Presentation is loading. Please wait.

Presentation is loading. Please wait.

1 Pipelining(2) CDA 3101 Discussion Section 09. 2 Question 1 Identify all of the data dependencies and necessary forwarding in the following code. No.

Published byJulio Youngman Modified over 9 years ago

Similar presentations

Presentation on theme: "1 Pipelining(2) CDA 3101 Discussion Section 09. 2 Question 1 Identify all of the data dependencies and necessary forwarding in the following code. No."— Presentation transcript:

1 1 Pipelining(2) CDA 3101 Discussion Section 09

2 2 Question 1 Identify all of the data dependencies and necessary forwarding in the following code. No branch prediction, No Delayed Slot. addi $t1,$0,0 addi $t2,$0,100 LOOP:lw $t4, 200($t2) add $t1, $t1, $t4 addi $t2, $t2, -4 bne $t2, $0,LOOP

3 3 Question 1 InstructionCC1CC2CC3CC4CC5CC6CC7CC8CC9CC 10 addi $t1,$0,0 IFIDEXMEMWB addi $t2,$0,100 IFIDEXMEMWB lw $t4, 200($t2) IFIDEXMEMWB add $t1, $t1, $t4 IFIDEXMEMWB addi $t2, $t2, -4 IFIDEXMEMWB bne $t2, $0,LOOP IFID

4 4 Question 1(cont) InstructionCC8CC9CC 10 CC 11 CC 12 CC 13 CC 14 CC 15 CC 16 CC 17 bne $t2, $0,LOOP IFID lw $t4, 200($t2) IFIDEXMEMWB add $t1, $t1, $t4 IFIDEXMEMWB addi $t2, $t2, -4 IFIDEXMEMWB bne $t2, $0,LOOP IFID

5 5 Question 1(cont) InstructionCC 15 CC 16 CC 17 CC 18 CC 19 CC 20 CC 21 CC 22 CC 23 CC 24 bne $t2, $0,LOOP IFID lw $t4, 200($t2) IFIDEXMEMWB add $t1, $t1, $t4 IFIDEXMEMWB addi $t2, $t2, -4 IFIDEXMEMWB bne $t2, $0,LOOP IFID

6 6 Question 2 Rewrite the following code with delay slot: addi $t1,$0,0 addi $t2,$0,100 LOOP:lw $t4, 200($t2) add $t1, $t1, $t4 addi $t2, $t2, -4 bne $t2, $0,LOOP

7 7 Question 2 Rewrite the following code with delay slot: addi $t1,$0,0 addi $t2,$0,100 LOOP:lw $t4, 200($t2) addi $t2, $t2, -4 bne $t2, $0,LOOP Delay Slot: add $t1, $t1, $t4

8 8 Question 2 InstructionCC 1 CC 2 CC 3 CC 4 CC 5 CC 6 CC 7 CC 8 CC 9 CC 10 CC 11 CC 12 addi $t1,$0,0 IFIDEXME M WB addi $t2,$0,10 0 IFIDEXME M WB lw $t4, 200($t2) IFIDEXME M WB addi $t2, $t2, -4 IFIDEXME M WB bne $t2, $0,LOOP IFID add $t1, $t1, $t4 IFIDEXME M WB lw $t4, 200($t2) IFIDEXME M WB

9 Question 3 Assume we have 10 branch outcomes as{T T T NT T T T NT NT T}, simulate the sequence on: 1-Bit predictor: (assume the original state is predict_bit =0) 2-Bit predictor: (assume the original state is predict_bit =01(weakly not taken) 9

10 1-Bit predictor 10 OutcomePredict bit(before ) PredictionPrediction bit (after) T0NTWrong1 T1TRight1 T1T 1 NT1TWrong0 T0NTWrong1 T1TRight1 T1T 1 NT1TWrong0 NT0 Right0 T0NTWrong1

11 2-Bit predictor 11 OutcomePredict bit(before ) PredictionPrediction bit (after) T01NTWrong11 T TRight11 T TRight11 NT11TWrong10 T TRight11 T TRight11 T TRight11 NT11TWrong10 NT10TWrong00 T NTWrong01

Download ppt "1 Pipelining(2) CDA 3101 Discussion Section 09. 2 Question 1 Identify all of the data dependencies and necessary forwarding in the following code. No."

Similar presentations

Lecture 4: CPU Performance

Lecture 4: CPU Performance
Morgan Kaufmann Publishers The Processor

Morgan Kaufmann Publishers The Processor
1 ECE369 ECE369 Pipelining. 2 ECE369 addm (rs), rt # Memory[R[rs]] = R[rt] + Memory[R[rs]]; Assume that we can read and write the memory in the same cycle.

1 ECE369 ECE369 Pipelining. 2 ECE369 addm (rs), rt # Memory[R[rs]] = R[rt] + Memory[R[rs]]; Assume that we can read and write the memory in the same cycle.
Pipeline Summary Try to put everything together for pipelines Before going onto caches. Peer Instruction Lecture Materials for Computer Architecture by.

Pipeline Summary Try to put everything together for pipelines Before going onto caches. Peer Instruction Lecture Materials for Computer Architecture by.
CMSC 611: Advanced Computer Architecture Pipelining Some material adapted from Mohamed Younis, UMBC CMSC 611 Spr 2003 course slides Some material adapted.

CMSC 611: Advanced Computer Architecture Pipelining Some material adapted from Mohamed Younis, UMBC CMSC 611 Spr 2003 course slides Some material adapted.
Lec. 27-1 ECE 463/521, Profs. Conte, Rotenberg and Gehringer, Dept. of ECE, NC State University Static Scheduling Techniques m Local scheduling (within.

Lec ECE 463/521, Profs. Conte, Rotenberg and Gehringer, Dept. of ECE, NC State University Static Scheduling Techniques m Local scheduling (within.
Pipelining and Control Hazards Oct

Pipelining and Control Hazards Oct
Pipeline Optimization

Pipeline Optimization
Pipeline Computer Organization II 1 Hazards Situations that prevent starting the next instruction in the next cycle Structural hazards – A required resource.

Pipeline Computer Organization II 1 Hazards Situations that prevent starting the next instruction in the next cycle Structural hazards – A required resource.
Pipelining 6.1, 6.2. Performance Measurements Cycle Time: Time __________________ Latency: Time to finish a _____________, start to finish Throughput:

Pipelining 6.1, 6.2. Performance Measurements Cycle Time: Time __________________ Latency: Time to finish a _____________, start to finish Throughput:
Pipeline Control Hazards and Instruction Variations Hakim Weatherspoon CS 3410, Spring 2011 Computer Science Cornell University See P&H Appendix 4.8 &

Pipeline Control Hazards and Instruction Variations Hakim Weatherspoon CS 3410, Spring 2011 Computer Science Cornell University See P&H Appendix 4.8 &
CIS429/529 Winter 2007 Pipelining II- 1 Additional pipelining topics Why pipelining is so hard: exception handling ILP techniques: loop unrolling.

CIS429/529 Winter 2007 Pipelining II- 1 Additional pipelining topics Why pipelining is so hard: exception handling ILP techniques: loop unrolling.
Prof. John Nestor ECE Department Lafayette College Easton, Pennsylvania 18042 ECE 313 - Computer Organization Lecture 19 - Pipelined.

Prof. John Nestor ECE Department Lafayette College Easton, Pennsylvania ECE Computer Organization Lecture 19 - Pipelined.
ENEE350 Ankur Srivastava University of Maryland, College Park Based on Slides from Mary Jane Irwin ( www.cse.psu.edu/~mji )www.cse.psu.edu/~mji www.cse.psu.edu/~cg431.

ENEE350 Ankur Srivastava University of Maryland, College Park Based on Slides from Mary Jane Irwin ( )
1 Chapter Six - 2nd Half Pipelined Processor Forwarding, Hazards, Branching EE3055 Web: www.csc.gatech.edu/copeland/3055.

1 Chapter Six - 2nd Half Pipelined Processor Forwarding, Hazards, Branching EE3055 Web:
1 Stalling  The easiest solution is to stall the pipeline  We could delay the AND instruction by introducing a one-cycle delay into the pipeline, sometimes.

1 Stalling  The easiest solution is to stall the pipeline  We could delay the AND instruction by introducing a one-cycle delay into the pipeline, sometimes.
Goal: Reduce the Penalty of Control Hazards

Goal: Reduce the Penalty of Control Hazards
Prof. John Nestor ECE Department Lafayette College Easton, Pennsylvania 18042 Computer Organization Pipelined Processor Design 3.

Prof. John Nestor ECE Department Lafayette College Easton, Pennsylvania Computer Organization Pipelined Processor Design 3.
 The actual result $1 - $3 is computed in clock cycle 3, before it’s needed in cycles 4 and 5  We forward that value to later instructions, to prevent.

 The actual result $1 - $3 is computed in clock cycle 3, before it’s needed in cycles 4 and 5  We forward that value to later instructions, to prevent.
King Fahd University of Petroleum and Minerals King Fahd University of Petroleum and Minerals Computer Engineering Department Computer Engineering Department.

King Fahd University of Petroleum and Minerals King Fahd University of Petroleum and Minerals Computer Engineering Department Computer Engineering Department.

Similar presentations

Ads by Google