慶應義塾大学
2011年度 秋学期
コンピューター・アーキテクチャ
Computer Architecture
第2回 10月07日 Lecture 2, October 07:
Faster!
Outline of This Lecture
- What's a Computer?
コンピュータって、何?
- What's in a Computer's Guts?
コンピュータの内蔵は?
- Fundamentals of Computer Design
コンピュータデザインの基礎
- Introduction
- Technology Trends
- Quantitative Principles of Design
定量的なデザイン概念
- Homework/課題
Contacting Me/Office Hours
連絡先/オフィスアワー
If you need to contact me, email is the preferred method. Please put
"COMP-ARCH:" in the Subject field of the email. If I do not respond to a
query within 24 hours, please resend. For more urgent matters, junsec
should know how to get ahold of me.
Office Hours, Fall 2011秋のオフィスアウアー:Wednesday (水曜日),
9-12, Delta N211. You may come to my office during this time without
an appointment. If you wish to see me otherwise, you can attempt to
find me directly, or send me email to arrange an appointment.
What's a Computer?
What's in a Computer?
(Here's the fun part...)
Our computer
定量てきなデザイン概念
Quantitative Principles of Design
Last time, we talked about Hennessy & Patterson's Five Principles:
- Take Advantage of Parallelism
- Principle of Locality
- Focus on the Common Case
- Amdahl's Law
- The Processor Performance Equation
I would add to this one imperative: Achieve Balance.
Take Advantage of Parallelism
Parallelism can be found by using multiple processors on different
parts of the problem, or multiple functional units (floating point
units, disk drives, etc.), or by pipelining, dividing an
individual computer instruction into several parts and executing the
parts of different instructions at the same time in different parts of
the CPU.
Principle of Locality
Programs and data tend to reuse data and instructions that have been
recently used. There are two forms of locality: spatial
and temporal. Locality is what allows a cache memory to
work.
Focus on the Common Case
The things that are done a lot should be fast; the things that are
rare may be slow.
Amdahl's Law
Amdahl's Law tells us how much improvement is possible by
making the common case fast, or by parallelizing part of the
algorithm. In the example below, 3/5 of the algorithm can be
parallelized, meaning that three times as much hardware applied to the
problem gains us only a reduction from five time units to three.
Some problems, most famously graphics, are known as "embarrassingly
parallel" problems, in which extracting parallelism is trivial, and
performance is primarily determined by input/output bandwidth and the
number of processing elements available. More generally, the
parallelism achievable is determined by the dependency graph.
Creating that graph and scheduling operations to maximize the
parallelism and enforce correctness is generally the shared
responsibility of the hardware architecture and the compiler.
プロセッサー・パフォマンス定式
The Processor Performance Equation
CPU time = |
(seconds
)/
program
|
= |
(Instructions
)/
program
|
× |
(Clock cycles
)/
Instruction
|
× |
(Seconds
)/
Clock cycle
|
宿題
Homework
Last week, the assignment was to recreate the graphs shown in
class. Probably, that assignment was alarmingly vague. The
description on SFC-SFS should be better now.
The source you need, including script files, are available in a
tar file here.
n.b.: Some of the parameters in the code have changed from what
was online last week!!! Please use this version.
The specification for OpenMP, and a "summary card" for C and C++,
are
available here.
The latest version is 3.1, but there is a Japanese version of the
3.0 spec available. 最新のバージョンは3.1だが、3.0の日本語版はあり
ますよ!
This week's homework (submit via SFS, due 10/21):
- Change the compiler from gcc
to icc, Intel's C compiler. Replot the data,
putting both sets of data (gcc and icc) on the plot. How
much faster does it get? Is the speedup the same for all
problem sizes?
- In architecture/src/qulib/sim.c, you will find the
functions cnot() and Hadamard(). In the
statement
/* XXX parallelizing this loop is tricky, but it's a "big" loop, so worth doing... */
#pragma omp parallel for schedule(static,8192) private(j,k,z)
the number 8192 indicates the size of the chunk of the large array
that each thread executes. Change that number both smaller and larger
in both functions to see the effects. Save these as separate
data sets, and plot them
all together on one plot.
- First, eliminate the "schedule" altogether; try it with
#pragma omp parallel for private(j,k,z)
- Next, try it with schedule(static,16).
- schedule(static,256).
- schedule(static,1024).
- schedule(static,4096).
- schedule(static,16384).
- By now, you should have some idea of what values will work
well. Choose the optimal value for the schedule size for
this application and machine.
- Read the text for next week.
Next Lecture
Next lecture:
第3回 10月14日 プロセッサー:命令の基本
Lecture 3, October 14: Processors: Basics of Instruction Sets
以下で、P-Hはコンピュータの構成と設計~ハードウエアとソフトウエアの
インタフェース 第3版、
H-Pはコンピュータアーキテクチャ 定量的アプローチ 第4版.
Below, P-H is Computer Organization and Design: The
Hardware-Software Interface, and H-P is Computer Architecture:
A Quantitative Approach.
Readings for next time:
- Follow-up from this lecture:
- P-H: Chapter 1
- H-P: Chapter 1.1 - 1.12
- For next time:
Additional Information
その他