[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <ZL44FFAkG8pKS1lv@smile.fi.intel.com>
Date: Mon, 24 Jul 2023 11:36:36 +0300
From: Andy Shevchenko <andriy.shevchenko@...ux.intel.com>
To: Yury Norov <yury.norov@...il.com>
Cc: Alexander Potapenko <glider@...gle.com>, catalin.marinas@....com,
will@...nel.org, pcc@...gle.com, andreyknvl@...il.com,
linux@...musvillemoes.dk, 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 v4 1/5] lib/bitmap: add bitmap_{set,get}_value()
On Sat, Jul 22, 2023 at 06:57:23PM -0700, Yury Norov wrote:
> On Thu, Jul 20, 2023 at 07:39:52PM +0200, Alexander Potapenko wrote:
> > + map[index] &= ~(GENMASK(nbits - 1, 0) << offset);
>
> 'GENMASK(nbits - 1, 0) << offset' looks really silly.
But you followed the thread to get a clue why it's written in this form, right?
...
> With all that I think the implementation should look something like
> this:
I would go this way if and only if the code generation on main architectures
with both GCC and clang is better.
And maybe even some performance tests need to be provided.
...
> Alexander, can you please try the above and compare?
> In previous iteration, I asked you to share disassembly listings for the
> functions. Can you please do that now?
Exactly what we need before going with your suggestion(s).
--
With Best Regards,
Andy Shevchenko
Powered by blists - more mailing lists