Re: [PATCH RFC] [X86] performance improvement for memcpy_64.S by fast string.

From: Ingo Molnar <mingo@elte.hu>
To: Pavel Machek <pavel@ucw.cz>
Cc: "H. Peter Anvin" <hpa@zytor.com>, "Ma, Ling" <ling.ma@intel.com>,
	Ingo Molnar <mingo@redhat.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	linux-kernel <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH RFC] [X86] performance improvement for memcpy_64.S by fast string.
Date: Fri, 13 Nov 2009 08:33:40 +0100	[thread overview]
Message-ID: <20091113073340.GA26127@elte.hu> (raw)
In-Reply-To: <20091112121619.GD1394@ucw.cz>

* Pavel Machek <pavel@ucw.cz> wrote:

> > Ling, if you are interested, could you send a user-space test-app to 
> > this thread that everyone could just compile and run on various older 
> > boxes, to gather a performance profile of hand-coded versus string ops 
> > performance?
> > 
> > ( And i think we can make a judgement based on cache-hot performance
> >   alone - if then the strings ops will perform comparatively better in
> >   cache-cold scenarios, so the cache-hot numbers would be a conservative
> >   estimate. )
> 
> Ugh, really? I'd expect cache-cold performance to be not helped at all 
> (memory bandwidth limit) and you'll get slow down from additional 
> i-cache misses...

That's my point - the new code is shorter, which will run comparatively 
faster in a cache-cold environment.

	Ingo