Not all qualifiers are asm qualifiers.  We can talk about that in a
nicer way than just giving a generic parser error.

This also adds two testcases for C++, that previously were for C only.


c/
	* c-parser.c (c_parser_asm_statement) <RID_CONST, RID_RESTRICT>: Give
	a more specific error message (instead of just falling through).

cp/
	* parser.c (cp_parser_asm_definition) <RID_CONST, RID_RESTRICT>: Give
	a more specific error message (instead of just falling through).

testsuite/
	* g++.dg/asm-qual-1.C: New testcase.
	* g++.dg/asm-qual-2.C: New testcase.
	* gcc.dg/asm-qual-1.c: Update.

From-SVN: r267279

Also as suggested by Jason.


c/
	* c-parser.c (c_parser_asm_statement): Keep track of the location each
	asm qualifier is first seen; use that to give nicer "duplicate asm
	qualifier" messages.  Delete 'quals" variable, instead pass the
	"is_volatile_ flag to build_asm_stmt directly.
	* c-tree.h (build_asm_stmt): Make the first arg bool instead of tree.
	* c-typeck.c (build_asm_stmt): Ditto; adjust.

cp/
	* parser.c (cp_parser_asm_definition): Rewrite the loop to work without
	"done" boolean variable.
	* parser.c (cp_parser_asm_definition): Keep track of the location each
	asm qualifier is first seen; use that to give nicer "duplicate asm
	qualifier" messages.

From-SVN: r267278

As suggested by Jason.


c/
	* c-parser.c (c_parser_asm_statement): Rewrite the loop to work without
	"done" boolean variable.

cp/
	* parser.c (cp_parser_asm_definition): Rewrite the loop to work without
	"done" boolean variable.

From-SVN: r267277

PR c++/88375 reports that errors relating to invalid conversions in
initializations are reported at unhelpfully vague locations, as in
e.g.:

enum struct a : int {
  one, two
};

struct foo {
  int e1, e2;
  a e3;
} arr[] = {
  { 1, 2, a::one },
  { 3, a::two },
  { 4, 5, a::two }
};

for which g++ trunk emits the vague:

pr88375.cc:12:1: error: cannot convert 'a' to 'int' in initialization
   12 | };
      | ^

with the error at the final closing brace.

This patch uses location information for the initializers, converting the
above to:

pr88375.cc:10:11: error: cannot convert 'a' to 'int' in initialization
   10 |   { 3, a::two },
      |        ~~~^~~
      |           |
      |           a

highlighting which subexpression is problematic, and its type.

Ideally we'd also issue a note showing the field decl being initialized,
but that turned out to be more invasive.

gcc/cp/ChangeLog:
	PR c++/88375
	* typeck.c (convert_for_assignment): Capture location of rhs
	before stripping, and if available.  Use the location when
	complaining about bad conversions, labelling it with the
	rhstype if the location was present.
	* typeck2.c (digest_init_r): Capture location of init before
	stripping.

gcc/testsuite/ChangeLog:
	PR c++/88375
	* g++.dg/init/pr88375-2.C: New test.
	* g++.dg/init/pr88375.C: New test.

From-SVN: r267276

Expose oacc_fn_attrib_level to be used in backends.

2018-12-19  Tom de Vries  <tdevries@suse.de>

	* omp-offload.c (oacc_fn_attrib_level): Remove static.
	* omp-offload.h (oacc_fn_attrib_level): Declare.

From-SVN: r267275

Expose oacc_default_dims to backends.

2018-12-19  Tom de Vries  <tdevries@suse.de>

	* omp-offload.c (oacc_get_default_dim): New function.
	* omp-offload.h (oacc_get_default_dim): Declare.

From-SVN: r267274

The C frontend is able (where expression locations are available) to print
problems with binary operators in 3-location form, labelling the types of
the expressions:

  arg_0 op arg_1
  ~~~~~ ^~ ~~~~~
    |        |
    |        arg1 type
    arg0 type

The C++ frontend currently just shows the combined location:

  arg_0 op arg_1
  ~~~~~~^~~~~~~~

and fails to highlight where the subexpressions are, or their types.

This patch introduces a op_location_t struct for handling the above
operator-location vs combined-location split, and a new
class binary_op_rich_location for displaying the above, so that the
C++ frontend is able to use the more detailed 3-location form for
type mismatches in binary operators, and for -Wtautological-compare
(where types are not displayed).  Both forms can be seen in this
example:

bad-binary-ops.C:69:20: error: no match for 'operator&&' (operand types are
  's' and 't')
   69 |   return ns_4::foo && ns_4::inner::bar;
      |          ~~~~~~~~~ ^~ ~~~~~~~~~~~~~~~~
      |                |                   |
      |                s                   t
bad-binary-ops.C:69:20: note: candidate: 'operator&&(bool, bool)' <built-in>
   69 |   return ns_4::foo && ns_4::inner::bar;
      |          ~~~~~~~~~~^~~~~~~~~~~~~~~~~~~

The patch also allows for some uses of macros in
-Wtautological-compare, where both sides of the comparison have
been spelled the same way, e.g.:

Wtautological-compare-ranges.c:23:11: warning: self-comparison always
   evaluates to true [-Wtautological-compare]
   23 |   if (FOO == FOO);
      |           ^~

gcc/c-family/ChangeLog:
	PR c++/87504
	* c-common.h (warn_tautological_cmp): Convert 1st param from
	location_t to const op_location_t &.
	* c-warn.c (find_array_ref_with_const_idx_r): Call fold_for_warn
	when testing for INTEGER_CST.
	(warn_tautological_bitwise_comparison): Convert 1st param from
	location_t to const op_location_t &; use it to build a
	binary_op_rich_location, and use this.
	(spelled_the_same_p): New function.
	(warn_tautological_cmp): Convert 1st param from location_t to
	const op_location_t &.  Warn for macro expansions if
	spelled_the_same_p.  Use binary_op_rich_location.

