[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <ZLVQ0NCC8SI5F8xR@smile.fi.intel.com>
Date: Mon, 17 Jul 2023 17:31:44 +0300
From: Andy Shevchenko <andriy.shevchenko@...ux.intel.com>
To: catalin.marinas@....com, will@...nel.org, pcc@...gle.com,
andreyknvl@...il.com, linux@...musvillemoes.dk,
yury.norov@...il.com, linux-kernel@...r.kernel.org,
linux-arm-kernel@...ts.infradead.org, eugenis@...gle.com,
syednwaris@...il.com, william.gray@...aro.org,
Arnd Bergmann <arnd@...db.de>
Subject: Re: [PATCH v3 1/5] lib/bitmap: add bitmap_{set,get}_value()
On Mon, Jul 17, 2023 at 05:29:12PM +0300, Andy Shevchenko wrote:
> On Mon, Jul 17, 2023 at 04:14:57PM +0200, Alexander Potapenko wrote:
...
> > > > + map[index] &= ~(GENMASK(nbits + offset - 1, offset));
> > >
> > > I remember that this construction may bring horrible code on some architectures
> > > with some version(s) of the compiler (*).
> >
> > Wow, even the trunk Clang and GCC seem to generate better code for
> > your version of this line: https://godbolt.org/z/36Kqxhe6j
>
> Wow, indeed! Perhaps time to report to clang and GCC people. I believe the root
> cause is that in the original version compiler can't prove that l is constant
> for GENMASK().
>
> > > To fix that I found an easy refactoring:
> > >
> > > map[index] &= ~(GENMASK(nbits, 0) << offset));
nbits - 1 it should be, btw. In any case it seems the code is still better.
> > I'll take this one.
> >
> > > (*) don't remember the actual versions, though, but anyway...
--
With Best Regards,
Andy Shevchenko
Powered by blists - more mailing lists