On Tue, 28 Nov 2023 at 12:21, Richard Sandiford
<richard.sandif...@arm.com> wrote:
>
> Philipp Tomsich <philipp.toms...@vrull.eu> writes:
> > This patch adds initial support for Ampere-1B core.
> >
> > The Ampere-1B core implements ARMv8.7 with the following (compiler
> > visible) extensions:
> > - CSSC (Common Short Sequence Compression instructions),
> > - MTE (Memory Tagging Extension)
> > - SM3/SM4
> >
> > gcc/ChangeLog:
> >
> > * config/aarch64/aarch64-cores.def (AARCH64_CORE): Add ampere-1b
> > * config/aarch64/aarch64-cost-tables.h: Add ampere1b_extra_costs
> > * config/aarch64/aarch64-tune.md: Regenerate
> > * config/aarch64/aarch64.cc: Include ampere1b tuning model
> > * doc/invoke.texi: Document -mcpu=ampere1b
> > * config/aarch64/tuning_models/ampere1b.h: New file.
>
> OK, thanks, but:
>
> >
> > Signed-off-by: Philipp Tomsich <philipp.toms...@vrull.eu>
> > ---
> >
> > Changes in v2:
> > - moved ampere1b model to a separated file
> > - regenerated aarch64-tune.md after rebase
> >
> > gcc/config/aarch64/aarch64-cores.def | 1 +
> > gcc/config/aarch64/aarch64-cost-tables.h | 107 ++++++++++++++++++
> > gcc/config/aarch64/aarch64-tune.md | 2 +-
> > gcc/config/aarch64/aarch64.cc | 1 +
> > gcc/config/aarch64/tuning_models/ampere1b.h | 114 ++++++++++++++++++++
> > gcc/doc/invoke.texi | 2 +-
> > 6 files changed, 225 insertions(+), 2 deletions(-)
> > create mode 100644 gcc/config/aarch64/tuning_models/ampere1b.h
> >
> > diff --git a/gcc/config/aarch64/aarch64-cores.def
> > b/gcc/config/aarch64/aarch64-cores.def
> > index 16752b77f4b..ad896a80f1f 100644
> > --- a/gcc/config/aarch64/aarch64-cores.def
> > +++ b/gcc/config/aarch64/aarch64-cores.def
> > @@ -74,6 +74,7 @@ AARCH64_CORE("thunderxt83", thunderxt83, thunderx,
> > V8A, (CRC, CRYPTO), thu
> > /* Ampere Computing ('\xC0') cores. */
> > AARCH64_CORE("ampere1", ampere1, cortexa57, V8_6A, (F16, RNG, AES, SHA3),
> > ampere1, 0xC0, 0xac3, -1)
> > AARCH64_CORE("ampere1a", ampere1a, cortexa57, V8_6A, (F16, RNG, AES, SHA3,
> > SM4, MEMTAG), ampere1a, 0xC0, 0xac4, -1)
> > +AARCH64_CORE("ampere1b", ampere1b, cortexa57, V8_7A, (F16, RNG, AES, SHA3,
> > SM4, MEMTAG, CSSC), ampere1b, 0xC0, 0xac5, -1)
> > /* Do not swap around "emag" and "xgene1",
> > this order is required to handle variant correctly. */
> > AARCH64_CORE("emag", emag, xgene1, V8A, (CRC, CRYPTO),
> > emag, 0x50, 0x000, 3)
> > diff --git a/gcc/config/aarch64/aarch64-cost-tables.h
> > b/gcc/config/aarch64/aarch64-cost-tables.h
> > index 0cb638f3a13..4c8da7f119b 100644
> > --- a/gcc/config/aarch64/aarch64-cost-tables.h
> > +++ b/gcc/config/aarch64/aarch64-cost-tables.h
> > @@ -882,4 +882,111 @@ const struct cpu_cost_table ampere1a_extra_costs =
> > }
> > };
> >
> > +const struct cpu_cost_table ampere1b_extra_costs =
> > +{
> > + /* ALU */
> > + {
> > + 0, /* arith. */
> > + 0, /* logical. */
> > + 0, /* shift. */
> > + COSTS_N_INSNS (1), /* 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 (2), /* flag_setting. */
> > + COSTS_N_INSNS (2), /* extend. */
