Why is my computer fast

Why is my computer fast - 02-1 02-1...

Info iconThis preview shows pages 1–8. Sign up to view the full content.

View Full Document Right Arrow Icon

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

View Full Document Right Arrow Icon

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

View Full Document Right Arrow Icon

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

View Full Document Right Arrow Icon

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

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: 02-1 02-1 ComponentsofCPUPerformanceandPerformanceEquation Whyismycomputerfast(orslow)? Wouldithelptoimprove ? CPUperformanceequation isonewaytostartansweringthesequestions. 02-1 EE4720LectureTransparency.Formatted9:07,19January2005fromlsli02. 02-1 02-2 02-2 CPUPerformanceDecomposedintoThreeComponents: • ClockFrequency ( φ ) Determinedbytechnologyandinfluencedbyorganization. • ClocksperInstruction (CPI) DeterminedbyISA,microarchitecture,compiler,andprogram. • InstructionCount (IC) Determinedbyprogram,compiler,andISA. Thesecombinedtoform CPUPerformanceEquation t T = 1 φ × CPI × IC , where t T denotestheexecutiontime. 02-2 EE4720LectureTransparency.Formatted9:07,19January2005fromlsli02. 02-2 02-3 02-3 CPUPerformance:SimpleSystem Executioninprogramorder ... ... oneatatime. Instr. 1 Instr. 2 Instr. 3 Time/cycles: Time/mms: 0 1 2 3 4 5 6 7 8 9 10 11 0 80 160 Instr. 500,000 1,999,996 39,999,920 IC=500 , 000; φ =50kHz; CPI=4. Executiontime:IC × CPI. × clockperiod. Here( andonlyhere) CPIisnumberofcyclesforeachinstruction. 02-3 EE4720LectureTransparency.Formatted9:07,19January2005fromlsli02. 02-3 02-4 02-4 Execution:Pipelined,InOrder ToRunFaster:OverlapInstructions (PipelinedExecution) Resultmustbesameasone-at-a-timeexecution ... ... nottoodifficulttoachieve. Instr. 1 Instr. 2 Instr. 3 Time/cycles: Time/mms: 0 1 2 3 4 5 6 7 8 9 10 11 0 20 40 Instr. 500,000 750,000 3,750,000 Instr. 4 Instr. 5 Instr. 6 Instr. 7 IC=500 , 000; φ =200kHz; CPI= 750000 500000 =1 . 5. Executiontimeatbest:IC × clockperiod ... ... assuming1cycletostarteachinstructionand ... ... instructioncanstarteachcycle.(Slowerinillustration.) 02-4 EE4720LectureTransparency.Formatted9:07,19January2005fromlsli02. 02-4 02-5 02-5 Execution:Pipelined,IdealOutofOrder ToRunEvenFaster:OverlapInstructionsandStartOutofOrder Sometimesskipaninstructionandexecuteitlater. Instr. 1 Instr. 2 Instr. 3 Time/cycles: Time/mms: 0 1 2 3 4 5 6 7 8 9 10 11 0 4 8 Instr. 500,000 500,000 500,000 Instr. 4 Instr. 5 Instr. 6 Instr. 7 Instr. 8 Instr. 9 IC=500 , 000; φ =200kHz; CPI=1. Executiontimeatbest:IC × clockperiod ... ... assuming1cycletostarteachinstruction ... ... instructioncanstarteachcycle. 02-5 EE4720LectureTransparency.Formatted9:07,19January2005fromlsli02. 02-5 02-6 02-6 Execution:Pipelined,IdealOutofOrder,Superscalar ToRunFastest 1 :Overlap,Out-of-Order,Start n perTick( n-WaySuperscalar ). Requiresabout n timesasmuchhardware.(Below, n =2.) Instr. 1 Instr. 2 Instr. 3 Time/cycles: Time/mms: 0 1 2 3 4 5 6 7 8 9 10 11 0 .008 .016 Instr. 500,000 250,000 500 Instr. 4 Instr. 5 Instr. 6 Instr. 7 Instr. 8 Instr. 9 Instr. 12 Instr. 14 Instr. 15 Instr. 13 Instr. 10 Instr. 16 Instr. 11 Instr. 17 Instr. 18 IC=500 , 000; φ =500MHz; CPI= 1 2 . Executiontimeatbest: 1 n × IC × clockperiod ... ... assuming1cycletostarteachinstructioninstructioncanstarteachcycle. 1 Usingaconventionalserialinstructionsetarchitecture. 02-6 EE4720LectureTransparency.Formatted9:07,19January2005fromlsli02. 02-6 02-7 02-7 Execution:Pipelined,OutofOrder,Superscalar...
View Full Document

{[ snackBarMessage ]}

Page1 / 30

Why is my computer fast - 02-1 02-1...

This preview shows document pages 1 - 8. Sign up to view the full document.

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