gcc/c/ChangeLog:
	PR c++/87504
	* c-typeck.c (class maybe_range_label_for_tree_type_mismatch):
	Move from here to gcc-rich-location.h and gcc-rich-location.c.
	(build_binary_op): Use struct op_location_t and
	class binary_op_rich_location.

gcc/cp/ChangeLog:
	PR c++/87504
	* call.c (op_error): Convert 1st param from location_t to
	const op_location_t &.  Use binary_op_rich_location for binary
	ops.
	(build_conditional_expr_1): Convert 1st param from location_t to
	const op_location_t &.
	(build_conditional_expr): Likewise.
	(build_new_op_1): Likewise.
	(build_new_op): Likewise.
	* cp-tree.h (build_conditional_expr): Likewise.
	(build_new_op): Likewise.
	(build_x_binary_op): Likewise.
	(cp_build_binary_op): Likewise.
	* parser.c (cp_parser_primary_expression): Build a location
	for id-expression nodes.
	(cp_parser_binary_expression): Use an op_location_t when
	calling build_x_binary_op.
	(cp_parser_operator): Build a location for user-defined literals.
	* typeck.c (build_x_binary_op): Convert 1st param from location_t
	to const op_location_t &.
	(cp_build_binary_op): Likewise.  Use binary_op_rich_location.

gcc/ChangeLog:
	PR c++/87504
	* gcc-rich-location.c
	(maybe_range_label_for_tree_type_mismatch::get_text): Move here from
	c/c-typeck.c.
	(binary_op_rich_location::binary_op_rich_location): New ctor.
	(binary_op_rich_location::use_operator_loc_p): New function.
	* gcc-rich-location.h
	(class maybe_range_label_for_tree_type_mismatch)): Move here from
	c/c-typeck.c.
	(struct op_location_t): New forward decl.
	(class binary_op_rich_location): New class.
	* tree.h (struct op_location_t): New struct.

gcc/testsuite/ChangeLog:
	* c-c++-common/Wtautological-compare-ranges.c: New test.
	* g++.dg/cpp0x/pr51420.C: Add -fdiagnostics-show-caret and update
	expected output.
	* g++.dg/diagnostic/bad-binary-ops.C: Update expected output from
	1-location form to 3-location form, with labelling of ranges with
	types.  Add examples of id-expression nodes with namespaces.
	* g++.dg/diagnostic/param-type-mismatch-2.C: Likewise.

From-SVN: r267273

This is v6 of the patch, as posted to:
  https://gcc.gnu.org/ml/gcc-patches/2018-12/msg01331.html


The C++ frontend gained various location wrapper nodes in r256448 (GCC 8).
That patch:
  https://gcc.gnu.org/ml/gcc-patches/2018-01/msg00799.html
added wrapper nodes around all nodes with !CAN_HAVE_LOCATION_P for:

* arguments at callsites, and for

* typeid, alignof, sizeof, and offsetof.

This is a followup to that patch, adding many more location wrappers
to the C++ frontend.  It adds location wrappers for nodes with
!CAN_HAVE_LOCATION_P to:

* all literal nodes (in cp_parser_primary_expression)

* all id-expression nodes (in finish_id_expression), except within a
  decltype.

* all mem-initializer nodes within a mem-initializer-list
  (in cp_parser_mem_initializer)

However, the patch also adds some suppressions: regions in the parser
for which wrapper nodes will not be created:

* within a template-parameter-list or template-argument-list (in
  cp_parser_template_parameter_list and cp_parser_template_argument_list
  respectively), to avoid encoding the spelling location of the nodes
  in types.  For example, "array<10>" and "array<10>" are the same type,
  despite the fact that the two different "10" tokens are spelled in
  different locations in the source.

* within a gnu-style attribute (none of are handlers are set up to cope
  with location wrappers yet)

* within various OpenMP clauses

The patch enables various improvements to locations for bad
initializations, for -Wchar-subscripts, and enables various other
improvements in the followup patch.

For example, given the followup buggy mem-initializer:

class X {
  X() : bad(42),
        good(42)
  { }
  void* bad;
  int good;
};

previously, our diagnostic was on the final close parenthesis of the
mem-initializer-list, leaving it unclear where the problem is:

t.cc: In constructor 'X::X()':
t.cc:3:16: error: invalid conversion from 'int' to 'void*' [-fpermissive]
    3 |         good(42)
      |                ^
      |                |
      |                int

whereas with the patch we highlight which expression is bogus:

t.cc: In constructor 'X::X()':
t.cc:2:13: error: invalid conversion from 'int' to 'void*' [-fpermissive]
    2 |   X() : bad(42),
      |             ^~
      |             |
      |             int

Similarly, the diagnostic for this bogus initialization:

i.cc:1:44: error: initializer-string for array of chars is too long [-fpermissive]
    1 | char test[3][4] = { "ok", "too long", "ok" };
      |                                            ^

is improved by the patch so that it indicates which string is too long:

i.cc:1:27: error: initializer-string for array of chars is too long [-fpermissive]
    1 | char test[3][4] = { "ok", "too long", "ok" };
      |                           ^~~~~~~~~~


gcc/c-family/ChangeLog:
	PR c++/43064
	PR c++/43486
	* c-common.c (unsafe_conversion_p): Fold any location wrapper.
	(verify_tree): Handle location wrappers.
	(c_common_truthvalue_conversion): Strip any location wrapper.
	Handle CONST_DECL.
	(fold_offsetof): Strip any location wrapper.
	(complete_array_type): Likewise for initial_value.
	(convert_vector_to_array_for_subscript): Call fold_for_warn on the
	index before checking for INTEGER_CST.
	* c-pretty-print.c (c_pretty_printer::primary_expression): Don't
	print parentheses around location wrappers.
	* c-warn.c (warn_logical_operator): Call fold_for_warn on op_right
	before checking for INTEGER_CST.
	(warn_tautological_bitwise_comparison): Call
	tree_strip_any_location_wrapper on lhs, rhs, and bitop's operand
	before checking for INTEGER_CST.
	(readonly_error): Strip any location wrapper.
	(warn_array_subscript_with_type_char): Strip location wrappers
	before checking for INTEGER_CST.  Use the location of the index if
	available.

