作者 |
CPU缓存技术项目讨论——合作伙伴哪里找? |
|
所跟贴 |
既然这样,特殊的memory access pattern (长尾现象),既然存在,总是可以加以利用吧? 答案是:响亮的 -- SBYY - (824 Byte) 2010-10-17 周日, 11:49 (641 reads) |
SBYY
头衔: 海归中尉 声望: 学员
加入时间: 2010/04/14 文章: 74
海归分: 4606
|
|
作者:SBYY 在 项目找投资与合作 发贴, 来自【海归网】 http://www.haiguinet.com
[推论: 所以我们的优化算法可以改善所有的应用, 可以在Intel的CPU 上统一采用 -- 难道CPU除了用来作web server, 还做别的吗?切!]
(有人怀疑我的CS知识太皮毛 --- 所以我也不敢说不信了。。。跟着喊吧,打倒Wintel! 中国人牛X! 万岁!)
Sorry to spoil your fun! -- but if it's easily spoiled, it probably is not real fun, so keep it up...
[其实,还是研究治癌比较好。。。那玩意儿,懂得人少些]Yeah, I may not understand, so please help me out:
Could you please explain to me,
"theoretical upper limit of cache replacement algorithms" -- is it regarding ALL possible software applications, or only specific applications be tested/optimized for?
I am aware of The theoretically optimal page replacement algorithm
(also known ad Belady's optimal page replacement policy), which is a theoretical concept, that can not be implemented for GENERAL PURPOSE OPERATING SYSTEM,unless the software application to run on it iis either known before hand or has specific memory access patterns.
So how is this "theoretical upper limit of cache replacement algorithms" defined here? -- in regard of software applications being executed on the CPU/OS.
Mind you, optimal solution regarding special type of software applications is still meaningful & maybe useful, but a far cry from the earth-shattering claims being made here.
作者:SBYY 在 项目找投资与合作 发贴, 来自【海归网】 http://www.haiguinet.com
|
|
|
返回顶端 |
|
|
|
|
|
|
您不能在本论坛发表新主题, 不能回复主题, 不能编辑自己的文章, 不能删除自己的文章, 不能发表投票, 您 不可以 发表活动帖子在本论坛, 不能添加附件可以下载文件, |
|
|