PIPELINE INTERRUPTS
Download as PPTX, PDF2 likes4,049 views
This document provides an overview of pipelining and interrupts in processors. It discusses how pipelining improves processor throughput by overlapping the execution of multiple instructions. An interrupt is described as a signal that causes the processor to suspend its current task and execute an interrupt handler to deal with the event. The document then explains pipelining concepts using an example of an assembly line for laundering clothes. It shows how pipelining reduces the time to complete multiple loads from 6 hours to 3.5 hours. Finally, it briefly discusses fault tolerance in systems using redundancy and different approaches like static and dynamic redundancy.
PIPELINE INTERRUPTS
- 1. MOOKAMBIGAI COLLEGE OF ENGINEERING M.R.KARTHIK III rd Year Department of Electronics & Communication Engineering
- 2. OVERVIEW OF PIPELINING Pipelining is widely used in modern processors. Pipelining improves system performance in terms of throughput. Pipelined organization requires sophisticated compilation techniques.
- 3. What is interrupt ? An interrupt is a signal to the processor emitted by hardware or software indicating an event that needs immediate attention. An interrupt alerts the processor to a high-priority condition requiring the interruption of the current code the processor is executing . The processor responds by suspending its current activities, saving its state, and executing a function called interrupt handler (or interrupt service routine, ISR) to deal with the event. This interruption is temporary, and after the interrupt handler finishes, the processor resumes execution of the previous thread.
- 5. Pipeline Concept Laundry Example ann, Brian, Cathy, Dave each have one load of clothes to wash, dry, and fold Washer takes 30 minutes Dryer takes 40 minutes “Folder” takes 20 minutes A B C D
- 6. Sequential method 6 PM 7 8 9 10 11 Midnight A B C D Time 30 40 20 30 40 20 30 40 20 30 40 20 Sequential laundry takes 6 hours for 4 loads If they learned pipelining, how long would laundry take?
- 7. Pipeline Concept Pipelined laundry takes 3.5 hours for 4 loads Pipelining doesn’t help latency of single task, it helps throughput of entire workload Unbalanced lengths of pipe stages reduces speedup A B C D 6 PM 7 8 9 T a s k O r d e r Time 30 40 40 40 40 20
- 8. Use the Idea of Pipelining in a Computer F 1 E 1 F 2 E 2 F 3 E 3 I1 I2 I3 (a) Sequential execution Instruction fetch unit Execution unit Interstage buffer B1 (b) Hardware organization Time Clock cycle 1 2 3 4 F1 E1 F2 E2 F3 E3 Instruction I1 I2 I3 (c) Pipelined execution Time Figure 8.1. Basic idea of instruction pipelining. Fetch + Execution
- 9. Shows maximum throughput . Where the first add instruction (Add1) is completed before the multiply instruction. Suppose that add instruction generate an interrupt the cpu in execution (EX) stage corresponding to cycle 4. CPU suspends its current activity , then cntrl is transferred to interrupt handler. It is possible to generate another interrupt by mul instruction ,say cycle . Once again CPU changes its state . Alternative solution is to introduce a small register set known as history buffer (HB ) It stores initial state temporarily
- 10. Fault Tolerance It is defined as the ability of a system to execute specified algorithm correctly regardless of hardware failures and program errors.
- 11. Redundancy When a one unit fails , its duties must be taken over by other unit of the system. These units are used to improve the system and to avoid computation error. They are termed as redundancy Redundancy can be introduce in several ways, they are Hardware Redundancy : Having multiple hardware units Software Redundancy : Multiple version of programs for critical operation Information Redundancy: error detecting code Time Redundancy : Retrying critical operations .
- 12. Fault- Tolerant System Design There are two basic approch in designing fault tolerant system, they are 1) Static redundancy 2) Dynamic redundancy
- 13. Static redundancy Static redundancy means use of redundant hardware or software components, which forms a permanent part of the system . To understand static redundancy consider triple modular redundancy ( TMR)
- 14. Dynamic redundancy The fault can be tolerated by reorganizing the system so that the function of fault unit are transferred to fault free unit . The re-organization can achieved in 3 steps Fault diagnoses Fault elimination Recovery