[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <163425869104.1688384.2477307279117424281@swboyd.mtv.corp.google.com>
Date: Thu, 14 Oct 2021 17:44:51 -0700
From: Stephen Boyd <sboyd@...nel.org>
To: Mark-PK Tsai <mark-pk.tsai@...iatek.com>, mturquette@...libre.com
Cc: mark-pk.tsai@...iatek.com, yj.chiang@...iatek.com,
matthias.bgg@...il.com, linux-clk@...r.kernel.org,
linux-kernel@...r.kernel.org, linux-arm-kernel@...ts.infradead.org,
linux-mediatek@...ts.infradead.org
Subject: Re: [PATCH] clk: make clk_core_lookup faster by using clk name hash
Quoting Mark-PK Tsai (2021-10-04 23:59:49)
> Compare hash value before strcmp the full name to make
> clk_core_lookup faster.
>
> It make clk driver probe 30 percent faster on the platform
> have 1483 registered clks and average clock name length 20.
Why is clk_core_lookup() a fast path for you?
Powered by blists - more mailing lists