From: Ilya Leoshkevich <iii@linux.ibm.com>
To: Segher Boessenkool <segher@kernel.crashing.org>
Cc: GCC Patches <gcc-patches@gcc.gnu.org>,
richard.guenther@gmail.com, richard.sandiford@arm.com,
joseph@codesourcery.com, krebbel@linux.ibm.com,
rdapp@linux.ibm.com
Subject: Re: [PATCH v3 4/9] S/390: Do not use signaling vector comparisons on z13
Date: Mon, 30 Sep 2019 13:36:00 -0000 [thread overview]
Message-ID: <8854D94C-1B4E-406B-AFB2-23FC79658EEB@linux.ibm.com> (raw)
In-Reply-To: <20190906103423.GW9749@gate.crashing.org>
> Am 06.09.2019 um 12:34 schrieb Segher Boessenkool <segher@kernel.crashing.org>:
>
> Hi Ilya,
>
> On Thu, Sep 05, 2019 at 01:10:14PM +0200, Ilya Leoshkevich wrote:
>> z13 supports only non-signaling vector comparisons. This means we
>> cannot vectorize LT, LE, GT, GE and LTGT when compiling for z13. Notify
>> middle-end about this using more restrictive operator predicate in
>> vcond<V_HW:mode><V_HW2:mode>.
>
>> +(define_predicate "vcond_comparison_operator"
>> + (match_operand 0 "comparison_operator")
>> +{
>> + if (!HONOR_NANS (GET_MODE (XEXP (op, 0)))
>> + && !HONOR_NANS (GET_MODE (XEXP (op, 1))))
>> + return true;
>> + switch (GET_CODE (op))
>> + {
>> + case LE:
>> + case LT:
>> + case GE:
>> + case GT:
>> + case LTGT:
>> + /* Signaling vector comparisons are supported only on z14+. */
>> + return TARGET_Z14;
>> + default:
>> + return true;
>> + }
>> +})
>
> Should you handle -fsignaling-nans here as well?
Do you mean disabling vectorisation of LE/LT/GE/GT/LTGT when
-fsignaling-nans is in effect? This makes sense to me. I could do that
here, but wouldn't common code (e.g. expand_vec_cond_expr_p) be a better
place?
next prev parent reply other threads:[~2019-09-30 13:36 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-09-05 11:10 [PATCH v3 0/9] S/390: Use signaling FP comparison instructions Ilya Leoshkevich
2019-09-05 11:10 ` [PATCH v3 1/9] Allow COND_EXPR and VEC_COND_EXPR condtions to trap Ilya Leoshkevich
2019-09-06 11:07 ` Richard Biener
2019-09-06 15:45 ` Ilya Leoshkevich
2019-09-09 8:43 ` Richard Biener
2019-09-05 11:11 ` [PATCH v3 3/9] Introduce can_vector_compare_p function Ilya Leoshkevich
2019-09-06 12:58 ` Richard Sandiford
2019-09-05 11:11 ` [PATCH v3 2/9] Introduce rtx_alloca, alloca_raw_REG and alloca_rtx_fmt_* Ilya Leoshkevich
2019-09-06 11:09 ` Richard Biener
2019-09-06 12:40 ` Richard Sandiford
2019-09-30 15:00 ` Ilya Leoshkevich
2019-09-05 11:11 ` [PATCH v3 4/9] S/390: Do not use signaling vector comparisons on z13 Ilya Leoshkevich
2019-09-06 10:34 ` Segher Boessenkool
2019-09-30 13:36 ` Ilya Leoshkevich [this message]
2019-10-01 0:24 ` Segher Boessenkool
2019-09-05 11:11 ` [PATCH v3 6/9] S/390: Remove code duplication in vec_unordered<mode> Ilya Leoshkevich
2019-09-30 14:41 ` Andreas Krebbel
2019-09-05 11:11 ` [PATCH v3 5/9] S/390: Implement vcond expander for V1TI,V1TF Ilya Leoshkevich
2019-09-30 14:51 ` Andreas Krebbel
2019-09-05 11:12 ` [PATCH v3 7/9] S/390: Remove code duplication in vec_* comparison expanders Ilya Leoshkevich
2019-09-30 14:50 ` Andreas Krebbel
2019-09-05 11:12 ` [PATCH v3 9/9] S/390: Test signaling FP comparison instructions Ilya Leoshkevich
2019-09-05 11:12 ` [PATCH v3 8/9] S/390: Use " Ilya Leoshkevich
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=8854D94C-1B4E-406B-AFB2-23FC79658EEB@linux.ibm.com \
--to=iii@linux.ibm.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=joseph@codesourcery.com \
--cc=krebbel@linux.ibm.com \
--cc=rdapp@linux.ibm.com \
--cc=richard.guenther@gmail.com \
--cc=richard.sandiford@arm.com \
--cc=segher@kernel.crashing.org \
/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).