21 Star 27 Fork 151

src-openEuler/gcc

加入 Gitee
与超过 1200万 开发者一起发现、参与优秀开源项目,私有仓库也完全免费 :)
免费加入
文件
该仓库未声明开源许可证文件(LICENSE),使用请关注具体项目描述及其代码上游依赖。
克隆/下载
0118-Backport-SME-aarch64-Simplify-feature-definitions.patch 59.70 KB
一键复制 编辑 原始数据 按行查看 历史
huangzifeng 提交于 2024-11-21 11:35 +08:00 . Sync patches from branch openEuler-24.09
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176
From deb18d5083d8f9edbdafac184c010a6720dc8dda Mon Sep 17 00:00:00 2001
From: Richard Sandiford <richard.sandiford@arm.com>
Date: Thu, 29 Sep 2022 11:32:54 +0100
Subject: [PATCH 019/157] [Backport][SME] aarch64: Simplify feature definitions
Reference: https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=11a113d501ff64fa4843e28d0a21b3f4e9d0d3de
Currently the aarch64-option-extensions.def entries, the
aarch64-cores.def entries, and the AARCH64_FL_FOR_* macros
have a transitive closure of dependencies that is maintained by hand.
This is a bit error-prone and is becoming less tenable as more features
are added. The main point of this patch is to maintain the closure
automatically instead.
For example, the +sve2-aes extension requires sve2 and aes.
This is now described using:
AARCH64_OPT_EXTENSION("sve2-aes", SVE2_AES, (SVE2, AES), ...)
If life was simple, we could just give the name of the feature
and the list of features that it requires/depends on. But sadly
things are more complicated. For example:
- the legacy +crypto option enables aes and sha2 only, but +nocrypto
disables all crypto-related extensions, including sm4.
- +fp16fml enables fp16, but armv8.4-a enables fp16fml without fp16.
fp16fml only has an effect when fp16 is also present; see the
comments for more details.
- +bf16 enables simd, but +bf16+nosimd is valid and enables just the
scalar bf16 instructions. rdma behaves similarly.
To handle cases like these, the option entries have extra fields to
specify what an explicit +foo enables and what an explicit +nofoo
disables, in addition to the absolute dependencies.
The other main changes are:
- AARCH64_FL_* are now defined automatically.
- the feature list for each architecture level moves from aarch64.h
to aarch64-arches.def.
As a consequence, we now have a (redundant) V8A feature flag.
While there, the patch uses a new typedef, aarch64_feature_flags,
for the set of feature flags. This should make it easier to switch
to a class if we run out of bits in the uint64_t.
For now the patch hardcodes the fact that crypto is the only
synthetic option. A later patch will remove this field.
To test for things that might not be covered by the testsuite,
I made the driver print out the all_extensions, all_cores and
all_archs arrays before and after the patch, with the following
tweaks:
- renumber the old AARCH64_FL_* bit assignments to match the .def order
- remove the new V8A flag when printing the new tables
- treat CRYPTO and CRYPTO | AES | SHA2 the same way when printing the
core tables
(On the last point: some cores enabled just CRYPTO while others enabled
CRYPTO, AES and SHA2. This doesn't cause a difference in behaviour
because of how the dependent macros are defined. With the new scheme,
all entries with CRYPTO automatically get AES and SHA2 too.)
The only difference is that +nofp now turns off dotprod. This was
another instance of an incomplete transitive closure, but unlike the
instances fixed in a previous patch, it had no observable effect.
gcc/
* config/aarch64/aarch64-option-extensions.def: Switch to a new format.
* config/aarch64/aarch64-cores.def: Use the same format to specify
lists of features.
* config/aarch64/aarch64-arches.def: Likewise, moving that information
from aarch64.h.
* config/aarch64/aarch64-opts.h (aarch64_feature_flags): New typedef.
* config/aarch64/aarch64.h (aarch64_feature): New class enum.
Turn AARCH64_FL_* macros into constexprs, getting the definitions
from aarch64-option-extensions.def. Remove AARCH64_FL_FOR_* macros.
* common/config/aarch64/aarch64-common.cc: Include
aarch64-feature-deps.h.
(all_extensions): Update for new .def format.
(all_extensions_by_on, all_cores, all_architectures): Likewise.
* config/aarch64/driver-aarch64.cc: Include aarch64-feature-deps.h.
(aarch64_extensions): Update for new .def format.
(aarch64_cpu_data, aarch64_arches): Likewise.
* config/aarch64/aarch64.cc: Include aarch64-feature-deps.h.
(all_architectures, all_cores): Update for new .def format.
* config/aarch64/aarch64-sve-builtins.cc
(check_required_extensions): Likewise.
---
gcc/common/config/aarch64/aarch64-common.cc | 29 +-
gcc/config/aarch64/aarch64-arches.def | 28 +-
gcc/config/aarch64/aarch64-cores.def | 130 +++----
gcc/config/aarch64/aarch64-feature-deps.h | 121 +++++++
.../aarch64/aarch64-option-extensions.def | 323 +++++++-----------
gcc/config/aarch64/aarch64-opts.h | 4 +
gcc/config/aarch64/aarch64-sve-builtins.cc | 5 +-
gcc/config/aarch64/aarch64.cc | 14 +-
gcc/config/aarch64/aarch64.h | 164 ++-------
gcc/config/aarch64/driver-aarch64.cc | 10 +-
10 files changed, 374 insertions(+), 454 deletions(-)
create mode 100644 gcc/config/aarch64/aarch64-feature-deps.h
diff --git a/gcc/common/config/aarch64/aarch64-common.cc b/gcc/common/config/aarch64/aarch64-common.cc
index a965ac660..74729bb30 100644
--- a/gcc/common/config/aarch64/aarch64-common.cc
+++ b/gcc/common/config/aarch64/aarch64-common.cc
@@ -30,6 +30,7 @@
#include "opts.h"
#include "flags.h"
#include "diagnostic.h"
+#include "config/aarch64/aarch64-feature-deps.h"
#ifdef TARGET_BIG_ENDIAN_DEFAULT
#undef TARGET_DEFAULT_TARGET_FLAGS
@@ -214,9 +215,12 @@ struct aarch64_option_extension
/* ISA extensions in AArch64. */
static const struct aarch64_option_extension all_extensions[] =
{
-#define AARCH64_OPT_EXTENSION(NAME, FLAG_CANONICAL, FLAGS_ON, FLAGS_OFF, \
- SYNTHETIC, Z) \
- {NAME, FLAG_CANONICAL, FLAGS_ON, FLAGS_OFF, SYNTHETIC},
+#define AARCH64_OPT_EXTENSION(NAME, IDENT, C, D, E, F) \
+ {NAME, AARCH64_FL_##IDENT, \
+ feature_deps::IDENT ().explicit_on & ~AARCH64_FL_##IDENT, \
+ feature_deps::get_flags_off (feature_deps::root_off_##IDENT) \
+ & ~AARCH64_FL_##IDENT, \
+ AARCH64_FL_##IDENT == AARCH64_FL_CRYPTO},
#include "config/aarch64/aarch64-option-extensions.def"
{NULL, 0, 0, 0, false}
};
@@ -225,9 +229,12 @@ static const struct aarch64_option_extension all_extensions[] =
bits and extension turned on. Cached for efficiency. */
static struct aarch64_option_extension all_extensions_by_on[] =
{
-#define AARCH64_OPT_EXTENSION(NAME, FLAG_CANONICAL, FLAGS_ON, FLAGS_OFF, \
- SYNTHETIC, Z) \
- {NAME, FLAG_CANONICAL, FLAGS_ON, FLAGS_OFF, SYNTHETIC},
+#define AARCH64_OPT_EXTENSION(NAME, IDENT, C, D, E, F) \
+ {NAME, AARCH64_FL_##IDENT, \
+ feature_deps::IDENT ().explicit_on & ~AARCH64_FL_##IDENT, \
+ feature_deps::get_flags_off (feature_deps::root_off_##IDENT) \
+ & ~AARCH64_FL_##IDENT, \
+ AARCH64_FL_##IDENT == AARCH64_FL_CRYPTO},
#include "config/aarch64/aarch64-option-extensions.def"
{NULL, 0, 0, 0, false}
};
@@ -250,18 +257,18 @@ struct arch_to_arch_name
the default set of architectural feature flags they support. */
static const struct processor_name_to_arch all_cores[] =
{
-#define AARCH64_CORE(NAME, X, IDENT, ARCH_IDENT, FLAGS, COSTS, IMP, PART, VARIANT) \
- {NAME, AARCH64_ARCH_##ARCH_IDENT, AARCH64_FL_FOR_##ARCH_IDENT | FLAGS},
+#define AARCH64_CORE(NAME, CORE_IDENT, C, ARCH_IDENT, E, F, G, H, I) \
+ {NAME, AARCH64_ARCH_##ARCH_IDENT, feature_deps::cpu_##CORE_IDENT},
#include "config/aarch64/aarch64-cores.def"
- {"generic", AARCH64_ARCH_V8A, AARCH64_FL_FOR_V8A},
+ {"generic", AARCH64_ARCH_V8A, feature_deps::V8A ().enable},
{"", aarch64_no_arch, 0}
};
/* Map architecture revisions to their string representation. */
static const struct arch_to_arch_name all_architectures[] =
{
-#define AARCH64_ARCH(NAME, CORE, ARCH_IDENT, ARCH, FLAGS) \
- {AARCH64_ARCH_##ARCH_IDENT, NAME, FLAGS},
+#define AARCH64_ARCH(NAME, B, ARCH_IDENT, D, E) \
+ {AARCH64_ARCH_##ARCH_IDENT, NAME, feature_deps::ARCH_IDENT ().enable},
#include "config/aarch64/aarch64-arches.def"
{aarch64_no_arch, "", 0}
};
diff --git a/gcc/config/aarch64/aarch64-arches.def b/gcc/config/aarch64/aarch64-arches.def
index ece96e22a..9f8246618 100644
--- a/gcc/config/aarch64/aarch64-arches.def
+++ b/gcc/config/aarch64/aarch64-arches.def
@@ -30,19 +30,19 @@
Due to the assumptions about the positions of these fields in config.gcc,
NAME should be kept as the first argument. */
-AARCH64_ARCH("armv8-a", generic, V8A, 8, AARCH64_FL_FOR_V8A)
-AARCH64_ARCH("armv8.1-a", generic, V8_1A, 8, AARCH64_FL_FOR_V8_1A)
-AARCH64_ARCH("armv8.2-a", generic, V8_2A, 8, AARCH64_FL_FOR_V8_2A)
-AARCH64_ARCH("armv8.3-a", generic, V8_3A, 8, AARCH64_FL_FOR_V8_3A)
-AARCH64_ARCH("armv8.4-a", generic, V8_4A, 8, AARCH64_FL_FOR_V8_4A)
-AARCH64_ARCH("armv8.5-a", generic, V8_5A, 8, AARCH64_FL_FOR_V8_5A)
-AARCH64_ARCH("armv8.6-a", generic, V8_6A, 8, AARCH64_FL_FOR_V8_6A)
-AARCH64_ARCH("armv8.7-a", generic, V8_7A, 8, AARCH64_FL_FOR_V8_7A)
-AARCH64_ARCH("armv8.8-a", generic, V8_8A, 8, AARCH64_FL_FOR_V8_8A)
-AARCH64_ARCH("armv8-r", generic, V8R , 8, AARCH64_FL_FOR_V8R)
-AARCH64_ARCH("armv9-a", generic, V9A , 9, AARCH64_FL_FOR_V9A)
-AARCH64_ARCH("armv9.1-a", generic, V9_1A, 9, AARCH64_FL_FOR_V9_1A)
-AARCH64_ARCH("armv9.2-a", generic, V9_2A, 9, AARCH64_FL_FOR_V9_2A)
-AARCH64_ARCH("armv9.3-a", generic, V9_3A, 9, AARCH64_FL_FOR_V9_3A)
+AARCH64_ARCH("armv8-a", generic, V8A, 8, (SIMD))
+AARCH64_ARCH("armv8.1-a", generic, V8_1A, 8, (V8A, LSE, CRC, RDMA))
+AARCH64_ARCH("armv8.2-a", generic, V8_2A, 8, (V8_1A))
+AARCH64_ARCH("armv8.3-a", generic, V8_3A, 8, (V8_2A, PAUTH))
+AARCH64_ARCH("armv8.4-a", generic, V8_4A, 8, (V8_3A, F16FML, DOTPROD, FLAGM))
+AARCH64_ARCH("armv8.5-a", generic, V8_5A, 8, (V8_4A, SB, SSBS, PREDRES))
+AARCH64_ARCH("armv8.6-a", generic, V8_6A, 8, (V8_5A, I8MM, BF16))
+AARCH64_ARCH("armv8.7-a", generic, V8_7A, 8, (V8_6A, LS64))
+AARCH64_ARCH("armv8.8-a", generic, V8_8A, 8, (V8_7A, MOPS))
+AARCH64_ARCH("armv8-r", generic, V8R , 8, (V8_4A))
+AARCH64_ARCH("armv9-a", generic, V9A , 9, (V8_5A, SVE2))
+AARCH64_ARCH("armv9.1-a", generic, V9_1A, 9, (V8_6A, V9A))
+AARCH64_ARCH("armv9.2-a", generic, V9_2A, 9, (V8_7A, V9_1A))
+AARCH64_ARCH("armv9.3-a", generic, V9_3A, 9, (V8_8A, V9_2A))
#undef AARCH64_ARCH
diff --git a/gcc/config/aarch64/aarch64-cores.def b/gcc/config/aarch64/aarch64-cores.def
index cf500d0a9..60299160b 100644
--- a/gcc/config/aarch64/aarch64-cores.def
+++ b/gcc/config/aarch64/aarch64-cores.def
@@ -46,132 +46,132 @@
/* ARMv8-A Architecture Processors. */
/* ARM ('A') cores. */
-AARCH64_CORE("cortex-a34", cortexa34, cortexa53, V8A, AARCH64_FL_CRC, cortexa35, 0x41, 0xd02, -1)
-AARCH64_CORE("cortex-a35", cortexa35, cortexa53, V8A, AARCH64_FL_CRC, cortexa35, 0x41, 0xd04, -1)
-AARCH64_CORE("cortex-a53", cortexa53, cortexa53, V8A, AARCH64_FL_CRC, cortexa53, 0x41, 0xd03, -1)
-AARCH64_CORE("cortex-a57", cortexa57, cortexa57, V8A, AARCH64_FL_CRC, cortexa57, 0x41, 0xd07, -1)
-AARCH64_CORE("cortex-a72", cortexa72, cortexa57, V8A, AARCH64_FL_CRC, cortexa72, 0x41, 0xd08, -1)
-AARCH64_CORE("cortex-a73", cortexa73, cortexa57, V8A, AARCH64_FL_CRC, cortexa73, 0x41, 0xd09, -1)
+AARCH64_CORE("cortex-a34", cortexa34, cortexa53, V8A, (CRC), cortexa35, 0x41, 0xd02, -1)
+AARCH64_CORE("cortex-a35", cortexa35, cortexa53, V8A, (CRC), cortexa35, 0x41, 0xd04, -1)
+AARCH64_CORE("cortex-a53", cortexa53, cortexa53, V8A, (CRC), cortexa53, 0x41, 0xd03, -1)
+AARCH64_CORE("cortex-a57", cortexa57, cortexa57, V8A, (CRC), cortexa57, 0x41, 0xd07, -1)
+AARCH64_CORE("cortex-a72", cortexa72, cortexa57, V8A, (CRC), cortexa72, 0x41, 0xd08, -1)
+AARCH64_CORE("cortex-a73", cortexa73, cortexa57, V8A, (CRC), cortexa73, 0x41, 0xd09, -1)
/* Cavium ('C') cores. */
-AARCH64_CORE("thunderx", thunderx, thunderx, V8A, AARCH64_FL_CRC | AARCH64_FL_CRYPTO, thunderx, 0x43, 0x0a0, -1)
+AARCH64_CORE("thunderx", thunderx, thunderx, V8A, (CRC, CRYPTO), thunderx, 0x43, 0x0a0, -1)
/* Do not swap around "thunderxt88p1" and "thunderxt88",
this order is required to handle variant correctly. */
-AARCH64_CORE("thunderxt88p1", thunderxt88p1, thunderx, V8A, AARCH64_FL_CRC | AARCH64_FL_CRYPTO, thunderxt88, 0x43, 0x0a1, 0)
-AARCH64_CORE("thunderxt88", thunderxt88, thunderx, V8A, AARCH64_FL_CRC | AARCH64_FL_CRYPTO, thunderxt88, 0x43, 0x0a1, -1)
+AARCH64_CORE("thunderxt88p1", thunderxt88p1, thunderx, V8A, (CRC, CRYPTO), thunderxt88, 0x43, 0x0a1, 0)
+AARCH64_CORE("thunderxt88", thunderxt88, thunderx, V8A, (CRC, CRYPTO), thunderxt88, 0x43, 0x0a1, -1)
/* OcteonTX is the official name for T81/T83. */
-AARCH64_CORE("octeontx", octeontx, thunderx, V8A, AARCH64_FL_CRC | AARCH64_FL_CRYPTO, thunderx, 0x43, 0x0a0, -1)
-AARCH64_CORE("octeontx81", octeontxt81, thunderx, V8A, AARCH64_FL_CRC | AARCH64_FL_CRYPTO, thunderx, 0x43, 0x0a2, -1)
-AARCH64_CORE("octeontx83", octeontxt83, thunderx, V8A, AARCH64_FL_CRC | AARCH64_FL_CRYPTO, thunderx, 0x43, 0x0a3, -1)
+AARCH64_CORE("octeontx", octeontx, thunderx, V8A, (CRC, CRYPTO), thunderx, 0x43, 0x0a0, -1)
+AARCH64_CORE("octeontx81", octeontxt81, thunderx, V8A, (CRC, CRYPTO), thunderx, 0x43, 0x0a2, -1)
+AARCH64_CORE("octeontx83", octeontxt83, thunderx, V8A, (CRC, CRYPTO), thunderx, 0x43, 0x0a3, -1)
-AARCH64_CORE("thunderxt81", thunderxt81, thunderx, V8A, AARCH64_FL_CRC | AARCH64_FL_CRYPTO, thunderx, 0x43, 0x0a2, -1)
-AARCH64_CORE("thunderxt83", thunderxt83, thunderx, V8A, AARCH64_FL_CRC | AARCH64_FL_CRYPTO, thunderx, 0x43, 0x0a3, -1)
+AARCH64_CORE("thunderxt81", thunderxt81, thunderx, V8A, (CRC, CRYPTO), thunderx, 0x43, 0x0a2, -1)
+AARCH64_CORE("thunderxt83", thunderxt83, thunderx, V8A, (CRC, CRYPTO), thunderx, 0x43, 0x0a3, -1)
/* Ampere Computing ('\xC0') cores. */
-AARCH64_CORE("ampere1", ampere1, cortexa57, V8_6A, 0, ampere1, 0xC0, 0xac3, -1)
+AARCH64_CORE("ampere1", ampere1, cortexa57, V8_6A, (), ampere1, 0xC0, 0xac3, -1)
/* Do not swap around "emag" and "xgene1",
this order is required to handle variant correctly. */
-AARCH64_CORE("emag", emag, xgene1, V8A, AARCH64_FL_CRC | AARCH64_FL_CRYPTO, emag, 0x50, 0x000, 3)
+AARCH64_CORE("emag", emag, xgene1, V8A, (CRC, CRYPTO), emag, 0x50, 0x000, 3)
/* APM ('P') cores. */
-AARCH64_CORE("xgene1", xgene1, xgene1, V8A, 0, xgene1, 0x50, 0x000, -1)
+AARCH64_CORE("xgene1", xgene1, xgene1, V8A, (), xgene1, 0x50, 0x000, -1)
/* Qualcomm ('Q') cores. */
-AARCH64_CORE("falkor", falkor, falkor, V8A, AARCH64_FL_CRC | AARCH64_FL_CRYPTO | AARCH64_FL_RDMA, qdf24xx, 0x51, 0xC00, -1)
-AARCH64_CORE("qdf24xx", qdf24xx, falkor, V8A, AARCH64_FL_CRC | AARCH64_FL_CRYPTO | AARCH64_FL_RDMA, qdf24xx, 0x51, 0xC00, -1)
+AARCH64_CORE("falkor", falkor, falkor, V8A, (CRC, CRYPTO, RDMA), qdf24xx, 0x51, 0xC00, -1)
+AARCH64_CORE("qdf24xx", qdf24xx, falkor, V8A, (CRC, CRYPTO, RDMA), qdf24xx, 0x51, 0xC00, -1)
/* Samsung ('S') cores. */
