From: Charlie Jenkins <charlie@rivosinc.com>
To: Al Viro <viro@zeniv.linux.org.uk>
Cc: Palmer Dabbelt <palmer@dabbelt.com>,
Conor Dooley <conor@kernel.org>,
Samuel Holland <samuel.holland@sifive.com>,
David Laight <David.Laight@aculab.com>,
Xiao Wang <xiao.w.wang@intel.com>, Evan Green <evan@rivosinc.com>,
linux-riscv@lists.infradead.org, linux-kernel@vger.kernel.org,
linux-arch@vger.kernel.org,
Paul Walmsley <paul.walmsley@sifive.com>,
Albert Ou <aou@eecs.berkeley.edu>, Arnd Bergmann <arnd@arndb.de>
Subject: Re: [PATCH v8 1/5] asm-generic: Improve csum_fold
Date: Fri, 27 Oct 2023 17:04:45 -0700 [thread overview]
Message-ID: <ZTxQHVplimd4tquE@ghost> (raw)
In-Reply-To: <20231027231036.GM800259@ZenIV>
On Sat, Oct 28, 2023 at 12:10:36AM +0100, Al Viro wrote:
> On Fri, Oct 27, 2023 at 03:43:51PM -0700, Charlie Jenkins wrote:
> > /*
> > * computes the checksum of a memory block at buff, length len,
> > * and adds in "sum" (32-bit)
> > @@ -31,9 +33,7 @@ extern __sum16 ip_fast_csum(const void *iph, unsigned int ihl);
> > static inline __sum16 csum_fold(__wsum csum)
> > {
> > u32 sum = (__force u32)csum;
> > - sum = (sum & 0xffff) + (sum >> 16);
> > - sum = (sum & 0xffff) + (sum >> 16);
> > - return (__force __sum16)~sum;
> > + return (__force __sum16)((~sum - ror32(sum, 16)) >> 16);
> > }
>
> Will (~(sum + ror32(sum, 16))>>16 produce worse code than that?
> Because at least with recent gcc this will generate the exact thing
> you get from arm inline asm...
Yes that will produce worse code because an out-of-order processor will be able to
leverage that ~sum and ror32(sum, 16) can be computed independently of
each other. There are more strict data dependencies in (~(sum +
ror32(sum, 16))>>16.
- Charlie
_______________________________________________
linux-riscv mailing list
linux-riscv@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-riscv
next prev parent reply other threads:[~2023-10-28 0:05 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-10-27 22:43 [PATCH v8 0/5] riscv: Add fine-tuned checksum functions Charlie Jenkins
2023-10-27 22:43 ` [PATCH v8 1/5] asm-generic: Improve csum_fold Charlie Jenkins
2023-10-27 23:10 ` Al Viro
2023-10-28 0:04 ` Charlie Jenkins [this message]
2023-10-27 22:43 ` [PATCH v8 2/5] riscv: Add static key for misaligned accesses Charlie Jenkins
2023-10-27 22:43 ` [PATCH v8 3/5] riscv: Checksum header Charlie Jenkins
2023-10-31 9:11 ` Wang, Xiao W
2023-10-31 22:53 ` Charlie Jenkins
2023-10-27 22:43 ` [PATCH v8 4/5] riscv: Add checksum library Charlie Jenkins
2023-10-31 9:51 ` Wang, Xiao W
2023-10-31 22:59 ` Charlie Jenkins
2023-10-27 22:43 ` [PATCH v8 5/5] riscv: Test checksum functions Charlie Jenkins
2023-10-31 7:57 ` [PATCH v8 0/5] riscv: Add fine-tuned " Conor Dooley
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=ZTxQHVplimd4tquE@ghost \
--to=charlie@rivosinc.com \
--cc=David.Laight@aculab.com \
--cc=aou@eecs.berkeley.edu \
--cc=arnd@arndb.de \
--cc=conor@kernel.org \
--cc=evan@rivosinc.com \
--cc=linux-arch@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-riscv@lists.infradead.org \
--cc=palmer@dabbelt.com \
--cc=paul.walmsley@sifive.com \
--cc=samuel.holland@sifive.com \
--cc=viro@zeniv.linux.org.uk \
--cc=xiao.w.wang@intel.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 NNTP newsgroup(s).