C++博客-HoneyCat的月光浴场-最新评论http://www.cppblog.com/HoneyCat/CommentsRSS.aspx我在很多世界的交叉点zh-cnTue, 11 May 2010 00:18:00 GMTTue, 11 May 2010 00:18:00 GMTcnblogsre: 游戏内存管理——初探（上）http://www.cppblog.com/HoneyCat/archive/2010/05/11/115017.html#115119矩阵操作矩阵操作Tue, 11 May 2010 09:01:00 GMThttp://www.cppblog.com/HoneyCat/archive/2010/05/11/115017.html#115119

矩阵操作 2010-05-11 17:01 发表评论
]]>re: 游戏内存管理——初探（上）http://www.cppblog.com/HoneyCat/archive/2010/05/11/115017.html#115064小时候可靓了小时候可靓了Tue, 11 May 2010 00:18:00 GMThttp://www.cppblog.com/HoneyCat/archive/2010/05/11/115017.html#115064看了下你发的这个介绍，貌似很高深。 主要是针对多核结构，都采用多线程和安全检测了。。我QQ是247869291，可以发到我QQ邮箱，谢谢哦！

小时候可靓了 2010-05-11 08:18 发表评论
]]>re: 游戏内存管理——初探（上）http://www.cppblog.com/HoneyCat/archive/2010/05/11/115017.html#115058chaoguchaoguMon, 10 May 2010 16:45:00 GMThttp://www.cppblog.com/HoneyCat/archive/2010/05/11/115017.html#115058我这还有一篇关于内存分配的文章，对你可能有帮助，如果需要发个邮件给我。
title：MMT: Exploiting Fine-Grained Parallelism in Dynamic Memory Management
Abstract—Dynamic memory management is one of the most
expensive but ubiquitous operations in many C/C++ applications.
Additional features such as security checks, while desirable,
further worsen memory management overheads. With
advent of multicore architecture, it is important to investigate
how dynamic memory management overheads for sequential
applications can be reduced.
In this paper, we propose a new approach for accelerating
dynamic memory management on multicore architecture, by
offloading dynamic management functions to a separate thread
that we refer to as memory management thread (MMT).
We show that an efficient MMT design can give significant
performance improvement by extracting parallelism while being
agnostic to the underlying memory management library
algorithms and data structures. We also show how parallelism
provided by MMT can be beneficial for high overhead memory
management tasks, for example, security checks related to
memory management.
We evaluate MMT on heap allocation-intensive benchmarks
running on an Intel core 2 quad platform for two widelyused
memory allocators: Doug Lea’s and PHKmalloc allocators.
On average, MMT achieves a speedup ratio of 1.19×
for both allocators, while both the application and memory
management libraries are unmodified and are oblivious to the
parallelization scheme. For PHKmalloc with security checks
turned on, MMT reduces the security check overheads from
21% to only 1% on average.


chaogu 2010-05-11 00:45 发表评论
]]>re: 游戏内存管理——初探（上）http://www.cppblog.com/HoneyCat/archive/2010/05/11/115017.html#115055小时候可靓了小时候可靓了Mon, 10 May 2010 16:08:00 GMThttp://www.cppblog.com/HoneyCat/archive/2010/05/11/115017.html#115055new delete是很好用的。但是如果需要频繁使用的时候，会造成内存粹片。当下一次再要分配的时候，如果系统发现找不到足够大的空间来分配。就会进行内存整理。调整内存页面数据。 这个整理数据的过程是很消耗时间的。（相对程序执行时间来说）。 而通过预分配并重载new delete。可以在一定程序上避免重复new delete时产生的额外开销。

这就是传说中的内存振荡和内存碎片。。。
上面的内存管理，是现在普遍采用的方法中的其中一种，并非新鲜事。 如果你觉得大家不用new delete是无聊。那你可以写篇贴子来喷。 但是如果你是在自己没有完全理解的情况下说这样的话，那我会很有意见。 有些东西，不能靠自己猜，特别是C/C++。

我不知道你是不是想要这个答案。或许，你指的是别样！！！

小时候可靓了 2010-05-11 00:08 发表评论
]]>re: 游戏内存管理——初探（上）http://www.cppblog.com/HoneyCat/archive/2010/05/10/115017.html#115040chaoguchaoguMon, 10 May 2010 14:11:00 GMThttp://www.cppblog.com/HoneyCat/archive/2010/05/10/115017.html#115040

chaogu 2010-05-10 22:11 发表评论
]]>re: 游戏内存管理——初探（上）http://www.cppblog.com/HoneyCat/archive/2010/05/10/115017.html#115019小时候可靓了小时候可靓了Mon, 10 May 2010 10:58:00 GMThttp://www.cppblog.com/HoneyCat/archive/2010/05/10/115017.html#115019

小时候可靓了 2010-05-10 18:58 发表评论
]]>