 0 "s_register_operand" "=&r")
+- (unspec_volatile:SI [(not:SI (and:SI
+- (match_operand:SI 1 "arm_sync_memory_operand" "+Q")
+- (match_operand:SI 2 "s_register_operand" "r")))
+- ]
+- VUNSPEC_SYNC_OLD_OP))
+- (set (match_dup 1)
+- (unspec_volatile:SI [(match_dup 1) (match_dup 2)]
+- VUNSPEC_SYNC_OLD_OP))
+- (clobber (reg:CC CC_REGNUM))
+- (clobber (match_scratch:SI 3 "=&r"))
+- (clobber (match_scratch:SI 4 "=&r"))]
+- "TARGET_HAVE_LDREX && TARGET_HAVE_MEMORY_BARRIER"
+- {
+- return arm_output_sync_insn (insn, operands);
+- }
+- [(set_attr "sync_result" "0")
+- (set_attr "sync_memory" "1")
+- (set_attr "sync_new_value" "2")
+- (set_attr "sync_t1" "3")
+- (set_attr "sync_t2" "4")
+- (set_attr "sync_op" "nand")
+- (set_attr "conds" "clob")
+- (set_attr "predicable" "no")])
+-
+ (define_insn "arm_sync_old_<sync_optab><mode>"
+ [(set (match_operand:SI 0 "s_register_operand" "=&r")
+ (unspec_volatile:SI [(syncop:SI
+- (zero_extend:SI
+- (match_operand:NARROW 1 "arm_sync_memory_operand" "+Q"))
+- (match_operand:SI 2 "s_register_operand" "r"))
+- ]
+- VUNSPEC_SYNC_OLD_OP))
++ (zero_extend:SI
++ (match_operand:NARROW 1 "arm_sync_memory_operand" "+Q"))
++ (match_operand:SI 2 "s_register_operand" "r"))
++ ]
++ VUNSPEC_SYNC_OLD_OP))
+ (set (match_dup 1)
+- (unspec_volatile:NARROW [(match_dup 1) (match_dup 2)]
+- VUNSPEC_SYNC_OLD_OP))
++ (unspec_volatile:NARROW [(match_dup 1) (match_dup 2)]
++ VUNSPEC_SYNC_OLD_OP))
+ (clobber (reg:CC CC_REGNUM))
+ (clobber (match_scratch:SI 3 "=&r"))
+ (clobber (match_scratch:SI 4 "<sync_clobber>"))]
+- "TARGET_HAVE_LDREXBHD && TARGET_HAVE_MEMORY_BARRIER"
++ "<sync_predtab>"
+ {
+ return arm_output_sync_insn (insn, operands);
+ }
+@@ -563,20 +431,46 @@
+ (set_attr "predicable" "no")])
+
+ (define_insn "arm_sync_old_nand<mode>"
++ [(set (match_operand:SIDI 0 "s_register_operand" "=&r")
++ (unspec_volatile:SIDI [(not:SIDI (and:SIDI
++ (match_operand:SIDI 1 "arm_sync_memory_operand" "+Q")
++ (match_operand:SIDI 2 "s_register_operand" "r")))
++ ]
++ VUNSPEC_SYNC_OLD_OP))
++ (set (match_dup 1)
++ (unspec_volatile:SIDI [(match_dup 1) (match_dup 2)]
++ VUNSPEC_SYNC_OLD_OP))
++ (clobber (reg:CC CC_REGNUM))
++ (clobber (match_scratch:SIDI 3 "=&r"))
++ (clobber (match_scratch:SI 4 "=&r"))]
++ "<sync_predtab>"
++ {
++ return arm_output_sync_insn (insn, operands);
++ }
++ [(set_attr "sync_result" "0")
++ (set_attr "sync_memory" "1")
++ (set_attr "sync_new_value" "2")
++ (set_attr "sync_t1" "3")
++ (set_attr "sync_t2" "4")
++ (set_attr "sync_op" "nand")
++ (set_attr "conds" "clob")
++ (set_attr "predicable" "no")])
++
++(define_insn "arm_sync_old_nand<mode>"
+ [(set (match_operand:SI 0 "s_register_operand" "=&r")
+- (unspec_volatile:SI [(not:SI (and:SI
+- (zero_extend:SI
+- (match_operand:NARROW 1 "arm_sync_memory_operand" "+Q"))
+- (match_operand:SI 2 "s_register_operand" "r")))
+- ]
+- VUNSPEC_SYNC_OLD_OP))
++ (unspec_volatile:SI [(not:SI (and:SI
++ (zero_extend:SI
++ (match_operand:NARROW 1 "arm_sync_memory_operand" "+Q"))
++ (match_operand:SI 2 "s_register_operand" "r")))
++ ]
++ VUNSPEC_SYNC_OLD_OP))
+ (set (match_dup 1)
+- (unspec_volatile:NARROW [(match_dup 1) (match_dup 2)]
+- VUNSPEC_SYNC_OLD_OP))
++ (unspec_volatile:NARROW [(match_dup 1) (match_dup 2)]
++ VUNSPEC_SYNC_OLD_OP))
+ (clobber (reg:CC CC_REGNUM))
+ (clobber (match_scratch:SI 3 "=&r"))
+ (clobber (match_scratch:SI 4 "=&r"))]
+- "TARGET_HAVE_LDREXBHD && TARGET_HAVE_MEMORY_BARRIER"
++ "<sync_predtab>"
+ {
+ return arm_output_sync_insn (insn, operands);
+ }
+
+=== modified file 'gcc/config/arm/t-linux-eabi'
+--- old/gcc/config/arm/t-linux-eabi 2011-01-03 20:52:22 +0000
++++ new/gcc/config/arm/t-linux-eabi 2011-10-14 15:50:44 +0000
+@@ -36,3 +36,4 @@
+ EXTRA_MULTILIB_PARTS=crtbegin.o crtend.o crtbeginS.o crtendS.o crtbeginT.o
+
+ LIB2FUNCS_STATIC_EXTRA += $(srcdir)/config/arm/linux-atomic.c
++LIB2FUNCS_STATIC_EXTRA += $(srcdir)/config/arm/linux-atomic-64bit.c
+
+=== added file 'gcc/testsuite/gcc.dg/di-longlong64-sync-1.c'
+--- old/gcc/testsuite/gcc.dg/di-longlong64-sync-1.c 1970-01-01 00:00:00 +0000
++++ new/gcc/testsuite/gcc.dg/di-longlong64-sync-1.c 2011-10-14 15:56:32 +0000
+@@ -0,0 +1,164 @@
++/* { dg-do run } */
++/* { dg-require-effective-target sync_longlong } */
++/* { dg-options "-std=gnu99" } */
++/* { dg-message "note: '__sync_fetch_and_nand' changed semantics in GCC 4.4" "" { target *-*-* } 0 } */
++/* { dg-message "note: '__sync_nand_and_fetch' changed semantics in GCC 4.4" "" { target *-*-* } 0 } */
++
++
++/* Test basic functionality of the intrinsics. The operations should
++ not be optimized away if no one checks the return values. */
++
++/* Based on ia64-sync-[12].c, but 1) long on ARM is 32 bit so use long long
++ (an explicit 64bit type maybe a better bet) and 2) Use values that cross
++ the 32bit boundary and cause carries since the actual maths are done as
++ pairs of 32 bit instructions. */
++
++/* Note: This file is #included by some of the ARM tests. */
++
++__extension__ typedef __SIZE_TYPE__ size_t;
++
++extern void abort (void);
++extern void *memcpy (void *, const void *, size_t);
++extern int memcmp (const void *, const void *, size_t);
++
++/* Temporary space where the work actually gets done. */
++static long long AL[24];
++/* Values copied into AL before we start. */
++static long long init_di[24] = { 0x100000002ll, 0x200000003ll, 0, 1,
++
++ 0x100000002ll, 0x100000002ll,
++ 0x100000002ll, 0x100000002ll,
++
++ 0, 0x1000e0de0000ll,
++ 42 , 0xc001c0de0000ll,
++
++ -1ll, 0, 0xff00ff0000ll, -1ll,
++
++ 0, 0x1000e0de0000ll,
++ 42 , 0xc001c0de0000ll,
++
++ -1ll, 0, 0xff00ff0000ll, -1ll};
++/* This is what should be in AL at the end. */
++static long long test_di[24] = { 0x1234567890ll, 0x1234567890ll, 1, 0,
++
++ 0x100000002ll, 0x100000002ll,
++ 0x100000002ll, 0x100000002ll,
++
++ 1, 0xc001c0de0000ll,
++ 20, 0x1000e0de0000ll,
++
++ 0x300000007ll , 0x500000009ll,
++ 0xf100ff0001ll, ~0xa00000007ll,
++
++ 1, 0xc001c0de0000ll,
++ 20, 0x1000e0de0000ll,
++
++ 0x300000007ll , 0x500000009ll,
++ 0xf100ff0001ll, ~0xa00000007ll };
++
++/* First check they work in terms of what they do to memory. */
++static void
++do_noret_di (void)
++{
++ __sync_val_compare_and_swap (AL+0, 0x100000002ll, 0x1234567890ll);
++ __sync_bool_compare_and_swap (AL+1, 0x200000003ll, 0x1234567890ll);
++ __sync_lock_test_and_set (AL+2, 1);
++ __sync_lock_release (AL+3);
++
++ /* The following tests should not change the value since the
++ original does NOT match. */
++ __sync_val_compare_and_swap (AL+4, 0x000000002ll, 0x1234567890ll);
++ __sync_val_compare_and_swap (AL+5, 0x100000000ll, 0x1234567890ll);
++ __sync_bool_compare_and_swap (AL+6, 0x000000002ll, 0x1234567890ll);
++ __sync_bool_compare_and_swap (AL+7, 0x100000000ll, 0x1234567890ll);
++
++ __sync_fetch_and_add (AL+8, 1);
++ __sync_fetch_and_add (AL+9, 0xb000e0000000ll); /* + to both halves & carry. */
++ __sync_fetch_and_sub (AL+10, 22);
++ __sync_fetch_and_sub (AL+11, 0xb000e0000000ll);
++
++ __sync_fetch_and_and (AL+12, 0x300000007ll);
++ __sync_fetch_and_or (AL+13, 0x500000009ll);
++ __sync_fetch_and_xor (AL+14, 0xe00000001ll);
++ __sync_fetch_and_nand (AL+15, 0xa00000007ll);
++
++ /* These should be the same as the fetch_and_* cases except for
++ return value. */
++ __sync_add_and_fetch (AL+16, 1);
++ /* add to both halves & carry. */
++ __sync_add_and_fetch (AL+17, 0xb000e0000000ll);
++ __sync_sub_and_fetch (AL+18, 22);
++ __sync_sub_and_fetch (AL+19, 0xb000e0000000ll);
++
++ __sync_and_and_fetch (AL+20, 0x300000007ll);
++ __sync_or_and_fetch (AL+21, 0x500000009ll);
++ __sync_xor_and_fetch (AL+22, 0xe00000001ll);
