Unit sem_spark was implementing the borrow-checker for the support of
ownership pointers in SPARK. It has been moved to gnat2why codebase to
facilitate its evolution and allow the more powerful flow analysis to
provide its results for better analysis on pointers.

2019-09-19  Yannick Moy  <moy@adacore.com>

gcc/ada/

	* gcc-interface/Make-lang.in: Remove references to sem_spark.
	* sem_spark.adb, sem_spark.ads: Remove unit.

From-SVN: r275944

GNAT implements Machine_Rounding as an alias for Rounding but, whereas
the implementation of the latter is in line when possible, that of the
former is always out of line, which is not aligned with the intent of
the Ada RM.

This changes the compiler to using for Machine_Rounding the same in line
implementation as Rounding when possible.

Running these commands:

  gcc -c f.adb -gnatD
  grep system f.adb.dg

On the following sources:

function F (Val : Float) return Integer is
begin
  return Integer (Float'Machine_Rounding (Val));
end;

Should execute silently.

2019-09-19  Eric Botcazou  <ebotcazou@adacore.com>

gcc/ada/

	* exp_attr.adb (Is_Inline_Floating_Point_Attribute): Treat
	Machine_Rounding as an alias for Rounding.
	* sem_res.adb (Simplify_Type_Conversion): Likewise.

From-SVN: r275943

In the case of GNAT-LLVM, the GNAT FE no longer does expansion of
up-level references identified by the subprogram unnesting machinery
into activation record references. This is now only done by the FE when
generating C code. This expansion is already taken care of by the
gnat-llvm middle phase, so there's no benefit to also doing it in the
front end.

2019-09-19  Gary Dismukes  <dismukes@adacore.com>

gcc/ada/

	* exp_unst.adb (Unnest_Subprogram): Bypass the transformation of
	up-level references unless Opt.Generate_C_Code is enabled.

From-SVN: r275942

In the general case, the comparison for equality of array objects is
implemented by a local function that contains, among other things, a
loop running over the elements, comparing them one by one and exiting
as soon as an element is not the same in the two array objects.

For the specific case of constrained 2-element arrays, this is rather
heavy and unnecessarily obfuscates the control flow of the program,
so this change implements a simple conjunction of comparisons for it.

Running these commands:

  gcc -c p.ads -O -gnatD
  grep loop p.ads.dg

On the following sources:

package P is

  type Rec is record
    Re : Float;
    Im : Float;
  end record;

  type Arr is array (1 .. 2) of Rec;

  function Equal (A, B : Arr) return Boolean is (A = B);

end P;

Should execute silently.

2019-09-19  Eric Botcazou  <ebotcazou@adacore.com>

gcc/ada/

	* exp_ch4.adb (Expand_Array_Equality): If optimization is
	enabled, generate a simple conjunction of comparisons for the
	specific case of constrained 1-dimensional 2-element arrays.
	Fix formatting.

From-SVN: r275941

Routines Homonym_Number and Get_Homonym_Number were exactly the same,
except for minor style differences. Keep the one in Exp_Util; remove the
one in Exp_Dbug. No test attached, because semantics is unaffected.

2019-09-19  Piotr Trojanek  <trojanek@adacore.com>

gcc/ada/

	* exp_dbug.ads, exp_dbug.adb (Get_Homonym_Number): Remove.
	(Append_Homonym_Number): Use Homonym_Number instead of
	Get_Homonym_Number.
	* exp_util.ads, exp_util.adb (Homonym_Number): Mirror style of
	the removed Get_Homonym_Number routine, i.e. initialize local
	objects at declaration and refine the type of result.
	* sem_util.adb (Add_Homonym_Suffix): Use Homonym_Number instead
	of Get_Homonym_Number.

From-SVN: r275940

This patch fixes a compiler abort on a dynamic predicate applied to the
full view of a type in a generic package declaration, when the
expression for the predicate is a conditionql expression that contains
references to components of the full view of the type.

2019-09-19  Ed Schonberg  <schonberg@adacore.com>

gcc/ada/

	* sem_ch13.adb (Check_Aspect_At_End_Of_Declarations): Simplify
	handling of expressions in predicates when the context is a
	generic unit.

gcc/testsuite/

	* gnat.dg/predicate14.adb, gnat.dg/predicate14.ads: New
	testcase.