> > + COSTS_N_INSNS (3), /* add. */
> > + COSTS_N_INSNS (3), /* extend_add. */
> > + COSTS_N_INSNS (12) /* idiv. */
> > + },
> > + /* MULT DImode */
> > + {
> > + COSTS_N_INSNS (2), /* simple. */
> > + 0, /* flag_setting (N/A). */
> > + COSTS_N_INSNS (2), /* extend. */
> > + COSTS_N_INSNS (3), /* add. */
> > + COSTS_N_INSNS (3), /* extend_add. */
> > + COSTS_N_INSNS (18) /* idiv. */
> > + }
> > + },
> > + /* LD/ST */
> > + {
> > + COSTS_N_INSNS (2), /* load. */
> > + COSTS_N_INSNS (2), /* load_sign_extend. */
> > + 0, /* ldrd (n/a). */
> > + 0, /* ldm_1st. */
> > + 0, /* ldm_regs_per_insn_1st. */
> > + 0, /* ldm_regs_per_insn_subsequent. */
> > + COSTS_N_INSNS (3), /* loadf. */
> > + COSTS_N_INSNS (3), /* loadd. */
> > + COSTS_N_INSNS (3), /* load_unaligned. */
> > + 0, /* store. */
> > + 0, /* strd. */
> > + 0, /* stm_1st. */
> > + 0, /* stm_regs_per_insn_1st. */
> > + 0, /* stm_regs_per_insn_subsequent. */
> > + COSTS_N_INSNS (1), /* storef. */
> > + COSTS_N_INSNS (1), /* stored. */
> > + COSTS_N_INSNS (1), /* store_unaligned. */
> > + COSTS_N_INSNS (3), /* loadv. */
> > + COSTS_N_INSNS (3) /* storev. */
> > + },
> > + {
> > + /* FP SFmode */
> > + {
> > + COSTS_N_INSNS (18), /* div. */
> > + COSTS_N_INSNS (3), /* mult. */
> > + COSTS_N_INSNS (3), /* mult_addsub. */
> > + COSTS_N_INSNS (3), /* fma. */
> > + COSTS_N_INSNS (2), /* addsub. */
> > + COSTS_N_INSNS (1), /* fpconst. */
> > + COSTS_N_INSNS (2), /* neg. */
> > + COSTS_N_INSNS (2), /* compare. */
> > + COSTS_N_INSNS (2), /* widen. */
> > + COSTS_N_INSNS (2), /* narrow. */
> > + COSTS_N_INSNS (6), /* toint. */
> > + COSTS_N_INSNS (4), /* fromint. */
> > + COSTS_N_INSNS (2) /* roundint. */
> > + },
> > + /* FP DFmode */
> > + {
> > + COSTS_N_INSNS (18), /* div. */
> > + COSTS_N_INSNS (3), /* mult. */
> > + COSTS_N_INSNS (3), /* mult_addsub. */
> > + COSTS_N_INSNS (3), /* fma. */
> > + COSTS_N_INSNS (2), /* addsub. */
> > + COSTS_N_INSNS (1), /* fpconst. */
> > + COSTS_N_INSNS (2), /* neg. */
> > + COSTS_N_INSNS (2), /* compare. */
> > + COSTS_N_INSNS (2), /* widen. */
> > + COSTS_N_INSNS (2), /* narrow. */
> > + COSTS_N_INSNS (6), /* toint. */
> > + COSTS_N_INSNS (4), /* fromint. */
> > + COSTS_N_INSNS (2) /* roundint. */
> > + }
> > + },
> > + /* Vector */
> > + {
> > + COSTS_N_INSNS (1), /* alu. */
> > + COSTS_N_INSNS (2), /* mult. */
> > + COSTS_N_INSNS (1), /* movi. */
> > + COSTS_N_INSNS (1), /* dup. */
> > + COSTS_N_INSNS (1) /* extract. */
> > + }
> > +};
> > +
> > #endif
> > diff --git a/gcc/config/aarch64/aarch64-tune.md
> > b/gcc/config/aarch64/aarch64-tune.md
> > index 61bb8521125..98e6882d432 100644
> > --- a/gcc/config/aarch64/aarch64-tune.md
> > +++ b/gcc/config/aarch64/aarch64-tune.md
> > @@ -1,5 +1,5 @@
> > ;; -*- buffer-read-only: t -*-
> > ;; Generated automatically by gentune.sh from aarch64-cores.def
> > (define_attr "tune"
> > -
