NotesForMidterm2 - time spent executing actual instructions...

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon
MULTIPLICATION AND DIVISION Binary Multiplication × 0 1 0 0 0 1 0 1 Multiplication Implementation Division PERFORMANCE Throughput – How many results per clock? How many results can be processed per second? What is the average execution rate of my program?
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
How much work (latency) is getting done? Latency – clocks from input to corresponding output How long does it take for my program to run? How long must I wait after typing return for the result? An upgrade with a faster processor improves throughput Design Tradeoffs Maximum Performance (instructions per second) Minimum Cost (size of circuit) Best Performance/Price(ration of MIPS to size) Execution Time – Elapsed Time/Wall Clock Time Counts everything (disk and memory accesses, I/O, etc.) A useful number, but often not good for comparison purposes CPU time – Doesn’t include I/O or time spent running other programs Can be broken up into system time and user time Instruction Count * CPI / Clock Rate Our Focus: User CPU Time
Background image of page 2
Background image of page 3
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: time spent executing actual instructions of our program Performance Performance = Program Executions/Time (executions/sec) X is n times faster than Y means Performance X / Performance Y = n Clock Cycles Cycle Time time between ticks = seconds per cycle Clock Rate cycles per second (frequency) Computer Performance Measure How To Improve Performance cycle time (seconds per cycle) clock rate (cycles per second) CPI (average clocks per instruction) a floating point intensive application might have a higher CPI MIPS (millions of instructions per second) this would be higher for a program using simple instructions CPI Freq IPS M = cycle second program cycles program seconds = Benchmarks Performance best determined by running a real application SPEC (System Performance Evaluation Cooperative) Amdahls Law unaffecte speedup affected improved t r t t + =...
View Full Document

This note was uploaded on 01/27/2012 for the course COMP 411 taught by Professor Singh during the Fall '08 term at UNC.

Page1 / 3

NotesForMidterm2 - time spent executing actual instructions...

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online