Parallel and Distributed Programming Using C++

Chapter 2. The Challenges of Parallel and Distributed Programming

	“The idea that you should really indicate the exact values of any physical quantity — temperature, density, potential field strength or whatever ... is a bold extrapolation.”
	--Erwin Shrodinger, Causality and Wave Mechanics

In this Chapter

• The Big Paradigm Shift

• Coordination Challenges

• Sometimes Hardware Fails and Software Quits

• Too Much Parallelization or Distribution Can Have Negative Consequences

• Selecting a Good Architecture Requires Research

• Different Techniques for Testing and Debugging are Required

• The Parallel or Distributed Design Must Be Communicated

• Summary

In the basic sequential model of programming, a computer program’s instructions are executed one at a time. The program ...