56b1c60e41
Merge from HSA branch to trunk 2016-11-23 Martin Jambor <mjambor@suse.cz> Martin Liska <mliska@suse.cz> gcc/ * hsa-builtins.def: New file. * Makefile.in (BUILTINS_DEF): Add hsa-builtins.def dependency. * builtins.def: Include hsa-builtins.def. (DEF_HSA_BUILTIN): New macro. * dumpfile.h (OPTGROUP_OPENMP): Define. * dumpfile.c (optgroup_options): Added OPTGROUP_OPENMP. * gimple.h (gf_mask): Added elements GF_OMP_FOR_GRID_INTRA_GROUP and GF_OMP_FOR_GRID_GROUP_ITER. (gimple_omp_for_grid_phony): Added checking assert. (gimple_omp_for_set_grid_phony): Likewise. (gimple_omp_for_grid_intra_group): New function. (gimple_omp_for_set_grid_intra_group): Likewise. (gimple_omp_for_grid_group_iter): Likewise. (gimple_omp_for_set_grid_group_iter): Likewise. * omp-low.c (check_omp_nesting_restrictions): Allow GRID loop where previosuly only distribute loop was permitted. (lower_lastprivate_clauses): Allow non tcc_comparison predicates. (grid_get_kernel_launch_attributes): Support multiple HSA grid dimensions. (grid_expand_omp_for_loop): Likewise and also support standalone distribute constructs. New parameter INTRA_GROUP, updated both users. (grid_expand_target_grid_body): Support standalone distribute constructs. (pass_data_expand_omp): Changed optinfo_flags to OPTGROUP_OPENMP. (pass_data_expand_omp_ssa): Likewise. (pass_data_omp_device_lower): Likewsie. (pass_data_lower_omp): Likewise. (pass_data_diagnose_omp_blocks): Likewise. (pass_data_oacc_device_lower): Likewise. (pass_data_omp_target_link): Likewise. (grid_lastprivate_predicate): New function. (lower_omp_for_lastprivate): Call grid_lastprivate_predicate for gridified loops. (lower_omp_for): Support standalone distribute constructs. (grid_prop): New type. (grid_safe_assignment_p): Check for assignments to group_sizes, new parameter GRID. (grid_seq_only_contains_local_assignments): New parameter GRID, pass it to callee. (grid_find_single_omp_among_assignments_1): Likewise, improve missed optimization info messages. (grid_find_single_omp_among_assignments): Likewise. (grid_find_ungridifiable_statement): Do not bail out for SIMDs. (grid_parallel_clauses_gridifiable): New function. (grid_inner_loop_gridifiable_p): Likewise. (grid_dist_follows_simple_pattern): Likewise. (grid_gfor_follows_tiling_pattern): Likewise. (grid_call_permissible_in_distribute_p): Likewise. (grid_handle_call_in_distribute): Likewise. (grid_dist_follows_tiling_pattern): Likewise. (grid_target_follows_gridifiable_pattern): Support standalone distribute constructs. (grid_var_segment): New enum. (grid_mark_variable_segment): New function. (grid_copy_leading_local_assignments): Call grid_mark_variable_segment if a new argument says so. (grid_process_grid_body): New function. (grid_eliminate_combined_simd_part): Likewise. (grid_mark_tiling_loops): Likewise. (grid_mark_tiling_parallels_and_loops): Likewise. (grid_process_kernel_body_copy): Support standalone distribute constructs. (grid_attempt_target_gridification): New grid variable holding overall gridification state. Support standalone distribute constructs and collapse clauses. * doc/optinfo.texi (Optimization groups): Document OPTGROUP_OPENMP. * hsa.h (hsa_bb): Add method method append_phi. (hsa_insn_br): Renamed to hsa_insn_cbr, renamed all occurences in all files too. (hsa_insn_br): New class, now the ancestor of hsa_incn_cbr. (is_a_helper <hsa_insn_br *>::test): New function. (is_a_helper <hsa_insn_cbr *>::test): Adjust to only cover conditional branch instructions. (hsa_insn_signal): Make a direct descendant of hsa_insn_basic. Add memorder constructor parameter and m_memory_order and m_signalop member variables. (hsa_insn_queue): Changed constructor parameters to common form. Added m_segment and m_memory_order member variables. (hsa_summary_t): Add private member function process_gpu_implementation_attributes. (hsa_function_summary): Rename m_binded_function to m_bound_function. (hsa_insn_basic_p): Remove typedef. (hsa_op_with_type): Change hsa_insn_basic_p into plain pointers. (hsa_op_reg_p): Remove typedef. (hsa_function_representation): Change hsa_op_reg_p into plain pointers. (hsa_insn_phi): Removed new and delete operators. (hsa_insn_br): Likewise. (hsa_insn_cbr): Likewise. (hsa_insn_sbr): Likewise. (hsa_insn_cmp): Likewise. (hsa_insn_mem): Likewise. (hsa_insn_atomic): Likewise. (hsa_insn_signal): Likewise. (hsa_insn_seg): Likewise. (hsa_insn_call): Likewise. (hsa_insn_arg_block): Likewise. (hsa_insn_comment): Likewise. (hsa_insn_srctype): Likewise. (hsa_insn_packed): Likewise. (hsa_insn_cvt): Likewise. (hsa_insn_alloca): Likewise. * hsa.c (hsa_destroy_insn): Also handle instances of hsa_insn_br. (process_gpu_implementation_attributes): New function. (link_functions): Move some functionality into it. Adjust after renaming m_binded_functions to m_bound_functions. (hsa_insn_basic::op_output_p): Add BRIG_OPCODE_DEBUGTRAP to the list of instructions with no output registers. (get_in_type): Return this if it is a register of matching size. (hsa_get_declaration_name): Moved to... * hsa-gen.c (hsa_get_declaration_name): ...here. Allocate temporary string on an obstack instead from ggc. (query_hsa_grid): Renamed to query_hsa_grid_dim, reimplemented, cut down to two overloads. (hsa_allocp_operand_address): Removed. (hsa_allocp_operand_immed): Likewise. (hsa_allocp_operand_reg): Likewise. (hsa_allocp_operand_code_list): Likewise. (hsa_allocp_operand_operand_list): Likewise. (hsa_allocp_inst_basic): Likewise. (hsa_allocp_inst_phi): Likewise. (hsa_allocp_inst_mem): Likewise. (hsa_allocp_inst_atomic): Likewise. (hsa_allocp_inst_signal): Likewise. (hsa_allocp_inst_seg): Likewise. (hsa_allocp_inst_cmp): Likewise. (hsa_allocp_inst_br): Likewise. (hsa_allocp_inst_sbr): Likewise. (hsa_allocp_inst_call): Likewise. (hsa_allocp_inst_arg_block): Likewise. (hsa_allocp_inst_comment): Likewise. (hsa_allocp_inst_queue): Likewise. (hsa_allocp_inst_srctype): Likewise. (hsa_allocp_inst_packed): Likewise. (hsa_allocp_inst_cvt): Likewise. (hsa_allocp_inst_alloca): Likewise. (hsa_allocp_bb): Likewise. (hsa_obstack): New. (hsa_init_data_for_cfun): Initialize obstack. (hsa_deinit_data_for_cfun): Release memory of the obstack. (hsa_op_immed::operator new): Use obstack instead of object_allocator. (hsa_op_reg::operator new): Likewise. (hsa_op_address::operator new): Likewise. (hsa_op_code_list::operator new): Likewise. (hsa_op_operand_list::operator new): Likewise. (hsa_insn_basic::operator new): Likewise. (hsa_insn_phi::operator new): Likewise. (hsa_insn_br::operator new): Likewise. (hsa_insn_sbr::operator new): Likewise. (hsa_insn_cmp::operator new): Likewise. (hsa_insn_mem::operator new): Likewise. (hsa_insn_atomic::operator new): Likewise. (hsa_insn_signal::operator new): Likewise. (hsa_insn_seg::operator new): Likewise. (hsa_insn_call::operator new): Likewise. (hsa_insn_arg_block::operator