Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

I love reading articles like this: "So, for example, a cache miss on Jesper's 3GHz processor takes about 32ns to resolve. It thus only takes two misses to wipe out the entire time budget for processing a packet."

Then I go back to adding another layer of abstraction to my bloated Java code and die a little inside.



Actually guys like him are making our life easier and so we don't have to worry about a lot of stuff like this. Abstractions are a necessity, don't feel bad. There is no way a small team using Java/Scala can accomplish what they usually do in the time frame they do it, without those abstractions. Computers are there to ease our lives after all.

p.s. not undermining the need to optimize and all


For completeness, generally memory access that misses the last level cache incurs 60-110 ns latency on recent DDR3 based x86 hardware, see eg. http://www.sisoftware.co.uk/?d=qa&f=ben_mem_latency&l=en&a=

I don't know what exactly the 32ns measurement is from, sounds similar to the "in-page" figures on the above page.


yeah, it's easy to cry when you see a real artist working on something, and you have to go back to your etch-a-sketch.


Real art may inspire the soul, but road signs keep you from dying.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: