aarch64: Add support for FUJITSU-MONAKA (-mcpu=fujitsu-monaka) CPU

This patch adds initial support for FUJITSU-MONAKA CPU.
The cost model will be corrected in the future.

2024-11-04  Yuta Mukai  <mukai.yuta@fujitsu.com>

gcc/ChangeLog:

	* config/aarch64/aarch64-cores.def (AARCH64_CORE): Add fujitsu-monaka.
	* config/aarch64/aarch64-tune.md: Regenerate.
	* config/aarch64/aarch64.cc: Include fujitsu-monaka tuning model.
	* doc/invoke.texi: Document -mcpu=fujitsu-monaka.
	* config/aarch64/tuning_models/fujitsu_monaka.h: New file.

diff --git a/gcc/config/aarch64/aarch64-cores.def b/gcc/config/aarch64/aarch64-cores.def
index cc2260036887721d0727548f96532fa9b5514a89..9d4abf222435e41f4704063b5a846a463aae30c8 100644 (file)
--- a/gcc/config/aarch64/aarch64-cores.def
+++ b/gcc/config/aarch64/aarch64-cores.def
@@ -132,6 +132,7 @@ AARCH64_CORE("octeontx2f95mm", octeontx2f95mm, cortexa57, V8_2A,  (CRYPTO, PROFI
 
 /* Fujitsu ('F') cores. */
 AARCH64_CORE("a64fx", a64fx, a64fx, V8_2A,  (F16, SVE), a64fx, 0x46, 0x001, -1)
+AARCH64_CORE("fujitsu-monaka", fujitsu_monaka, cortexa57, V9_3A, (F16, FP8, LS64, RNG, CRYPTO, SVE2_AES, SVE2_BITPERM, SVE2_SHA3, SVE2_SM4), fujitsu_monaka, 0x46, 0x003, -1)
 
 /* HiSilicon ('H') cores. */
 AARCH64_CORE("tsv110",  tsv110, tsv110, V8_2A,  (CRYPTO, F16), tsv110,   0x48, 0xd01, -1)

diff --git a/gcc/config/aarch64/aarch64-tune.md b/gcc/config/aarch64/aarch64-tune.md
index 4fce0c507f6c0605f8846abe03d7d77641395c5b..4423a99f3afe8b6bab553e46ac4df9fa9b3813b8 100644 (file)
--- 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,thunderxt88,thunderxt88p1,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,oryon1,cortexa57cortexa53,cortexa72cortexa53,cortexa73cortexa35,cortexa73cortexa53,cortexa75cortexa55,cortexa76cortexa55,cortexr82,cortexa510,cortexa520,cortexa710,cortexa715,cortexa720,cortexa725,cortexx2,cortexx3,cortexx4,cortexx925,neoversen2,cobalt100,neoversen3,neoversev2,grace,neoversev3,neoversev3ae,demeter,generic,generic_armv8_a,generic_armv9_a"
+       "cortexa34,cortexa35,cortexa53,cortexa57,cortexa72,cortexa73,thunderx,thunderxt88,thunderxt88p1,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,fujitsu_monaka,tsv110,thunderx3t110,neoversev1,zeus,neoverse512tvb,saphira,oryon1,cortexa57cortexa53,cortexa72cortexa53,cortexa73cortexa35,cortexa73cortexa53,cortexa75cortexa55,cortexa76cortexa55,cortexr82,cortexa510,cortexa520,cortexa710,cortexa715,cortexa720,cortexa725,cortexx2,cortexx3,cortexx4,cortexx925,neoversen2,cobalt100,neoversen3,neoversev2,grace,neoversev3,neoversev3ae,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 00f99d5004cac9af9b78dd51120fde9d7e7781c6..9347e06f0e9ebbfd1a3d083d9a74bd1ca3f2b06c 100644 (file)
--- a/gcc/config/aarch64/aarch64.cc
+++ b/gcc/config/aarch64/aarch64.cc
@@ -426,6 +426,7 @@ static const struct aarch64_flag_desc aarch64_tuning_flags[] =
 #include "tuning_models/neoversev3.h"
 #include "tuning_models/neoversev3ae.h"
 #include "tuning_models/a64fx.h"
+#include "tuning_models/fujitsu_monaka.h"
 
 /* Support for fine-grained override of the tuning structures.  */
 struct aarch64_tuning_override_function

diff --git a/gcc/config/aarch64/tuning_models/fujitsu_monaka.h b/gcc/config/aarch64/tuning_models/fujitsu_monaka.h
new file mode 100644 (file)
index 0000000..c3a1e06
--- /dev/null
+++ b/gcc/config/aarch64/tuning_models/fujitsu_monaka.h
@@ -0,0 +1,65 @@
+/* Tuning model description for FUJITSU-MONAKA.
+   Copyright (C) 2009-2024 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_FUJITSU_MONAKA
+#define GCC_AARCH64_H_FUJITSU_MONAKA
+
+#include "generic.h"
+#include "generic_armv9_a.h"
+
+/* Tuning parameters for FUJITSU-MONAKA processor.  It is copied from the
+   generic one except for the vector width for now.  */
+static const struct tune_params fujitsu_monaka_tunings =
+{
+  &cortexa76_extra_costs,
+  &generic_armv9_a_addrcost_table,
+  &generic_armv9_a_regmove_cost,
+  &generic_armv9_a_vector_cost,
+  &generic_branch_cost,
+  &generic_approx_modes,
+  SVE_256, /* sve_width.  */
+  { 4, /* load_int.  */
+    1, /* store_int.  */
+    6, /* load_fp.  */
+    2, /* store_fp.  */
+    6, /* load_pred.  */
+    1 /* store_pred.  */
+  }, /* 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,   /* 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_CHEAP_SHIFT_EXTEND
+   | AARCH64_EXTRA_TUNE_USE_NEW_VECTOR_COSTS
+   | AARCH64_EXTRA_TUNE_MATCHED_VECTOR_THROUGHPUT),    /* tune_flags.  */
+  &generic_prefetch_tune,
+  AARCH64_LDP_STP_POLICY_ALWAYS,   /* ldp_policy_model.  */
+  AARCH64_LDP_STP_POLICY_ALWAYS           /* stp_policy_model.  */
+};
+
+#endif /* GCC_AARCH64_H_FUJITSU_MONAKA.  */

diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index 8d92d46eca161c74aa13a52362dad9fa90dc1208..28ef2cde43d3046c9322ccb30738b1506622e9e9 100644 (file)
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -21493,7 +21493,7 @@ performance of the code.  Permissible values for this option are:
 @samp{octeontx2}, @samp{octeontx2t98}, @samp{octeontx2t96}
 @samp{octeontx2t93}, @samp{octeontx2f95}, @samp{octeontx2f95n},
 @samp{octeontx2f95mm},
-@samp{a64fx},
+@samp{a64fx}, @samp{fujitsu-monaka},
 @samp{thunderx}, @samp{thunderxt88},
 @samp{thunderxt88p1}, @samp{thunderxt81}, @samp{tsv110},
 @samp{thunderxt83}, @samp{thunderx2t99}, @samp{thunderx3t110}, @samp{zeus},