This is the mail archive of the gcc-patches@gcc.gnu.org mailing list for the GCC project.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

Re: add taishanv110 pipeline scheduling


On Thu, Dec 6, 2018 at 9:31 AM wuyuan (E) <wuyuan5@huawei.com> wrote:
>
> Hi ARM maintainers:
>         The taishanv110 core uses generic pipeline scheduling, which restricted the performance of taishanv110 core. By adding the pipeline scheduling of taishanv110 core in GCC,The performance of taishanv110 has been improved.
>         The patch  as follows, please join.
>
>
> diff --git a/gcc/ChangeLog b/gcc/ChangeLog
> old mode 100644
> new mode 100755
> index c4ec556..d6cf1d3
> --- a/gcc/ChangeLog
> +++ b/gcc/ChangeLog
> @@ -1,3 +1,9 @@
> +2018-12-05  wuyuan  <wuyuan5@huawei.com>
> +

Better be "Wu Yuan"

> +       * config/aarch64/aarch64-cores.def: New CPU.
> +       * config/aarch64/aarch64.md : Add "tsv110.md"
> +       * gcc/config/aarch64/tsv110.md : pipeline description
> +
Can remove the "gcc/" part.

> 2018-11-26  David Malcolm  <dmalcolm@redhat.com>
>
>           * dump-context.h (dump_context::dump_loc): Convert 1st param from
> diff --git a/gcc/config/aarch64/aarch64-cores.def b/gcc/config/aarch64/aarch64-cores.def
> index 74be5db..8e84844 100644
> --- a/gcc/config/aarch64/aarch64-cores.def
> +++ b/gcc/config/aarch64/aarch64-cores.def
> @@ -99,7 +99,7 @@ AARCH64_CORE("ares",  ares, cortexa57, 8_2A,  AARCH64_FL_FOR_ARCH8_2 | AARCH64_F
> /* ARMv8.4-A Architecture Processors.  */
>
> /* HiSilicon ('H') cores. */
> -AARCH64_CORE("tsv110",     tsv110,    cortexa57,    8_4A, AARCH64_FL_FOR_ARCH8_4 | AARCH64_FL_CRYPTO | AARCH64_FL_F16 | AARCH64_FL_AES | AARCH64_FL_SHA2, tsv110,   0x48, 0xd01, -1)
> +AARCH64_CORE("tsv110",     tsv110,    tsv110,    8_4A, AARCH64_FL_FOR_ARCH8_4 | AARCH64_FL_CRYPTO | AARCH64_FL_F16 | AARCH64_FL_AES | AARCH64_FL_SHA2, tsv110,   0x48, 0xd01, -1)
>
> /* Qualcomm ('Q') cores. */
> AARCH64_CORE("saphira",     saphira,    saphira,    8_4A,  AARCH64_FL_FOR_ARCH8_4 | AARCH64_FL_CRYPTO | AARCH64_FL_RCPC, saphira,   0x51, 0xC01, -1)
> diff --git a/gcc/config/aarch64/aarch64.md b/gcc/config/aarch64/aarch64.md
> index 82af4d4..5278d6b 100644
> --- a/gcc/config/aarch64/aarch64.md
> +++ b/gcc/config/aarch64/aarch64.md
> @@ -348,7 +348,7 @@
> (include "thunderx.md")
> (include "../arm/xgene1.md")
> (include "thunderx2t99.md")
> -
> +(include "tsv110.md")
> ;; -------------------------------------------------------------------
> ;; Jumps and other miscellaneous insns
> ;; -------------------------------------------------------------------
> diff --git a/gcc/config/aarch64/tsv110.md b/gcc/config/aarch64/tsv110.md
> new file mode 100644
> index 0000000..e912447
> --- /dev/null
> +++ b/gcc/config/aarch64/tsv110.md
> @@ -0,0 +1,708 @@
> +;; tsv110 pipeline description
> +;; Copyright (C) 2014-2016 Free Software Foundation, Inc.
> +;;

Given this is a new file, I think the copyright year should be updated.

