Skip to content

R
riscv-gcc-1
Switch branch/tag
  1. 09 Jan, 2018 15 commits
  3. 08 Jan, 2018 25 commits
    • re PR target/83677 (PPC: The xxpermr instruction is not generated correctly) · a25811c8 
      [gcc]

2018-01-08  Bill Schmidt  <wschmidt@linux.vnet.ibm.com>

	PR target/83677
	* config/rs6000/altivec.md (*altivec_vpermr_<mode>_internal):
	Reverse order of second and third operands in first alternative.
	* config/rs6000/rs6000.c (rs6000_expand_vector_set): Reverse order
	of first and second elements in UNSPEC_VPERMR vector.
	(altivec_expand_vec_perm_le): Likewise.

[gcc/testsuite]

2018-01-08  Bill Schmidt  <wschmidt@linux.vnet.ibm.com>

	PR target/83677
	* gcc.target/powerpc/pr83677.c: New file.

From-SVN: r256358
      Bill Schmidt committed
    • quad-float128.h (IBM128_TYPE): Explicitly use __ibm128, instead of trying to use long double. · 68df9882 
      2018-01-08  Michael Meissner  <meissner@linux.vnet.ibm.com>

	* config/rs6000/quad-float128.h (IBM128_TYPE): Explicitly use
	__ibm128, instead of trying to use long double.
	(CVT_FLOAT128_TO_IBM128): Use TFtype instead of __float128 to
	accomidate -mabi=ieeelongdouble multilibs.
	(CVT_IBM128_TO_FLOAT128): Likewise.
	* config/rs6000/ibm-ldouble.c (IBM128_TYPE): New macro to define
	the appropriate IBM extended double type.
	(__gcc_qadd): Change all occurances of long double to IBM128_TYPE.
	(__gcc_qsub): Likewise.
	(__gcc_qmul): Likewise.
	(__gcc_qdiv): Likewise.
	(pack_ldouble): Likewise.
	(__gcc_qneg): Likewise.
	(__gcc_qeq): Likewise.
	(__gcc_qne): Likewise.
	(__gcc_qge): Likewise.
	(__gcc_qle): Likewise.
	(__gcc_stoq): Likewise.
	(__gcc_dtoq): Likewise.
	(__gcc_itoq): Likewise.
	(__gcc_utoq): Likewise.
	(__gcc_qunord): Likewise.
	* config/rs6000/_mulkc3.c (toplevel): Include soft-fp.h and
	quad-float128.h for the definitions.
	(COPYSIGN): Use the f128 version instead of the q version.
	(INFINITY): Likewise.
	(__mulkc3): Use TFmode/TCmode for float128 scalar/complex types.
	* config/rs6000/_divkc3.c (toplevel): Include soft-fp.h and
	quad-float128.h for the definitions.
	(COPYSIGN): Use the f128 version instead of the q version.
	(INFINITY): Likewise.
	(FABS): Likewise.
	(__divkc3): Use TFmode/TCmode for float128 scalar/complex types.
	* config/rs6000/extendkftf2-sw.c (__extendkftf2_sw): Likewise.
	* config/rs6000/trunctfkf2-sw.c (__trunctfkf2_sw): Likewise.

From-SVN: r256354
      Michael Meissner committed
    • quad-float128.h (IBM128_TYPE): Explicitly use __ibm128, instead of trying to use long double. · d5eea0f7 
      2018-01-08  Michael Meissner  <meissner@linux.vnet.ibm.com>

	* config/rs6000/quad-float128.h (IBM128_TYPE): Explicitly use
	__ibm128, instead of trying to use long double.
	(CVT_FLOAT128_TO_IBM128): Use TFtype instead of __float128 to
	accomidate -mabi=ieeelongdouble multilibs.
	(CVT_IBM128_TO_FLOAT128): Likewise.
	* config/rs6000/ibm-ldouble.c (IBM128_TYPE): New macro to define
	the appropriate IBM extended double type.
	(__gcc_qadd): Change all occurances of long double to IBM128_TYPE.
	(__gcc_qsub): Likewise.
	(__gcc_qmul): Likewise.
	(__gcc_qdiv): Likewise.
	(pack_ldouble): Likewise.
	(__gcc_qneg): Likewise.
	(__gcc_qeq): Likewise.
	(__gcc_qne): Likewise.
	(__gcc_qge): Likewise.
	(__gcc_qle): Likewise.
	(__gcc_stoq): Likewise.
	(__gcc_dtoq): Likewise.
	(__gcc_itoq): Likewise.
	(__gcc_utoq): Likewise.
	(__gcc_qunord): Likewise.
	* config/rs6000/_mulkc3.c (toplevel): Include soft-fp.h and
	quad-float128.h for the definitions.
	(COPYSIGN): Use the f128 version instead of the q version.
	(INFINITY): Likewise.
	(__mulkc3): Use TFmode/TCmode for float128 scalar/complex types.
	* config/rs6000/_divkc3.c (toplevel): Include soft-fp.h and
	quad-float128.h for the definitions.
	(COPYSIGN): Use the f128 version instead of the q version.
	(INFINITY): Likewise.
	(FABS): Likewise.
	(__divkc3): Use TFmode/TCmode for float128 scalar/complex types.
	* config/rs6000/extendkftf2-sw.c (__extendkftf2_sw): Likewise.
	* config/rs6000/trunctfkf2-sw.c (__trunctfkf2_sw): Likewise.

