diff options
author | Caroline Tice <cmtice@google.com> | 2016-04-08 17:51:51 +0000 |
---|---|---|
committer | Caroline Tice <cmtice@google.com> | 2016-04-08 17:51:51 +0000 |
commit | 0ad57cd327762de2a39165ad4496a87f2e5a7248 (patch) | |
tree | 95acce4cd1f8da37b7ed1e6b6e64b88e703bb7cb | |
parent | 734219f1f4227f2d25ea2df9abfc879285c5df13 (diff) |
Add files that previous commit (GCC unification)
forgot to 'svn add' before.
git-svn-id: https://gcc.gnu.org/svn/gcc/branches/google/gcc-4_9-mobile@234836 138bc75d-0d04-0410-961f-82ee72b054a4
-rw-r--r-- | gcc/config/arm/cortex-a57.md | 798 | ||||
-rw-r--r-- | gcc/testsuite/gcc.c-torture/compile/pr65735.c | 21 | ||||
-rw-r--r-- | gcc/testsuite/gcc.dg/tree-ssa/pr65447.c | 54 | ||||
-rw-r--r-- | gcc/testsuite/gcc.dg/tree-ssa/scev-10.c | 21 | ||||
-rw-r--r-- | gcc/testsuite/gcc.dg/tree-ssa/scev-8.c | 62 | ||||
-rw-r--r-- | gcc/testsuite/gcc.dg/tree-ssa/scev-9.c | 21 | ||||
-rw-r--r-- | gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-10.c | 24 | ||||
-rw-r--r-- | gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-6.c | 43 | ||||
-rw-r--r-- | gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-7.c | 127 | ||||
-rw-r--r-- | gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-8.c | 440 | ||||
-rw-r--r-- | gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-9.c | 50 | ||||
-rw-r--r-- | gcc/testsuite/gcc.dg/vect/pr48052.c | 26 |
12 files changed, 1687 insertions, 0 deletions
diff --git a/gcc/config/arm/cortex-a57.md b/gcc/config/arm/cortex-a57.md new file mode 100644 index 00000000000..65c186b99a3 --- /dev/null +++ b/gcc/config/arm/cortex-a57.md @@ -0,0 +1,798 @@ +;; ARM Cortex-A57 pipeline description +;; Copyright (C) 2014-2015 Free Software Foundation, Inc. +;; +;; This file is part of GCC. +;; +;; GCC is free software; you can redistribute it and/or modify it +;; under the terms of the GNU General Public License as published by +;; the Free Software Foundation; either version 3, or (at your option) +;; any later version. +;; +;; GCC is distributed in the hope that it will be useful, but +;; WITHOUT ANY WARRANTY; without even the implied warranty of +;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +;; General Public License for more details. +;; +;; You should have received a copy of the GNU General Public License +;; along with GCC; see the file COPYING3. If not see +;; <http://www.gnu.org/licenses/>. + +(define_automaton "cortex_a57") + +(define_attr "cortex_a57_neon_type" + "neon_abd, neon_abd_q, neon_arith_acc, neon_arith_acc_q, + neon_arith_basic, neon_arith_complex, + neon_reduc_add_acc, neon_multiply, neon_multiply_q, + neon_multiply_long, neon_mla, neon_mla_q, neon_mla_long, + neon_sat_mla_long, neon_shift_acc, neon_shift_imm_basic, + neon_shift_imm_complex, + neon_shift_reg_basic, neon_shift_reg_basic_q, neon_shift_reg_complex, + neon_shift_reg_complex_q, neon_fp_negabs, neon_fp_arith, + neon_fp_arith_q, neon_fp_reductions_q, neon_fp_cvt_int, + neon_fp_cvt_int_q, neon_fp_cvt16, neon_fp_minmax, neon_fp_mul, + neon_fp_mul_q, neon_fp_mla, neon_fp_mla_q, neon_fp_recpe_rsqrte, + neon_fp_recpe_rsqrte_q, neon_fp_recps_rsqrts, neon_fp_recps_rsqrts_q, + neon_bitops, neon_bitops_q, neon_from_gp, + neon_from_gp_q, neon_move, neon_tbl3_tbl4, neon_zip_q, neon_to_gp, + neon_load_a, neon_load_b, neon_load_c, neon_load_d, neon_load_e, + neon_load_f, neon_store_a, neon_store_b, neon_store_complex, + unknown" + (cond [ + (eq_attr "type" "neon_abd, neon_abd_long") + (const_string "neon_abd") + (eq_attr "type" "neon_abd_q") + (const_string "neon_abd_q") + (eq_attr "type" "neon_arith_acc, neon_reduc_add_acc,\ + neon_reduc_add_acc_q") + (const_string "neon_arith_acc") + (eq_attr "type" "neon_arith_acc_q") + (const_string "neon_arith_acc_q") + (eq_attr "type" "neon_add, neon_add_q, neon_add_long,\ + neon_add_widen, neon_neg, neon_neg_q,\ + neon_reduc_add, neon_reduc_add_q,\ + neon_reduc_add_long, neon_sub, neon_sub_q,\ + neon_sub_long, neon_sub_widen, neon_logic,\ + neon_logic_q, neon_tst, neon_tst_q") + (const_string "neon_arith_basic") + (eq_attr "type" "neon_abs, neon_abs_q, neon_add_halve_narrow_q,\ + neon_add_halve, neon_add_halve_q,\ + neon_sub_halve, neon_sub_halve_q, neon_qabs,\ + neon_qabs_q, neon_qadd, neon_qadd_q, neon_qneg,\ + neon_qneg_q, neon_qsub, neon_qsub_q,\ + neon_sub_halve_narrow_q,\ + neon_compare, neon_compare_q,\ + neon_compare_zero, neon_compare_zero_q,\ + neon_minmax, neon_minmax_q, neon_reduc_minmax,\ + neon_reduc_minmax_q") + (const_string "neon_arith_complex") + + (eq_attr "type" "neon_mul_b, neon_mul_h, neon_mul_s,\ + neon_mul_h_scalar, neon_mul_s_scalar,\ + neon_sat_mul_b, neon_sat_mul_h,\ + neon_sat_mul_s, neon_sat_mul_h_scalar,\ + neon_sat_mul_s_scalar,\ + neon_mul_b_long, neon_mul_h_long,\ + neon_mul_s_long, neon_mul_d_long,\ + neon_mul_h_scalar_long, neon_mul_s_scalar_long,\ + neon_sat_mul_b_long, neon_sat_mul_h_long,\ + neon_sat_mul_s_long, neon_sat_mul_h_scalar_long,\ + neon_sat_mul_s_scalar_long") + (const_string "neon_multiply") + (eq_attr "type" "neon_mul_b_q, neon_mul_h_q, neon_mul_s_q,\ + neon_mul_h_scalar_q, neon_mul_s_scalar_q,\ + neon_sat_mul_b_q, neon_sat_mul_h_q,\ + neon_sat_mul_s_q, neon_sat_mul_h_scalar_q,\ + neon_sat_mul_s_scalar_q") + (const_string "neon_multiply_q") + (eq_attr "type" "neon_mla_b, neon_mla_h, neon_mla_s,\ + neon_mla_h_scalar, neon_mla_s_scalar,\ + neon_mla_b_long, neon_mla_h_long,\ + neon_mla_s_long,\ + neon_mla_h_scalar_long, neon_mla_s_scalar_long") + (const_string "neon_mla") + (eq_attr "type" "neon_mla_b_q, neon_mla_h_q, neon_mla_s_q,\ + neon_mla_h_scalar_q, neon_mla_s_scalar_q") + (const_string "neon_mla_q") + (eq_attr "type" "neon_sat_mla_b_long, neon_sat_mla_h_long,\ + neon_sat_mla_s_long, neon_sat_mla_h_scalar_long,\ + neon_sat_mla_s_scalar_long") + (const_string "neon_sat_mla_long") + + (eq_attr "type" "neon_shift_acc, neon_shift_acc_q") + (const_string "neon_shift_acc") + (eq_attr "type" "neon_shift_imm, neon_shift_imm_q,\ + neon_shift_imm_narrow_q, neon_shift_imm_long") + (const_string "neon_shift_imm_basic") + (eq_attr "type" "neon_sat_shift_imm, neon_sat_shift_imm_q,\ + neon_sat_shift_imm_narrow_q") + (const_string "neon_shift_imm_complex") + (eq_attr "type" "neon_shift_reg") + (const_string "neon_shift_reg_basic") + (eq_attr "type" "neon_shift_reg_q") + (const_string "neon_shift_reg_basic_q") + (eq_attr "type" "neon_sat_shift_reg") + (const_string "neon_shift_reg_complex") + (eq_attr "type" "neon_sat_shift_reg_q") + (const_string "neon_shift_reg_complex_q") + + (eq_attr "type" "neon_fp_neg_s, neon_fp_neg_s_q,\ + neon_fp_abs_s, neon_fp_abs_s_q,\ + neon_fp_neg_d, neon_fp_neg_d_q,\ + neon_fp_abs_d, neon_fp_abs_d_q") + (const_string "neon_fp_negabs") + (eq_attr "type" "neon_fp_addsub_s, neon_fp_abd_s,\ + neon_fp_reduc_add_s, neon_fp_compare_s,\ + neon_fp_minmax_s, neon_fp_round_s,\ + neon_fp_addsub_d, neon_fp_abd_d,\ + neon_fp_reduc_add_d, neon_fp_compare_d,\ + neon_fp_minmax_d, neon_fp_round_d,\ + neon_fp_reduc_minmax_s, neon_fp_reduc_minmax_d") + (const_string "neon_fp_arith") + (eq_attr "type" "neon_fp_addsub_s_q, neon_fp_abd_s_q,\ + neon_fp_reduc_add_s_q, neon_fp_compare_s_q,\ + neon_fp_minmax_s_q, neon_fp_round_s_q,\ + neon_fp_addsub_d_q, neon_fp_abd_d_q,\ + neon_fp_reduc_add_d_q, neon_fp_compare_d_q,\ + neon_fp_minmax_d_q, neon_fp_round_d_q") + (const_string "neon_fp_arith_q") + (eq_attr "type" "neon_fp_reduc_minmax_s_q,\ + neon_fp_reduc_minmax_d_q,\ + neon_fp_reduc_add_s_q, neon_fp_reduc_add_d_q") + (const_string "neon_fp_reductions_q") + (eq_attr "type" "neon_fp_to_int_s, neon_int_to_fp_s,\ + neon_fp_to_int_d, neon_int_to_fp_d") + (const_string "neon_fp_cvt_int") + (eq_attr "type" "neon_fp_to_int_s_q, neon_int_to_fp_s_q,\ + neon_fp_to_int_d_q, neon_int_to_fp_d_q") + (const_string "neon_fp_cvt_int_q") + (eq_attr "type" "neon_fp_cvt_narrow_s_q, neon_fp_cvt_widen_h") + (const_string "neon_fp_cvt16") + (eq_attr "type" "neon_fp_mul_s, neon_fp_mul_s_scalar,\ + neon_fp_mul_d") + (const_string "neon_fp_mul") + (eq_attr "type" "neon_fp_mul_s_q, neon_fp_mul_s_scalar_q,\ + neon_fp_mul_d_q, neon_fp_mul_d_scalar_q") + (const_string "neon_fp_mul_q") + (eq_attr "type" "neon_fp_mla_s, neon_fp_mla_s_scalar,\ + neon_fp_mla_d") + (const_string "neon_fp_mla") + (eq_attr "type" "neon_fp_mla_s_q, neon_fp_mla_s_scalar_q, + neon_fp_mla_d_q, neon_fp_mla_d_scalar_q") + (const_string "neon_fp_mla_q") + (eq_attr "type" "neon_fp_recpe_s, neon_fp_rsqrte_s,\ + neon_fp_recpx_s,\ + neon_fp_recpe_d, neon_fp_rsqrte_d,\ + neon_fp_recpx_d") + (const_string "neon_fp_recpe_rsqrte") + (eq_attr "type" "neon_fp_recpe_s_q, neon_fp_rsqrte_s_q,\ + neon_fp_recpx_s_q,\ + neon_fp_recpe_d_q, neon_fp_rsqrte_d_q,\ + neon_fp_recpx_d_q") + (const_string "neon_fp_recpe_rsqrte_q") + (eq_attr "type" "neon_fp_recps_s, neon_fp_rsqrts_s,\ + neon_fp_recps_d, neon_fp_rsqrts_d") + (const_string "neon_fp_recps_rsqrts") + (eq_attr "type" "neon_fp_recps_s_q, neon_fp_rsqrts_s_q,\ + neon_fp_recps_d_q, neon_fp_rsqrts_d_q") + (const_string "neon_fp_recps_rsqrts_q") + (eq_attr "type" "neon_bsl, neon_cls, neon_cnt,\ + neon_rev, neon_permute, neon_rbit,\ + neon_tbl1, neon_tbl2, neon_zip,\ + neon_dup, neon_dup_q, neon_ext, neon_ext_q,\ + neon_move, neon_move_q, neon_move_narrow_q") + (const_string "neon_bitops") + (eq_attr "type" "neon_bsl_q, neon_cls_q, neon_cnt_q,\ + neon_rev_q, neon_permute_q, neon_rbit_q") + (const_string "neon_bitops_q") + (eq_attr "type" "neon_from_gp,f_mcr,f_mcrr") + (const_string "neon_from_gp") + (eq_attr "type" "neon_from_gp_q") + (const_string "neon_from_gp_q") + (eq_attr "type" "neon_tbl3, neon_tbl4") + (const_string "neon_tbl3_tbl4") + (eq_attr "type" "neon_zip_q") + (const_string "neon_zip_q") + (eq_attr "type" "neon_to_gp, neon_to_gp_q,f_mrc,f_mrrc") + (const_string "neon_to_gp") + + (eq_attr "type" "f_loads, f_loadd,\ + neon_load1_1reg, neon_load1_1reg_q,\ + neon_load1_2reg, neon_load1_2reg_q") + (const_string "neon_load_a") + (eq_attr "type" "neon_load1_3reg, neon_load1_3reg_q,\ + neon_load1_4reg, neon_load1_4reg_q") + (const_string "neon_load_b") + (eq_attr "type" "neon_load1_one_lane, neon_load1_one_lane_q,\ + neon_load1_all_lanes, neon_load1_all_lanes_q,\ + neon_load2_2reg, neon_load2_2reg_q,\ + neon_load2_all_lanes, neon_load2_all_lanes_q") + (const_string "neon_load_c") + (eq_attr "type" "neon_load2_4reg, neon_load2_4reg_q,\ + neon_load3_3reg, neon_load3_3reg_q,\ + neon_load3_one_lane, neon_load3_one_lane_q,\ + neon_load4_4reg, neon_load4_4reg_q") + (const_string "neon_load_d") + (eq_attr "type" "neon_load2_one_lane, neon_load2_one_lane_q,\ + neon_load3_all_lanes, neon_load3_all_lanes_q,\ + neon_load4_all_lanes, neon_load4_all_lanes_q") + (const_string "neon_load_e") + (eq_attr "type" "neon_load4_one_lane, neon_load4_one_lane_q") + (const_string "neon_load_f") + + (eq_attr "type" "f_stores, f_stored,\ + neon_store1_1reg") + (const_string "neon_store_a") + (eq_attr "type" "neon_store1_2reg, neon_store1_1reg_q") + (const_string "neon_store_b") + (eq_attr "type" "neon_store1_3reg, neon_store1_3reg_q,\ + neon_store3_3reg, neon_store3_3reg_q,\ + neon_store2_4reg, neon_store2_4reg_q,\ + neon_store4_4reg, neon_store4_4reg_q,\ + neon_store2_2reg, neon_store2_2reg_q,\ + neon_store3_one_lane, neon_store3_one_lane_q,\ + neon_store4_one_lane, neon_store4_one_lane_q,\ + neon_store1_4reg, neon_store1_4reg_q,\ + neon_store1_one_lane, neon_store1_one_lane_q,\ + neon_store2_one_lane, neon_store2_one_lane_q") + (const_string "neon_store_complex")] + (const_string "unknown"))) + +;; The Cortex-A57 core is modelled as a triple issue pipeline that has +;; the following functional units. +;; 1. Two pipelines for integer operations: SX1, SX2 + +(define_cpu_unit "ca57_sx1_issue" "cortex_a57") +(define_reservation "ca57_sx1" "ca57_sx1_issue") + +(define_cpu_unit "ca57_sx2_issue" "cortex_a57") +(define_reservation "ca57_sx2" "ca57_sx2_issue") + +;; 2. One pipeline for complex integer operations: MX + +(define_cpu_unit "ca57_mx_issue" + "cortex_a57") +(define_reservation "ca57_mx" "ca57_mx_issue") +(define_reservation "ca57_mx_block" "ca57_mx_issue") + +;; 3. Two asymmetric pipelines for Neon and FP operations: CX1, CX2 +(define_automaton "cortex_a57_cx") + +(define_cpu_unit "ca57_cx1_issue" + "cortex_a57_cx") +(define_cpu_unit "ca57_cx2_issue" + "cortex_a57_cx") + +(define_reservation "ca57_cx1" "ca57_cx1_issue") + +(define_reservation "ca57_cx2" "ca57_cx2_issue") +(define_reservation "ca57_cx2_block" "ca57_cx2_issue*2") + +;; 4. One pipeline for branch operations: BX + +(define_cpu_unit "ca57_bx_issue" "cortex_a57") +(define_reservation "ca57_bx" "ca57_bx_issue") + +;; 5. Two pipelines for load and store operations: LS1, LS2. The most +;; valuable thing we can do is force a structural hazard to split +;; up loads/stores. + +(define_cpu_unit "ca57_ls_issue" "cortex_a57") +(define_cpu_unit "ca57_ldr, ca57_str" "cortex_a57") +(define_reservation "ca57_load_model" "ca57_ls_issue,ca57_ldr*2") +(define_reservation "ca57_store_model" "ca57_ls_issue,ca57_str") + +;; Block all issue queues. + +(define_reservation "ca57_block" "ca57_cx1_issue + ca57_cx2_issue + + ca57_mx_issue + ca57_sx1_issue + + ca57_sx2_issue + ca57_ls_issue") + +;; Simple Execution Unit: +;; +;; Simple ALU without shift +(define_insn_reservation "cortex_a57_alu" 2 + (and (eq_attr "tune" "cortexa57") + (eq_attr "type" "alu_imm,alus_imm,logic_imm,logics_imm,\ + alu_reg,alus_reg,logic_reg,logics_reg,\ + adc_imm,adcs_imm,adc_reg,adcs_reg,\ + adr,bfm,clz,rbit,rev,\ + shift_imm,shift_reg,\ + mov_imm,mov_reg,\ + mvn_imm,mvn_reg,\ + mrs,multiple,no_insn")) + "ca57_sx1|ca57_sx2") + +;; ALU ops with immediate shift +(define_insn_reservation "cortex_a57_alu_shift" 3 + (and (eq_attr "tune" "cortexa57") + (eq_attr "type" "extend,\ + alu_shift_imm,alus_shift_imm,\ + crc,logic_shift_imm,logics_shift_imm,\ + mov_shift,mvn_shift")) + "ca57_mx") + +;; Multi-Cycle Execution Unit: +;; +;; ALU ops with register controlled shift +(define_insn_reservation "cortex_a57_alu_shift_reg" 3 + (and (eq_attr "tune" "cortexa57") + (eq_attr "type" "alu_shift_reg,alus_shift_reg,\ + logic_shift_reg,logics_shift_reg,\ + mov_shift_reg,mvn_shift_reg")) + "ca57_mx") + +;; All multiplies +;; TODO: AArch32 and AArch64 have different behaviour +(define_insn_reservation "cortex_a57_mult32" 3 + (and (eq_attr "tune" "cortexa57") + (ior (eq_attr "mul32" "yes") + (eq_attr "mul64" "yes"))) + "ca57_mx") + +;; Integer divide +(define_insn_reservation "cortex_a57_div" 10 + (and (eq_attr "tune" "cortexa57") + (eq_attr "type" "udiv,sdiv")) + "ca57_mx_issue,ca57_mx_block*3") + +;; Block all issue pipes for a cycle +(define_insn_reservation "cortex_a57_block" 1 + (and (eq_attr "tune" "cortexa57") + (eq_attr "type" "block")) + "ca57_block") + +;; Branch execution Unit +;; +;; Branches take one issue slot. +;; No latency as there is no result +(define_insn_reservation "cortex_a57_branch" 0 + (and (eq_attr "tune" "cortexa57") + (eq_attr "type" "branch")) + "ca57_bx") + +;; Load-store execution Unit +;; +;; Loads of up to two words. +(define_insn_reservation "cortex_a57_load1" 5 + (and (eq_attr "tune" "cortexa57") + (eq_attr "type" "load_byte,load1,load2")) + "ca57_load_model") + +;; Loads of three or four words. +(define_insn_reservation "cortex_a57_load3" 5 + (and (eq_attr "tune" "cortexa57") + (eq_attr "type" "load3,load4")) + "ca57_ls_issue*2,ca57_load_model") + +;; Stores of up to two words. +(define_insn_reservation "cortex_a57_store1" 0 + (and (eq_attr "tune" "cortexa57") + (eq_attr "type" "store1,store2")) + "ca57_store_model") + +;; Stores of three or four words. +(define_insn_reservation "cortex_a57_store3" 0 + (and (eq_attr "tune" "cortexa57") + (eq_attr "type" "store3,store4")) + "ca57_ls_issue*2,ca57_store_model") + +;; Advanced SIMD Unit - Integer Arithmetic Instructions. + +(define_insn_reservation "cortex_a57_neon_abd" 5 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_abd")) + "ca57_cx1|ca57_cx2") + +(define_insn_reservation "cortex_a57_neon_abd_q" 5 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_abd_q")) + "ca57_cx1+ca57_cx2") + +(define_insn_reservation "cortex_a57_neon_aba" 7 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_arith_acc")) + "ca57_cx2") + +(define_insn_reservation "cortex_a57_neon_aba_q" 8 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_arith_acc_q")) + "ca57_cx2+(ca57_cx2_issue,ca57_cx2)") + +(define_insn_reservation "cortex_a57_neon_arith_basic" 4 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_arith_basic")) + "ca57_cx1|ca57_cx2") + +(define_insn_reservation "cortex_a57_neon_arith_complex" 5 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_arith_complex")) + "ca57_cx1|ca57_cx2") + +;; Integer Multiply