++ __sync_nand_and_fetch (AL+23, 0xa00000007ll);
++}
++
++/* Now check return values. */
++static void
++do_ret_di (void)
++{
++ if (__sync_val_compare_and_swap (AL+0, 0x100000002ll, 0x1234567890ll) !=
++ 0x100000002ll) abort ();
++ if (__sync_bool_compare_and_swap (AL+1, 0x200000003ll, 0x1234567890ll) !=
++ 1) abort ();
++ if (__sync_lock_test_and_set (AL+2, 1) != 0) abort ();
++ __sync_lock_release (AL+3); /* no return value, but keep to match results. */
++
++ /* The following tests should not change the value since the
++ original does NOT match. */
++ if (__sync_val_compare_and_swap (AL+4, 0x000000002ll, 0x1234567890ll) !=
++ 0x100000002ll) abort ();
++ if (__sync_val_compare_and_swap (AL+5, 0x100000000ll, 0x1234567890ll) !=
++ 0x100000002ll) abort ();
++ if (__sync_bool_compare_and_swap (AL+6, 0x000000002ll, 0x1234567890ll) !=
++ 0) abort ();
++ if (__sync_bool_compare_and_swap (AL+7, 0x100000000ll, 0x1234567890ll) !=
++ 0) abort ();
++
++ if (__sync_fetch_and_add (AL+8, 1) != 0) abort ();
++ if (__sync_fetch_and_add (AL+9, 0xb000e0000000ll) != 0x1000e0de0000ll) abort ();
++ if (__sync_fetch_and_sub (AL+10, 22) != 42) abort ();
++ if (__sync_fetch_and_sub (AL+11, 0xb000e0000000ll) != 0xc001c0de0000ll)
++ abort ();
++
++ if (__sync_fetch_and_and (AL+12, 0x300000007ll) != -1ll) abort ();
++ if (__sync_fetch_and_or (AL+13, 0x500000009ll) != 0) abort ();
++ if (__sync_fetch_and_xor (AL+14, 0xe00000001ll) != 0xff00ff0000ll) abort ();
++ if (__sync_fetch_and_nand (AL+15, 0xa00000007ll) != -1ll) abort ();
++
++ /* These should be the same as the fetch_and_* cases except for
++ return value. */
++ if (__sync_add_and_fetch (AL+16, 1) != 1) abort ();
++ if (__sync_add_and_fetch (AL+17, 0xb000e0000000ll) != 0xc001c0de0000ll)
++ abort ();
++ if (__sync_sub_and_fetch (AL+18, 22) != 20) abort ();
++ if (__sync_sub_and_fetch (AL+19, 0xb000e0000000ll) != 0x1000e0de0000ll)
++ abort ();
++
++ if (__sync_and_and_fetch (AL+20, 0x300000007ll) != 0x300000007ll) abort ();
++ if (__sync_or_and_fetch (AL+21, 0x500000009ll) != 0x500000009ll) abort ();
++ if (__sync_xor_and_fetch (AL+22, 0xe00000001ll) != 0xf100ff0001ll) abort ();
++ if (__sync_nand_and_fetch (AL+23, 0xa00000007ll) != ~0xa00000007ll) abort ();
++}
++
++int main ()
++{
++ memcpy (AL, init_di, sizeof (init_di));
++
++ do_noret_di ();
++
++ if (memcmp (AL, test_di, sizeof (test_di)))
++ abort ();
++
++ memcpy (AL, init_di, sizeof (init_di));
++
++ do_ret_di ();
++
++ if (memcmp (AL, test_di, sizeof (test_di)))
++ abort ();
++
++ return 0;
++}
+
+=== added file 'gcc/testsuite/gcc.dg/di-sync-multithread.c'
+--- old/gcc/testsuite/gcc.dg/di-sync-multithread.c 1970-01-01 00:00:00 +0000
++++ new/gcc/testsuite/gcc.dg/di-sync-multithread.c 2011-10-14 15:56:32 +0000
+@@ -0,0 +1,205 @@
++/* { dg-do run } */
++/* { dg-require-effective-target sync_longlong } */
++/* { dg-require-effective-target pthread_h } */
++/* { dg-require-effective-target pthread } */
++/* { dg-options "-pthread -std=gnu99" } */
++
++/* test of long long atomic ops performed in parallel in 3 pthreads
++ david.gilbert@linaro.org */
++
++#include <pthread.h>
++#include <unistd.h>
++
++/*#define DEBUGIT 1 */
++
++#ifdef DEBUGIT
++#include <stdio.h>
++
++#define DOABORT(x,...) {\
++ fprintf (stderr, x, __VA_ARGS__); fflush (stderr); abort ();\
++ }
++
++#else
++
++#define DOABORT(x,...) abort ();
++
++#endif
++
++/* Passed to each thread to describe which bits it is going to work on. */
++struct threadwork {
++ unsigned long long count; /* incremented each time the worker loops. */
++ unsigned int thread; /* ID */
++ unsigned int addlsb; /* 8 bit */
++ unsigned int logic1lsb; /* 5 bit */
++ unsigned int logic2lsb; /* 8 bit */
++};
++
++/* The shared word where all the atomic work is done. */
++static volatile long long workspace;
++
++/* A shared word to tell the workers to quit when non-0. */
++static long long doquit;
++
++extern void abort (void);
++
++/* Note this test doesn't test the return values much. */
++void*
++worker (void* data)
++{
++ struct threadwork *tw = (struct threadwork*)data;
++ long long add1bit = 1ll << tw->addlsb;
++ long long logic1bit = 1ll << tw->logic1lsb;
++ long long logic2bit = 1ll << tw->logic2lsb;
++
++ /* Clear the bits we use. */
++ __sync_and_and_fetch (&workspace, ~(0xffll * add1bit));
++ __sync_fetch_and_and (&workspace, ~(0x1fll * logic1bit));
++ __sync_fetch_and_and (&workspace, ~(0xffll * logic2bit));
++
++ do
++ {
++ long long tmp1, tmp2, tmp3;
++ /* OK, lets try and do some stuff to the workspace - by the end
++ of the main loop our area should be the same as it is now - i.e. 0. */
++
++ /* Push the arithmetic section upto 128 - one of the threads will
++ case this to carry accross the 32bit boundary. */
++ for (tmp2 = 0; tmp2 < 64; tmp2++)
++ {
++ /* Add 2 using the two different adds. */
++ tmp1 = __sync_add_and_fetch (&workspace, add1bit);
++ tmp3 = __sync_fetch_and_add (&workspace, add1bit);
++
++ /* The value should be the intermediate add value in both cases. */
++ if ((tmp1 & (add1bit * 0xff)) != (tmp3 & (add1bit * 0xff)))
++ DOABORT ("Mismatch of add intermediates on thread %d "
++ "workspace=0x%llx tmp1=0x%llx "
++ "tmp2=0x%llx tmp3=0x%llx\n",
++ tw->thread, workspace, tmp1, tmp2, tmp3);
++ }
++
++ /* Set the logic bits. */
++ tmp2=__sync_or_and_fetch (&workspace,
++ 0x1fll * logic1bit | 0xffll * logic2bit);
++
++ /* Check the logic bits are set and the arithmetic value is correct. */
++ if ((tmp2 & (0x1fll * logic1bit | 0xffll * logic2bit
++ | 0xffll * add1bit))
++ != (0x1fll * logic1bit | 0xffll * logic2bit | 0x80ll * add1bit))
++ DOABORT ("Midloop check failed on thread %d "
++ "workspace=0x%llx tmp2=0x%llx "
++ "masktmp2=0x%llx expected=0x%llx\n",
++ tw->thread, workspace, tmp2,
++ tmp2 & (0x1fll * logic1bit | 0xffll * logic2bit |
++ 0xffll * add1bit),
++ (0x1fll * logic1bit | 0xffll * logic2bit | 0x80ll * add1bit));
++
++ /* Pull the arithmetic set back down to 0 - again this should cause a
++ carry across the 32bit boundary in one thread. */
++
++ for (tmp2 = 0; tmp2 < 64; tmp2++)
++ {
++ /* Subtract 2 using the two different subs. */
++ tmp1=__sync_sub_and_fetch (&workspace, add1bit);
++ tmp3=__sync_fetch_and_sub (&workspace, add1bit);
++
++ /* The value should be the intermediate sub value in both cases. */
++ if ((tmp1 & (add1bit * 0xff)) != (tmp3 & (add1bit * 0xff)))
++ DOABORT ("Mismatch of sub intermediates on thread %d "
++ "workspace=0x%llx tmp1=0x%llx "
++ "tmp2=0x%llx tmp3=0x%llx\n",
++ tw->thread, workspace, tmp1, tmp2, tmp3);
++ }
++
++
++ /* Clear the logic bits. */
++ __sync_fetch_and_xor (&workspace, 0x1fll * logic1bit);
++ tmp3=__sync_and_and_fetch (&workspace, ~(0xffll * logic2bit));
++
++ /* The logic bits and the arithmetic bits should be zero again. */
++ if (tmp3 & (0x1fll * logic1bit | 0xffll * logic2bit | 0xffll * add1bit))
++ DOABORT ("End of worker loop; bits none 0 on thread %d "
++ "workspace=0x%llx tmp3=0x%llx "
++ "mask=0x%llx maskedtmp3=0x%llx\n",
++ tw->thread, workspace, tmp3, (0x1fll * logic1bit |
++ 0xffll * logic2bit | 0xffll * add1bit),
++ tmp3 & (0x1fll * logic1bit | 0xffll * logic2bit | 0xffll * add1bit));
++
++ __sync_add_and_fetch (&tw->count, 1);
++ }
++ while (!__sync_bool_compare_and_swap (&doquit, 1, 1));
++
++ pthread_exit (0);
++}
++
++int
++main ()
++{
++ /* We have 3 threads doing three sets of operations, an 8 bit
++ arithmetic field, a 5 bit logic field and an 8 bit logic
++ field (just to pack them all in).
++
++ 6 5 4 4 3 2 1
++ 3 6 8 0 2 4 6 8 0
++ |...,...|...,...|...,...|...,...|...,...|...,...|...,...|...,...
