Cache friendly algorithm
Presented by Yossi Moalem at Core C++ 2022.
I believe we all know that cache memory is a lot faster than main memory. Therefore, if we want performant code, we need to think about the memory. We need to think not only about the algorithms we are using, but also on how the data is laid out in the memory. However, most talks about the subject discuss the theory, and provide very simple examples, that are very far from real-life scenarios. In this talk I will discuss one complex case I had to optimize, which although it used relatively smart logic, performed badly. We will see how to find bottlenecks and how to resolve them, to get much better performance.
-----
Yossi is a software developer at Fortinet EDR division. He has over 15 years of experience as a professional programmer, mainly in C/C++. Yossi considers the standard as light reading and spends all his spare time learning new technologies and methodologies (much to the delight of his wife!!). He likes teaching and sharing his knowledge, but what really does it for him is refactoring legacy code into beautifully crafted code. On the positive side, he loves Led Zeppelin.
