ECE 15B Computer Organization Spring 2011 Dmitri Strukov Lecture 1: Introduction Partially adapted from Computer Organization and Design, 4 th edition, Patterson and Hennessy, and classes taught by Patterson at Berkeley, Ryan Kastner at UCSB and Mary Jane Irwin at Penn State
33
Embed
ECE 15B Spring 2011 › ~strukov › ece15bSpring2011 › ...ECE 15B Computer Organization Spring 2011 Dmitri Strukov Lecture 1: Introduction Partially adapted from Computer Organization
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
ECE 15B Computer OrganizationSpring 2011
Dmitri Strukov
Lecture 1: Introduction
Partially adapted from Computer Organization and Design, 4th edition, Patterson and Hennessy, and classes taught by Patterson at Berkeley, Ryan Kastner at UCSB and Mary Jane Irwin at Penn State
Office hours: Wednesday 3:00 – 5:00 pm or by appointment
l h d l liplease see my schedule online http://www.ece.ucsb.edu/~strukov/DmitriWebPage_files/calendar.htm
ECE 15B Spring 2011
Course Logistics : TAsCourse Logistics : TAs
Sam Masooman [email protected] hours: Phelps 1435, Available time slots: Thursday 12:30 am 1:30 pmAvailable time slots: Thursday 12:30 am ‐1:30 pmDiscussion session: Girvetz Hall 2119, Monday 5:00‐5:50 pm
Jian Zhen [email protected] h ECI L b ( ill i )Office hours: ECI Lab (still tentative)Available time slots: Friday 10:00 am – 11:00 amDiscussion session: Phelps 1448, Friday 9:00‐9:50 pmDiscussion session: Phelps 1448, Friday 9:00 9:50 pm
ECE 15B Spring 2011
Course Logistics: MaterialCourse Logistics: Material
• Required: Computer Organization and Design: The• Required: Computer Organization and Design: The Hardware/Software Interface, Fourth Edition, Patterson and Hennessy (COD). The third edition is also accepted.
• Recommended: MIPS Assembly Language Programming, Robert L. Britton, 2003.
• Additional (not required): The C Programming Language, Kernighan and Ritchie (K&R), 2nd edition
• C language manual webpage from Stanford University
• Class Participation: 5%– Attendance & discussion in class– Attendance & discussion in class
ECE 15B Spring 2011
Course Logistics: Approximate Schedule
• Approximate schedule on class syllabusApproximate schedule on class syllabus– 1 hw/project/quiz per week
Hw/projects typically due Fridays at 11:00 pm in– Hw/projects typically due Fridays at 11:00 pm in HFH, 3rd floor (box labeled ECE15B)
• Last year lecture viewgraphs will be replaced• Last year lecture viewgraphs will be replaced with newest one on the day of lecture
H j d i i d l i ill b• Hw, projects description, and solutions will be posted on the web
(HW#0 already online)ECE 15B Spring 2011
Course Logistics: Approximate ScheduleCourse introduction 1Overview of computer organization (hw) 1Arithmetic instructions 1Data transfer instructions 1Control flow instructions 1Logic/shift/overflow 1 Procedures 2Procedures 2 Instruction representation 1Memory addressing modes 1Floating point arithmetic 1Floating point arithmetic 1Pointers and arrays 1 String, lists, stacks 1Memory management 2y gCompiling, assembling, linking and loading 1History of computing 1 Final review 1 In class quiz 2
ECE 15B Spring 2011
Key milestones in semiconductor i d t d t tindustry and computer systems
• 1946 First digital electronic programmable• 1946 First digital electronic programmable computer by John Mauchy and J.P. Eckert (UPenn) , ENIAC (1,800 sq ft, 18,000 vacuum tubes, 50 tones( , q , , ,
• 1954 First silicon transistor by TI
• 1958 First integrated circuit by Jack Kilby by TI
• 1971 First (single chip) microprocessor – Intel 4004 by Ted Hoff and others, 10‐um, 2300 transistors
VAX : 1.25x/year 1978 to 1986• RISC + x86: 1.52x/year 1986 to 2002• RISC + x86: 1.20x/year 2002 to presentECE 15B Spring 2011
ECE 15B Spring 2011
Other computing platforms (why not everything from silicon are(why not everything from silicon are
microprocessors?)I l NRE tInvolves NRE cost
Cost Nonrecurring engineering cost/volume + Production cost
ECE 15B Spring 2011
Cost = Nonrecurring engineering cost/volume + Production costProduction cost = (1+Defect density * Area/ alpha) alpha, where alpha = 1 to 5
Other computing platforms ( h h )(why not everything microprocessors?)