Instructions. + +(define_insn_reservation "cortex_a57_neon_multiply" 6 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_multiply")) + "ca57_cx1") + +(define_insn_reservation "cortex_a57_neon_multiply_q" 7 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_multiply_q")) + "ca57_cx1+(ca57_cx1_issue,ca57_cx1)") + +(define_insn_reservation "cortex_a57_neon_mla" 6 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_mla")) + "ca57_cx1") + +(define_insn_reservation "cortex_a57_neon_mla_q" 7 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_mla_q")) + "ca57_cx1+(ca57_cx1_issue,ca57_cx1)") + +(define_insn_reservation "cortex_a57_neon_sat_mla_long" 6 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_sat_mla_long")) + "ca57_cx1") + +;; Integer Shift Instructions. + +(define_insn_reservation + "cortex_a57_neon_shift_acc" 7 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_shift_acc")) + "ca57_cx2") + +(define_insn_reservation + "cortex_a57_neon_shift_imm_basic" 4 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_shift_imm_basic")) + "ca57_cx2") + +(define_insn_reservation + "cortex_a57_neon_shift_imm_complex" 5 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_shift_imm_complex")) + "ca57_cx2") + +(define_insn_reservation + "cortex_a57_neon_shift_reg_basic" 4 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_shift_reg_basic")) + "ca57_cx2") + +(define_insn_reservation + "cortex_a57_neon_shift_reg_basic_q" 5 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_shift_reg_basic_q")) + "ca57_cx2+(ca57_cx2_issue,ca57_cx2)") + +(define_insn_reservation + "cortex_a57_neon_shift_reg_complex" 5 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_shift_reg_complex")) + "ca57_cx2") + +(define_insn_reservation + "cortex_a57_neon_shift_reg_complex_q" 6 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_shift_reg_complex_q")) + "ca57_cx2+(ca57_cx2_issue,ca57_cx2)") + +;; Floating Point Instructions. + +(define_insn_reservation + "cortex_a57_neon_fp_negabs" 4 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_fp_negabs")) + "(ca57_cx1|ca57_cx2)") + +(define_insn_reservation + "cortex_a57_neon_fp_arith" 6 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_fp_arith")) + "(ca57_cx1|ca57_cx2)") + +(define_insn_reservation + "cortex_a57_neon_fp_arith_q" 6 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_fp_arith_q")) + "(ca57_cx1+ca57_cx2)") + +(define_insn_reservation + "cortex_a57_neon_fp_reductions_q" 10 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_fp_reductions_q")) + "(ca57_cx1+ca57_cx2),(ca57_cx1|ca57_cx2)") + +(define_insn_reservation + "cortex_a57_neon_fp_cvt_int" 6 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_fp_cvt_int")) + "(ca57_cx1|ca57_cx2)") + +(define_insn_reservation + "cortex_a57_neon_fp_cvt_int_q" 6 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_fp_cvt_int_q")) + "(ca57_cx1+ca57_cx2)") + +(define_insn_reservation + "cortex_a57_neon_fp_cvt16" 10 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_fp_cvt16")) + "(ca57_cx1_issue+ca57_cx2_issue),(ca57_cx1|ca57_cx2)") + +(define_insn_reservation + "cortex_a57_neon_fp_mul" 5 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_fp_mul")) + "(ca57_cx1|ca57_cx2)") + +(define_insn_reservation + "cortex_a57_neon_fp_mul_q" 5 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_fp_mul_q")) + "(ca57_cx1+ca57_cx2)") + +(define_insn_reservation + "cortex_a57_neon_fp_mla" 9 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_fp_mla")) + "(ca57_cx1,ca57_cx1)|(ca57_cx2,ca57_cx2)") + +(define_insn_reservation + "cortex_a57_neon_fp_mla_q" 9 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_fp_mla_q")) + "(ca57_cx1+ca57_cx2),(ca57_cx1,ca57_cx2)") + +(define_insn_reservation + "cortex_a57_neon_fp_recpe_rsqrte" 6 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_fp_recpe_rsqrte")) + "(ca57_cx1|ca57_cx2)") + +(define_insn_reservation + "cortex_a57_neon_fp_recpe_rsqrte_q" 6 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_fp_recpe_rsqrte_q")) + "(ca57_cx1+ca57_cx2)") + +(define_insn_reservation + "cortex_a57_neon_fp_recps_rsqrts" 10 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_fp_recps_rsqrts")) + "(ca57_cx1|ca57_cx2)") + +(define_insn_reservation + "cortex_a57_neon_fp_recps_rsqrts_q" 10 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_fp_recps_rsqrts_q")) + "(ca57_cx1+ca57_cx2)") + +;; Miscellaneous Instructions. + +(define_insn_reservation + "cortex_a57_neon_bitops" 4 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_bitops")) + "(ca57_cx1|ca57_cx2)") + +(define_insn_reservation + "cortex_a57_neon_bitops_q" 4 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_bitops_q")) + "(ca57_cx1+ca57_cx2)") + +(define_insn_reservation + "cortex_a57_neon_from_gp" 9 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_from_gp")) + "(ca57_ls_issue+ca57_cx1_issue,ca57_cx1) + |(ca57_ls_issue+ca57_cx2_issue,ca57_cx2)") + +(define_insn_reservation + "cortex_a57_neon_from_gp_q" 9 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_from_gp_q")) + "(ca57_ls_issue+ca57_cx1_issue,ca57_cx1) + +(ca57_ls_issue+ca57_cx2_issue,ca57_cx2)") + +(define_insn_reservation + "cortex_a57_neon_tbl3_tbl4" 7 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_tbl3_tbl4")) + "(ca57_cx1_issue,ca57_cx1) + +(ca57_cx2_issue,ca57_cx2)") + +(define_insn_reservation + "cortex_a57_neon_zip_q" 7 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_zip_q")) + "(ca57_cx1_issue,ca57_cx1) + +(ca57_cx2_issue,ca57_cx2)") + +(define_insn_reservation + "cortex_a57_neon_to_gp" 