blocks|key|1174382|text|我在ARMv7上做了一些基准测试，参见https://github.com/reinhrst/ARMBarriers的报告，我在EuroLLVM演讲的幻灯片，以及我使用的seqlock代码。|type|unstyled|depth|inlineStyleRanges|entityRanges|offset|length|data|1174383|小故事:在seqlock代码中，获取/释放函数比顺序一致的版本快大约40%25。|1174384|📷|atomic|1174385|​|1174386|entityMap|0|LINK|mutability|MUTABLE|url|https://github.com/reinhrst/ARMBarriers|1|IMAGE|IMMUTABLE|imageUrl|https://ask.qcloudimg.com/http-save/yehe-900000/53103093d4985fcb3972bcf78b1fa530.png|imageAlt^0|J|13|0|0|0|0|1|1|0|0^^$0|@$1|2|3|4|5|6|7|Y|8|@]|9|@$A|Z|B|10|1|11]]|C|$]]|$1|D|3|E|5|6|7|12|8|@]|9|@]|C|$]]|$1|F|3|G|5|H|7|13|8|@]|9|@$A|14|B|15|1|16]]|C|$]]|$1|I|3|J|5|6|7|17|8|@]|9|@]|C|$]]|$1|K|3|-4|5|6|7|18|8|@]|9|@]|C|$]]]|L|$M|$5|N|O|P|C|$Q|R]]|S|$5|T|O|U|C|$V|W|X|-4]]]]

I did a bit of benchmarking on ARMv7, see <a href="https://github.com/reinhrst/ARMBarriers" rel="nofollow noreferrer">https://github.com/reinhrst/ARMBarriers</a> for the report, the slides for my talk at EuroLLVM, and the seqlock code I used.

Short story: in the seqlock code, the Acquire/Release function was about 40% faster than the sequentially consistent version.
<img src="https://i.stack.imgur.com/sTUJt.png" alt="enter image description here">

blocks|key|1174340|text|这可能不是最好的解决方案，但到目前为止，我一直在我的一个项目中使用CDSChecker进行一些基准测试。我还没有在完整的程序中使用它，但更多的只是在独立的单元上使用。|type|unstyled|depth|inlineStyleRanges|entityRanges|offset|length|data|1174341|entityMap|0|LINK|mutability|MUTABLE|url|http://demsky.eecs.uci.edu/cdschecker/README.html^0|X|A|0|0^^$0|@$1|2|3|4|5|6|7|L|8|@]|9|@$A|M|B|N|1|O]]|C|$]]|$1|D|3|-4|5|6|7|P|8|@]|9|@]|C|$]]]|E|$F|$5|G|H|I|C|$J|K]]]]

This might not be the best solution but so far I have been using <a href="http://demsky.eecs.uci.edu/cdschecker/README.html" rel="nofollow">CDSChecker</a> for some bench-marking in one of my projects. I have not yet used it on complete programs but more just on independent units.

blocks|key|1189342|text|对于特定的代码块(工作窃取出队)，我发现了一个非常好的paper，它对使用弱原子的C11版本进行了基准测试，仅使用sc原子，手工优化的汇编，以及使用完全放松的原子的不正确版本。(巧合的是，前面提到的CDSChecker后来在C11版本中发现了一个错误。)类似的例子也很受欢迎。|type|unstyled|depth|inlineStyleRanges|entityRanges|offset|length|data|1189343|entityMap|0|LINK|mutability|MUTABLE|url|http://www.di.ens.fr/~zappa/readings/ppopp13.pdf^0|R|5|0|0^^$0|@$1|2|3|4|5|6|7|L|8|@]|9|@$A|M|B|N|1|O]]|C|$]]|$1|D|3|-4|5|6|7|P|8|@]|9|@]|C|$]]]|E|$F|$5|G|H|I|C|$J|K]]]]

For a particular chunk of code (a work-stealing dequeue), I found a very nice 
<a href="http://www.di.ens.fr/~zappa/readings/ppopp13.pdf" rel="nofollow">paper</a> that benchmarks a C11 version with weak atomics, with sc-atomics only, hand-optimized assembly, and an incorrect version using fully relaxed atomics. (By coincidence, a bug was later found in the C11 version by the aforementioned CDSChecker.) Similar examples are welcome.