From-SVN: r256353
      Michael Meissner committed
    • expr.c (gfc_check_pointer_assign): Fix typo in comment. · a4f759de 
      2018-01-08  Steven G. Kargl  <kargl@gcc.gnu.org>

	* expr.c (gfc_check_pointer_assign): Fix typo in comment.

From-SVN: r256352
      Steven G. Kargl committed
    • rs6000-string.c (do_load_for_compare_from_addr): New function. · 5ec3397e 
      2018-01-08  Aaron Sawdey  <acsawdey@linux.vnet.ibm.com>

	* config/rs6000/rs6000-string.c (do_load_for_compare_from_addr): New
	function.
	(do_ifelse): New function.
	(do_isel): New function.
	(do_sub3): New function.
	(do_add3): New function.
	(do_load_mask_compare): New function.
	(do_overlap_load_compare): New function.
	(expand_compare_loop): New function.
	(expand_block_compare): Call expand_compare_loop() when appropriate.
	* config/rs6000/rs6000.opt (-mblock-compare-inline-limit): Change
	option description.
	(-mblock-compare-inline-loop-limit): New option.

From-SVN: r256351
      Aaron Sawdey committed
    • re PR rtl-optimization/81308 (ICE in calc_dfs_tree, at dominance.c:458) · 5a2a87e1 
      	PR rtl-optimizatin/81308
	* tree-switch-conversion.c (cfg_altered): New file scoped static.
	(process_switch): If group_case_labels makes a change, then set
	cfg_altered.
	(pass_convert_switch::execute): If a switch is converted, then
	set cfg_altered.  Return TODO_cfg_cleanup if cfg_altered is true.

	PR rtl-optimizatin/81308
	* g++.dg/pr81308-1.C: New test.
	* g++.dg/pr81308-2.C: New test.

From-SVN: r256349
      Jeff Law committed
    • re PR rtl-optimization/81308 (ICE in calc_dfs_tree, at dominance.c:458) · b9a4d2ba 
      	PR rtl-optimization/81308
	* recog.c (split_all_insns): Conditionally cleanup the CFG after
	splitting insns.

From-SVN: r256348
      Jeff Law committed
    • rs6000.c (rs6000_legitimate_combined_insn): Updated with the new names of the… · 7f047768 
      rs6000.c (rs6000_legitimate_combined_insn): Updated with the new names of the branch decrement patterns...

* config/rs6000/rs6000.c (rs6000_legitimate_combined_insn): Updated
	with the new names of the branch decrement patterns, and added the
	names of the branch decrement conditional patterns.

From-SVN: r256347
      Aaron Sawdey committed
    • PR target/83663 - Revert r255946 · 647c61f1 
      gcc/

2018-01-08  Vidya Praveen  <vidyapraveen@arm.com>

	PR target/83663 - Revert r255946
	* config/aarch64/aarch64.c (aarch64_expand_vector_init): Modify code
	generation for cases where splatting a value is not useful.
	* simplify-rtx.c (simplify_ternary_operation): Simplify vec_merge
	across a vec_duplicate and a paradoxical subreg forming a vector
	mode to a vec_concat.

gcc/testsuite/

2018-01-08  Vidya Praveen  <vidyapraveen@arm.com>

	PR target/83663 - Revert r255946
	* gcc.target/aarch64/vect-slp-dup.c: New.

From-SVN: r256346
      Vidya Praveen committed
    • [arm] Add -march=armv8.3-a and dotprod multilib selection rules · a00a4222 
      We don't have the t-aprofile, t-multilib and t-arm-elf mapping
rules for multilibs when using the variants of -march=armv8.3-a
and the dotproduct extension.
This patch adds them. -march=armv8.3-a behaves in the same
way as -march=armv8.2-a in this regard.