7 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_to_gp")) + "((ca57_ls_issue+ca57_sx1_issue),ca57_sx1) + |((ca57_ls_issue+ca57_sx2_issue),ca57_sx2)") + +;; Load Instructions. + +(define_insn_reservation + "cortex_a57_neon_load_a" 6 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_load_a")) + "ca57_load_model") + +(define_insn_reservation + "cortex_a57_neon_load_b" 7 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_load_b")) + "ca57_ls_issue,ca57_ls_issue+ca57_ldr,ca57_ldr*2") + +(define_insn_reservation + "cortex_a57_neon_load_c" 9 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_load_c")) + "ca57_load_model+(ca57_cx1|ca57_cx2)") + +(define_insn_reservation + "cortex_a57_neon_load_d" 11 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_load_d")) + "ca57_cx1_issue+ca57_cx2_issue, + ca57_ls_issue+ca57_ls_issue,ca57_ldr*2") + +(define_insn_reservation + "cortex_a57_neon_load_e" 9 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_load_e")) + "ca57_load_model+(ca57_cx1|ca57_cx2)") + +(define_insn_reservation + "cortex_a57_neon_load_f" 11 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_load_f")) + "ca57_cx1_issue+ca57_cx2_issue, + ca57_ls_issue+ca57_ls_issue,ca57_ldr*2") + +;; Store Instructions. + +(define_insn_reservation + "cortex_a57_neon_store_a" 0 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_store_a")) + "ca57_store_model") + +(define_insn_reservation + "cortex_a57_neon_store_b" 0 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_store_b")) + "ca57_store_model") + +;; These block issue for a number of cycles proportional to the number +;; of 64-bit chunks they will store, we don't attempt to model that +;; precisely, treat them as blocking execution for two cycles when +;; issued. +(define_insn_reservation + "cortex_a57_neon_store_complex" 0 + (and (eq_attr "tune" "cortexa57") + (eq_attr "cortex_a57_neon_type" "neon_store_complex")) + "ca57_block*2") + +;; Floating-Point Operations. + +(define_insn_reservation "cortex_a57_fp_const" 4 + (and (eq_attr "tune" "cortexa57") + (eq_attr "type" "fconsts,fconstd")) + "(ca57_cx1|ca57_cx2)") + +(define_insn_reservation "cortex_a57_fp_add_sub" 6 + (and (eq_attr "tune" "cortexa57") + (eq_attr "type" "fadds,faddd")) + "(ca57_cx1|ca57_cx2)") + +(define_insn_reservation "cortex_a57_fp_mul" 6 + (and (eq_attr "tune" "cortexa57") + (eq_attr "type" "fmuls,fmuld")) + "(ca57_cx1|ca57_cx2)") + +(define_insn_reservation "cortex_a57_fp_mac" 10 + (and (eq_attr "tune" "cortexa57") + (eq_attr "type" "fmacs,ffmas,fmacd,ffmad")) + "(ca57_cx1,nothing,nothing,ca57_cx1) \ + |(ca57_cx2,nothing,nothing,ca57_cx2)") + +(define_insn_reservation "cortex_a57_fp_cvt" 6 + (and (eq_attr "tune" "cortexa57") + (eq_attr "type" "f_cvt,f_cvtf2i,f_cvti2f")) + "(ca57_cx1|ca57_cx2)") + +(define_insn_reservation "cortex_a57_fp_cmp" 7 + (and (eq_attr "tune" "cortexa57") + (eq_attr "type" "fcmps,fcmpd")) + "ca57_cx2") + +(define_insn_reservation "cortex_a57_fp_arith" 4 + (and (eq_attr "tune" "cortexa57") + (eq_attr "type" "ffariths,ffarithd")) + "(ca57_cx1|ca57_cx2)") + +(define_insn_reservation "cortex_a57_fp_cpys" 4 + (and (eq_attr "tune" "cortexa57") + (eq_attr "type" "fmov")) + "(ca57_cx1|ca57_cx2)") + +(define_insn_reservation "cortex_a57_fp_divs" 12 + (and (eq_attr "tune" "cortexa57") + (eq_attr "type" "fdivs, fsqrts,\ + neon_fp_div_s, neon_fp_sqrt_s")) + "ca57_cx2_block*5") + +(define_insn_reservation "cortex_a57_fp_divd" 16 + (and (eq_attr "tune" "cortexa57") + (eq_attr "type" "fdivd, fsqrtd, neon_fp_div_d, neon_fp_sqrt_d")) + "ca57_cx2_block*3") + +(define_insn_reservation "cortex_a57_neon_fp_div_q" 20 + (and (eq_attr "tune" "cortexa57") + (eq_attr "type" "fdivd, fsqrtd,\ + neon_fp_div_s_q, neon_fp_div_d_q,\ + neon_fp_sqrt_s_q, neon_fp_sqrt_d_q")) + "ca57_cx2_block*3") + +(define_insn_reservation "cortex_a57_crypto_simple" 4 + (and (eq_attr "tune" "cortexa57") + (eq_attr "type" "crypto_aese,crypto_aesmc,crypto_sha1_fast,\ + crypto_sha256_fast")) + "ca57_cx2") + +(define_insn_reservation "cortex_a57_crypto_complex" 7 + (and (eq_attr "tune" "cortexa57") + (eq_attr "type" "crypto_sha1_slow,crypto_sha256_slow")) + "ca57_cx2+(ca57_cx2_issue,ca57_cx2)") + +(define_insn_reservation "cortex_a57_crypto_xor" 7 + (and (eq_attr "tune" "cortexa57") + (eq_attr "type" "crypto_sha1_xor")) + "(ca57_cx1+ca57_cx2)") + +;; We lie with calls. They take up all issue slots, but are otherwise +;; not harmful. +(define_insn_reservation "cortex_a57_call" 1 + (and (eq_attr "tune" "cortexa57") + (eq_attr "type" "call")) + "ca57_sx1_issue+ca57_sx2_issue+ca57_cx1_issue+ca57_cx2_issue\ + +ca57_mx_issue+ca57_bx_issue+ca57_ls_issue" +) + +;; Simple execution unit bypasses +(define_bypass 1 "cortex_a57_alu" + "cortex_a57_alu,cortex_a57_alu_shift,cortex_a57_alu_shift_reg") +(define_bypass 2 "cortex_a57_alu_shift" + "cortex_a57_alu,cortex_a57_alu_shift,cortex_a57_alu_shift_reg") +(define_bypass 2 "cortex_a57_alu_shift_reg" + "cortex_a57_alu,cortex_a57_alu_shift,cortex_a57_alu_shift_reg") +(define_bypass 1 "cortex_a57_alu" "cortex_a57_load1,cortex_a57_load3") +(define_bypass 2 "cortex_a57_alu_shift" "cortex_a57_load1,cortex_a57_load3") +(define_bypass 2 "cortex_a57_alu_shift_reg" + "cortex_a57_load1,cortex_a57_load3") + +;; An MLA or a MUL can feed a dependent MLA. +(define_bypass 5 "cortex_a57_neon_*mla*,cortex_a57_neon_*mul*" + "cortex_a57_neon_*mla*") + +(define_bypass 5 "cortex_a57_fp_mul,cortex_a57_fp_mac" + "cortex_a57_fp_mac") + +;; We don't need to care about control hazards, either the branch is +;; predicted in which case