[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20200108072641.GR30412@brightrain.aerifal.cx>
Date: Wed, 8 Jan 2020 02:26:41 -0500
From: Rich Felker <dalias@...c.org>
To: musl@...ts.openwall.com
Subject: Re: [PATCH] math: move i386 sqrt to C
On Tue, Jan 07, 2020 at 04:06:05PM +0300, Alexander Monakov wrote:
> ---
> Since union ldshape does not have a dedicated field for 32 least significant
> bits of the x87 long double mantissa, keeping the original approach with
>
> ux.i.m -= (fpsr & 0x200) - 0x100;
>
> would lead to a 64-bit subtraction that is not trivial for the compiler to
> optimize to 32-bit subtraction as done in the original assembly. Therefore
> I have elected to change the approach and use
>
> ux.i.m ^= (fpsr & 0x200) + 0x200;
>
> which is easier to optimize to a 32-bit rather than 64-bit xor.
>
> Thoughts?
I think it looks like a good change. Ideally the compiler would see,
since the branch was taken where the low bits are 0x400, that
subtracting a value less than 0x400 can't borrow from the high 32
bits. But I don't think current compilers do such range/value
analysis, and it doesn't seem like there are anny downsides to your
approach anyway.
Rich
Powered by blists - more mailing lists
Confused about mailing lists and their use?
Read about mailing lists on Wikipedia
and check out these
guidelines on proper formatting of your messages.