Bootstrapped and tested with the aprofile multilib list.
Checked that --print-multi-directory gives sensible results
with armv8.3-a options and extensions.
I've also added some armv8.3-a, fp16 and dotprod
combination tests to multilib.exp

	* config/arm/t-aprofile (MULTILIB_MATCHES): Add mapping rules for
	-march=armv8.3-a variants.
	* config/arm/t-multilib: Likewise.
	* config/arm/t-arm-elf: Likewise.  Handle dotprod extension.

	* gcc.target/arm/multilib.exp: Add fp16, dotprod and armv8.3-a
	combination tests.

From-SVN: r256345
      Kyrylo Tkachov committed
    • rs6000.md (cceq_ior_compare): Remove * so I can use it to generate rtl. · 8f2c6023 
      2018-01-08  Aaron Sawdey  <acsawdey@linux.vnet.ibm.com>

	* config/rs6000/rs6000.md (cceq_ior_compare): Remove * so I can use it
	to generate rtl.
	(cceq_ior_compare_complement): Give it a name so I can use it, and
	change boolean_or_operator predicate to boolean_operator so it can
	be used to generate a crand.
	(eqne): New code iterator.
	(bd/bd_neg): New code_attrs.
	(<bd>_<mode>): New name for ctr<mode>_internal[12] now combined into
	a single define_insn.
	(<bd>tf_<mode>): A new insn pattern for the conditional form branch
	decrement (bdnzt/bdnzf/bdzt/bdzf).
	* config/rs6000/rs6000.c (rs6000_legitimate_combined_insn): Updated
	with the new names of the branch decrement patterns, and added the
	names of the branch decrement conditional patterns.

From-SVN: r256344
      Aaron Sawdey committed
    • re PR tree-optimization/83563 ([graphite] ICE: Segmentation fault (in instantiate_scev_r)) · b33086c0 
      2018-01-08  Richard Biener  <rguenther@suse.de>

	PR tree-optimization/83563
	* graphite.c (canonicalize_loop_closed_ssa_form): Reset the SCEV
	cache.

	* gcc.dg/graphite/pr83563.c: New testcase.

From-SVN: r256343
      Richard Biener committed
    • re PR c++/83713 (ICE in do_narrow at gcc/convert.c:474) · 87c4dace 
      2018-01-08  Richard Biener  <rguenther@suse.de>

	PR middle-end/83713
	* convert.c (do_narrow): Properly guard TYPE_OVERFLOW_WRAPS checks.

	* g++.dg/torture/pr83713.C: New testcase.

From-SVN: r256341
      Richard Biener committed
    • Xfail ssa-dom-cse-2.c for nvptx · 960c02b8 
      2018-01-08  Tom de Vries  <tom@codesourcery.com>

	* gcc.dg/tree-ssa/ssa-dom-cse-2.c: Xfail scan for nvptx.

From-SVN: r256340
      Tom de Vries committed
    • re PR tree-optimization/83685 (ICE: SSA corruption) · e207c079 
      2018-01-08  Richard Biener  <rguenther@suse.de>

	PR tree-optimization/83685
	* tree-ssa-pre.c (create_expression_by_pieces): Do not insert
	references to abnormals.

	* gcc.dg/torture/pr83685.c: New testcase.

From-SVN: r256339
      Richard Biener committed
    • re PR lto/83719 (ICE (segfault) in hash_table<indirect_string_hasher, xcallocator>::elements()) · 131a0e78 
      2018-01-08  Richard Biener  <rguenther@suse.de>

	PR lto/83719
	* dwarf2out.c (output_indirect_strings): Handle empty
	skeleton_debug_str_hash.
	(dwarf2out_early_finish): Index strings for -gsplit-dwarf.

	* gcc.dg/lto/pr83719_0.c: New testcase.

From-SVN: r256338
      Richard Biener committed
    • PR 78534 Regression on 32-bit targets · 4135a21f 
      By switching from int to size_t in order to handle larger values,
r256322 introduced a bug that manifested itself on 32-bit
targets. Fixed by using the correct type to store the result of a
next_array_record call.

Regtested on x86_64-pc-linux-gnu and i686-pc-linux-gnu, committed to
trunk as obvious.

libgfortran/ChangeLog:

2018-01-08  Janne Blomqvist  <jb@gcc.gnu.org>

	PR 78534, bugfix for r256322
	* io/transfer.c (next_record_w): Use correct type for return value
	of next_array_record.

