Course Introduction

CS61C

Great Ideas

in

Computer Architecture

(a.k.a. Machine Structures)

cs61c.org

Assistant Teaching Professor

Lisa Yan

Yan, SP26

01-Course Introduction (1)

​

🎉 Welcome to CS61C!!! 🎉

Yan, SP26

01-Course Introduction (2)

​

Live Lecture, Enrollment Updates

Slides: cs61c.org

​

Concurrent enrollment student?

We will add you so that you can submit assignments while we wait for official enrollment.

Please move towards the center of each row!

​

If you cannot find a fixed seat to sit in,�for safety reasons we will need to ask you to leave.

• Join lectures via Zoom: https://cs61c.org/sp26/lecture-zoom
• Asynchronously: Recording posted on bCourses every evening

Ask questions via Lecture 01 on Ed! [NOT on Zoom]

Yan, SP26

01-Course Introduction (3)

​

Thinking about Machine Structures

Slides: cs61c.org/

Agenda

• Thinking about Machine Structures
• Great Ideas in Computer Architecture
• What you need to know about this class

Yan, SP26

01-Course Introduction (4)

​

CS61C is NOT about C Programming…!!

It is about the hardware-software interface.

• What the programmer needs to know to achieve the highest possible performance.

​

Languages like C are closer to the underlying hardware.

• Unlike languages like Snap!, Python, Java
• We can talk about hardware features in higher-level terms
• C allows programmer to explicitly harness underlying hardware parallelism for high performance

Yan, SP26

01-Course Introduction (5)

​

Old-School CS61C

Note: �Fake 1954 photo

Snopes

Yan, SP26

01-Course Introduction (6)

​

New-School CS61C (1/3)

Personal Mobile Devices

Network Edge Devices

Yan, SP26

01-Course Introduction (7)

​

New-School CS61C (2/3)

​

Yan, SP26

01-Course Introduction (8)

​

New-School CS61C (3/3)

​

​

A popular laptop sticker

Yan, SP26

01-Course Introduction (9)

​

We learned Old School “Machine Structures”...

Digital Design

Transistors

Circuit Design

Datapath & Control

CS61C

I/O system

Processor

Operating System (Mac OS X)

Application (ex: browser)

Instruction Set

Architecture

Memory

Hardware

Software

Assembler

Fabrication

Compiler

Yan, SP26

01-Course Introduction (10)

​

New school Machine Structures is much more complicated!

Parallel Requests

Assigned to computer

e.g., Search “Cats”

Parallel Threads

Assigned to core�e.g., Lookup, Ads

Parallel Instructions

>1 instruction @ one time,�e.g., 5 pipelined instructions

Parallel Data�>1 data item @ one time

e.g., Add of 4 pairs of words

Hardware descriptions

All gates work in parallel, at same time

​

Hardware

PC

Software

Yan, SP26

01-Course Introduction (11)

​

Great Ideas in Computer Architecture

Slides: cs61c.org/

Agenda

• Thinking about Machine Structures
• Great Ideas in Computer Architecture
• What you need to know about this class

Yan, SP26

01-Course Introduction (12)

​

6 Great Ideas in Computer Architecture

1. Abstraction (Layers of Representation/Interpretation)
2. Moore’s Law
3. Principle of Locality/Memory Hierarchy
4. Parallelism
5. Performance Measurement & Improvement
6. Dependability via Redundancy

Yan, SP26

01-Course Introduction (13)

​

Great Idea #1: Abstraction (Levels of Representation/Interpretation)

Structure and Interpretation of Computing Programs, �my good friend…

import numpy

​

x = 3

x = "hello, world"

x = [3, "cs61a", True]

x = len

x = numpy

x = lambda x: x + 2

In CS61A: Anything can be a Python name.

Yan, SP26

01-Course Introduction (14)

​

We’ll make HW/SW Contact!!!

lw x3 0(x10)

lw x4 4(x10)

sw x4 0(x10)

sw x3 4(x10)

High Level Language�Program (e.g., C)

Assembly Language �Program (e.g., RISC-V)

Machine Language Program (RISC-V)

Compiler

Assembler

Hardware Architecture Description�(e.g., block diagrams)

Logic Circuit Description�(Circuit Schematic Diagrams)

Architecture Implementation

temp = v[k];

v[k] = v[k+1];

v[k+1] = temp;

1000 1101 1110 0010 0000 0000 0000 0000

1000 1110 0001 0000 0000 0000 0000 0100

1010 1110 0001 0010 0000 0000 0000 0000

1010 1101 1110 0010 0000 0000 0000 0100

The Creation of Adam, Michelangelo, c. 1512

Anything can be a number—data, instructions, etc.

Yan, SP26

01-Course Introduction (15)

​

Great Idea #2: Moore’s Law - 1965

Source: Intel

Yan, SP26

01-Course Introduction (16)

​

Great Idea #2: Moore’s Law - 2005

Yan, SP26

01-Course Introduction (17)

​

Moore’s Law…?

