Document information
- University
- Politecnico di Milano
- Degree programme
- Computer Engineering
- Subject
- Advanced Computer Architectures
- Academic year
- 2020-2021
- Classification
- Exam · Full exam
- Content
- Exam paper only
- Original format
- Text
- Searchable text
Full exam for Advanced Computer Architectures in the Computer Engineering degree programme at Politecnico di Milano. The document covers: Dipartimento di Elettronica e Informazione Politecnico di Milano 20133 Milano (Italia) Piazza Leonardo da Vinci, 32 Tel. (+39) 02-2399.3400 Fax (+39) 02-2399.3411 Advanced Computer Architecture June 09, 2021 Prof. Marco Santambrogio Name Last Name Pick 2 out of th 3 problems, DO
Full exam for Advanced Computer Architectures in the Computer Engineering degree programme at Politecnico di Milano. The document covers: Dipartimento di Elettronica e Informazione Politecnico di Milano 20133 Milano (Italia) Piazza Leonardo da Vinci, 32 Tel. (+39) 02-2399.3400 Fax (+39) 02-2399.3411 Advanced Computer Architecture June 09, 2021 Prof. Marco Santambrogio Name Last Name Pick 2 out of th 3 problems, DO
Import quality: text was extracted directly from the original document.
Representative passages recognised in different parts of the material. The full extracted text remains available to search, while this compact preview makes the page easier to read.
Dipartimento di Elettronica e Informazione Politecnico di Milano 20133 Milano (Italia) Piazza Leonardo da Vinci, 32 Tel. (+39) 02-2399.3400 Fax (+39) 02-2399.3411 Advanced Computer Architecture June 09, 2021 Prof. Marco Santambrogio Name Last Name Pick 2 out of th 3 problems, DO NOT DO ALL THE 3! Questions (from Forms) (20%) Problem 1 (40%) Problem 2 (40%) Problem 3 (40%) Total (100%) Problem 1 Assume that the following code is executed on a CPU with SCOREBOARD and with the following units: 1 LOAD/STORE unit with Latency= 1 2 MULT units with latency = 10 1 DIVIDE unit with latency = 30 1 ADD/SUBD unit with latency 2 Issue Read Op Exec Co. Write R. LD F6 32+ R2 1 2 3 4 LD F2 45+ R3 5 6 7 8 MULTD F0 F4 F2 6 9 19 20 ADD F8 F2 F6 7 9 10 11 DIVD F12 F8 F0 8 21 51 52 SUBD F8 F6 F2 9 13 14 15 A. List all the possible conflicts in the code. B. Is there a “configuration” that can respect the shown execution? How many units? Which kind? What latency? C. If the previous table was not correct, please, write the right one by having: 1 LOAD: 1cc 2 MULT: 10cc 1 DIVL 30cc 3 ADD/SUB: 1cc Answer 1.A 1 LDU 1 CC 2 MULT 10 1 DIV 30 1 ADD/SUB 2 RAW F6 I1-I4 RAW F6 I1-I6 RAW F2 I2-I3 RAW F2 I2-I4 RAW F2 I2-I6 RAW F0 I3-I5 RAW F8 I4-I5 WAR F8 I5-I6 WAW F8 I4-I5 Answer 1.B Answer 1.C Issue Read Op Exec Co. Write R. LD F6 32+ R2 LD F2 45+ R3 MULTD F0 F4 F2 ADD F8 F2 F6 DIVD F12 F8 F0 SUBD F8 F6 F2 1 2 3 4 5 6 7 8 6 9 7 9 19 10 20 11 8 21 51 52 12 13 14 22 No for several reasons, among which WAW and WAR unsolved, and the given latency of the FU is not respected. One of those is enough to say that no. Problem 2 Consider the following access pattern on a two-processor system with a direct-mapped, write-back cache with one cache block and a two cache block memory. Assume the MESI protocol is used,…
First page of the document.