New User Special Price Expires in

Let's log you in.

Sign in with Facebook


Don't have a StudySoup account? Create one here!


Create a StudySoup account

Be part of our community, it's free to join!

Sign up with Facebook


Create your account
By creating an account you agree to StudySoup's terms and conditions and privacy policy

Already have a StudySoup account? Login here

Lecture 1 & 2 (August 12 & 14, 2015)

by: Andreas

Lecture 1 & 2 (August 12 & 14, 2015) CZ3001, CE3001

GPA 4.56
Advanced Computer Architecture
Chng Kee Wah, Kavallur Pisharath Gopi Smitha, Leong Yin Yoke Junie, Pramod Kumar Meher

Almost Ready


These notes were just uploaded, and will be ready to view shortly.

Purchase these notes here, or revisit this page.

Either way, we'll remind you when they're ready :)

Preview These Notes for FREE

Get a free preview of these Notes, just enter your email below.

Unlock Preview
Unlock Preview

Preview these materials now for free

Why put in your email? Get access to more of this material and other relevant free materials for your school

View Preview

About this Document

Advanced Computer Architecture
Chng Kee Wah, Kavallur Pisharath Gopi Smitha, Leong Yin Yoke Junie, Pramod Kumar Meher
Class Notes
25 ?




Popular in Advanced Computer Architecture

Popular in Computer Science and Engineering

This 8 page Class Notes was uploaded by Andreas on Thursday September 17, 2015. The Class Notes belongs to CZ3001, CE3001 at Nanyang Technological University taught by Chng Kee Wah, Kavallur Pisharath Gopi Smitha, Leong Yin Yoke Junie, Pramod Kumar Meher in Summer 2015. Since its upload, it has received 617 views. For similar materials see Advanced Computer Architecture in Computer Science and Engineering at Nanyang Technological University.

Similar to CZ3001, CE3001 at NTU

Popular in Computer Science and Engineering


Reviews for Lecture 1 & 2 (August 12 & 14, 2015)


Report this Material


What is Karma?


Karma is the currency of StudySoup.

You can buy or earn more Karma at anytime and redeem it for class notes, study guides, flashcards, and more!