blocks|key|1189345|text|这个问题本身没有意义，理解其中的原因很重要。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1189346|原子操作只是对标量对象的简单操作，除了它可以用于线程间通信之外；排序只影响保证用于其他内存位置的内容。|1189347|注意:标准文本没有正式地保证这一点，但它的目的是保证这一点，而一致的C/C%2B%2B线程语义方法必须基于这一点。|1189348|您可以比较乘法和余弦的速度，但不能比较输出"hello+world“和刷新cout的成本。流或文件的刷新没有固有的价格标签:它与其他操作相关。|offset|length|style|CODE|1189349|你不能比较阻塞的操作的速度，直到之前的某个操作完成，而另一个没有完成。|1189350|此外，您不能在真空中进行基准测试。你需要一些工作负载，一种操作模式。|1189351|你需要学习很多关于现代CPU设计的知识，我所说的现代指的是过去20年里发明的任何东西。你必须至少对真实CPU的复杂性和它运行代码的方式、多核如何操作以及内存缓存的一般原则有一些了解，才能梦想设计一个有用的抽象基准测试。|1189352|或者，您可以编写您的程序，并对其进行分析，以查看原子操作是否真的存在问题。|1189353|entityMap^0|0|0|0|11|4|0|0|0|0|0^^$0|@$1|2|3|4|5|6|7|V|8|@]|9|@]|A|$]]|$1|B|3|C|5|6|7|W|8|@]|9|@]|A|$]]|$1|D|3|E|5|6|7|X|8|@]|9|@]|A|$]]|$1|F|3|G|5|6|7|Y|8|@$H|Z|I|10|J|K]]|9|@]|A|$]]|$1|L|3|M|5|6|7|11|8|@]|9|@]|A|$]]|$1|N|3|O|5|6|7|12|8|@]|9|@]|A|$]]|$1|P|3|Q|5|6|7|13|8|@]|9|@]|A|$]]|$1|R|3|S|5|6|7|14|8|@]|9|@]|A|$]]|$1|T|3|-4|5|6|7|15|8|@]|9|@]|A|$]]]|U|$]]

The question as such doesn't make sense, and it's important to understand why.

An atomic operation is just a simple operation on a scalar object except that it can be used for inter thread communication; the ordering only affects what is guaranteed for other memory locations.

[Note: the standard text doesn't formally guarantees that, but it's meant to guarantee that, and a consistent approach to C/C++ thread semantics must be based on that.]

You can compare the speed of a multiplication and a cosine, but not compare the cost of outputting "hello world" and flushing <code>cout</code>. The flush on a stream or file doesn't have an intrinsic price tag: it relates to other operations.

You can't compare the speed of an operation that blocks until some previous operation is complete with one that doesn't. 

Also, you can't benchmark in a vacuum. You need some workload, a pattern of operations.

You would need to learn a lot on modern CPU design, and by modern I mean anything that was invented in the last two decades. You have to have at least some idea of the complexity of a real CPU and the way it runs code, how multi core operates, and the general principles of memory caches, to even dream of designing a useful benchmark in the abstract.

Or, you could just write your program, and profile it to see if there is really an issue with atomic operations.

Can anyone point to benchmark results comparing performance of C11/C++11 code using relaxed atomic operations (particularly <code>memory_order_release</code> and <code>memory_order_acquire</code>, but also <code>memory_order_consume</code> and <code>memory_order_relaxed</code>) versus the default <code>memory_order_seq_cst</code>? All architectures are of interest. Thanks in advance.

C11/C++11 weak memory benchmarks

翻译质量差，导致语言生硬或混乱。

没有提供实际的解决方法或示例。

解答不清晰，无法理解或解决问题。

页面排版不美观，阅读体验差。

文章

问答

视频

学习中心

腾讯云实验室

直播

竞赛

腾讯云代码分析专区

腾讯iOA零信任安全管理系统专区

腾讯云架构师技术同盟交流圈

腾讯云数据库专区

腾讯云顾问专区

腾讯云原生专区

腾讯混元专区

腾讯云TCE专区

腾讯云Lighthouse专区

腾讯云HAI专区

腾讯云Edgeone专区

腾讯云存储专区

腾讯云智能专区

腾讯轻联专区 

腾讯云开发专区

TAPD专区

腾讯轻量云游戏服专区

腾讯云最具价值专家

腾讯云架构师技术同盟

腾讯云创作之星

腾讯云开发者先锋

腾讯云代码助手

云原生构建

TAPD 敏捷项目管理

Cloud Studio

SDK中心

API中心

命令行工具

涵盖代码开发、场景应用、自动测试全流程，助你从零构建专属AI助手

一站式MCP教程库，解锁AI应用新玩法

有谁能指出使用宽松原子操作(特别是memory_order_release和memory_order_acquire，但也包括memory_order_consume和memory_order_relaxed)与默认memory_order_seq_cst进行C11/C++11代码性能比较的基准测试结果？所有的架构都很有趣。提前谢谢。

问C11/C++11弱内存基准测试
EN

回答 4

Stack Overflow用户

Stack Overflow用户

Stack Overflow用户

社区

活动

圈层

关于

腾讯云开发者

热门产品

热门推荐

更多推荐

问C11/C++11弱内存基准测试EN

回答 4

Stack Overflow用户

Stack Overflow用户

Stack Overflow用户

社区

活动

圈层

关于

腾讯云开发者

热门产品

热门推荐

更多推荐

问C11/C++11弱内存基准测试
EN