BR,
Terry

> +;; 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 "tsv110")
> +
> +(define_attr "tsv110_neon_type"
> +  "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_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_abs,neon_abs_q,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,\
> +                              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_basic")
> +         (eq_attr "type" "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")
> +           (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_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,\
> +                              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,\
> +                              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_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,\
> +                              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_multiply_q")
> +
> +         (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,\
> +                              neon_fp_minmax_s,neon_fp_minmax_d,\
> +                              neon_fp_reduc_minmax_s,neon_fp_reduc_minmax_d")
> +           (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_round_s,\
> +                              neon_fp_addsub_d, neon_fp_abd_d,\
> +                              neon_fp_reduc_add_d, neon_fp_compare_d,\
> +                              neon_fp_round_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" "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 tsv110 core is modelled as issues pipeline that has
> +;; the following functional units.
> +;; 1.  Three pipelines for integer operations: ALU1, ALU2, ALU3
> +
> +(define_cpu_unit "tsv110_alu1_issue" "tsv110")
> +(define_reservation "tsv110_alu1" "tsv110_alu1_issue")
> +
> +(define_cpu_unit "tsv110_alu2_issue" "tsv110")
> +(define_reservation "tsv110_alu2" "tsv110_alu2_issue")
> +
> +(define_cpu_unit "tsv110_alu3_issue" "tsv110")
> +(define_reservation "tsv110_alu3" "tsv110_alu3_issue")
> +
> +;; 2.  One pipeline for complex integer operations: MDU
> +
> +(define_cpu_unit "tsv110_mdu_issue" "tsv110")
> +(define_reservation "tsv110_mdu" "tsv110_mdu_issue")
> +
> +;; 3.  Two asymmetric pipelines for Asimd and FP operations: FSU1, FSU2
> +(define_automaton "tsv110_fsu")
> +
> +(define_cpu_unit "tsv110_fsu1_issue"
> +                 "tsv110_fsu")
> +(define_cpu_unit "tsv110_fsu2_issue"
> +                 "tsv110_fsu")
> +
> +(define_reservation "tsv110_fsu1" "tsv110_fsu1_issue")
> +(define_reservation "tsv110_fsu2" "tsv110_fsu2_issue")
> +
> +;; 4.  Two pipeline for branch operations but same with alu2 and alu3: BRU1, BRU2
> +
> +;; 5.  Two pipelines for load and store operations: LS1, LS2.
> +
> +(define_cpu_unit "tsv110_ls1_issue" "tsv110")
> +(define_cpu_unit "tsv110_ls2_issue" "tsv110")
> +(define_reservation "tsv110_ls1" "tsv110_ls1_issue")
> +(define_reservation "tsv110_ls2" "tsv110_ls2_issue")
> +
> +;; Block all issue queues.
> +
> +(define_reservation "tsv110_block" "tsv110_fsu1_issue + tsv110_fsu2_issue
> +                                      + tsv110_mdu_issue + tsv110_alu1_issue
> +                                      + tsv110_alu2_issue + tsv110_alu3_issue + tsv110_ls1_issue + tsv110_ls2_issue")
> +
> +;; Simple Execution Unit:
> +;;
> +;; Simple ALU without shift
> +(define_insn_reservation "tsv110_alu" 1
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "alu_imm,logic_imm,\
> +                           alu_sreg,logic_reg,\
> +                           adc_imm,adc_reg,\
> +                           adr,bfm,clz,rbit,rev,\
> +                           shift_imm,shift_reg,\
> +                           mov_imm,mov_reg,\
> +                           mvn_imm,mvn_reg,\
> +                           mrs,multiple,no_insn"))
> +  "tsv110_alu1|tsv110_alu2|tsv110_alu3")
> +
> +(define_insn_reservation "tsv110_alus" 1
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "alus_imm,logics_imm,\