-AARCH64_CORE("exynos-m1", exynosm1, exynosm1, V8A, AARCH64_FL_CRC | AARCH64_FL_CRYPTO, exynosm1, 0x53, 0x001, -1)
+AARCH64_CORE("exynos-m1", exynosm1, exynosm1, V8A, (CRC, CRYPTO), exynosm1, 0x53, 0x001, -1)
/* HXT ('h') cores. */
-AARCH64_CORE("phecda", phecda, falkor, V8A, AARCH64_FL_CRC | AARCH64_FL_CRYPTO, qdf24xx, 0x68, 0x000, -1)
+AARCH64_CORE("phecda", phecda, falkor, V8A, (CRC, CRYPTO), qdf24xx, 0x68, 0x000, -1)
/* ARMv8.1-A Architecture Processors. */
/* Broadcom ('B') cores. */
-AARCH64_CORE("thunderx2t99p1", thunderx2t99p1, thunderx2t99, V8_1A, AARCH64_FL_CRYPTO, thunderx2t99, 0x42, 0x516, -1)
-AARCH64_CORE("vulcan", vulcan, thunderx2t99, V8_1A, AARCH64_FL_CRYPTO, thunderx2t99, 0x42, 0x516, -1)
+AARCH64_CORE("thunderx2t99p1", thunderx2t99p1, thunderx2t99, V8_1A, (CRYPTO), thunderx2t99, 0x42, 0x516, -1)
+AARCH64_CORE("vulcan", vulcan, thunderx2t99, V8_1A, (CRYPTO), thunderx2t99, 0x42, 0x516, -1)
/* Cavium ('C') cores. */
-AARCH64_CORE("thunderx2t99", thunderx2t99, thunderx2t99, V8_1A, AARCH64_FL_CRYPTO, thunderx2t99, 0x43, 0x0af, -1)
+AARCH64_CORE("thunderx2t99", thunderx2t99, thunderx2t99, V8_1A, (CRYPTO), thunderx2t99, 0x43, 0x0af, -1)
/* ARMv8.2-A Architecture Processors. */
/* ARM ('A') cores. */
-AARCH64_CORE("cortex-a55", cortexa55, cortexa53, V8_2A, AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD, cortexa53, 0x41, 0xd05, -1)
-AARCH64_CORE("cortex-a75", cortexa75, cortexa57, V8_2A, AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD, cortexa73, 0x41, 0xd0a, -1)
-AARCH64_CORE("cortex-a76", cortexa76, cortexa57, V8_2A, AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD, neoversen1, 0x41, 0xd0b, -1)
-AARCH64_CORE("cortex-a76ae", cortexa76ae, cortexa57, V8_2A, AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD | AARCH64_FL_SSBS, neoversen1, 0x41, 0xd0e, -1)
-AARCH64_CORE("cortex-a77", cortexa77, cortexa57, V8_2A, AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD | AARCH64_FL_SSBS, neoversen1, 0x41, 0xd0d, -1)
-AARCH64_CORE("cortex-a78", cortexa78, cortexa57, V8_2A, AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD | AARCH64_FL_SSBS | AARCH64_FL_PROFILE, neoversen1, 0x41, 0xd41, -1)
-AARCH64_CORE("cortex-a78ae", cortexa78ae, cortexa57, V8_2A, AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD | AARCH64_FL_SSBS | AARCH64_FL_PROFILE, neoversen1, 0x41, 0xd42, -1)
-AARCH64_CORE("cortex-a78c", cortexa78c, cortexa57, V8_2A, AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD | AARCH64_FL_SSBS | AARCH64_FL_PROFILE | AARCH64_FL_FLAGM | AARCH64_FL_PAUTH, neoversen1, 0x41, 0xd4b, -1)
-AARCH64_CORE("cortex-a65", cortexa65, cortexa53, V8_2A, AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD | AARCH64_FL_SSBS, cortexa73, 0x41, 0xd06, -1)
-AARCH64_CORE("cortex-a65ae", cortexa65ae, cortexa53, V8_2A, AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD | AARCH64_FL_SSBS, cortexa73, 0x41, 0xd43, -1)
-AARCH64_CORE("cortex-x1", cortexx1, cortexa57, V8_2A, AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD | AARCH64_FL_SSBS | AARCH64_FL_PROFILE, neoversen1, 0x41, 0xd44, -1)
-AARCH64_CORE("ares", ares, cortexa57, V8_2A, AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD | AARCH64_FL_PROFILE, neoversen1, 0x41, 0xd0c, -1)
-AARCH64_CORE("neoverse-n1", neoversen1, cortexa57, V8_2A, AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD | AARCH64_FL_PROFILE, neoversen1, 0x41, 0xd0c, -1)
-AARCH64_CORE("neoverse-e1", neoversee1, cortexa53, V8_2A, AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD | AARCH64_FL_SSBS, cortexa73, 0x41, 0xd4a, -1)
+AARCH64_CORE("cortex-a55", cortexa55, cortexa53, V8_2A, (F16, RCPC, DOTPROD), cortexa53, 0x41, 0xd05, -1)
+AARCH64_CORE("cortex-a75", cortexa75, cortexa57, V8_2A, (F16, RCPC, DOTPROD), cortexa73, 0x41, 0xd0a, -1)
+AARCH64_CORE("cortex-a76", cortexa76, cortexa57, V8_2A, (F16, RCPC, DOTPROD), neoversen1, 0x41, 0xd0b, -1)
+AARCH64_CORE("cortex-a76ae", cortexa76ae, cortexa57, V8_2A, (F16, RCPC, DOTPROD, SSBS), neoversen1, 0x41, 0xd0e, -1)
+AARCH64_CORE("cortex-a77", cortexa77, cortexa57, V8_2A, (F16, RCPC, DOTPROD, SSBS), neoversen1, 0x41, 0xd0d, -1)
+AARCH64_CORE("cortex-a78", cortexa78, cortexa57, V8_2A, (F16, RCPC, DOTPROD, SSBS, PROFILE), neoversen1, 0x41, 0xd41, -1)
+AARCH64_CORE("cortex-a78ae", cortexa78ae, cortexa57, V8_2A, (F16, RCPC, DOTPROD, SSBS, PROFILE), neoversen1, 0x41, 0xd42, -1)
+AARCH64_CORE("cortex-a78c", cortexa78c, cortexa57, V8_2A, (F16, RCPC, DOTPROD, SSBS, PROFILE, FLAGM, PAUTH), neoversen1, 0x41, 0xd4b, -1)
+AARCH64_CORE("cortex-a65", cortexa65, cortexa53, V8_2A, (F16, RCPC, DOTPROD, SSBS), cortexa73, 0x41, 0xd06, -1)
+AARCH64_CORE("cortex-a65ae", cortexa65ae, cortexa53, V8_2A, (F16, RCPC, DOTPROD, SSBS), cortexa73, 0x41, 0xd43, -1)
+AARCH64_CORE("cortex-x1", cortexx1, cortexa57, V8_2A, (F16, RCPC, DOTPROD, SSBS, PROFILE), neoversen1, 0x41, 0xd44, -1)
+AARCH64_CORE("ares", ares, cortexa57, V8_2A, (F16, RCPC, DOTPROD, PROFILE), neoversen1, 0x41, 0xd0c, -1)
+AARCH64_CORE("neoverse-n1", neoversen1, cortexa57, V8_2A, (F16, RCPC, DOTPROD, PROFILE), neoversen1, 0x41, 0xd0c, -1)
+AARCH64_CORE("neoverse-e1", neoversee1, cortexa53, V8_2A, (F16, RCPC, DOTPROD, SSBS), cortexa73, 0x41, 0xd4a, -1)
/* Cavium ('C') cores. */
-AARCH64_CORE("octeontx2", octeontx2, cortexa57, V8_2A, AARCH64_FL_CRYPTO | AARCH64_FL_PROFILE, cortexa57, 0x43, 0x0b0, -1)
-AARCH64_CORE("octeontx2t98", octeontx2t98, cortexa57, V8_2A, AARCH64_FL_CRYPTO | AARCH64_FL_PROFILE, cortexa57, 0x43, 0x0b1, -1)
-AARCH64_CORE("octeontx2t96", octeontx2t96, cortexa57, V8_2A, AARCH64_FL_CRYPTO | AARCH64_FL_PROFILE, cortexa57, 0x43, 0x0b2, -1)
+AARCH64_CORE("octeontx2", octeontx2, cortexa57, V8_2A, (CRYPTO, PROFILE), cortexa57, 0x43, 0x0b0, -1)
+AARCH64_CORE("octeontx2t98", octeontx2t98, cortexa57, V8_2A, (CRYPTO, PROFILE), cortexa57, 0x43, 0x0b1, -1)
+AARCH64_CORE("octeontx2t96", octeontx2t96, cortexa57, V8_2A, (CRYPTO, PROFILE), cortexa57, 0x43, 0x0b2, -1)
/* Note OcteonTX2 T93 is an alias to OcteonTX2 T96. */
-AARCH64_CORE("octeontx2t93", octeontx2t93, cortexa57, V8_2A, AARCH64_FL_CRYPTO | AARCH64_FL_PROFILE, cortexa57, 0x43, 0x0b2, -1)
-AARCH64_CORE("octeontx2f95", octeontx2f95, cortexa57, V8_2A, AARCH64_FL_CRYPTO | AARCH64_FL_PROFILE, cortexa57, 0x43, 0x0b3, -1)
-AARCH64_CORE("octeontx2f95n", octeontx2f95n, cortexa57, V8_2A, AARCH64_FL_CRYPTO | AARCH64_FL_PROFILE, cortexa57, 0x43, 0x0b4, -1)
-AARCH64_CORE("octeontx2f95mm", octeontx2f95mm, cortexa57, V8_2A, AARCH64_FL_CRYPTO | AARCH64_FL_PROFILE, cortexa57, 0x43, 0x0b5, -1)
+AARCH64_CORE("octeontx2t93", octeontx2t93, cortexa57, V8_2A, (CRYPTO, PROFILE), cortexa57, 0x43, 0x0b2, -1)
+AARCH64_CORE("octeontx2f95", octeontx2f95, cortexa57, V8_2A, (CRYPTO, PROFILE), cortexa57, 0x43, 0x0b3, -1)
+AARCH64_CORE("octeontx2f95n", octeontx2f95n, cortexa57, V8_2A, (CRYPTO, PROFILE), cortexa57, 0x43, 0x0b4, -1)
+AARCH64_CORE("octeontx2f95mm", octeontx2f95mm, cortexa57, V8_2A, (CRYPTO, PROFILE), cortexa57, 0x43, 0x0b5, -1)
/* Fujitsu ('F') cores. */
-AARCH64_CORE("a64fx", a64fx, a64fx, V8_2A, AARCH64_FL_F16 | AARCH64_FL_SVE, a64fx, 0x46, 0x001, -1)
+AARCH64_CORE("a64fx", a64fx, a64fx, V8_2A, (F16, SVE), a64fx, 0x46, 0x001, -1)
/* HiSilicon ('H') cores. */
-AARCH64_CORE("tsv110", tsv110, tsv110, V8_2A, AARCH64_FL_CRYPTO | AARCH64_FL_F16 | AARCH64_FL_AES | AARCH64_FL_SHA2, tsv110, 0x48, 0xd01, -1)
