\documentstyle[class,11pt]{article}
\def\ClassName{Computer~Organization}
\def\ClassNumber{CS~333}
\handedout{(10/29/95) Handout \#12}
\vspace{0.5in}

\begin{flushleft}
{\large \bf Homework \#5} \\
{\bf Due before 5pm, November 6, 1995 \\
Turn in at TA's office L423 DCL (Basement)} \\
(Slide in under door if locked.)
\end{flushleft}
\begin{document}

{\bf NOTE the MONDAY due date.}

{\it As with all class assignments, you are expected to work the problems
on your own.  Discussions with other students should be limited to
understanding the problem and discussing general issues, NOT solving
the problems.  Electronic mail or posting to the course news group
(uiuc.class.cs333) is probably the fastest way to get clarification of
any problems, but you are welcome to contact any of the teaching staff
directly.  Check the WWW (URL: http://www-courses.cs.uiuc.edu/{$\sim$}cs333) 
for course information such as office hours.}

{\bf Introduction:} This assignment focuses on vector processors,
their relation to instruction-level parallel scalar processors, and
basics of memory hierarchies.  Before starting the homework, you
should have read Appendix B, and Chapter 5.1-5 in the textbook.

{\bf Problems:}
If you feel that a problem is specified insufficiently, state clearly
and justify the assumptions you are making.  Please write your
solutions neatly, making sure to SHOW CLEARLY how you arrived at your
answers.  Illegible or insufficiently clear solutions may be graded 
as incorrect.

\begin{problems}
\problem \Points{40}
{\bf Vector Machine Performance} -- H\&P B.3 (page B-43)

\problem \Points{10}
{\bf Vector Machine vs. ILP} -- Using the vector machine and program
fragment in H\&P Problem B.3, (i.e. the above problem)
consider a comparison
against a quad issue superscalar machine with equivalent clock rate
and functional unit parallelism (number of functional units and their
latencies).  Assume the quad issue, similar to the DEC Alpha 21164 and
IBM PowerPC 620 can issue at most two integer and two floating point
instructions per cycle (e.g. no more than 2 integer ops in a given
cycle and likewise for the floats).  Calculate $N_V$?  and show your
work.

\problem \Points{15}
{\bf Software for Vector Machines} -- H\&P Exercises B.9 (page B-45) 

\problem \Points{10}
{\bf Memory Hierarchies I} -- H\&P Exercise 5.3

\problem \Points{10}
{\bf Memory Hierarchies II} -- H\&P Exercise 5.5

\problem \Points{15}
{\bf Memory Hierarchies III} -- H\&P Exercise 5.7


\end{problems}

\end{document}