Efficient Batched Predecessor Search in Shared Memory on GPUs

Karsin, Ben; Casanova, Henri; Sitchinava, Nodari

doi:10.1109/hipc.2015.40

Cited by 5 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Over the past decade, a lot of research has focused on designing efficient algorithms to solve a range of classical problems on GPUs [9,12,17,27,36,37,39]. These works have introduced several optimization techniques, such as coalesced memory accesses [10,11,35], branch divergence elimination [19,23], and bank conflict avoidance [1,6,9,19]. Several empirical models for specific GPUs have been proposed that use micro-benchmarking [5,41], and several fast GPU algorithms have been produced [10,17,39] via the use of benchmarks [40] and application of hardware-specific optimization techniques to existing algorithms.…”

Section: Related Workmentioning

confidence: 99%

Analysis-driven Engineering of Comparison-based Sorting Algorithms on GPUs

Karsin

Weichert

Casanova

et al. 2018

Proceedings of the 2018 International Conference on Supercomputing

Self Cite

View full text Add to dashboard Cite

We study the relationship between memory accesses, bank conflicts, thread multiplicity (also known as over-subscription) and instruction-level parallelism in comparison-based sorting algorithms for Graphics Processing Units (GPUs). We experimentally validate a proposed formula that relates these parameters with asymptotic analysis of the number of memory accesses by an algorithm. Using this formula we analyze and compare several GPU sorting algorithms, identifying key performance bottlenecks in each one of them. Based on this analysis we propose a GPU-efficient multiway mergesort algorithm, GPU-MMS, which minimizes or eliminates these bottlenecks and balances various limiting factors for specific hardware.We realize an implementation of GPU-MMS and compare it to sorting algorithm implementations in state-of-the-art GPU libraries on three GPU architectures. Despite these library implementations being highly optimized, we find that GPU-MMS outperforms them by an average of 21% for random integer inputs and 14% for random key-value pairs.

show abstract

Section: Related Workmentioning

confidence: 99%

Analysis-driven Engineering of Comparison-based Sorting Algorithms on GPUs

Karsin

Weichert

Casanova

et al. 2018

Proceedings of the 2018 International Conference on Supercomputing

Self Cite

View full text Add to dashboard Cite

show abstract

“…Over the past decade, many works have focused on designing efficient algorithms to solve a range of classical problems on the GPU [8,26,37,19,36,39,12]. These works have introduced several optimization techniques, such as coalesced memory accesses [11,34,9], branch reduction [23,20], and bank conflict avoidance [20,6]. Several empirical models for specific GPUs have been proposed that use micro-benchmarking [41,17,5], and several fast GPU algorithms have been produced [9,19,39] via the use of empirical benchmarks [40] and the application of hardwarespecific optimization techniques to existing algorithms.…”

Section: Related Workmentioning

confidence: 99%

An Efficient Multiway Mergesort for GPU Architectures

Casanova,

Iacono,

Karsin

et al. 2017

Preprint

Self Cite

View full text Add to dashboard Cite

Sorting is a primitive operation that is a building block for countless algorithms. As such, it is important to design sorting algorithms that approach peak performance on a range of hardware architectures. Graphics Processing Units (GPUs) are particularly attractive architectures as they provides massive parallelism and computing power. However, the intricacies of their compute and memory hierarchies make designing GPU-efficient algorithms challenging. In this work we present GPU Multiway Mergesort (MMS), a new GPU-efficient multiway mergesort algorithm. MMS employs a new partitioning technique that exposes the parallelism needed by modern GPU architectures. To the best of our knowledge, MMS is the first sorting algorithm for the GPU that is asymptotically optimal in terms of global memory accesses and that is completely free of shared memory bank conflicts.We realize an initial implementation of MMS, evaluate its performance on three modern GPU architectures, and compare it to competitive implementations available in state-of-theart GPU libraries. Despite these implementations being highly optimized, MMS compares favorably, achieving performance improvements for most random inputs. Furthermore, unlike MMS, state-of-the-art algorithms are susceptible to bank conflicts. We find that for certain inputs that cause these algorithms to incur large numbers of bank conflicts, MMS can achieve up to a 37.6% speedup over its fastest competitor. Overall, even though its current implementation is not fully optimized, due to its efficient use of the memory hierarchy, MMS outperforms the fastest comparison-based sorting implementations available to date.

show abstract

Engineering Worst-Case Inputs for Pairwise Merge Sort on GPUs

Berney

Sitchinava

2020

2020 IEEE International Parallel and Distributed Processing Symposium (IPDPS)

View full text Add to dashboard Cite

Efficient Batched Predecessor Search in Shared Memory on GPUs

Cited by 5 publications

References 13 publications

Analysis-driven Engineering of Comparison-based Sorting Algorithms on GPUs

Analysis-driven Engineering of Comparison-based Sorting Algorithms on GPUs

An Efficient Multiway Mergesort for GPU Architectures

Engineering Worst-Case Inputs for Pairwise Merge Sort on GPUs

Contact Info

Product

Resources

About