From-SVN: r275939

If a for loop starts with "for X in F (...)'Range loop", where F is a
function returning an unconstrained array, then memory is leaked. This
patch fixes that bug.

Running these commands:

  gnatmake -q -f main.adb
  main

On the following sources:

with Text_IO; use Text_IO;
package P is

   function Get_Objects return String;

end P;

package body P is
   function Get_Objects return String is
   begin
      return "xyzzy";
   end Get_Objects;

end P;

with Text_IO; use Text_IO;
pragma Warnings (Off, "an internal GNAT unit");
with System.Secondary_Stack;
pragma Warnings (On, "an internal GNAT unit");
with P; use P;

procedure Main is
   Max_Iterations : constant Integer := 1_000;

   procedure Leak_Call is
   begin
      for Id in Get_Objects'Range loop
         null;
      end loop;
   end Leak_Call;

   procedure SS_Info is new System.Secondary_Stack.SS_Info
(Text_IO.Put_Line);

begin
   for Iteration in 1 .. Max_Iterations loop
      Leak_Call;
   end loop;

   SS_Info;

end Main;

Should produce the following output:

  Secondary Stack information:
    Total size              :  10240 bytes
    Current allocated space :  0 bytes
    Number of Chunks        :  1
    Default size of Chunks  :  10240

2019-09-19  Bob Duff  <duff@adacore.com>

gcc/ada/

	* sem_attr.adb (Resolve_Attribute): Make sure the secondary
	stack is properly managed in the case of a 'Range attribute in a
	loop.

From-SVN: r275938

2019-09-19  Raphael Amiard  <amiard@adacore.com>

gcc/ada/

	* libgnat/a-cfhase.ads (Set): Add comments to public primitives.

From-SVN: r275937

2019-09-19  Raphael Amiard  <amiard@adacore.com>

gcc/ada/

	* libgnat/a-cbhama.ads, libgnat/a-cbhase.ads,
	libgnat/a-chtgop.ads (Clear): Refine comments

From-SVN: r275936

This fixes a spurious type mismatch failure reported between formal and
actual of a call to a subprogram that comes from the instantiation of a
child generic unit that itself contains an instantiation of a slibling
child generic unit, when the parent is itself a generic unit with
private part. The regression was introduced by a recent change made to
clear the Is_Generic_Actual_Type on the implicit full view built when a
generic package is instantiated on a private type.

2019-09-19  Eric Botcazou  <ebotcazou@adacore.com>

gcc/ada/

	* sem_ch12.adb (Restore_Private_Views): Comment out new code
	that clear the Is_Generic_Actual_Type also on the full view.

gcc/testsuite/

	* gnat.dg/generic_inst13.adb,
	gnat.dg/generic_inst13_pkg-nested_g.ads,
	gnat.dg/generic_inst13_pkg-ops_g.ads,
	gnat.dg/generic_inst13_pkg.ads: New testcase.

From-SVN: r275935

This patch fixes a bug where an array object initialized with a
concatenation, and that has an aspect_specification for Alignment,
causes the compiler goes into an infinite loop.

2019-09-19  Bob Duff  <duff@adacore.com>

gcc/ada/

	* exp_ch3.adb (Rewrite_As_Renaming): Return False if there are
	any aspect specifications, because otherwise Insert_Actions
	blows up.

gcc/testsuite/

	* gnat.dg/concat3.adb: New testcase.

From-SVN: r275934

This fixes a regression introduced by the previous change that improved
the handling of explicit by-reference mechanism. For the very specific
case of a component of a bit-packed array, the front-end still needs to
insert a copy around the call because this is where the rewriting into
the sequence of mask-and-shifts is done for the code generator.

2019-09-19  Eric Botcazou  <ebotcazou@adacore.com>

gcc/ada/

	* exp_ch6.adb (Add_Simple_Call_By_Copy_Code): Add
	Bit_Packed_Array parameter and documet it. Always insert a copy
	if it is set True.
	(Expand_Actuals): Adjust the calls to
	Add_Simple_Call_By_Copy_Code.

gcc/testsuite/

	* gnat.dg/pack26.adb: New testcase.

