From: Simon Marchi <simon.marchi@polymtl.ca>
To: Walfred Tedeschi <walfred.tedeschi@intel.com>
Cc: palves@redhat.com, qiyaoltc@gmail.com, gdb-patches@sourceware.org
Subject: Re: [PATCH] gdb - avx512: tests were failing due to missing memory aligment.
Date: Sat, 16 Sep 2017 13:57:00 -0000 [thread overview]
Message-ID: <c7398a57a1b719dc40588475e839dd3a@polymtl.ca> (raw)
In-Reply-To: <1504687613-14649-2-git-send-email-walfred.tedeschi@intel.com>
On 2017-09-06 10:46, Walfred Tedeschi wrote:
> Test was running on a fault during code execution. Analysis have shown
> that the wrong instruction had been used. An instruction that takes
> not alligned memory is more appropriated for the task.
LGTM, you guys are the experts about that :)
> ChangeLog:
>
> 2017-06-26 Walfred Tedeschi <walfred.tedeschi@intel.com>
>
> gdb/ChangeLog:
> * testsuite/gdb.arch/i386-avx512.c (move_zmm_data_to_reg): Use
> vmovups instead vmovaps.
> (move_zmm_data_to_memory): Use vmovups instead vmovaps.
>
> ---
> gdb/testsuite/gdb.arch/i386-avx512.c | 128
> +++++++++++++++++------------------
> 1 file changed, 64 insertions(+), 64 deletions(-)
>
> diff --git a/gdb/testsuite/gdb.arch/i386-avx512.c
> b/gdb/testsuite/gdb.arch/i386-avx512.c
> index 52c0ead..3e955a4 100644
> --- a/gdb/testsuite/gdb.arch/i386-avx512.c
> +++ b/gdb/testsuite/gdb.arch/i386-avx512.c
> @@ -127,44 +127,44 @@ move_k_data_to_memory (void)
> void
> move_zmm_data_to_reg (void)
> {
> - asm ("vmovaps 0(%0), %%zmm0\n\t"
> - "vmovaps 64(%0), %%zmm1\n\t"
> - "vmovaps 128(%0), %%zmm2\n\t"
> - "vmovaps 192(%0), %%zmm3\n\t"
> - "vmovaps 256(%0), %%zmm4\n\t"
> - "vmovaps 320(%0), %%zmm5\n\t"
> - "vmovaps 384(%0), %%zmm6\n\t"
> - "vmovaps 448(%0), %%zmm7\n\t"
> + asm ("vmovups 0(%0), %%zmm0 \n\t"
> + "vmovups 64(%0), %%zmm1 \n\t"
> + "vmovups 128(%0), %%zmm2 \n\t"
> + "vmovups 192(%0), %%zmm3 \n\t"
> + "vmovups 256(%0), %%zmm4 \n\t"
> + "vmovups 320(%0), %%zmm5 \n\t"
> + "vmovups 384(%0), %%zmm6 \n\t"
> + "vmovups 448(%0), %%zmm7 \n\t"
Any reason for the added trailing space?
Thanks,
Simon
next prev parent reply other threads:[~2017-09-16 13:57 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-09-06 8:47 [PATCH] icc: allow code path for newer versions of icc Walfred Tedeschi
2017-09-06 8:47 ` [PATCH] symlookup: improves symbol lookup when a file is specified Walfred Tedeschi
2017-09-20 15:22 ` [ping][PATCH] " Tedeschi, Walfred
2017-10-09 7:35 ` Tedeschi, Walfred
2017-10-09 12:42 ` [PATCH] " Pedro Alves
2017-10-09 14:06 ` Tedeschi, Walfred
2017-09-06 8:47 ` [PATCH] gdb - avx512: tests were failing due to missing memory aligment Walfred Tedeschi
2017-09-16 13:57 ` Simon Marchi [this message]
2017-09-17 20:22 ` Yao Qi
2017-09-18 14:18 ` Tedeschi, Walfred
2017-09-20 13:39 ` [pushed] " Tedeschi, Walfred
2017-09-16 13:49 ` [PATCH] icc: allow code path for newer versions of icc Simon Marchi
2017-09-18 14:17 ` Tedeschi, Walfred
2017-09-18 15:34 ` Pedro Alves
2017-09-18 16:24 ` Simon Marchi
2017-09-18 16:34 ` Tedeschi, Walfred
2017-09-18 19:13 ` Simon Marchi
2017-09-20 15:19 ` Tedeschi, Walfred
2017-09-20 15:45 ` Pedro Alves
2017-09-20 15:55 ` Tedeschi, Walfred
2017-09-21 11:27 ` Tedeschi, Walfred
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=c7398a57a1b719dc40588475e839dd3a@polymtl.ca \
--to=simon.marchi@polymtl.ca \
--cc=gdb-patches@sourceware.org \
--cc=palves@redhat.com \
--cc=qiyaoltc@gmail.com \
--cc=walfred.tedeschi@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