+AARCH64_CORE("tsv110", tsv110, tsv110, V8_2A, (CRYPTO, F16), tsv110, 0x48, 0xd01, -1)
/* ARMv8.3-A Architecture Processors. */
/* Marvell cores (TX3). */
-AARCH64_CORE("thunderx3t110", thunderx3t110, thunderx3t110, V8_3A, AARCH64_FL_CRYPTO | AARCH64_FL_RCPC | AARCH64_FL_SM4 | AARCH64_FL_SHA3 | AARCH64_FL_F16FML, thunderx3t110, 0x43, 0x0b8, 0x0a)
+AARCH64_CORE("thunderx3t110", thunderx3t110, thunderx3t110, V8_3A, (CRYPTO, RCPC, SM4, SHA3, F16FML), thunderx3t110, 0x43, 0x0b8, 0x0a)
/* ARMv8.4-A Architecture Processors. */
/* Arm ('A') cores. */
-AARCH64_CORE("zeus", zeus, cortexa57, V8_4A, 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, V8_4A, 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-512tvb", neoverse512tvb, cortexa57, V8_4A, AARCH64_FL_SVE | AARCH64_FL_RCPC | AARCH64_FL_I8MM | AARCH64_FL_BF16 | AARCH64_FL_F16 | AARCH64_FL_PROFILE | AARCH64_FL_SSBS | AARCH64_FL_RNG, neoverse512tvb, INVALID_IMP, INVALID_CORE, -1)
+AARCH64_CORE("zeus", zeus, cortexa57, V8_4A, (SVE, RCPC, I8MM, BF16, PROFILE, SSBS, RNG), neoversev1, 0x41, 0xd40, -1)
+AARCH64_CORE("neoverse-v1", neoversev1, cortexa57, V8_4A, (SVE, RCPC, I8MM, BF16, PROFILE, SSBS, RNG), neoversev1, 0x41, 0xd40, -1)
+AARCH64_CORE("neoverse-512tvb", neoverse512tvb, cortexa57, V8_4A, (SVE, RCPC, I8MM, BF16, PROFILE, SSBS, RNG), neoverse512tvb, INVALID_IMP, INVALID_CORE, -1)
/* Qualcomm ('Q') cores. */
-AARCH64_CORE("saphira", saphira, saphira, V8_4A, AARCH64_FL_CRYPTO | AARCH64_FL_RCPC, saphira, 0x51, 0xC01, -1)
+AARCH64_CORE("saphira", saphira, saphira, V8_4A, (CRYPTO, RCPC), saphira, 0x51, 0xC01, -1)
/* ARMv8-A big.LITTLE implementations. */
-AARCH64_CORE("cortex-a57.cortex-a53", cortexa57cortexa53, cortexa53, V8A, AARCH64_FL_CRC, cortexa57, 0x41, AARCH64_BIG_LITTLE (0xd07, 0xd03), -1)
-AARCH64_CORE("cortex-a72.cortex-a53", cortexa72cortexa53, cortexa53, V8A, AARCH64_FL_CRC, cortexa72, 0x41, AARCH64_BIG_LITTLE (0xd08, 0xd03), -1)
-AARCH64_CORE("cortex-a73.cortex-a35", cortexa73cortexa35, cortexa53, V8A, AARCH64_FL_CRC, cortexa73, 0x41, AARCH64_BIG_LITTLE (0xd09, 0xd04), -1)
-AARCH64_CORE("cortex-a73.cortex-a53", cortexa73cortexa53, cortexa53, V8A, AARCH64_FL_CRC, cortexa73, 0x41, AARCH64_BIG_LITTLE (0xd09, 0xd03), -1)
+AARCH64_CORE("cortex-a57.cortex-a53", cortexa57cortexa53, cortexa53, V8A, (CRC), cortexa57, 0x41, AARCH64_BIG_LITTLE (0xd07, 0xd03), -1)
+AARCH64_CORE("cortex-a72.cortex-a53", cortexa72cortexa53, cortexa53, V8A, (CRC), cortexa72, 0x41, AARCH64_BIG_LITTLE (0xd08, 0xd03), -1)
+AARCH64_CORE("cortex-a73.cortex-a35", cortexa73cortexa35, cortexa53, V8A, (CRC), cortexa73, 0x41, AARCH64_BIG_LITTLE (0xd09, 0xd04), -1)
+AARCH64_CORE("cortex-a73.cortex-a53", cortexa73cortexa53, cortexa53, V8A, (CRC), cortexa73, 0x41, AARCH64_BIG_LITTLE (0xd09, 0xd03), -1)
/* ARM DynamIQ big.LITTLE configurations. */
-AARCH64_CORE("cortex-a75.cortex-a55", cortexa75cortexa55, cortexa53, V8_2A, AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD, cortexa73, 0x41, AARCH64_BIG_LITTLE (0xd0a, 0xd05), -1)
-AARCH64_CORE("cortex-a76.cortex-a55", cortexa76cortexa55, cortexa53, V8_2A, AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD, neoversen1, 0x41, AARCH64_BIG_LITTLE (0xd0b, 0xd05), -1)
+AARCH64_CORE("cortex-a75.cortex-a55", cortexa75cortexa55, cortexa53, V8_2A, (F16, RCPC, DOTPROD), cortexa73, 0x41, AARCH64_BIG_LITTLE (0xd0a, 0xd05), -1)
+AARCH64_CORE("cortex-a76.cortex-a55", cortexa76cortexa55, cortexa53, V8_2A, (F16, RCPC, DOTPROD), neoversen1, 0x41, AARCH64_BIG_LITTLE (0xd0b, 0xd05), -1)
/* Armv8-R Architecture Processors. */
-AARCH64_CORE("cortex-r82", cortexr82, cortexa53, V8R, 0, cortexa53, 0x41, 0xd15, -1)
+AARCH64_CORE("cortex-r82", cortexr82, cortexa53, V8R, (), cortexa53, 0x41, 0xd15, -1)
/* Armv9.0-A Architecture Processors. */
/* Arm ('A') cores. */
-AARCH64_CORE("cortex-a510", cortexa510, cortexa55, V9A, AARCH64_FL_SVE2_BITPERM | AARCH64_FL_MEMTAG | AARCH64_FL_I8MM | AARCH64_FL_BF16, cortexa53, 0x41, 0xd46, -1)
+AARCH64_CORE("cortex-a510", cortexa510, cortexa55, V9A, (SVE2_BITPERM, MEMTAG, I8MM, BF16), cortexa53, 0x41, 0xd46, -1)
-AARCH64_CORE("cortex-a710", cortexa710, cortexa57, V9A, AARCH64_FL_SVE2_BITPERM | AARCH64_FL_MEMTAG | AARCH64_FL_I8MM | AARCH64_FL_BF16, neoversen2, 0x41, 0xd47, -1)
+AARCH64_CORE("cortex-a710", cortexa710, cortexa57, V9A, (SVE2_BITPERM, MEMTAG, I8MM, BF16), neoversen2, 0x41, 0xd47, -1)
-AARCH64_CORE("cortex-x2", cortexx2, cortexa57, V9A, AARCH64_FL_SVE2_BITPERM | AARCH64_FL_MEMTAG | AARCH64_FL_I8MM | AARCH64_FL_BF16, neoversen2, 0x41, 0xd48, -1)
+AARCH64_CORE("cortex-x2", cortexx2, cortexa57, V9A, (SVE2_BITPERM, MEMTAG, I8MM, BF16), neoversen2, 0x41, 0xd48, -1)
-AARCH64_CORE("neoverse-n2", neoversen2, cortexa57, V9A, AARCH64_FL_I8MM | AARCH64_FL_BF16 | AARCH64_FL_SVE2_BITPERM | AARCH64_FL_RNG | AARCH64_FL_MEMTAG | AARCH64_FL_PROFILE, neoversen2, 0x41, 0xd49, -1)
+AARCH64_CORE("neoverse-n2", neoversen2, cortexa57, V9A, (I8MM, BF16, SVE2_BITPERM, RNG, MEMTAG, PROFILE), neoversen2, 0x41, 0xd49, -1)
-AARCH64_CORE("demeter", demeter, cortexa57, V9A, AARCH64_FL_I8MM | AARCH64_FL_BF16 | AARCH64_FL_SVE2_BITPERM | AARCH64_FL_RNG | AARCH64_FL_MEMTAG | AARCH64_FL_PROFILE, neoversev2, 0x41, 0xd4f, -1)
-AARCH64_CORE("neoverse-v2", neoversev2, cortexa57, V9A, AARCH64_FL_I8MM | AARCH64_FL_BF16 | AARCH64_FL_SVE2_BITPERM | AARCH64_FL_RNG | AARCH64_FL_MEMTAG | AARCH64_FL_PROFILE, neoversev2, 0x41, 0xd4f, -1)
+AARCH64_CORE("demeter", demeter, cortexa57, V9A, (I8MM, BF16, SVE2_BITPERM, RNG, MEMTAG, PROFILE), neoversev2, 0x41, 0xd4f, -1)
+AARCH64_CORE("neoverse-v2", neoversev2, cortexa57, V9A, (I8MM, BF16, SVE2_BITPERM, RNG, MEMTAG, PROFILE), neoversev2, 0x41, 0xd4f, -1)
#undef AARCH64_CORE
diff --git a/gcc/config/aarch64/aarch64-feature-deps.h b/gcc/config/aarch64/aarch64-feature-deps.h
new file mode 100644
index 000000000..3e33cb2ce
--- /dev/null
+++ b/gcc/config/aarch64/aarch64-feature-deps.h
@@ -0,0 +1,121 @@
+/* Feature dependency helpers for AArch64.
+ Copyright (C) 2022 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 AARCH64_FEATURE_DEPS_H
+#define AARCH64_FEATURE_DEPS_H 1
+
+namespace {
+namespace feature_deps {
+
+/* Together, these definitions of get_flags take a list of
+ feature names (representing functions that are defined below)
+ and return the set of associated flags. */
+constexpr aarch64_feature_flags get_flags () { return 0; }
+
+template<typename T1, typename ...Ts>
+constexpr aarch64_feature_flags
+get_flags (T1 i, Ts... args)
+{
+ return i ().flag | get_flags (args...);
+}
+
+/* Like get_flags, but return the transitive closure of those features
+ and the ones that they rely on. */
+constexpr aarch64_feature_flags get_enable () { return 0; }
+
+template<typename T1, typename ...Ts>
+constexpr aarch64_feature_flags
+get_enable (T1 i, Ts... args)
+{
+ return i ().enable | get_enable (args...);
+}
+
+/* Define info<FEATURE> such that it has the following static constant
+ variables:
+
+ - flag: the aarch64_feature_flags bit associated with FEATURE
+
+ - enable: the transitive closure of the features that FEATURE requires,
+ plus FLAG itself
+
+ - explicit_on: the transitive closure of the features that an
+ explicit +FEATURE enables, including FLAG itself. This is
+ always a superset of ENABLE
+
+ Also define a function FEATURE () that returns an info<FEATURE>
+ (which is an empty structure, since all members are static).