From-SVN: r275933

This patch fixes a bug in which if a symbol is not found, gnatxref can
sometimes enter an infinite loop. No impact on compilation.

2019-09-19  Bob Duff  <duff@adacore.com>

gcc/ada/

	* xref_lib.adb (Get_Symbol_Name): If we reach EOF in the first
	loop without finding the symbol, return "???". Otherwise, it's
	an infinite loop.
	(Parse_EOL): Assert that we're not already at EOF.  Remove
	processing of LF/CR -- there are no operating systems that use
	that.

From-SVN: r275932

This improves the handling of an explicit by-reference passing mechanism
specified by means of the GNAT pragma Export_Function.  This device sort
of circumvents the rules of the language for the by-reference passing
mechanism and it's then up to the programmer to ensure that the actual
parameter is addressable; if it is not, the compiler will generate a
temporary around the call, thus effectively passing the actual by copy.

It turns out that the compiler was too conservative when determining
whether the actual parameter is addressable, in particular if it's a
component of a record type subject to a representation clause.

The change effectively moves this computation from the front-end to the
back-end, which has much more information on the layout and alignment
of types and thus can be less conservative.

2019-09-19  Eric Botcazou  <ebotcazou@adacore.com>

gcc/ada/

	* exp_ch6.adb (Is_Legal_Copy): Also return false for an aliased
	formal and a formal passed by reference in convention Ada.  Add
	missing guard to the existing test on Is_Valued_Procedure.

From-SVN: r275931

2019-09-19  Bob Duff  <duff@adacore.com>

gcc/ada/

	* rtsfind.ads (RTE_Available): Improve comment.

From-SVN: r275930

2019-09-19  Richard Biener  <rguenther@suse.de>

	* tree-parloops.c (parloops_is_slp_reduction): Do not set
	LOOP_VINFO_OPERANDS_SWAPPED.
	(parloops_is_simple_reduction): Likewise.
	* tree-vect-loop.c (_loop_vec_info::_loop_vec_info): Do not
	initialize operands_swapped.
	(_loop_vec_info::~_loop_vec_info): Do not re-canonicalize stmts.
	(vect_is_slp_reduction): Do not swap operands.
	* tree-vectorizer.h (_loop_vec_info::operands_swapped): Remove.
	(LOOP_VINFO_OPERANDS_SWAPPED): Likewise.

From-SVN: r275928

Extend pass rpad to handle avx512f vcvtusi2ss vcvtusi2ss
538.imagick_r improved by 4% with single copy run on SKYLAKE workstation.

gcc/
	* config/i386/i386.md
	(*floatuns<SWI48:mode><MODEF:mode>2_avx512):
	Add avx_partial_xmm_update.

gcc/testsuie
	* gcc.target/i386/pr87007-3.c: New test.

From-SVN: r275926

	PR target/91683
	* config/riscv/riscv-protos.h (riscv_split_symbol): New bool parameter.
	(riscv_move_integer): Likewise.
	* config/riscv/riscv.c (riscv_split_integer): Pass FALSE for new
	riscv_move_integer arg.
	(riscv_legitimize_move): Likewise.
	(riscv_force_temporary): New parameter in_splitter.  Don't call
	force_reg if true.
	(riscv_unspec_offset_high): Pass FALSE for new riscv_force_temporary
	arg.
	(riscv_add_offset): Likewise.
	(riscv_split_symbol): New parameter in_splitter.  Pass to
	riscv_force_temporary.
	(riscv_legitimize_address): Pass FALSE for new riscv_split_symbol
	arg.
	(riscv_move_integer): New parameter in_splitter.  New local
	can_create_psuedo.  Don't call riscv_split_integer or force_reg when
	in_splitter TRUE.
	(riscv_legitimize_const_move): Pass FALSE for new riscv_move_integer,
	riscv_split_symbol, and riscv_force_temporary args.
	* config/riscv/riscv.md (low<mode>+1): Pass TRUE for new
	riscv_move_integer arg.
	(low<mode>+2): Pass TRUE for new riscv_split_symbol arg.

