This patch adds a tuning struct for the Arm Ares CPU and uses it for -m{cpu,tune}=ares.
The tunings are an initial attempt and may be improved upon in the future, but they serve
as a decent starting point for GCC 9.
With this I see a 1.3% improvement on SPEC2006 int and 0.3% on SPEC2006 fp with -mcpu=ares.
On SPEC2017 I see a 0.6% improvement in intrate and changes in the noise for fprate.
* config/aarch64/aarch64.c (ares_tunings): Define.
* config/aarch64/aarch64-cores.def (ares): Use the above.
From-SVN: r268015
+2019-01-17 Kyrylo Tkachov <kyrylo.tkachov@arm.com>
+
+ * config/aarch64/aarch64.c (ares_tunings): Define.
+ * config/aarch64/aarch64-cores.def (ares): Use the above.
+
2019-01-17 Wei Xiao <wei3.xiao@intel.com>
PR target/88794
AARCH64_CORE("cortex-a55", cortexa55, cortexa53, 8_2A, AARCH64_FL_FOR_ARCH8_2 | AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD, cortexa53, 0x41, 0xd05, -1)
AARCH64_CORE("cortex-a75", cortexa75, cortexa57, 8_2A, AARCH64_FL_FOR_ARCH8_2 | AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD, cortexa73, 0x41, 0xd0a, -1)
AARCH64_CORE("cortex-a76", cortexa76, cortexa57, 8_2A, AARCH64_FL_FOR_ARCH8_2 | AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD, cortexa72, 0x41, 0xd0b, -1)
-AARCH64_CORE("ares", ares, cortexa57, 8_2A, AARCH64_FL_FOR_ARCH8_2 | AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD | AARCH64_FL_PROFILE, cortexa72, 0x41, 0xd0c, -1)
+AARCH64_CORE("ares", ares, cortexa57, 8_2A, AARCH64_FL_FOR_ARCH8_2 | AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD | AARCH64_FL_PROFILE, ares, 0x41, 0xd0c, -1)
/* HiSilicon ('H') cores. */
AARCH64_CORE("tsv110", tsv110, cortexa57, 8_2A, AARCH64_FL_FOR_ARCH8_2 | AARCH64_FL_CRYPTO | AARCH64_FL_F16 | AARCH64_FL_AES | AARCH64_FL_SHA2, tsv110, 0x48, 0xd01, -1)
&thunderx2t99_prefetch_tune
};
+static const struct tune_params ares_tunings =
+{
+ &cortexa57_extra_costs,
+ &generic_addrcost_table,
+ &generic_regmove_cost,
+ &cortexa57_vector_cost,
+ &generic_branch_cost,
+ &generic_approx_modes,
+ SVE_NOT_IMPLEMENTED, /* sve_width */
+ 4, /* memmov_cost */
+ 3, /* issue_rate */
+ AARCH64_FUSE_AES_AESMC, /* fusible_ops */
+ "32:16", /* function_align. */
+ "32:16", /* jump_align. */
+ "32:16", /* loop_align. */
+ 2, /* int_reassoc_width. */
+ 4, /* fp_reassoc_width. */
+ 2, /* 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. */
+ &generic_prefetch_tune
+};
+
/* Support for fine-grained override of the tuning structures. */
struct aarch64_tuning_override_function
{