Embedded Processor Oriented Compiler Infrastructure

Djukic, Miodrag; Popović, Miroslav; Cetic, Nenad; Povazan, Ivan

doi:10.4316/aece.2014.03016

Cited by 2 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To estimate DMA speed we used measuring tool that we previously developed [12]. Tool is based on a C Compiler infrastructure that we also developed for this target platform [13]. Measuring tool is disassembling executable application for target platform and converts it to intermediate representation (IR).…”

Section: Library Performancementioning

confidence: 99%

See 1 more Smart Citation

A Run-Time Library for Parallel Processing on a Multi-core DSP

Cetic

Popović

Djukic

et al. 2013

2013 3rd Eastern European Regional Conference on the Engineering of Computer Based Systems

View full text Add to dashboard Cite

Future of the computer based systems resides in the multi-core and many-core architectures. Thanks to availability of different multi-core processors, many parallelization tools and techniques emerged. However, majority of them rely on the shared memory architecture model, where data to multiple core processors is simply accessible. In this paper we present a simple hardware abstraction that targets features of a multicore DSP processor with distributed memory architecture, aiming support for program parallelization. Both manual and automatic code parallelization approaches can use library routines described in this paper. By validating performance of multiple manually created test cases we demonstrate capabilities of presented approach. Performance is estimated by measuring time necessary for DMA data transfer between the cores using GPIO pins attached to the DSP. In addition, earlier developed C code parallelization technique for the same DSP is extended to use this library providing full working solution verified on real hardware.

show abstract

Section: Library Performancementioning

confidence: 99%

“…Static analysis is providing less accurate data but runs faster. We are performing whole program simulation with the profiling using compiler simulator that we previously developed [13]. Profiling is giving total number of cycles spent in each function.…”

Section: B Load Ballancingmentioning

confidence: 99%