From-SVN: r275925

From-SVN: r275924

    
    This CL serves as part of an initial change for enabling gollvm
    building on arm64 linux, the rest of the change will be covered by
    another one to the gollvm repo.
    
    Incorporate type definition of 'uint128' to 'runtime' and 'syscall'
    packges, the change is not specific to arm64 linux but made available
    for all platforms.
    
    Verified by building and unit-testing gollvm on linux x86-64 and arm64.
    
    Verified by building and checking gccgo on linux x86-64 and arm64.
    
    Fixes golang/go#33711
    
    Change-Id: I4720c7d810cfd4ef720962fb4104c5641b2459c0

From-SVN: r275919

We currently use default mid-end expanders for logical DImode operations.
These split operations without first splitting off complex immediates or
memory operands.  The resulting expansions are non-optimal and allow for
fewer LDRD/STRD opportunities.  So add back explicit expanders which ensure
memory operands and immediates are handled more efficiently.

    gcc/
	PR target/91738
	* config/arm/arm.md (<logical_op>di3): Expand explicitly.
	(one_cmpldi2): Likewise.
	* config/arm/arm.c (const_ok_for_dimode_op): Return true if one
	of the constant parts is simple.
	* config/arm/iterators.md (LOGICAL): Add new code iterator.
	(logical_op): Add new code attribute.
	(logical_OP): Likewise.
	* config/arm/predicates.md (arm_anddi_operand): Add predicate.
	(arm_iordi_operand): Add predicate.
	(arm_xordi_operand): Add predicate.

From-SVN: r275907

On Skylake, we should move integer register to SSE register without
going through memory.  This patch restores Skylake SImode hard register
store cost to 6.

gcc/

	PR target/90878
	* config/i386/x86-tune-costs.h (skylake_cost): Restore SImode
	hard register store cost to 6.

gcc/testsuite/

	PR target/90878
	* gcc.target/i386/pr90878.c: New test.

From-SVN: r275906

On Skylake, SImode store cost isn't less than half cost of 128-bit vector
store.  This patch increases Skylake SImode pseudo register store cost to
make it the same as QImode and HImode.

gcc/

	PR target/91446
	* config/i386/x86-tune-costs.h (skylake_cost): Increase SImode
	pseudo register store cost from 3 to 6 to make it the same as
	QImode and HImode.

gcc/testsuite/

	PR target/91446
	* gcc.target/i386/pr91446.c: New test.

From-SVN: r275905

Cleanup 64-bit multiplies.  Combine the expanders using iterators.
Merge the signed/unsigned multiplies as well as the pre-Armv6 and Armv6
variants.  Split DImode operands early into parallel sets inside the
MULL/MLAL instructions - this improves register allocation and avoids
subreg issues due to other DImode operations splitting early.

    gcc/
	* config/arm/arm.md (maddsidi4): Remove expander.
	(mulsidi3adddi): Remove pattern.
	(mulsidi3adddi_v6): Likewise.
	(mulsidi3_nov6): Likewise.
	(mulsidi3_v6): Likewise.
	(umulsidi3): Remove expander.
	(umulsidi3_nov6): Remove pattern.
	(umulsidi3_v6): Likewise.
	(umulsidi3adddi): Likewise.
	(umulsidi3adddi_v6): Likewise.
	(<Us>mulsidi3): Add combined expander.
	(<Us>maddsidi4): Likewise.
	(<US>mull): Add combined umull and smull pattern.
	(<US>mlal): Likewise.
	* config/arm/iterators.md (Us): Add new iterator.

From-SVN: r275901

Cleanup the various highpart multiply patterns using iterators.
As a result the signed and unsigned variants and the pre-Armv6
multiply operand constraints are all handled in a single pattern
and simple expander.

    gcc/
	* config/arm/arm.md (smulsi3_highpart): Use <US> and <SE> iterators.
	(smulsi3_highpart_nov6): Remove pattern.
	(smulsi3_highpart_v6): Likewise.
	(umulsi3_highpart): Likewise.
	(umulsi3_highpart_nov6): Likewise.
	(umulsi3_highpart_v6): Likewise.
	(<US>mull_high): Add new combined multiply pattern.

