关于此课程： In this course, you will learn to design the computer architecture of complex modern microprocessors.
制作方： 普林斯顿大学
教学方： David Wentzlaff , Assistant Professor
Electrical Engineering
| 级别 | Advanced |
| 语言 | English |
| 如何通过 | 通过所有计分作业以完成课程。 |
| 用户评分 |
授课大纲
第 1 周
Introduction, Instruction Set Architecture, and Microcode
This lecture will give you a broad overview of the course, as well as the description of architecture, micro-architecture and instruction set architectures.
8 视频, 2 阅读材料
- 视频: Course Introduction
- Reading: Readings
- 视频: Course Overview
- 视频: Motivation
- 视频: Course Content
- 视频: Architecture and Microarchitecture
- 视频: Machine Models
- 视频: ISA Characteristics
- 视频: Recap
- Reading: Problem Set 1 & 1A
Pipelining Review
This lecture covers the basic concept of pipeline and two different types of hazards.
4 视频, 1 阅读材料
- Reading: Readings
- 视频: Microcoded Microarchitecture
- 视频: Pipeline Basics
- 视频: Structural Hazard
- 视频: Data Hazards
第 2 周
Cache Review
This lecture covers control hazards and the motivation for caches.
5 视频, 1 阅读材料
- Reading: Readings
- 视频: Control Hazards, Jumps
- 视频: Control Hazards, Branch
- 视频: Control Hazards, Others
- 视频: Memory Technologies
- 视频: Motivation for Caches
Superscalar 1
This lecture covers cache characteristics and basic superscalar architecture.
5 视频, 1 阅读材料
- Reading: Readings
- 视频: Classifying Caches
- 视频: Cache Performance
- 视频: Superscalar 1
- 视频: Basic Two-way In-order Superscalar
- 视频: Fetch Logic and Alignment
第 3 周
Superscalar 2 & Exceptions
This lecture covers the common issues for superscalar architecture.
4 视频, 1 阅读材料
- Reading: Readings
- 视频: Baseline Superscalar and Alignment
- 视频: Interrupts and Bypassing
- 视频: Interrupts and Exceptions
- 视频: Introduction to Out-of-Order Processors
Superscalar 3
This lecture covers different kinds of architectures for out-of-order processors.
5 视频, 2 阅读材料
- 视频: Review of Out-of-Order Processors
- 视频: I2O2 Processors
- 视频: I2O1 Processors
- 视频: IO3 Processors
- 视频: IO2I Processors
- Reading: Problem Set 2
- Reading: Problem Set 1 Solutions
第 4 周
Superscalar 4
This lecture covers the common methods used to improve the performance of out-of-order processors including register renaming and memory disambiguation.
5 视频
- 视频: Speculation and Branch
- 视频: Register Renaming Introduction
- 视频: Register Renaming with Pointers to IQ and ROB
- 视频: Register Renaming with Values in IQ and ROB
- 视频: Memory Disambiguation
VLIW 1
This lecture covers the basic concept of very long instruction word (VLIW) processors.
5 视频, 3 阅读材料
- Reading: Readings
- 视频: Limits of Out-of-Order Design Complexity
- 视频: Introduction to VLIW
- 视频: VLIW Compiler Optimizations
- 视频: Classic VLIW Challenges
- 视频: Introduction to Predication
- Reading: Problem Set 3
- Reading: Problem Set 2 Solutions
第 5 周
VLIW2
This lecture covers the common methods used to improve VLIW performance.
6 视频, 1 阅读材料
- Reading: Readings
- 视频: Scheduling Model Review
- 视频: Review of Predication
- 视频: Predication Implementation
- 视频: Speculation Execution
- 视频: Dynamic Events and Clustered VLIWs
- 视频: Case Study: IA-64/Itanium
已评分: Midterm
Branch Prediction
This lecture covers the motivation and implementation of branch predictors.
5 视频, 1 阅读材料
- Reading: Readings
- 视频: Branch Cost Motivation
- 视频: Branch Prediction Introduction
- 视频: Static Outcome Prediction
- 视频: Dynamic Outcome Prediction
- 视频: Target Address Prediction
第 6 周
Advanced Caches 1
This lecture covers the advanced mechanisms used to improve cache performance.
6 视频, 1 阅读材料
- Reading: Readings
- 视频: Basic Cache Optimizations
- 视频: Cache Pipelining
- 视频: Write Buffers
- 视频: Multilevel Caches
- 视频: Victim Caches
- 视频: Prefetching
Advanced Caches 2
This lecture covers more advanced mechanisms used to improve cache performance.