gcc/ChangeLog:
	PR c++/43064
	PR c++/43486
	* convert.c: Include "selftest.h".
	(preserve_any_location_wrapper): New function.
	(convert_to_pointer_maybe_fold): Update to handle location
	wrappers.
	(convert_to_real_maybe_fold): Likewise.
	(convert_to_integer_1): Strip expr when using TREE_OVERFLOW.
	Handle location wrappers when checking for INTEGER_CST.
	(convert_to_integer_maybe_fold): Update to handle location
	wrappers.
	(convert_to_complex_maybe_fold): Likewise.
	(selftest::test_convert_to_integer_maybe_fold): New functions.
	(selftest::convert_c_tests): New function.
	* convert.h (preserve_any_location_wrapper): New decl.
	* fold-const.c (size_binop_loc): Strip location wrappers when
	using TREE_OVERFLOW.
	(operand_equal_p): Strip any location wrappers.
	(integer_valued_real_p): Strip any location wrapper.
	* selftest-run-tests.c (selftest::run_tests): Call
	selftest::convert_c_tests.
	* selftest.h (selftest::convert_c_tests): New decl.
	* tree.c (build_complex): Assert that REAL and IMAG are constants.
	(integer_zerop): Look through location wrappers.
	(integer_onep): Likewise.
	(integer_each_onep): Likewise.
	(integer_all_onesp): Likewise.
	(integer_minus_onep): Likewise.
	(integer_pow2p): Likewise.
	(integer_nonzerop): Likewise.
	(integer_truep): Likewise.
	(fixed_zerop): Likewise.
	(real_zerop): Likewise.
	(real_onep): Likewise.
	(real_minus_onep): Likewise.
	(tree_int_cst_equal): Likewise.
	(simple_cst_equal): Treat location wrappers with non-equal source
	locations as being unequal.
	(uniform_integer_cst_p): Look through location wrappers.
	(maybe_wrap_with_location): Don't create wrappers if any
	auto_suppress_location_wrappers are active.
	(suppress_location_wrappers): New variable.
	(selftest::test_predicates): New test.
	(selftest::tree_c_tests): Call it.
	* tree.h (CONSTANT_CLASS_OR_WRAPPER_P): New macro.
	(suppress_location_wrappers): New decl.
	(class auto_suppress_location_wrappers): New class.

gcc/cp/ChangeLog:
	PR c++/43064
	PR c++/43486
	* call.c (build_conditional_expr_1): Strip location wrappers when
	checking for CONST_DECL.
	(conversion_null_warnings): Use location of "expr" if available.
	* class.c (fixed_type_or_null): Handle location wrappers.
	* constexpr.c (potential_constant_expression_1): Likewise.
	* cvt.c (ignore_overflows): Strip location wrappers when
	checking for INTEGER_CST, and re-wrap the result if present.
	(ocp_convert): Call fold_for_warn before checking for INTEGER_CST.
	* decl.c (reshape_init_r): Strip any location wrapper.
	(undeduced_auto_decl): Likewise.
	* expr.c (mark_discarded_use): Likewise for expr.
	* init.c (build_aggr_init): Likewise before checking init for
	DECL_P.
	(warn_placement_new_too_small): Call fold_for_warn on adj before
	checking for CONSTANT_CLASS_P, and on nelts.  Strip any location
	wrapper from op0 and on oper before checking for VAR_P.
	* parser.c (cp_parser_primary_expression): Call
	maybe_add_location_wrapper on numeric and string literals.
	(cp_parser_postfix_expression): Strip any location wrapper when
	checking for DECL_IS_BUILTIN_CONSTANT_P.
	(cp_parser_unary_expression): Ensure that folding of NEGATE_EXPR
	around a constant happens in the presence of location wrappers and
	returns a wrapped result.
	(cp_parser_has_attribute_expression): Strip any location wrapper
	from "oper".
	(cp_parser_binary_expression): Strip any location wrapper when
	checking for DECL_P on the lhs.
	(cp_parser_decltype): Strip any location wrapper from result of
	cp_parser_decltype_expr.
	(cp_parser_mem_initializer): Add location wrappers to the
	parenthesized expression list.
	(cp_parser_template_parameter_list): Don't create wrapper nodes
	within a template-parameter-list.
	(cp_parser_template_argument_list): Don't create wrapper nodes
	within a template-argument-list.
	(cp_parser_parameter_declaration): Strip location wrappers from
	default arguments.
	(cp_parser_gnu_attribute_list): Don't create wrapper nodes.
	(cp_parser_std_attribute_spec_seq): Likewise.
	(cp_parser_omp_all_clauses): Don't create wrapper nodes within
	OpenMP clauses.
	(cp_parser_omp_for_loop): Likewise.
	(cp_parser_omp_declare_reduction_exprs): Likewise.
	* pt.c (convert_nontype_argument_function): Strip location
	wrappers from fn_no_ptr before checking for FUNCTION_DECL.
	(tsubst_default_argument): Move note about which callsite led to
	instantiation to after the check_default_argument call.
	(do_auto_deduction): Likewise from init before checking for
	DECL_P.
	* semantics.c (force_paren_expr): Likewise from expr before
	checking for DECL_P.
	(finish_parenthesized_expr): Likewise from expr before
	checking for STRING_CST.
	(perform_koenig_lookup): Likewise from fn.
	(finish_call_expr): Likewise.
	(finish_id_expression): Rename to...
	(finish_id_expression_1): ...this, calling
	maybe_add_location_wrapper on the result.
	(capture_decltype): Use lookup_name_real rather than value_member
	when looking up decl within the capture-list.
	* tree.c (cp_stabilize_reference): Strip any location wrapper.
	(builtin_valid_in_constant_expr_p): Likewise.
	(strip_typedefs_expr): Strip any location wrapper before checking
	for decls or constants.
	(is_overloaded_fn): Likewise.
	(maybe_get_fns): Likewise.
	(selftest::test_lvalue_kind): Verify lvalue_p.
	* typeck.c (cxx_sizeof_expr): Strip any location wrapper.
	(cxx_alignof_expr): Likewise.
	(is_bitfield_expr_with_lowered_type): Handle location wrappers.
	(cp_build_array_ref): Call maybe_constant_value on "idx".
	(cp_build_binary_op): Strip location wrapper from first_arg before
	checking for PARM_DECL.  Likewise for op1 before checking for
	INTEGER_CST in two places.  Likewise for orig_op0 and orig_op1
	when checking for STRING_CST.
	(cp_build_addr_expr_1): Likewise for arg when checking for
	FUNCTION_DECL.
	(cp_build_modify_expr): Likewise for newrhs when checking for
	STRING_CST.
	(convert_for_assignment): Don't strip location wrappers when
	stripping NON_LVALUE_EXPR.
	(maybe_warn_about_returning_address_of_local): Strip location
	wrapper from whats_returned before checking for DECL_P.
	(can_do_nrvo_p): Strip location wrapper from retval.
	(treat_lvalue_as_rvalue_p): Likewise.
	(check_return_expr): Likewise.
	* typeck2.c (cxx_incomplete_type_diagnostic): Strip location
	wrapper from value before checking for VAR_P or PARM_DECL.
	(digest_init_r): Strip location wrapper from init.  When
	copying "init", also copy the wrapped node.