Date Created: 09/17/15
Introduction 5 basic hardware of computer ALU gt performs arithmetic and logical operations Control unit gt generates control signals for various functions load read write data to and from registersmemory and perform ALU operation etc ALU control unit register CPU Memory gt main and secondary memory onemultiple level cache etc IO peripherals gt mouse screen speakers keyboard etc Computer architecture concerns about design and implementation of computer hardware at different levels It specifies from broad to specific Hardware components gt functionality and interconnections system architecture Instruction sets gt programmer needs to understand the meaning in order to write a correct and efficient program instructionset architectureISA o How the instruction work 0 What are the requirements Implementation of ISA gt execution of instructions in hardware microarchitecturecomputer organization Instruction cycle Fetch gt fetch from memory get ready to fetch the next one Decode gt decode instruction fetch operands Execute gt perform ALU operation Memory access gt perform load readstore write data Write back gt write the calculated result back to register file Reason to increase computer speed Increase user convenience gt better GUI more complex software more volume of data Increase transmission speed and bandwidth Increase resolution of imagevideo Increase security need gt 128 to 1024 bit Moore s law 0 Number of transistors in IC doubles around every 2 years 0 After every 10 years gt 30 times more transistors 0 Computer architecture should be designed accordingly to maximize the use of every transistors Power consumption 0 Transistors is smaller and faster 0 Higher performance caused more power consumption 0 Use parallel processing and pipeline Key features Main goals gt increase performance reduce power consumption Memory hierarchy gt efficient cache faster and costeffective Pipeline pipeline datapath and parallel instruction execution VLIW superscalarmultiissue processors Data parallel computing GPU vector SIMDsingle instruction multiple data machines Multicore processors heterogeneous multiprocessor systems on chip Custom computing and domainspecific architecture specialize to do certain task gt mixed up different type of technology ASICapplicationspecific integrated circuit FPGA general purpose processor Performance Execution time CPU time 0 Time involved in executing certain number of instructions 0 Usual choice for indicate processor performance 0 Reciprocal of performance gt performance 1execution time 0 Instruction count x CPI x clock period Higher performance gt shorter clock period higher clock frequency more CPI cycle per instruction lower execution time Each instruction might not require the same amount of CPI Average CPI sum of CPI of each category x instruction count for each category total number of instruction 91715 842 PM Performance Execution time Instruction count x Average CPI x time If ICkIC wk is the weight of instructions of category k average CPI sum of wkx CPIk for k ranging from 1 to n for n number of categories of instructions Execution time is affected by 0 Clock period 0 Semiconductor technology gt small and faster chip 0 Data path design and implementation whole computing circuits gt better circuit more efficient data path 0 Instruction count 0 Program application how complex the instructions are gt use simpler algorithm 0 ISA different types of instructions available how to execute the instructions gt nearer operand CISC gt less instructions more clock period required RISC gt more instructions less clock period required 0 ISA gt RISC has less CPI than CISC 1 CPI 0 Data path design Multicycle data path CPI gt 1 Pipelined data path minimum CPI 1 Parallel data path VLIWsuperscalar processors SIMD and multicore processors gt tasklevel parallelism can be implemented CPI lt 1 0 Parallel and pipelined hardware design gt reduce CPI Decrease in one may lead to increase in the other two 0 Goal gt increase instructions as necessary but results in overall lower CPI Performance enhancement challenges 0 Clock period reduction increase in clock frequency 0 CPI possibly and power consumption increases 0 Memory operations may be longer than a clock period memorywall problem 0 IC reduction 0 CISC more complex instructions gt clock period increase 0 Multiissues processors gt VLIWsuperscalar processors SIMD and vector processor 0 CPI reduction 0 Instruction pipeline 0 Multicore processing gt threadlevel parallelism Amdahls law Speedup via parallelism is limited by that component of an application which cannot be enhanced sequential component Speedup execution time in base computer execution time in rated computer execution time before enhancement execution time after enhancement Time required for unenhanced fraction T x 1 enhanced fraction Time required for enhanced fraction T x enhanced fraction enhancement factor Total time T x 1 enhanced fraction x enhancement factor 1 enhancement factor If enhancement factor is very large total time T x unenhanced fraction gt maximum speedup 1unenhanced fraction MIPS FLOPS MIPS Million of instructions per second Nativesimple MIPS instruction count execution time x 106 Peak MIPS 0 Choosing a sequence of instructions instruction mix which give the maximum possible MIPS even if it is impractical or not used 0 Vary between each types of instructions and types of computers Relative MIPS 0 Estimated relative to a reference machine 0 Referenced execution time x referenced MIPS rated execution time 0 Useful to rate designs of the same computer Varies with ISA complexity CPI etc and choice of instruction mix program Doesn t correlate directly with quality of performance Floatingpoint operations per seconds megaFLOPS 106 FLOPS gigaFLOPS 1012 FLOPS teraFLOPS 1015 FLOPS petaFLOPS 1018 FLOPS etc Usually used for scientific research machines China Tianhe2 supercomputer gt currently the fastest 3386 petaFLOPS IBM Blue GeneL supercomputer gt 596 teraFLOPS


Buy Material

Are you sure you want to buy this material for

25 Karma

Buy Material

BOOM! Enjoy Your Free Notes!

We've added these Notes to your profile, click here to view them now.


You're already Subscribed!

Looks like you've already subscribed to StudySoup, you won't need to purchase another subscription to get this material. To access this material simply click 'View Full Document'

Why people love StudySoup

Bentley McCaw University of Florida

"I was shooting for a perfect 4.0 GPA this semester. Having StudySoup as a study aid was critical to helping me achieve my goal...and I nailed it!"

Janice Dongeun University of Washington

"I used the money I made selling my notes & study guides to pay for spring break in Olympia, Washington...which was Sweet!"

Steve Martinelli UC Los Angeles

"There's no way I would have passed my Organic Chemistry class this semester without the notes and study guides I got from StudySoup."


"Their 'Elite Notetakers' are making over $1,200/month in sales by creating high quality content that helps their classmates in a time of need."

Become an Elite Notetaker and start selling your notes online!

Refund Policy


All subscriptions to StudySoup are paid in full at the time of subscribing. To change your credit card information or to cancel your subscription, go to "Edit Settings". All credit card information will be available there. If you should decide to cancel your subscription, it will continue to be valid until the next payment period, as all payments for the current period were made in advance. For special circumstances, please email


StudySoup has more than 1 million course-specific study resources to help students study smarter. If you’re having trouble finding what you’re looking for, our customer support team can help you find what you need! Feel free to contact them here:

Recurring Subscriptions: If you have canceled your recurring subscription on the day of renewal and have not downloaded any documents, you may request a refund by submitting an email to

Satisfaction Guarantee: If you’re not satisfied with your subscription, you can contact us for further help. Contact must be made within 3 business days of your subscription purchase and your refund request will be subject for review.

Please Note: Refunds can never be provided more than 30 days after the initial purchase date regardless of your activity on the site.