+
+ Building up the list feature-by-feature ensures that the definition
+ files are in topological order. */
+template<aarch64_feature> struct info;
+
+#define HANDLE(IDENT, REQUIRES, EXPLICIT_ON) \
+ template<> struct info<aarch64_feature::IDENT> { \
+ static constexpr auto flag = AARCH64_FL_##IDENT; \
+ static constexpr auto enable = flag | get_enable REQUIRES; \
+ static constexpr auto explicit_on = enable | get_enable EXPLICIT_ON; \
+ }; \
+ constexpr info<aarch64_feature::IDENT> IDENT () \
+ { \
+ return info<aarch64_feature::IDENT> (); \
+ }
+#define AARCH64_OPT_EXTENSION(A, IDENT, REQUIRES, EXPLICIT_ON, E, F) \
+ HANDLE (IDENT, REQUIRES, EXPLICIT_ON)
+#define AARCH64_ARCH(A, B, IDENT, D, REQUIRES) HANDLE (IDENT, REQUIRES, ())
+#include "config/aarch64/aarch64-option-extensions.def"
+#include "config/aarch64/aarch64-arches.def"
+#undef HANDLE
+
+/* Return the set of all features that would need to be disabled if
+ the features in MASK are disabled.
+
+ Note that the size of the expression varies linearly with the number
+ of features, which means that invoking this function once per feature
+ is quadratic in the number of features. However, collecting the same
+ information at compiler start-up is likely to be quadratic too, so
+ we're better off paying the cost once per compiler build rather than
+ once per compiler run. */
+constexpr aarch64_feature_flags
+get_flags_off (aarch64_feature_flags mask)
+{
+ return (0
+#define AARCH64_OPT_EXTENSION(A, IDENT, C, D, E, F) \
+ | (feature_deps::IDENT ().enable & mask ? AARCH64_FL_##IDENT : 0)
+#include "config/aarch64/aarch64-option-extensions.def"
+ );
+}
+
+/* Define root_off_<IDENT> variables for each feature, giving the set of
+ features that must be turned off by +noIDENT. This set is not transitively
+ closed; use get_flags_off to complete the closure. */
+#define AARCH64_OPT_EXTENSION(A, IDENT, C, D, EXPLICIT_OFF, F) \
+ constexpr auto root_off_##IDENT \
+ = AARCH64_FL_##IDENT | get_flags EXPLICIT_OFF;
+#include "config/aarch64/aarch64-option-extensions.def"
+
+/* Define cpu_<NAME> variables for each CPU, giving the transitive
+ closure of all the features that the CPU supports. */
+#define AARCH64_CORE(A, CORE_IDENT, C, ARCH_IDENT, FEATURES, F, G, H, I) \
+ constexpr auto cpu_##CORE_IDENT = ARCH_IDENT ().enable | get_enable FEATURES;
+#include "config/aarch64/aarch64-cores.def"
+
+}
+}
+
+#endif
diff --git a/gcc/config/aarch64/aarch64-option-extensions.def b/gcc/config/aarch64/aarch64-option-extensions.def
index df2c8d19b..bdf4baf30 100644
--- a/gcc/config/aarch64/aarch64-option-extensions.def
+++ b/gcc/config/aarch64/aarch64-option-extensions.def
@@ -21,23 +21,34 @@
Before using #include to read this file, define a macro:
- AARCH64_OPT_EXTENSION(EXT_NAME, FLAG_CANONICAL, FLAGS_ON, FLAGS_OFF,
- SYNTHETIC, FEATURE_STRING)
-
- - EXT_NAME is the name of the extension, represented as a string constant.
- - FLAGS_CANONICAL is the canonical internal name for this flag.
- - FLAGS_ON are the bitwise-or of the features that enabling the extension
- adds, or zero if enabling this extension has no effect on other features.
- - FLAGS_OFF are the bitwise-or of the features that disabling the extension
- removes, or zero if disabling this extension has no effect on other
- features.
- - SYNTHETIC is a boolean to indicate whether the option is a purely synthetic
- grouping of options and that the option itself has no feature bit (e.g.
- crypto). This is used to determine when sum of the individual options in
- FLAGS_ON can be replaced by FLAG_CANONICAL in options minimization. If the
- group is synthetic then they can be replaced when all options in FLAGS_ON
- are enabled, otherwise they can only be replaced when
- FLAGS_ON | FLAG_CANONICAL are enabled.
+ AARCH64_OPT_EXTENSION(NAME, IDENT, REQUIRES, EXPLICIT_ON,
+ EXPLICIT_OFF, FEATURE_STRING)
+
+ - NAME is the name of the extension, represented as a string constant.
+
+ - IDENT is the canonical internal name for this flag.
+
+ - REQUIRES is a list of features that must be enabled whenever this
+ feature is enabled. The relationship is implicitly transitive:
+ if A appears in B's REQUIRES and B appears in C's REQUIRES then
+ A and B must be enabled whenever C is. Thus, turning on C also
+ turns on A and B, while turning off A or B also turns off C.
+
+ - EXPLICIT_ON is a list of features that are enabled by an explicit
+ +NAME specification, in addition to those listed in REQUIRES.
+ Usually this is an empty list; comments below explain the exceptions.
+ The list is implicitly transitively closed wrt REQUIRES (but *not*
+ to EXPLICIT_ON, since NAME is the only thing explicit in +NAME).
+ Thus if A is in B's REQUIRES and B is in C's EXPLICIT_ON, +C will
+ enable both B and A. B's EXPLICIT_ON has no effect on +C.
+
+ - EXPLICIT_OFF is a list of features that are disabled by an explicit
+ +noNAME specification, in addition to the features that are transitively
+ dependent on NAME (according to REQUIRES). As with EXPLICIT_ON,
+ this is usually an empty list; comments below explain the exceptions.
+ If a feature A appears in this list then the list implicitly includes
+ any features that are transitively dependent on A (according to REQUIRES).
+
- FEAT_STRING is a string containing the entries in the 'Features' field of
/proc/cpuinfo on a GNU/Linux system that correspond to this architecture
extension being available. Sometimes multiple entries are needed to enable
@@ -47,197 +58,95 @@
that are required. Their order is not important. An empty string means
do not detect this feature during auto detection.
- NOTE: Any changes to the AARCH64_OPT_EXTENSION macro need to be mirrored in
- config.gcc. */
-
-/* Enabling "fp" just enables "fp".
- Disabling "fp" also disables "simd", "crypto", "fp16", "aes", "sha2",
- "sha3", sm3/sm4, "sve", "sve2", "sve2-aes", "sve2-sha3", "sve2-sm4",
- "sve2-bitperm", "i8mm", "f32mm", "f64mm", and "bf16". */
-AARCH64_OPT_EXTENSION("fp", AARCH64_FL_FP, 0, AARCH64_FL_SIMD | \
- AARCH64_FL_CRYPTO | AARCH64_FL_F16 | AARCH64_FL_AES | \
- AARCH64_FL_SHA2 | AARCH64_FL_SHA3 | AARCH64_FL_SM4 | \
- AARCH64_FL_SVE | AARCH64_FL_SVE2 | AARCH64_FL_SVE2_AES | \
- AARCH64_FL_SVE2_SHA3 | AARCH64_FL_SVE2_SM4 | \
- AARCH64_FL_SVE2_BITPERM | AARCH64_FL_I8MM | \
- AARCH64_FL_F32MM | AARCH64_FL_F64MM | AARCH64_FL_BF16,
- false, "fp")
-
-/* Enabling "simd" also enables "fp".
- Disabling "simd" also disables "crypto", "dotprod", "aes", "sha2", "sha3",
- "sm3/sm4", "sve", "sve2", "sve2-aes", "sve2-sha3", "sve2-sm4",
- "sve2-bitperm", "i8mm", "f32mm" and "f64mm". */
-AARCH64_OPT_EXTENSION("simd", AARCH64_FL_SIMD, AARCH64_FL_FP, \
- AARCH64_FL_CRYPTO | AARCH64_FL_DOTPROD | \
- AARCH64_FL_AES | AARCH64_FL_SHA2 | AARCH64_FL_SHA3 | \
- AARCH64_FL_SM4 | AARCH64_FL_SVE | AARCH64_FL_SVE2 | \
- AARCH64_FL_SVE2_AES | AARCH64_FL_SVE2_SHA3 | \
- AARCH64_FL_SVE2_SM4 | AARCH64_FL_SVE2_BITPERM | \
- AARCH64_FL_I8MM | AARCH64_FL_F32MM | AARCH64_FL_F64MM, \
- false, "asimd")
-
-/* Enabling or disabling "crc" only changes "crc". */
-AARCH64_OPT_EXTENSION("crc", AARCH64_FL_CRC, 0, 0, false, "crc32")
-
-/* Enabling or disabling "lse" only changes "lse". */
-AARCH64_OPT_EXTENSION("lse", AARCH64_FL_LSE, 0, 0, false, "atomics")
-
-/* Enabling "fp16" also enables "fp".
- Disabling "fp16" disables "fp16", "fp16fml", "sve", "sve2",
- "sve2-aes", "sve2-sha3", "sve2-sm4", "sve2-bitperm", "f32mm" and
- "f64mm". */
-AARCH64_OPT_EXTENSION("fp16", AARCH64_FL_F16, AARCH64_FL_FP, \
- AARCH64_FL_F16FML | AARCH64_FL_SVE | AARCH64_FL_F32MM | \
- AARCH64_FL_F64MM | AARCH64_FL_SVE2 | \
- AARCH64_FL_SVE2_AES | AARCH64_FL_SVE2_SHA3 | \
- AARCH64_FL_SVE2_SM4 | AARCH64_FL_SVE2_BITPERM, false, \
- "fphp asimdhp")
-
-/* Enabling or disabling "rcpc" only changes "rcpc". */
-AARCH64_OPT_EXTENSION("rcpc", AARCH64_FL_RCPC, 0, 0, false, "lrcpc")
-
-/* Enabling "rdma" also enables "fp", "simd".
- Disabling "rdma" just disables "rdma". */
-AARCH64_OPT_EXTENSION("rdma", AARCH64_FL_RDMA, \
- AARCH64_FL_FP | AARCH64_FL_SIMD, 0, false, "asimdrdm")
-
-/* Enabling "dotprod" also enables "simd".
- Disabling "dotprod" only disables "dotprod". */
-AARCH64_OPT_EXTENSION("dotprod", AARCH64_FL_DOTPROD, AARCH64_FL_FPSIMD, 0, \
- false, "asimddp")
-
-/* Enabling "aes" also enables "simd".
- Disabling "aes" disables "aes" and "sve2-aes'. */
-AARCH64_OPT_EXTENSION("aes", AARCH64_FL_AES, AARCH64_FL_FPSIMD, \
- AARCH64_FL_SVE2_AES | AARCH64_FL_CRYPTO, false, "aes")
-
-/* Enabling "sha2" also enables "simd".
- Disabling "sha2" just disables "sha2". */
-AARCH64_OPT_EXTENSION("sha2", AARCH64_FL_SHA2, AARCH64_FL_FPSIMD, \
- AARCH64_FL_CRYPTO | AARCH64_FL_SHA3 | \
- AARCH64_FL_SVE2_SHA3, false, "sha1 sha2")
-
-/* Enabling "crypto" also enables "fp", "simd", "aes" and "sha2".
- Disabling "crypto" disables "crypto", "aes", "sha2", "sha3" and "sm3/sm4",
- "sve2-aes", "sve2-sha3", "sve2-sm4". */
-AARCH64_OPT_EXTENSION("crypto", AARCH64_FL_CRYPTO, AARCH64_FL_FP | \
- AARCH64_FL_SIMD | AARCH64_FL_AES | AARCH64_FL_SHA2, \
- AARCH64_FL_AES | AARCH64_FL_SHA2 | AARCH64_FL_SHA3 | \
- AARCH64_FL_SM4 | AARCH64_FL_SVE2_AES | \
- AARCH64_FL_SVE2_SHA3 | AARCH64_FL_SVE2_SM4, true, \
+ The list of features must follow topological order wrt REQUIRES
+ and EXPLICIT_ON. For example, if A is in B's REQUIRES list, A must
+ come before B. This is enforced by aarch64-feature-deps.h.
+
+ NOTE: Any changes to the AARCH64_OPT_EXTENSION macro need to be mirrored in
+ config.gcc. */
+
+AARCH64_OPT_EXTENSION("fp", FP, (), (), (), "fp")
+
+AARCH64_OPT_EXTENSION("simd", SIMD, (FP), (), (), "asimd")
+
+AARCH64_OPT_EXTENSION("crc", CRC, (), (), (), "crc32")
+
+AARCH64_OPT_EXTENSION("lse", LSE, (), (), (), "atomics")
+
+/* +nofp16 disables an implicit F16FML, even though an implicit F16FML
+ does not imply F16. See F16FML for more details. */
+AARCH64_OPT_EXTENSION("fp16", F16, (FP), (), (F16FML), "fphp asimdhp")
+
+AARCH64_OPT_EXTENSION("rcpc", RCPC, (), (), (), "lrcpc")
+
+/* An explicit +rdma implies +simd, but +rdma+nosimd still enables scalar
+ RDMA instructions. */
+AARCH64_OPT_EXTENSION("rdma", RDMA, (), (SIMD), (), "asimdrdm")
+
+AARCH64_OPT_EXTENSION("dotprod", DOTPROD, (SIMD), (), (), "asimddp")
+
+AARCH64_OPT_EXTENSION("aes", AES, (SIMD), (), (), "aes")
+
+AARCH64_OPT_EXTENSION("sha2", SHA2, (SIMD), (), (), "sha1 sha2")
+
+/* +nocrypto disables AES, SHA2 and SM4, and anything that depends on them
+ (such as SHA3 and the SVE2 crypto extensions). */
+AARCH64_OPT_EXTENSION("crypto", CRYPTO, (AES, SHA2), (), (AES, SHA2, SM4),
"aes pmull sha1 sha2")
-/* Enabling "sha3" enables "simd" and "sha2".
- Disabling "sha3" disables "sha3" and "sve2-sha3". */
-AARCH64_OPT_EXTENSION("sha3", AARCH64_FL_SHA3, AARCH64_FL_FPSIMD | \
- AARCH64_FL_SHA2, AARCH64_FL_SVE2_SHA3, false, \
- "sha3 sha512")
-
-/* Enabling "sm4" also enables "simd".
- Disabling "sm4" disables "sm4" and "sve2-sm4". */
-AARCH64_OPT_EXTENSION("sm4", AARCH64_FL_SM4, AARCH64_FL_FPSIMD, \
- AARCH64_FL_SVE2_SM4, false, "sm3 sm4")
-
-/* Enabling "fp16fml" also enables "fp" and "fp16".
- Disabling "fp16fml" just disables "fp16fml". */
-AARCH64_OPT_EXTENSION("fp16fml", AARCH64_FL_F16FML, \
- AARCH64_FL_FP | AARCH64_FL_F16, 0, false, "asimdfhm")
-
-/* Enabling "sve" also enables "fp16", "fp" and "simd".
- Disabling "sve" disables "sve", "f32mm", "f64mm", "sve2", "sve2-aes",
- "sve2-sha3", "sve2-sm4" and "sve2-bitperm". */
-AARCH64_OPT_EXTENSION("sve", AARCH64_FL_SVE, AARCH64_FL_FP | AARCH64_FL_SIMD | \
- AARCH64_FL_F16, AARCH64_FL_F32MM | AARCH64_FL_F64MM | \
- AARCH64_FL_SVE2 | AARCH64_FL_SVE2_AES | \
- AARCH64_FL_SVE2_SHA3 | AARCH64_FL_SVE2_SM4 | \
- AARCH64_FL_SVE2_BITPERM, false, "sve")
-
-/* Enabling/Disabling "profile" does not enable/disable any other feature. */
-AARCH64_OPT_EXTENSION("profile", AARCH64_FL_PROFILE, 0, 0, false, "")
-
-/* Enabling/Disabling "rng" only changes "rng". */
-AARCH64_OPT_EXTENSION("rng", AARCH64_FL_RNG, 0, 0, false, "rng")
-
-/* Enabling/Disabling "memtag" only changes "memtag". */
-AARCH64_OPT_EXTENSION("memtag", AARCH64_FL_MEMTAG, 0, 0, false, "")
-
-/* Enabling/Disabling "sb" only changes "sb". */
-AARCH64_OPT_EXTENSION("sb", AARCH64_FL_SB, 0, 0, false, "sb")
-
-/* Enabling/Disabling "ssbs" only changes "ssbs". */
-AARCH64_OPT_EXTENSION("ssbs", AARCH64_FL_SSBS, 0, 0, false, "ssbs")
-
-/* Enabling/Disabling "predres" only changes "predres". */
-AARCH64_OPT_EXTENSION("predres", AARCH64_FL_PREDRES, 0, 0, false, "")
-
-/* Enabling "sve2" also enables "sve", "fp16", "fp", and "simd".
- Disabling "sve2" disables "sve2", "sve2-aes", "sve2-sha3", "sve2-sm4", and
- "sve2-bitperm". */
-AARCH64_OPT_EXTENSION("sve2", AARCH64_FL_SVE2, AARCH64_FL_SVE | \
- AARCH64_FL_FP | AARCH64_FL_SIMD | AARCH64_FL_F16, \
- AARCH64_FL_SVE2_AES | AARCH64_FL_SVE2_SHA3 | \
- AARCH64_FL_SVE2_SM4 | AARCH64_FL_SVE2_BITPERM, false, "sve2")
-
-/* Enabling "sve2-sm4" also enables "sm4", "simd", "fp16", "fp", "sve", and
- "sve2". Disabling "sve2-sm4" just disables "sve2-sm4". */
-AARCH64_OPT_EXTENSION("sve2-sm4", AARCH64_FL_SVE2_SM4, AARCH64_FL_SM4 | \
- AARCH64_FL_SIMD | AARCH64_FL_F16 | AARCH64_FL_FP | \
- AARCH64_FL_SVE | AARCH64_FL_SVE2, 0, false, "svesm4")
-
-/* Enabling "sve2-aes" also enables "aes", "simd", "fp16", "fp", "sve", and
- "sve2". Disabling "sve2-aes" just disables "sve2-aes". */
-AARCH64_OPT_EXTENSION("sve2-aes", AARCH64_FL_SVE2_AES, AARCH64_FL_AES | \
- AARCH64_FL_SIMD | AARCH64_FL_F16 | AARCH64_FL_FP | \
- AARCH64_FL_SVE | AARCH64_FL_SVE2, 0, false, "sveaes")
-
-/* Enabling "sve2-sha3" also enables "sha3", "simd", "fp16", "fp", "sve", and
- "sve2". Disabling "sve2-sha3" just disables "sve2-sha3". */
-AARCH64_OPT_EXTENSION("sve2-sha3", AARCH64_FL_SVE2_SHA3, AARCH64_FL_SHA3 | \
- AARCH64_FL_SHA2 | \
- AARCH64_FL_SIMD | AARCH64_FL_F16 | AARCH64_FL_FP | \
- AARCH64_FL_SVE | AARCH64_FL_SVE2, 0, false, "svesha3")
-
-/* Enabling "sve2-bitperm" also enables "simd", "fp16", "fp", "sve", and
- "sve2". Disabling "sve2-bitperm" just disables "sve2-bitperm". */
-AARCH64_OPT_EXTENSION("sve2-bitperm", AARCH64_FL_SVE2_BITPERM, AARCH64_FL_SIMD | \
- AARCH64_FL_F16 | AARCH64_FL_FP | AARCH64_FL_SVE | \
- AARCH64_FL_SVE2, 0, false, "svebitperm")
-
-/* Enabling or disabling "tme" only changes "tme". */
-AARCH64_OPT_EXTENSION("tme", AARCH64_FL_TME, 0, 0, false, "")
-
-/* Enabling "i8mm" also enables "simd" and "fp".
- Disabling "i8mm" only disables "i8mm". */
-AARCH64_OPT_EXTENSION("i8mm", AARCH64_FL_I8MM, \
- AARCH64_FL_SIMD | AARCH64_FL_FP, 0, false, "i8mm")
-
-/* Enabling "f32mm" also enables "sve", "fp16", "fp", and "simd".
- Disabling "f32mm" only disables "f32mm". */
-AARCH64_OPT_EXTENSION("f32mm", AARCH64_FL_F32MM, \
- AARCH64_FL_SVE | AARCH64_FL_F16 | AARCH64_FL_FP | \
- AARCH64_FL_SIMD, 0, false, "f32mm")
-
-/* Enabling "f64mm" also enables "sve", "fp16", "fp", and "simd".
- Disabling "f64mm" only disables "f64mm". */
-AARCH64_OPT_EXTENSION("f64mm", AARCH64_FL_F64MM, \
- AARCH64_FL_SVE | AARCH64_FL_F16 | AARCH64_FL_FP | \
- AARCH64_FL_SIMD, 0, false, "f64mm")
-
-/* Enabling "bf16" also enables "simd" and "fp".
- Disabling "bf16" only disables "bf16". */
-AARCH64_OPT_EXTENSION("bf16", AARCH64_FL_BF16, \
- AARCH64_FL_SIMD | AARCH64_FL_FP, 0, false, "bf16")
-
-/* Enabling/Disabling "flagm" only changes "flagm". */
-AARCH64_OPT_EXTENSION("flagm", AARCH64_FL_FLAGM, 0, 0, false, "flagm")
-
-/* Enabling/Disabling "pauth" only changes "pauth". */
-AARCH64_OPT_EXTENSION("pauth", AARCH64_FL_PAUTH, 0, 0, false, "paca pacg")
-
-/* Enabling/Disabling "ls64" only changes "ls64". */
-AARCH64_OPT_EXTENSION("ls64", AARCH64_FL_LS64, 0, 0, false, "")
-
-/* Enabling/disabling "mops" only changes "mops". */
-AARCH64_OPT_EXTENSION("mops", AARCH64_FL_MOPS, 0, 0, false, "")
+AARCH64_OPT_EXTENSION("sha3", SHA3, (SHA2), (), (), "sha3 sha512")
+
+AARCH64_OPT_EXTENSION("sm4", SM4, (SIMD), (), (), "sm3 sm4")
+
+/* An explicit +fp16fml implies +fp16, but a dependence on it does not.
+ Thus -march=armv8.4-a implies F16FML but not F16. -march=armv8.4-a+fp16
+ and -march=armv8.4-a+fp16fml are equivalent and enable both F16FML and F16.
+ -march=armv8.4-a+nofp16+fp16 enables F16 but not F16FML. */
+AARCH64_OPT_EXTENSION("fp16fml", F16FML, (), (F16), (), "asimdfhm")
+
+AARCH64_OPT_EXTENSION("sve", SVE, (SIMD, F16), (), (), "sve")
+
+AARCH64_OPT_EXTENSION("profile", PROFILE, (), (), (), "")
+
+AARCH64_OPT_EXTENSION("rng", RNG, (), (), (), "rng")
+
+AARCH64_OPT_EXTENSION("memtag", MEMTAG, (), (), (), "")
+
+AARCH64_OPT_EXTENSION("sb", SB, (), (), (), "sb")
+
+AARCH64_OPT_EXTENSION("ssbs", SSBS, (), (), (), "ssbs")
+
+AARCH64_OPT_EXTENSION("predres", PREDRES, (), (), (), "")
+
+AARCH64_OPT_EXTENSION("sve2", SVE2, (SVE), (), (), "sve2")
+
+AARCH64_OPT_EXTENSION("sve2-sm4", SVE2_SM4, (SVE2, SM4), (), (), "svesm4")
+
+AARCH64_OPT_EXTENSION("sve2-aes", SVE2_AES, (SVE2, AES), (), (), "sveaes")
+
+AARCH64_OPT_EXTENSION("sve2-sha3", SVE2_SHA3, (SVE2, SHA3), (), (), "svesha3")
+
+AARCH64_OPT_EXTENSION("sve2-bitperm", SVE2_BITPERM, (SVE2), (), (),
+ "svebitperm")
+
+AARCH64_OPT_EXTENSION("tme", TME, (), (), (), "")
+
+AARCH64_OPT_EXTENSION("i8mm", I8MM, (SIMD), (), (), "i8mm")
+
+AARCH64_OPT_EXTENSION("f32mm", F32MM, (SVE), (), (), "f32mm")
+
+AARCH64_OPT_EXTENSION("f64mm", F64MM, (SVE), (), (), "f64mm")
+
+/* An explicit +bf16 implies +simd, but +bf16+nosimd still enables scalar BF16
+ instructions. */
+AARCH64_OPT_EXTENSION("bf16", BF16, (FP), (SIMD), (), "bf16")
+
+AARCH64_OPT_EXTENSION("flagm", FLAGM, (), (), (), "flagm")
+
+AARCH64_OPT_EXTENSION("pauth", PAUTH, (), (), (), "paca pacg")
+
+AARCH64_OPT_EXTENSION("ls64", LS64, (), (), (), "")
+
+AARCH64_OPT_EXTENSION("mops", MOPS, (), (), (), "")
#undef AARCH64_OPT_EXTENSION
diff --git a/gcc/config/aarch64/aarch64-opts.h b/gcc/config/aarch64/aarch64-opts.h
index 421648a15..ba23c90c4 100644
--- a/gcc/config/aarch64/aarch64-opts.h
+++ b/gcc/config/aarch64/aarch64-opts.h
@@ -22,6 +22,10 @@
#ifndef GCC_AARCH64_OPTS_H
#define GCC_AARCH64_OPTS_H
+#ifndef USED_FOR_TARGET
+typedef uint64_t aarch64_feature_flags;
+#endif
+
/* The various cores that implement AArch64. */
enum aarch64_processor
{
diff --git a/gcc/config/aarch64/aarch64-sve-builtins.cc b/gcc/config/aarch64/aarch64-sve-builtins.cc
index 12d9beee4..c06e99339 100644
--- a/gcc/config/aarch64/aarch64-sve-builtins.cc
+++ b/gcc/config/aarch64/aarch64-sve-builtins.cc
@@ -701,9 +701,8 @@ check_required_extensions (location_t location, tree fndecl,
return check_required_registers (location, fndecl);
static const struct { uint64_t flag; const char *name; } extensions[] = {
-#define AARCH64_OPT_EXTENSION(EXT_NAME, FLAG_CANONICAL, FLAGS_ON, FLAGS_OFF, \
- SYNTHETIC, FEATURE_STRING) \
- { FLAG_CANONICAL, EXT_NAME },
+#define AARCH64_OPT_EXTENSION(EXT_NAME, IDENT, C, D, E, F) \
+ { AARCH64_FL_##IDENT, EXT_NAME },
#include "aarch64-option-extensions.def"
};
diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
index f975aad07..1363873b1 100644
--- a/gcc/config/aarch64/aarch64.cc
+++ b/gcc/config/aarch64/aarch64.cc
@@ -81,6 +81,7 @@
#include "rtlanal.h"
#include "tree-dfa.h"
#include "asan.h"
+#include "aarch64-feature-deps.h"
/* This file should be included last. */
#include "target-def.h"
@@ -2935,8 +2936,9 @@ struct processor
/* Architectures implementing AArch64. */
static const struct processor all_architectures[] =
{
-#define AARCH64_ARCH(NAME, CORE, ARCH_IDENT, ARCH_REV, FLAGS) \
- {NAME, CORE, CORE, AARCH64_ARCH_##ARCH_IDENT, FLAGS, NULL},
+#define AARCH64_ARCH(NAME, CORE, ARCH_IDENT, D, E) \
+ {NAME, CORE, CORE, AARCH64_ARCH_##ARCH_IDENT, \
+ feature_deps::ARCH_IDENT ().enable, NULL},
#include "aarch64-arches.def"
{NULL, aarch64_none, aarch64_none, aarch64_no_arch, 0, NULL}
};
@@ -2944,12 +2946,12 @@ static const struct processor all_architectures[] =
/* Processor cores implementing AArch64. */
static const struct processor all_cores[] =
{
-#define AARCH64_CORE(NAME, IDENT, SCHED, ARCH, FLAGS, COSTS, IMP, PART, VARIANT) \
- {NAME, IDENT, SCHED, AARCH64_ARCH_##ARCH, \
- AARCH64_FL_FOR_##ARCH | FLAGS, &COSTS##_tunings},
+#define AARCH64_CORE(NAME, IDENT, SCHED, ARCH, E, COSTS, G, H, I) \
+ {NAME, IDENT, SCHED, AARCH64_ARCH_##ARCH, \
+ feature_deps::cpu_##IDENT, &COSTS##_tunings},
#include "aarch64-cores.def"
{"generic", generic, cortexa53, AARCH64_ARCH_V8A,
- AARCH64_FL_FOR_V8A, &generic_tunings},
+ feature_deps::V8A ().enable, &generic_tunings},
{NULL, aarch64_none, aarch64_none, aarch64_no_arch, 0, NULL}
};
diff --git a/gcc/config/aarch64/aarch64.h b/gcc/config/aarch64/aarch64.h
index f4e0cd148..50a2ef444 100644
--- a/gcc/config/aarch64/aarch64.h
+++ b/gcc/config/aarch64/aarch64.h
@@ -144,149 +144,27 @@
#define PCC_BITFIELD_TYPE_MATTERS 1
-/* Instruction tuning/selection flags. */
-
-/* Bit values used to identify processor capabilities. */
-#define AARCH64_FL_SIMD (1 << 0) /* Has SIMD instructions. */
-#define AARCH64_FL_FP (1 << 1) /* Has FP. */
-#define AARCH64_FL_CRYPTO (1 << 2) /* Has crypto. */
-#define AARCH64_FL_CRC (1 << 3) /* Has CRC. */
-/* ARMv8.1-A architecture extensions. */
-#define AARCH64_FL_LSE (1 << 4) /* Has Large System Extensions. */
-#define AARCH64_FL_RDMA (1 << 5) /* Has Round Double Multiply Add. */
-#define AARCH64_FL_V8_1A (1 << 6) /* Has ARMv8.1-A extensions. */
-/* Armv8-R. */
-#define AARCH64_FL_V8R (1 << 7) /* Armv8-R AArch64. */
-/* ARMv8.2-A architecture extensions. */
-#define AARCH64_FL_V8_2A (1 << 8) /* Has ARMv8.2-A features. */
-#define AARCH64_FL_F16 (1 << 9) /* Has ARMv8.2-A FP16 extensions. */
-#define AARCH64_FL_SVE (1 << 10) /* Has Scalable Vector Extensions. */
-/* ARMv8.3-A architecture extensions. */
-#define AARCH64_FL_V8_3A (1 << 11) /* Has ARMv8.3-A features. */
-#define AARCH64_FL_RCPC (1 << 12) /* Has support for RCpc model. */