> +                           alus_sreg,logics_reg,\
> +                           adcs_imm,adcs_reg"))
> +  "tsv110_alu2|tsv110_alu3")
> +
> +;; ALU ops with shift
> +(define_insn_reservation "tsv110_alu_shift" 2
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "extend,\
> +                           alu_shift_imm,alu_shift_reg,\
> +                           crc,logic_shift_imm,logic_shift_reg,\
> +                           mov_shift,mvn_shift,\
> +                           mov_shift_reg,mvn_shift_reg"))
> +  "tsv110_mdu")
> +
> +(define_insn_reservation "tsv110_alus_shift" 2
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "alus_shift_imm,alus_shift_reg,\
> +                           logics_shift_imm,logics_shift_reg"))
> +  "tsv110_alu2")
> +
> +;; Multiplies instructions
> +(define_insn_reservation "tsv110_mult" 3
> +  (and (eq_attr "tune" "tsv110")
> +       (ior (eq_attr "mul32" "yes")
> +           (eq_attr "mul64" "yes")))
> +  "tsv110_mdu")
> +
> +;; Integer divide
> +(define_insn_reservation "tsv110_div" 10
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "udiv,sdiv"))
> +  "tsv110_mdu*10")
> +
> +;; Block all issue pipes for a cycle
> +(define_insn_reservation "tsv110_block" 1
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "block"))
> +  "tsv110_block")
> +
> +;; Branch execution Unit
> +;;
> +;; Branches take two issue slot.
> +;; No latency as there is no result
> +(define_insn_reservation "tsv110_branch" 0
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "branch"))
> +  "tsv110_alu1|tsv110_alu2")
> +
> +;; Load-store execution Unit
> +;;
> +;; Loads of up to two words.
> +(define_insn_reservation "tsv110_load1" 4
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "load1,load2"))
> +  "tsv110_ls1|tsv110_ls2")
> +
> +;; Stores of up to two words.
> +(define_insn_reservation "tsv110_store1" 0
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "store1,store2"))
> +  "tsv110_ls1|tsv110_ls2")
> +
> +;; Advanced SIMD Unit - Integer Arithmetic Instructions.
> +
> +(define_insn_reservation  "tsv110_neon_abd_aba" 4
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "neon_abd,neon_arith_acc"))
> +  "tsv110_fsu1,tsv110_fsu2")
> +
> +(define_insn_reservation  "tsv110_neon_abd_aba_q" 4
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "neon_arith_acc_q"))
> +  "(tsv110_fsu1,tsv110_fsu2)+(tsv110_fsu1,tsv110_fsu2)")
> +
> +(define_insn_reservation  "tsv110_neon_arith_basic" 2
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "tsv110_neon_type" "neon_arith_basic"))
> +  "tsv110_fsu1,tsv110_fsu2")
> +
> +(define_insn_reservation  "tsv110_neon_arith_complex" 4
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "tsv110_neon_type" "neon_arith_complex"))
> +  "tsv110_fsu1,tsv110_fsu2")
> +
> +;; Integer Multiply Instructions.
> +;; D-form
> +(define_insn_reservation "tsv110_neon_multiply" 4
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "tsv110_neon_type" "neon_multiply"))
> +  "tsv110_fsu1")
> +
> +(define_insn_reservation "tsv110_neon_multiply_dlong" 2
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "neon_mul_d_long"))
> +  "tsv110_fsu1")
> +
> +;; Q-form
> +(define_insn_reservation "tsv110_neon_multiply_q" 8
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "tsv110_neon_type" "neon_multiply_q"))
> +  "(tsv110_fsu1,tsv110_fsu1)+(tsv110_fsu1,tsv110_fsu1)")
> +
> +;; Integer Shift Instructions.
> +
> +(define_insn_reservation
> +  "tsv110_neon_shift_acc" 4
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "tsv110_neon_type" "neon_shift_acc,\
> +          neon_shift_imm_basic,neon_shift_imm_complex,neon_shift_reg_basic,\
> +          neon_shift_reg_complex"))
> +  "tsv110_fsu1")
> +
> +(define_insn_reservation
> +  "tsv110_neon_shift_acc_q" 4
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "tsv110_neon_type" "neon_shift_reg_basic_q,\
> +          neon_shift_reg_complex_q"))
> +  "(tsv110_fsu1,tsv110_fsu1)+(tsv110_fsu1,tsv110_fsu1)")
> +
> +;; Floating Point Instructions.