Seems to be tapering…?�(more later)

Yan, SP26

01-Course Introduction (18)

​

A’s Law…?

Teachers College Record Volume 114 Number 7, 2012, p. 1-23

Yan, SP26

01-Course Introduction (19)

​

Great Idea #3: Principle of Locality / Memory Hierarchy (1/2)

Yan, SP26

01-Course Introduction (20)

​

Great Idea #3: Principle of Locality / Memory Hierarchy (2/2)

Jim Gray�Turing Award

B.S. Cal 1966

Ph.D. Cal 1969

​

​

Storage Latency Analogy: How Far Away is the Data?

On-chip cache

Yan, SP26

01-Course Introduction (21)

​

Great Idea #4: Parallelism

Yan, SP26

01-Course Introduction (22)

​

Great Idea #4: Parallelism

Thread-Level Parallelism

Yan, SP26

01-Course Introduction (23)

​

Great Idea #4: Parallelism

In time slot 3:

• Instruction 1 is being executed
• Instruction 2 is being decoded
• Instruction 3 is being fetched from memory

​

Instruction-Level Parallelism

Yan, SP26

01-Course Introduction (24)

​

…Amdahl’s Law

Gene Amdahl

Computer Pioneer

​

Caveat!�(more later)

Yan, SP26

01-Course Introduction (25)

​

Great Idea #5: Performance Measurement & Improvement

Match application to underlying hardware to exploit:

• Locality;
• Parallelism;
• Special hardware features, like specialized instructions�(e.g., matrix manipulation).

​

Metrics of Latency/Throughput:

• How long to set the problem up and complete it�(or how many tasks can be completed in a given time)
• How much faster does it execute once it gets going

Yan, SP26

01-Course Introduction (26)

​

Great Idea #6: Dependability via Redundancy

Yan, SP26

01-Course Introduction (27)

​

Great Idea #6: Dependability via Redundancy

Design with redundancy so that a failing piece doesn’t make the whole system fail.

1 + 1 = 2

1 + 1 = 2

1 + 1 = 1

2 of 3 agree ✅

1 + 1 = 2

Yan, SP26

01-Course Introduction (28)

​

Great Idea #6: Dependability via Redundancy (3/3)

Applies to everything from datacenters to storage to memory…to instructors!

• Increasing transistor density�reduces the cost of redundancy
• Error-correcting codes:�Redundant memory bits so that can lose�1 bit but no data
• RAID: Redundant disks so that can lose 1 disk �but not lose data
• Redundant datacenters so that can �lose 1 datacenter but Internet service �stays online

Yan, SP26

01-Course Introduction (29)

​

(dramatic pause)

Yan, SP26

01-Course Introduction (30)

​

Why is computer architecture exciting today?

Yan, SP26

01-Course Introduction (31)

​

Reason 1: Changing Constraints

• Moore’s Law ending
• Power limitations
• Amdahl’s Law

Yan, SP26

01-Course Introduction (32)

​

Reason 2: Era of Domain-Specific Computing

• Number of deployed devices continues to grow, but there is no single killer application.
• Diversification of needs, architectures
• Machine learning is common for most domains

Yan, SP26

01-Course Introduction (33)

​

Old Conventional Wisdom

• Moore’s Law + Dennard Scaling = faster, cheaper, lower-power general-purpose computers each year
• In glory days, 1%/week performance improvement!
• Dumb to compete by designing parallel or specialized computers
• By time you’ve finished design, the next generation of general-purpose will beat you!

Yan, SP26

01-Course Introduction (34)

​

New Conventional Wisdom

Each domain requires heterogeneous systems.

• Multiple processor cores
• GPUs,
• NPUs,
• accelerators,
• interfaces,
• memory, …

Apple M14 (link)

Yan, SP26

01-Course Introduction (35)

​

New Conventional Wisdom

Google TPU3

Specialized Engine for training Neural Networks

Deployed in cloud

1024 chips, > 100PetaFLOPs

​

​

Yan, SP26

01-Course Introduction (36)

​

Top Companies in the World

Job/Internship Interviews: They grill you with technical questions, so it’s what you know and can do, not your GPA.

• CS61C gives good stuff to say!

Largest Companies�by Market Cap

Yan, SP26

01-Course Introduction (37)

​

Patterson and Hennessy win Turing Award! (2017)

https://engineering.berkeley.edu/news/2018/06/patterson-wins-turing-award/

Innovations in computer architecture often defy conventional wisdom.

