🚀 go-pugleaf

                                  CS 6241A
                                  CRN 86169
                                 TTh 4:30-6

A special version of CS 6241 - Design and Implementation of Compilers - will
be offered during Fall Semester, 2000.  
See the end of this course description for prerequisite expectations.

                Compiler Optimizations for Modern Processors
                     Krishna V. Palem and Wong Weng-Fai

        The primary goal of this course is to provide an in-depth study of
state-of-the-art code optimization techniques used in compilers for modern
processors.  The performance gap between optimized and unoptimized code
continues to widen as modern processors evolve.  The evolution includes
hardware features such as pipelined functional units other forms of
instruction-level parallelism, and sophisticated memory hierarchies for
exploiting data locality.  These hardware features are aimed at yielding
high performance, and are critically dependent on the code being optimized
appropriately.  The emerging explicitly parallel instruction computing
(EPIC) processors such as Itanium and McKinley are significantly dependent
on a range of aggressive program optimizations to yield performance.  Rather
than burdening the programmer with this additional complexity during code
development, modern compilers offer automatic support for code optimization.

        The course is self-contained and begins with a detailed view of the
design of optimizing compilers with emphasis on the EPIC space.  In each
case, the rationale guiding the important decisions underlying the design
will be discussed.  A typical optimizing compiler contains a sequence of
restructuring and code optimization techniques, which will be covered during
the classroom lectures; issues related to interactions among individual
optimizations will also be discussed.

        A significant aspect of this course is the ability to learn
industry-strength compiler optimization technology via on-line
demonstrations and a hands-on laboratory session centered around the
Trimaran (www.trimaran.org) system.  Students will be able to and encouraged
to undertake projects spanning the course of the semester involving the
design, implementation and validation of such optimizations.

        The course will also discuss the impact of the source language and
the target architecture on the effectiveness of optimizations.  The
optimizations covered are also relevant for RISC processors, such as the IBM
RS/6000, Power PC, DEC Alpha, Sun Sparc, HP PA-RISC, and MIPS, and
third-generation programming languages such as Fortran and C.  Extensions
for optimizing object-oriented languages such as C ++ will also be
mentioned.

        The course is relevant to students aiming to develop skills leading
to careers as systems programmers and analysts, scientific programmers,
computer designers and architects, technical managers, mathematics and
computer science teachers, or anyone facing the prospect of building,
modifying, maintaining, writing or teaching about compilers.  At the
conclusion of the course, the students should be knowledgeable about
optimization techniques used in modern compilers including those for EPIC
processors, from the viewpoint of the compiler user as well as of the
compiler designer.

Recommended Prerequisites:  The course as taught will be self-contained.
However, students without background in the following topics will likely
find it necessary to do extra work to develop their knowledge in these
areas:
        1. Fundamentals of compiler construction and computer architecture
(as from undergraduate courses).
        2. Elementary background in the design and analysis of algorithms.
Project work in the course will require:
        3. Programming skills and familiarity with C/C++.

Reading material:  Lectures will be based on detailed notes (over 400 pages)
developed by Krishna Palem and Vivek Sarkar; individual lectures will be
provided to the student in soft- and/or hardcopy form one week prior to each
lecture.

                                    *****
-- 
					
				-Scheduling Account (schedule@cc.gatech.edu)