Coalesced Redundant Block Synchronization on GPGPU
Main Article Content
Abstract
Speculative parallelization is a mainstream technology used to increase the instruction level parallelism and the thread level speculation. Since the computations are executed faster on GPU’s, the application programs can be still executed faster in combination and increase the performance. The execution order is rearranged to increase the performance enhancements through the load/store pair dependencies determined in a different categories to increase the instruction level parallelism. In this paper it is proved that how speculation reduces the memory latencies and increase in instruction execution through the proof with merge sort program using the cuda-memcheck and CUDA-GDB. The profiler GPROF is used for sequential program and the parallel program uses CUDA which uses the mechanism of synchronization through coalesced redundant blocks on GPU.
Keywords-: synchronization, GPGPU, instruction level parallelism, thread level parallelism, performance, redundant blocks, coalescing.
Downloads
Article Details
COPYRIGHT
Submission of a manuscript implies: that the work described has not been published before, that it is not under consideration for publication elsewhere; that if and when the manuscript is accepted for publication, the authors agree to automatic transfer of the copyright to the publisher.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
- The journal allows the author(s) to retain publishing rights without restrictions.
- The journal allows the author(s) to hold the copyright without restrictions.