> > "cortexa34,cortexa35,cortexa53,cortexa57,cortexa72,cortexa73,thunderx,thunderxt88p1,thunderxt88,octeontx,octeontxt81,octeontxt83,thunderxt81,thunderxt83,ampere1,ampere1a,emag,xgene1,falkor,qdf24xx,exynosm1,phecda,thunderx2t99p1,vulcan,thunderx2t99,cortexa55,cortexa75,cortexa76,cortexa76ae,cortexa77,cortexa78,cortexa78ae,cortexa78c,cortexa65,cortexa65ae,cortexx1,cortexx1c,neoversen1,ares,neoversee1,octeontx2,octeontx2t98,octeontx2t96,octeontx2t93,octeontx2f95,octeontx2f95n,octeontx2f95mm,a64fx,tsv110,thunderx3t110,neoversev1,zeus,neoverse512tvb,saphira,cortexa57cortexa53,cortexa72cortexa53,cortexa73cortexa35,cortexa73cortexa53,cortexa75cortexa55,cortexa76cortexa55,cortexr82,cortexa510,cortexa520,cortexa710,cortexa715,cortexa720,cortexx2,cortexx3,cortexx4,neoversen2,neoversev2,demeter,generic,generic_armv8_a,generic_armv9_a"
> > +
> > "cortexa34,cortexa35,cortexa53,cortexa57,cortexa72,cortexa73,thunderx,thunderxt88p1,thunderxt88,octeontx,octeontxt81,octeontxt83,thunderxt81,thunderxt83,ampere1,ampere1a,ampere1b,emag,xgene1,falkor,qdf24xx,exynosm1,phecda,thunderx2t99p1,vulcan,thunderx2t99,cortexa55,cortexa75,cortexa76,cortexa76ae,cortexa77,cortexa78,cortexa78ae,cortexa78c,cortexa65,cortexa65ae,cortexx1,cortexx1c,neoversen1,ares,neoversee1,octeontx2,octeontx2t98,octeontx2t96,octeontx2t93,octeontx2f95,octeontx2f95n,octeontx2f95mm,a64fx,tsv110,thunderx3t110,neoversev1,zeus,neoverse512tvb,saphira,cortexa57cortexa53,cortexa72cortexa53,cortexa73cortexa35,cortexa73cortexa53,cortexa75cortexa55,cortexa76cortexa55,cortexr82,cortexa510,cortexa520,cortexa710,cortexa715,cortexa720,cortexx2,cortexx3,cortexx4,neoversen2,neoversev2,demeter,generic,generic_armv8_a,generic_armv9_a"
> > (const (symbol_ref "((enum attr_tune) aarch64_tune)")))
> > diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
> > index f6f6f94bf43..6a6cceb52c7 100644
> > --- a/gcc/config/aarch64/aarch64.cc
> > +++ b/gcc/config/aarch64/aarch64.cc
> > @@ -375,6 +375,7 @@ static const struct aarch64_flag_desc
> > aarch64_tuning_flags[] =
> > #include "tuning_models/neoversen1.h"
> > #include "tuning_models/ampere1.h"
> > #include "tuning_models/ampere1a.h"
> > +#include "tuning_models/ampere1b.h"
> > #include "tuning_models/neoversev1.h"
> > #include "tuning_models/neoverse512tvb.h"
> > #include "tuning_models/neoversen2.h"
> > diff --git a/gcc/config/aarch64/tuning_models/ampere1b.h
> > b/gcc/config/aarch64/tuning_models/ampere1b.h
> > new file mode 100644
> > index 00000000000..c4928f50d29
> > --- /dev/null
> > +++ b/gcc/config/aarch64/tuning_models/ampere1b.h
> > @@ -0,0 +1,114 @@
> > +/* Tuning model description for the Ampere1B core.
> > + Copyright (C) 2023 Free Software Foundation, Inc.
> > +
> > + This file is part of GCC.
> > +
> > + GCC is free software; you can redistribute it and/or modify it
> > + under the terms of the GNU General Public License as published by
> > + the Free Software Foundation; either version 3, or (at your option)
> > + any later version.
> > +
> > + GCC is distributed in the hope that it will be useful, but
> > + WITHOUT ANY WARRANTY; without even the implied warranty of
> > + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
> > + General Public License for more details.
