[aarch64] Add HiSilicon tsv110 CPU support

This patch adds HiSilicon's an mcpu: tsv110, which supports v8_4A.
It has been tested on aarch64 and no regressions from this patch.

2018-09-21  Shaokun Zhang  <zhangshaokun@hisilicon.com>
            Bo Zhou  <zbo.zhou@hisilicon.com>

	* config/aarch64/aarch64-cores.def (tsv110): New CPU.
	* config/aarch64/aarch64-tune.md: Regenerated.
	* doc/invoke.texi (AArch64 Options/-mtune): Add "tsv110".
	* config/aarch64/aarch64.c (tsv110_tunings): New tuning table.
	* config/aarch64/aarch64-cost-tables.h: Add "tsv110" extra costs.

Co-Authored-By: Bo Zhou <zbo.zhou@hisilicon.com>

From-SVN: r264470
This commit is contained in:
Shaokun Zhang 2018-09-21 12:25:12 +00:00 committed by Kyrylo Tkachov
parent cbd29d0eae
commit 910f72e78f
6 changed files with 200 additions and 2 deletions

View File

@ -1,3 +1,12 @@
2018-09-21 Shaokun Zhang <zhangshaokun@hisilicon.com>
Bo Zhou <zbo.zhou@hisilicon.com>
* config/aarch64/aarch64-cores.def (tsv110): New CPU.
* config/aarch64/aarch64-tune.md: Regenerated.
* doc/invoke.texi (AArch64 Options/-mtune): Add "tsv110".
* config/aarch64/aarch64.c (tsv110_tunings): New tuning table.
* config/aarch64/aarch64-cost-tables.h: Add "tsv110" extra costs.
2018-09-21 Andrew Stubbs <ams@codesourcery.com>
Julian Brown <julian@codesourcery.com>

View File

@ -92,6 +92,9 @@ AARCH64_CORE("cortex-a76", cortexa76, cortexa57, 8_2A, AARCH64_FL_FOR_ARCH8_2
/* 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)
/* Qualcomm ('Q') cores. */
AARCH64_CORE("saphira", saphira, falkor, 8_4A, AARCH64_FL_FOR_ARCH8_4 | AARCH64_FL_CRYPTO | AARCH64_FL_RCPC, saphira, 0x51, 0xC01, -1)