new): Likewise. (hsa_insn_comment::operator new): Likewise. (hsa_insn_srctype::operator new): Likewise. (hsa_insn_packed::operator new): Likewise. (hsa_insn_cvt::operator new): Likewise. (hsa_insn_alloca::operator new): Likewise. (hsa_init_new_bb): Likewise. (hsa_bb::append_phi): New function. (gen_hsa_phi_from_gimple_phi): Use it. (get_symbol_for_decl): Fix dinstinguishing between global and local functions. Put local variables into a segment according to their attribute or static flag, if there is one. (hsa_insn_br::hsa_insn_br): New. (hsa_insn_br::operator new): Likewise. (hsa_insn_cbr::hsa_insn_cbr): Set width via ancestor constructor. (query_hsa_grid_nodim): New function. (multiply_grid_dim_characteristics): Likewise. (gen_get_num_threads): Likewise. (gen_get_num_teams): Reimplemented. (gen_get_team_num): Likewise. (gen_hsa_insns_for_known_library_call): Updated calls to the above helper functions. (get_memory_order_name): Removed. (get_memory_order): Likewise. (hsa_memorder_from_tree): New function. (gen_hsa_ternary_atomic_for_builtin): Renamed to gen_hsa_atomic_for_builtin, can also create signals. (gen_hsa_insns_for_call): Handle many new builtins. Adjust to use hsa_memory_order_from_tree and gen_hsa_atomic_for_builtin. (hsa_insn_atomic): Fix function comment. (hsa_insn_signal::hsa_insn_signal): Fix comment. Update call to ancestor constructor and initialization of new member variables. (hsa_insn_queue::hsa_insn_queue): Added initialization of new member variables. (hsa_get_host_function): Handle functions with no bound CPU implementation. Fix binded to bound. (get_brig_function_name): Likewise. (HSA_SORRY_ATV): Remove semicolon after macro. (HSA_SORRY_AT): Likewise. (omp_simple_builtin::generate): Add missing semicolons. (hsa_insn_phi::operator new): Removed. (hsa_insn_br::operator new): Likewise. (hsa_insn_cbr::operator new): Likewise. (hsa_insn_sbr::operator new): Likewise. (hsa_insn_cmp::operator new): Likewise. (hsa_insn_mem::operator new): Likewise. (hsa_insn_atomic::operator new): Likewise. (hsa_insn_signal::operator new): Likewise. (hsa_insn_seg::operator new): Likewise. (hsa_insn_call::operator new): Likewise. (hsa_insn_arg_block::operator new): Likewise. (hsa_insn_comment::operator new): Likewise. (hsa_insn_srctype::operator new): Likewise. (hsa_insn_packed::operator new): Likewise. (hsa_insn_cvt::operator new): Likewise. (hsa_insn_alloca::operator new): Likewise. (get_symbol_for_decl): Accept CONST_DECLs, put them to readonly segment. (gen_hsa_addr): Also process CONST_DECLs. (gen_hsa_addr_insns): Process CONST_DECLs by creating private copies. (gen_hsa_unary_operation): Make sure the function does not use bittype source type for firstbit and lastbit operations. (gen_hsa_popcount_to_dest): Make sure the function uses a bittype source type. * hsa-brig.c (emit_insn_operands): Cope with zero operands in an instruction. (emit_branch_insn): Renamed to emit_cond_branch_insn. Emit the width stored in the class. (emit_generic_branch_insn): New function. (emit_insn): Call emit_generic_branch_insn. (emit_signal_insn): Remove obsolete comment. Update member variable name, pick a type according to profile. (emit_alloca_insn): Remove obsolete comment. (emit_atomic_insn): Likewise. (emit_queue_insn): Get segment and memory order from the IR object. (hsa_brig_section): Make allocate_new_chunk, chunks and cur_chunk provate, add a default NULL parameter to add