CUDA

General-purpose computing on graphics processing units (GPGPU, also referred to as GPGP and to a lesser extent GP²) is the technique of using a GPU, which typically handles computation only for computer graphics, to perform computation in applications traditionally handled by the CPU. It is made possible by the addition of programmable stages and higher precision arithmetic to the rendering pipelines, which allows software developers to use stream processing on non-graphics data. Source: http://en.wikipedia.org/wiki/GPGPU

It’s impossible to get a solid, well-rounded CS education without understanding computer organization and architecture because too many things depend on such understanding.

Performance analysis of practical software

Parallel software and its execution

Embedded and mobile computing

High-performance game programming

High-performance databases

Accelerators, GPGPU computing and related topics

Modern compilers and code optimization

Low- and mid-level networking issues

Computer Organization and Architecture lets you know how exactly each instruction is executed at the micro level. If you plan to study embedded systems/ processor design, these concepts are very important, as they form the basis of design strategy. It is also a well-known fact that assembly coding is closest to the computer, and it is always most optimum, if written properly.

You should study computer architecture if you have an interest and talent in that area. The advance in computers is limitless and as more and more services are provided by computers, creative and learned inventors, service people and builders will have a key role in the advancement of those computer technologies.