View File

@ -334,4 +334,108 @@ const struct cpu_cost_table thunderx2t99_extra_costs =
}
};
const struct cpu_cost_table tsv110_extra_costs =
{
/* ALU */
{
0, /* arith. */
0, /* logical. */
0, /* shift. */
0, /* shift_reg. */
COSTS_N_INSNS (1), /* arith_shift. */
COSTS_N_INSNS (1), /* arith_shift_reg. */
COSTS_N_INSNS (1), /* log_shift. */
COSTS_N_INSNS (1), /* log_shift_reg. */
0, /* extend. */
COSTS_N_INSNS (1), /* extend_arith. */
0, /* bfi. */
0, /* bfx. */
0, /* clz. */
0, /* rev. */
0, /* non_exec. */
true /* non_exec_costs_exec. */
},
{
/* MULT SImode */
{
COSTS_N_INSNS (2), /* simple. */
COSTS_N_INSNS (2), /* flag_setting. */
COSTS_N_INSNS (2), /* extend. */
COSTS_N_INSNS (2), /* add. */
COSTS_N_INSNS (2), /* extend_add. */
COSTS_N_INSNS (11) /* idiv. */
},
/* MULT DImode */
{
COSTS_N_INSNS (3), /* simple. */
0, /* flag_setting (N/A). */
COSTS_N_INSNS (3), /* extend. */
COSTS_N_INSNS (3), /* add. */
COSTS_N_INSNS (3), /* extend_add. */
COSTS_N_INSNS (19) /* idiv. */
}
},
/* LD/ST */
{
COSTS_N_INSNS (3), /* load. */
COSTS_N_INSNS (4), /* load_sign_extend. */
COSTS_N_INSNS (3), /* ldrd. */
COSTS_N_INSNS (3), /* ldm_1st. */
1, /* ldm_regs_per_insn_1st. */
2, /* ldm_regs_per_insn_subsequent. */
COSTS_N_INSNS (4), /* loadf. */
COSTS_N_INSNS (4), /* loadd. */
COSTS_N_INSNS (4), /* load_unaligned. */
0, /* store. */
0, /* strd. */
0, /* stm_1st. */
1, /* stm_regs_per_insn_1st. */
2, /* stm_regs_per_insn_subsequent. */
0, /* storef. */
0, /* stored. */
COSTS_N_INSNS (1), /* store_unaligned. */
COSTS_N_INSNS (4), /* loadv. */
COSTS_N_INSNS (4) /* storev. */
},
{
/* FP SFmode */
{
COSTS_N_INSNS (10), /* div. */
COSTS_N_INSNS (4), /* mult. */
COSTS_N_INSNS (4), /* mult_addsub. */
COSTS_N_INSNS (4), /* fma. */
COSTS_N_INSNS (4), /* addsub. */
COSTS_N_INSNS (1), /* fpconst. */
COSTS_N_INSNS (1), /* neg. */
COSTS_N_INSNS (1), /* compare. */
COSTS_N_INSNS (2), /* widen. */
COSTS_N_INSNS (2), /* narrow. */
COSTS_N_INSNS (2), /* toint. */
COSTS_N_INSNS (1), /* fromint. */
COSTS_N_INSNS (2) /* roundint. */
},
/* FP DFmode */
{
COSTS_N_INSNS (17), /* div. */
COSTS_N_INSNS (4), /* mult. */
COSTS_N_INSNS (6), /* mult_addsub. */
COSTS_N_INSNS (6), /* fma. */
COSTS_N_INSNS (3), /* addsub. */
COSTS_N_INSNS (1), /* fpconst. */
COSTS_N_INSNS (1), /* neg. */
COSTS_N_INSNS (1), /* compare. */
COSTS_N_INSNS (2), /* widen. */
COSTS_N_INSNS (2), /* narrow. */
COSTS_N_INSNS (2), /* toint. */
COSTS_N_INSNS (1), /* fromint. */
COSTS_N_INSNS (2) /* roundint. */
}
},
/* Vector */
{
COSTS_N_INSNS (1) /* alu. */
}
};
#endif

View File

@ -1,5 +1,5 @@
;; -*- buffer-read-only: t -*-
;; Generated automatically by gentune.sh from aarch64-cores.def
(define_attr "tune"
"cortexa35,cortexa53,cortexa57,cortexa72,cortexa73,thunderx,thunderxt88p1,thunderxt88,thunderxt81,thunderxt83,xgene1,falkor,qdf24xx,exynosm1,phecda,thunderx2t99p1,vulcan,thunderx2t99,cortexa55,cortexa75,cortexa76,saphira,cortexa57cortexa53,cortexa72cortexa53,cortexa73cortexa35,cortexa73cortexa53,cortexa75cortexa55,cortexa76cortexa55"
"cortexa35,cortexa53,cortexa57,cortexa72,cortexa73,thunderx,thunderxt88p1,thunderxt88,thunderxt81,thunderxt83,xgene1,falkor,qdf24xx,exynosm1,phecda,thunderx2t99p1,vulcan,thunderx2t99,cortexa55,cortexa75,cortexa76,tsv110,saphira,cortexa57cortexa53,cortexa72cortexa53,cortexa73cortexa35,cortexa73cortexa53,cortexa75cortexa55,cortexa76cortexa55"
(const (symbol_ref "((enum attr_tune) aarch64_tune)")))

