Dynamic Parallel Media Processing using Speculative Broadcast Loop ( SBL ) ( Extended
نویسندگان
چکیده
This paper presents the results of a study of dynamic parallel media processing using Speculative Broadcast Loop (SBL), a speculative run-time loop-level parallelization method. Due to processing regularity, multimedia applications typically contain extensive parallelism. Data parallelism between independent loop iterations may be supported by subword parallelism methods, but much of the data parallelism is of a larger granularity that may not be effectively supported with subword parallelism. Larger-scale parallel processing methods are needed to support the full range of data parallelism in multimedia. Because static parallel compilation methods are often unable to recognize all parallelism at compile time, a run-time method is assumed for the speculative execution of parallel loop iterations. The SBL run-time method combines SIMD parallelism with large-scale speculative execution for supporting data parallelism in multimedia.
منابع مشابه
The Potential of Synergistic Static, Dynamic and Speculative Loop Nest Optimizations for Automatic Parallelization
Research in automatic parallelization of loop-centric programs started with static analysis, then broadened its arsenal to include dynamic inspection-execution and speculative execution, the best results involving hybrid static-dynamic schemes. Beyond the detection of parallelism in a sequential program, scalable parallelization on many-core processors involves hard and interesting parallelism ...
متن کاملTolerating First Level Memory Access Latency in High-Performance Systems
In order to improve performance, future parallel systems will continue to increase the processing power of each node in a system. As node processors, though, can execute more instructions concurrently, they become more sensitive to the rst level memory access latency. This paper presents a set of hardware and software techniques, collectively referred to as register preloading, to effectively t...
متن کاملTOLERATING FIRST LEVEL MEMORY ACCESS LATENCYIN HIGH - PERFORMANCE SYSTEMSWilliam
In order to improve performance, future parallel systems will continue to increase the processing power of each node in a system. As node processors, though, can execute more instructions concurrently, they become more sensitive to the rst level memory access latency. This paper presents a set of hardware and software techniques , collectively referred to as register preloading, to effectively ...
متن کاملSafe Parallel Programming in an Interpreted Language
Parallel programming is increasingly important with the advent of multicore processors. However, modern software is difficult to parallelize because of the high degree of modularization. It is unclear whether a piece of code is parallel if it calls other functions. Dynamic languages such as Ruby, Python, and Matlab represent modularization to the extreme. A program, also known as a script, requ...
متن کاملSpeculative Program Parallelization with Scalable and Decentralized Runtime Verification
Thread Level Speculation (TLS) is a dynamic code parallelization technique proposed to keep the software in pace with the advances in hardware, in particular, to automatically parallelize programs to take advantage of the multicore processors. Being speculative, frameworks of this type unavoidably rely on verification systems that are similar to software transactional memory, and that require v...
متن کامل