From c8c77ed747abb61a7f3cf34f71539bc87a5d6c3c Mon Sep 17 00:00:00 2001 From: Kyrylo Tkachov Date: Fri, 2 Oct 2020 15:23:19 +0100 Subject: [PATCH] AArch64: Add neoversev1_tunings struct This patch adds a Neoverse V1-specific tuning struct that currently is just a deduplication of the N1 struct it was using before and specifying the SVE width. This will allow us to tweak Neoverse V1 things in the future as needed. Bootstrapped and tested on aarch64-none-linux-gnu. gcc/ * config/aarch64/aarch64.c (neoversev1_tunings): Define. * config/aarch64/aarch64-cores.def (zeus): Use it. (neoverse-v1): Likewise. --- gcc/config/aarch64/aarch64-cores.def | 4 ++-- gcc/config/aarch64/aarch64.c | 26 ++++++++++++++++++++++++++ 2 files changed, 28 insertions(+), 2 deletions(-) diff --git a/gcc/config/aarch64/aarch64-cores.def b/gcc/config/aarch64/aarch64-cores.def index ac2a9b4cfe6..b2e1932d120 100644 --- a/gcc/config/aarch64/aarch64-cores.def +++ b/gcc/config/aarch64/aarch64-cores.def @@ -136,8 +136,8 @@ AARCH64_CORE("thunderx3t110", thunderx3t110, thunderx3t110, 8_3A, AARCH64_FL_ /* ARMv8.4-A Architecture Processors. */ /* Arm ('A') cores. */ -AARCH64_CORE("zeus", zeus, cortexa57, 8_4A, AARCH64_FL_FOR_ARCH8_4 | AARCH64_FL_SVE | AARCH64_FL_RCPC | AARCH64_FL_I8MM | AARCH64_FL_BF16 | AARCH64_FL_F16 | AARCH64_FL_PROFILE | AARCH64_FL_SSBS | AARCH64_FL_RNG, neoversen1, 0x41, 0xd40, -1) -AARCH64_CORE("neoverse-v1", neoversev1, cortexa57, 8_4A, AARCH64_FL_FOR_ARCH8_4 | AARCH64_FL_SVE | AARCH64_FL_RCPC | AARCH64_FL_I8MM | AARCH64_FL_BF16 | AARCH64_FL_F16 | AARCH64_FL_PROFILE | AARCH64_FL_SSBS | AARCH64_FL_RNG, neoversen1, 0x41, 0xd40, -1) +AARCH64_CORE("zeus", zeus, cortexa57, 8_4A, AARCH64_FL_FOR_ARCH8_4 | AARCH64_FL_SVE | AARCH64_FL_RCPC | AARCH64_FL_I8MM | AARCH64_FL_BF16 | AARCH64_FL_F16 | AARCH64_FL_PROFILE | AARCH64_FL_SSBS | AARCH64_FL_RNG, neoversev1, 0x41, 0xd40, -1) +AARCH64_CORE("neoverse-v1", neoversev1, cortexa57, 8_4A, AARCH64_FL_FOR_ARCH8_4 | AARCH64_FL_SVE | AARCH64_FL_RCPC | AARCH64_FL_I8MM | AARCH64_FL_BF16 | AARCH64_FL_F16 | AARCH64_FL_PROFILE | AARCH64_FL_SSBS | AARCH64_FL_RNG, neoversev1, 0x41, 0xd40, -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.c b/gcc/config/aarch64/aarch64.c index a3408f48c82..3cf20ea5ab7 100644 --- a/gcc/config/aarch64/aarch64.c +++ b/gcc/config/aarch64/aarch64.c @@ -1336,6 +1336,32 @@ static const struct tune_params neoversen1_tunings = &generic_prefetch_tune }; +static const struct tune_params neoversev1_tunings = +{ + &cortexa57_extra_costs, + &generic_addrcost_table, + &generic_regmove_cost, + &cortexa57_vector_cost, + &generic_branch_cost, + &generic_approx_modes, + SVE_256, /* sve_width */ + 4, /* memmov_cost */ + 3, /* issue_rate */ + (AARCH64_FUSE_AES_AESMC | AARCH64_FUSE_CMP_BRANCH), /* fusible_ops */ + "32:16", /* function_align. */ + "4", /* 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 +}; + static const struct tune_params a64fx_tunings = { &generic_extra_costs,