From: "Rafał Pietrak" <embedded@ztk-rp.eu>
To: "Richard Earnshaw (lists)" <Richard.Earnshaw@arm.com>,
Ian Lance Taylor <iant@golang.org>
Cc: Martin Uecker <muecker@gwdg.de>, "gcc@gcc.gnu.org" <gcc@gcc.gnu.org>
Subject: Re: wishlist: support for shorter pointers
Date: Mon, 3 Jul 2023 19:34:41 +0200 [thread overview]
Message-ID: <53154623-01fc-62e6-fe25-9f164b67e6e3@ztk-rp.eu> (raw)
In-Reply-To: <33c6c1a6-ca51-bf57-fdcd-d62b738a6f99@arm.com>
W dniu 3.07.2023 o 18:57, Richard Earnshaw (lists) pisze:
> On 03/07/2023 17:42, Rafał Pietrak via Gcc wrote:
>> Hi Ian,
[---------]
>> And WiKi reporting up to 40% performance improvements in some corner
>> cases is impressive and encouraging. I believe, that the reported
>> average of 5-8% improvement would be significantly better within MCU
>> tiny resources environment. In MCU world, such improvement could mean
>> fit-nofit of a project into a particular device.
>>
>> -R
>
> I think you need to be very careful when reading benchmarketing (sic)
> numbers like this. Firstly, this is a 32-bit vs 64-bit measurement;
> secondly, the benchmark (spec 2000) is very old now and IIRC was not
> fully optimized for 64-bit processors (it predates the 64-bit version of
> the x86 instruction set); thirdly, there are benchmarks in SPEC which
> are very sensitive to cache size and the 32-bit ABI just happened to
> allow them to fit enough data in the caches to make the numbers leap.
Yes. Sure. I am. I thought I've expressed it clearly, that the
"fantastic 40%" I regard as just "corner case" - those don't usually
reflect ordinary usage.
I was only highlighting the fact, that mare 5-8% improvement can result
on fit-nofit of a particular design into a particular device ... in
consequence requiring to use 4k-RAM device instead of 2k-RAM one.
Tiny improvements of performance of x64 workhorses can become relatively
huge in micros like stm32. That's all.
-R
next prev parent reply other threads:[~2023-07-03 17:35 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-06-27 12:26 Rafał Pietrak
2023-06-28 1:54 ` waffl3x
2023-06-28 7:13 ` Rafał Pietrak
2023-06-28 7:31 ` Jonathan Wakely
2023-06-28 8:35 ` Rafał Pietrak
2023-06-28 9:56 ` waffl3x
2023-06-28 10:43 ` Rafał Pietrak
2023-06-28 12:12 ` waffl3x
2023-06-28 12:23 ` Rafał Pietrak
2023-07-03 14:52 ` David Brown
2023-07-03 16:29 ` Rafał Pietrak
2023-07-04 14:20 ` Rafał Pietrak
2023-07-04 15:13 ` David Brown
2023-07-04 16:15 ` Rafał Pietrak
2023-06-28 7:34 ` waffl3x
2023-06-28 8:41 ` Rafał Pietrak
2023-06-28 13:00 ` Martin Uecker
2023-06-28 14:51 ` Rafał Pietrak
2023-06-28 15:44 ` Richard Earnshaw (lists)
2023-06-28 16:07 ` Martin Uecker
2023-06-28 16:49 ` Richard Earnshaw (lists)
2023-06-28 17:00 ` Martin Uecker
2023-06-28 16:48 ` Rafał Pietrak
2023-06-29 6:19 ` Rafał Pietrak
2023-07-03 15:07 ` Ian Lance Taylor
2023-07-03 16:42 ` Rafał Pietrak
2023-07-03 16:57 ` Richard Earnshaw (lists)
2023-07-03 17:34 ` Rafał Pietrak [this message]
2023-07-04 12:38 ` David Brown
2023-07-04 12:57 ` Oleg Endo
2023-07-04 14:46 ` Rafał Pietrak
2023-07-04 15:55 ` David Brown
2023-07-04 16:20 ` Rafał Pietrak
2023-07-04 22:57 ` Martin Uecker
2023-07-05 5:26 ` Rafał Pietrak
2023-07-05 7:29 ` Martin Uecker
2023-07-05 8:05 ` Rafał Pietrak
2023-07-05 9:11 ` David Brown
2023-07-05 9:25 ` Martin Uecker
2023-07-05 11:34 ` David Brown
2023-07-05 12:01 ` Martin Uecker
2023-07-05 9:42 ` Rafał Pietrak
2023-07-05 11:55 ` David Brown
2023-07-05 12:25 ` Rafał Pietrak
2023-07-05 12:57 ` David Brown
2023-07-05 13:29 ` Rafał Pietrak
2023-07-05 14:45 ` David Brown
2023-07-05 16:13 ` Rafał Pietrak
2023-07-05 17:39 ` David Brown
2023-07-06 7:00 ` Rafał Pietrak
2023-07-06 12:53 ` David Brown
2023-07-05 9:29 ` Martin Uecker
2023-07-05 10:17 ` Rafał Pietrak
2023-07-05 10:48 ` Martin Uecker
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=53154623-01fc-62e6-fe25-9f164b67e6e3@ztk-rp.eu \
--to=embedded@ztk-rp.eu \
--cc=Richard.Earnshaw@arm.com \
--cc=gcc@gcc.gnu.org \
--cc=iant@golang.org \
--cc=muecker@gwdg.de \
/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).