++ - T0 -- T1 -- T2 --T2 -- T0 -*- T2-- T1-- T1 -***- T0-
++ logic2 logic2 arith log2 arith log1 log1 arith log1
++
++ */
++ unsigned int t;
++ long long tmp;
++ int err;
++
++ struct threadwork tw[3]={
++ { 0ll, 0, 27, 0, 56 },
++ { 0ll, 1, 8,16, 48 },
++ { 0ll, 2, 40,21, 35 }
++ };
++
++ pthread_t threads[3];
++
++ __sync_lock_release (&doquit);
++
++ /* Get the work space into a known value - All 1's. */
++ __sync_lock_release (&workspace); /* Now all 0. */
++ tmp = __sync_val_compare_and_swap (&workspace, 0, -1ll);
++ if (tmp!=0)
++ DOABORT ("Initial __sync_val_compare_and_swap wasn't 0 workspace=0x%llx "
++ "tmp=0x%llx\n", workspace,tmp);
++
++ for (t = 0; t < 3; t++)
++ {
++ err=pthread_create (&threads[t], NULL , worker, &tw[t]);
++ if (err) DOABORT ("pthread_create failed on thread %d with error %d\n",
++ t, err);
++ };
++
++ sleep (5);
++
++ /* Stop please. */
++ __sync_lock_test_and_set (&doquit, 1ll);
++
++ for (t = 0; t < 3; t++)
++ {
++ err=pthread_join (threads[t], NULL);
++ if (err)
++ DOABORT ("pthread_join failed on thread %d with error %d\n", t, err);
++ };
++
++ __sync_synchronize ();
++
++ /* OK, so all the workers have finished -
++ the workers should have zero'd their workspace, the unused areas
++ should still be 1. */
++ if (!__sync_bool_compare_and_swap (&workspace, 0x040000e0ll, 0))
++ DOABORT ("End of run workspace mismatch, got %llx\n", workspace);
++
++ /* All the workers should have done some work. */
++ for (t = 0; t < 3; t++)
++ {
++ if (tw[t].count == 0) DOABORT ("Worker %d gave 0 count\n", t);
++ };
++
++ return 0;
++}
++
+
+=== added file 'gcc/testsuite/gcc.target/arm/di-longlong64-sync-withhelpers.c'
+--- old/gcc/testsuite/gcc.target/arm/di-longlong64-sync-withhelpers.c 1970-01-01 00:00:00 +0000
++++ new/gcc/testsuite/gcc.target/arm/di-longlong64-sync-withhelpers.c 2011-10-14 15:56:32 +0000
+@@ -0,0 +1,14 @@
++/* { dg-do compile } */
++/* { dg-require-effective-target arm_arch_v5_ok } */
++/* { dg-options "-std=gnu99" } */
++/* { dg-add-options arm_arch_v5 } */
++/* { dg-message "note: '__sync_fetch_and_nand' changed semantics in GCC 4.4" "" { target *-*-* } 0 } */
++/* { dg-message "note: '__sync_nand_and_fetch' changed semantics in GCC 4.4" "" { target *-*-* } 0 } */
++/* { dg-message "file included" "In file included" { target *-*-* } 0 } */
++
++#include "../../gcc.dg/di-longlong64-sync-1.c"
++
++/* On an old ARM we have no ldrexd or strexd so we have to use helpers. */
++/* { dg-final { scan-assembler-not "ldrexd" } } */
++/* { dg-final { scan-assembler-not "strexd" } } */
++/* { dg-final { scan-assembler "__sync_" } } */
+
+=== added file 'gcc/testsuite/gcc.target/arm/di-longlong64-sync-withldrexd.c'
+--- old/gcc/testsuite/gcc.target/arm/di-longlong64-sync-withldrexd.c 1970-01-01 00:00:00 +0000
++++ new/gcc/testsuite/gcc.target/arm/di-longlong64-sync-withldrexd.c 2011-10-14 15:56:32 +0000
+@@ -0,0 +1,17 @@
++/* { dg-do compile } */
++/* { dg-require-effective-target arm_arm_ok } */
++/* { dg-options "-marm -std=gnu99" } */
++/* { dg-require-effective-target arm_arch_v6k_ok } */
++/* { dg-add-options arm_arch_v6k } */
++/* { dg-message "note: '__sync_fetch_and_nand' changed semantics in GCC 4.4" "" { target *-*-* } 0 } */
++/* { dg-message "note: '__sync_nand_and_fetch' changed semantics in GCC 4.4" "" { target *-*-* } 0 } */
++/* { dg-message "file included" "In file included" { target *-*-* } 0 } */
++
++#include "../../gcc.dg/di-longlong64-sync-1.c"
++
++/* We should be using ldrexd, strexd and no helpers or shorter ldrex. */
++/* { dg-final { scan-assembler-times "\tldrexd" 46 } } */
++/* { dg-final { scan-assembler-times "\tstrexd" 46 } } */
++/* { dg-final { scan-assembler-not "__sync_" } } */
++/* { dg-final { scan-assembler-not "ldrex\t" } } */
++/* { dg-final { scan-assembler-not "strex\t" } } */
+
+=== modified file 'gcc/testsuite/lib/target-supports.exp'
+--- old/gcc/testsuite/lib/target-supports.exp 2011-11-22 17:10:17 +0000
++++ new/gcc/testsuite/lib/target-supports.exp 2011-11-28 15:07:01 +0000
+@@ -2000,6 +2000,47 @@
+ check_effective_target_arm_fp16_ok_nocache]
+ }
+
++# Creates a series of routines that return 1 if the given architecture
++# can be selected and a routine to give the flags to select that architecture
++# Note: Extra flags may be added to disable options from newer compilers
++# (Thumb in particular - but others may be added in the future)
++# Usage: /* { dg-require-effective-target arm_arch_v5_ok } */
++# /* { dg-add-options arm_arch_v5 } */
++foreach { armfunc armflag armdef } { v5 "-march=armv5 -marm" __ARM_ARCH_5__
++ v6 "-march=armv6" __ARM_ARCH_6__
++ v6k "-march=armv6k" __ARM_ARCH_6K__
++ v7a "-march=armv7-a" __ARM_ARCH_7A__ } {
++ eval [string map [list FUNC $armfunc FLAG $armflag DEF $armdef ] {
++ proc check_effective_target_arm_arch_FUNC_ok { } {
++ if { [ string match "*-marm*" "FLAG" ] &&
++ ![check_effective_target_arm_arm_ok] } {
++ return 0
++ }
++ return [check_no_compiler_messages arm_arch_FUNC_ok assembly {
++ #if !defined (DEF)
++ #error FOO
++ #endif
++ } "FLAG" ]
++ }
++
++ proc add_options_for_arm_arch_FUNC { flags } {
++ return "$flags FLAG"
++ }
++ }]
++}
++
++# Return 1 if this is an ARM target where -marm causes ARM to be
++# used (not Thumb)
++
++proc check_effective_target_arm_arm_ok { } {
++ return [check_no_compiler_messages arm_arm_ok assembly {
++ #if !defined (__arm__) || defined (__thumb__) || defined (__thumb2__)
++ #error FOO
++ #endif
++ } "-marm"]
++}
++
++
+ # Return 1 is this is an ARM target where -mthumb causes Thumb-1 to be
+ # used.
+
+@@ -3384,6 +3425,31 @@
+ return $et_sync_int_long_saved
+ }
+
++# Return 1 if the target supports atomic operations on "long long" and can
++# execute them
++# So far only put checks in for ARM, others may want to add their own
++proc check_effective_target_sync_longlong { } {
++ return [check_runtime sync_longlong_runtime {
++ #include <stdlib.h>
++ int main ()
++ {
++ long long l1;
++
++ if (sizeof (long long) != 8)
++ exit (1);
++
++ #ifdef __arm__
++ /* Just check for native; checking for kernel fallback is tricky. */
++ asm volatile ("ldrexd r0,r1, [%0]" : : "r" (&l1) : "r0", "r1");
++ #else
++ # error "Add other suitable archs here"
++ #endif
++
++ exit (0);
++ }
++ } "" ]
++}
++
+ # Return 1 if the target supports atomic operations on "char" and "short".
+
+ proc check_effective_target_sync_char_short { } {
+
--- /dev/null
+2011-11-27 Ira Rosen <ira.rosen@linaro.org>
+
+ Needs to be merged upstream:
+
+ gcc/
+ * tree-vect-patterns.c (widened_name_p): Rename to ...
+ (type_conversion_p): ... this. Add new argument to determine
+ if it's a promotion or demotion operation. Check for
+ CONVERT_EXPR_CODE_P instead of NOP_EXPR.
+ (vect_recog_dot_prod_pattern): Call type_conversion_p instead
+ widened_name_p.
+ (vect_recog_widen_mult_pattern, vect_recog_widen_sum_pattern,
+ vect_operation_fits_smaller_type, vect_recog_widen_shift_pattern):
+ Likewise.
+ (vect_recog_mixed_size_cond_pattern): Likewise and allow
+ non-constant then and else clauses.
+
+ gcc/testsuite/
+ * gcc.dg/vect/bb-slp-cond-3.c: New test.
+ * gcc.dg/vect/bb-slp-cond-4.c: New test.
