From: Igor Munkin via Tarantool-patches <tarantool-patches@dev.tarantool.org>
To: Sergey Kaplun <skaplun@tarantool.org>
Cc: tarantool-patches@dev.tarantool.org
Subject: Re: [Tarantool-patches] [PATCH luajit] IR_MIN/IR_MAX is non-commutative due to underlying FPU ops.
Date: Thu, 23 Nov 2023 06:30:49 +0000 [thread overview]
Message-ID: <ZV7xmbvRJCjMniqr@tarantool.org> (raw)
In-Reply-To: <20231024101420.12398-1-skaplun@tarantool.org>
Sergey,
I've checked the patchset into all long-term branches in
tarantool/luajit and bumped a new version in master, release/2.11 and
release/2.10.
On 24.10.23, Sergey Kaplun via Tarantool-patches wrote:
> From: Mike Pall <mike>
>
> Thanks to Peter Cawley.
>
> (cherry-picked from commit 7a2b83a0c5d980bf3db0aeda33c79e7bb4b3da01)
>
> Even after the commit c05d103305da0626e025dbf81370ca9f4f788c83 ("Fix
> math.min()/math.max() inconsistencies."), some of the corner cases (see
> tests in the commit for details) for `math.min()`/`math.max()` still
> inconsistent in the JIT and the VM. This happens because `IR_MIN` and
> `IR_MAX` are marked as commutative, so their operands were swapped by
> `asm_swapops()`. As a result, because `minsd`[1]/`maxsd`[2] instructions
> don't change the sign byte of the destination register, its sign is
> preserved if we compare 0 with -0. When we compare something with NaN,
> the second source operand (either a NaN or a valid floating-point value)
> is written to the result. Hence, swapping the operands changed the
> resulting value.
>
> This patch removes the commutative flag from the aforementioned IRs to
> prevent swapping of their operands.
>
> [1]: https://c9x.me/x86/html/file_module_x86_id_173.html
> [2]: https://c9x.me/x86/html/file_module_x86_id_168.html
>
> Sergey Kaplun:
> * added the description and the test for the problem
>
> Part of tarantool/tarantool#9145
> ---
>
> Branch: https://github.com/tarantool/luajit/tree/skaplun/lj-1082-min-max-0-commutative
> Tarantool PR: https://github.com/tarantool/tarantool/pull/9294
> Related Issues:
> * https://github.com/tarantool/tarantool/issues/9145
> * https://github.com/LuaJIT/LuaJIT/issues/1082
> * https://github.com/LuaJIT/LuaJIT/issues/957
>
> src/lj_ir.h | 4 +-
> test/tarantool-tests/gh-6163-min-max.test.lua | 23 ++++-------
> .../lj-1082-min-max-0-commutative.test.lua | 41 +++++++++++++++++++
> 3 files changed, 51 insertions(+), 17 deletions(-)
> create mode 100644 test/tarantool-tests/lj-1082-min-max-0-commutative.test.lua
>
<snipped>
> --
> 2.42.0
>
--
Best regards,
IM
prev parent reply other threads:[~2023-11-23 6:36 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-10-24 10:14 Sergey Kaplun via Tarantool-patches
2023-10-24 11:35 ` Maxim Kokryashkin via Tarantool-patches
2023-11-10 11:18 ` Sergey Bronnikov via Tarantool-patches
2023-11-23 6:30 ` Igor Munkin via Tarantool-patches [this message]
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=ZV7xmbvRJCjMniqr@tarantool.org \
--to=tarantool-patches@dev.tarantool.org \
--cc=imun@tarantool.org \
--cc=skaplun@tarantool.org \
--subject='Re: [Tarantool-patches] [PATCH luajit] IR_MIN/IR_MAX is non-commutative due to underlying FPU ops.' \
/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
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox