Jon Stokes also wrote Inside the machine[1], a great introduction to microprocessors architecture.

[1] https://www.amazon.com/Inside-Machine-Introduction-Microproc...

> moved to a team working on low level networking software for high performance computing.

> I don't know why data sometimes has to be aligned to cache lines or what cache lines even are.

> I try to learn these things in my spare time but it's a real struggle.

Well the good news is you don't need to learn this in your spare time, because it's your job, so you can learn it on the clock?

Take a look at Inside the Machine [1] to get an in-depth, but accessible, understanding of how a somewhat dated Intel processor works, then read the optimization manual for the processor you use, and you'll have a much better foundation for your work.

Figure out how to use Intel vTune or similar, and you'll be able to get a good idea of what your system is doing. Read posts about Netflix's CDN machines, which are very high performance networking machines; you'll absorb a lot of information and terminology, hopefully.

Sorry, that doesn't help you meet people, I'm a curmudgeon and don't have advice there. Cultivate your network of people you'ld like to bounce ideas off of? But keep in mind, lots of people want to leave work at work.

[1] https://www.amazon.com/Inside-Machine-Introduction-Microproc...

A computer architecture class. For books, [1] is what you will probably use in any decent computer architecture class, and [2] is a good read from a more general audience perspective, if a bit dated.

1. https://www.amazon.com/Computer-Architecture-Fifth-Quantitat...

2. https://www.amazon.com/Inside-Machine-Introduction-Microproc...

So true. Jon Stokes also wrote the great book "Inside the Machine: An Illustrated Introduction to Microprocessors and Computer Architecture" while he worked at Ars Technica. I have it still in my bookshelf. http://www.amazon.com/Inside-Machine-Introduction-Microproce...

Higher clock speed, more instructions per cycle and good pipelining architecture means higher single-core raw performance.

We had already complex pipelining superscalar architecture with Pentium Pro and Pentium 4 (Netburst/Prescott). The current Core Architecture has a lot simpler pipelining based on Pentium 3/M. (see http://en.wikipedia.org/wiki/Clock_rate )

I favor a high single-core over a slow many-core CPUs.

Have you ever coded a many-core application that runs on thousands of CPUs? I have done using it using http://en.wikipedia.org/wiki/Cilk , http://en.wikipedia.org/wiki/OpenMP (and CUDA and OpenCL on GPU), as well as traditional using operating system process and threads.

You need new algorithms that work on massive parallel computers. Converting algorithms from serial to massive parallel is possible in many cases, but really hard science work (have done it).

Nevertheless, for a specific domain I would need a really high speed single-core CPU.

A good book about the topic is "Inside the Machine" from ArsTechnica: http://www.amazon.com/Inside-Machine-Introduction-Microproce... ...and various university lectures.