From: "Martin Storsjö" <martin@martin.st>
Subject: Re: [PATCH] msvcrt: Avoid disallowed unaligned writes in memset on ARM
Message-Id: <f55eb0f4-2c97-7775-1e96-951870d09f67@martin.st>
Date: Fri, 17 Sep 2021 23:19:51 +0300 (EEST)
In-Reply-To: <e630f42-e3fd-55e8-24f-8c84526d8fa5@martin.st>
References: <20210915202745.3661089-1-martin@martin.st> <00876200-ab90-e23e-86e5-df022b6b0199@gmail.com> <e51bb39-534-27ba-a45f-43e1b535c61@martin.st> <e630f42-e3fd-55e8-24f-8c84526d8fa5@martin.st>

On Thu, 16 Sep 2021, Martin Storsjö wrote:

> On Thu, 16 Sep 2021, Martin Storsjö wrote:
>
>> Clang doesn't seem to know/exploit that the regular 32 bit store 
>> instructions work unaligned though, so the smaller stores get exploded into 
>> a long series of single byte writes. But I guess that's just a missed 
>> optimization opportunity in Clang, I'll see if I can report it.
>
> FWIW this seems to be a target specific issue; Clang does optimize it 
> correctly for an armv7-linux-gnueabihf target, but not for armv7-windows. 
> I'll see about getting that fixed.

For the record, this should have been fixed in Clang now: 
https://reviews.llvm.org/D109960

// Martin