-#define AARCH64_FL_DOTPROD (1 << 13) /* Has ARMv8.2-A Dot Product ins. */
-/* New flags to split crypto into aes and sha2. */
-#define AARCH64_FL_AES (1 << 14) /* Has Crypto AES. */
-#define AARCH64_FL_SHA2 (1 << 15) /* Has Crypto SHA2. */
-/* ARMv8.4-A architecture extensions. */
-#define AARCH64_FL_V8_4A (1 << 16) /* Has ARMv8.4-A features. */
-#define AARCH64_FL_SM4 (1 << 17) /* Has ARMv8.4-A SM3 and SM4. */
-#define AARCH64_FL_SHA3 (1 << 18) /* Has ARMv8.4-a SHA3 and SHA512. */
-#define AARCH64_FL_F16FML (1 << 19) /* Has ARMv8.4-a FP16 extensions. */
-
-/* Statistical Profiling extensions. */
-#define AARCH64_FL_PROFILE (1 << 21)
-
-/* ARMv8.5-A architecture extensions. */
-#define AARCH64_FL_V8_5A (1 << 22) /* Has ARMv8.5-A features. */
-#define AARCH64_FL_RNG (1 << 23) /* ARMv8.5-A Random Number Insns. */
-#define AARCH64_FL_MEMTAG (1 << 24) /* ARMv8.5-A Memory Tagging
- Extensions. */
-
-/* Speculation Barrier instruction supported. */
-#define AARCH64_FL_SB (1 << 25)
-
-/* Speculative Store Bypass Safe instruction supported. */
-#define AARCH64_FL_SSBS (1 << 26)
-
-/* Execution and Data Prediction Restriction instructions supported. */
-#define AARCH64_FL_PREDRES (1 << 27)
-
-/* SVE2 instruction supported. */
-#define AARCH64_FL_SVE2 (1 << 28)
-#define AARCH64_FL_SVE2_AES (1 << 29)
-#define AARCH64_FL_SVE2_SM4 (1 << 30)
-#define AARCH64_FL_SVE2_SHA3 (1ULL << 31)
-#define AARCH64_FL_SVE2_BITPERM (1ULL << 32)
-
-/* Transactional Memory Extension. */
-#define AARCH64_FL_TME (1ULL << 33) /* Has TME instructions. */
-
-/* Armv8.6-A architecture extensions. */
-#define AARCH64_FL_V8_6A (1ULL << 34)
-
-/* 8-bit Integer Matrix Multiply (I8MM) extensions. */
-#define AARCH64_FL_I8MM (1ULL << 35)
-
-/* Brain half-precision floating-point (BFloat16) Extension. */
-#define AARCH64_FL_BF16 (1ULL << 36)
-
-/* 32-bit Floating-point Matrix Multiply (F32MM) extensions. */
-#define AARCH64_FL_F32MM (1ULL << 37)
-
-/* 64-bit Floating-point Matrix Multiply (F64MM) extensions. */
-#define AARCH64_FL_F64MM (1ULL << 38)
-
-/* Flag Manipulation Instructions (FLAGM) extension. */
-#define AARCH64_FL_FLAGM (1ULL << 39)
-
-/* Pointer Authentication (PAUTH) extension. */
-#define AARCH64_FL_PAUTH (1ULL << 40)
-
-/* Armv9.0-A. */
-#define AARCH64_FL_V9A (1ULL << 41) /* Armv9.0-A Architecture. */
-
-/* 64-byte atomic load/store extensions. */
-#define AARCH64_FL_LS64 (1ULL << 42)
-
-/* Armv8.7-a architecture extensions. */
-#define AARCH64_FL_V8_7A (1ULL << 43)
-
-/* Hardware memory operation instructions. */
-#define AARCH64_FL_MOPS (1ULL << 44)
-
-/* Armv8.8-a architecture extensions. */
-#define AARCH64_FL_V8_8A (1ULL << 45)
-
-/* Armv9.1-A. */
-#define AARCH64_FL_V9_1A (1ULL << 46)
-
-/* Armv9.2-A. */
-#define AARCH64_FL_V9_2A (1ULL << 47)
-
-/* Armv9.3-A. */
-#define AARCH64_FL_V9_3A (1ULL << 48)
-
-/* Has FP and SIMD. */
-#define AARCH64_FL_FPSIMD (AARCH64_FL_FP | AARCH64_FL_SIMD)
-
-/* Has FP without SIMD. */
-#define AARCH64_FL_FPQ16 (AARCH64_FL_FP & ~AARCH64_FL_SIMD)
-
-/* Architecture flags that effect instruction selection. */
-#define AARCH64_FL_FOR_V8A (AARCH64_FL_FPSIMD)
-#define AARCH64_FL_FOR_V8_1A \
- (AARCH64_FL_FOR_V8A | AARCH64_FL_LSE | AARCH64_FL_CRC \
- | AARCH64_FL_RDMA | AARCH64_FL_V8_1A)
-#define AARCH64_FL_FOR_V8_2A \
- (AARCH64_FL_FOR_V8_1A | AARCH64_FL_V8_2A)
-#define AARCH64_FL_FOR_V8_3A \
- (AARCH64_FL_FOR_V8_2A | AARCH64_FL_V8_3A | AARCH64_FL_PAUTH)
-#define AARCH64_FL_FOR_V8_4A \
- (AARCH64_FL_FOR_V8_3A | AARCH64_FL_V8_4A | AARCH64_FL_F16FML \
- | AARCH64_FL_DOTPROD | AARCH64_FL_FLAGM)
-#define AARCH64_FL_FOR_V8_5A \
- (AARCH64_FL_FOR_V8_4A | AARCH64_FL_V8_5A \
- | AARCH64_FL_SB | AARCH64_FL_SSBS | AARCH64_FL_PREDRES)
-#define AARCH64_FL_FOR_V8_6A \
- (AARCH64_FL_FOR_V8_5A | AARCH64_FL_V8_6A | AARCH64_FL_FPSIMD \
- | AARCH64_FL_I8MM | AARCH64_FL_BF16)
-#define AARCH64_FL_FOR_V8_7A \
- (AARCH64_FL_FOR_V8_6A | AARCH64_FL_V8_7A | AARCH64_FL_LS64)
-#define AARCH64_FL_FOR_V8_8A \
- (AARCH64_FL_FOR_V8_7A | AARCH64_FL_V8_8A | AARCH64_FL_MOPS)
-
-#define AARCH64_FL_FOR_V8R \
- (AARCH64_FL_FOR_V8_4A | AARCH64_FL_V8R)
-#define AARCH64_FL_FOR_V9A \
- (AARCH64_FL_FOR_V8_5A | AARCH64_FL_SVE | AARCH64_FL_SVE2 | AARCH64_FL_V9A \
- | AARCH64_FL_F16)
-#define AARCH64_FL_FOR_V9_1A \
- (AARCH64_FL_FOR_V9A | AARCH64_FL_FOR_V8_6A | AARCH64_FL_V9_1A)
-#define AARCH64_FL_FOR_V9_2A \
- (AARCH64_FL_FOR_V9_1A | AARCH64_FL_FOR_V8_7A | AARCH64_FL_V9_2A)
-#define AARCH64_FL_FOR_V9_3A \
- (AARCH64_FL_FOR_V9_2A | AARCH64_FL_FOR_V8_8A | AARCH64_FL_V9_3A)
+#ifndef USED_FOR_TARGET
+
+/* Define an enum of all features (architectures and extensions). */
+enum class aarch64_feature : unsigned char {
+#define AARCH64_OPT_EXTENSION(A, IDENT, C, D, E, F) IDENT,
+#define AARCH64_ARCH(A, B, IDENT, D, E) IDENT,
+#include "aarch64-option-extensions.def"
+#include "aarch64-arches.def"
+};
+
+/* Define unique flags for each of the above. */
+#define HANDLE(IDENT) \
+ constexpr auto AARCH64_FL_##IDENT \
+ = aarch64_feature_flags (1) << int (aarch64_feature::IDENT);
+#define AARCH64_OPT_EXTENSION(A, IDENT, C, D, E, F) HANDLE (IDENT)
+#define AARCH64_ARCH(A, B, IDENT, D, E) HANDLE (IDENT)
+#include "aarch64-option-extensions.def"
+#include "aarch64-arches.def"
+#undef HANDLE
+
+#endif
/* Macros to test ISA flags. */
diff --git a/gcc/config/aarch64/driver-aarch64.cc b/gcc/config/aarch64/driver-aarch64.cc
index 97690de62..ddfc9451f 100644
--- a/gcc/config/aarch64/driver-aarch64.cc
+++ b/gcc/config/aarch64/driver-aarch64.cc
@@ -26,6 +26,7 @@
#include "coretypes.h"
#include "tm.h"
#include "aarch64-protos.h"
+#include "aarch64-feature-deps.h"
struct aarch64_arch_extension
{
@@ -34,9 +35,8 @@ struct aarch64_arch_extension
const char *feat_string;
};
-#define AARCH64_OPT_EXTENSION(EXT_NAME, FLAG_CANONICAL, FLAGS_ON, FLAGS_OFF, \
- SYNTHETIC, FEATURE_STRING) \
- { EXT_NAME, FLAG_CANONICAL, FEATURE_STRING },
+#define AARCH64_OPT_EXTENSION(EXT_NAME, IDENT, C, D, E, FEATURE_STRING) \
+ { EXT_NAME, AARCH64_FL_##IDENT, FEATURE_STRING },
static struct aarch64_arch_extension aarch64_extensions[] =
{
#include "aarch64-option-extensions.def"
@@ -62,7 +62,7 @@ struct aarch64_core_data
#define DEFAULT_ARCH "8A"
#define AARCH64_CORE(CORE_NAME, CORE_IDENT, SCHED, ARCH, FLAGS, COSTS, IMP, PART, VARIANT) \
- { CORE_NAME, #ARCH, IMP, PART, VARIANT, AARCH64_FL_FOR_##ARCH | FLAGS },
+ { CORE_NAME, #ARCH, IMP, PART, VARIANT, feature_deps::cpu_##CORE_IDENT },
static struct aarch64_core_data aarch64_cpu_data[] =
{
@@ -80,7 +80,7 @@ struct aarch64_arch_driver_info
/* Skip the leading "V" in the architecture name. */
#define AARCH64_ARCH(NAME, CORE, ARCH_IDENT, ARCH_REV, FLAGS) \
- { #ARCH_IDENT + 1, NAME, FLAGS },
+ { #ARCH_IDENT + 1, NAME, feature_deps::ARCH_IDENT ().enable },
static struct aarch64_arch_driver_info aarch64_arches[] =
{
--
2.33.0
Loading...
马建仓 AI 助手
尝试更多
代码解读
代码找茬
代码优化
1
https://gitee.com/src-openeuler/gcc.git
git@gitee.com:src-openeuler/gcc.git
src-openeuler
gcc
gcc
master

搜索帮助