> +
> +(define_insn_reservation
> +  "tsv110_neon_fp_negabs" 2
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "tsv110_neon_type" "neon_fp_negabs"))
> +  "(tsv110_fsu1|tsv110_fsu2)")
> +
> +(define_insn_reservation
> +  "tsv110_neon_fp_arith" 4
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "tsv110_neon_type" "neon_fp_arith"))
> +  "(tsv110_fsu1|tsv110_fsu2)")
> +
> +(define_insn_reservation
> +  "tsv110_neon_fp_arith_q" 4
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "tsv110_neon_type" "neon_fp_arith_q"))
> +  "(tsv110_fsu1+tsv110_fsu2)")
> +
> +(define_insn_reservation
> +  "tsv110_neon_fp_minmax_q" 2
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "neon_fp_minmax_s_q,neon_fp_minmax_d_q"))
> +  "(tsv110_fsu1+tsv110_fsu2)")
> +
> +(define_insn_reservation
> +  "tsv110_neon_fp_reductions_q" 4
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "tsv110_neon_type" "neon_fp_reductions_q"))
> +  "(tsv110_fsu1|tsv110_fsu2)")
> +
> +(define_insn_reservation
> +  "tsv110_neon_fp_cvt_int" 2
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "tsv110_neon_type" "neon_fp_cvt_int,neon_fp_cvt_int_q"))
> +  "(tsv110_fsu1|tsv110_fsu2)")
> +
> +(define_insn_reservation
> +  "tsv110_neon_fp_mul" 5
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "tsv110_neon_type" "neon_fp_mul"))
> +  "(tsv110_fsu1|tsv110_fsu2)")
> +
> +(define_insn_reservation
> +  "tsv110_neon_fp_mul_q" 5
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "tsv110_neon_type" "neon_fp_mul_q"))
> +  "(tsv110_fsu1+tsv110_fsu2)")
> +
> +(define_insn_reservation
> +  "tsv110_neon_fp_mla" 7
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "tsv110_neon_type" "neon_fp_mla,\
> +          neon_fp_recps_rsqrts"))
> +  "(tsv110_fsu1|tsv110_fsu2)")
> +
> +(define_insn_reservation
> +  "tsv110_neon_fp_recpe_rsqrte" 3
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "tsv110_neon_type" "neon_fp_recpe_rsqrte"))
> +  "(tsv110_fsu1|tsv110_fsu2)")
> +
> +(define_insn_reservation
> +  "tsv110_neon_fp_mla_q" 7
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "tsv110_neon_type" "neon_fp_mla_q,\
> +          neon_fp_recps_rsqrts_q"))
> +  "(tsv110_fsu1+tsv110_fsu2)")
> +
> +(define_insn_reservation
> +  "tsv110_neon_fp_recpe_rsqrte_q" 3
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "tsv110_neon_type" "neon_fp_recpe_rsqrte_q"))
> +  "(tsv110_fsu1+tsv110_fsu2)")
> +
> +;; Miscellaneous Instructions.
> +
> +(define_insn_reservation
> +  "tsv110_neon_bitops" 2
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "tsv110_neon_type" "neon_bitops"))
> +  "(tsv110_fsu1,tsv110_fsu2)")
> +
> +(define_insn_reservation
> +  "tsv110_neon_dup" 4
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "neon_from_gp,f_mcr"))
> +  "(tsv110_alu1,tsv110_fsu1,tsv110_fsu2)")
> +
> +(define_insn_reservation
> +  "tsv110_neon_mov" 2
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "f_mcrr"))
> +  "(tsv110_fsu1|tsv110_fsu2)")
> +
> +(define_insn_reservation
> +  "tsv110_neon_bitops_q" 2
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "tsv110_neon_type" "neon_bitops_q"))
> +  "(tsv110_fsu1+tsv110_fsu2)")
> +
> +(define_insn_reservation
> +  "tsv110_neon_from_gp_q" 4
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "tsv110_neon_type" "neon_from_gp_q"))
> +  "(tsv110_alu1,tsv110_fsu1,tsv110_fsu2)")
> +
> +(define_insn_reservation
> +  "tsv110_neon_to_gp" 3
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "neon_to_gp,neon_to_gp_q"))
> +  "(tsv110_fsu1)")
> +
> +;; Load Instructions.