we pay no penalty, or the branch is +;; mispredicted in which case instruction scheduling will be unlikely to +;; help. +(define_bypass 1 "cortex_a57_*" + "cortex_a57_call,cortex_a57_branch") + diff --git a/gcc/testsuite/gcc.c-torture/compile/pr65735.c b/gcc/testsuite/gcc.c-torture/compile/pr65735.c new file mode 100644 index 00000000000..c30de8ea398 --- /dev/null +++ b/gcc/testsuite/gcc.c-torture/compile/pr65735.c @@ -0,0 +1,21 @@ +/* PR tree-optimization/65735 */ + +int foo (void); + +void +bar (int a, int b, int c) +{ + while (!a) + { + c = foo (); + if (c == 7) + c = b; + switch (c) + { + case 1: + a = b++; + if (b) + b = 1; + } + } +} diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr65447.c b/gcc/testsuite/gcc.dg/tree-ssa/pr65447.c new file mode 100644 index 00000000000..c5bddbfba92 --- /dev/null +++ b/gcc/testsuite/gcc.dg/tree-ssa/pr65447.c @@ -0,0 +1,54 @@ +/* { dg-do compile } */ +/* { dg-options "-O2 -fdump-tree-ivopts-details" } */ + +void foo (double *p) +{ + int i; + for (i = -20000; i < 200000; i+= 40) + { + p[i+0] = 1.0; + p[i+1] = 1.0; + p[i+2] = 1.0; + p[i+3] = 1.0; + p[i+4] = 1.0; + p[i+5] = 1.0; + p[i+6] = 1.0; + p[i+7] = 1.0; + p[i+8] = 1.0; + p[i+9] = 1.0; + p[i+10] = 1.0; + p[i+11] = 1.0; + p[i+12] = 1.0; + p[i+13] = 1.0; + p[i+14] = 1.0; + p[i+15] = 1.0; + p[i+16] = 1.0; + p[i+17] = 1.0; + p[i+18] = 1.0; + p[i+19] = 1.0; + p[i+20] = 1.0; + p[i+21] = 1.0; + p[i+22] = 1.0; + p[i+23] = 1.0; + p[i+24] = 1.0; + p[i+25] = 1.0; + p[i+26] = 1.0; + p[i+27] = 1.0; + p[i+28] = 1.0; + p[i+29] = 1.0; + p[i+30] = 1.0; + p[i+31] = 1.0; + p[i+32] = 1.0; + p[i+33] = 1.0; + p[i+34] = 1.0; + p[i+35] = 1.0; + p[i+36] = 1.0; + p[i+37] = 1.0; + p[i+38] = 1.0; + p[i+39] = 1.0; + } +} + +/* We should groups address type IV uses. */ +/* { dg-final { scan-tree-dump-not "\\nuse 2\\n" "ivopts" } } */ +/* { dg-final { cleanup-tree-dump "ivopts" } } */ diff --git a/gcc/testsuite/gcc.dg/tree-ssa/scev-10.c b/gcc/testsuite/gcc.dg/tree-ssa/scev-10.c new file mode 100644 index 00000000000..2e16c894b73 --- /dev/null +++ b/gcc/testsuite/gcc.dg/tree-ssa/scev-10.c @@ -0,0 +1,21 @@ +/* { dg-do compile } */ +/* { dg-options "-O2 -fdump-tree-ivopts-details" } */ + +int *a; + +int +foo (signed char s, signed char l) +{ + signed char i; + int sum = 0; + + for (i = s; i < l; i++) + { + sum += a[i]; + } + + return sum; +} + +/* Address of array reference is scev. */ +/* { dg-final { scan-tree-dump-times "use \[0-9\]\n address" 1 "ivopts" } } */ diff --git a/gcc/testsuite/gcc.dg/tree-ssa/scev-8.c b/gcc/testsuite/gcc.dg/tree-ssa/scev-8.c new file mode 100644 index 00000000000..766f674d55b --- /dev/null +++ b/gcc/testsuite/gcc.dg/tree-ssa/scev-8.c @@ -0,0 +1,62 @@ +/* { dg-do compile } */ +/* { dg-options "-O2 -fdump-tree-ivopts-details" } */ + +int *a; + +int +foo1 (long long s, long long l) +{ + long long i; + + for (i = s; i < l; i++) + { + a[(short)i] = 0; + } + return 0; +} + +int +foo2 (unsigned char s, unsigned char l, unsigned char c) +{ + unsigned char i, step = 1; + int sum = 0; + + for (i = s; i < l; i++) + { + sum += a[c]; + c += step; + } + + return sum; +} + +int +foo3 (unsigned char s, unsigned char l, unsigned char c) +{ + unsigned char i; + int sum = 0; + + for (i = s; i != l; i += c) + { + sum += a[i]; + } + + return sum; +} + +int +foo4 (unsigned char s, unsigned char l) +{ + unsigned char i; + int sum = 0; + + for (i = s; i != l; i++) + { + sum += a[i]; + } + + return sum; +} + +/* Address of array references are not scevs. */ +/* { dg-final { scan-tree-dump-not "use \[0-9\]\n address" "ivopts" } } */ diff --git a/gcc/testsuite/gcc.dg/tree-ssa/scev-9.c b/gcc/testsuite/gcc.dg/tree-ssa/scev-9.c new file mode 100644 index 00000000000..557e3385013 --- /dev/null +++ b/gcc/testsuite/gcc.dg/tree-ssa/scev-9.c @@ -0,0 +1,21 @@ +/* { dg-do compile } */ +/* { dg-options "-O2 -fdump-tree-ivopts-details" } */ + +int *a; + +int +foo (unsigned char s, unsigned char l) +{ + unsigned char i; + int sum = 0; + + for (i = s; i < l; i += 1) + { + sum += a[i]; + } + + return sum; +} + +/* Address of array reference is scev. */ +/* { dg-final { scan-tree-dump-times "use \[0-9\]\n address" 1 "ivopts" } } */ diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-10.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-10.c new file mode 100644 index 00000000000..4acf580e1d7 --- /dev/null +++ b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-10.c @@ -0,0 +1,24 @@ +/* PR 65177 */ +/* { dg-do compile } */ +/* { dg-options "-O3" } */ + +typedef struct p7_profile_s {} P7_PROFILE; +enum p7t_statetype_e { + p7T_S = 4, p7T_N = 5, p7T_E = 7, p7T_C = 8, p7T_J = 10, }; +typedef struct p7_trace_s {} P7_TRACE; +typedef struct p7_gmx_s { + int L; +} P7_GMX; +static inline int select_c(const P7_PROFILE *gm, const P7_GMX *pp, const P7_GMX *gx, int i) { + float path[2]; + return ((path[0] > path[1]) ? p7T_C : p7T_E); +} +void p7_GOATrace(const P7_PROFILE *gm, const P7_GMX *pp, const P7_GMX *gx, P7_TRACE *tr) { + int i = gx->L; + int sprv, scur; + while (sprv != p7T_S) { + switch (sprv) { case p7T_C: scur = select_c(gm, pp, gx, i); break; } + if ( (scur == p7T_N || scur == p7T_J || scur == p7T_C) && scur == sprv) i--; + sprv = scur; + } +} diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-6.