Commit 5ec1ae3b by Evandro Menezes Committed by Evandro Menezes

Add cost model for Exynos M1

gcc/
	* config/aarch64/aarch64-cores.def: Use the Exynos M1 cost model.
	* config/aarch64/aarch64.c (exynosm1_addrcost_table): New variable.
	(exynosm1_regmove_cost): Likewise.
	(exynosm1_vector_cost): Likewise.
	(exynosm1_tunings): Likewise.
	* config/arm/aarch-cost-tables.h (exynosm1_extra_costs): Likewise.
	* config/arm/arm.c (arm_exynosm1_tune): Likewise.
	* config/arm/arm-cores.def: Use the Exynos M1 cost model.

From-SVN: r231233
parent b3e46655
2015-12-03 Evandro Menezes <e.menezes@samsung.com>
* config/aarch64/aarch64-cores.def: Use the Exynos M1 cost model.
* config/aarch64/aarch64.c (exynosm1_addrcost_table): New variable.
(exynosm1_regmove_cost): Likewise.
(exynosm1_vector_cost): Likewise.
(exynosm1_tunings): Likewise.
* config/arm/aarch-cost-tables.h (exynosm1_extra_costs): Likewise.
* config/arm/arm.c (arm_exynos_m1_tune): Likewise.
2015-12-03 Alan Lawrence <alan.lawrence@arm.com> 2015-12-03 Alan Lawrence <alan.lawrence@arm.com>
Richard Biener <richard.guenther@gmail.com> Richard Biener <richard.guenther@gmail.com>
...@@ -44,7 +44,7 @@ AARCH64_CORE("cortex-a35", cortexa35, cortexa53, 8A, AARCH64_FL_FOR_ARCH8 | AA ...@@ -44,7 +44,7 @@ AARCH64_CORE("cortex-a35", cortexa35, cortexa53, 8A, AARCH64_FL_FOR_ARCH8 | AA
AARCH64_CORE("cortex-a53", cortexa53, cortexa53, 8A, AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC, cortexa53, "0x41", "0xd03") AARCH64_CORE("cortex-a53", cortexa53, cortexa53, 8A, AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC, cortexa53, "0x41", "0xd03")
AARCH64_CORE("cortex-a57", cortexa57, cortexa57, 8A, AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC, cortexa57, "0x41", "0xd07") AARCH64_CORE("cortex-a57", cortexa57, cortexa57, 8A, AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC, cortexa57, "0x41", "0xd07")
AARCH64_CORE("cortex-a72", cortexa72, cortexa57, 8A, AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC, cortexa72, "0x41", "0xd08") AARCH64_CORE("cortex-a72", cortexa72, cortexa57, 8A, AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC, cortexa72, "0x41", "0xd08")
AARCH64_CORE("exynos-m1", exynosm1, cortexa57, 8A, AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC | AARCH64_FL_CRYPTO, cortexa72, "0x53", "0x001") AARCH64_CORE("exynos-m1", exynosm1, cortexa57, 8A, AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC | AARCH64_FL_CRYPTO, exynosm1, "0x53", "0x001")
AARCH64_CORE("qdf24xx", qdf24xx, cortexa57, 8A, AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC | AARCH64_FL_CRYPTO, cortexa57, "0x51", "0x800") AARCH64_CORE("qdf24xx", qdf24xx, cortexa57, 8A, AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC | AARCH64_FL_CRYPTO, cortexa57, "0x51", "0x800")
AARCH64_CORE("thunderx", thunderx, thunderx, 8A, AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC | AARCH64_FL_CRYPTO, thunderx, "0x43", "0x0a1") AARCH64_CORE("thunderx", thunderx, thunderx, 8A, AARCH64_FL_FOR_ARCH8 | AARCH64_FL_CRC | AARCH64_FL_CRYPTO, thunderx, "0x43", "0x0a1")
AARCH64_CORE("xgene1", xgene1, xgene1, 8A, AARCH64_FL_FOR_ARCH8, xgene1, "0x50", "0x000") AARCH64_CORE("xgene1", xgene1, xgene1, 8A, AARCH64_FL_FOR_ARCH8, xgene1, "0x50", "0x000")
......