gcc/objc/ChangeLog:
	PR c++/43064
	PR c++/43486
	* objc-act.c (objc_maybe_build_component_ref): Strip any location
	wrapper before checking for UOBJC_SUPER_decl and self_decl.
	(objc_finish_message_expr): Strip any location wrapper.
	(gen_declaration): Strip location wrappers from "w".

gcc/testsuite/ChangeLog:
	PR c++/43064
	PR c++/43486
	* c-c++-common/pr51712.c (valid2): Mark xfail as passing on C++.
	* g++.dg/cpp0x/constexpr-47969.C: Update column of expected error.
	* g++.dg/cpp0x/constexpr-ex2.C: Likewise.
	* g++.dg/cpp0x/scoped_enum2.C: Likewise.
	* g++.dg/cpp1z/decomp48.C: Update expected location of warning
	for named local variables to use that of the local variable.
	* g++.dg/ext/vla1.C: Update column.
	* g++.dg/init/array43.C: Update expected column to be that of the
	initializer.
	* g++.dg/init/initializer-string-too-long.C: New test.
	* g++.dg/init/new44.C: Add "-ftrack-macro-expansion=0".
	* g++.dg/init/pr43064-1.C: New test.
	* g++.dg/init/pr43064-2.C: New test.
	* g++.dg/init/pr43064-3.C: New test.
	* g++.dg/other/fold1.C: Update column of expected error.
	* g++.dg/parse/crash36.C: Likewise.
	* g++.dg/plugin/diagnostic-test-expressions-1.C: Add negative
	integer and float expressions.
	* g++.dg/template/defarg6.C: Move expected error to the default
	argument; add expected message about where instantiated.
	* g++.dg/wrappers/Wparentheses.C: New test.
	* g++.old-deja/g++.bugs/900402_02.C: Update column of expected
	error.

From-SVN: r267272

This patch is the analog to r266868-r266870, but for SSSE3.
The SSSE3 tests had been inadvertently made to PASS without actually running
the test code. Actually running the code turned up some previously undetected
issues.

This patch fixes some issues in the implementations, fixes up the tests
to use a union for the test data, which avoids strict aliasing issues,
and enables the tests to actually run (by removing a dependency on
__BUILTIN_CPU_SUPPORTS).

Also, there's a fairly insignificant change in the testcases that walk
through the data as pairs of vectors from:
  [0] and [1]
  [2] and [3]
  ...
  [n-4] and [n-3]
  [n-2] and [n-1]

to:
  [0] and [1]
  [1] and [2]
  ...
  [n-3] and [n-2]
  [n-2] and [n-1]

Since the testcases compute the correct answers based on the input, no
other changes were necessary to effect the change.

2018-12-19  Paul A. Clarke  <pc@us.ibm.com>

[gcc]

	* config/rs6000/tmmintrin.h (_mm_hadds_epi16): Vector lanes swapped.
	(_mm_hsub_epi32): Likewise.
	(_mm_shuffle_epi8): Fix reversed interpretation of parameters.
	(_mm_shuffle_pi8): Likewise.
	(_mm_addubs_pi16): Likewise.

[gcc/testsuite]

	* gcc.target/powerpc/ssse3-check.h: Enable tests to run.
	* gcc.target/powerpc/ssse3-pabsb.c: Code fixes for strict aliasing
	issues.
	* gcc.target/powerpc/ssse3-pabsd.c: Likewise.
	* gcc.target/powerpc/ssse3-palignr.c: Likewise.
	* gcc.target/powerpc/ssse3-phaddd.c: Likewise.
	* gcc.target/powerpc/ssse3-phaddsw.c: Likewise.
	* gcc.target/powerpc/ssse3-phaddw.c: Likewise.
	* gcc.target/powerpc/ssse3-phsubd.c: Likewise.
	* gcc.target/powerpc/ssse3-phsubw.c: Likewise.
	* gcc.target/powerpc/ssse3-pmulhrsw.c: Likewise.
	* gcc.target/powerpc/ssse3-pshufb.c: Likewise.
	* gcc.target/powerpc/ssse3-psignb.c: Likewise.
	* gcc.target/powerpc/ssse3-psignd.c: Likewise.
	* gcc.target/powerpc/ssse3-psignw.c: Likewise.
	* gcc.target/powerpc/ssse3-vals.h: Provide input data as a union.

From-SVN: r267271

FP instructions are only enabled for TARGET_32BIT and TARGET_HARD_FLOAT
but GCC only gives an error when TARGET_HARD_FLOAT is true and -mfpu is
not set. Among other things, it makes some of the cmse tests (eg.
gcc.target/arm/cmse/baseline/softfp.c) fail when targeting
-march=armv8-m.base -mcmse -mfpu=<something> -mfloat-abi=softfp. This
commit adds an extra check for TARGET_32BIT to TARGET_HARD_FLOAT such
that it is false on TARGET_THUMB1 targets even when a FPU is specified.