4 视频, 2 阅读材料
- Reading: Readings
- 视频: Multiporting and Banking
- 视频: Software Memory Optimizations
- 视频: Non-blocking Caches
- 视频: Critical Word First and Early Restart
- Reading: Problem Set 3 Solutions
第 7 周
Memory Protection
This lecture covers memory management and protection.
5 视频, 2 阅读材料
- Reading: Readings
- 视频: Memory Management Introduction
- 视频: Base and Bound Registers
- 视频: Page Based Memory Systems
- 视频: Translation and Protection
- 视频: TLB Processing
- Reading: Problem Set 4 & 4A
Vector Processors and GPUs
This lecture covers the vector processor and optimizations for vector processors.
6 视频, 1 阅读材料
- Reading: Readings
- 视频: Address Translation Review
- 视频: Cache and Memory Protection Interaction
- 视频: Vector Processor Introduction
- 视频: Vector Parallelism
- 视频: Vector Hardware Optimizations
- 视频: Vector Software and Compiler Optimizations
第 8 周
Multithreading
This lecture covers different types of multithreading.
6 视频, 1 阅读材料
- Reading: Readings
- 视频: Reduction, Scatter/Gather, and the Cray 1
- 视频: SIMD
- 视频: GPUs
- 视频: Multithreading Motivation
- 视频: Coarse-Grain Multithreading
- 视频: Simultaneous Multithreading
Parallel Programming 1
This lecture covers the concepts of parallelism, consistency models, and basic parallel programming techniques.
4 视频, 1 阅读材料
- Reading: Readings
- 视频: SMT Implementation
- 视频: Introduction to Parallelism
- 视频: Sequential Consistency
- 视频: Introduction to Locks
第 9 周
Parallel Programming 2
This lecture covers the solutions for the consistency problem in parallel programming.
5 视频
- 视频: Sequential Consistency Review
- 视频: Locks and Semaphores
- 视频: Atomic Operations
- 视频: Memory Fences
- 视频: Dekker's Algorithm
Small Multiprocessors
This lecture covers the implementation of small multiprocessors.
5 视频, 2 阅读材料
- Reading: Readings
- 视频: Locking Review
- 视频: Bus Implementation
- 视频: Cache Coherence
- 视频: Bus-Based Multiprocessors
- 视频: Cache Coherence Protocols
- Reading: Problem Set 4 Solutions
第 10 周
Multiprocessor Interconnect 1
This lecture covers the design of interconnects for a multiprocessor.
4 视频, 2 阅读材料
- Reading: Readings
- 视频: More Cache Coherence Protocols
- 视频: Introduction to Interconnection Networks
- 视频: Message Passing
- 视频: Interconnect Design
- Reading: Problem Set 5 & 5A
Multiprocessor Interconnect 2
This lecture covers the design of interconnects for multiprocessor and network topology.
5 视频, 1 阅读材料
- Reading: Readings
- 视频: Networking Review
- 视频: Topology
- 视频: Topology Parameters
- 视频: Network Performance
- 视频: Routing and Flow Control
第 11 周
Large Multiprocessors (Directory Protocols)
This lecture covers the motivation and implementation of directory protocol used for coherence on large multiproccesors.
6 视频, 2 阅读材料
- Reading: Readings
- 视频: Credit Based Flow Control
- 视频: Deadlock
- 视频: False Sharing
- 视频: Introduction to Directory Coherence
- 视频: Implementation
- 视频: Scalability of Directory Coherence
- Reading: Problem Set 5 Solutions
已评分: Final Exam
常见问题解答
运作方式
Coursework
Each course is like an interactive textbook, featuring pre-recorded videos, quizzes and projects.
Help from Your Peers
Connect with thousands of other learners and debate ideas, discuss course material, and get help mastering concepts.
制作方
普林斯顿大学
Princeton University is a private research university located in Princeton, New Jersey, United States. It is one of the eight universities of the Ivy League, and one of the nine Colonial Colleges founded before the American Revolution.
评分和审阅
Just great!
NICE
Thank you, you course is greate.
But:
1) Difficult to study from a cellar phone.
2) I would choose another assembler
The course presents advanced material, not easily found elsewhere. Labs would have definitely facilitated the learning in this case and I hope they will be added in the future.