Broadly speaking, the first half of of the course will look at systems that already exist, focusing primarily on offerings from Intel and IBM.  The second half will look at the ideas being proposed in the most recent research literature. 

In addition to the readings below, you will often need to look up things on your own.  For example, you may encounter a term or a concept in a paper that you do not understand.  In that case you will need to research that topic on your own to fill gaps in your understanding.  I recommend getting a copy of Hennessey and Patterson's "Computer Architecture: A Quantitative Approach" to fill in the gaps.

Since modern processors are so complex, there is no way that we can grasp them in a single session.  Thus, oftentimes we will discuss a processor over multiple sessions; this means that multiple presenters will need to work together on a topic.  It is up to the presenters to split up the presentation amongst them.  E.g., the first presenter may spend a class period giving a relatively high-level overview of the processor and the second presenter may pick one or two particularly interesting aspects of the processor and go over them in gory details.