Automatically exploiting cross-invocation parallelism using runtime information

Automatic parallelization is a promising approach to producing scalable multi-threaded programs for multicore architectures. Many existing automatic techniques only parallelize iterations within a loop invocation and synchronize threads at the end of each loop invocation. When parallel code contains...

Full description

Saved in:
Bibliographic Details
Main Authors: August, David I., Huang, Jialu, Beard, Stephen R., Johnson, Nick P., Jablin, Thomas B.
Format: Conference Proceeding
Language:English
Subjects:
Arrays
Engines
Instruction sets
Parallel processing
Runtime
Schedules
Software and its engineering > Software notations and tools > Compilers
Software and its engineering > Software notations and tools > General programming languages > Language features
Synchronization
Theory of computation > Models of computation > Concurrency
Theory of computation > Models of computation > Concurrency > Parallel computing models
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Automatic parallelization is a promising approach to producing scalable multi-threaded programs for multicore architectures. Many existing automatic techniques only parallelize iterations within a loop invocation and synchronize threads at the end of each loop invocation. When parallel code contains many loop invocations, synchronization can easily become a performance bottleneck. Some automatic techniques address this problem by exploiting cross-invocation parallelism. These techniques use static analysis to partition iterations among threads to avoid crossthread dependences. However, this partitioning is not always achievable at compile-time, because program input determines dependence patterns at run-time. By contrast, this paper proposes DOMORE, the first automatic parallelization technique that uses runtime information to exploit additional cross-invocation parallelism. Instead of partitioning iterations statically, DOMORE dynamically detects crossthread dependences and synchronizes only when necessary. DOMORE consists of a compiler and a runtime library. At compile time, DOMORE automatically parallelizes loops and inserts a custom runtime engine into programs. At run-time, the engine observes dependences and synchronizes iterations only when necessary. For six programs, DOMORE achieves a geomean loop speedup of 2.1x over parallel execution without cross-invocation parallelization and of 3.2 x over sequential execution on eight cores.
DOI:10.1109/CGO.2013.6495001