From: Vineet Gupta <vineetg@rivosinc.com>
To: Andrew Waterman <andrew@sifive.com>, Sergei Lewis <slewis@rivosinc.com>
Cc: libc-alpha@sourceware.org
Subject: Re: [PATCH 2/2] riscv: vectorised mem* and str* functions
Date: Thu, 2 Feb 2023 16:13:15 -0800 [thread overview]
Message-ID: <b25ff49a-166f-876a-5533-4ee3f4c515a6@rivosinc.com> (raw)
In-Reply-To: <CA++6G0DbRQ=RFNPAW94-L6ynTHxECUb6sxaXUMwq-pP_8NfbUQ@mail.gmail.com>
On 2/1/23 11:03, Andrew Waterman wrote:
>> +#ifndef __riscv_strict_align
> strict-align is not the right thing to check here. As the RVA profile
> document explains, all RVA-compliant implementations must support
> misaligned loads and stores (so strict-align will be false), but they
> might execute extremely slowly (e.g., via trap and emulate), and so
> this approach will unduly penalize some implementations.
FWIW, the proposed __riscv_strict_align if generated can have 2 possible
values:
- 1 (explicit -mstrict-align used in build)
- 2 cpu tune param indicated unaligned access is slow (like with
trap-n-emulate)
So if theory code can still be written to cater to that.
-Vineet
next prev parent reply other threads:[~2023-02-03 0:13 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-02-01 9:52 [PATCH 1/2] riscv: sysdeps support for vectorised functions Sergei Lewis
2023-02-01 9:52 ` [PATCH 2/2] riscv: vectorised mem* and str* functions Sergei Lewis
2023-02-01 15:33 ` Jeff Law
2023-02-01 16:42 ` Florian Weimer
2023-02-01 17:07 ` Jeff Law
2023-02-02 9:34 ` Sergei Lewis
2023-02-06 12:49 ` Sergei Lewis
2023-02-01 17:17 ` Adhemerval Zanella Netto
2023-02-01 17:38 ` Adhemerval Zanella Netto
2023-02-01 18:13 ` Noah Goldstein
2023-02-02 10:02 ` Sergei Lewis
2023-02-02 14:26 ` Adhemerval Zanella Netto
2023-02-02 15:20 ` Sergei Lewis
2023-02-02 15:35 ` Sergei Lewis
2023-02-03 11:35 ` Adhemerval Zanella Netto
2023-02-03 14:04 ` Sergei Lewis
2023-02-01 18:11 ` Noah Goldstein
2023-02-01 18:13 ` Andrew Waterman
2023-02-01 19:03 ` Andrew Waterman
2023-02-03 0:13 ` Vineet Gupta [this message]
2023-02-03 0:51 ` Andrew Waterman
2023-05-03 2:11 ` Yun Hsiang
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=b25ff49a-166f-876a-5533-4ee3f4c515a6@rivosinc.com \
--to=vineetg@rivosinc.com \
--cc=andrew@sifive.com \
--cc=libc-alpha@sourceware.org \
--cc=slewis@rivosinc.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).