2018-12-19  thomas Preud'homme  <thomas.preudhomme@linaro.org>

    gcc/
    * config/arm/arm.h (TARGET_HARD_FLOAT): Restrict to TARGET_32BIT
    targets.
    * config/arm/arm.c (output_return_instruction): Only check
    TARGET_HARD_FLOAT to decide whether FP instructions are available.

    gcc/testsuite/
    * gcc.target/arm/cmse/baseline/softfp.c: Force an FPU.

From-SVN: r267270

Add pr85381*.c test-cases that are already passing without the fix for PR85381.

Build and reg-tested on x86_64 with nvptx accelerator.

2018-12-19  Tom de Vries  <tdevries@suse.de>

	* testsuite/libgomp.oacc-c-c++-common/pr85381-2.c: New test.
	* testsuite/libgomp.oacc-c-c++-common/pr85381-3.c: New test.
	* testsuite/libgomp.oacc-c-c++-common/pr85381-4.c: New test.

From-SVN: r267268

The goacc.exp test-cases nvptx-merged-loop.c and nvptx-sese-1.c are failing
during linking due to missing libgomp.spec.

Move them to the libgomp testsuite.

Build and reg-tested on x86_64 with nvptx accelerator.

2018-12-19  Tom de Vries  <tdevries@suse.de>

	* gcc.dg/goacc/nvptx-merged-loop.c: Move to
	libgomp/testsuite/libgomp.oacc-c-c++-common.
	* gcc.dg/goacc/nvptx-sese-1.c: Same.

	* testsuite/lib/libgomp.exp: Add load_lib of scanoffloadrtl.exp.
	* testsuite/libgomp.oacc-c-c++-common/nvptx-merged-loop.c: Move from
	gcc/testsuite/gcc.dg/goacc.
	* testsuite/libgomp.oacc-c-c++-common/nvptx-sese-1.c: Same.

From-SVN: r267267

Add scan-offload-rtl-dump, similar to scan-offload-tree-dump.

Build and reg-tested on x86_64 with nvptx accelerator.

2018-12-19  Tom de Vries  <tom@codesourcery.com>

	* lib/scanoffloadrtl.exp: New file.
	* gcc.dg-selftests/dg-final.exp (dg_final_directive_check_num_args): Add
	offload-rtl.

	* doc/sourcebuild.texi (Commands for use in dg-final, Scan optimization
	dump files): Add offload-rtl.

From-SVN: r267266

This pattern optimises a scalar extract from a vector loaded from
memory to be just a scalar load from memory.  But to do a 64-bit
integer load you need 64-bit integer registers, which needs
TARGET_POWERPC64.


	PR target/88213
	* config/rs6000/vsx.md (*vsx_extract_<P:mode>_<VSX_D:mode>_load):
	Require TARGET_POWERPC64.

From-SVN: r267263

re PR tree-optimization/88533 (Higher performance penalty of array-bounds checking for sparse-matrix vector multiply)

2018-12-19  Richard Biener  <rguenther@suse.de>

	PR tree-optimization/88533
	Revert
	2018-04-30  Richard Biener  <rguenther@suse.de>

	PR tree-optimization/28364
	PR tree-optimization/85275
	* tree-ssa-loop-ch.c (ch_base::copy_headers): Stop after
	copying first exit test.

	* gcc.dg/tree-ssa/ssa-dom-thread-7.c: Adjust.

	* tree-ssa-loop-ch.c: Include tree-phinodes.h and
	ssa-iterators.h.
	(should_duplicate_loop_header_p): Track whether stmt compute
	loop invariants or values based on IVs.  Apart from the
	original loop header only duplicate blocks with exit tests
	that are based on IVs or invariants.

	* gcc.dg/tree-ssa/copy-headers-6.c: New testcase.
	* gcc.dg/tree-ssa/copy-headers-7.c: Likewise.
	* gcc.dg/tree-ssa/ivopt_mult_1.c: Un-XFAIL.
	* gcc.dg/tree-ssa/ivopt_mult_2.c: Likewise.

From-SVN: r267262

Use MAX, MIN, and ROUND_UP macros to simplify code.

Build and reg-tested on x86_64 with nvptx accelerator.

2018-12-19  Tom de Vries  <tdevries@suse.de>

	* config/nvptx/nvptx.c (nvptx_gen_shared_bcast, shared_prop_gen)
	(nvptx_goacc_expand_accel_var): Use MAX and ROUND_UP.
	(nvptx_assemble_value, nvptx_output_skip): Use MIN.
	(nvptx_shared_propagate, nvptx_single, nvptx_expand_shared_addr): Use
	MAX.

From-SVN: r267261

Rename state propagation functions to avoid worker/vector terminology.

Build and reg-tested on x86_64 with nvptx accelerator.

2018-12-19  Tom de Vries  <tdevries@suse.de>

	* config/nvptx/nvptx.c (nvptx_gen_wcast): Rename as
	nvptx_gen_warp_bcast.
	(nvptx_gen_wcast): Rename to nvptx_gen_shared_bcast, add bool
	vector argument, and update call to nvptx_gen_shared_bcast.
	(propagator_fn): Add bool argument.
	(nvptx_propagate): New bool argument, pass bool argument to fn.
	(vprop_gen): Rename to warp_prop_gen, update call to
	nvptx_gen_warp_bcast.
	(nvptx_vpropagate): Rename to nvptx_warp_propagate, update call to
	nvptx_propagate.
	(wprop_gen): Rename to shared_prop_gen, update call to
	nvptx_gen_shared_bcast.
	(nvptx_wpropagate): Rename to nvptx_shared_propagate, update call
	to nvptx_propagate.
	(nvptx_wsync): Rename to nvptx_cta_sync.
	(nvptx_single): Update calls to nvptx_gen_warp_bcast,
	nvptx_gen_shared_bcast and nvptx_cta_sync.
	(nvptx_process_pars): Likewise.
	(write_worker_buffer): Rename as write_shared_buffer.
	(nvptx_file_end): Update calls to write_shared_buffer.
	(nvptx_expand_worker_addr): Rename as nvptx_expand_shared_addr.
	(nvptx_expand_builtin): Update call to nvptx_expand_shared_addr.
	(nvptx_get_worker_red_addr): Rename as nvptx_get_shared_red_addr.
	(nvptx_goacc_reduction_setup): Update call to
	nvptx_get_shared_red_addr.
	(nvptx_goacc_reduction_fini): Likewise.
	(nvptx_goacc_reduction_teardown): Likewise.