> +
> +(define_insn_reservation
> +  "tsv110_neon_ld1_lane" 8
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "neon_load1_one_lane,neon_load1_one_lane_q,\
> +          neon_load1_all_lanes,neon_load1_all_lanes_q"))
> +  "((tsv110_ls1*2)|(tsv110_ls2*2)|(tsv110_fsu1*2)|(tsv110_fsu2*2))")
> +
> +(define_insn_reservation
> +  "tsv110_neon_ld1_reg1" 6
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "f_loads,f_loadd,neon_load1_1reg,neon_load1_1reg_q"))
> +  "((tsv110_ls1)|(tsv110_ls2))")
> +
> +(define_insn_reservation
> +  "tsv110_neon_ld1_reg2" 6
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "neon_load1_2reg,neon_load1_2reg_q"))
> +  "((tsv110_ls1*2)|(tsv110_ls2*2))")
> +
> +(define_insn_reservation
> +  "tsv110_neon_ld1_reg3" 7
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "neon_load1_3reg,neon_load1_3reg_q"))
> +  "((tsv110_ls1*6)|(tsv110_ls2*6))")
> +
> +(define_insn_reservation
> +  "tsv110_neon_ld1_reg4" 7
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "neon_load1_4reg,neon_load1_4reg_q"))
> +  "((tsv110_ls1*8)|(tsv110_ls2*8))")
> +
> +(define_insn_reservation
> +  "tsv110_neon_ld2" 8
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "neon_load1_2reg,neon_load1_2reg_q,\
> +          neon_load2_2reg,neon_load2_2reg_q,neon_load2_all_lanes,\
> +          neon_load2_all_lanes_q,neon_load2_one_lane,neon_load2_one_lane_q"))
> +  "((tsv110_ls1*4)|(tsv110_ls2*4)|(tsv110_fsu1*4)|(tsv110_fsu2*4))")
> +
> +(define_insn_reservation
> +  "tsv110_neon_ld3" 9
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "neon_load3_3reg,neon_load3_3reg_q,\
> +          neon_load3_one_lane,neon_load3_one_lane_q,\
> +          neon_load3_all_lanes,neon_load3_all_lanes_q"))
> +  "((tsv110_ls1*6)|(tsv110_ls2*6)|(tsv110_fsu1*6)|(tsv110_fsu2*6))")
> +
> +(define_insn_reservation
> +  "tsv110_neon_ld4_lane" 9
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "neon_load4_all_lanes,neon_load4_all_lanes_q,\
> +          neon_load4_one_lane,neon_load4_one_lane_q"))
> +  "((tsv110_ls1*8)|(tsv110_ls2*8)|(tsv110_fsu1*8)|(tsv110_fsu2*8))")
> +
> +(define_insn_reservation
> +  "tsv110_neon_ld4_reg" 11
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "neon_load4_all_lanes,neon_load4_all_lanes_q,\
> +          neon_load4_one_lane,neon_load4_one_lane_q"))
> +  "((tsv110_ls1*16)|(tsv110_ls2*16)|(tsv110_fsu1*16)|(tsv110_fsu2*16))")
> +
> +;; Store Instructions.
> +
> +(define_insn_reservation
> +  "tsv110_neon_store_a" 0
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "tsv110_neon_type" "neon_store_a"))
> +  "tsv110_fsu1|tsv110_fsu2")
> +
> +(define_insn_reservation
> +  "tsv110_neon_store_b" 0
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "tsv110_neon_type" "neon_store_b"))
> +  "(tsv110_fsu1|tsv110_fsu2)")
> +
> +;; 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
> +  "tsv110_neon_store_complex" 0
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "tsv110_neon_type" "neon_store_complex"))
> +  "tsv110_block*2")
> +
> +;; Floating-Point Operations.