From-SVN: r256337
      Janne Blomqvist committed
    • Require stack size for some test-cases · 4c035a23 
      2018-01-08  Tom de Vries  <tom@codesourcery.com>

	* gcc.dg/graphite/interchange-7.c: Add dg-require-stack-size.
	* gcc.dg/graphite/run-id-1.c: Same.
	* gcc.dg/tree-ssa/loop-interchange-4.c: Same.

From-SVN: r256336
      Tom de Vries committed
    • re PR fortran/83611 ([PDT] Assignment of parameterized types causes double free error in runtime) · 0b627b58 
      2018-01-08  Paul Thomas  <pault@gcc.gnu.org>

	PR fortran/83611
	* decl.c (gfc_get_pdt_instance): If parameterized arrays have
	an initializer, convert the kind parameters and add to the
	component if the instance.
	* trans-array.c (structure_alloc_comps): Add 'is_pdt_type' and
	use it with case COPY_ALLOC_COMP. Call 'duplicate_allocatable'
	for parameterized arrays. Clean up typos in comments. Convert
	parameterized array initializers and copy into the array.
	* trans-expr.c (gfc_trans_scalar_assign): Do a deep copy for
	parameterized types.
	*trans-stmt.c (trans_associate_var): Deallocate associate vars
	as necessary, when they are PDT function results for example.

	PR fortran/83731
	* trans-array.c (structure_alloc_comps): Only compare len parms
	when they are declared explicitly.

2018-01-08  Paul Thomas  <pault@gcc.gnu.org>

	PR fortran/83611
	* gfortran.dg/pdt_15.f03 : Bump count of 'n.data = 0B' to 8.
	* gfortran.dg/pdt_26.f03 : Bump count of '_malloc' to 9.
	* gfortran.dg/pdt_27.f03 : New test.

	PR fortran/83731
	* gfortran.dg/pdt_28.f03 : New test.

From-SVN: r256335
      Paul Thomas committed
    • [ARC] Revamp trampoline implementation · efcc2e30 
      The new implementation attempts to clean up the existing trampoline
implementation for ARC making it to work for linux type of systems.

gcc/
2018-01-08  Claudiu Zissulescu  <claziss@synopsys.com>

        * config/arc/arc.c (TARGET_TRAMPOLINE_ADJUST_ADDRESS): Delete.
        (emit_store_direct): Likewise.
        (arc_trampoline_adjust_address): Likewise.
        (arc_asm_trampoline_template): New function.
        (arc_initialize_trampoline): Use asm_trampoline_template.
        (TARGET_ASM_TRAMPOLINE_TEMPLATE): Define.
        * config/arc/arc.h (TRAMPOLINE_SIZE): Adjust to 16.
        *config/arc/arc.md (flush_icache): Delete pattern.

From-SVN: r256334
      Claudiu Zissulescu committed
    • [ARC] Enable unaligned access. · 85e5629f 
      Use munaligned-access to control if we can have unaligned accesses.  For ARC
HS family unaligned access is always on.

2018-01-08  Claudiu Zissulescu  <claziss@synopsys.com>

	* config/arc/arc-c.def (__ARC_UNALIGNED__): New define.
	* config/arc/arc.h (STRICT_ALIGNMENT): Control this macro using
	munaligned-access.

From-SVN: r256333
      Claudiu Zissulescu committed
    • Require alloca for some test-cases · b5da8f94 
      2018-01-08  Tom de Vries  <tom@codesourcery.com>

	* c-c++-common/builtins.c: Require effective target alloca.
	* gcc.dg/Wrestrict.c: Same.
	* gcc.dg/tree-ssa/loop-interchange-15.c: Same.

From-SVN: r256332
      Tom de Vries committed
    • epiphany: Enable Ada run-time build · 34113d65 
      gcc/

	PR target/83681
	* config/epiphany/epiphany.h (make_pass_mode_switch_use): Guard
	by not USED_FOR_TARGET.
	(make_pass_resolve_sw_modes): Likewise.

From-SVN: r256331
      Sebastian Huber committed
    • nios2: Enable Ada run-time build · 05122129 
      gcc/
	* config/nios2/nios2.h (nios2_section_threshold): Guard by not
	USED_FOR_TARGET.

From-SVN: r256330
      Sebastian Huber committed
    • re PR tree-optimization/83580 (Wrong code caused by vectorization) · 3e1b80ff 
      2018-01-08  Richard Biener  <rguenther@suse.de>

	PR middle-end/83580
	* tree-data-ref.c (split_constant_offset): Remove STRIP_NOPS.

	* gcc.dg/torture/pr83580.c: New testcase.

From-SVN: r256329
      Richard Biener committed