Homework
From CS252
←Older revision | Newer revision→
Homework 7 - Due Saturday, 4/15/06 10pm PST
(Homework 7 Responses will be available here)
1. Read "A Case for Redundant Arrays of Inexpensive Disks (RAID)" by David Patterson, Garth Gibson and Randy Katz (available in papers section of wiki).
Comment on the following:
- What was main motivation for RAID in paper?
- Did prediction of processor performance and disk capacity hold?
- How propose balance performance and capacity of RAID 1 to RAID 5? What do you think of it?
- What were some of the open issues? Which were significant
- In retrospect, what do you think were important contributions? What did the authors get wrong?
2. Complete problem set linked here in pairs.
Homework 6 - Due Tuesday, 4/4/06 10pm PST
(Homework 6 Responses are available here)
Read "Virtual Machine Monitors: Current Technology and Future Trends" by Mendel Rosenblum and Tal Garfinkel (available in papers section of wiki).
Comment on the following:
- How old are VMs? Why did it lie fallow so long?
- Why do authors say this old technology got hot again?
- What are 3 main implementation issues, and their key
challenges , techniques , and future support opportunities?
- What important role do you think VMs will play in the future
Information Technology? Why?
Homework 5 - Due Friday, 3/10/06 10pm PST
(Homework 5 Responses are available here)
1. Read "Validity of the Single Processor Approach to Achieving Large-Scale Computing Capabilities" by Gene Amdahl (available in Papers section of wiki).
Comment on the following:
- How long is paper? How much of it is Amdahl’s Law?
- What other comments about parallelism besides Amdahl’s Law?
2. Read "Parallel Programmer Productivity: A Case Study of Novice Parallel Programmers" by Hochstein et al (available in Papers section of wiki).
Comment on the following:
- What programming styles were investigated?
- What was methodology?
- How would you redesign the experiment they did?
- What other metrics would be important to capture?
- Assuming these results of programming productivity reflect the real world, what should architectures of the future do (or not do)?
3. Complete problem set linked here in pairs.
Homework 4 - Due Monday, 2/27/06 10pm PST
(Homework 4 Responses are available here)
1. Read "The CRAY-1 computer system" by R.M. Russell, Comm. of the ACM, January 1978. (available in Papers section of wiki)
Comment on the following:
- vector vs. scalar speed
- min. size vector faster than scalar loop
- relative speed to other computers
- clock rate, size of register state, memory size, number of functional units,
and general impressions compared to today’s CPUs
2. Complete problem set linked here in pairs. (due Wednesday 3/1/06 by 10pm)
Homework 3 - Due Friday, 2/17/06 10pm PST
(Homework 3 Responses are available here)
1. Complete the problem set linked here in pairs.
2. Read "Simultaneous Multithreading: A Platform for Next Generation Processors", by Susan Eggers et al. (available in Papers section of wiki)
Comment on the following:
- What assumption were made about computer organization before adding SMT?
- How does it compare to Wall’s claims of ILP limits?
- What changes were made to add SMT?
- What performance advantages are claimed? For what workloads?
Homework 2 - Due Friday, 2/10/06 10pm PST
(Homework 2 Responses are available here)
Read “Limits of instruction-level parallelism,” by David Wall, Nov 1993 (available in Papers section of wiki)
Read pages 1-35 (about ½ of paper is figures).
- In your comments, rank in order of importance alias analysis, branch
prediction, jump prediction, register renaming, and speculative execution
- Mention what are limits to this study of limits of ILP
Email your comments to archanag@cs by Friday. Responses will be posted on Saturday. Review other responses before discussion on Monday.
Homework 1 - Due Friday, 2/3/06 10pm PST
(Homework 1 Responses are available here)
Read the following papers (available in Papers section of wiki):
- Architecture of the IBM System/360 - G.M. Amdahl, G.A. Blaauw and F.P. Brooks Jr.
- Design of the B 5000 System - William Lonergan and Paul King
- The Case for the Reduced Instruction Set Computer - Patterson and Ditzel
- Comments on "The Case for the Reduced Instruction Set Computer," by Patterson and Ditzel - Douglas W. Clark and William D. Strecker
Comment on the papers, specifically addressing (but not limited to):
- B5000 (1961) vs. IBM 360 (1964)
- What key different architecture decisions did they make? E.g., data size, floating point size, instruction size, registers, …
- Which largely survive to this day in current ISAs? In JVM?
- RISC vs. CISC (1980)
- What arguments were made for and against RISC and CISC?
- Which has history settled?
E-mail your comments in text format to archanag@cs AND pattrsn@cs
