Homework 13 - Answers

docx

School

University of Minnesota-Twin Cities *

*We aren’t endorsed by this school

Course

232

Subject

Computer Science

Date

Dec 6, 2023

Type

docx

Pages

4

Uploaded by AgentNewt551

Report
ICS 232 Computer Organization & Architecture Homework 13 - Chapter 9 - 10 points Due Date: 8/11/2022 Name: Key Note: Please post your homework to ICS232 D2L on or before the due date. Chapter 9 – Alternative Architectures Essential Terms and Concepts 3. Describe how register windowing makes procedure call more efficient? Storing parameters in registers is much faster than storing them in the stack. Therefore, the speed of procedures call can be improved. 7. Do all programming problems lend themselves to parallel execution? What is the limiting factor? No. Many times serial execution is required to merge data from parallel tasks. 12. Explain the limitation inherent in a register-register vector processing machine? The number of registers limits the number of elements that can be processed at one time. 13. Give two reasons for the efficiency of vector processors. Fewer instructions are executed and there is a continuous source of data so pre-fetching can occur. 21. What is reentrant code? The same code can be executed at the same time by multiple threads. Exercises 1. Why do RISC machines operate on registers?
ICS 232 Computer Organization & Architecture Homework 13 - Chapter 9 - 10 points Due Date: 8/11/2022 RISC machines limit the instructions that can access memory to load and store instructions only. This means that all other instructions use registers. This requires fewer cycles and speeds up the execution of the code and, thus, the performance of the hardware. The goal for RISC architectures is to achieve single-cycle instructions, which would not be possible if instructions had to access memory instead of registers. 4. Suppose a RISC machine uses overlapping register windows with: • 10 global registers • 6 input parameter registers • 10 local registers • 6 output parameter registers How large is each overlapping register window? 6 6. A RISC processor has 152 total registers, with 12 designated as global registers. The 10 register windows each have 6 input registers and 6 output registers. How many local registers are in each register window set? HINT: Remember, due to the circular nature of the windows, the output registers of the last window are shared as the input registers of the first window. 152 = 12 + 10 x (local + 6) local = 8 9. Recall our discussions from Chapter 8 regarding context switches. These occur when one process stops using the CPU and another process begins. In this sense, register windows could be viewed as a potential weakness of RISC. Explain why this is the case. During a context switch, all information about the currently executing process must be saved, including the values in the register windows. When the process is restored, the values in the register windows must be restored as well. Depending on the size of the windows, this could be a very time-consuming process.
ICS 232 Computer Organization & Architecture Homework 13 - Chapter 9 - 10 points Due Date: 8/11/2022 13. Explain the difference between loosely coupled and tightly coupled architectures. Loosely coupled and tightly coupled are terms that describe how multiprocessors deal with memory. If there is one large, centralized, shared memory, we say the system is tightly coupled. If there are multiple, physically distributed memories, we say the system is loosely coupled. 21. Why are distributed systems desirable? Distributed systems allow for resource sharing (such as sharing of printers and files), and thus, can reduce system cost. They also allow for redundancy, which increases reliability (if one site fails, the remaining sites can still function). These systems also speed up computation, as jobs can be distributed and run concurrently at many sites. Lastly, distributed systems run programs that, due to the nature of the system, can share data with other systems more easily via the communications network and communicate with remote sites. 28. Compare and contrast supervised learning and unsupervised learning with regard to neural networks. Supervised learning assumes that for each input, the output is known a priori. In unsupervised learning, no outputs are known in advance. 33. Indicate whether each of the following applies to CISC or RISC by placing either a C (for CISC) or an R (for RISC) in the blank. __ R __ 1. Simple instructions averaging 1 clock cycle to execute __ C __ 2. Single register set __ R __ 3. Complexity is in the compiler __ R __ 4. Highly pipelined __ C __ 5. Any instruction can reference memory __ C __ 6. Instructions are interpreted by the microprogram __ R __ 7. Fixed length, easily decoded instruction format __ C __ 8. Highly specialized, infrequently used instructions __ R __ 9. Use of overlapping register windows
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
  • Access to all documents
  • Unlimited textbook solutions
  • 24/7 expert homework help
ICS 232 Computer Organization & Architecture Homework 13 - Chapter 9 - 10 points Due Date: 8/11/2022 __ R __ 10. Relatively few addressing modes Prepare for Final Exam Complete Project 2 Continue working on Your Group Project Continue working on Homework 14 (Bonus)