...@@ -216,6 +216,22 @@ static const struct cpu_addrcost_table cortexa57_addrcost_table = ...@@ -216,6 +216,22 @@ static const struct cpu_addrcost_table cortexa57_addrcost_table =
0, /* imm_offset */ 0, /* imm_offset */
}; };
static const struct cpu_addrcost_table exynosm1_addrcost_table =
{
{
0, /* hi */
0, /* si */
0, /* di */
2, /* ti */
},
0, /* pre_modify */
0, /* post_modify */
1, /* register_offset */
1, /* register_sextend */
2, /* register_zextend */
0, /* imm_offset */
};
static const struct cpu_addrcost_table xgene1_addrcost_table = static const struct cpu_addrcost_table xgene1_addrcost_table =
{ {
{ {
...@@ -262,6 +278,16 @@ static const struct cpu_regmove_cost cortexa53_regmove_cost = ...@@ -262,6 +278,16 @@ static const struct cpu_regmove_cost cortexa53_regmove_cost =
2 /* FP2FP */ 2 /* FP2FP */
}; };
static const struct cpu_regmove_cost exynosm1_regmove_cost =
{
1, /* GP2GP */
/* Avoid the use of slow int<->fp moves for spilling by setting
their cost higher than memmov_cost (actual, 4 and 9). */
9, /* GP2FP */
9, /* FP2GP */
1 /* FP2FP */
};
static const struct cpu_regmove_cost thunderx_regmove_cost = static const struct cpu_regmove_cost thunderx_regmove_cost =
{ {
2, /* GP2GP */ 2, /* GP2GP */
...@@ -314,6 +340,22 @@ static const struct cpu_vector_cost cortexa57_vector_cost = ...@@ -314,6 +340,22 @@ static const struct cpu_vector_cost cortexa57_vector_cost =
1 /* cond_not_taken_branch_cost */ 1 /* cond_not_taken_branch_cost */
}; };
static const struct cpu_vector_cost exynosm1_vector_cost =
{
1, /* scalar_stmt_cost */
5, /* scalar_load_cost */
1, /* scalar_store_cost */
3, /* vec_stmt_cost */
3, /* vec_to_scalar_cost */
3, /* 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. */ /* Generic costs for vector insn classes. */
static const struct cpu_vector_cost xgene1_vector_cost = static const struct cpu_vector_cost xgene1_vector_cost =
{ {
...@@ -470,6 +512,30 @@ static const struct tune_params cortexa72_tunings = ...@@ -470,6 +512,30 @@ static const struct tune_params cortexa72_tunings =
(AARCH64_EXTRA_TUNE_NONE) /* tune_flags. */ (AARCH64_EXTRA_TUNE_NONE) /* tune_flags. */
}; };
static const struct tune_params exynosm1_tunings =
{
&exynosm1_extra_costs,
&exynosm1_addrcost_table,
&exynosm1_regmove_cost,
&exynosm1_vector_cost,
&generic_branch_cost,
4, /* memmov_cost */
3, /* issue_rate */
(AARCH64_FUSE_NOTHING), /* fusible_ops */
4, /* function_align. */
4, /* jump_align. */
4, /* 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. */
48, /* max_case_values. */
64, /* cache_line_size. */
tune_params::AUTOPREFETCHER_OFF, /* autoprefetcher_model. */
(AARCH64_EXTRA_TUNE_NONE) /* tune_flags. */
};
static const struct tune_params thunderx_tunings = static const struct tune_params thunderx_tunings =
{ {
&thunderx_extra_costs, &thunderx_extra_costs,
......
