1. 30 Aug, 2013 3 commits
  2. 29 Aug, 2013 15 commits
  3. 28 Aug, 2013 17 commits
  4. 27 Aug, 2013 5 commits
    • ipa-prop.h (ipa_pass_through_data): New field type_preserved. · b8f6e610
      2013-08-27  Martin Jambor  <mjambor@suse.cz>
      
      	* ipa-prop.h (ipa_pass_through_data): New field type_preserved.
      	(ipa_ancestor_jf_data): Likewise.
      	(ipa_get_jf_pass_through_agg_preserved): Fix comment typo.
      	(ipa_get_jf_pass_through_type_preserved): New function.
      	(ipa_get_jf_ancestor_agg_preserved): Fix comment typo.
      	(ipa_get_jf_ancestor_type_preserved): New function.
      	* ipa-cp.c (ipa_get_jf_pass_through_result): Honor type_preserved
      	flag.
      	(ipa_get_jf_ancestor_result): Likewise.
      	(propagate_vals_accross_pass_through): Use
      	ipa_get_jf_pass_through_result to do all the value mappings.
      	* ipa-prop.c (ipa_print_node_jump_functions_for_edge): Dump the
      	type_preserved flag.
      	(ipa_set_jf_cst_copy): New function.
      	(ipa_set_jf_simple_pass_through): Set the type_preserved flag.
      	(ipa_set_jf_arith_pass_through): Likewise.
      	(ipa_set_ancestor_jf): Likewise.
      	(compute_complex_assign_jump_func): Set type_preserved instead of
      	punting.
      	(ipa_compute_jump_functions_for_edge): Likewise.
      	(combine_known_type_and_ancestor_jfs): Honor type_preserved.
      	(update_jump_functions_after_inlining): Update type_preserved.
      	Explicitely create jump functions when combining one with
      	pass_through.
      	(ipa_write_jump_function): Stream the type_preserved flags.
      	(ipa_read_jump_function): Likewise.
      
