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 956afa707149f7b58b3488bc33680ff96f4e425d..6532bdaafb521a20368e522826e2b69cdaca647e 100644 (file)
--- a/gcc/config/aarch64/aarch64-cores.def
+++ b/gcc/config/aarch64/aarch64-cores.def
@@ -176,5 +176,6 @@ AARCH64_CORE("cobalt-100",   cobalt100, cortexa57, 9A, AARCH64_FL_FOR_ARCH9 | AA
 
 AARCH64_CORE("demeter", demeter, cortexa57, 9A, AARCH64_FL_FOR_ARCH9 | 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, 9A, AARCH64_FL_FOR_ARCH9 | 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("grace", grace, cortexa57, 9A, AARCH64_FL_FOR_ARCH9 | AARCH64_FL_I8MM | AARCH64_FL_BF16 | AARCH64_FL_SVE2_BITPERM | AARCH64_FL_CRYPTO | AARCH64_FL_SHA3 | AARCH64_FL_SM4 | AARCH64_FL_SVE2_AES | AARCH64_FL_SVE2_SHA3 | AARCH64_FL_SVE2_SM4 | AARCH64_FL_PROFILE, neoversev2, 0x41, 0xd4f, -1)
 
 #undef AARCH64_CORE

diff --git a/gcc/config/aarch64/aarch64-tune.md b/gcc/config/aarch64/aarch64-tune.md
index 2c1852c8fe67115b323caa8ed74e6d1c719b4256..0c139e3e72987d37938092027d58e9acc19d63e8 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,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,ares,neoversen1,neoversee1,octeontx2,octeontx2t98,octeontx2t96,octeontx2t93,octeontx2f95,octeontx2f95n,octeontx2f95mm,a64fx,tsv110,thunderx3t110,zeus,neoversev1,neoverse512tvb,saphira,cortexa57cortexa53,cortexa72cortexa53,cortexa73cortexa35,cortexa73cortexa53,cortexa75cortexa55,cortexa76cortexa55,cortexr82,cortexa510,cortexa710,cortexx2,neoversen2,cobalt100,demeter,neoversev2"
+       "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,ares,neoversen1,neoversee1,octeontx2,octeontx2t98,octeontx2t96,octeontx2t93,octeontx2f95,octeontx2f95n,octeontx2f95mm,a64fx,tsv110,thunderx3t110,zeus,neoversev1,neoverse512tvb,saphira,cortexa57cortexa53,cortexa72cortexa53,cortexa73cortexa35,cortexa73cortexa53,cortexa75cortexa55,cortexa76cortexa55,cortexr82,cortexa510,cortexa710,cortexx2,neoversen2,cobalt100,demeter,neoversev2,grace"
        (const (symbol_ref "((enum attr_tune) aarch64_tune)")))

diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index c83f667260e1ee7bf10460511f27a9d42d6c8a60..fbfa3241e7f61c01a6bc8ed093f1bf3717e68ac1 100644 (file)
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -19203,8 +19203,8 @@ performance of the code.  Permissible values for this option are:
 @samp{cortex-a78}, @samp{cortex-a78ae}, @samp{cortex-a78c},
 @samp{ares}, @samp{exynos-m1}, @samp{emag}, @samp{falkor},
 @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},