This is the mail archive of the libstdc++@gcc.gnu.org mailing list for the libstdc++ project.

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]
Other format:	[Raw text]

Re: [Patch] Nathan's improvements to basic_string

From: Paolo Carlini <pcarlini at unitus dot it>
To: Nathan Myers <ncm-nospam at cantrip dot org>
Cc: libstdc++ at gcc dot gnu dot org
Date: Wed, 18 Jun 2003 22:35:46 +0200
Subject: Re: [Patch] Nathan's improvements to basic_string
References: <3EE8CDF1.6070103@unitus.it> <20030612201400.GY8942@tofu.dreamhost.com> <20030613215934.GC8942@tofu.dreamhost.com> <20030617184319.GJ8942@tofu.dreamhost.com> <20030618203308.GS8942@tofu.dreamhost.com>

Nathan Myers wrote:

Apologies for replying to my own post again; I have more numbers.

And what numbers!

A lock/add seems to cost 11.6 ns, or [16] cycles, on this hardware when there is no contention.

I tried it with two threads on a dual Opteron. With the patch the runtime was exactly the same as with one thread. Without, it was from 20 to 50 times slower, and 4 to 10 times slower than with one thread.

Astonishing, Nathan!

Thanks again for your contribution.
Paolo.

References:
- [Patch] Nathan's improvements to basic_string
  - From: Paolo Carlini
- Re: [Patch] Nathan's improvements to basic_string
  - From: Nathan Myers
- Re: [Patch] Nathan's improvements to basic_string
  - From: Nathan Myers
- Re: [Patch] Nathan's improvements to basic_string
  - From: Nathan Myers
- Re: [Patch] Nathan's improvements to basic_string
  - From: Nathan Myers

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]