+
+=== added file 'gcc/testsuite/gcc.dg/vect/bb-slp-cond-3.c'
+--- old/gcc/testsuite/gcc.dg/vect/bb-slp-cond-3.c 1970-01-01 00:00:00 +0000
++++ new/gcc/testsuite/gcc.dg/vect/bb-slp-cond-3.c 2011-11-27 11:29:32 +0000
+@@ -0,0 +1,85 @@
++/* { dg-require-effective-target vect_condition } */
++
++#include "tree-vect.h"
++
++#define N 64
++
++/* Comparison in int, then/else and result in unsigned char. */
++
++static inline unsigned char
++foo (int x, int y, int a, int b)
++{
++ if (x >= y)
++ return a;
++ else
++ return b;
++}
++
++__attribute__((noinline, noclone)) void
++bar (unsigned char * __restrict__ a, unsigned char * __restrict__ b,
++ unsigned char * __restrict__ c, unsigned char * __restrict__ d,
++ unsigned char * __restrict__ e, int stride, int w)
++{
++ int i;
++ for (i = 0; i < N/stride; i++, a += stride, b += stride, c += stride,
++ d += stride, e += stride)
++ {
++ e[0] = foo (c[0], d[0], a[0] * w, b[0] * w);
++ e[1] = foo (c[1], d[1], a[1] * w, b[1] * w);
++ e[2] = foo (c[2], d[2], a[2] * w, b[2] * w);
++ e[3] = foo (c[3], d[3], a[3] * w, b[3] * w);
++ e[4] = foo (c[4], d[4], a[4] * w, b[4] * w);
++ e[5] = foo (c[5], d[5], a[5] * w, b[5] * w);
++ e[6] = foo (c[6], d[6], a[6] * w, b[6] * w);
++ e[7] = foo (c[7], d[7], a[7] * w, b[7] * w);
++ e[8] = foo (c[8], d[8], a[8] * w, b[8] * w);
++ e[9] = foo (c[9], d[9], a[9] * w, b[9] * w);
++ e[10] = foo (c[10], d[10], a[10] * w, b[10] * w);
++ e[11] = foo (c[11], d[11], a[11] * w, b[11] * w);
++ e[12] = foo (c[12], d[12], a[12] * w, b[12] * w);
++ e[13] = foo (c[13], d[13], a[13] * w, b[13] * w);
++ e[14] = foo (c[14], d[14], a[14] * w, b[14] * w);
++ e[15] = foo (c[15], d[15], a[15] * w, b[15] * w);
++ }
++}
++
++
++unsigned char a[N], b[N], c[N], d[N], e[N];
++
++int main ()
++{
++ int i;
++
++ check_vect ();
++
++ for (i = 0; i < N; i++)
++ {
++ a[i] = i;
++ b[i] = 5;
++ e[i] = 0;
++
++ switch (i % 9)
++ {
++ case 0: asm (""); c[i] = i; d[i] = i + 1; break;
++ case 1: c[i] = 0; d[i] = 0; break;
++ case 2: c[i] = i + 1; d[i] = i - 1; break;
++ case 3: c[i] = i; d[i] = i + 7; break;
++ case 4: c[i] = i; d[i] = i; break;
++ case 5: c[i] = i + 16; d[i] = i + 3; break;
++ case 6: c[i] = i - 5; d[i] = i; break;
++ case 7: c[i] = i; d[i] = i; break;
++ case 8: c[i] = i; d[i] = i - 7; break;
++ }
++ }
++
++ bar (a, b, c, d, e, 16, 2);
++ for (i = 0; i < N; i++)
++ if (e[i] != ((i % 3) == 0 ? 10 : 2 * i))
++ abort ();
++
++ return 0;
++}
++
++/* { dg-final { scan-tree-dump-times "basic block vectorized using SLP" 1 "slp" { target { vect_element_align && vect_int_mult } } } } */
++/* { dg-final { cleanup-tree-dump "slp" } } */
++
+
+=== added file 'gcc/testsuite/gcc.dg/vect/bb-slp-cond-4.c'
+--- old/gcc/testsuite/gcc.dg/vect/bb-slp-cond-4.c 1970-01-01 00:00:00 +0000
++++ new/gcc/testsuite/gcc.dg/vect/bb-slp-cond-4.c 2011-11-27 11:29:32 +0000
+@@ -0,0 +1,85 @@
++/* { dg-require-effective-target vect_condition } */
++
++#include "tree-vect.h"
++
++#define N 64
++
++/* Comparison in short, then/else and result in int. */
++static inline int
++foo (short x, short y, int a, int b)
++{
++ if (x >= y)
++ return a;
++ else
++ return b;
++}
++
++__attribute__((noinline, noclone)) void
++bar (short * __restrict__ a, short * __restrict__ b,
++ short * __restrict__ c, short * __restrict__ d,
++ int * __restrict__ e, int stride, int w)
++{
++ int i;
++ for (i = 0; i < N/stride; i++, a += stride, b += stride, c += stride,
++ d += stride, e += stride)
++ {
++ e[0] = foo (c[0], d[0], a[0], b[0]);
++ e[1] = foo (c[1], d[1], a[1], b[1]);
++ e[2] = foo (c[2], d[2], a[2], b[2]);
++ e[3] = foo (c[3], d[3], a[3], b[3]);
++ e[4] = foo (c[4], d[4], a[4], b[4]);
++ e[5] = foo (c[5], d[5], a[5], b[5]);
++ e[6] = foo (c[6], d[6], a[6], b[6]);
++ e[7] = foo (c[7], d[7], a[7], b[7]);
++ e[8] = foo (c[8], d[8], a[8], b[8]);
++ e[9] = foo (c[9], d[9], a[9], b[9]);
++ e[10] = foo (c[10], d[10], a[10], b[10]);
++ e[11] = foo (c[11], d[11], a[11], b[11]);
++ e[12] = foo (c[12], d[12], a[12], b[12]);
++ e[13] = foo (c[13], d[13], a[13], b[13]);
++ e[14] = foo (c[14], d[14], a[14], b[14]);
++ e[15] = foo (c[15], d[15], a[15], b[15]);
++ }
++}
++
++
++short a[N], b[N], c[N], d[N];
++int e[N];
++
++int main ()
++{
++ int i;
++
++ check_vect ();
++
++ for (i = 0; i < N; i++)
++ {
++ a[i] = i;
++ b[i] = 5;
++ e[i] = 0;
++
++ switch (i % 9)
++ {
++ case 0: asm (""); c[i] = - i - 1; d[i] = i + 1; break;
++ case 1: c[i] = 0; d[i] = 0; break;
++ case 2: c[i] = i + 1; d[i] = - i - 1; break;
++ case 3: c[i] = i; d[i] = i + 7; break;
++ case 4: c[i] = i; d[i] = i; break;
++ case 5: c[i] = i + 16; d[i] = i + 3; break;
++ case 6: c[i] = - i - 5; d[i] = - i; break;
++ case 7: c[i] = - i; d[i] = - i; break;
++ case 8: c[i] = - i; d[i] = - i - 7; break;
++ }
++ }
++
++ bar (a, b, c, d, e, 16, 2);
++ for (i = 0; i < N; i++)
++ if (e[i] != ((i % 3) == 0 ? 5 : i))
++ abort ();
++
++ return 0;
++}
++
++/* { dg-final { scan-tree-dump-times "basic block vectorized using SLP" 1 "slp" { target vect_element_align } } } */
++/* { dg-final { cleanup-tree-dump "slp" } } */
++
+
+=== modified file 'gcc/tree-vect-patterns.c'
+--- old/gcc/tree-vect-patterns.c 2011-11-23 07:49:33 +0000
++++ new/gcc/tree-vect-patterns.c 2011-11-27 12:17:31 +0000
+@@ -62,18 +62,16 @@
+ vect_recog_mixed_size_cond_pattern};
+
+
+-/* Function widened_name_p
+-
+- Check whether NAME, an ssa-name used in USE_STMT,
+- is a result of a type-promotion, such that:
+- DEF_STMT: NAME = NOP (name0)
+- where the type of name0 (HALF_TYPE) is smaller than the type of NAME.
++/* Check whether NAME, an ssa-name used in USE_STMT,
++ is a result of a type promotion or demotion, such that:
++ DEF_STMT: NAME = NOP (name0)
++ where the type of name0 (ORIG_TYPE) is smaller/bigger than the type of NAME.
+ If CHECK_SIGN is TRUE, check that either both types are signed or both are
+ unsigned. */
+
+ static bool
+-widened_name_p (tree name, gimple use_stmt, tree *half_type, gimple *def_stmt,
+- bool check_sign)
++type_conversion_p (tree name, gimple use_stmt, bool check_sign,
++ tree *orig_type, gimple *def_stmt, bool *promotion)
+ {
+ tree dummy;
+ gimple dummy_gimple;
+@@ -96,21 +94,27 @@
+ && dt != vect_external_def && dt != vect_constant_def)
+ return false;
+
+- if (! *def_stmt)
++ if (!*def_stmt)
+ return false;
+
+ if (!is_gimple_assign (*def_stmt))
+ return false;
+
+- if (gimple_assign_rhs_code (*def_stmt) != NOP_EXPR)
++ if (!CONVERT_EXPR_CODE_P (gimple_assign_rhs_code (*def_stmt)))
+ return false;
+
+ oprnd0 = gimple_assign_rhs1 (*def_stmt);
+
+- *half_type = TREE_TYPE (oprnd0);
+- if (!INTEGRAL_TYPE_P (type) || !INTEGRAL_TYPE_P (*half_type)
+- || ((TYPE_UNSIGNED (type) != TYPE_UNSIGNED (*half_type)) && check_sign)
+- || (TYPE_PRECISION (type) < (TYPE_PRECISION (*half_type) * 2)))
++ *orig_type = TREE_TYPE (oprnd0);
++ if (!INTEGRAL_TYPE_P (type) || !INTEGRAL_TYPE_P (*orig_type)
++ || ((TYPE_UNSIGNED (type) != TYPE_UNSIGNED (*orig_type)) && check_sign))
++ return false;
++
++ if (TYPE_PRECISION (type) >= (TYPE_PRECISION (*orig_type) * 2))
++ *promotion = true;
++ else if (TYPE_PRECISION (*orig_type) >= (TYPE_PRECISION (type) * 2))
++ *promotion = false;
++ else
+ return false;
+
+ if (!vect_is_simple_use (oprnd0, loop_vinfo, bb_vinfo, &dummy_gimple, &dummy,
+@@ -192,6 +196,7 @@
+ loop_vec_info loop_info = STMT_VINFO_LOOP_VINFO (stmt_vinfo);
+ struct loop *loop;
+ tree var, rhs;
++ bool promotion;
+
+ if (!loop_info)
+ return NULL;
+@@ -255,7 +260,9 @@
+ return NULL;
+ stmt = last_stmt;
+
+- if (widened_name_p (oprnd0, stmt, &half_type, &def_stmt, true))
++ if (type_conversion_p (oprnd0, stmt, true, &half_type, &def_stmt,
++ &promotion)
++ && promotion)
+ {
+ stmt = def_stmt;
+ oprnd0 = gimple_assign_rhs1 (stmt);
+@@ -310,10 +317,14 @@
+ if (!types_compatible_p (TREE_TYPE (oprnd0), prod_type)
+ || !types_compatible_p (TREE_TYPE (oprnd1), prod_type))
+ return NULL;
+- if (!widened_name_p (oprnd0, stmt, &half_type0, &def_stmt, true))
++ if (!type_conversion_p (oprnd0, stmt, true, &half_type0, &def_stmt,
++ &promotion)
++ || !promotion)
+ return NULL;
+ oprnd00 = gimple_assign_rhs1 (def_stmt);
+- if (!widened_name_p (oprnd1, stmt, &half_type1, &def_stmt, true))
++ if (!type_conversion_p (oprnd0, stmt, true, &half_type1, &def_stmt,
++ &promotion)
++ || !promotion)
+ return NULL;
+ oprnd01 = gimple_assign_rhs1 (def_stmt);
+ if (!types_compatible_p (half_type0, half_type1))
+@@ -526,7 +537,7 @@
+ enum tree_code dummy_code;
+ int dummy_int;
+ VEC (tree, heap) *dummy_vec;
+- bool op1_ok;
++ bool op1_ok, promotion;
+
+ if (!is_gimple_assign (last_stmt))
+ return NULL;
+@@ -546,12 +557,14 @@
+ return NULL;
+
+ /* Check argument 0. */
+- if (!widened_name_p (oprnd0, last_stmt, &half_type0, &def_stmt0, false))
++ if (!type_conversion_p (oprnd0, last_stmt, false, &half_type0, &def_stmt0,
++ &promotion)
++ || !promotion)
+ return NULL;
+- /* Check argument 1. */
+- op1_ok = widened_name_p (oprnd1, last_stmt, &half_type1, &def_stmt1, false);
+-
+- if (op1_ok)
++ /* Check argument 1. */
++ op1_ok = type_conversion_p (oprnd1, last_stmt, false, &half_type1,
++ &def_stmt1, &promotion);
++ if (op1_ok && promotion)
+ {
+ oprnd0 = gimple_assign_rhs1 (def_stmt0);
+ oprnd1 = gimple_assign_rhs1 (def_stmt1);
+@@ -793,6 +806,7 @@
+ loop_vec_info loop_info = STMT_VINFO_LOOP_VINFO (stmt_vinfo);
+ struct loop *loop;
+ tree var;
++ bool promotion;
+
+ if (!loop_info)
+ return NULL;
+@@ -832,8 +846,10 @@
+ Left to check that oprnd0 is defined by a cast from type 'type' to type
+ 'TYPE'. */
+
+- if (!widened_name_p (oprnd0, last_stmt, &half_type, &stmt, true))
+- return NULL;
++ if (!type_conversion_p (oprnd0, last_stmt, true, &half_type, &stmt,
++ &promotion)
++ || !promotion)
++ return NULL;
+
+ oprnd0 = gimple_assign_rhs1 (stmt);
+ *type_in = half_type;
+@@ -899,6 +915,7 @@
+ gimple def_stmt, new_stmt;
+ bool first = false;
+ loop_vec_info loop_info = STMT_VINFO_LOOP_VINFO (vinfo_for_stmt (stmt));
++ bool promotion;
+ bb_vec_info bb_info = STMT_VINFO_BB_VINFO (vinfo_for_stmt (stmt));
+ struct loop *loop = NULL;
+
+@@ -933,7 +950,9 @@
+ else
+ {
+ first = true;
+- if (!widened_name_p (oprnd, stmt, &half_type, &def_stmt, false)
++ if (!type_conversion_p (oprnd, stmt, false, &half_type, &def_stmt,
++ &promotion)
++ || !promotion
+ || !gimple_bb (def_stmt)
+ || (loop && !flow_bb_inside_loop_p (loop, gimple_bb (def_stmt)))
+ || (!loop && gimple_bb (def_stmt) != BB_VINFO_BB (bb_info)
+@@ -1327,6 +1346,7 @@
+ VEC (tree, heap) * dummy_vec;
+ gimple use_stmt = NULL;
+ bool over_widen = false;
++ bool promotion;
+
+ if (!is_gimple_assign (last_stmt) || !vinfo_for_stmt (last_stmt))
+ return NULL;
+@@ -1381,8 +1401,10 @@
+ return NULL;
+
+ /* Check operand 0: it has to be defined by a type promotion. */
+- if (!widened_name_p (oprnd0, last_stmt, &half_type0, &def_stmt0, false))
+- return NULL;
++ if (!type_conversion_p (oprnd0, last_stmt, false, &half_type0, &def_stmt0,
++ &promotion)
++ || !promotion)
++ return NULL;
+
+ /* Check operand 1: has to be positive. We check that it fits the type
+ in vect_handle_widen_op_by_const (). */
+@@ -1492,9 +1514,9 @@
+ S1 a_T = x_t CMP y_t ? b_T : c_T;
+
+ where type 'TYPE' is an integral type which has different size
+- from 'type'. b_T and c_T are constants and if 'TYPE' is wider
++ from 'type'. b_T and c_T are either constants (and if 'TYPE' is wider
+ than 'type', the constants need to fit into an integer type
+- with the same width as 'type'.
++ with the same width as 'type') or results of conversion from 'type'.
+
+ Input:
+
+@@ -1523,6 +1545,9 @@
+ enum machine_mode cmpmode;
+ gimple pattern_stmt, def_stmt;
+ loop_vec_info loop_vinfo = STMT_VINFO_LOOP_VINFO (stmt_vinfo);
++ tree orig_type0 = NULL_TREE, orig_type1 = NULL_TREE;
++ gimple def_stmt0 = NULL, def_stmt1 = NULL;
++ bool promotion;
+ bb_vec_info bb_vinfo = STMT_VINFO_BB_VINFO (stmt_vinfo);
+
+ if (!is_gimple_assign (last_stmt)
+@@ -1535,25 +1560,40 @@
+ then_clause = TREE_OPERAND (op, 1);
+ else_clause = TREE_OPERAND (op, 2);
+
+- if (TREE_CODE (then_clause) != INTEGER_CST
+- || TREE_CODE (else_clause) != INTEGER_CST)
+- return NULL;
+-
+ if (!COMPARISON_CLASS_P (cond_expr))
+ return NULL;
+
+ type = gimple_expr_type (last_stmt);
+ comp_type = TREE_TYPE (TREE_OPERAND (cond_expr, 0));
+- if (!INTEGRAL_TYPE_P (comp_type)
+- || !INTEGRAL_TYPE_P (type))
+- return NULL;
+-
+ comp_vectype = get_vectype_for_scalar_type (comp_type);
+ if (comp_vectype == NULL_TREE)
+ return NULL;
+
++ if (types_compatible_p (type, comp_type)
++ || !INTEGRAL_TYPE_P (comp_type)
++ || !INTEGRAL_TYPE_P (type))
++ return NULL;
++
++ if ((TREE_CODE (then_clause) != INTEGER_CST
++ && !type_conversion_p (then_clause, last_stmt, false, &orig_type0,
++ &def_stmt0, &promotion))
++ || (TREE_CODE (else_clause) != INTEGER_CST
++ && !type_conversion_p (else_clause, last_stmt, false, &orig_type1,
++ &def_stmt1, &promotion)))
++ return NULL;
++
++ if (orig_type0 && orig_type1
++ && (!types_compatible_p (orig_type0, orig_type1)
++ || !types_compatible_p (orig_type0, comp_type)))
++ return NULL;
++
++ if (orig_type0)
++ then_clause = gimple_assign_rhs1 (def_stmt0);
++
++ if (orig_type1)
++ else_clause = gimple_assign_rhs1 (def_stmt1);
++
+ cmpmode = GET_MODE_INNER (TYPE_MODE (comp_vectype));
+-
+ if (GET_MODE_BITSIZE (TYPE_MODE (type)) == GET_MODE_BITSIZE (cmpmode))
+ return NULL;
+
+@@ -1561,18 +1601,15 @@
+ if (vectype == NULL_TREE)
+ return NULL;
+
+- if (types_compatible_p (vectype, comp_vectype))
+- return NULL;
+-
+ if (!expand_vec_cond_expr_p (comp_vectype, TYPE_MODE (comp_vectype)))
+ return NULL;
+
+- if (GET_MODE_BITSIZE (TYPE_MODE (type)) > GET_MODE_BITSIZE (cmpmode))
+- {
+- if (!int_fits_type_p (then_clause, comp_type)
+- || !int_fits_type_p (else_clause, comp_type))
+- return NULL;
+- }
++ if (GET_MODE_BITSIZE (TYPE_MODE (type)) > GET_MODE_BITSIZE (cmpmode)
++ && ((TREE_CODE (then_clause) == INTEGER_CST
++ && !int_fits_type_p (then_clause, comp_type))
++ || (TREE_CODE (else_clause) == INTEGER_CST
++ && !int_fits_type_p (else_clause, comp_type))))
++ return NULL;
+
+ tmp = build3 (COND_EXPR, comp_type, unshare_expr (cond_expr),
+ fold_convert (comp_type, then_clause),
+
--- /dev/null
+2011-12-05 Ramana Radhakrishnan <ramana.radhakrishnan@linaro.org>
+
+ Backport from mainline -A15 tuning.
+ 2011-11-30 Matthew Gretton-Dann <matthew.gretton-dann@arm.com>
+
+ * config/arm/arm.c (arm_issue_rate): Cortex-A15 can triple issue.
+ * config/arm/arm.md (mul64): New attribute.
+ (generic_sched): Cortex-A15 is not scheduled generically.
+ (cortex-a15.md): Include.
+ * config/arm/cortex-a15.md: New machine description.
+ * config/arm/t-arm (MD_INCLUDES): Add cortex-a15.md.
+
+ 2011-11-30 Matthew Gretton-Dann <matthew.gretton-dann@arm.com>
+ * config/arm/t-arm (MD_INCLUDES): Ensure all md files are listed.
+
+=== modified file 'gcc/config/arm/arm.c'
+--- old/gcc/config/arm/arm.c 2011-12-05 10:55:48 +0000
++++ new/gcc/config/arm/arm.c 2011-12-05 12:33:25 +0000
+@@ -24056,6 +24056,9 @@
+ {
+ switch (arm_tune)
+ {
++ case cortexa15:
++ return 3;
++
+ case cortexr4:
+ case cortexr4f:
+ case cortexr5:
+
+=== modified file 'gcc/config/arm/arm.md'
+--- old/gcc/config/arm/arm.md 2011-10-26 11:38:30 +0000
++++ new/gcc/config/arm/arm.md 2011-12-02 00:38:59 +0000
+@@ -345,6 +345,13 @@
+ (const_string "mult")
+ (const_string "alu")))
+
++; Is this an (integer side) multiply with a 64-bit result?
