hrcak mascot   Srce   HID

Izvorni znanstveni članak
https://doi.org/10.31803/tg-20191104183930

Multiplication of medium-density matrices using TensorFlow on multicore CPUs

Siraphob Theeracheep   ORCID icon orcid.org/0000-0001-9859-1053 ; Department of Mathematics and Computer Science, Faculty of Science, Chulalongkorn University, Bangkok 10330, Thailand
Jaruloj Chongstitvatana ; Department of Mathematics and Computer Science, Faculty of Science, Chulalongkorn University, Bangkok 10330, Thailand

Puni tekst: engleski, pdf (944 KB) str. 286-290 preuzimanja: 319* citiraj
APA 6th Edition
Theeracheep, S. i Chongstitvatana, J. (2019). Multiplication of medium-density matrices using TensorFlow on multicore CPUs. Tehnički glasnik, 13 (4), 286-290. https://doi.org/10.31803/tg-20191104183930
MLA 8th Edition
Theeracheep, Siraphob i Jaruloj Chongstitvatana. "Multiplication of medium-density matrices using TensorFlow on multicore CPUs." Tehnički glasnik, vol. 13, br. 4, 2019, str. 286-290. https://doi.org/10.31803/tg-20191104183930. Citirano 24.06.2021.
Chicago 17th Edition
Theeracheep, Siraphob i Jaruloj Chongstitvatana. "Multiplication of medium-density matrices using TensorFlow on multicore CPUs." Tehnički glasnik 13, br. 4 (2019): 286-290. https://doi.org/10.31803/tg-20191104183930
Harvard
Theeracheep, S., i Chongstitvatana, J. (2019). 'Multiplication of medium-density matrices using TensorFlow on multicore CPUs', Tehnički glasnik, 13(4), str. 286-290. https://doi.org/10.31803/tg-20191104183930
Vancouver
Theeracheep S, Chongstitvatana J. Multiplication of medium-density matrices using TensorFlow on multicore CPUs. Tehnički glasnik [Internet]. 2019 [pristupljeno 24.06.2021.];13(4):286-290. https://doi.org/10.31803/tg-20191104183930
IEEE
S. Theeracheep i J. Chongstitvatana, "Multiplication of medium-density matrices using TensorFlow on multicore CPUs", Tehnički glasnik, vol.13, br. 4, str. 286-290, 2019. [Online]. https://doi.org/10.31803/tg-20191104183930

Sažetak
Matrix multiplication is an essential part of many applications, such as linear algebra, image processing and machine learning. One platform used in such applications is TensorFlow, which is a machine learning library whose structure is based on dataflow programming paradigm. In this work, a method for multiplication of medium-density matrices on multicore CPUs using TensorFlow platform is proposed. This method, called tbt_matmul, utilizes TensorFlow built-in methods tf.matmul and tf.sparse_matmul. By partitioning each input matrix into four smaller sub-matrices, called tiles, and applying an appropriate multiplication method to each pair depending on their density, the proposed method outperforms the built-in methods for matrices of medium density and matrices of significantly uneven distribution of non-zeros.

Ključne riječi
Sparse matrix; Matrix multiplication; TensorFlow

Hrčak ID: 229496

URI
https://hrcak.srce.hr/229496

Posjeta: 556 *