* [PATCH][aarch64] Use neoversen1 tuning struct for -mcpu=cortex-a76
@ 2019-07-30 17:08 Kyrill Tkachov
2019-08-12 18:48 ` James Greenhalgh
0 siblings, 1 reply; 2+ messages in thread
From: Kyrill Tkachov @ 2019-07-30 17:08 UTC (permalink / raw)
To: gcc-patches; +Cc: Richard Earnshaw, Marcus Shawcroft, James Greenhalgh
[-- Attachment #1: Type: text/plain, Size: 491 bytes --]
Hi all,
The neoversen1 tuning struct gives better performance on the Cortex-A76,
so use that.
The only difference from the current tuning is the function and label
alignment settings.
This gives about 1.3% improvement on SPEC2006 int and 0.3% on SPEC2006 fp.
Tested on aarch64-none-elf.
Ok for trunk?
Thanks,
Kyrill
2019-07-31 Kyrylo Tkachov <kyrylo.tkachov@arm.com>
   * config/aarch64/aarch64-cores.def (cortex-a76): Use neoversen1 tuning
   struct.
[-- Attachment #2: a76-tuning.patch --]
[-- Type: text/x-patch, Size: 1612 bytes --]
diff --git a/gcc/config/aarch64/aarch64-cores.def b/gcc/config/aarch64/aarch64-cores.def
index 82d91d62519f0476e059718d8c2f02e3ea5a0613..bd257aeb34e7948caf729e5a684ddd9ceba457a4 100644
--- a/gcc/config/aarch64/aarch64-cores.def
+++ b/gcc/config/aarch64/aarch64-cores.def
@@ -99,7 +99,7 @@ AARCH64_CORE("thunderx2t99", thunderx2t99, thunderx2t99, 8_1A, AARCH64_FL_FOR
/* ARM ('A') cores. */
AARCH64_CORE("cortex-a55", cortexa55, cortexa53, 8_2A, AARCH64_FL_FOR_ARCH8_2 | AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD, cortexa53, 0x41, 0xd05, -1)
AARCH64_CORE("cortex-a75", cortexa75, cortexa57, 8_2A, AARCH64_FL_FOR_ARCH8_2 | AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD, cortexa73, 0x41, 0xd0a, -1)
-AARCH64_CORE("cortex-a76", cortexa76, cortexa57, 8_2A, AARCH64_FL_FOR_ARCH8_2 | AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD, cortexa72, 0x41, 0xd0b, -1)
+AARCH64_CORE("cortex-a76", cortexa76, cortexa57, 8_2A, AARCH64_FL_FOR_ARCH8_2 | AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD, neoversen1, 0x41, 0xd0b, -1)
AARCH64_CORE("ares", ares, cortexa57, 8_2A, AARCH64_FL_FOR_ARCH8_2 | AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD | AARCH64_FL_PROFILE, neoversen1, 0x41, 0xd0c, -1)
AARCH64_CORE("neoverse-n1", neoversen1, cortexa57, 8_2A, AARCH64_FL_FOR_ARCH8_2 | AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD | AARCH64_FL_PROFILE, neoversen1, 0x41, 0xd0c, -1)
AARCH64_CORE("neoverse-e1", neoversee1, cortexa53, 8_2A, AARCH64_FL_FOR_ARCH8_2 | AARCH64_FL_F16 | AARCH64_FL_RCPC | AARCH64_FL_DOTPROD | AARCH64_FL_SSBS, cortexa53, 0x41, 0xd4a, -1)
^ permalink raw reply [flat|nested] 2+ messages in thread
* Re: [PATCH][aarch64] Use neoversen1 tuning struct for -mcpu=cortex-a76
2019-07-30 17:08 [PATCH][aarch64] Use neoversen1 tuning struct for -mcpu=cortex-a76 Kyrill Tkachov
@ 2019-08-12 18:48 ` James Greenhalgh
0 siblings, 0 replies; 2+ messages in thread
From: James Greenhalgh @ 2019-08-12 18:48 UTC (permalink / raw)
To: Kyrill Tkachov; +Cc: gcc-patches, Richard Earnshaw, Marcus Shawcroft, nd
On Tue, Jul 30, 2019 at 05:59:15PM +0100, Kyrill Tkachov wrote:
> Hi all,
>
> The neoversen1 tuning struct gives better performance on the Cortex-A76,
> so use that.
> The only difference from the current tuning is the function and label
> alignment settings.
>
> This gives about 1.3% improvement on SPEC2006 int and 0.3% on SPEC2006 fp.
>
> Tested on aarch64-none-elf.
>
> Ok for trunk?
OK.
Thanks,
James
> Thanks,
> Kyrill
>
> 2019-07-31 Kyrylo Tkachov <kyrylo.tkachov@arm.com>
>
> Â Â Â * config/aarch64/aarch64-cores.def (cortex-a76): Use neoversen1 tuning
> Â Â Â struct.
>
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2019-08-12 17:08 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2019-07-30 17:08 [PATCH][aarch64] Use neoversen1 tuning struct for -mcpu=cortex-a76 Kyrill Tkachov
2019-08-12 18:48 ` James Greenhalgh
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).