++(define_attr "mul64" "no,yes"
++ (if_then_else
++ (eq_attr "insn" "smlalxy,umull,umulls,umlal,umlals,smull,smulls,smlal,smlals")
++ (const_string "yes")
++ (const_string "no")))
++
+ ; Load scheduling, set from the arm_ld_sched variable
+ ; initialized by arm_option_override()
+ (define_attr "ldsched" "no,yes" (const (symbol_ref "arm_ld_sched")))
+@@ -511,7 +518,7 @@
+
+ (define_attr "generic_sched" "yes,no"
+ (const (if_then_else
+- (ior (eq_attr "tune" "fa526,fa626,fa606te,fa626te,fmp626,fa726te,arm926ejs,arm1020e,arm1026ejs,arm1136js,arm1136jfs,cortexa5,cortexa8,cortexa9,cortexm4")
++ (ior (eq_attr "tune" "fa526,fa626,fa606te,fa626te,fmp626,fa726te,arm926ejs,arm1020e,arm1026ejs,arm1136js,arm1136jfs,cortexa5,cortexa8,cortexa9,cortexa15,cortexm4")
+ (eq_attr "tune_cortexr4" "yes"))
+ (const_string "no")
+ (const_string "yes"))))
+@@ -537,6 +544,7 @@
+ (include "cortex-a5.md")
+ (include "cortex-a8.md")
+ (include "cortex-a9.md")
++(include "cortex-a15.md")
+ (include "cortex-r4.md")
+ (include "cortex-r4f.md")
+ (include "cortex-m4.md")
+
+=== added file 'gcc/config/arm/cortex-a15.md'
+--- old/gcc/config/arm/cortex-a15.md 1970-01-01 00:00:00 +0000
++++ new/gcc/config/arm/cortex-a15.md 2011-12-02 00:38:59 +0000
+@@ -0,0 +1,186 @@
++;; ARM Cortex-A15 pipeline description
++;; Copyright (C) 2011 Free Software Foundation, Inc.
++;;
++;; Written by Matthew Gretton-Dann <matthew.gretton-dann@arm.com>
++
++;; This file is part of GCC.
++;;
++;; GCC is free software; you can redistribute it and/or modify it
++;; under the terms of the GNU General Public License as published by
++;; the Free Software Foundation; either version 3, or (at your option)
++;; any later version.
++;;
++;; GCC is distributed in the hope that it will be useful, but
++;; WITHOUT ANY WARRANTY; without even the implied warranty of
++;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
++;; General Public License for more details.
++;;
++;; You should have received a copy of the GNU General Public License
++;; along with GCC; see the file COPYING3. If not see
++;; <http://www.gnu.org/licenses/>.
++
++(define_automaton "cortex_a15")
++
++;; The Cortex-A15 core is modelled as a triple issue pipeline that has
++;; the following dispatch units.
++;; 1. Two pipelines for simple integer operations: SX1, SX2
++;; 2. Two pipelines for Neon and FP data-processing operations: CX1, CX2
++;; 3. One pipeline for branch operations: BX
++;; 4. One pipeline for integer multiply and divide operations: MX
++;; 5. Two pipelines for load and store operations: LS1, LS2
++;;
++;; We can issue into three pipelines per-cycle.
++;;
++;; We assume that where we have unit pairs xx1 is always filled before xx2.
++
++;; The three issue units
++(define_cpu_unit "ca15_i0, ca15_i1, ca15_i2" "cortex_a15")
++
++(define_reservation "ca15_issue1" "(ca15_i0|ca15_i1|ca15_i2)")
++(define_reservation "ca15_issue2" "((ca15_i0+ca15_i1)|(ca15_i1+ca15_i2))")
++(define_reservation "ca15_issue3" "(ca15_i0+ca15_i1+ca15_i2)")
++(final_presence_set "ca15_i1" "ca15_i0")
++(final_presence_set "ca15_i2" "ca15_i1")
++
++;; The main dispatch units
++(define_cpu_unit "ca15_sx1, ca15_sx2" "cortex_a15")
++(define_cpu_unit "ca15_cx1, ca15_cx2" "cortex_a15")
++(define_cpu_unit "ca15_ls1, ca15_ls2" "cortex_a15")
++(define_cpu_unit "ca15_bx, ca15_mx" "cortex_a15")
++
++(define_reservation "ca15_ls" "(ca15_ls1|ca15_ls2)")
++
++;; The extended load-store pipeline
++(define_cpu_unit "ca15_ldr, ca15_str" "cortex_a15")
++
++;; The extended ALU pipeline
++(define_cpu_unit "ca15_sx1_alu, ca15_sx1_shf, ca15_sx1_sat" "cortex_a15")
++(define_cpu_unit "ca15_sx2_alu, ca15_sx2_shf, ca15_sx2_sat" "cortex_a15")
++
++;; Simple Execution Unit:
++;;
++;; Simple ALU without shift
++(define_insn_reservation "cortex_a15_alu" 2
++ (and (eq_attr "tune" "cortexa15")
++ (and (eq_attr "type" "alu")
++ (eq_attr "neon_type" "none")))
++ "ca15_issue1,(ca15_sx1,ca15_sx1_alu)|(ca15_sx2,ca15_sx2_alu)")
++
++;; ALU ops with immediate shift
++(define_insn_reservation "cortex_a15_alu_shift" 3
++ (and (eq_attr "tune" "cortexa15")
++ (and (eq_attr "type" "alu_shift")
++ (eq_attr "neon_type" "none")))
++ "ca15_issue1,(ca15_sx1,ca15_sx1+ca15_sx1_shf,ca15_sx1_alu)\
++ |(ca15_sx2,ca15_sx2+ca15_sx2_shf,ca15_sx2_alu)")
++
++;; ALU ops with register controlled shift
++(define_insn_reservation "cortex_a15_alu_shift_reg" 3
++ (and (eq_attr "tune" "cortexa15")
++ (and (eq_attr "type" "alu_shift_reg")
++ (eq_attr "neon_type" "none")))
++ "(ca15_issue2,ca15_sx1+ca15_sx2,ca15_sx1_shf,ca15_sx2_alu)\
++ |(ca15_issue1,(ca15_issue1+ca15_sx2,ca15_sx1+ca15_sx2_shf)\
++ |(ca15_issue1+ca15_sx1,ca15_sx1+ca15_sx1_shf),ca15_sx1_alu)")
++
++;; Multiply Execution Unit:
++;;
++;; 32-bit multiplies
++(define_insn_reservation "cortex_a15_mult32" 3
++ (and (eq_attr "tune" "cortexa15")
++ (and (eq_attr "type" "mult")
++ (and (eq_attr "neon_type" "none")
++ (eq_attr "mul64" "no"))))
++ "ca15_issue1,ca15_mx")
++
++;; 64-bit multiplies
++(define_insn_reservation "cortex_a15_mult64" 4
++ (and (eq_attr "tune" "cortexa15")
++ (and (eq_attr "type" "mult")
++ (and (eq_attr "neon_type" "none")
++ (eq_attr "mul64" "yes"))))
++ "ca15_issue1,ca15_mx*2")
++
++;; Integer divide
++(define_insn_reservation "cortex_a15_udiv" 9
++ (and (eq_attr "tune" "cortexa15")
++ (eq_attr "insn" "udiv"))
++ "ca15_issue1,ca15_mx")
++
++(define_insn_reservation "cortex_a15_sdiv" 10
++ (and (eq_attr "tune" "cortexa15")
++ (eq_attr "insn" "sdiv"))
++ "ca15_issue1,ca15_mx")
++
++;; Block all issue pipes for a cycle
++(define_insn_reservation "cortex_a15_block" 1
++ (and (eq_attr "tune" "cortexa15")
++ (and (eq_attr "type" "block")
++ (eq_attr "neon_type" "none")))
++ "ca15_issue3")
++
++;; Branch execution Unit
++;;
++;; Branches take one issue slot.
++;; No latency as there is no result
++(define_insn_reservation "cortex_a15_branch" 0
++ (and (eq_attr "tune" "cortexa15")
++ (and (eq_attr "type" "branch")
++ (eq_attr "neon_type" "none")))
++ "ca15_issue1,ca15_bx")
++
++
++;; We lie with calls. They take up all issue slots, and form a block in the
++;; pipeline. The result however is available the next cycle.
++;;
++;; Addition of new units requires this to be updated.
++(define_insn_reservation "cortex_a15_call" 1
++ (and (eq_attr "tune" "cortexa15")
++ (and (eq_attr "type" "call")
++ (eq_attr "neon_type" "none")))
++ "ca15_issue3,\
++ ca15_sx1+ca15_sx2+ca15_bx+ca15_mx+ca15_cx1+ca15_cx2+ca15_ls1+ca15_ls2,\
++ ca15_sx1_alu+ca15_sx1_shf+ca15_sx1_sat+ca15_sx2_alu+ca15_sx2_shf\
++ +ca15_sx2_sat+ca15_ldr+ca15_str")
++
++;; Load-store execution Unit
++;;
++;; Loads of up to two words.
++(define_insn_reservation "cortex_a15_load1" 4
++ (and (eq_attr "tune" "cortexa15")
++ (and (eq_attr "type" "load_byte,load1,load2")
++ (eq_attr "neon_type" "none")))
++ "ca15_issue1,ca15_ls,ca15_ldr,nothing")
++
++;; Loads of three or four words.
++(define_insn_reservation "cortex_a15_load3" 5
++ (and (eq_attr "tune" "cortexa15")
++ (and (eq_attr "type" "load3,load4")
++ (eq_attr "neon_type" "none")))
++ "ca15_issue2,ca15_ls1+ca15_ls2,ca15_ldr,ca15_ldr,nothing")
++
++;; Stores of up to two words.
++(define_insn_reservation "cortex_a15_store1" 0
++ (and (eq_attr "tune" "cortexa15")
++ (and (eq_attr "type" "store1,store2")
++ (eq_attr "neon_type" "none")))
++ "ca15_issue1,ca15_ls,ca15_str")
++
++;; Stores of three or four words.
++(define_insn_reservation "cortex_a15_store3" 0
++ (and (eq_attr "tune" "cortexa15")
++ (and (eq_attr "type" "store3,store4")
++ (eq_attr "neon_type" "none")))
++ "ca15_issue2,ca15_ls1+ca15_ls2,ca15_str,ca15_str")
++
++;; Simple execution unit bypasses
++(define_bypass 1 "cortex_a15_alu"
++ "cortex_a15_alu,cortex_a15_alu_shift,cortex_a15_alu_shift_reg")
++(define_bypass 2 "cortex_a15_alu_shift"
++ "cortex_a15_alu,cortex_a15_alu_shift,cortex_a15_alu_shift_reg")
++(define_bypass 2 "cortex_a15_alu_shift_reg"
++ "cortex_a15_alu,cortex_a15_alu_shift,cortex_a15_alu_shift_reg")
++(define_bypass 1 "cortex_a15_alu" "cortex_a15_load1,cortex_a15_load3")
++(define_bypass 2 "cortex_a15_alu_shift" "cortex_a15_load1,cortex_a15_load3")
++(define_bypass 2 "cortex_a15_alu_shift_reg"
++ "cortex_a15_load1,cortex_a15_load3")
+
+=== modified file 'gcc/config/arm/t-arm'
+--- old/gcc/config/arm/t-arm 2011-01-03 20:52:22 +0000
++++ new/gcc/config/arm/t-arm 2011-12-02 00:38:59 +0000
+@@ -31,6 +31,16 @@
+ $(srcdir)/config/arm/fmp626.md \
+ $(srcdir)/config/arm/fa726te.md \
+ $(srcdir)/config/arm/arm926ejs.md \
++ $(srcdir)/config/arm/cortex-a15.md \
++ $(srcdir)/config/arm/cortex-a5.md \
++ $(srcdir)/config/arm/cortex-a8.md \
++ $(srcdir)/config/arm/cortex-a8-neon.md \
++ $(srcdir)/config/arm/cortex-a9.md \
++ $(srcdir)/config/arm/cortex-a9-neon.md \
++ $(srcdir)/config/arm/cortex-m4-fpu.md \
++ $(srcdir)/config/arm/cortex-m4.md \
++ $(srcdir)/config/arm/cortex-r4f.md \
++ $(srcdir)/config/arm/cortex-r4.md \
+ $(srcdir)/config/arm/cirrus.md \
+ $(srcdir)/config/arm/fpa.md \
+ $(srcdir)/config/arm/vec-common.md \
+
--- /dev/null
+2011-12-20 Ira Rosen <ira.rosen@linaro.org>
+
+ Backport from mainline:
+
+ 2011-11-29 Ira Rosen <ira.rosen@linaro.org>
+
+ PR tree-optimization/51301
+ gcc/
+ * tree-vect-patterns.c (vect_recog_over_widening_pattern): Check that
+ the last statement doesn't convert to a bigger type than the original
+ type of the computation.