From-SVN: r267260

Rename worker_bcast variables to oacc_bcast, avoiding worker terminology.

Build and reg-tested on x86_64 with nvptx accelerator.

2018-12-19  Tom de Vries  <tdevries@suse.de>

	* config/nvptx/nvptx.c (worker_bcast_size): Rename as
	oacc_bcast_size.
	(worker_bcast_align): Rename as oacc_bcast_align.
	(worker_bcast_sym): Rename as oacc_bcast_sym.
	(nvptx_option_override): Update usage of oacc_bcast_*.
	(struct wcast_data_t): Rename as broadcast_data_t.
	(nvptx_gen_wcast): Update type of data argument and usage of
	oacc_bcast_align.
	(wprop_gen): Update type of data_ and usage of oacc_bcast_align.
	(nvptx_wpropagate): Update type of data and usage of
	oacc_bcast_{sym,size}.
	(nvptx_single): Update type of data and usage of oacc_bcast_size.
	(nvptx_file_end): Update usage of oacc_bcast_{sym,align,size}.

From-SVN: r267259

Allow the logical barrier operand of nvptx_barsync to be a register, and add a
thread count operand.

Build and reg-tested on x86_64 with nvptx accelerator.

2018-12-19  Tom de Vries  <tdevries@suse.de>

	* config/nvptx/nvptx.md (nvptx_barsync): Add and handle operand.
	* config/nvptx/nvptx.c (nvptx_wsync): Update call to gen_nvptx_barsync.

From-SVN: r267258

For openacc loops, we generate this style of code:
...
        @%r41   bra.uni $L5;
        @%r40   bra     $L6;
                mov.u64 %r32, %ar0;
                cvta.shared.u64 %r39, __worker_bcast;
                st.u64  [%r39], %r32;
$L6:
$L5:
                bar.sync        0;
        @%r40   bra     $L4;
                cvta.shared.u64 %r38, __worker_bcast;
                ld.u64  %r32, [%r38];
                ...
$L4:
                bar.sync        1;
...

The first barrier is there to ensure that no thread reads the broadcast buffer
before it's written.  The second barrier is there to ensure that no thread
overwrites the broadcast buffer before all threads have read it (as well as
implementing the obligatory synchronization after a worker loop).

We've been using the logical barrier resources '0' and '1' for these two
barriers, but there's no reason why we can't use the same one.

Use logical barrier resource '0' for both barriers, making the openacc
implementation claim less resources.

Build and reg-tested on x86_64 with nvptx accelerator.

2018-12-19  Tom de Vries  <tdevries@suse.de>

	* config/nvptx/nvptx.c (nvptx_single): Always pass false to
	nvptx_wsync.
	(nvptx_process_pars): Likewise.

From-SVN: r267257

Implement TARGET_SET_CURRENT_FUNCTION for nvptx.  This gives us a place to
add initialization or reset actions that need to be executed on a per-function
basis.

Build and reg-tested on x86_64 with nvptx accelerator.

2018-12-19  Tom de Vries  <tdevries@suse.de>

	* config/nvptx/nvptx.c (nvptx_previous_fndecl): Declare.
	(nvptx_set_current_function): New function.
	(TARGET_SET_CURRENT_FUNCTION): Define.

From-SVN: r267256

For HiSilicon's tsv110 cpu core, it supports some v8_4A features, but
some mandatory features are not implemented.

2018-12-19  Shaokun Zhang  <zhangshaokun@hisilicon.com>

	* config/aarch64/aarch64-cores.def (tsv110): Fix architecture.  This
	part is really Armv8.2 with some permitted Armv8.4 extensions.

From-SVN: r267255

re PR target/88541 (VPCLMULQDQ 256-bit inline function unavailable with optimization but without enabled AVX512VL support)

	PR target/88541
	* config/i386/vpclmulqdqintrin.h (_mm256_clmulepi64_epi128): Enable
	for -mavx -mvpclmulqdq rather than just for -mavx512vl -mvpclmulqdq.

	* gcc.target/i386/avx-vpclmulqdq-1.c: New test.

From-SVN: r267254

	PR c++/87934
	* constexpr.c (cxx_eval_constant_expression) <case CONSTRUCTOR>: Do
	re-process TREE_CONSTANT CONSTRUCTORs if they aren't reduced constant
	expressions.

	* g++.dg/cpp0x/constexpr-87934.C: New test.

From-SVN: r267253

PR 86153 was originally filed when changes to the C++11's
implementation of vector resize(size_type) limited inlining that were
required for testsuite/g++.dg/pr83239.C to verify that we did not
issue an undesired warning.

That was worked by increasing the limit for inlining, but that in turn
caused the C++98 implementation of vector resize, that is
significantly different, to also be fully inlined, and that happened
to issue the very warnings the test was meant to verify we did NOT
issue.

The reason we issued the warnings was that we failed to optimize out
some parts of _M_fill_insert, used by the C++98 version of vector
resize, although the call of _M_fill_insert was guarded by a test that
could never pass: test testcase only calls resize when the vector size
is >= 3, to decrement the size by two.  The limitation we hit in VRP
was that the compared values could pass as an overflow test, if the
vector size was 0 or 1 (we knew it wasn't), but even with dynamic
ranges we failed to decide that the test result could be determined at
compile time, even though after the test we introduced ASSERT_EXPRs
that required a condition known to be false from earlier ones.

I pondered turning ASSERT_EXPRs that show impossible conditions into
traps, to enable subsequent instructions to be optimized, but I ended
up finding an earlier spot in which an overflow test that would have
introduced the impossible ASSERT_EXPR can have its result deduced from
earlier known ranges and resolved to the other path.

Although such overflow tests could be uniformly simplified to compares
against a constant, the original code would only perform such
simplifications when the test could be resolved to an equality test
against zero.  I've thus avoided introducing compares against other
constants, and instead added code that will only simplify overflow
tests that weren't simplified before when the condition can be
evaluated at compile time.


for  gcc/ChangeLog

	PR testsuite/86153
	PR middle-end/83239
	* vr-values.c
	(vr_values::vrp_evaluate_conditional_warnv_with_ops): Extend
	simplification of overflow tests to cover cases in which we
	can determine the result of the comparison.

for  gcc/testsuite/ChangeLog

	PR testsuite/86153
	PR middle-end/83239
	* gcc.dg/vrp-overflow-1.c: New.

From-SVN: r267252

When binding an object to a template parameter of reference type, we
take the address of the object and dereference that address.  The type
of the address may still carry (template) typedefs, but
verify_unstripped_args_1 rejects such typedefs other than in the top
level of template arguments.

Canonicalizing the type we want to convert to right after any
substitutions or deductions avoids that issue.


for  gcc/cp/ChangeLog

	PR c++/87012
	* pt.c (convert_template_argument): Canonicalize type after
	tsubst/deduce.

for  gcc/testsuite/ChangeLog

	PR c++/87012
	* g++.dg/cpp0x/pr87012.C: New.

From-SVN: r267251

This patch started out from the testcase in PR88146, that attempted to
synthesize an inherited ctor without any args before a varargs
ellipsis and crashed while at that, because of the unguarded
dereferencing of the parm type list, that usually contains a
terminator.  The terminator is not there for varargs functions,
however, and without any other args, we ended up dereferencing a NULL
pointer.  Oops.

Guarding accesses to parm would be easy, but not necessary.  In
do_build_copy_constructor, non-inherited ctors are copy-ctors, that
always have at least one parm, so parm needs not be guarded when we
know the access will only take place when we're dealing with an
inherited ctor.  The only other problematic use was in the cvquals
initializer, a variable only used in a loop over fields, that we
skipped individually in inherited ctors.  I've guarded the cvquals
initialization and the entire loop over fields so they only run for
copy-ctors.

Avoiding the crash from unguarded accesses was easy, but I thought we
should still produce the sorry message we got in other testcases that
passed arguments through the ellipsis in inherited ctors.  I put a
check in, and noticed the inherited ctors were synthesized with the
location assigned to the class name, although they were initially
assigned the location of the using declaration.  I decided the latter
was better, and arranged for the better location to be retained.

Further investigation revealed the lack of a sorry message had to do
with the call being in a non-evaluated context, in this case, a
noexcept expression.  The sorry would be correctly reported in other
contexts, so I rolled back the check I'd added, but retained the
source location improvement.

I was still concerned about issuing sorry messages while instantiating
template ctors even in non-evaluated contexts, e.g., if a template
ctor had a base initializer that used an inherited ctor with enough
arguments that they'd go through an ellipsis.  I wanted to defer the
instantiation of such template ctors, but that would have been wrong
for constexpr template ctors, and already done for non-constexpr ones.
So, I just consolidated multiple test variants into a single testcase
that explores and explains various of the possibilities I thought of.


for  gcc/cp/ChangeLog

	PR c++/88146
	* method.c (do_build_copy_constructor): Guard cvquals init and
	loop over fields to run for non-inherited ctors only.
	(synthesize_method): Retain location of inherited ctor.

for  gcc/testsuite/ChangeLog

	PR c++/88146
	* g++.dg/cpp0x/inh-ctor32.C: New.

From-SVN: r267250

auto-profile.c (afdo_indirect_call): Skip generating histogram value if we can't find cgraph_node for then...

	* auto-profile.c (afdo_indirect_call): Skip generating histogram
	value if we can't find cgraph_node for then indirected callee.  Save
	profile_id of the cgraph_node in histogram value's first counter.
	* value-prof.c (gimple_value_profile_transformations): Don't skip
	for flag_auto_profile.

From-SVN: r267249

From-SVN: r267248

re PR rtl-optimization/87759 (ICE in lra_assign, at lra-assigns.c:1624, or ICE: Maximum number of LRA assignment passes is achieved (30), or compile-time hog)

	PR rtl-optimization/87759
	* gcc.target/i386/pr87759.c: Require int128 effective target.

From-SVN: r267245

re PR rtl-optimization/87759 (ICE in lra_assign, at lra-assigns.c:1624, or ICE: Maximum number of LRA assignment passes is achieved (30), or compile-time hog)

2018-12-18  Vladimir Makarov  <vmakarov@redhat.com>

	PR rtl-optimization/87759
	* lra-assigns.c (lra_split_hard_reg_for): Recalculate
	non_reload_pseudos.

2018-12-18  Vladimir Makarov  <vmakarov@redhat.com>

	PR rtl-optimization/87759
	* gcc.target/i386/pr87759.c: New.

From-SVN: r267244

re PR tree-optimization/88464 (AVX-512 vectorization of masked scatter failing with "not suitable for scatter store")

