[aarch64] Add support for -mcpu=grace

This adds support for the NVIDIA Grace CPU to aarch64.
We reuse the tuning decisions for the Neoverse V2 core, but include a
number of architecture features that are not enabled by default in
-mcpu=neoverse-v2.

This allows Grace users to more simply target the CPU with -mcpu=grace
rather than remembering what extensions to tag on top of
-mcpu=neoverse-v2.

Bootstrapped and tested on aarch64-none-linux-gnu.
gcc/

	* config/aarch64/aarch64-cores.def (grace): New entry.
	* config/aarch64/aarch64-tune.md: Regenerate.
	* doc/invoke.texi (AArch64 Options): Document the above.

Signed-off-by: Kyrylo Tkachov <ktkachov@nvidia.com>

diff --git a/gcc/config/aarch64/aarch64-cores.def b/gcc/config/aarch64/aarch64-cores.def
index 0e05e81761cb1399d4e85a6c77330db59c676bd4..e58bc0f27de3d60d39c02d2be2aa15570bd5db4d 100644 (file)
--- a/gcc/config/aarch64/aarch64-cores.def
+++ b/gcc/config/aarch64/aarch64-cores.def
@@ -194,6 +194,8 @@ AARCH64_CORE("neoverse-n2", neoversen2, cortexa57, V9A, (I8MM, BF16, SVE2_BITPER
 AARCH64_CORE("cobalt-100",   cobalt100, cortexa57, V9A, (I8MM, BF16, SVE2_BITPERM, RNG, MEMTAG, PROFILE), neoversen2, 0x6d, 0xd49, -1)
 
 AARCH64_CORE("neoverse-v2", neoversev2, cortexa57, V9A, (I8MM, BF16, SVE2_BITPERM, RNG, MEMTAG, PROFILE), neoversev2, 0x41, 0xd4f, -1)
+AARCH64_CORE("grace", grace, cortexa57, V9A, (I8MM, BF16, SVE2_BITPERM, SVE2_AES, SVE2_SHA3, SVE2_SM4, PROFILE), neoversev2, 0x41, 0xd4f, -1)
+
 AARCH64_CORE("demeter", demeter, cortexa57, V9A, (I8MM, BF16, SVE2_BITPERM, RNG, MEMTAG, PROFILE), neoversev2, 0x41, 0xd4f, -1)
 
 /* Generic Architecture Processors.  */

diff --git a/gcc/config/aarch64/aarch64-tune.md b/gcc/config/aarch64/aarch64-tune.md
index 9b1f32a0330ab0eed98a84b6b5f332344278a439..719fd3dc62a5860aad3aa92785413892e46f8816 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,cortexx2,cortexx3,cortexx4,neoversen2,cobalt100,neoversev2,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,tsv110,thunderx3t110,neoversev1,zeus,neoverse512tvb,saphira,oryon1,cortexa57cortexa53,cortexa72cortexa53,cortexa73cortexa35,cortexa73cortexa53,cortexa75cortexa55,cortexa76cortexa55,cortexr82,cortexa510,cortexa520,cortexa710,cortexa715,cortexa720,cortexx2,cortexx3,cortexx4,neoversen2,cobalt100,neoversev2,grace,demeter,generic,generic_armv8_a,generic_armv9_a"
        (const (symbol_ref "((enum attr_tune) aarch64_tune)")))

diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index 729dbc1691ee4a0433e3b7025962c7549bdb647a..30c4b002d1f9b39d33f6c403bf51554703cf73fd 100644 (file)
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -21437,8 +21437,8 @@ performance of the code.  Permissible values for this option are:
 @samp{ares}, @samp{exynos-m1}, @samp{emag}, @samp{falkor},
 @samp{oryon-1},
 @samp{neoverse-512tvb}, @samp{neoverse-e1}, @samp{neoverse-n1},
-@samp{neoverse-n2}, @samp{neoverse-v1}, @samp{neoverse-v2}, @samp{qdf24xx},
-@samp{saphira}, @samp{phecda}, @samp{xgene1}, @samp{vulcan},
+@samp{neoverse-n2}, @samp{neoverse-v1}, @samp{neoverse-v2}, @samp{grace},
+@samp{qdf24xx}, @samp{saphira}, @samp{phecda}, @samp{xgene1}, @samp{vulcan},
 @samp{octeontx}, @samp{octeontx81},  @samp{octeontx83},
 @samp{octeontx2}, @samp{octeontx2t98}, @samp{octeontx2t96}
 @samp{octeontx2t93}, @samp{octeontx2f95}, @samp{octeontx2f95n},