View File

@ -276,6 +276,22 @@ static const struct cpu_addrcost_table thunderx2t99_addrcost_table =
0, /* imm_offset */
};
static const struct cpu_addrcost_table tsv110_addrcost_table =
{
{
1, /* hi */
0, /* si */
0, /* di */
1, /* ti */
},
0, /* pre_modify */
0, /* post_modify */
0, /* register_offset */
1, /* register_sextend */
1, /* register_zextend */
0, /* imm_offset */
};
static const struct cpu_addrcost_table qdf24xx_addrcost_table =
{
{
@ -368,6 +384,16 @@ static const struct cpu_regmove_cost thunderx2t99_regmove_cost =
4 /* FP2FP */
};
static const struct cpu_regmove_cost tsv110_regmove_cost =
{
1, /* GP2GP */
/* Avoid the use of slow int<->fp moves for spilling by setting
their cost higher than memmov_cost. */
2, /* GP2FP */
3, /* FP2GP */
2 /* FP2FP */
};
/* Generic costs for vector insn classes. */
static const struct cpu_vector_cost generic_vector_cost =
{
@ -428,6 +454,25 @@ static const struct cpu_vector_cost thunderx_vector_cost =
3 /* cond_not_taken_branch_cost */
};
static const struct cpu_vector_cost tsv110_vector_cost =
{
1, /* scalar_int_stmt_cost */
1, /* scalar_fp_stmt_cost */
5, /* scalar_load_cost */
1, /* scalar_store_cost */
2, /* vec_int_stmt_cost */
2, /* vec_fp_stmt_cost */
2, /* vec_permute_cost */
3, /* vec_to_scalar_cost */
2, /* scalar_to_vec_cost */
5, /* vec_align_load_cost */
5, /* vec_unalign_load_cost */
1, /* vec_unalign_store_cost */
1, /* vec_store_cost */
1, /* cond_taken_branch_cost */
1 /* cond_not_taken_branch_cost */
};
/* Generic costs for vector insn classes. */
static const struct cpu_vector_cost cortexa57_vector_cost =
{
@ -605,6 +650,17 @@ static const cpu_prefetch_tune thunderx2t99_prefetch_tune =
-1 /* default_opt_level */
};
static const cpu_prefetch_tune tsv110_prefetch_tune =
{
0, /* num_slots */
64, /* l1_cache_size */
64, /* l1_cache_line_size */
512, /* l2_cache_size */
true, /* prefetch_dynamic_strides */
-1, /* minimum_stride */
-1 /* default_opt_level */
};
static const struct tune_params generic_tunings =
{
&cortexa57_extra_costs,
@ -838,6 +894,32 @@ static const struct tune_params thunderx_tunings =
&thunderx_prefetch_tune
};
static const struct tune_params tsv110_tunings =
{
&tsv110_extra_costs,
&tsv110_addrcost_table,
&tsv110_regmove_cost,
&tsv110_vector_cost,
&generic_branch_cost,
&generic_approx_modes,
4, /* memmov_cost */
4, /* issue_rate */
(AARCH64_FUSE_AES_AESMC | AARCH64_FUSE_CMP_BRANCH
| AARCH64_FUSE_ALU_BRANCH), /* fusible_ops */
"16", /* function_align. */
"4", /* jump_align. */
"8", /* loop_align. */
2, /* int_reassoc_width. */
4, /* fp_reassoc_width. */
1, /* vec_reassoc_width. */
2, /* min_div_recip_mul_sf. */
2, /* min_div_recip_mul_df. */
0, /* max_case_values. */
tune_params::AUTOPREFETCHER_WEAK, /* autoprefetcher_model. */
(AARCH64_EXTRA_TUNE_NONE), /* tune_flags. */
&tsv110_prefetch_tune
};
static const struct tune_params xgene1_tunings =
{
&xgene1_extra_costs,

View File

@ -14998,7 +14998,7 @@ performance of the code. Permissible values for this option are:
@samp{cortex-a57}, @samp{cortex-a72}, @samp{cortex-a73}, @samp{cortex-a75},
@samp{cortex-a76}, @samp{exynos-m1}, @samp{falkor}, @samp{qdf24xx},
@samp{saphira}, @samp{phecda}, @samp{xgene1}, @samp{vulcan}, @samp{thunderx},
@samp{thunderxt88}, @samp{thunderxt88p1}, @samp{thunderxt81},
@samp{thunderxt88}, @samp{thunderxt88p1}, @samp{thunderxt81},@samp{tsv110},
@samp{thunderxt83}, @samp{thunderx2t99}, @samp{cortex-a57.cortex-a53},
@samp{cortex-a72.cortex-a53}, @samp{cortex-a73.cortex-a35},
@samp{cortex-a73.cortex-a53}, @samp{cortex-a75.cortex-a55},