Data races, critical sections, processor loading, Operating System

Research the phenomenon of data races. Give an example of how an unprotected data race can give rise to data inconsistency. How do OpenMP and Cilk resolve this problem?

Data race is that situation or condition in which multiple threads, without intervening synchronization, try to access the same memory location, with at least one thread performing a write operation. For eg. many data races occur on numerical algorithms owing to chaotic relaxation and asynchronous iterative methods. Also, there are systems where synchronized threads or processes maintain probabilities with best-estimate-matrix and may race with one other to provide updates.This is usually described in higher-level language specs by the phrase: "undefined behavior." A data race could legitimately reprogram the BIOS delete data from the disk and may also stop the processor's fan leading to a multi-core meltdown. 

example code:

 

int checker = 0;

int counts = 0;

Lock lock;

 

bool TryEnter() {

    if (checker == /* get thread id */) {

        counts += 1;

        return true;

    }

 

    if (lock.TryEnter()) {

        checker = /* get thread id */;

        return true;

    }

    return false;

}

 

void Exit() {

    if (counts != 0) {

        counts -= 1;

        return;

    }

    checker = 0;

    lock.Exit();

}

 

the compiler or the processor may “optimize” this program as:

 

void Exit() {

    if (counts != 0) {

        counts -= 1;

        return;

    }

    checker = 42;

    checker = 0;

    lock.Exit();

} 

The effect of this is perhaps not observable in the current thread, nor is it observable by other threads in the absence of data races. Here, the unfortunate thread whose ID is 42 might observe this value and take the ignite the mistake. 

OpenMP and Cilk resolve data racing through a technique known as Data parallelism.It focuses on distributing the data across different parallel computing nodes. This is achieved when each processor performs the same task on different pieces of distributed data. In some situations, a single execution thread controls operations on all pieces of data. In others, individual threads control the operation, but they execute the same code.

Posted Date: 6/29/2012 2:09:57 AM | Location : United States







Related Discussions:- Data races, critical sections, processor loading, Assignment Help, Ask Question on Data races, critical sections, processor loading, Get Answer, Expert's Help, Data races, critical sections, processor loading Discussions

Write discussion on Data races, critical sections, processor loading
Your posts are moderated
Related Questions
Q. Explain application of consumer behaviour? Consumer behaviour is described as the dynamic interaction of affect and cognition and behaviour and the environment by human bein


idle thread The special thread a dispatcher will run when no ready thread is found. The primary purpose of the idle process and its threads is to remove what would otherwise b

The term thread-safe in computer programming describes that routine or portion of the program that may be called from multiple programming threads without uncalled for interactions

Write a short note on disk structure Modern disk drives are initiate as large one dimensional array of logical blocks where the logical block is the smallest unit of transfer.

Q. Presume that we agree that 1 kilobyte is 1,024 bytes 1 megabyte is 1,0242 bytes and 1 gigabyte is 1,0243 bytes. This progression carries on through terabytes, petabytes, and ex


Explain Processing Predefined Application Protocols Implementing and swift processing of predefined application protocols is sure to improve performance of server - side applic

Define UFD and MFD. In the two-level directory structure, every user has her own user file directory (UFD). Every UFD has a similar structure, but lists only the files of a one

What does it mean for something to be thread-safe? By saying that X is thread-safe, we mean that if multiple threads use X at the same time, we don't have to worry about concurrenc