From: Wilco Dijkstra <Wilco.Dijkstra@arm.com>
To: "Naveen.Hurugalawadi@cavium.com" <Naveen.Hurugalawadi@cavium.com>,
"Andrew.pinski@cavium.com" <Andrew.pinski@cavium.com>,
Kyrylo Tkachov <Kyrylo.Tkachov@arm.com>,
James Greenhalgh <James.Greenhalgh@arm.com>
Cc: nd <nd@arm.com>, GCC Patches <gcc-patches@gcc.gnu.org>
Subject: Re: [PATCH][AArch64] Implement ALU_BRANCH fusion
Date: Wed, 15 Mar 2017 15:20:00 -0000 [thread overview]
Message-ID: <DB6PR0802MB2615C7C0031757AEE914E4C183270@DB6PR0802MB2615.eurprd08.prod.outlook.com> (raw)
In-Reply-To: <VI1PR0802MB26218E2C0940948518A0571783210@VI1PR0802MB2621.eurprd08.prod.outlook.com>
Hi,
I think the patch isn't quite complete yet. You will also need changes in
generic code. Currently sched_macro_fuse_insns() does:
if (any_condjump_p (insn))
{
unsigned int condreg1, condreg2;
rtx cc_reg_1;
targetm.fixed_condition_code_regs (&condreg1, &condreg2);
cc_reg_1 = gen_rtx_REG (CCmode, condreg1);
prev = prev_nonnote_nondebug_insn (insn);
if (!reg_referenced_p (cc_reg_1, PATTERN (insn))
|| !prev
|| !modified_in_p (cc_reg_1, prev))
return;
}
Ie. it explicitly looks for a flag-setting ALU instruction whose condition is
used by a conditional branch, so none of the cases in your patch can match.
Note this code also excludes all CBZ type branches as fusion candidates,
is that intended too?
Wilco
next parent reply other threads:[~2017-03-15 15:20 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <VI1PR0802MB26218E2C0940948518A0571783210@VI1PR0802MB2621.eurprd08.prod.outlook.com>
2017-03-15 15:20 ` Wilco Dijkstra [this message]
2017-03-21 5:37 ` Andrew Pinski
2017-03-27 7:33 ` Hurugalawadi, Naveen
2017-04-25 7:44 ` [PING][PATCH][AArch64] " Hurugalawadi, Naveen
2017-04-25 11:39 ` Wilco Dijkstra
2017-04-26 12:59 ` Hurugalawadi, Naveen
2017-04-26 14:29 ` Wilco Dijkstra
2017-04-27 7:32 ` Hurugalawadi, Naveen
2017-05-11 4:57 ` [PING] [PATCH] [AArch64] " Hurugalawadi, Naveen
2017-05-26 7:14 ` [PING 2] " Hurugalawadi, Naveen
2017-05-26 11:39 ` Wilco Dijkstra
2017-06-14 10:29 ` [PING 3] " Hurugalawadi, Naveen
2017-06-14 11:37 ` [PING][PATCH][AArch64] " James Greenhalgh
2017-03-06 5:12 [PATCH][AArch64] " Hurugalawadi, Naveen
2017-03-08 18:04 ` James Greenhalgh
2017-03-09 6:22 ` Hurugalawadi, Naveen
2017-03-09 10:22 ` James Greenhalgh
2017-03-15 5:33 ` Hurugalawadi, Naveen
2017-03-15 9:23 ` Kyrill Tkachov
2017-03-15 10:04 ` Hurugalawadi, Naveen
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=DB6PR0802MB2615C7C0031757AEE914E4C183270@DB6PR0802MB2615.eurprd08.prod.outlook.com \
--to=wilco.dijkstra@arm.com \
--cc=Andrew.pinski@cavium.com \
--cc=James.Greenhalgh@arm.com \
--cc=Kyrylo.Tkachov@arm.com \
--cc=Naveen.Hurugalawadi@cavium.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=nd@arm.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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).