> > +
> > + You should have received a copy of the GNU General Public License
> > + along with GCC; see the file COPYING3. If not see
> > + <http://www.gnu.org/licenses/>. */
> > +
> > +#ifndef GCC_AARCH64_H_AMPERE1B
> > +#define GCC_AARCH64_H_AMPERE1B
> > +
> > +#include "generic.h"
> > +
> > +static const cpu_prefetch_tune ampere1b_prefetch_tune =
> > +{
> > + 48, /* num_slots */
> > + 64, /* l1_cache_size */
> > + 64, /* l1_cache_line_size */
> > + 2048, /* l2_cache_size */
> > + true, /* prefetch_dynamic_strides */
> > + -1, /* minimum_stride */
> > + -1 /* default_opt_level */
> > +};
> > +
> > +static const advsimd_vec_cost ampere1b_advsimd_vector_cost =
> > +{
> > + 1, /* int_stmt_cost */
> > + 3, /* fp_stmt_cost */
> > + 0, /* ld2_st2_permute_cost */
> > + 0, /* ld3_st3_permute_cost */
> > + 0, /* ld4_st4_permute_cost */
> > + 2, /* permute_cost */
> > + 8, /* reduc_i8_cost */
> > + 6, /* reduc_i16_cost */
> > + 4, /* reduc_i32_cost */
> > + 2, /* reduc_i64_cost */
> > + 9, /* reduc_f16_cost */
> > + 6, /* reduc_f32_cost */
> > + 3, /* reduc_f64_cost */
> > + 5, /* store_elt_extra_cost */
> > + 5, /* vec_to_scalar_cost */
> > + 5, /* scalar_to_vec_cost */
> > + 4, /* align_load_cost */
> > + 4, /* unalign_load_cost */
> > + 1, /* unalign_store_cost */
> > + 1 /* store_cost */
> > +};
> > +
> > +/* Ampere-1B costs for vector insn classes. */
> > +static const struct cpu_vector_cost ampere1b_vector_cost =
> > +{
> > + 1, /* scalar_int_stmt_cost */
> > + 3, /* scalar_fp_stmt_cost */
> > + 4, /* scalar_load_cost */
> > + 1, /* scalar_store_cost */
> > + 1, /* cond_taken_branch_cost */
> > + 1, /* cond_not_taken_branch_cost */
> > + &ere1b_advsimd_vector_cost, /* advsimd */
> > + nullptr, /* sve */
> > + nullptr /* issue_info */
> > +};
> > +
> > +static const struct tune_params ampere1b_tunings =
> > +{
> > + &ere1b_extra_costs,
> > + &generic_addrcost_table,
> > + &generic_regmove_cost,
> > + &ere1b_vector_cost,
> > + &generic_branch_cost,
> > + &generic_approx_modes,
> > + SVE_NOT_IMPLEMENTED, /* sve_width */
> > + { 3, /* load_int. */
> > + 1, /* store_int. */
> > + 4, /* load_fp. */
> > + 4, /* store_fp. */
> > + 4, /* load_pred. */
> > + 4 /* store_pred. */
> > + }, /* memmov_cost. */
> > + 4, /* issue_rate */
> > + (AARCH64_FUSE_ADRP_ADD | AARCH64_FUSE_AES_AESMC |
> > + AARCH64_FUSE_MOV_MOVK | AARCH64_FUSE_MOVK_MOVK |
> > + AARCH64_FUSE_ALU_BRANCH /* adds, ands, bics, ccmp, ccmn */ |
> > + AARCH64_FUSE_CMP_BRANCH | AARCH64_FUSE_ALU_CBZ |
> > + AARCH64_FUSE_ADDSUB_2REG_CONST1),
> > + /* fusible_ops */
> > + "32", /* function_align. */
> > + "4", /* jump_align. */
> > + "32:16", /* loop_align. */
> > + 2, /* int_reassoc_width. */
> > + 4, /* fp_reassoc_width. */
> > + 1, /* 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. */
>
> would you mind testing the performance of
> AARCH64_EXTRA_TUNE_USE_NEW_VECTOR_COSTS? The plan was to make that
> the default at some stage.
We are tuning the entire vector costs for the entire Ampere1-family
(some changes will be needed due to ongoing work to improve the
vectorization of x264 and optimized permute/shuffle sequences) and
plan to include AARCH64_EXTRA_TUNE_USE_NEW_VECTOR_COSTS throughout.
However, this is unlikely to be completed before the end of this year.
OK to apply now and revisit later?
>
> Richard
>
> > + &ere1b_prefetch_tune,
> > + AARCH64_LDP_STP_POLICY_ALIGNED, /* ldp_policy_model. */
> > + AARCH64_LDP_STP_POLICY_ALIGNED /* stp_policy_model. */
> > +};
> > +
> > +#endif /* GCC_AARCH64_H_AMPERE1B */
> > diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
> > index 7666de1e9b2..54e4101e7a2 100644
> > --- a/gcc/doc/invoke.texi
> > +++ b/gcc/doc/invoke.texi
> > @@ -20851,7 +20851,7 @@ performance of the code. Permissible values for
> > this option are:
> > @samp{cortex-r82}, @samp{cortex-x1}, @samp{cortex-x1c}, @samp{cortex-x2},
> > @samp{cortex-x3}, @samp{cortex-x4}, @samp{cortex-a510}, @samp{cortex-a520},
> > @samp{cortex-a710}, @samp{cortex-a715}, @samp{cortex-a720}, @samp{ampere1},
> > -@samp{ampere1a}, and @samp{native}.
> > +@samp{ampere1a}, @samp{ampere1b}, and @samp{native}.
> >
> > The values @samp{cortex-a57.cortex-a53}, @samp{cortex-a72.cortex-a53},
> > @samp{cortex-a73.cortex-a35}, @samp{cortex-a73.cortex-a53},
