Loop Dissevering: A Technique for Temporally Partitioning Loops in Dynamically Reconfigurable Computing Platforms
نویسنده
چکیده
This paper presents a technique, called loop dissevering, to temporally partitioning any type of loop presented in programming languages. The technique can be used in the presence of complex loops that oversize the physically available hardware resources. Unlike loop fission or distribution, the technique can be applied to all types of loops and it is not constrained by loop dependences. Thus, the technique guarantees the compilation of complex loops that otherwise cannot be mapped to the target reconfigurable computing architecture. Moreover, the technique only needs to communicate scalar variables between temporal partitions (configurations) and does not need auxiliary array variables used for scalar expansion when applying loop distribution. We show results of applying the technique when compiling C programs to the PACT eXtreme Processing Platform (XPP) and to a hypothetical version with faster switching between contexts. We show that the technique leads to implementations using fewer resources and might lead to performance improvements when it is possible to overlap some of the execution stages (e.g., fetch, configure, and compute). As performance is concerned, the technique is as most efficient as fast is the reconfiguration time.
منابع مشابه
Parallelization in Co-Compilation for Configurable Accelerators - A Host / Accelerator Partitioning Compilation Method
Fig. 1: Makimoto’s wave: summarizing the history of paradigm shifts in semiconductor markets. the future? Abstract— The paper introduces a novel co-compiler and its “vertical” parallelization method, including a general model for co-operating host/accelerator platforms and a new parallelizing compilation technique derived from it. Small examples are used for illustration. It explains the exploi...
متن کاملInternationales Begegnungs-und Forschungszentrum Für Informatik
s of Talks JÜRGEN BECKER The Impact of Reconfigurable Hardware Platforms on the Overhead of Parallelism NEIL W. BERGMANN Identifying Characteristics of Algorithms Which Make Them Suitable for Reconfigurable Computing Implementations GORDON BREBNER Dynamically Reconfigurable FPGAs GORDON BREBNER Soft Circuitry KARL-HEINZ BRENNER Technologies for Realizing Dynamically Reconfigurable Optical Inter...
متن کاملImplementation of VlSI Based Image Compression Approach on Reconfigurable Computing System - A Survey
Image data require huge amounts of disk space and large bandwidths for transmission. Hence, imagecompression is necessary to reduce the amount of data required to represent a digital image. Thereforean efficient technique for image compression is highly pushed to demand. Although, lots of compressiontechniques are available, but the technique which is faster, memory efficient and simple, surely...
متن کاملSelf-loop Pipelining and Reconfigurable Dataflow Arrays
This paper presents some interesting concepts of static dataflow machines that can be used by reconfigurable computing architectures. We introduce some data-driven reconfigurable arrays and summarize techniques to map imperative software programs to those architectures, some of them being focus of current research work. In particular, we briefly present a novel technique for pipelining loops. E...
متن کاملAn Optimized Three Region Partitioning Technique to Maximize Parallelism of Nested Loops With Non-uniform Dependences
There are many methods for nested loop partitioning exist; however, most of them perform poorly when they partition loops with non-uniform dependences. This paper proposes a generalized and optimized loop partitioning mechanism which can exploit parallelism in nested loops with non-uniform dependences. Our approach based on the region partitioning technique divides the loop into variable size p...
متن کامل