From-SVN: r275899

2019-09-18  Richard Biener  <rguenther@suse.de>

	* tree-vect-loop.c (vect_is_simple_reduction): Remove operand
	swapping.
	(vectorize_fold_left_reduction): Remove assert.
	(vectorizable_reduction): Also expect COND_EXPR non-reduction
	operand in position 2.  Remove assert.

From-SVN: r275898

Cleanup the 32-bit multiply patterns.  Merge the pre-Armv6 with the Armv6
patterns, remove useless alternatives and order the accumulator operands
to prefer MLA Ra, Rb, Rc, Ra whenever feasible.

    gcc/
	* config/arm/arm.md (arm_mulsi3): Remove pattern.
	(arm_mulsi3_v6): Likewise.
	(mulsi3addsi_v6): Likewise.
	(mulsi3subsi): Likewise.
	(mul): Add new multiply pattern.
	(mla): Likewise.
	(mls): Likewise.

From-SVN: r275897

2019-09-18  Richard Biener  <rguenther@suse.de>

	* tree-parloops.c (report_ploop_op): Copy from report_vect_op.
	(parloops_valid_reduction_input_p): Copy from
	valid_reduction_input_p.
	(parloops_is_slp_reduction): Copy from vect_is_slp_reduction.
	(parloops_needs_fold_left_reduction_p): Copy from
	needs_fold_left_reduction_p.
	(parloops_is_simple_reduction): Copy from
	vect_is_simple_reduction.
	(parloops_force_simple_reduction): Copy from
	vect_force_simple_reduction.
	(gather_scalar_reductions): Adjust.
	* tree-vect-loop.c (vect_force_simple_reduction): Make static.
	* tree-vectorizer.h (vect_force_simple_reduction): Remove.

From-SVN: r275896

2019-09-18  Martin Liska  <mliska@suse.cz>

	* clang-format: Tweak configuration based on new
	options offered.

From-SVN: r275875

2019-09-18  Richard Biener  <rguenther@suse.de>

	* tree-vectorizer.h (get_initial_def_for_reduction): Remove.
	* tree-vect-loop.c (get_initial_def_for_reduction): Make
	static.
	(vect_create_epilog_for_reduction): Remove dead code.

From-SVN: r275874

assemble_real used GEN_INT to create integers directly from the
longs returned by real_to_target.  assemble_integer then went on
to interpret the const_ints as though they had the mode corresponding
to the accompanying size parameter:

      imode = mode_for_size (size * BITS_PER_UNIT, mclass, 0).require ();

      for (i = 0; i < size; i += subsize)
	{
	  rtx partial = simplify_subreg (omode, x, imode, i);

But in the assemble_real case, X might not be canonical for IMODE.

If the interface to assemble_integer is supposed to allow outputting
(say) the low 4 bytes of a DImode integer, then the simplify_subreg
above is wrong.  But if the number of bytes passed to assemble_integer
is supposed to be the number of bytes that the integer actually contains,
assemble_real is wrong.

This patch takes the latter interpretation and makes assemble_real
generate const_ints that are canonical for the number of bytes passed.

The flip_storage_order handling assumes that each long is a full
SImode, which e.g. excludes BITS_PER_UNIT != 8 and float formats
whose memory size is not a multiple of 32 bits (which includes
HFmode at least).  The patch therefore leaves that code alone.
If interpreting each integer as SImode is correct, the const_ints
that it generates are also correct.

2019-09-18  Richard Sandiford  <richard.sandiford@arm.com>

gcc/
	* varasm.c (assemble_real): Generate canonical const_ints.

From-SVN: r275873

2019-09-18  Richard Biener  <rguenther@suse.de>

	PR lto/91763
	* lto-streamer-in.c (input_eh_regions): Move EH init to
	lto_materialize_function.
	* tree-streamer-in.c (lto_input_ts_function_decl_tree_pointers):
	Likewise.

	lto/
	* lto.c (lto_materialize_function): Initialize EH by looking
	at the function personality and flag_exceptions setting.

From-SVN: r275872

CONSTANT lattice values are symbolic constants rather than
compile-time constants, so among other things can be POLY_INT_CSTs.
This patch fixes a case in which we assumed all CONSTANTs were either
ADDR_EXPRs or INTEGER_CSTs.