	PR target/88464
	* config/i386/i386-builtin-types.def
	(VOID_FTYPE_PDOUBLE_QI_V8SI_V4DF_INT,
	VOID_FTYPE_PFLOAT_QI_V4DI_V8SF_INT,
	VOID_FTYPE_PLONGLONG_QI_V8SI_V4DI_INT,
	VOID_FTYPE_PINT_QI_V4DI_V8SI_INT,
	VOID_FTYPE_PDOUBLE_QI_V4SI_V2DF_INT,
	VOID_FTYPE_PFLOAT_QI_V2DI_V4SF_INT,
	VOID_FTYPE_PLONGLONG_QI_V4SI_V2DI_INT,
	VOID_FTYPE_PINT_QI_V2DI_V4SI_INT): New builtin types.
	* config/i386/i386.c (enum ix86_builtins): Add
	IX86_BUILTIN_SCATTERALTSIV4DF, IX86_BUILTIN_SCATTERALTDIV8SF,
	IX86_BUILTIN_SCATTERALTSIV4DI, IX86_BUILTIN_SCATTERALTDIV8SI,
	IX86_BUILTIN_SCATTERALTSIV2DF, IX86_BUILTIN_SCATTERALTDIV4SF,
	IX86_BUILTIN_SCATTERALTSIV2DI and IX86_BUILTIN_SCATTERALTDIV4SI.
	(ix86_init_mmx_sse_builtins): Fix up names of IX86_BUILTIN_GATHERALT*,
	IX86_BUILTIN_GATHER3ALT* and IX86_BUILTIN_SCATTERALT* builtins to
	match the IX86_BUILTIN codes.  Build 	IX86_BUILTIN_SCATTERALTSIV4DF,
	IX86_BUILTIN_SCATTERALTDIV8SF, IX86_BUILTIN_SCATTERALTSIV4DI,
	IX86_BUILTIN_SCATTERALTDIV8SI, IX86_BUILTIN_SCATTERALTSIV2DF,
	IX86_BUILTIN_SCATTERALTDIV4SF, IX86_BUILTIN_SCATTERALTSIV2DI and
	IX86_BUILTIN_SCATTERALTDIV4SI decls.
	(ix86_vectorize_builtin_scatter): Expand those new builtins.

	* gcc.target/i386/avx512f-pr88464-5.c: New test.
	* gcc.target/i386/avx512f-pr88464-6.c: New test.
	* gcc.target/i386/avx512f-pr88464-7.c: New test.
	* gcc.target/i386/avx512f-pr88464-8.c: New test.
	* gcc.target/i386/avx512vl-pr88464-5.c: New test.
	* gcc.target/i386/avx512vl-pr88464-6.c: New test.
	* gcc.target/i386/avx512vl-pr88464-7.c: New test.
	* gcc.target/i386/avx512vl-pr88464-8.c: New test.
	* gcc.target/i386/avx512vl-pr88464-9.c: New test.
	* gcc.target/i386/avx512vl-pr88464-10.c: New test.
	* gcc.target/i386/avx512vl-pr88464-11.c: New test.
	* gcc.target/i386/avx512vl-pr88464-12.c: New test.
	* gcc.target/i386/avx512vl-pr88464-13.c: New test.
	* gcc.target/i386/avx512vl-pr88464-14.c: New test.
	* gcc.target/i386/avx512vl-pr88464-15.c: New test.
	* gcc.target/i386/avx512vl-pr88464-16.c: New test.

From-SVN: r267239

	* include/bits/fs_dir.h (operator<<): Overload for directory_entry,
	as per LWG 3171.
	* testsuite/27_io/filesystem/directory_entry/lwg3171.cc: New test.

From-SVN: r267238

	* src/filesystem/std-dir.cc (filesystem::_Dir::advance): Move new
	path instead of copying.

From-SVN: r267237

Now that path::operator/=(basic_string_view<value_type>) works directly
from the string argument, instead of constructing a temporary path from
the string, it's potentially more efficient to do 'path(x) /= s' instead
of 'x / s'. This changes the only relevant place in the library.

	* src/filesystem/std-dir.cc (filesystem::_Dir::advance): Append
	string to lvalue to avoid creating temporary path.

From-SVN: r267236

The resolution for LWG 2936 defines the comparison more precisely, which
this patch implements. The patch also defines comparisons with strings
to work without constructing a temporary path object (so avoids any
memory allocations).

	* include/bits/fs_path.h (path::compare(const string_type&))
	(path::compare(const value_type*)): Add noexcept and construct a
	string view to compare to instead of a path.
	(path::compare(basic_string_view<value_type>)): Add noexcept. Remove
	inline definition.
	* src/filesystem/std-path.cc (path::_Parser): Track last type read
	from input.
	(path::_Parser::next()): Return a final empty component when the
	input ends in a non-root directory separator.
	(path::_M_append(basic_string_view<value_type>)): Remove special cases
	for trailing non-root directory separator.
	(path::_M_concat(basic_string_view<value_type>)): Likewise.
	(path::compare(const path&)): Implement LWG 2936.
	(path::compare(basic_string_view<value_type>)): Define in terms of
	components returned by parser, consistent with LWG 2936.
	* testsuite/27_io/filesystem/path/compare/lwg2936.cc: New.
	* testsuite/27_io/filesystem/path/compare/path.cc: Test more cases.
	* testsuite/27_io/filesystem/path/compare/strings.cc: Likewise.

From-SVN: r267235

	* include/std/string_view [__cplusplus > 201703L]
	(basic_string_view::starts_with(basic_string_view)): Implement
	proposed resolution of LWG 3040 to avoid redundant length check.
	(basic_string_view::starts_with(_CharT)): Implement proposed
	resolution of LWG 3040 to check at most one character.
	(basic_string_view::ends_with(_CharT)): Likewise.

From-SVN: r267234

extend.texi (PowerPC Altivec/VSX Built-in Functions): Describe when a typedef name can be used as the type specifier for a vector type...

2018-12-18  Bill Schmidt  <wschmidt@linux.ibm.com>

	* doc/extend.texi (PowerPC Altivec/VSX Built-in Functions):
	Describe when a typedef name can be used as the type specifier for
	a vector type, and when it cannot.

From-SVN: r267232

In GCC 9 the aarch64 port learned how to do V16QImode SAD operations on signed and unsigned chars.
But I had missed enabling the effective target for that.
This patch enables that target for non-SVE aarch64.
Two new tests now PASS on aarch64:
gcc.dg/vect/slp-reduc-sad.c
gcc.dg/vect/vect-reduc-sad.c

	* lib/target-supports.exp (check_effective_target_vect_usad_char):
	Add non-SVE aarch64 to supported list.

From-SVN: r267230

2018-12-18  Jozef Lawrynowicz  <jozef.l@mittosystems.com>

	* config/msp430/msp430.h: Define TARGET_VTABLE_ENTRY_ALIGN.

From-SVN: r267229