Telegram-канал "Easton Man's Channel" — @easton_channel

Easton Man's Channel

22 Jun, 22:30

Daniel Lemire's blog
Performance tip: avoid unnecessary copies

Telegraph | source

Performance tip: avoid unnecessary copies

Copying data in software is cheap, but it is not at all free. As you start optimizing your code, you might find that copies become a performance bottleneck. Let me be clear that copies really are cheap. It is often more performant to copy that data than to track the same memory across different thre...

80 0 0 1

Easton Man's Channel

22 Jun, 18:48

Chips and Cheese
Testing AMD’s Bergamo: Zen 4c Spam
#ChipAndCheese

Telegraph | source
(author: clamchowder)

Testing AMD’s Bergamo: Zen 4c Spam

Server CPUs have pushed high core counts for a long time, though they way they got high core counts has varied. Bergamo is AMD’s move to increase core counts beyond what scaling up an interconnect can do, by using density focused Zen 4c cores. It’s a strategy with parallels to Intel’s upcoming Sierr...

92 0 0

Easton Man's Channel

22 Jun, 11:47

#龙芯 #JamesAslan
#高通 #Oryon

https://zhuanlan.zhihu.com/p/704707254

111 0 2

Easton Man's Channel

22 Jun, 03:20

Репост из: David's random thoughts

Zen 5 抢先体验：Ryzen AI 9 365 (Strix Point SoC) 简单测试 https://blog.hjc.im/zen5-preliminary-review.html

（以后文章不发知乎了）

97 0 4

Easton Man's Channel

20 Jun, 20:28

Daniel Lemire's blog
Validating gigabytes of Unicode strings per second… in C#?

Telegraph | source

Validating gigabytes of Unicode strings per second… in C#?

We have been working on a fast library to validate and transcode Unicode and other formats such as base64 in C++: simdutf. We wondered: could we achieve the same good results in C#? Microsoft’s .NET framework has made great strides in leveraging advanced instructions. For instance, if your processor...

129 0 1

Easton Man's Channel

16 Jun, 01:05

Chips and Cheese
Intel Details Skymont
#ChipAndCheese

Telegraph | source
(author: clamchowder)

Intel Details Skymont

Previously Intel’s Skymont slides were published in low resolution, and I wrote a short article on them. Now, the presentation is public with higher resolution slides and presenter audio. Because there’s a lot more detail to comment on, it’s time for a follow up to give a more complete picture of In...

204 0 1

Easton Man's Channel

14 Jun, 00:18

Daniel Lemire's blog
Rolling your own fast matrix multiplication: loop order and vectorization

Telegraph | source

Rolling your own fast matrix multiplication: loop order and …

If you must multiply matrices, you should use dedicated libraries. However, we sometimes need to roll our own code. In C++, you can quickly write your own Matrix template: template struct Matrix { Matrix(size_t rows, size_t cols) : data(new T[rows * cols]), rows(rows), cols(cols) {} T &...

186 0 0

Easton Man's Channel

11 Jun, 00:03

Chips and Cheese
Tracing Intel’s Atom Journey: Goldmont Plus
#ChipAndCheese

Telegraph | source
(author: clamchowder)

Tracing Intel’s Atom Journey: Goldmont Plus

Today Intel’s Atom line occupies a prominent place in Intel’s best client chips. Atom cores are also going into Intel’s upcoming Sierra Forest server CPU, where they’ll similarly aim to deliver area efficient multithreaded performance. But a few generations ago, Intel’s Atoms were stuck in low power...

207 0 0 1

Easton Man's Channel

8 Jun, 08:07

Daniel Lemire's blog
Scan HTML faster with SIMD instructions: Chrome edition

Telegraph | source

Scan HTML faster with SIMD instructions: Chrome edition

Modern processors have instructions to process several bytes at once. Effectively all processors have the capability of processing 16 bytes one once. These instructions are called SIMD, for single instruction, multiple data. It was once an open question whether these instructions could be useful to ...

191 0 2 1

金枪鱼之夜：支持多种 ISA 扩展的二进制背后的秘密

随着算力需求的提升，我们不断往 CPU 加入新的 ISA 扩展来提高指令表达能力。然而，在软件分发过程中，为每一种 CPU 所支持的 ISA 扩展组合进行编译与分发并不现实，无法接受各种组合的软件构建成本以及镜像站的存储成本。因此，在目前的软件中，往往通过增加性能敏感函数针对不同 ISA 的实现，配合一些函数重定向方法来解决问题。然而，这些方法或多或少存在性能或安全的问题，特别是 IFUNC 机制更是被著名的 xz 软件后门所利用。因此，cyy 希望在 Tunight 上与大家分享目前常见软件实现一个二进制支持多种 ISA 扩展的方法，以及探讨目前的性能与安全问题的案例以及可行的解决方案。

- 主讲人：陈泱宇
- 时间：2024/06/08（校历第十五周周六） 19:00-21:00 UTC +08:00
- 活动形式：线下 + 线上会议 + 直播
- 地点：三教 3104
- 线上会议：Zoom 会议: 970 8479 0044, 密码 20240608
- 直播链接：YouTube 直播: https://youtube.com/live/s78ynPBsTtY