diff options
| author | Di Zhao <dizhao@os.amperecomputing.com> | 2023-12-01 16:16:40 +0800 |
|---|---|---|
| committer | Di Zhao <dizhao@os.amperecomputing.com> | 2023-12-01 17:02:46 +0800 |
| commit | 6563d6767ed0f702458f8975cd5d73676c4604cc (patch) | |
| tree | 6f9fabbd0e345e03b15cc84b19096552a4b82c98 /gcc | |
| parent | 82288550012c9382ddfd75a0b4b1bb467d445744 (diff) | |
| download | gcc-6563d6767ed0f702458f8975cd5d73676c4604cc.zip gcc-6563d6767ed0f702458f8975cd5d73676c4604cc.tar.gz gcc-6563d6767ed0f702458f8975cd5d73676c4604cc.tar.bz2 | |
aarch64: modify Ampere CPU tunings on reassociation/FMA
1. Allow reassociation on FP additions.
2. Avoid generating loop-dependant FMA chains. Added a tuning
option 'AARCH64_EXTRA_TUNE_AVOID_CROSS_LOOP_FMA' for this.
gcc/ChangeLog:
* config/aarch64/aarch64-tuning-flags.def
(AARCH64_EXTRA_TUNING_OPTION): New tuning option to avoid
cross-loop FMA.
* config/aarch64/aarch64.cc
(aarch64_override_options_internal): Set
param_avoid_fma_max_bits according to tuning option.
* config/aarch64/tuning_models/ampere1.h (ampere1_tunings):
Modify tunings related with FMA.
* config/aarch64/tuning_models/ampere1a.h (ampere1a_tunings):
Likewise.
* config/aarch64/tuning_models/ampere1b.h (ampere1b_tunings):
Likewise.
Diffstat (limited to 'gcc')
| -rw-r--r-- | gcc/config/aarch64/aarch64-tuning-flags.def | 2 | ||||
| -rw-r--r-- | gcc/config/aarch64/aarch64.cc | 6 | ||||
| -rw-r--r-- | gcc/config/aarch64/tuning_models/ampere1.h | 2 | ||||
| -rw-r--r-- | gcc/config/aarch64/tuning_models/ampere1a.h | 4 | ||||
| -rw-r--r-- | gcc/config/aarch64/tuning_models/ampere1b.h | 5 |
5 files changed, 14 insertions, 5 deletions
diff --git a/gcc/config/aarch64/aarch64-tuning-flags.def b/gcc/config/aarch64/aarch64-tuning-flags.def index 774568e..f28a738 100644 --- a/gcc/config/aarch64/aarch64-tuning-flags.def +++ b/gcc/config/aarch64/aarch64-tuning-flags.def @@ -47,4 +47,6 @@ AARCH64_EXTRA_TUNING_OPTION ("use_new_vector_costs", USE_NEW_VECTOR_COSTS) AARCH64_EXTRA_TUNING_OPTION ("matched_vector_throughput", MATCHED_VECTOR_THROUGHPUT) +AARCH64_EXTRA_TUNING_OPTION ("avoid_cross_loop_fma", AVOID_CROSS_LOOP_FMA) + #undef AARCH64_EXTRA_TUNING_OPTION diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc index bde21f7..0f83ec0 100644 --- a/gcc/config/aarch64/aarch64.cc +++ b/gcc/config/aarch64/aarch64.cc @@ -16083,6 +16083,12 @@ aarch64_override_options_internal (struct gcc_options *opts) && opts->x_optimize >= aarch64_tune_params.prefetch->default_opt_level) opts->x_flag_prefetch_loop_arrays = 1; + /* Avoid loop-dependant FMA chains. */ + if (aarch64_tune_params.extra_tuning_flags + & AARCH64_EXTRA_TUNE_AVOID_CROSS_LOOP_FMA) + SET_OPTION_IF_UNSET (opts, &global_options_set, param_avoid_fma_max_bits, + 512); + aarch64_override_options_after_change_1 (opts); } diff --git a/gcc/config/aarch64/tuning_models/ampere1.h b/gcc/config/aarch64/tuning_models/ampere1.h index 8d2a1c6..a144e8f 100644 --- a/gcc/config/aarch64/tuning_models/ampere1.h +++ b/gcc/config/aarch64/tuning_models/ampere1.h @@ -104,7 +104,7 @@ static const struct tune_params ampere1_tunings = 2, /* min_div_recip_mul_df. */ 0, /* max_case_values. */ tune_params::AUTOPREFETCHER_WEAK, /* autoprefetcher_model. */ - (AARCH64_EXTRA_TUNE_NONE), /* tune_flags. */ + (AARCH64_EXTRA_TUNE_AVOID_CROSS_LOOP_FMA), /* tune_flags. */ &ere1_prefetch_tune, AARCH64_LDP_STP_POLICY_ALIGNED, /* ldp_policy_model. */ AARCH64_LDP_STP_POLICY_ALIGNED /* stp_policy_model. */ diff --git a/gcc/config/aarch64/tuning_models/ampere1a.h b/gcc/config/aarch64/tuning_models/ampere1a.h index c419ffb..f688ed0 100644 --- a/gcc/config/aarch64/tuning_models/ampere1a.h +++ b/gcc/config/aarch64/tuning_models/ampere1a.h @@ -50,13 +50,13 @@ static const struct tune_params ampere1a_tunings = "32:16", /* loop_align. */ 2, /* int_reassoc_width. */ 4, /* fp_reassoc_width. */ - 1, /* fma_reassoc_width. */ + 4, /* fma_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. */ + (AARCH64_EXTRA_TUNE_AVOID_CROSS_LOOP_FMA), /* tune_flags. */ &ere1_prefetch_tune, AARCH64_LDP_STP_POLICY_ALIGNED, /* ldp_policy_model. */ AARCH64_LDP_STP_POLICY_ALIGNED /* stp_policy_model. */ diff --git a/gcc/config/aarch64/tuning_models/ampere1b.h b/gcc/config/aarch64/tuning_models/ampere1b.h index c4928f5..a98b6a9 100644 --- a/gcc/config/aarch64/tuning_models/ampere1b.h +++ b/gcc/config/aarch64/tuning_models/ampere1b.h @@ -99,13 +99,14 @@ static const struct tune_params ampere1b_tunings = "32:16", /* loop_align. */ 2, /* int_reassoc_width. */ 4, /* fp_reassoc_width. */ - 1, /* fma_reassoc_width. */ + 4, /* fma_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_STRONG, /* autoprefetcher_model. */ - (AARCH64_EXTRA_TUNE_CHEAP_SHIFT_EXTEND), /* tune_flags. */ + (AARCH64_EXTRA_TUNE_CHEAP_SHIFT_EXTEND | + AARCH64_EXTRA_TUNE_AVOID_CROSS_LOOP_FMA), /* tune_flags. */ &ere1b_prefetch_tune, AARCH64_LDP_STP_POLICY_ALIGNED, /* ldp_policy_model. */ AARCH64_LDP_STP_POLICY_ALIGNED /* stp_policy_model. */ |