...@@ -331,6 +331,109 @@ const struct cpu_cost_table cortexa57_extra_costs = ...@@ -331,6 +331,109 @@ const struct cpu_cost_table cortexa57_extra_costs =
} }
}; };
const struct cpu_cost_table exynosm1_extra_costs =
{
/* ALU */
{
0, /* arith. */
0, /* logical. */
0, /* shift. */
COSTS_N_INSNS (0), /* shift_reg. */
0, /* arith_shift. */
COSTS_N_INSNS (1), /* arith_shift_reg. */
0, /* 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 (3), /* flag_setting. */
COSTS_N_INSNS (4), /* extend. */
COSTS_N_INSNS (2), /* add. */
COSTS_N_INSNS (4), /* extend_add. */
COSTS_N_INSNS (19) /* idiv. */
},
/* MULT DImode */
{
COSTS_N_INSNS (3), /* simple. */
0, /* flag_setting (N/A). */
COSTS_N_INSNS (4), /* extend. */
COSTS_N_INSNS (3), /* add. */
COSTS_N_INSNS (4), /* extend_add. */
COSTS_N_INSNS (35) /* idiv. */
}
},
/* LD/ST */
{
COSTS_N_INSNS (3), /* load. */
COSTS_N_INSNS (4), /* load_sign_extend. */
COSTS_N_INSNS (3), /* ldrd. */
COSTS_N_INSNS (2), /* 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. */
0, /* store_unaligned. */
COSTS_N_INSNS (1), /* loadv. */
COSTS_N_INSNS (1) /* storev. */
},
{
/* FP SFmode */
{
COSTS_N_INSNS (21), /* div. */
COSTS_N_INSNS (3), /* mult. */
COSTS_N_INSNS (4), /* mult_addsub. */
COSTS_N_INSNS (4), /* fma. */
COSTS_N_INSNS (2), /* addsub. */
COSTS_N_INSNS (0), /* fpconst. */
COSTS_N_INSNS (0), /* neg. */
COSTS_N_INSNS (3), /* compare. */
COSTS_N_INSNS (2), /* widen. */
COSTS_N_INSNS (2), /* narrow. */
COSTS_N_INSNS (12), /* toint. */
COSTS_N_INSNS (7), /* fromint. */
COSTS_N_INSNS (2) /* roundint. */
},
/* FP DFmode */
{
COSTS_N_INSNS (34), /* div. */
COSTS_N_INSNS (3), /* mult. */
COSTS_N_INSNS (4), /* mult_addsub. */
COSTS_N_INSNS (4), /* fma. */
COSTS_N_INSNS (2), /* addsub. */
COSTS_N_INSNS (0), /* fpconst. */
COSTS_N_INSNS (0), /* neg. */
COSTS_N_INSNS (3), /* compare. */
COSTS_N_INSNS (2), /* widen. */
COSTS_N_INSNS (2), /* narrow. */
COSTS_N_INSNS (12), /* toint. */
COSTS_N_INSNS (7), /* fromint. */
COSTS_N_INSNS (2) /* roundint. */
}
},
/* Vector */
{
COSTS_N_INSNS (0) /* alu. */
}
};
const struct cpu_cost_table xgene1_extra_costs = const struct cpu_cost_table xgene1_extra_costs =
{ {
/* ALU */ /* ALU */
......