      From-SVN: r202036
      Martin Jambor committed
    • Makefile.in (omp-low.o): Depend on $(TARGET_H). · 74bf76ed
      	* Makefile.in (omp-low.o): Depend on $(TARGET_H).
      	* cfgloop.h (struct loop): Add safelen, force_vect, simduid.
      	* function.h (struct function): Add has_force_vect_loops and
      	has_simduid_loops.
      	* gimple-pretty-print.c (dump_gimple_omp_for): Handle
      	GF_OMP_FOR_KIND*.
      	* gimple.c (gimple_build_omp_critical): Add KIND argument and
      	handle it.
      	* gimple.def: Update CLAUSES comments.
      	* gimple.h (enum gf_mask): Add GF_OMP_FOR_KIND_{FOR,SIMD}.
      	(gimple_build_omp_for): Add argument to prototype.
      	(gimple_omp_for_kind): New.
      	(gimple_omp_for_set_kind): New.
      	* gimplify.c (enum gimplify_omp_var_data): Add GOVD_LINEAR to
      	GOVD_DATA_SHARE_CLASS.
      	(enum omp_region_type): Add ORT_SIMD.
      	(gimple_add_tmp_var): Handle ORT_SIMD.
      	(gimplify_var_or_parm_decl): Same.
      	(is_gimple_stmt): Same.
      	(omp_firstprivatize_variable): Same.
      	(omp_add_variable): Only use splay_tree_insert if lookup failed.
      	(omp_notice_variable): Handle ORT_SIMD.
      	(omp_is_private): Add SIMD argument and handle it as well as
      	ORT_SIMD.
      	(omp_check_private): Handle ORT_SIMD.
      	(gimplify_scan_omp_clauses): Handle OMP_CLAUSE_LINEAR and
      	OMP_CLAUSE_SAFELEN.
      	(gimplify_adjust_omp_clauses_1): Handle GOVD_LINEAR.
      	Handle OMP_CLAUSE_LASTPRIVATE.
      	(gimplify_adjust_omp_clauses): Handle OMP_CLAUSE_LINEAR and
      	OMP_CLAUSE_SAFELEN.
      	(gimplify_omp_for): Handle OMP_SIMD and OMP_CLAUSE_LINEAR.
      	(gimplify_expr): Handle OMP_SIMD.
      	* internal-fn.c (expand_GOMP_SIMD_LANE): New.
      	(expand_GOMP_SIMD_VF): New.
      	(expand_GOMP_SIMD_LAST_LANE): New.
      	* internal-fn.def (GOMP_SIMD_LANE): New.
      	(GOMP_SIMD_VF): New.
      	(GOMP_SIMD_LAST_LANE): New.
      	* omp-low.c: Include target.h.
      	(extract_omp_for_data): Handle OMP_SIMD, OMP_CLAUSE_LINEAR,
      	OMP_CLAUSE_SAFELEN.
      	(check_omp_nesting_restrictions): Same.
      	(omp_max_vf): New.
      	(lower_rec_simd_input_clauses): New.
      	(lower_rec_input_clauses): Handle OMP_SIMD, GF_OMP_FOR_KIND_SIMD,
      	OMP_CLAUSE_LINEAR.
      	(lower_lastprivate_clauses): Handle OMP_CLAUSE_LINEAR,
      	GF_OMP_FOR_KIND_SIMD, OMP_SIMD.
      	(expand_omp_build_assign): New.
      	(expand_omp_for_init_counts): New.
      	(expand_omp_for_init_vars): New.
      	(extract_omp_for_update_vars): New.
      	(expand_omp_for_generic): Use expand_omp_for_{init,update}_vars
      	and rewrite accordingly.
      	(expand_omp_simd): New.
      	(expand_omp_for): Use expand_omp_simd.
      	(lower_omp_for_lastprivate): Unshare vinit when appropriate.
      	(lower_omp_for): Do not lower the body.
      	* tree-data-ref (get_references_in_stmt): Allow IFN_GOMP_SIMD_LANE
      	in their own loops.
      	* tree-flow.h (find_omp_clause): Remove prototype.
      	* tree-if-conv.c (main_tree_if_conversion): Run if doing if
      	conversion, forcing vectorization of the loop, or if
      	flag_tree_vectorize.
      	(gate_tree_if_conversion): Similarly.
      	* tree-inline.c (remap_gimple_stmt): Pass for kind argument to
      	gimple_build_omp_for.
      	(copy_cfg_body): set has_force_vect_loops and has_simduid_loops.
      	* tree-parloops (create_parallel_loop): Pass kind argument to
      	gimple_build_omp_for.
      	* tree-pretty-print.c (dump_omp_clause): Add cases for
      	OMP_CLAUSE_UNIFORM, OMP_CLAUSE_LINEAR, OMP_CLAUSE_SAFELEN,
      	OMP_CLAUSE__SIMDUID_.
      	(dump_generic_node): Handle OMP_SIMD.
      	* tree-ssa-ccp.c (likely_value): Handle IFN_GOMP_SIMD*.
      	* tree-ssa-loop-ivcanon.c (tree_unroll_loops_completely_1): Do not
      	unroll OMP_SIMD loops here.
      	* tree-ssa-loop.c (gate_tree_vectorize): Run if
      	has_force_vect_loops.
      	* tree-vect-data-refs.c (vect_analyze_data_ref_dependence): Handle
      	loop->safelen
      	(vect_analyze_data_refs): Handle simd loops.
      	* tree-vect-loop.c (vectorizable_live_operation): Handle
      	IFN_GOMP_SIMD*.
      	* tree-vect-stmts.c (vectorizable_call): Handle
      	IFN_GOMP_SIMD_LANE.
      	(vectorizable_store): Handle STMT_VINFO_SIMD_LANE_ACCESS_P.
      	(vectorizable_load): Same.
      	* tree-vectorizer.c: Include hash-table.h and
      	tree-ssa-propagate.h.
      	(struct simduid_to_vf): New.
      	(simduid_to_vf::hash): New.
      	(simduid_to-vf::equal): New.
      	(struct simd_array_to_simduid): New.
      	(simd_array_to_simduid::hash): New.
      	(simd_array_to_simduid::equal): New.
      	(adjust_simduid_builtins): New.
      	(struct note_simd_array_uses_struct): New.
      	(note_simd_array_uses_cb): New.
      	(note_simd_array_uses): New.
      	(vectorize_loops): Handle simd hints and adjust simd builtins
      	accordingly.
      	* tree-vectorizer.h (struct _stmt_vec_info): Add
      	simd_lane_access_p field.
      	(STMT_VINFO_SIMD_LANE_ACCESS_P): New macro.
      	* tree.c (omp_clause_num_ops): Add entries for OMP_CLAUSE_LINEAR,
      	OMP_CLAUSE_SAFELEN, OMP_CLAUSE__SIMDUID_, OMP_CLAUSE_UNIFORM.
      	(omp_clause_code_name): Same.
      	(walk_tree_1): Handle OMP_CLAUSE_UNIFORM, OMP_CLAUSE_SAFELEN,
      	OMP_CLAUSE__SIMDUID_, OMP_CLAUSE_LINEAR.
      	* tree.def (OMP_SIMD): New entry.
      	* tree.h (enum omp_clause_code): Add entries for
      	OMP_CLAUSE_LINEAR, OMP_CLAUSE_UNIFORM, OMP_CLAUSE_SAFELEN,
      	OMP_CLAUSE__SIMDUID_.
      	(OMP_CLAUSE_DECL): Adjust range for new clauses.
      	(OMP_CLAUSE_LINEAR_NO_COPYIN): New.
      	(OMP_CLAUSE_LINEAR_NO_COPYOUT): New.
      	(OMP_CLAUSE_LINEAR_STEP): New.
      	(OMP_CLAUSE_SAFELEN_EXPR): New.
      	(OMP_CLAUSE__SIMDUID__DECL): New.
      	(find_omp_clause): New prototype.
      cp/
      	* cp-tree.h (CP_OMP_CLAUSE_INFO): Adjust range for new clauses.
      
      Co-Authored-By: Aldy Hernandez <aldyh@redhat.com>
      
      From-SVN: r202029
      Jakub Jelinek committed
    • Update Haswell processor detection · d0cf4e84
      	* config/i386/driver-i386.c (host_detect_local_cpu): Update
      	Haswell processor detection.
      
      From-SVN: r202028
      H.J. Lu committed
    • re PR target/57927 (-march=core-avx2 different than -march=native on INTEL Haswell (i7-4700K)) · 992592ec
      	PR target/57927
      	* config/i386/driver-i386.c (host_detect_local_cpu): Add detection
      	of Ivy Bridge and Haswell processors.  Assume core-avx2 for unknown
      	AVX2 capable processors.
      
      From-SVN: r202026
      Christian Widmer committed
    • arm_neon.h: Replace all inline asm implementations of vget_low_* with implementations in... · 9116eb22
      2013-08-27  Tejas Belagod  <tejas.belagod@arm.com>
      
              * config/aarch64/arm_neon.h: Replace all inline asm implementations
              of vget_low_* with implementations in terms of other intrinsics.
      
      From-SVN: r202023
      Tejas Belagod committed