[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAFyWVaaAg9TuNVPbNmP0ongf6y2hmqFMiXJZHo8K84O4-BV0yw@mail.gmail.com>
Date: Fri, 25 Jan 2019 17:33:50 -0800
From: Jim Wilson <jimw@...ive.com>
To: Palmer Dabbelt <palmer@...ive.com>
Cc: bjorn.topel@...il.com, Christoph Hellwig <hch@...radead.org>,
linux-riscv@...ts.infradead.org, David Lee <davidlee@...ive.com>,
daniel@...earbox.net, netdev@...r.kernel.org
Subject: Re: [RFC PATCH 1/3] riscv: set HAVE_EFFICIENT_UNALIGNED_ACCESS
On Fri, Jan 25, 2019 at 12:21 PM Palmer Dabbelt <palmer@...ive.com> wrote:
> Jim, would you be opposed to something like this?
This looks OK to me.
> + builtin_define_with_int_value ("__riscv_tune_misaligned_load_cost",
> + riscv_tune_info->slow_unaligned_access ? 1024 : 1);
> + builtin_define_with_int_value ("__riscv_tune_misaligned_store_cost",
> + riscv_tune_info->slow_unaligned_access ? 1024 : 1);
It would be nice to have a better way to compute these values, maybe
an extra field in the tune structure, but we can always worry about
that later when we need it.
Jim
Powered by blists - more mailing lists