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-6.c new file mode 100644 index 00000000000..bb34a7432e1 --- /dev/null +++ b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-6.c @@ -0,0 +1,43 @@ +/* { dg-do compile } */ +/* { dg-options "-O2 -fdump-tree-dom1-details" } */ +/* { dg-final { scan-tree-dump-times "FSM" 6 "dom1" } } */ +/* { dg-final { cleanup-tree-dump "dom1" } } */ + +int sum0, sum1, sum2, sum3; +int foo (char *s, char **ret) +{ + int state=0; + char c; + + for (; *s && state != 4; s++) + { + c = *s; + if (c == '*') + { + s++; + break; + } + switch (state) + { + case 0: + if (c == '+') + state = 1; + else if (c != '-') + sum0+=c; + break; + case 1: + if (c == '+') + state = 2; + else if (c == '-') + state = 0; + else + sum1+=c; + break; + default: + break; + } + + } + *ret = s; + return state; +} diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-7.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-7.c new file mode 100644 index 00000000000..21474f0b496 --- /dev/null +++ b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-7.c @@ -0,0 +1,127 @@ +/* { dg-do compile } */ +/* { dg-options "-O2 -fdump-tree-dom1-details" } */ +/* { dg-final { scan-tree-dump-times "FSM" 19 "dom1" } } */ +/* { dg-final { cleanup-tree-dump "dom1" } } */ + +enum STATE { + S0=0, + SI, + S1, + S2, + S3, + S4, + S5, + S6 +}; + +int bar (enum STATE s); + +enum STATE foo (unsigned char **y, unsigned *c) +{ + unsigned char *x = *y; + unsigned char n; + enum STATE s = S0; + + for( ; *x && s != SI; x++ ) + { + n = *x; + if (n == 'x') + { + x++; + break; + } + switch(s) + { + case S0: + if(bar(n)) + s = S3; + else if( n == 'a' || n == 'b' ) + s = S1; + else if( n == 'c' ) + s = S4; + else + { + s = SI; + c[SI]++; + } + c[S0]++; + break; + case S1: + if(bar(n)) + { + s = S3; + c[S1]++; + } + else if( n == 'c' ) + { + s = S4; + c[S1]++; + } + else + { + s = SI; + c[S1]++; + } + break; + case S3: + if( n == 'c' ) + { + s = S4; + c[S3]++; + } + else if(!bar(n)) + { + s = SI; + c[S3]++; + } + break; + case S4: + if( n == 'E' || n == 'e' ) + { + s = S2; + c[S4]++; + } + else if(!bar(n)) + { + s = SI; + c[S4]++; + } + break; + case S2: + if( n == 'a' || n == 'b' ) + { + s = S5; + c[S2]++; + } + else + { + s = SI; + c[S2]++; + } + break; + case S5: + if(bar(n)) + { + s = S6; + c[S5]++; + } + else + { + s = SI; + c[S5]++; + } + break; + case S6: + if(!bar(n)) + { + s = SI; + c[SI]++; + } + break; + default: + break; + } + } + *y=x; + return s; +} diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-8.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-8.c new file mode 100644 index 00000000000..9be75aaf21d --- /dev/null +++ b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-8.c @@ -0,0 +1,440 @@ +/* PR 64878 */ +/* { dg-options "-O2" } */ +/* { dg-do run } */ + +struct A { int a1; }; +struct B { char *b1; int b2; int b3; }; +struct C { char *c1; int c2; struct B *c3; }; +extern struct A *f1 (char *s); +static struct A *f2 (struct C *x); +__attribute__ ((noinline, noclone)) int f3 (struct A *x, struct A *z) { asm volatile ("" : : "g" (x), "g" (z) : "memory"); return 0; } +__attribute__ ((noinline, noclone)) void f4 (struct A *x, char *y, struct A *z) { asm volatile ("" : : "g" (x), "g" (z), "g" (y) : "memory"); } +__attribute__ ((noinline, noclone)) struct B *f5 (void) { static char b[32]; static struct B f3 = { b, 0, 32 }; return &f3; } +__attribute__ ((noinline, noclone)) int f6 (struct B *p, char *w, int z) { asm volatile ("" : : "g" (p), "g" (w), "g" (z) : "memory"); return 0; } +__attribute__ ((noinline, noclone)) void f7 (struct B *p) { asm volatile ("" : : "g" (p) : "memory"); } +__attribute__ ((noinline, noclone)) void f8 (struct B *p) { asm volatile ("" : : "g" (p) : "memory"); } +__attribute__ ((noinline, noclone)) void f9 (struct A *x) { asm volatile ("" : : "g" (x) : "memory"); } +__attribute__ ((noinline, noclone)) struct A *f10 (void) { static struct A j; asm volatile ("" : : : "memory"); return &j; } +__attribute__ ((noinline, noclone)) struct A *f11 (void) { static struct A j; asm volatile ("" : : : "memory"); return &j; } +__attribute__ ((noinline, noclone)) struct A *f12 (int b) { static struct A j; asm volatile ("" : : "g" (b) : "memory"); return &j; } +__attribute__ ((noinline, noclone)) struct A *f13 (int i) { static struct A j; asm volatile ("" : : "g" (i) : "memory"); return &j; } +__attribute__ ((noinline, noclone)) struct A *f14 (double d) { static struct A j; asm volatile ("" : : "g" (&d) : "memory"); return &j; } +__attribute__ ((noinline, noclone)) struct A *f15 (char *s) { static struct A j; asm volatile ("" : : "g" (s) : "memory"); return &j; } +char *t = "0123456789abcdef"; +char *u = "0123456789.+-e"; + +__attribute__ ((noinline, noclone)) struct A * +f1 (char *s) +{ + struct C f; + struct A *o; + f.c1 = s; + f.c2 = 0; + f.c3 = f5 (); + o = f2 (&f); + f8 (f.c3); + return o; +} + +static struct A * +f2 (struct C *x) +{ + int a, b, e = 0; + struct A *f = 0, *o; + char *g = 0; + char h = '\0'; + int i = 0, j = 0; + a = 0; + b = 1; + char c; + do + { + c = x->c1[x->c2]; + switch (a) + { + case 0: + if (c == ' ') + x->c2++; + else if (c == '/') + { + a = 4; + j = x->c2++; + } + else + a = b; + break; + case 1: + switch (c) + { + case '{': + a = 0; + b = 15; + f = f10 (); + x->c2++; + break; + case '[': + a = 0; + b = 13; + f = f11 (); + x->c2++; + break; + case 'N': + case 'n': + a = 3; + j = x->c2++; + break; + case '"': + case '\'': + h = c; + f7 (x->c3); + a = 8; + j = ++x->c2; + break; + case 'T': + case 't': + case 'F': + case 'f': + a = 11; + j = x->c2++; + break; + case '0' ... '9': + case '-': + i = 0; + a = 12; + j = x->c2++; + break; + default: + e = 1; + goto out; + } + break; + case 2: + goto out; + case 3: + if (__builtin_strncmp ("null", x->c1 + j, x->c2 - j)) + { + e = 2; + goto out; + } + if (x->c2 - j == 