qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Richard Henderson <richard.henderson@linaro.org>
To: "Víctor Colombo" <victor.colombo@eldorado.org.br>,
	qemu-devel@nongnu.org, qemu-ppc@nongnu.org
Cc: danielhb413@gmail.com, matheus.ferst@eldorado.org.br,
	groug@kaod.org, david@gibson.dropbear.id.au, clg@kaod.org
Subject: Re: [PATCH] target/ppc: Change VSX instructions behavior to fill with zeros
Date: Sun, 6 Feb 2022 11:36:21 +1100	[thread overview]
Message-ID: <a5fe4228-fb40-607b-8c07-0ae79e4d0c43@linaro.org> (raw)
In-Reply-To: <20220204181944.65063-1-victor.colombo@eldorado.org.br>

On 2/5/22 05:19, Víctor Colombo wrote:
> ISA v3.1 changed some VSX instructions behavior by changing what the
> other words/doubleword in the result should contain when the result is
> only one word/doubleword. e.g. xsmaxdp operates on doubleword 0 and
> saves the result also in doubleword 0.
> Before, the second doubleword result was undefined according to the
> ISA, but now it's stated that it should be zeroed.
> 
> Even tough the result was undefined before, hardware implementing these
> instructions already filled these fields with 0s. Changing every ISA
> version in QEMU to this behavior makes the results match what happens
> in hardware.
> 
> Signed-off-by: Víctor Colombo<victor.colombo@eldorado.org.br>
> 
> ---
> 
> This patch is a proposal on a previous RFC I sent on this topic [1].
> I preferred this approach because it makes QEMU behavior closer to the
> real hardware.
> 
> The affected instructions have the following note in the ISA:
> 
> """
> Previous versions of the architecture allowed the
> contents of doubleword 1 of the result register to be
> undefined. However, all processors that support
> this instruction write 0s into doubleword 1 of the
> result register, as is required by this version of the
> architecture.
> """
> 
> This patch is not exhaustive as
> 1. some instructions that had its behavior changed are not 'corrected'
>      by this patch (mostly multiply-add instructions);
> 2. some instructions changed the behavior to also replicate the result
>      in the other word from the doubleword if the result is a single
>      word e.g. xscvdpuxws. So, this patch only focus on the 'zeroing'
>      part, not the replication;
> 
> Best regards,
> 
> -- Víctor
> 
> [1]https://lists.gnu.org/archive/html/qemu-ppc/2021-12/msg00198.html
> ---
>   target/ppc/fpu_helper.c             | 26 +++++++++++++-------------
>   target/ppc/translate/vsx-impl.c.inc |  4 +++-
>   2 files changed, 16 insertions(+), 14 deletions(-)

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>

r~


  reply	other threads:[~2022-02-06  0:38 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-02-04 18:19 [PATCH] target/ppc: Change VSX instructions behavior to fill with zeros Víctor Colombo
2022-02-06  0:36 ` Richard Henderson [this message]
2022-02-09  7:45 ` Cédric Le Goater

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=a5fe4228-fb40-607b-8c07-0ae79e4d0c43@linaro.org \
    --to=richard.henderson@linaro.org \
    --cc=clg@kaod.org \
    --cc=danielhb413@gmail.com \
    --cc=david@gibson.dropbear.id.au \
    --cc=groug@kaod.org \
    --cc=matheus.ferst@eldorado.org.br \
    --cc=qemu-devel@nongnu.org \
    --cc=qemu-ppc@nongnu.org \
    --cc=victor.colombo@eldorado.org.br \
    /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).