+
+ gcc/testsuite/
+ * gcc.dg/vect/pr51301.c: New test.
+
+=== added file 'gcc/testsuite/gcc.dg/vect/pr51301.c'
+--- old/gcc/testsuite/gcc.dg/vect/pr51301.c 1970-01-01 00:00:00 +0000
++++ new/gcc/testsuite/gcc.dg/vect/pr51301.c 2011-11-30 17:54:51 +0000
+@@ -0,0 +1,15 @@
++/* { dg-do compile } */
++
++typedef signed char int8_t;
++typedef signed long long int64_t;
++int64_t
++f0a (int8_t * __restrict__ arg1)
++{
++ int idx;
++ int64_t result = 0;
++ for (idx = 0; idx < 416; idx += 1)
++ result += arg1[idx] << (arg1[idx] == arg1[idx]);
++ return result;
++}
++
++/* { dg-final { cleanup-tree-dump "vect" } } */
+
+=== modified file 'gcc/tree-vect-patterns.c'
+--- old/gcc/tree-vect-patterns.c 2011-11-27 12:17:31 +0000
++++ new/gcc/tree-vect-patterns.c 2011-12-20 07:47:44 +0000
+@@ -1138,6 +1138,7 @@
+ struct loop *loop = NULL;
+ bb_vec_info bb_vinfo;
+ stmt_vec_info stmt_vinfo;
++ tree type = NULL;
+
+ stmt_vinfo = vinfo_for_stmt (stmt);
+ loop_vinfo = STMT_VINFO_LOOP_VINFO (stmt_vinfo);
+@@ -1207,6 +1208,7 @@
+ print_gimple_stmt (vect_dump, pattern_stmt, 0, TDF_SLIM);
+ }
+
++ type = gimple_expr_type (stmt);
+ prev_stmt = stmt;
+ stmt = use_stmt;
+
+@@ -1222,9 +1224,11 @@
+ {
+ use_lhs = gimple_assign_lhs (use_stmt);
+ use_type = TREE_TYPE (use_lhs);
+- /* Support only type promotion or signedess change. */
++ /* Support only type promotion or signedess change. Check that USE_TYPE
++ is not bigger than the original type. */
+ if (!INTEGRAL_TYPE_P (use_type)
+- || TYPE_PRECISION (new_type) > TYPE_PRECISION (use_type))
++ || TYPE_PRECISION (new_type) > TYPE_PRECISION (use_type)
++ || TYPE_PRECISION (type) < TYPE_PRECISION (use_type))
+ return NULL;
+
+ if (TYPE_UNSIGNED (new_type) != TYPE_UNSIGNED (use_type)
+
--- /dev/null
+2011-12-30 Richard Sandiford <richard.sandiford@linaro.org>
+
+ gcc/
+ Backport from mainline:
+
+ 2011-10-12 Richard Sandiford <richard.sandiford@linaro.org>
+
+ * expr.h (copy_blkmode_to_reg): Declare.
+ * expr.c (copy_blkmode_to_reg): New function.
+ (expand_assignment): Don't expand register RESULT_DECLs before
+ the lhs. Use copy_blkmode_to_reg to copy BLKmode values into a
+ RESULT_DECL register.
+ (expand_expr_real_1): Handle BLKmode decls when looking for promotion.
+ * stmt.c (expand_return): Move BLKmode-to-register code into
+ copy_blkmode_to_reg.
+
+=== modified file 'gcc/expr.c'
+--- old/gcc/expr.c 2011-10-23 13:33:07 +0000
++++ new/gcc/expr.c 2011-12-30 09:41:30 +0000
+@@ -2180,6 +2180,111 @@
+ return tgtblk;
+ }
+
++/* Copy BLKmode value SRC into a register of mode MODE. Return the
++ register if it contains any data, otherwise return null.
++
++ This is used on targets that return BLKmode values in registers. */
++
++rtx
++copy_blkmode_to_reg (enum machine_mode mode, tree src)
++{
++ int i, n_regs;
++ unsigned HOST_WIDE_INT bitpos, xbitpos, padding_correction = 0, bytes;
++ unsigned int bitsize;
++ rtx *dst_words, dst, x, src_word = NULL_RTX, dst_word = NULL_RTX;
++ enum machine_mode dst_mode;
++
++ gcc_assert (TYPE_MODE (TREE_TYPE (src)) == BLKmode);
++
++ x = expand_normal (src);
++
++ bytes = int_size_in_bytes (TREE_TYPE (src));
++ if (bytes == 0)
++ return NULL_RTX;
++
++ /* If the structure doesn't take up a whole number of words, see
++ whether the register value should be padded on the left or on
++ the right. Set PADDING_CORRECTION to the number of padding
++ bits needed on the left side.
++
++ In most ABIs, the structure will be returned at the least end of
++ the register, which translates to right padding on little-endian
++ targets and left padding on big-endian targets. The opposite
++ holds if the structure is returned at the most significant
++ end of the register. */
++ if (bytes % UNITS_PER_WORD != 0
++ && (targetm.calls.return_in_msb (TREE_TYPE (src))
++ ? !BYTES_BIG_ENDIAN
++ : BYTES_BIG_ENDIAN))
++ padding_correction = (BITS_PER_WORD - ((bytes % UNITS_PER_WORD)
++ * BITS_PER_UNIT));
++
++ n_regs = (bytes + UNITS_PER_WORD - 1) / UNITS_PER_WORD;
++ dst_words = XALLOCAVEC (rtx, n_regs);
++ bitsize = MIN (TYPE_ALIGN (TREE_TYPE (src)), BITS_PER_WORD);
++
++ /* Copy the structure BITSIZE bits at a time. */
++ for (bitpos = 0, xbitpos = padding_correction;
++ bitpos < bytes * BITS_PER_UNIT;
++ bitpos += bitsize, xbitpos += bitsize)
++ {
++ /* We need a new destination pseudo each time xbitpos is
++ on a word boundary and when xbitpos == padding_correction
++ (the first time through). */
++ if (xbitpos % BITS_PER_WORD == 0
++ || xbitpos == padding_correction)
++ {
++ /* Generate an appropriate register. */
++ dst_word = gen_reg_rtx (word_mode);
++ dst_words[xbitpos / BITS_PER_WORD] = dst_word;
++
++ /* Clear the destination before we move anything into it. */
++ emit_move_insn (dst_word, CONST0_RTX (word_mode));
++ }
++
++ /* We need a new source operand each time bitpos is on a word
++ boundary. */
++ if (bitpos % BITS_PER_WORD == 0)
++ src_word = operand_subword_force (x, bitpos / BITS_PER_WORD, BLKmode);
++
++ /* Use bitpos for the source extraction (left justified) and
++ xbitpos for the destination store (right justified). */
++ store_bit_field (dst_word, bitsize, xbitpos % BITS_PER_WORD, word_mode,
++ extract_bit_field (src_word, bitsize,
++ bitpos % BITS_PER_WORD, 1, false,
++ NULL_RTX, word_mode, word_mode));
++ }
++
++ if (mode == BLKmode)
++ {
++ /* Find the smallest integer mode large enough to hold the
++ entire structure. */
++ for (mode = GET_CLASS_NARROWEST_MODE (MODE_INT);
++ mode != VOIDmode;
++ mode = GET_MODE_WIDER_MODE (mode))
++ /* Have we found a large enough mode? */
++ if (GET_MODE_SIZE (mode) >= bytes)
++ break;
++
++ /* A suitable mode should have been found. */
++ gcc_assert (mode != VOIDmode);
++ }
++
++ if (GET_MODE_SIZE (mode) < GET_MODE_SIZE (word_mode))
++ dst_mode = word_mode;
++ else
++ dst_mode = mode;
++ dst = gen_reg_rtx (dst_mode);
++
++ for (i = 0; i < n_regs; i++)
++ emit_move_insn (operand_subword (dst, i, 0, dst_mode), dst_words[i]);
++
++ if (mode != dst_mode)
++ dst = gen_lowpart (mode, dst);
++
++ return dst;
++}
++
+ /* Add a USE expression for REG to the (possibly empty) list pointed
+ to by CALL_FUSAGE. REG must denote a hard register. */
+
+@@ -4382,7 +4487,9 @@
+ if (TREE_CODE (from) == CALL_EXPR && ! aggregate_value_p (from, from)
+ && COMPLETE_TYPE_P (TREE_TYPE (from))
+ && TREE_CODE (TYPE_SIZE (TREE_TYPE (from))) == INTEGER_CST
+- && ! (((TREE_CODE (to) == VAR_DECL || TREE_CODE (to) == PARM_DECL)
++ && ! (((TREE_CODE (to) == VAR_DECL
++ || TREE_CODE (to) == PARM_DECL
++ || TREE_CODE (to) == RESULT_DECL)
+ && REG_P (DECL_RTL (to)))
+ || TREE_CODE (to) == SSA_NAME))
+ {
+@@ -4428,12 +4535,15 @@
+ rtx temp;
+
+ push_temp_slots ();
+- temp = expand_expr (from, NULL_RTX, GET_MODE (to_rtx), EXPAND_NORMAL);
++ if (REG_P (to_rtx) && TYPE_MODE (TREE_TYPE (from)) == BLKmode)
++ temp = copy_blkmode_to_reg (GET_MODE (to_rtx), from);
++ else
++ temp = expand_expr (from, NULL_RTX, GET_MODE (to_rtx), EXPAND_NORMAL);
+
+ if (GET_CODE (to_rtx) == PARALLEL)
+ emit_group_load (to_rtx, temp, TREE_TYPE (from),
+ int_size_in_bytes (TREE_TYPE (from)));
+- else
++ else if (temp)
+ emit_move_insn (to_rtx, temp);
+
+ preserve_temp_slots (to_rtx);
+@@ -8567,10 +8677,15 @@
+ return temp;
+ }
+
+- /* If the mode of DECL_RTL does not match that of the decl, it
+- must be a promoted value. We return a SUBREG of the wanted mode,
+- but mark it so that we know that it was already extended. */
+- if (REG_P (decl_rtl) && GET_MODE (decl_rtl) != DECL_MODE (exp))
++ /* If the mode of DECL_RTL does not match that of the decl,