> +
> +(define_insn_reservation "tsv110_fp_const" 2
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "fconsts,fconstd,fmov"))
> +  "(tsv110_fsu1|tsv110_fsu2)")
> +
> +(define_insn_reservation "tsv110_fp_add_sub" 5
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "fadds,faddd,fmuls,fmuld"))
> +  "(tsv110_fsu1|tsv110_fsu2)")
> +
> +(define_insn_reservation "tsv110_fp_mac" 7
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "fmacs,ffmas,fmacd,ffmad"))
> +  "(tsv110_fsu1|tsv110_fsu2)")
> +
> +(define_insn_reservation "tsv110_fp_cvt" 3
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "f_cvt"))
> +  "(tsv110_fsu1|tsv110_fsu2)")
> +
> +(define_insn_reservation "tsv110_fp_cvtf2i" 4
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "f_cvtf2i"))
> +  "(tsv110_fsu1)")
> +
> +(define_insn_reservation "tsv110_fp_cvti2f" 4
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "f_cvti2f"))
> +  "((tsv110_alu1*3)|(tsv110_fsu1*3)|(tsv110_fsu2*3))")
> +
> +(define_insn_reservation "tsv110_fp_cmp" 4
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "fcmps,fcmpd"))
> +  "(tsv110_fsu1|tsv110_fsu2)")
> +
> +(define_insn_reservation "tsv110_fp_arith" 2
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "ffariths,ffarithd"))
> +  "(tsv110_fsu1|tsv110_fsu2)")
> +
> +(define_insn_reservation "tsv110_fp_divs" 12
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "fdivs,neon_fp_div_s,fdivd,neon_fp_div_d,\
> +          neon_fp_div_s_q,neon_fp_div_d_q"))
> +  "(tsv110_fsu1*12)")
> +
> +(define_insn_reservation "tsv110_fp_sqrts" 24
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "fsqrts,neon_fp_sqrt_s,fsqrtd,neon_fp_sqrt_d,\
> +          neon_fp_sqrt_s_q,neon_fp_sqrt_d_q"))
> +  "(tsv110_fsu2*24)")
> +
> +(define_insn_reservation "tsv110_crypto_aes" 3
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "crypto_aese,crypto_aesmc"))
> +  "tsv110_fsu1")
> +
> +(define_insn_reservation "tsv110_crypto_sha1_fast" 2
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "crypto_sha1_fast,crypto_sha1_xor"))
> +  "(tsv110_fsu1|tsv110_fsu2)")
> +
> +(define_insn_reservation "tsv110_crypto_sha256_fast" 2
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "crypto_sha1_fast"))
> +  "(tsv110_fsu1)")
> +
> +(define_insn_reservation "tsv110_crypto_complex" 5
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "crypto_sha1_slow,crypto_sha256_slow"))
> +  "tsv110_fsu1")
> +
> +;; We lie with calls.  They take up all issue slots, but are otherwise
> +;; not harmful.
> +(define_insn_reservation "tsv110_call" 1
> +  (and (eq_attr "tune" "tsv110")
> +       (eq_attr "type" "call"))
> +  "tsv110_alu1_issue+tsv110_alu2_issue+tsv110_alu3_issue+tsv110_fsu1_issue+tsv110_fsu2_issue\
> +    +tsv110_mdu_issue+tsv110_ls1_issue+tsv110_ls2_issue"
> +)
> +
> +;; Simple execution unit bypasses
> +(define_bypass 1 "tsv110_alu"
> +                "tsv110_alu,tsv110_alu_shift")
> +(define_bypass 2 "tsv110_alu_shift"
> +                "tsv110_alu,tsv110_alu_shift")
> +
> +;; An MLA or a MUL can feed a dependent MLA.
> +(define_bypass 3 "tsv110_neon_*mla*,tsv110_neon_*mul*"
> +                 "tsv110_neon_*mla*")
> +
> +;; 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 "tsv110_*"
> +                 "tsv110_call,tsv110_branch")


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]