4) + { + f = 0; + b = 2; + a = 0; + } + else + x->c2++; + break; + case 4: + if (c == '*') + a = 5; + else if (c == '/') + a = 6; + else + { + e = 8; + goto out; + } + x->c2++; + break; + case 5: + if (c == '*') + a = 7; + x->c2++; + break; + case 6: + if (c == '\n') + a = 0; + x->c2++; + break; + case 7: + if (c == '/') + a = 0; + else + a = 5; + x->c2++; + break; + case 8: + if (c == h) + { + f6 (x->c3, x->c1 + j, x->c2 - j); + f = f15 (x->c3->b1); + b = 2; + a = 0; + } + else if (c == '\\') + { + b = 8; + a = 9; + } + x->c2++; + break; + case 9: + switch (c) + { + case '"': + case '\\': + f6 (x->c3, x->c1 + j, x->c2 - j - 1); + j = x->c2++; + a = b; + break; + case 'b': + case 'n': + case 'r': + case 't': + f6 (x->c3, x->c1 + j, x->c2 - j - 1); + if (c == 'b') + f6 (x->c3, "\b", 1); + else if (c == 'n') + f6 (x->c3, "\n", 1); + else if (c == 'r') + f6 (x->c3, "\r", 1); + else if (c == 't') + f6 (x->c3, "\t", 1); + j = ++x->c2; + a = b; + break; + case 'u': + f6 (x->c3, x->c1 + j, x->c2 - j - 1); + j = ++x->c2; + a = 10; + break; + default: + e = 7; + goto out; + } + break; + case 10: + if (__builtin_strchr (t, c)) + { + x->c2++; + if (x->c2 - j == 4) + { + unsigned char w[3]; + unsigned int s = + (((x->c1[j] <= '9') ? x->c1[j] - '0' : (x->c1[j] & 7) + 9) << 12) + + (((x->c1[j + 1] <= '9') ? x->c1[j + 1] - '0' : (x->c1[j + 1] & 7) + 9) << 8) + + (((x->c1[j + 2] <= '9') ? x->c1[j + 2] - '0' : (x->c1[j + 2] & 7) + 9) << 4) + + ((x->c1[j + 3] <= '9') ? x->c1[j + 3] - '0' : (x->c1[j + 3] & 7) + 9); + if (s < 0x80) + { + w[0] = s; + f6 (x->c3, (char *) w, 1); + } + else if (s < 0x800) + { + w[0] = 0xc0 | (s >> 6); + w[1] = 0x80 | (s & 0x3f); + f6 (x->c3, (char *) w, 2); + } + else + { + w[0] = 0x0 | (s >> 12); + w[1] = 0x80 | ((s >> 6) & 0x3f); + w[2] = 0x80 | (s & 0x3f); + f6 (x->c3, (char *) w, 3); + } + j = x->c2; + a = b; + } + } + else + { + e = 7; + goto out; + } + break; + case 11: + if (__builtin_strncmp ("true", x->c1 + j, x->c2 - j) == 0) + { + if (x->c2 - j == 4) + { + f = f12 (1); + b = 2; + a = 0; + } + else + x->c2++; + } + else if (__builtin_strncmp ("false", x->c1 + j, x->c2 - j) == 0) + { + if (x->c2 - j == 5) + { + f = f12 (0); + b = 2; + a = 0; + } + else + x->c2++; + } + else + { + e = 3; + goto out; + } + break; + case 12: + if (!c || !__builtin_strchr (u, c)) + { + if (!i) + f = f13 (0); + else + f = f14 (0.0); + b = 2; + a = 0; + } + else + { + if (c == '.' || c == 'e') + i = 1; + x->c2++; + } + break; + case 13: + if (c == ']') + { + x->c2++; + b = 2; + a = 0; + } + else + { + o = f2 (x); + if (((unsigned long) o > (unsigned long) -4000L)) + { + e = 5; + goto out; + } + f3 (f, o); + b = 14; + a = 0; + } + break; + case 14: + if (c == ']') + { + x->c2++; + b = 2; + a = 0; + } + else if (c == ',') + { + x->c2++; + b = 13; + a = 0; + } + else + { + f9 (f); + e = 5; + goto out; + } + break; + case 15: + a = 16; + j = x->c2; + break; + case 16: + if (c == '}') + { + x->c2++; + b = 2; + a = 0; + } + else if (c == '"' || c == '\'') + { + h = c; + f7 (x->c3); + a = 17; + j = ++x->c2; + } + else + { + e = 6; + goto out; + } + break; + case 17: + if (c == h) + { + f6 (x->c3, x->c1 + j, x->c2 - j); + g = __builtin_strdup (x->c3->b1); + b = 18; + a = 0; + } + else if (c == '\\') + { + b = 17; + a = 9; + } + x->c2++; + break; + case 18: + if (c == ':') + { + x->c2++; + b = 19; + a = 0; + } + else + { + e = -6; + goto out; + } + break; + case 19: + o = f2 (x); + if (((unsigned long) o > (unsigned long) -4000L)) + { + e = 6; + goto out; + } + f4 (f, g, o); + __builtin_free (g); + g = 0; + b = 20; + a = 0; + break; + case 20: + if (c == '}') + { + x->c2++; + b = 2; + a = 0; + } + else if (c == ',') + { + x->c2++; + b = 15; + a = 0; + } + else + { + e = 6; + goto out; + } + break; + } + } + while (c); + if (a != 2 && b != 2) + e = 9; +out: + __builtin_free (g); + if (e == 0) + return f; + f9 (f); + return 0; +} + +int +main () +{ + asm volatile ("" : : : "memory"); + struct A *r = f1 ("{ \"id\": null, \"blahah\": \"foobarbazbar\", \"barbar\": { \"barbarbarba\":" + "\"abcdefgh\", \"ijklmnopqr\": \"stuvwxyzabcdefghijklmnopqrstuv\", \"xyzxyz\":" + " [ \"1\" ] } }"); + if (!r) + __builtin_abort (); + return 0; +} diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-9.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-9.c new file mode 100644 index 00000000000..6be42038bce --- /dev/null +++ b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-9.c @@ -0,0 +1,50 @@ +/* PR 65048 */ +/* { dg-do compile } */ +/* { dg-options "-O3" } */ + +int a, b, c, d; +void fn (void); + +int +foo (x) +{ + switch (x) + { + case 'A': + return 'T'; + case 'U': + return 'A'; + } +} + +void +bar (int x, int y) +{ + switch (c) + { + case 'U': + switch (x) + { + default: + fn (); + case 'G': + switch (y) + { + case 'A': + d = 7; + } + } + } +} + +void +baz (void) +{ + while (1) + { + a = foo (); + b = foo (); + bar (a, b); + } +} + diff --git a/gcc/testsuite/gcc.dg/vect/pr48052.c b/gcc/testsuite/gcc.dg/vect/pr48052.c new file mode 100644 index 00000000000..c822ebd4154 --- /dev/null +++ b/gcc/testsuite/gcc.dg/vect/pr48052.c @@ -0,0 +1,26 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-O3 -std=c99" } */ + +int foo(int* A, int* B, unsigned start, unsigned BS) +{ + int s; + for (unsigned k = start; k < start + BS; k++) + { + s += A[k] * B[k]; + } + + return s; +} + +int bar(int* A, int* B, unsigned BS) +{ + int s; + for (unsigned k = 0; k < BS; k++) + { + s += A[k] * B[k]; + } + + return s; +} + +/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 2 "vect" } } */ |