Efficient representation of higher-dimensional arrays by dimension transformations

Hasan, K. M. Azharul; Shaikh, Abu Hanif

doi:10.1007/s11227-016-1954-x

Cited by 10 publications

(1 citation statement)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the dimension transformation, the target data are colocated which helps to design less complicated algorithms for efficient retrieval. The superiority of transformation is well studied in the loop transformation technique for compiler optimization 9 and higher dimensional matrix operations 10 . The array cells are rearranged by changing the loop nests to make them closer to the cache memory in the loop transformation.…”

Section: Introductionmentioning

confidence: 99%

Multidimensional query processing algorithm by dimension transformation

Rimi

Hasan

Tsuji

2023

Sci Rep

View full text Add to dashboard Cite

Multidimensional query processing is an important access pattern for multidimensional scientific data. We propose an in-memory multidimensional query processing algorithm for dense data using a higher-dimensional array. We developed a new array system namely a Converted two-dimensional Array (C2A) of a multidimensional array of dimension n ($$n > 2$$ n > 2 ) where the n dimensions are transformed into 2 dimensions. Using the C2A, we design and analyze less complex algorithms that show improve performance for data locality and cache miss rate. Therefore, improved performance for data retrieval is achieved. We demonstrate algorithms for single key and range key queries for both Traditional Multidimensional Array(TMA) and C2A. We also compare the performance of both schemes. The cost of index computation gets high when the number of dimensions increases in a TMA but the proposed C2A based algorithm shows less computation cost. The cache miss rate is also lower for in C2A based algorithm than TMA based algorithm. Theoretical and experimental results show that the performance of C2A based algorithm outperforms the TMA-based algorithms.

show abstract

Section: Introductionmentioning

confidence: 99%

Multidimensional query processing algorithm by dimension transformation

Rimi

Hasan

Tsuji

2023

Sci Rep

View full text Add to dashboard Cite

show abstract

Efficient Query Processing for Multidimensional Data Cubes

Rimi

Hasan

2020

Cyber Security and Computer Science

View full text Add to dashboard Cite

Parallel Computation of Hadamard Product for Dynamic Dataset on Google Colab

Shariar

Hasan

2021

ICT With Intelligent Applications

View full text Add to dashboard Cite

Hadamard product, the element-wise product of tensors, is an important tool for many real-life applications such as machine LSTM, multimodal learning, object recognition, and segmentation. In this paper, we propose a faster processing of hadamard product by the parallel computation on graphics processing unit (GPU) for dynamic data. Most of the computations for real-life data are multidimensional and dynamic which expand during run time. In this scheme, we use dynamic memory allocation that allows further expansion of the dimension size and high memory utilization based on the notion of extendable array. Since high dimensionality is difficult to handle, we use a dimension conversion technique where the n-dimensional array structure is transformed into a 2-dimensional structure. Furthermore, to handle the future data, we apply the converted extendable array structure to get Scalable Hadamard Product (SHDP) for dynamic dataset. Then, we implement a parallel algorithm for the parallel processing of the SHDP that partitions and distributes the element-wise product during runtime. We utilize the maximum available GPU threads for the faster performance of the hadamard product. We found good speed-up for the proposed partitioning while applying to "Google Colab".

show abstract

Efficient representation of higher-dimensional arrays by dimension transformations

Cited by 10 publications

References 32 publications

Multidimensional query processing algorithm by dimension transformation

Multidimensional query processing algorithm by dimension transformation

Efficient Query Processing for Multidimensional Data Cubes

Parallel Computation of Hadamard Product for Dynamic Dataset on Google Colab

Contact Info

Product

Resources

About