This is tested by later SVE patches.

2019-09-18  Richard Sandiford  <richard.sandiford@arm.com>

gcc/
	* tree-ssa-ccp.c (get_value_for_expr): Check whether CONSTANTs
	are INTEGER_CSTs.

From-SVN: r275871

Source-level SVE vectors should be gimplified in the same way
as normal fixed-length vectors rather than as VLAs.

This is tested by later SVE patches.

2019-09-18  Richard Sandiford  <richard.sandiford@arm.com>

gcc/
	* gimplify.c (gimplify_decl_expr): Use poly_int_tree_p instead
	of checking specifically for INTEGER_CST.

From-SVN: r275870

This patch makes compute_record_mode handle SVE vectors in the
same way as it would handle fixed-length vectors.  There should
be no change in behaviour for other targets.

This is needed for the SVE equivalent of arm_neon.h types like
int8x8x2_t (i.e. a pair of int8x8_ts).

2019-09-18  Richard Sandiford  <richard.sandiford@arm.com>

gcc/
	* stor-layout.c (compute_record_mode): Operate on poly_uint64
	sizes instead of uhwi sizes.

From-SVN: r275869

loc_list_for_tree_1 and add_const_value_attribute currently ICE
on POLY_INTs.  loc_list_for_tree_1 can do something sensible but
add_const_value_attribute has to punt, since the constant there
needs to be a link-time rather than load-time or run-time constant.

This is tested by later SVE patches.

2019-09-18  Richard Sandiford  <richard.sandiford@arm.com>

gcc/
	* dwarf2out.c (loc_list_from_tree_1): Handle POLY_INT_CST.
	(add_const_value_attribute): Handle CONST_POLY_INT.

From-SVN: r275868

2019-09-18  Martin Liska  <mliska@suse.cz>

	* dbgcnt.def (store_merging): New counter.
	* gimple-ssa-store-merging.c (imm_store_chain_info::output_merged_stores):
	Use it in store merging.

From-SVN: r275867

The recent Copy_Bitfield change caused gnatbind to change elaboration
order, causing different error messages.

2019-09-18  Bob Duff  <duff@adacore.com>

gcc/ada/

	* exp_ch5.adb (Expand_Assign_Array_Loop_Or_Bitfield): Move call
	to RTE_Available later, so it doesn't disturb the elab order.
	The RE_Copy_Bitfield entity is defined in package
	System.Bitfields which has a dependency on package
	System.Bitfield_Utils, which has it its spec:

	   pragma Elaborate_Body;

	The query on RTE_Available forces loading and analyzing
	System.Bitfields and all its withed units.

From-SVN: r275866

This eliminates a spurious alignment warning given by the compiler on an
address clause when the No_Exception_Propagation restriction is in
effect and the -gnatw.x switch is used. In this configuration the
address clauses whose expression is itself of the form X'Address would
not be sufficiently analyzed and, therefore, the compiler might give
false positive warnings.

2019-09-18  Eric Botcazou  <ebotcazou@adacore.com>

gcc/ada/

	* checks.ads (Alignment_Warnings_Record): Add P component.
	* checks.adb (Apply_Address_Clause_Check): Be prepared to kill
	the warning also if the clause is of the form X'Address.
	(Validate_Alignment_Check_Warning): Kill the warning if the
	clause is of the form X'Address and the alignment of X is
	compatible.

gcc/testsuite/

	* gnat.dg/warn31.adb, gnat.dg/warn31.ads: New testcase.

From-SVN: r275865

This patch fixes a compiler abort on a case expression whose
alternatives are universal_real constants, when the case expression is
an operand in a multiplication or division whose other operand is of a
fixed-point type.

2019-09-18  Ed Schonberg  <schonberg@adacore.com>

gcc/ada/

	* sem_res.adb (Set_Mixed_Node_Expression): If a conditional
	expression has universal_real alternaitves and the context is
	Universal_Fixed, as when it is an operand in a fixed-point
	multiplication or division, resolve the expression with a
	visible fixed-point type, which must be unique.

gcc/testsuite/

	* gnat.dg/fixedpnt8.adb: New testcase.

From-SVN: r275864