...@@ -169,7 +169,7 @@ ARM_CORE("cortex-a35", cortexa35, cortexa53, 8A, ARM_FSET_MAKE_CPU1 (FL_LDSCHED ...@@ -169,7 +169,7 @@ ARM_CORE("cortex-a35", cortexa35, cortexa53, 8A, ARM_FSET_MAKE_CPU1 (FL_LDSCHED
ARM_CORE("cortex-a53", cortexa53, cortexa53, 8A, ARM_FSET_MAKE_CPU1 (FL_LDSCHED | FL_CRC32 | FL_FOR_ARCH8A), cortex_a53) ARM_CORE("cortex-a53", cortexa53, cortexa53, 8A, ARM_FSET_MAKE_CPU1 (FL_LDSCHED | FL_CRC32 | FL_FOR_ARCH8A), cortex_a53)
ARM_CORE("cortex-a57", cortexa57, cortexa57, 8A, ARM_FSET_MAKE_CPU1 (FL_LDSCHED | FL_CRC32 | FL_FOR_ARCH8A), cortex_a57) ARM_CORE("cortex-a57", cortexa57, cortexa57, 8A, ARM_FSET_MAKE_CPU1 (FL_LDSCHED | FL_CRC32 | FL_FOR_ARCH8A), cortex_a57)
ARM_CORE("cortex-a72", cortexa72, cortexa57, 8A, ARM_FSET_MAKE_CPU1 (FL_LDSCHED | FL_CRC32 | FL_FOR_ARCH8A), cortex_a57) ARM_CORE("cortex-a72", cortexa72, cortexa57, 8A, ARM_FSET_MAKE_CPU1 (FL_LDSCHED | FL_CRC32 | FL_FOR_ARCH8A), cortex_a57)
ARM_CORE("exynos-m1", exynosm1, cortexa57, 8A, ARM_FSET_MAKE_CPU1 (FL_LDSCHED | FL_CRC32 | FL_FOR_ARCH8A), cortex_a57) ARM_CORE("exynos-m1", exynosm1, exynosm1, 8A, ARM_FSET_MAKE_CPU1 (FL_LDSCHED | FL_CRC32 | FL_FOR_ARCH8A), exynosm1)
ARM_CORE("qdf24xx", qdf24xx, cortexa57, 8A, ARM_FSET_MAKE_CPU1 (FL_LDSCHED | FL_CRC32 | FL_FOR_ARCH8A), cortex_a57) ARM_CORE("qdf24xx", qdf24xx, cortexa57, 8A, ARM_FSET_MAKE_CPU1 (FL_LDSCHED | FL_CRC32 | FL_FOR_ARCH8A), cortex_a57)
ARM_CORE("xgene1", xgene1, xgene1, 8A, ARM_FSET_MAKE_CPU1 (FL_LDSCHED | FL_FOR_ARCH8A), xgene1) ARM_CORE("xgene1", xgene1, xgene1, 8A, ARM_FSET_MAKE_CPU1 (FL_LDSCHED | FL_FOR_ARCH8A), xgene1)
......
...@@ -2006,6 +2006,29 @@ const struct tune_params arm_cortex_a57_tune = ...@@ -2006,6 +2006,29 @@ const struct tune_params arm_cortex_a57_tune =
tune_params::SCHED_AUTOPREF_FULL tune_params::SCHED_AUTOPREF_FULL
}; };
const struct tune_params arm_exynosm1_tune =
{
arm_9e_rtx_costs,
&exynosm1_extra_costs,
NULL, /* Sched adj cost. */
arm_default_branch_cost,
&arm_default_vec_cost,
1, /* Constant limit. */
2, /* Max cond insns. */
8, /* Memset max inline. */
3, /* Issue rate. */
ARM_PREFETCH_NOT_BENEFICIAL,
tune_params::PREF_CONST_POOL_FALSE,
tune_params::PREF_LDRD_TRUE,
tune_params::LOG_OP_NON_SHORT_CIRCUIT_FALSE, /* Thumb. */
tune_params::LOG_OP_NON_SHORT_CIRCUIT_FALSE, /* ARM. */
tune_params::DISPARAGE_FLAGS_ALL,
tune_params::PREF_NEON_64_FALSE,
tune_params::PREF_NEON_STRINGOPS_TRUE,
tune_params::FUSE_NOTHING,
tune_params::SCHED_AUTOPREF_OFF
};
const struct tune_params arm_xgene1_tune = const struct tune_params arm_xgene1_tune =
{ {
arm_9e_rtx_costs, arm_9e_rtx_costs,
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment