Automatic parallelization
From Wikipedia, the free encyclopedia
Automatic parallelization, also auto parallelization, autoparallelization, parallelization, or //ization (shorthand), the last two of which imply automation when used in context, refers to the use of a modern optimizing parallelizing compiler to convert sequential code into multi-threaded or vectorized (or even both) code in order to utilize multiple processors simultaneously in a shared-memory multiprocessor (SMP) machine. The goal of automatic parallelization is to relieve programers from the tedious and error-prone manual parallelization process. Though the quality of automatic parallelization has improved in the past several decades, fully automatic parallelization of sequential programs by compilers remains a grand challenge due to its need for complex program analysis and the unknown factors (such as input data range) during compilation.
The programming control structures on which autoparallelization places the most focus are loops, because, in general, most of the execution time of a program takes place inside some form of loop. A parallelizing compiler tries to split up a loop so that its iterations can be executed on separate processors concurrently.
Contents |
[edit] Compiler parallelization analysis
The compiler usually conducts two passes of analysis before actual parallelization in order to determine the following:
- Is it safe to parallelize the loop? Answering this question needs accurate dependence analysis and alias analysis
- Is it worthwhile to parallelize it? This answer requires a reliable estimation of the program workload and the capacity of the parallel system.
The first pass of the compiler performs a data dependence analysis of the loop to determine whether each iteration of the loop can be executed independently of the others. Data dependence can sometimes be dealt with, but it may incur additional overhead in the form of message passing, synchronization of shared memory, or some other method of processor communication.
The second pass attempts to justify the parallelization effort by comparing the theoretical execution time of the code after parallelization to the code's sequential execution time. Somewhat counterintuitively, code does not always benefit from parallel execution. The extra overhead that can be associated with using multiple processors can eat into the potential speedup of parallelized code.
[edit] Example
The Fortran code below can be auto-parallelized by a compiler because each iteration is independent of the others, and the final result of array z will be correct regardless of the execution order of the other iterations.
do i=1 to n
z[i] = x[i] + y[i]
enddo
On the other hand, the following code cannot be auto-parallelized, because the value of z[i] depends on the result of the previous iteration, z[i-1].
do i=1 to n
z[i] = z[i-1]*2
enddo
This does not mean that the code cannot be parallelized. However, current parallelizing compilers are not usually capable of bringing out these parallelisms automatically, and it is questionable whether this code would benefit from parallelization in the first place.
[edit] Workaround
Due to the inherent difficulties in full automatic parallelization, several easier approaches exist to get a parallel program in higher quality. They are:
- Allow programmers to add "hints" to their programs to guide compiler parallelization, such as HPF for distributed memory systems and OpenMP for shared memory systems.
- Build an interactive system between programmers and parallelizing tools/compilers. Notable examples are SUIF Explorer, the Polaris compiler, and ParaWise (formally CAPTools).
- Hardware-supported speculative multithreading.
[edit] Historical parallelizing compilers
Most research compilers for automatic parallelization consider Fortran programs, because Fortran makes stronger guarantees about aliasing than languages such as C. Typical examples are:
- Vienna Fortran compiler
- Paradigm compiler
- Polaris compiler
- SUIF compiler