method. (hsa_brig_section::add): Added a new parameter, store pointer to output data there if it is non-NULL. (emit_function_directives): Use this new parameter instead of calculating the pointer itself, fix function comment. (hsa_brig_emit_function): Add forgotten endian conversion. (hsa_output_kernels): Remove unnecessary building of kernel_dependencies_vector_type. (emit_immediate_operand): Declare. (emit_directive_variable): Also emit initializers of CONST_DECLs. (gen_hsa_insn_for_internal_fn_call): Also handle IFN_RSQRT. (verify_function_arguments): Properly detect variadic arguments. * hsa-dump.c (hsa_width_specifier_name): New function. (dump_hsa_insn_1): Dump generic branch instructions, update signal member variable name. Special dumping for queue objects. * ipa-hsa.c (process_hsa_functions): Adjust after renaming m_binded_functions to m_bound_functions. Copy externally visible flag to the node. (ipa_hsa_write_summary): Likewise. (ipa_hsa_read_section): Likewise. gcc/fortran/ * f95-lang.c (DEF_HSA_BUILTIN): New macro. gcc/testsuite/ * c-c++-common/gomp/gridify-1.c: Update scan string. * gfortran.dg/gomp/gridify-1.f90: Likewise. * c-c++-common/gomp/gridify-2.c: New test. * c-c++-common/gomp/gridify-3.c: Likewise. libgomp/ * testsuite/libgomp.hsa.c/bits-insns.c: New test. * testsuite/libgomp.hsa.c/tiling-1.c: Likewise. * testsuite/libgomp.hsa.c/tiling-2.c: Likewise. Co-Authored-By: Martin Liska <mliska@suse.cz> From-SVN: r242761
74 lines
1.8 KiB
C
74 lines
1.8 KiB
C
#include <math.h>
|
|
|
|
#define N 12
|
|
|
|
int main()
|
|
{
|
|
unsigned int arguments[N] = {0u, 1u, 2u, 3u, 111u, 333u, 444u, 0x80000000u, 0x0000ffffu, 0xf0000000u, 0xff000000u, 0xffffffffu};
|
|
int clrsb[N] = {};
|
|
int clz[N] = {};
|
|
int ctz[N] = {};
|
|
int ffs[N] = {};
|
|
int parity[N] = {};
|
|
int popcount[N] = {};
|
|
|
|
int ref_clrsb[N] = {};
|
|
int ref_clz[N] = {};
|
|
int ref_ctz[N] = {};
|
|
int ref_ffs[N] = {};
|
|
int ref_parity[N] = {};
|
|
int ref_popcount[N] = {};
|
|
|
|
for (unsigned i = 0; i < N; i++)
|
|
{
|
|
ref_clrsb[i] = __builtin_clrsb (arguments[i]);
|
|
ref_clz[i] = __builtin_clz (arguments[i]);
|
|
ref_ctz[i] = __builtin_ctz (arguments[i]);
|
|
ref_ffs[i] = __builtin_ffs (arguments[i]);
|
|
ref_parity[i] = __builtin_parity (arguments[i]);
|
|
ref_popcount[i] = __builtin_popcount (arguments[i]);
|
|
}
|
|
|
|
#pragma omp target map(from:clz, ctz, ffs, parity, popcount)
|
|
{
|
|
for (unsigned i = 0; i < N; i++)
|
|
{
|
|
clrsb[i] = __builtin_clrsb (arguments[i]);
|
|
clz[i] = __builtin_clz (arguments[i]);
|
|
ctz[i] = __builtin_ctz (arguments[i]);
|
|
ffs[i] = __builtin_ffs (arguments[i]);
|
|
parity[i] = __builtin_parity (arguments[i]);
|
|
popcount[i] = __builtin_popcount (arguments[i]);
|
|
}
|
|
}
|
|
|
|
for (unsigned i = 0; i < N; i++)
|
|
if (ref_clrsb[i] != clrsb[i])
|
|
__builtin_abort ();
|
|
|
|
/* CLZ of zero is undefined for zero. */
|
|
for (unsigned i = 1; i < N; i++)
|
|
if (ref_clz[i] != clz[i])
|
|
__builtin_abort ();
|
|
|
|
/* Likewise for ctz */
|
|
for (unsigned i = 1; i < N; i++)
|
|
if (ref_ctz[i] != ctz[i])
|
|
__builtin_abort ();
|
|
|
|
for (unsigned i = 0; i < N; i++)
|
|
if (ref_ffs[i] != ffs[i])
|
|
__builtin_abort ();
|
|
|
|
for (unsigned i = 0; i < N; i++)
|
|
if (ref_parity[i] != parity[i])
|
|
__builtin_abort ();
|
|
|
|
for (unsigned i = 0; i < N; i++)
|
|
if (ref_popcount[i] != popcount[i])
|
|
__builtin_abort ();
|
|
|
|
return 0;
|
|
}
|
|
|