Yan, SP26

01-Course Introduction (38)

​

What you need to know about this class

Slides: cs61c.org/

Agenda

• Thinking about Machine Structures
• Great Ideas in Computer Architecture
• What you need to know about this class

Yan, SP26

01-Course Introduction (39)

​

Our Spring 2026 Course Staff

Yan, SP26

01-Course Introduction (40)

​

Course Information

Course Website: https://cs61c.org/

Instructor: Lisa Yan

​

• Website: Course resources (lectures, handouts, assignments)
• EdStem
• Every announcement, discussion, clarification happens here

Yan, SP26

01-Course Introduction (41)

​

Today’s required reading

Read our Course Policies in full:

https://cs61c.org/sp26/policies

Yan, SP26

01-Course Introduction (42)

​

Typical Week

Yan, SP26

01-Course Introduction (43)

​

Next week (Week 2)

*Welcome Form: Submit discussion preference.

• Regular (1-hr) vs. Bridge (2-hr) vs. Video discussion
• Discussion attendance taken starting Week 3

Yan, SP26

01-Course Introduction (44)

​

Course policy highlights

Lateness and Accommodations Policy:�flexible assignment extensions

• If you need just a little time, pre-approved automated extension
• If you need more time, one-time custom extension
• If your life is falling apart, or you need else, talk to us!

​

Exams: Quest (CBTF), paper Midterm, paper Final

Absolute Grading! (not curved!)

​

DSP Students: Submit your letter of accommodation ASAP!

Yan, SP26

01-Course Introduction (45)

​

Yoda says…

“Always in motion, the future is…”

Our precise schedule (lectures, assignments, labs) may change slightly over the course of the semester.

Yan, SP26

01-Course Introduction (46)

​

(somber pause)

Yan, SP26

01-Course Introduction (47)

​

We expect that what you hand in for this course is yours.

Yan, SP26

01-Course Introduction (48)

​

Collaboration and Independent Work Policy

It is NOT acceptable:

• To copy solutions from other students.
• To copy (or start your) solutions from the Web.
• To be irresponsible and create opportunities for unscrupulous students (e.g., public GitHubs, walking away while logged on, leaving notes around, etc.).

You are encouraged to help teach others to debug.

• Beyond that, we don’t want you sharing approaches or ideas or code or whiteboarding with other students. The "pseudocode/algorithm” is sometimes the entire point!
• HKN/tutoring working through pseudocode are not allowed.
• On Ed: Answer questions that help classmates debug. Don’t share code, nor code snippets.

We expect that what you hand in is yours.

​

Yan, SP26

01-Course Introduction (49)

​

Collaboration and Independent Work Policy

Assignment Collaboration:

• All homework and labs are to be your work ALONE.
• Projects can be done either solo or in pairs.
• Partners commit to responsibility to working synchronously with each other, not other partner teams.

Yan, SP26

01-Course Introduction (50)

​

Excessive Collaboration and Academic Misconduct

We have tools, developed over many years, for detecting this. You WILL be caught, and the penalties WILL be severe. If you have questions whether a behavior is crossing the line, ask!

• At minimum: negative points in the assignment AND a report to the Center of Student Conduct.
• Both Giver and Receiver are equally culpable and suffer equal penalties.

50-100 students are caught every semester.

• We also check intermediate student work—accounted for 60% of Fall 2023 cases.
• Plagiarism at any point in your work is unacceptable.

Yan, SP26

01-Course Introduction (51)

​

What about working with AI?

• Acceptable uses of AI
• “Teach me <CS61C topic>”
• Try: “teach it to me as if I were in grade school” (then middle school → high school → college) if lost to get big ideas first.
• “Do you have any mnemonics to help me remember X?”
• “Generate some exam problems for me to practice”
• “Can you teach me debugging techniques for C or RISC-V?”

​

• Unacceptable uses of AI (and Googling and other people)
• “Here’s the project prompt, please do it for me”
• “Write this function for me”
• “Here’s my broken code, debug it for me”

Yan, SP26

01-Course Introduction (52)

​

Finally: Our goals as instructors

With all of that said—you will have plenty of opportunities to demonstrate success.

• Our ultimate goal is for you to learn the material, not to stress you out.
• If you are feeling lost, please reach out. It is much better to do so than to violate our trust. We are in this together!

To make your experience in CS61C as enjoyable & informative as possible

• Humor, enthusiasm, guests, technology-in-the-news
• Fun, challenging projects & HW
• Pro-student accommodations policies
• Peer discussion opportunities in section, learn how to learn

To maintain Cal standards of excellence

• Projects & exams as rigorous as every year.

Yan, SP26

01-Course Introduction (53)

​

Welcome to CS61C!!!

CS61C: Learn 6 great ideas in computer architecture to enable high performance programming via parallelism, not just learn C.

1. Abstraction (Layers of Representation / Interpretation)
2. Moore’s Law
3. Principle of Locality/Memory Hierarchy
4. Parallelism
5. Performance Measurement and Improvement
6. Dependability via Redundancy

Yan, SP26

01-Course Introduction (54)

​