++ there are two cases: we are dealing with a BLKmode value
++ that is returned in a register, or we are dealing with
++ a promoted value. In the latter case, return a SUBREG
++ of the wanted mode, but mark it so that we know that it
++ was already extended. */
++ if (REG_P (decl_rtl)
++ && DECL_MODE (exp) != BLKmode
++ && GET_MODE (decl_rtl) != DECL_MODE (exp))
+ {
+ enum machine_mode pmode;
+
+
+=== modified file 'gcc/expr.h'
+--- old/gcc/expr.h 2011-03-03 21:56:58 +0000
++++ new/gcc/expr.h 2011-10-12 08:01:43 +0000
+@@ -324,6 +324,8 @@
+ /* Copy BLKmode object from a set of registers. */
+ extern rtx copy_blkmode_from_reg (rtx, rtx, tree);
+
++extern rtx copy_blkmode_to_reg (enum machine_mode, tree);
++
+ /* Mark REG as holding a parameter for the next CALL_INSN. */
+ extern void use_reg (rtx *, rtx);
+
+
+=== modified file 'gcc/stmt.c'
+--- old/gcc/stmt.c 2011-03-03 21:56:58 +0000
++++ new/gcc/stmt.c 2011-10-12 08:01:43 +0000
+@@ -1684,119 +1684,21 @@
+ expand_value_return (result_rtl);
+
+ /* If the result is an aggregate that is being returned in one (or more)
+- registers, load the registers here. The compiler currently can't handle
+- copying a BLKmode value into registers. We could put this code in a
+- more general area (for use by everyone instead of just function
+- call/return), but until this feature is generally usable it is kept here
+- (and in expand_call). */
++ registers, load the registers here. */
+
+ else if (retval_rhs != 0
+ && TYPE_MODE (TREE_TYPE (retval_rhs)) == BLKmode
+ && REG_P (result_rtl))
+ {
+- int i;
+- unsigned HOST_WIDE_INT bitpos, xbitpos;
+- unsigned HOST_WIDE_INT padding_correction = 0;
+- unsigned HOST_WIDE_INT bytes
+- = int_size_in_bytes (TREE_TYPE (retval_rhs));
+- int n_regs = (bytes + UNITS_PER_WORD - 1) / UNITS_PER_WORD;
+- unsigned int bitsize
+- = MIN (TYPE_ALIGN (TREE_TYPE (retval_rhs)), BITS_PER_WORD);
+- rtx *result_pseudos = XALLOCAVEC (rtx, n_regs);
+- rtx result_reg, src = NULL_RTX, dst = NULL_RTX;
+- rtx result_val = expand_normal (retval_rhs);
+- enum machine_mode tmpmode, result_reg_mode;
+-
+- if (bytes == 0)
+- {
+- expand_null_return ();
+- return;
+- }
+-
+- /* If the structure doesn't take up a whole number of words, see
+- whether the register value should be padded on the left or on
+- the right. Set PADDING_CORRECTION to the number of padding
+- bits needed on the left side.
+-
+- In most ABIs, the structure will be returned at the least end of
+- the register, which translates to right padding on little-endian
+- targets and left padding on big-endian targets. The opposite
+- holds if the structure is returned at the most significant
+- end of the register. */
+- if (bytes % UNITS_PER_WORD != 0
+- && (targetm.calls.return_in_msb (TREE_TYPE (retval_rhs))
+- ? !BYTES_BIG_ENDIAN
+- : BYTES_BIG_ENDIAN))
+- padding_correction = (BITS_PER_WORD - ((bytes % UNITS_PER_WORD)
+- * BITS_PER_UNIT));
+-
+- /* Copy the structure BITSIZE bits at a time. */
+- for (bitpos = 0, xbitpos = padding_correction;
+- bitpos < bytes * BITS_PER_UNIT;
+- bitpos += bitsize, xbitpos += bitsize)
+- {
+- /* We need a new destination pseudo each time xbitpos is
+- on a word boundary and when xbitpos == padding_correction
+- (the first time through). */
+- if (xbitpos % BITS_PER_WORD == 0
+- || xbitpos == padding_correction)
+- {
+- /* Generate an appropriate register. */
+- dst = gen_reg_rtx (word_mode);
+- result_pseudos[xbitpos / BITS_PER_WORD] = dst;
+-
+- /* Clear the destination before we move anything into it. */
+- emit_move_insn (dst, CONST0_RTX (GET_MODE (dst)));
+- }
+-
+- /* We need a new source operand each time bitpos is on a word
+- boundary. */
+- if (bitpos % BITS_PER_WORD == 0)
+- src = operand_subword_force (result_val,
+- bitpos / BITS_PER_WORD,
+- BLKmode);
+-
+- /* Use bitpos for the source extraction (left justified) and
+- xbitpos for the destination store (right justified). */
+- store_bit_field (dst, bitsize, xbitpos % BITS_PER_WORD, word_mode,
+- extract_bit_field (src, bitsize,
+- bitpos % BITS_PER_WORD, 1, false,
+- NULL_RTX, word_mode, word_mode));
+- }
+-
+- tmpmode = GET_MODE (result_rtl);
+- if (tmpmode == BLKmode)
+- {
+- /* Find the smallest integer mode large enough to hold the
+- entire structure and use that mode instead of BLKmode
+- on the USE insn for the return register. */
+- for (tmpmode = GET_CLASS_NARROWEST_MODE (MODE_INT);
+- tmpmode != VOIDmode;
+- tmpmode = GET_MODE_WIDER_MODE (tmpmode))
+- /* Have we found a large enough mode? */
+- if (GET_MODE_SIZE (tmpmode) >= bytes)
+- break;
+-
+- /* A suitable mode should have been found. */
+- gcc_assert (tmpmode != VOIDmode);
+-
+- PUT_MODE (result_rtl, tmpmode);
+- }
+-
+- if (GET_MODE_SIZE (tmpmode) < GET_MODE_SIZE (word_mode))
+- result_reg_mode = word_mode;
++ val = copy_blkmode_to_reg (GET_MODE (result_rtl), retval_rhs);
++ if (val)
++ {
++ /* Use the mode of the result value on the return register. */
++ PUT_MODE (result_rtl, GET_MODE (val));
++ expand_value_return (val);
++ }
+ else
+- result_reg_mode = tmpmode;
+- result_reg = gen_reg_rtx (result_reg_mode);
+-
+- for (i = 0; i < n_regs; i++)
+- emit_move_insn (operand_subword (result_reg, i, 0, result_reg_mode),
+- result_pseudos[i]);
+-
+- if (tmpmode != result_reg_mode)
+- result_reg = gen_lowpart (tmpmode, result_reg);
+-
+- expand_value_return (result_reg);
++ expand_null_return ();
+ }
+ else if (retval_rhs != 0
+ && !VOID_TYPE_P (TREE_TYPE (retval_rhs))
+
+=== added file 'gcc/testsuite/g++.dg/pr48660.C'
+--- old/gcc/testsuite/g++.dg/pr48660.C 1970-01-01 00:00:00 +0000
++++ new/gcc/testsuite/g++.dg/pr48660.C 2011-10-12 08:01:43 +0000
+@@ -0,0 +1,22 @@
++template<int N> struct val { char a[N]; };
++
++class Base
++{
++public:
++ virtual val<1> get1() const = 0;
++ virtual val<2> get2() const = 0;
++ virtual val<3> get3() const = 0;
++ virtual val<4> get4() const = 0;
++};
++
++class Derived : public virtual Base
++{
++public:
++ virtual val<1> get1() const { return foo->get1(); }
++ virtual val<2> get2() const { return foo->get2(); }
++ virtual val<3> get3() const { return foo->get3(); }
++ virtual val<4> get4() const { return foo->get4(); }
++ Base *foo;
++};
++
++Base* make() { return new Derived; }
+
--- /dev/null
+2012-01-05 Michael Hope <michael.hope@linaro.org>
+
+ Backport from mainline r182271:
+
+ 2011-12-13 Revital Eres <revital.eres@linaro.org>
+
+ gcc/
+ * modulo-sched.c (mark_loop_unsched): Free bbs.
+
+=== modified file 'gcc/modulo-sched.c'
+--- old/gcc/modulo-sched.c 2011-10-30 05:31:00 +0000
++++ new/gcc/modulo-sched.c 2012-01-05 02:45:23 +0000
+@@ -1204,6 +1204,8 @@
+
+ for (i = 0; i < loop->num_nodes; i++)
+ bbs[i]->flags |= BB_DISABLE_SCHEDULE;
++
++ free (bbs);
+ }
+
+ /* Return true if all the BBs of the loop are empty except the
+
file://linaro/gcc-4.6-linaro-r106839.patch \
file://linaro/gcc-4.6-linaro-r106840.patch \
file://linaro/gcc-4.6-linaro-r106841.patch \
+file://linaro/gcc-4.6-linaro-r106842.patch \
+file://linaro/gcc-4.6-linaro-r106843.patch \
+file://linaro/gcc-4.6-linaro-r106844.patch \
+file://linaro/gcc-4.6-linaro-r106845.patch \
+file://linaro/gcc-4.6-linaro-r106846.patch \
+file://linaro/gcc-4.6-linaro-r106848.patch \
+file://linaro/gcc-4.6-linaro-r106853.patch \
+file://linaro/gcc-4.6-linaro-r106854.patch \
+file://linaro/gcc-4.6-linaro-r106855.patch \
"
# this will prepend this layer to FILESPATH
FILESEXTRAPATHS := "${THISDIR}/gcc-4.6"
-PRINC = "4"
+PRINC = "5"
ARM_INSTRUCTION_SET = "arm"
projects / scm / bb / tizen-distro.git / commitdiff