μPmanufacturing cost (at small volumes)
ASIC
performance
Market size:‐ Semiconductor industry >$1000B‐Microprocessor (w embedded) > $100BMicroprocessor (w. embedded) > $100BFor comparison: USA GDP ~ $14000B (24% of worlds total)
Other computing platforms ( h h )(why not everything microprocessors?)
ECE 15B: So what’s in it for me?ECE 15B: So what s in it for me?
• Learning computer systems from aLearning computer systems from a programmer’s point of view– What the programmer writes– What the programmer writes
– How it is converted to something the computer understandsunderstands
– How computer interprets the program
What makes programs go slow– What makes programs go slow
ECE 15B Spring 2011
The Rise of Embedded ComputersIn millions
Intel Atom, ~ 50 M Tran.
Population 6.4B in 2004, i.e. ~ 1PC, 2.2 cell phones, and 2.5 televisions for every 8 people on the planet ECE 15B Spring 2011
Advantages of Higher‐Level Languages ?h l l l• Higher‐level languages
Allow the programmer to think in a more natural language and for their intended use (Fortran for scientific computation, Cobol for b i i Li f b l i l ti J f bbusiness programming, Lisp for symbol manipulation, Java for web programming, …)
Improve programmer productivity – more understandable code that is easier to debug and validatethat is easier to debug and validate
Improve program maintainability
Allow programs to be independent of the computer on which they are developed (compilers and assemblers can translate high levelare developed (compilers and assemblers can translate high‐level language programs to the binary instructions of any machine)
Emergence of optimizing compilers that produce very efficient assembly code optimized for the target machine
• As a result, very little programming is done
assembly code optimized for the target machine
today at the assembler levelECE 15B Spring 2011
ECE 15B: So what’s in it for me?ECE 15B: So what s in it for me?
• Learn big ideas in computer engineeringLearn big ideas in computer engineering– Principle of abstraction used to build systems as layers
– 5 classic components of a computer– Data can be anything (integers, floating point, characters): program determines what it is
– Stored program concept: instructions just dataP i i l f l li l i d i– Principle of locality, exploited via memory hierarchy
– Greater performance by exploiting parallelism– Greater performance by exploiting parallelism
ECE 15B Spring 2011
ECE 15B: can also help youECE 15B: can also help you
• Assembly Language Programmingy g g g g– This is a skill you will pick up as a side effect of understanding big ideas
• Hardware Design• Hardware Design– Hardware at the abstract level with only a little bit of physical implementation details to give perspective
• Understand Language Concept– If you know one, you should be able to learn another “low” level programming language on your ownlow level programming language on your own
– C constructs used in many other “higher” level programming languages
ECE 15B Spring 2011
ECE 15B: Does Not TeachECE 15B: Does Not Teach
• A specific assembler languagespec c asse b e a guage– 486 instruction set– ARM instruction set (i.e. Apple A5 processor with ARM Cortex‐A9 in iPad2, or iPhone)
– PowerPC instruction set
B t h l i h d ti ll• Because technologies change so dramatically – Learning the concepts is more important that learning the languagethe language
– Learning abstract ideas is more important that learning the specific features
ECE 15B Spring 2011
My Own Background...
MMT Simulator
• Features– Assembler & Debug
C l i l i– Cycle‐accurate simulation
– GUI and Script support
– Detailed statistics including runtime conflictsruntime conflicts
• Implementation– C ‐ 35 K lines of code
– TCL ‐ 7 K lines of code
ECE 15B Spring 2011
Memory latency reduction with fine‐grain migrating threads in NUMA shared‐memory multiprocessors” (with M. Dorojevets) in: Proc. PDCS’02, Cambridge, MA, Nov. 2002, pp. 762‐767
SummarySummary
• Continued rapid improvement in computingContinued rapid improvement in computing– May end up soon but new paradigms and concept will likely inherit a lot from traditional computerwill likely inherit a lot from traditional computer implantation, e.g. multi core
• Hardware/software interface is important layer in the hierarchy to understand howlayer in the hierarchy to understand how computing is implemented